00:00:33 -!- copumpkin has joined.
00:01:28 -!- shikhin has quit (Ping timeout: 255 seconds).
00:09:52 -!- Lymia has quit (Ping timeout: 244 seconds).
00:19:29 <Sgeo> Do Apple laptops ever break down the way this laptop is breaking down?
00:19:45 <Sgeo> Whenever I move the screen, there's a chance of a bunch of stuff getting tinted blue
00:19:51 <Sgeo> Is this something I can fix?
00:20:37 <Sgeo> It seems to be particular colors
00:31:13 -!- not^v has joined.
00:33:07 -!- shachaf has joined.
00:56:26 -!- Lymia has joined.
01:02:35 <Sgeo> http://www.snopes.com/college/homework/foundcar.asp
01:02:38 <Sgeo> I've read that book!
01:03:08 <Sgeo> I don't know what printing it was
01:05:06 <Sgeo> Apparently the author is a felon
01:08:21 <Bike> you've read Rapid Interpretation of EKGs?
01:08:36 -!- not^v has quit (Ping timeout: 265 seconds).
01:11:02 <Bike> are you like, into electrocardiology
01:12:32 <Sgeo> My dad's a doctor. The book was lying around
01:12:37 <Sgeo> This was when I was a kid
01:12:49 -!- zzo38 has joined.
01:20:32 <int-e> . o O ( I guess it has been a while since http://www.schlockmercenary.com/2014-06-15 so a reminder was in order. http://www.schlockmercenary.com/2014-10-30 )
01:22:48 -!- shikhout has quit (Ping timeout: 250 seconds).
01:29:05 -!- Phantom_Hoover has joined.
01:29:05 -!- Phantom_Hoover has quit (Changing host).
01:29:05 -!- Phantom_Hoover has joined.
01:33:16 -!- Lymia has quit (Ping timeout: 255 seconds).
01:46:39 -!- copumpkin has quit (Ping timeout: 256 seconds).
01:50:01 -!- not^v has joined.
02:11:28 <MDude> But if they're in a ring around the planet, how could they *all* pplint to one spot?
02:11:56 <Bike> spot could be somewhere off the planet
02:12:03 <MDude> It's have to be one of the poles, and then it'd be at an odd angle.
02:16:04 <int-e> MDude: I think half of them would be enough.
02:16:32 <MDude> It would, but still.
02:17:07 -!- not^v has quit (Ping timeout: 272 seconds).
02:17:23 <int-e> This is Schlock talking. Schlock is not known for impeccable logic. He's known for his love of big guns, and being near indestructible.
02:22:20 <MDude> That's fair enough.
02:24:01 <int-e> hey how about this excuse ...
02:24:46 <MDude> The planet could be considered one spot, if "spot" is takes as peing sufficiently imprecise/on large enough of a scale?
02:24:58 <int-e> those mirrors could just change their orbit slightly until they're all in sight of the target?
02:25:25 <int-e> of course that would produce a ring with a gap
02:25:39 <MDude> They should all just reflect it back to where it came. BURN THE SUN.
02:25:43 <int-e> but that's a small sacrifice when logic is at stake ;-)
02:26:18 <MDude> They could form a smaller, thicker ring on one side of a planet.
02:27:05 <int-e> I was looking for a solution that does not require a lot of energy per mirror (to maintain its orbit).
02:27:49 <int-e> rather I was looking for something that current Earth satellites might be capable of doing.
02:28:45 <int-e> ooh, logic. http://thedevilspanties.com/archives/10247 ... looks painful.
02:31:57 -!- hjulle has joined.
02:32:12 -!- hjulle has quit (Remote host closed the connection).
02:41:44 -!- Lymia has joined.
02:42:00 <Lymia> I took a look at Maptools to see if I could bypass GM protections and stuff
02:42:18 <Lymia> I ended up with a proof of concept for arbitary file write on servers with no authentication needd.
02:44:30 <Lymia> They accept connections from clients
02:44:35 <Lymia> I feel safe calling them servers.
02:46:29 <int-e> Never mind, Google enlightened me about the context.
02:47:03 <vanila> Recommendations on languages to easily write bootstrapping compilers in?
02:47:37 <int-e> Lymia: How about "The best part is all this isn't limited to a single PC. You can utilize the integrated server function to let your players maintain your server, [...]"
02:52:17 -!- copumpkin has joined.
03:19:11 -!- contrapumpkin has joined.
03:20:56 -!- vanila has quit (Quit: Leaving).
03:22:10 -!- copumpkin has quit (Ping timeout: 255 seconds).
03:25:09 -!- contrapumpkin has changed nick to copumpkin.
03:28:04 -!- copumpkin has quit (Read error: Connection reset by peer).
03:29:48 -!- copumpkin has joined.
03:35:22 -!- copumpkin has quit (Ping timeout: 240 seconds).
03:41:08 -!- copumpkin has joined.
03:49:25 -!- oerjan has joined.
03:51:10 -!- Samhain has changed nick to centrinia.
03:58:18 <zzo38> Now I bought some new Akagi book, as well as a Famicom. I don't know how to connect it up to the TV set, yet.
04:00:09 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
04:04:37 <Sgeo> The March 2016 cruise I wanted to go on was cancelled, I think
04:21:52 -!- MDude has changed nick to MDream.
04:52:54 -!- copumpkin has joined.
04:56:39 -!- not^v has joined.
05:01:47 -!- not^v has quit (Ping timeout: 272 seconds).
06:54:46 -!- shikhin has joined.
07:04:10 -!- ais523 has joined.
07:16:35 -!- MoALTz has joined.
07:16:56 -!- shikhin has quit (Ping timeout: 244 seconds).
07:18:58 -!- ais523 has changed nick to ais523\unfoog.
07:22:17 -!- centrinia has quit (Ping timeout: 265 seconds).
07:41:18 -!- mihow has joined.
07:52:50 -!- centrinia has joined.
08:39:02 <HackEgo> [wiki] [[Talk:FakeASM]] http://esolangs.org/w/index.php?diff=40742&oldid=40735 * Rdebath * (+493) /* Um Esoteric Language ? */
08:49:44 <Sgeo> "On the ship or ashore the speed and reliability of internet may not be optimal. Expect to encounter issues with uploading or downloading attachments, possible frequent outages, computer freezups, access to USB ports, etc."
08:53:19 -!- AnotherTest has joined.
08:53:28 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
09:16:46 -!- Froox has quit (Read error: Connection reset by peer).
09:24:49 -!- Phantom_Hoover has joined.
10:20:31 -!- oerjan has quit (Quit: leaving).
11:10:48 -!- hjulle has joined.
11:33:03 -!- MDream has changed nick to MDude.
11:38:08 <J_Arcane> new *nix OS for z80s. https://github.com/EtchedPixels/FUZIX cc: zzo38
11:45:53 -!- ais523 has joined.
11:49:41 -!- ais523\unfoog has quit (Ping timeout: 264 seconds).
11:51:22 -!- ais523 has changed nick to ais523\unfoog.
11:53:44 -!- centrinia has quit (Ping timeout: 250 seconds).
12:02:17 -!- MoALTz has quit (Quit: Leaving).
12:06:54 -!- ais523\unfoog has quit.
12:07:00 -!- ais523 has joined.
12:21:55 -!- AnotherTest has quit (Remote host closed the connection).
12:23:59 -!- ais523 has changed nick to ais523\unfoog.
12:25:24 -!- SignX has joined.
12:35:52 <SignX> I am trying to implement a Brainfuck interpreter in my own programming language and I am a bit unsure whether the approach i am taking is going to lead anywhere. How do you implement a imperative programming language in a declarative one?
12:48:27 <Jafet> You could start with a simpler language, like deadfish.
12:50:13 -!- SignX has quit (Ping timeout: 246 seconds).
12:55:50 -!- SignX has joined.
12:58:45 <SignX> Jager: I was under the impression brainfuck already was a simple language. But you think deadfish is a better choice?
13:02:49 <mroman> deadfish is even simpler
13:02:52 <mroman> mainly because no loops .
13:06:08 <SignX> Aha, thx. I have to go. Bye!
13:06:10 -!- SignX has quit (Quit: Page closed).
13:07:47 -!- qlkzy has quit (Excess Flood).
13:10:12 -!- qlkzy has joined.
13:22:51 -!- ais523\unfoog has quit.
13:46:26 <Melvar> ( the (Monad id) %instance
13:46:26 <idris-bot> constructor of Prelude.Monad.Monad (\{meth0} => \{meth1} => \{meth2} => \{meth3} => meth meth) : Monad id
14:09:34 -!- Frooxius has joined.
15:34:11 -!- ais523 has joined.
15:54:32 -!- blsqbot has quit (Quit: Exiting).
15:55:28 -!- blsqbot has joined.
15:55:39 <blsqbot> {1 3 6 10 15 21 28 36 45 55}
15:56:15 <mroman> fizzie: Even with a partial builtin you don't beat 12B ;)
15:56:42 <mroman> (you would with a partial sum builtin though)
15:56:52 <mroman> (pa is the partial command)
15:56:59 <blsqbot> {1 2 6 24 120 720 5040 40320 362880 3628800}
15:58:12 <blsqbot> {{1} {2 1} {3 2 1} {4 3 2 1} {5 4 3 2 1} {6 5 4 3 2 1} {7 6 5 4 3 2 1} {8 7 6 5
15:58:52 <blsqbot> {{} {1} {1 2} {1 2 3} {1 2 3 4} {1 2 3 4 5} {1 2 3 4 5 6} {1 2 3 4 5 6 7} {1 2 3
15:58:55 <blsqbot> {0 1 3 6 10 15 21 28 36 45 55}
16:00:33 -!- blsqbot has quit (Read error: Connection reset by peer).
16:01:31 <Melvar> ( the (StateT Integer id ()) $ do put (!get + 1)
16:01:31 <idris-bot> ST (\st => ((), prim__addBigInt st 1)) : StateT Integer id ()
16:02:03 <Melvar> ( runState (the (StateT Integer id ()) $ do put (!get + 1)) 2
16:02:09 <Melvar> ( runStateT (the (StateT Integer id ()) $ do put (!get + 1)) 2
16:02:59 <Melvar> Best identity monad: actually id.
16:07:51 -!- blsqbot has joined.
16:07:56 <blsqbot> {"abcd" "bcda" "cdab" "dabc"}
16:08:20 <blsqbot> {{"abcd"} ERROR: Burlesque: (_+) Invalid arguments! {"abcd" "bcda"} ERROR: Burle
16:08:31 <blsqbot> {{ERROR: Burlesque: (\[) Invalid arguments! "abcd"} {ERROR: Burlesque: (\[) Inva
16:08:40 <blsqbot> {"abcd" "abcdbcda" "abcdbcdacdab" "abcdbcdacdabdabc"}
16:08:55 <blsqbot> {"world" "worldorldw" "worldorldwrldwo" "worldorldwrldwoldwor" "worldorldwrldwol
16:09:07 <blsqbot> {"abc" "abcbca" "abcbcacab"}
16:10:34 <mroman> Work on Burlesque 1.7.4 has started :D
16:14:19 <b_jonas> is that the one that will have variables?
16:18:25 <ais523> hmm, Snowflake would make for an excellent golfing language
16:18:44 <ais523> especially if the interpreter was persistent between runs (which it really should be)
16:31:16 -!- nys has joined.
16:46:32 -!- blsqbot has quit (Ping timeout: 260 seconds).
17:45:50 -!- adu has joined.
17:45:57 -!- blsqbot has joined.
17:45:59 <blsqbot> {{{{1}}} {{{1} {1 2}} {{1 2} {1}}} {{{1} {1 2} {1 2 3}} {{1 2} {1 2 3} {1}} {{1
17:46:37 <blsqbot> {{{{1}}} {{{1} {1 2}} {{1 2} {1}}}}
17:47:07 <blsqbot> Ain't nobody got time fo' dat!
17:47:12 <blsqbot> Ain't nobody got time fo' dat!
17:47:15 <blsqbot> {1 {{1}} 1 {{1 2} {1 2 2 1}}}
17:47:19 <blsqbot> {1 {{1}} 1 {{1 2} {1 2 2 1}} 1 {{1 2 3} {1 2 3 2 1 3} {1 2 3 2 1 3 3 2 1} {1 2 3
17:48:08 <mroman> !blsq 3ro{roq++pa}paL[
17:48:11 <mroman> !blsq 4ro{roq++pa}paL[
17:48:14 <mroman> !blsq 14ro{roq++pa}paL[
17:58:30 <blsqbot> {ERROR: Burlesque: (pa) Invalid arguments! 9 5 1 4 1 3}
17:58:42 <blsqbot> {ERROR: Burlesque: (pa) Invalid arguments! {4 1 5 9} 1 3}
17:58:55 <blsqbot> {ERROR: Burlesque: (pa) Invalid arguments! 9 {1 4 1 5} 3}
17:59:03 <blsqbot> {{{3} 1 5 9 {3 1} 1 5 9 {3 1 4} 1 5 9}}
18:08:09 -!- adu has left.
18:14:30 <blsqbot> {1 3 6 10 15 21 28 36 45 55}
18:14:40 <blsqbot> {1 2 6 24 120 720 5040 40320 362880 3628800}
18:16:22 <fizzie> If that's an O(n^2) thing, I'm slightly afraid of the time limits, compared to a regular scan[lr]1?-based partial thing.
18:25:15 <mroman> but I'm implementing a version of it that works differently
18:25:36 <mroman> (i.e. one that takes ?+)
18:25:43 <mroman> and which will be more efficient
18:26:46 <mroman> pa will be usably for commands that work on lists
18:26:55 <mroman> and PA will be usable the other way
18:26:56 <b_jonas> mroman: is this associating the direction that has to be O(n^2), or the direciton where it coudl be O(n)?
18:27:01 <mroman> where you just collect intermediate results
18:27:29 <mroman> pa just builds up tails
18:27:35 <mroman> and maps the supplied block over it
18:27:39 <blsqbot> {{} {1} {1 2} {1 2 3} {1 2 3 4} {1 2 3 4 5} {1 2 3 4 5 6} {1 2 3 4 5 6 7} {1 2 3
18:27:43 <blsqbot> {0 1 3 6 10 15 21 28 36 45 55}
18:28:33 <mroman> which is inefficient but there might be some weird use cases for it
18:28:47 <mroman> like that one or I don't know
18:29:16 <int-e> > foldl (flip (:)) [] [1..3] -- hmm
18:29:24 <int-e> > scanl (flip (:)) [] [1..3]
18:29:56 <blsqbot> ERROR: Burlesque: (pa) Invalid arguments!
18:30:02 <blsqbot> ERROR: Burlesque: (pa) Invalid arguments!
18:30:07 <mroman> !blsq "barfuss"XXq\[pa
18:30:07 <blsqbot> {"b" "ba" "bar" "barf" "barfu" "barfus" "barfuss"}
18:30:29 <blsqbot> {{{3}} ERROR: Burlesque: ([+) Invalid arguments! {{3 1}} ERROR: Burlesque: ([+)
18:30:33 <mroman> gotta add a (BlsqStr x :) too
18:30:39 <blsqbot> ERROR: Unknown command: (PA)!
18:30:46 <b_jonas> !blsq {3 1 4 1 5}{{bx[+}r[}pa
18:30:46 <blsqbot> {3 ERROR: Burlesque: ([+) Invalid arguments! ERROR: Burlesque: ([+) Invalid argu
18:30:47 <mroman> that one is not implemented yet
18:30:51 <b_jonas> !blsq {3 1 4 1 5}{{bx+]}r[}pa
18:30:51 <blsqbot> {3 ERROR: Burlesque: (+]) Invalid arguments! ERROR: Burlesque: (+]) Invalid argu
18:30:59 <mroman> !blsq {3 1 4 1 5}{im}pa
18:31:04 <b_jonas> !blsq {3 1 4 1 5}{{bxj[+}r[}pa
18:31:04 <blsqbot> {3 {1 3} {4 {1 3}} {1 {4 {1 3}}} {5 {1 {4 {1 3}}}}}
18:31:27 <mroman> !blsq {3 1 4 1 5}{p^}pa
18:31:27 <blsqbot> {3 1 3 4 1 3 1 4 1 3 5 1 4 1 3}
18:31:30 <b_jonas> ^ that can be done in linear time, and
18:31:37 <b_jonas> !blsq {3 1 4 1 5}{<-{bxj[+}r[}pa
18:31:37 <blsqbot> {3 {3 1} {3 {1 4}} {3 {1 {4 1}}} {3 {1 {4 {1 5}}}}}
18:32:32 <int-e> C-x RET c <-- who's supposed to remember this?!
18:32:40 <mroman> !blsq "barFUsS"XX{)<-}pa
18:32:41 <blsqbot> {{'B} {'B 'A} {'B 'A 'R} {'B 'A 'R 'f} {'B 'A 'R 'f 'u} {'B 'A 'R 'f 'u 'S} {'B
18:32:49 <mroman> !blsq "barFUsS"XX{)<-\[}pa
18:32:49 <blsqbot> {"B" "BA" "BAR" "BARf" "BARfu" "BARfuS" "BARfuSs"}
18:33:51 <int-e> > mapM words["big bare flat","foot"]
18:33:53 <lambdabot> [["big","foot"],["bare","foot"],["flat","foot"]]
18:34:08 <int-e> > concat<$>mapM words["big bare flat","foot"]
18:34:54 <int-e> > concat<$>words=<<["big bare flat","foot"]
18:46:58 <int-e> . o O ( somehow, Make 24 is far more satisfying in Perl than in Haskell )
18:52:46 <b_jonas> oh, you got it down to 181
19:02:06 <int-e> let's see how short it'll look in two weeks...
19:02:45 <int-e> in this problem there are so many approaches that one could try
19:14:21 -!- vanila has joined.
19:17:09 <vanila> I started an analyzer to see if prolog query is deterministic
19:17:21 <vanila> should be able to compile them to haskell
19:17:28 <vanila> type classes and instances
19:23:44 -!- shikhin has joined.
19:51:15 <HackEgo> [wiki] [[Talk:FakeASM]] http://esolangs.org/w/index.php?diff=40743&oldid=40742 * Zzo38 * (+445)
19:56:23 -!- MoALTz has joined.
20:08:16 -!- AnotherTest has joined.
20:51:13 -!- boily has joined.
21:01:21 -!- boily has quit (Quit: QUID CHIC).
21:01:44 -!- boily has joined.
21:01:58 -!- boily has quit (Client Quit).
21:10:16 <mroman> !blsq 1{2 3 4}{#<}e!#s
21:10:32 <blsqbot> ERROR: Burlesque: (st) Invalid arguments!
21:11:04 <mroman> !blsq 1{2 3 4}{#<}rs#s
21:11:28 <mroman> (rs is a form of eval that doesn't touch the current stack)
21:11:39 <mroman> !blsq 1{2 3 4}{#<}e!#s
21:18:36 -!- blsqbot has quit (Ping timeout: 260 seconds).
21:34:00 -!- ais523 has changed nick to ais523\unfoog.
21:51:25 -!- ais523\unfoog has quit.
22:04:45 <zzo38> Is there a single-file simple LZMA2 compression and decompression library?
22:05:47 <zzo38> (Additionally, I require that it be cross-platform and free-software.)
22:17:21 -!- FreeFull has quit (Ping timeout: 265 seconds).
22:19:20 -!- FreeFull has joined.
22:19:34 -!- FreeFull has quit (Changing host).
22:19:34 -!- FreeFull has joined.
22:22:09 <b_jonas> zzo38: I don't know any of those for lzma2, sorry (though you could try to put some existing source code to one file). do you need lzma2? would some other compression and decompression not do?
22:22:59 <zzo38> Well, LZMA would probably do too, it doesn't have to be LZMA2.
22:23:16 <zzo38> (The data I am trying to compress doesn't compress well with DEFLATE.)
22:23:51 <b_jonas> zzo38: dunno, try to take the non-machine specific part of the compressor from xz or 7z and massage it to one file.
22:24:04 <b_jonas> but that's probably not so easy
22:29:36 <zzo38> I also don't need filters like xz has, nor support for a file listing. I don't know what algorithm Bzip2 uses, but that seems to work well too.
22:31:13 <b_jonas> could you use some domain-specific compression method, or domain-specific preprocessing?
22:32:19 <zzo38> I am compressing a "Z-Machine Archive", which contains a story file, capability set, metadata, and possibly also sounds and pictures.
22:32:58 <b_jonas> zzo38: um, some of those might be different from the others. can you somehow separate it to sounds, pictures, and the rest, and see how each compresses,
22:33:25 <b_jonas> then use sound and picture specific compression for those parts, and zip-like byte compression for the byte-oriented text stuff, possibly after some preprocessing?
22:35:06 <zzo38> Actually, all of the data is already somewhat compressed in different ways (text in story files is packed to 5-bits per character and also uses a simple dictionary coding scheme; YZIP picture libraries are compressed using Huffman, XOR, palettes, and stippling; XZIP picture libraries and sounds aren't compressed at all)
22:35:33 <b_jonas> zzo38: yes, that's the problem. you might want to unpack the text so taht you can zip it after
22:35:50 <b_jonas> like, if it's 5 bits per character, but zip is very 8-bit oriented, it's harder for it to compress
22:35:52 <zzo38> I could allow it to avoid compressing some parts if compressing them wouldn't help, and add a mode to the program to disable all compression, but other than that I want to just use a single compression algorithm.
22:36:05 <zzo38> b_jonas: I know that, although it isn't always predictable where the text even is in the file.
22:36:22 <b_jonas> zzo38: yeah... that could be tricky. you may need some imperfect heuristics
22:36:35 <b_jonas> as long as you compress losslessly, it shouldn't be a problem if you sometimes misidentify stuff
22:36:41 <b_jonas> does the compression have to be fast?
22:36:55 <zzo38> Yes, that was a thought too. But since I found out that bzip2 works good enough, I thought that could be used.
22:37:26 <zzo38> b_jonas: No it doesn't have to be particularly fast (although it would be a good idea for the decompression not to be too slow)
22:37:28 <b_jonas> if bzip2 works well, that might be easier to get a small implementation, but I think bzip2 is byte-oriented too (and png is too while we're there)
22:38:28 <zzo38> Yes, although I found that bzip2 does work. (Another thing about the Z-machine text packing: It is packed three 5-bit characters into two bytes; the remaining bit tells if it is finished or not.)
22:38:28 <int-e> bzip2 is definitely byte oriented
22:39:16 <int-e> oh that should be fine. then every repeated string comes in just two versions, essentially.
22:39:21 <b_jonas> zzo38: oh, that's better! better than packing 8 characters in 5 bytes that is, because you have less synchronization problems
22:39:45 <myname> it depends on where it is in the text
22:40:19 <zzo38> It might not be the best compression, but it does work reasonably well; DEFLATE doesn't work so well from my testing.
22:41:30 <int-e> myname: abcdef can be packed as (abc)(def)(ghi), (..a)(bcd)(efg)(hi.), (.ab)(cde)(fgh)(i..); bwt will put the repeated center parts together and probably produce decent predictions (and thus compression) anyway.
22:42:02 <int-e> (sorry, abcdefghi - I added another triplet as an afterthought)\
22:42:50 <int-e> but the point was that while having only 1 encoding would be ideal, having 3 is better than having 8.
22:43:03 <b_jonas> zzo38: so how quickly do the text and other segments mix? can you try to pack each part normally and after expanding the text, and choose whichever compresses better?
22:44:21 <zzo38> b_jonas: I did think of that too, although the alignment is also unpredictable (sometimes on an even byte boundary, and sometimes odd).
22:44:49 <b_jonas> even text, odd text, bytes
22:44:52 -!- AnotherTest has quit (Ping timeout: 240 seconds).
22:44:57 <int-e> zzo38: how does this work? does the z machine encode addresses that are then decoded and displayed as strings?
22:46:20 <zzo38> int-e: It depends on the situation. The PRINTI and PRINTR instructions are followed by text strings inline; PRINT and PRINTB point to other strings (PRINT always to even alignment, PRINTB to even or odd); an object header may point to a string representing the "short description" of an object, and the vocabulary also contains packed strings.
22:46:29 <int-e> (I sort of expected the files to have a string table instead, with code providing indices into the table, a bit like java objects... but I never investigated)
22:46:52 <b_jonas> that means the thingies can change very quickly
22:48:20 <int-e> (Ok, PRINTI is more efficient than that; it saves the index.)
22:49:07 <int-e> zzo38: Do you know whether games ever exploit common suffixes of strings, if the alignment allows it?
22:50:09 <zzo38> int-e: As far as I know no existing files do, but if I make my own, they would exploit a whole lot of stuff (I mentioned these things in a document called the Tricky Document).
22:53:40 <b_jonas> zzo38: so how much is it possible to try to follow all the possible execution paths hoping all of them are actually possible, sort of like decompiling, and that way try to determine which parts of the image are text and stuff?
22:53:52 -!- idris-bot has quit (Ping timeout: 244 seconds).
22:54:41 <zzo38> b_jonas: That is probably very complicated. I am not intending to cause the best possible compression anyways though; I am just trying to make it to be reasonably good compression.
22:57:53 <b_jonas> zzo38: you could try to concatenate the seven source files from the bzip2 program, that isn't too many, there's only like seven source files, plus some headers
22:58:04 <b_jonas> zzo38: you could try to remove the checksumming part, though that doesn't really add much
22:59:25 <b_jonas> zzo38: or you could similarly try to catenate the lzma stuff from the 7z sources or something
22:59:28 <zzo38> The archiver program uses its own header formats and stuff, so, I want to use it in a library. And, yes I don't need checksumming and stuff; the uncompressed format it is known to figure out when the data is finished, so it will know when to stop.
23:00:08 <zzo38> I will look to see how the bzip2 codes are working so that I can learn that.
23:09:10 <b_jonas> ooh, strange choice, rng! two wands of polymorph in a chest in a starting room.
23:11:59 <myname> i like playing as a dragon, it makes things so convinient
23:12:15 <myname> lay some eggs, hatch them, eat babys
23:14:22 -!- impomatic_ has joined.
23:16:12 <b_jonas> what a crazy mines level layout
23:17:02 <b_jonas> well, this was a quick deat
23:21:19 -!- Sprocklem has joined.
23:24:08 -!- vyv_ has joined.
23:24:09 -!- vyv has quit (Ping timeout: 260 seconds).
23:34:30 <Sgeo> b_jonas: what game?
23:34:41 <Sgeo> Oh, NetHack I assume
23:45:50 -!- FreeFull has quit (Ping timeout: 244 seconds).
23:46:39 -!- FreeFull has joined.
00:07:06 -!- oerjan has joined.
00:13:13 -!- shikhin has quit (Ping timeout: 244 seconds).
01:05:16 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
01:07:43 <oerjan> just a few hours until we can see what inscrutable magic henkma did to the belgians.
01:10:37 <oerjan> i was about to say henkma sounds like it could be flemish but there's a distinctively japanese twitter with that nick
01:14:37 -!- MoALTz_ has joined.
01:15:48 -!- centrinia has joined.
01:17:30 -!- MoALTz has quit (Ping timeout: 244 seconds).
01:34:10 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
01:38:49 <oerjan> argh, time to find out how to disable the power-off button on my keyboard, or at least make it ask for confirmation.
01:39:21 <oerjan> (well, slightly above the keyboard proper, but close enough that this isn't the first time i've hit it by accident.)
01:41:37 <oerjan> apparently there is no option to ask for confirmation. make it do the same as shutting the lid, then.
01:43:39 <oerjan> gah IE has forgotten the tabs i had open
01:44:39 <oerjan> it's like anyone there has thought that a forced power-off is the time you _most_ want it to save its current state carefully.
02:32:06 -!- centrinia has quit (Ping timeout: 250 seconds).
02:47:28 -!- centrinia has joined.
20:14:35 -!- esowiki has joined.
20:14:36 -!- glogbot has joined.
20:14:39 -!- esowiki has joined.
20:14:39 -!- esowiki has joined.
20:14:39 -!- EgoBot has joined.
20:15:35 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
20:28:39 <oerjan> THE DEAD BOTS ARE RISING
20:30:14 -!- Sprocklem has joined.
20:31:04 <int-e> cue for metasepia?
20:31:30 <olsner> metasepia seems to be dependent on its human
20:31:43 <int-e> > map(tail.tails).(init.inits)$"1234"
20:31:57 <int-e> > map(init.tails).(tail.inits)$"1234"
20:31:59 <lambdabot> [["1"],["12","2"],["123","23","3"],["1234","234","34","4"]]
20:32:38 <fizzie> Needs some reordering.
20:33:04 <int-e> > concat.transpose.map(tail.inits).(init.tails)$"1234"
20:33:05 <lambdabot> ["1","2","3","4","12","23","34","123","234","1234"]
20:33:20 <fizzie> Now I guess we've got a bfjoust conflict, then. :/
20:33:24 <zemhill> fizzie: "!bfjoust progname code". See http://zem.fi/bfjoust/ for documentation.
20:33:25 <EgoBot> Use: !bfjoust <program name> <program> . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/
20:33:55 <fizzie> What's the CONSENSUS on how to PROCEED?
20:33:58 <zemhill> elliott: I do !bfjoust; see http://zem.fi/bfjoust/ for more information.
20:33:58 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
20:34:02 <EgoBot> userinterps: Users can add interpreters written in any of the languages in !help languages. See !help addinterp, delinterp, show | !userinterps. List interpreters added with !addinterp.
20:34:06 <EgoBot> addinterp: !addinterp <name> <language> <code>. Add a new interpreter to EgoBot. This interpreter will be run once every time you type !<name> <subcode>, and receive the program code as input.
20:34:14 <elliott> (uh, this output seems broken.)
20:34:27 <elliott> no, that was definitely "hlp"
20:34:33 <elliott> !addinterp bfjoust sh true
20:34:34 <EgoBot> Interpreter bfjoust installed.
20:34:35 <zemhill> elliott: "!bfjoust progname code". See http://zem.fi/bfjoust/ for documentation.
20:34:36 <EgoBot> Use: !bfjoust <program name> <program> . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/
20:34:41 <EgoBot> Interpreter bfjoust deleted.
20:34:56 <fizzie> I'm not seeing anything weird.
20:35:14 -!- Bicyclidine has joined.
20:35:15 <fizzie> I mean, anything weirder than the usual.
20:35:51 <elliott> maybe my irssi or mosh or terminal is choking on the weird stuff it uses to prevent botloops
20:37:24 <myname> i should make a bot that triggers on zero-width spaces only
20:38:46 <oerjan> int-e: you don't need the init. before tails, also id=<< is shorter than concat if things fit
20:40:13 <oerjan> elliott: HackEgo uses the same stuff afaik
20:40:26 <HackEgo> Runs arbitrary code in GNU/Linux. Type "`<command>", or "`run <command>" for full shell commands. "`fetch <URL>" downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert <rev>" can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
20:40:38 <elliott> well EgoBot's output definitely looks weird to me
20:40:58 <oerjan> i see none of your weirdness
20:41:49 <int-e> 20:34:41: <EgoBot> <U+200B>Interpreter bfjoust deleted.
20:41:52 <oerjan> int-e: that problem really chose an awkward ordering of sets.
20:44:04 -!- centrinia has joined.
20:45:19 -!- AndoDaan has quit (Ping timeout: 272 seconds).
20:47:44 <fizzie> oerjan: I thought it was a very natural ordering.
20:48:22 <int-e> it's awkward to produce programmatically.
20:48:34 <int-e> at least in Haskell
20:49:52 <olsner> sorted by increasing length, then lexicographically?
20:50:12 <mroman> olsner: "THE DEAD BOTS ARE RISING" sounds like a promising movie title
20:50:34 <oerjan> someone's tab completion is acting up *cough*
20:50:39 <olsner> mroman: yes, or maybe DEAD BOT RISING
20:50:41 <int-e> olsner: nah, substrings of length 1 in order of appearance, the those of length 2 in order of appearance, etc.
20:50:59 <olsner> oh, so a stable sort on length, like?
20:53:03 <int-e> something like that
20:53:36 <oerjan> i suppose sortBy (comparing length) would work to make that from a simpler construction
20:53:46 <oerjan> but so does concat.transpose
20:55:19 <oerjan> all of which are disgustingly long and require importing Data.List
21:23:19 <b_jonas> what? isn't transpose in Prelude?
21:23:42 <oerjan> neither are inits or tails
21:24:08 <oerjan> although i found a reasonably short replacement for tails...
21:30:55 -!- idris-bot has quit (Quit: Terminated).
21:31:14 -!- Melvar has quit (Quit: rebooting).
21:32:24 <oerjan> i found a 45-46 char Prelude-only thing that constructs the substrings
21:32:40 <oerjan> which means it's shorter than the transpose version if you include the import
21:35:27 -!- Melvar has joined.
21:46:35 -!- idris-bot has joined.
21:59:54 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
22:08:21 <int-e> `` perl -e '$_=1234;/.+(?{print"$&\n"})(*F)/' # I think the Perl people would also be happier with another order.
22:08:22 <HackEgo> 1234 \ 123 \ 12 \ 1 \ 234 \ 23 \ 2 \ 34 \ 3 \ 4
22:08:56 -!- Bicyclidine has joined.
22:09:13 <b_jonas> int-e: what? the order is completely defined by the docs, and reliable
22:09:24 <b_jonas> int-e: what order would you prefer?
22:10:24 <int-e> b_jonas: I meant using another order in the specification of http://golf.shinh.org/p.rb?Prime+Substrings
22:12:31 <b_jonas> `perl -e hello=~/.+(?{print$&," "})(?!)/
22:12:32 <HackEgo> hello hell hel he h ello ell el e llo ll l lo l o
22:12:39 <b_jonas> `perl -e bravo=~/.+(?{print$&," "})(?!)/
22:12:40 <HackEgo> bravo brav bra br b ravo rav ra r avo av a vo v o
22:12:44 <b_jonas> `perl -e bravo=~/.+?(?{print$&," "})(?!)/
22:12:44 <HackEgo> b br bra brav bravo r ra rav ravo a av avo v vo o
22:12:52 <b_jonas> `perl -e bravo=~/.*\K.+(?{print$&," "})(?!)/
22:12:53 <HackEgo> o vo v avo av a ravo rav ra r bravo brav bra br b o vo v avo av a ravo rav ra r o vo v avo av a o vo v o
22:12:57 <b_jonas> `perl -e bravo=~/.*\K.+?(?{print$&," "})(?!)/
22:12:58 <HackEgo> o v vo a av avo r ra rav ravo b br bra brav bravo o v vo a av avo r ra rav ravo o v vo a av avo o v vo o
22:13:13 <b_jonas> you can get any order from regexen
22:13:29 <b_jonas> sorted by length is probably more difficult
22:13:44 <int-e> --> b r a v o br ra av vo bra rav avo brav ravo bravo
22:15:59 <int-e> it's something like a breadth first search
22:17:40 <int-e> perl -e 'bravo=~/.{$_}(?{print"$&\n"})(*F)/ for(1..5)'
22:17:45 <int-e> `` perl -e 'bravo=~/.{$_}(?{print"$&\n"})(*F)/ for(1..5)'
22:17:46 <HackEgo> Eval-group not allowed at runtime, use re 'eval' in regex m/.{1}(?{print"$&\n"})(*F)/ at -e line 1.
22:18:07 -!- nys has joined.
22:18:16 <int-e> funny. works for me.
22:18:32 <HackEgo> \ This is perl 5, version 14, subversion 2 (v5.14.2) built for x86_64-linux-gnu-thread-multi \ (with 88 registered patches, see perl -V for more detail) \ \ Copyright 1987-2011, Larry Wall \ \ Perl may be copied only under the terms of either the Artistic License or the \ GNU General Public License, which may be found in the Perl 5 source kit
22:19:07 <int-e> Right. v5.20.1 here.
22:19:57 -!- `^_^ has joined.
22:20:23 <int-e> but v5.14.2 on anagol, so it won't work there either
22:22:08 <int-e> `` perl -e 'use re "eval";bravo=~/.{$_}(?{print"$&\n"})(*F)/ for(1..5)'
22:22:09 <HackEgo> b \ r \ a \ v \ o \ br \ ra \ av \ vo \ bra \ rav \ avo \ brav \ ravo \ bravo
22:22:27 -!- Sprocklem has quit (Ping timeout: 250 seconds).
22:23:05 -!- nycs has quit (Ping timeout: 244 seconds).
22:23:38 <zzo38> How can you convert a timestamp in a text format (including the timezone) into a UNIX timestamp number, in a C code?
22:24:19 <fizzie> `run perl -e '@a = ("bravo"); while ($a[-1] =~ /\S\S/) { push @a, $a[-1] =~ s/(\S)(\S*)(\S)/$1$2 $2$3/rg; } print join(" ", @a)' # probably not a useful direction, but fun nevertheless
22:24:20 <HackEgo> bravo brav ravo bra rav rav avo br ra ra av ra av av vo b r r a r a a v r a a v a v v o
22:25:23 <fizzie> I think the appropriate answer to that is "with difficulty", because POSIX strptime is entirely useless when it comes to time zones.
22:29:53 <zzo38> Then is there better way?
22:33:56 <fizzie> I think I've seen some attempts that are based on recognizing the time zone separately, (temporarily) doing tzset and parsing the rest via normal strptime. But that seems quite nasty.
22:34:53 <zzo38> How does that do? I require it to work both Windows and UNIX computers.
22:37:20 <fizzie> I somewhat suspect it wouldn't really work on Windows.
22:42:00 <oerjan> now if i only knew a good haskell golf prime test that worked up to 999...
22:42:14 <oerjan> also, if i could make my trivial one work on 0 and 1.
22:43:10 <tromp> > nubBy(((>1).).gcd)[2..]
22:43:11 <lambdabot> [2,3,5,7,11,13,17,19,23,29,31,37,41,43,47,53,59,61,67,71,73,79,83,89,97,101,...
22:43:35 <oerjan> not a list, a test hth
22:43:51 <oerjan> also nubBy is no good, it's not in Prelude.
22:46:34 <tromp> how bout using fermat's test and avoiding the 3 exceptions?
22:47:16 <int-e> but naive is better than that
22:47:40 <tromp> yes, naive shorted and much slower
22:47:51 <int-e> speed shouldn't be a problem?
22:48:51 <oerjan> it doesn't seem to be a problem, since i already ran one that failed because i forgot about 0 and 1
22:49:58 <int-e> yeah. not a problem at all.
22:50:21 -!- AndoDaan has joined.
22:52:17 <FireFly> Argh. How annoying, the input isn't newline-terminated
22:54:27 <oerjan> but it feels too long, anyway
22:57:42 -!- boily has joined.
23:01:00 -!- oerjan has quit (Quit: Good night).
23:02:07 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
23:07:55 -!- boily_ has joined.
23:10:02 <zzo38> Someone told me to use Kronisk but that is C++ and not C.
23:11:12 -!- Bicyclidine has joined.
23:13:24 -!- boily_ has quit (Quit: DUPLICATE CHICKEN).
23:26:55 -!- nys has quit (Ping timeout: 264 seconds).
23:27:18 -!- nys has joined.
23:32:05 <fizzie> FireFly: I would estimate that roughly 98% of the problems are missing the newline on the last line.
23:32:29 -!- mihow has quit (Quit: mihow).
23:41:09 -!- `^_^ has quit (Quit: This computer has gone to sleep).
23:52:54 -!- Phantom_Hoover has joined.
00:04:01 -!- AndoDaan has quit (Quit: HydraIRC -> http://www.hydrairc.com <- *I* use it, so it must be good!).
00:04:23 -!- Bicyclidine has quit (Ping timeout: 256 seconds).
00:04:25 -!- AndoDaan has joined.
00:11:50 -!- boily has quit (Quit: ANATIDÆ CHICKEN).
00:15:33 -!- Bicyclidine has joined.
00:22:31 -!- AndoDaan has quit (Ping timeout: 256 seconds).
00:45:26 <FireFly> That's a bit annoying for J golfing
01:06:47 -!- Bicyclidine has quit (Ping timeout: 265 seconds).
01:12:28 <Sgeo> I should play Nomyx
01:12:34 <Sgeo> Is Nomyx the new PerlNomic
01:40:56 -!- Phantom_Hoover has quit (Remote host closed the connection).
02:05:10 -!- AndoDaan has joined.
02:09:10 -!- Deewiant has quit (Ping timeout: 260 seconds).
02:10:57 -!- Deewiant has joined.
02:17:47 -!- drlemon has joined.
02:44:51 -!- centrinia has quit (Ping timeout: 255 seconds).
02:54:58 <zzo38> Why does this program crash when "i" or "i-" or "i_" is specified but not "i-_" and "i_-"?
02:55:00 <zzo38> http://sprunge.us/iedA
02:57:35 <PixelToast> zzo38, i dunno but i made you http://i.imgur.com/hnRkv1R.png
03:20:19 <vanila> would that be logical and
03:26:54 <newsham> 2047 = 2^11 - 1, a fine bitmask.
03:27:06 -!- vanila has quit (Quit: Leaving).
03:41:43 <zzo38> It is bitwise, but I don't expect that would explain it crashing?
03:43:54 <zzo38> O nevermind I found the mistake.
03:52:23 -!- password2 has joined.
03:56:16 -!- nys has quit (Quit: quit).
04:07:40 -!- TodPunk has quit (Read error: Connection reset by peer).
04:08:05 -!- TodPunk has joined.
04:46:59 <Sgeo> Is it just me or does Nomyx have a lot of infrastructure that is not rules?
04:49:03 <PixelToast> Sgeo, i dunno but i made you http://ptoast.tk/logo/SGEO.png
04:50:55 <Sgeo> I thought you were a bot
04:51:31 <Sgeo> Still think you're maybe running a script
04:53:12 <PixelToast> the logo thing isnt though, i just got bored and generated logos for you
04:57:50 -!- Parf has joined.
04:59:38 -!- Parf has left.
04:59:47 <elliott> http://ptoast.tk/logo/PENIS.png ok.
05:03:39 <Sgeo> Wait what? There doesn't seem to be a script there, QNTM didn't work
05:04:08 <Sgeo> Oh there's a listing of all files and I can only assume PENIS was there for some reason
05:04:57 <PixelToast> elliott, my bot generates the logos, and my friends like to mess with eachother
05:08:17 <PixelToast> this should work http://i.imgur.com/jvdKyAi.png
05:12:07 <Sgeo> All the YouTube spammers seem to have decided that my name is Alex. I'm not sure why.
05:12:33 <Sgeo> "Hey Alex this is the pretty at the restaurant!"
05:12:42 <Sgeo> I... who calls themselves 'the pretty'?
05:24:26 -!- AndoDaan_ has joined.
05:26:56 -!- AndoDaan has quit (Ping timeout: 245 seconds).
05:30:10 -!- Sgeo has quit (Read error: Connection reset by peer).
05:30:24 -!- Sgeo has joined.
05:33:14 <int-e> @tell oerjan I think the 62 characters "prime numbers" solution relied on n+k-patterns. (meaning, I have a 62 characters version that works with n+k-patterns). The timing is right; ghc accepted them before 7.0, and 7.0.1 was released in November 2010.
05:34:10 -!- centrinia has joined.
05:59:24 <int-e> @tell oerjan and btw I've browsed previous solutions a bit; there doesn't seem to be a magical primality test besides the Fermat one.
06:00:09 -!- password2 has quit (Ping timeout: 255 seconds).
06:02:01 -!- password2 has joined.
06:07:22 -!- password2 has quit (Ping timeout: 265 seconds).
06:17:31 -!- contrapumpkin has joined.
06:18:58 -!- copumpkin has quit (*.net *.split).
06:20:14 -!- MDude has changed nick to MDream.
06:31:16 -!- AndoDaan has joined.
06:33:54 -!- AndoDaan_ has quit (Ping timeout: 256 seconds).
06:57:42 -!- shikhin has joined.
07:07:35 <zzo38> Why are some SQL implementations not supporting triggers on views? I find it to be a very useful feature.
07:12:52 <int-e> sounds tricky to implement.
07:20:29 -!- contrapumpkin has changed nick to copumpkin.
07:20:44 <int-e> I guess it's easy enough for projections, managable for views that just filter rows of a single table by some not-so-clever where clause, and gets exceedingly complicated if views are defined by arbitrary select statements. how do you explain which cases will work and which won't?
07:22:06 -!- MoALTz has quit (Quit: Leaving).
07:24:40 <zzo38> int-e: Well, if it is INSTEAD OF INSERT, then it is easy. For INSTEAD OF UPDATE and INSTEAD OF DELETE, the implementation can internally do a SELECT on it and call the triggers according to the ones that match the WHERE clauses of the UPDATE and DELETE statements. (Triggers other than INSTEAD OF may be more complicated for views, but I don't need them anyways, and SQLite doesn't implement them.)
07:28:46 <zzo38> So I do not quite understand everything you are meaning.
07:30:19 <int-e> I see. So you do not want something that triggers when the underlying tables are changed; instead, you want to translate updates on the view into updates on the underlying tables. That sounds quite a bit less scary.
07:31:34 <zzo38> I like the way SQLite does it: Doing an INSERT, UPDATE, or DELETE on a view only calls all of the applicable attached triggers and does nothing else (if there are no triggers of the correct type, it is an error).
07:32:24 <zzo38> So it won't automatically know how to write to the underlying table and stuff like that; you have to put it in yourself if you want it.
07:33:43 <zzo38> The INSTEAD OF keyword indicates its working like this.
07:33:54 <int-e> I did not consider "instead of" triggers at all. So we were talking cross purposes.
07:34:24 <zzo38> (If you want it to trigger when the underlying tables are changed, you can put triggers on the tables themselves. Tables in SQLite support BEFORE and AFTER triggers; not INSTEAD OF. Views support only INSTEAD OF; not BEFORE and AFTER.)
07:34:39 <int-e> (nor did I consider applying updates to a view rather than tables)
07:45:17 -!- shikhout has joined.
07:48:23 -!- shikhin has quit (Ping timeout: 265 seconds).
07:53:29 -!- PixelToast has changed nick to ^v.
07:58:12 -!- AndoDaan_ has joined.
07:58:48 <zzo38> I find that I rarely use triggers other than INSTEAD OF INSERT, although they are sometimes useful.
08:00:26 -!- AndoDaan has quit (Ping timeout: 244 seconds).
08:36:22 -!- AndoDaan has joined.
08:38:00 -!- AndoDaan_ has quit (Ping timeout: 256 seconds).
08:48:11 <zzo38> Do you use SQL sometimes, and do you use views and triggers often?
08:49:36 <mroman> prime substrings are substrings that represent primes?
08:50:09 <mroman> !blsq 2{"33"jCO}GO\[ri
08:50:09 <blsqbot> Ain't nobody got time fo' dat!
08:50:14 <mroman> !blsq 2{"33"jCO}GO\[)ri
08:50:18 <mroman> !blsq 2{"33"jCO}GO\[ri
08:50:32 <mroman> !blsq 2{"33"jCO}GO\[ri{fCL[2==}m[
08:50:39 <mroman> !blsq 2{"33"jCO}GO\[ri{fCL[}m[
08:50:46 <mroman> !blsq 2{"33"jCO}GO\[ri{fCL[1==}m[
08:50:52 <mroman> !blsq 2{"33"jCO}GO\[ri{fCL[1==Sh}m[\[
08:51:08 <mroman> !blsq 5{"37373"jCO}GO\[ri{fCL[1==Sh}m[\[
08:51:46 <mroman> !blsq 5{"37373"jCO}GO\[ri{fCU_}m[\[
08:51:46 <blsqbot> {1 1 1 1 1 1 1 1 1 1 1 1 1 1 1}
08:53:01 <mroman> !blsq 5{"37373"jCO}GO\[ri{fC[-z?Sh}m[\[
08:53:18 <mroman> fizzie: Do you use fC[-z? as a prime check?
08:55:41 <fizzie> I used that originally, but working around zero cost more than using fcL[2== instead (which deals with zero properly).
08:55:50 <blsqbot> That line gave me an error
08:56:15 <fizzie> Well, "properly" is a matter of opinion, but suitably-for-this-purpose anyway.
08:56:26 <b_jonas> what? isn't there a bulit-in prime check in blsq?
08:57:13 <fizzie> (0fC gives a "divide by zero" error.)
08:58:31 <mroman> b_jonas: nope there isn't
08:59:15 <mroman> fc is horribly slower than fC
08:59:30 <mroman> I guess 0fC should return {0} or something
09:00:03 <mroman> I'll add a prime check built-in in 1.7.4
09:00:21 <mroman> that uses trial divisions for small integers and miller rabin for larger ones
09:00:30 <fizzie> I also tried Jfcpd== but it's no shorter than fcL[2== and fails for 1.
09:01:13 <fizzie> It works for zero, due to {}pd being 1.
09:01:36 <mroman> fizzie: I defined {}pd as 1 because math told to do so
09:01:52 <blsqbot> ERROR: Burlesque: (r[) Empty list!
09:02:15 <mroman> nah that won't help either :)
09:02:38 <mroman> b_jonas: theres factor and prime-factors
09:03:06 <blsqbot> {2 3 4 5 7 8 9 11 13 16 17 19 23 25 27 29 31 32}
09:03:07 <b_jonas> mroman: and one for divisors too?
09:03:25 <blsqbot> {2 3 4 5 7 8 9 11 13 16 17 19 23 25 27 29 31 32 37 41 43 47 49 53 59 61 64 67 71
09:03:50 <b_jonas> list of positive divisors of a number
09:03:57 <mroman> that's what factors does
09:04:20 <blsqbot> {1 2 3 4 6 8 9 12 16 18 24 36 48 72 144}
09:04:33 <mroman> @oeis 23,25,27,29,31,32,37,41,43
09:04:36 <lambdabot> Powers of primes. Alternatively, 1 and the prime powers (p^k, p prime, k >= ...
09:04:59 <blsqbot> {{2} {3} {2 2} {5} {7} {2 2 2} {3 3} {11} {13} {2 2 2 2} {17} {19} {23} {5 5} {3
09:05:32 <j-bot> b_jonas: 144 144 144 144 144 144 144 144 144 144 144 144 144 144 144
09:06:37 <j-bot> b_jonas: 1 2 3 4 6 8 9 12 16 18 24 36 48 72 144
09:07:57 <mroman> that looks unreadable as hell.
09:08:15 <j-bot> mroman: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 12...
09:08:21 <j-bot> mroman: |syntax error
09:08:25 <j-bot> mroman: |syntax error
09:08:37 <mroman> You got me. I don't know J.
09:09:52 <mroman> 100ro{fCsm}f[ is just 1..100, calculate prime factors and filter for lists where all elements are the same
09:11:17 <blsqbot> {1 1 1 0 1 1 1 0 0 1 1 0 1 1 1 0 1 0 1 0 1 1 1 0 0 1 0 0 1 1 1 0 1 1 1 0 1 1 1 0
09:11:23 <blsqbot> {1 2 3 5 6 7 10 11 13 14 15 17 19 21 22 23 26 29 30 31 33 34 35 37 38 39 41 42 4
09:12:03 <mroman> @oeis 7,10,11,13,14,15,17,19,21,22
09:12:07 <lambdabot> Squarefree numbers (or square-free numbers): numbers that are not divisible ...
09:12:59 <mroman> there should be FO and FZ like GO and GZ
09:13:14 <mroman> 100{fCU_}FO instead of 100ro{fCU_}f[
09:14:08 <mroman> sometimes you can workaround the 0 by doing
09:14:36 <mroman> i.e. instead of 100rz{...}f[ -> 100ro{...}f[0
09:15:31 <fizzie> I guess, but here it's the individual substrings that are occasionally 0.
09:16:59 <fizzie> Since a 0 is what I need as the output for 0, what I did was J{...}if which is not too bad, but still 5B.
09:18:45 <AndoDaan> I worked so hard to get J{}if out of my first solution... and here you have it, and your code is still 5B shorter
09:19:14 <fizzie> AndoDaan: I mean, I had J{}if before; I don't have it any more.
09:19:14 <mroman> fizzie: Your recommendation for 0fC is what?
09:20:07 <blsqbot> Ain't nobody got time fo' dat!
09:20:20 <fizzie> mroman: 1fC seems to be {}, so maybe 0fC could be too. But I don't know.
09:20:39 <mroman> yeah. {} is probably best
09:20:49 <mroman> fc for negative numbers should contain -1
09:20:59 <AndoDaan> 0fC gives a dived by zero error. i think.
09:22:33 <mroman> so -8fc should probably be {-1 -2 -4 -8 1 2 4 8}?
09:23:19 <blsqbot> ERROR: Unknown command: (ng)!
09:23:36 -!- centrinia has quit (Ping timeout: 245 seconds).
09:24:21 <fizzie> Couldn't you use the same logic to argue that 8fc should be that too?
09:24:57 <mroman> but that wouldn't be what a Burlesque-user would expect it to do :D
09:25:10 <mroman> I don't know what a Burlesque-user expects -8fc to be
09:25:11 -!- shikhout has changed nick to shikhin.
09:25:30 <AndoDaan> mroman: I was thinking about a command that might be helpful. you have z?, which is useful in filtering false results. So i thought a o?, is one?, could come in handy.
09:25:58 <mroman> which isn't exactly "is one"
09:26:14 <mroman> !blsq {"a" "" "bc" "" "d"}:z?
09:26:17 <mroman> !blsq {"a" "" "bc" "" "d"}:nz
09:26:39 <mroman> !blsq {1 0 1 0 0 1}{}f[
09:27:09 <mroman> AndoDaan: by "is one" you mean "integer 1"?
09:27:45 <AndoDaan> i know 1== is only three char, but for it to work with :
09:27:59 <AndoDaan> it has to be a singly command, right?
09:28:24 <AndoDaan> unless i overlooked something very useful.
09:28:42 <mroman> yes. : only takes a single command
09:30:12 <fizzie> Do ){...} and :{...} mean anything? If not, you could use them as one-byte-saving shorthand for {...}m[ and {...}f[. Though it's a bit silly.
09:30:55 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:32:01 <blsqbot> {{+. ap} 1 {+. ap} 2 {+. ap} 3}
09:32:26 <blsqbot> {{+. +]} 1 {+. +]} 2 {+. +]} 3}
09:32:37 <blsqbot> {{bx +.} 1 {bx +.} 2 {bx +.} 3}
09:33:21 <fizzie> Oh, I guess it does have a meaning.
09:33:24 <mroman> fizzie: yes @ ){} and :{}
09:33:49 <fizzie> Right, so ){...} is just {{...}}m[.
09:34:13 <mroman> fizzie: but I can add m{...} and f{...} instead of {}m[ or {}f[
09:34:27 <blsqbot> {{) +.} 1 {) +.} 2 {) +.} 3}
09:34:52 <blsqbot> {{pP +.} 1 {pP +.} 2 {pP +.} 3}
09:36:23 <AndoDaan> is there anything that can shorten ]muN ?
09:41:06 <fizzie> AndoDaan: You can turn something like ln{...}]muN into {...Sh}WL at least. There are so many commands, maybe there's some way of also avoiding the Sh.
09:45:06 <AndoDaan> see dammit. I knew I was messing up with ln everytime.
09:47:20 <b_jonas> mroman: what is the command for computing the exp of a floating point number in blsq?
09:50:11 <b_jonas> mroman: also, what's the command for getting all infixes of a particular length of a block, given the length? and what's the command for getting non-overlapping infixes of a particular length, except the last one may be shorter?
09:51:07 <b_jonas> mroman: and what's the command for getting all prefixes of a block, or all suffixes?
09:52:51 <blsqbot> ERROR: Burlesque: (z[) Invalid arguments!
09:53:31 <blsqbot> {{'m 'o} {'o 'n} {'n 's} {'s 't} {'t 'e} {'e 'r}}
10:03:40 <mroman> b_jonas: there's su (substrings)
10:03:54 <mroman> and 1.7.4 has inits and tails
10:04:00 <mroman> (1.7.3 doesn't have that yet)
10:04:20 <blsqbot> ERROR: Burlesque: (**) Invalid arguments!
10:04:24 <blsqbot> ERROR: Unknown command: (.^)!
10:05:41 <blsqbot> {1.0 6.5808859910179205 19.812990745274643 43.30806042677592 79.43235916621322 1
10:05:50 <blsqbot> {2.718281828459045 7.3890560989306495 20.085536923187664 54.59815003314423 148.4
10:06:13 <blsqbot> {"2.718" "7.389" "20.086" "54.598" "148.413" "403.429" "1096.633" "2980.958" "81
10:06:50 <blsqbot> {"m" "n" "o" "s" "t" "mo" "ns" "on" "st" "mon" "nst" "ons" "mons" "onst" "monst"
10:06:59 <b_jonas> ok, but how do I get only the 3-long substrings,
10:07:25 <b_jonas> ok, and how about breaking to non-overlapping substrings?
10:08:09 <b_jonas> oh, it might be right there
10:08:23 <b_jonas> !blsq "non-overlapping infixes"3co
10:08:23 <blsqbot> {"non" "-ov" "erl" "app" "ing" " in" "fix" "es"}
10:08:34 <b_jonas> I should have searched for "chunk"
10:09:01 <mroman> I thought you meant count occurrences of a substring without overlap
10:10:26 <mroman> but that would be a nice builtin!
10:10:35 <mroman> oc - occurences, OC - non-overlapping occurences
10:11:28 <b_jonas> !blsq {0 0 0 0 0 0 0 1 0 1 1 0 1}{}fi
10:11:37 <b_jonas> [ 0 0 0 0 0 0 0 1 0 1 1 0 1 i.1
10:11:50 <b_jonas> !blsq {0 0 0 0 0 0 0 0 0 0 0 0 0}{}fi
10:13:49 <b_jonas> !blsq {"hello" "world"}{XX}m[tp
10:13:49 <blsqbot> {{'h 'w} {'e 'o} {'l 'r} {'l 'l} {'o 'd}}
10:14:23 <b_jonas> !blsq {"hello" "world"}{XX}m[tp{\[}m[
10:14:24 <blsqbot> {"hw" "eo" "lr" "ll" "od"}
10:14:43 <b_jonas> !blsq {"hello" "world"}{XX}m[tp{}\m
10:14:43 <blsqbot> {'h 'w 'e 'o 'l 'r 'l 'l 'o 'd}
10:14:48 <b_jonas> !blsq {"hello" "world"}{XX}m[tp{\[}m[
10:14:48 <blsqbot> {"hw" "eo" "lr" "ll" "od"}
10:15:09 <mroman> !blsq {"hello" "world"})XXtp)\[
10:15:09 <blsqbot> {"hw" "eo" "lr" "ll" "od"}
10:15:27 <mroman> !blsq "hello""world"z[)\[
10:15:27 <blsqbot> {"hw" "eo" "lr" "ll" "od"}
10:15:44 <mroman> ) is a prefix for maps
10:15:58 <mroman> )ab = {ab}m[, )5 = {5}m[ and so forth.
10:18:24 <mroman> () "quotes" a command so it is pushed to the stack rather than being executed
10:18:48 <blsqbot> ERROR: Burlesque: (e!) Invalid arguments!
10:19:06 <mroman> nobody probably needs that but it's there :D
10:19:59 <mroman> ((9)) is shorter than "(9)"Q fwiw
10:22:25 <b_jonas> ok... that's the part I'm not sure I want to understand now
10:25:01 <mroman> meh. it's pretty simple
10:25:16 <mroman> ( ) just wraps something in a "Quoted"
10:25:31 <mroman> and if the interpreter sees a "Quoted" it unwraps it and pushes the thing inside to the stack
10:26:35 <mroman> (.+ produces an error because there are no numbers on the stack)
10:27:38 -!- oerjan has joined.
10:32:32 <mroman> What happens if I clone a repository from github
10:32:45 <mroman> make some committs, merge those committs into my master branch
10:32:58 <mroman> and then someone makes committs to the repository on github I cloned from
10:33:27 <mroman> can I just pull those committs?
10:33:44 <mroman> (technically I have to remotes)
10:34:28 <mroman> my local repository -> my repository on bitbucket and the official repository on github
11:09:21 -!- AndoDaan has quit (Ping timeout: 258 seconds).
11:11:14 <lambdabot> int-e said 5h 37m 59s ago: I think the 62 characters "prime numbers" solution relied on n+k-patterns. (meaning, I have a 62 characters version that works with n+k-patterns). The timing is right; ghc accepted them before 7.0, and 7.0.1 was released in November 2010.
11:11:14 <lambdabot> int-e said 5h 11m 49s ago: and btw I've browsed previous solutions a bit; there doesn't seem to be a magical primality test besides the Fermat one.
11:11:50 <oerjan> which means you must have beat me on something _else_...
11:12:12 <oerjan> or possibly my naive prime test is too naive...
11:13:51 -!- AndoDaan has joined.
11:20:13 -!- impomatic_ has joined.
11:23:18 <oerjan> hm shortening that x<2 test is exactly what n+k-patterns would be good at, isn't it.
11:52:30 -!- centrinia has joined.
12:03:56 -!- AndoDaan_ has joined.
12:06:00 -!- AndoDaan has quit (Ping timeout: 255 seconds).
12:20:57 <oerjan> wait i didn't finish reading the logs yesterday
12:22:26 -!- sebbu2 has joined.
12:22:26 -!- sebbu2 has quit (Changing host).
12:22:26 -!- sebbu2 has joined.
12:22:58 -!- sebbu has quit (Ping timeout: 256 seconds).
12:32:43 -!- sebbu2 has changed nick to sebbu.
12:56:44 -!- centrinia has quit (Ping timeout: 264 seconds).
13:02:04 -!- monotone has quit (Ping timeout: 258 seconds).
13:13:24 -!- monotone has joined.
13:45:56 -!- shikhout has joined.
13:46:53 -!- AndoDaan_ has quit (Ping timeout: 272 seconds).
13:49:32 -!- shikhin has quit (Ping timeout: 264 seconds).
14:10:25 -!- ^v has quit (Ping timeout: 240 seconds).
14:22:09 -!- shikhout has changed nick to shikhin.
14:27:20 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=40774&oldid=40424 * 67.78.57.11 * (+29) /* Derivative Ideas */
14:32:39 -!- vanila has joined.
14:42:43 -!- hello has joined.
14:59:14 -!- `^_^v has joined.
15:05:57 -!- drdanmaku has joined.
15:13:50 -!- hello has left ("Leaving").
15:35:33 -!- Sprocklem has joined.
15:44:44 -!- oerjan has quit (Quit: leaving).
15:56:21 -!- AndoDaan has joined.
15:56:43 -!- mihow has joined.
16:04:27 -!- perrier has quit (Read error: Connection reset by peer).
16:10:58 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=40775&oldid=40774 * 67.78.57.11 * (+141) /* Joke/Silly Ideas */
16:14:20 -!- hjulle has quit (Ping timeout: 264 seconds).
16:22:50 -!- ^v has joined.
16:51:54 -!- password2 has joined.
16:52:35 -!- password2 has quit (Max SendQ exceeded).
16:53:08 -!- password2 has joined.
17:05:17 -!- Sprocklem has quit (Ping timeout: 245 seconds).
17:41:54 -!- password2 has quit (Ping timeout: 258 seconds).
17:55:17 -!- AnotherTest has joined.
17:55:38 -!- password2 has joined.
18:05:44 -!- esowiki has joined.
18:05:48 -!- esowiki has joined.
18:05:49 -!- esowiki has joined.
18:06:24 -!- esowiki has joined.
18:06:28 -!- esowiki has joined.
18:06:29 -!- esowiki has joined.
18:07:04 -!- esowiki has joined.
18:07:08 -!- esowiki has joined.
18:07:09 -!- esowiki has joined.
18:07:44 -!- esowiki has joined.
18:07:48 -!- esowiki has joined.
18:07:49 -!- esowiki has joined.
18:08:24 -!- esowiki has joined.
18:08:28 -!- esowiki has joined.
18:08:29 -!- esowiki has joined.
18:09:28 -!- esowiki has joined.
18:09:32 -!- esowiki has joined.
18:09:33 -!- esowiki has joined.
18:10:20 -!- esowiki has joined.
18:10:22 -!- glogbot has joined.
18:10:24 -!- esowiki has joined.
18:10:25 -!- esowiki has joined.
18:12:04 -!- FireFly has joined.
18:33:50 <HackEgo> [wiki] [[Element]] N http://esolangs.org/w/index.php?oldid=40776 * 67.78.57.11 * (+2753) Created page with "'''Element''' is a simple language by [http://codegolf.stackexchange.com/users/2867/phiNotPi phiNotPi]. It is supposedly designed as "very compact and human-readable". Each in..."
19:13:52 -!- tiara- has joined.
19:21:19 -!- tswett has joined.
19:22:11 <tswett> Someone please create a type theory that only describes functions whose output length is at most a polynomial function of the input length.
19:22:58 <tswett> Such a theory would have the neat property that you can't prove that the unary naturals are isomorphic to the binary naturals, because the function from the binary naturals to the unary naturals grows too fast.
19:23:28 <tswett> Likewise, exponentiation can't be defined as a function unat -> unat -> unat or bnat -> bnat -> bnat; the best you can do is bnat -> unat -> bnat.
19:23:57 <tswett> Sounds ultrafinitistic, doesn't it?
19:24:57 -!- tiara- has left ("Salir").
19:27:18 <b_jonas> you'll have to ask people who are good in algebraic logic.
19:28:16 -!- AndoDaan has quit (Ping timeout: 265 seconds).
19:28:32 <vanila> 11:24:49 <tswett> Someone please create a type theory that only describes functions whose output length is at most a polynomial function of the input length.
19:28:36 <vanila> isnt that simple typed lambda calculus/
19:29:24 <vanila> https://archive.org/stream/arxiv-cs0701022/cs0701022_djvu.txt
19:34:53 -!- Sprocklem has joined.
19:45:26 <tswett> vanila: good question.
19:45:50 -!- shikhout has joined.
19:47:03 -!- MDream has changed nick to MDude.
19:49:02 -!- shikhin has quit (Ping timeout: 250 seconds).
19:49:08 <tswett> Can the STLC represent the modulo function?
19:49:59 <b_jonas> tswett: with what encoding of the numbers?
19:51:04 -!- shikhout has changed nick to shikhin.
19:54:25 <tswett> I guess the STLC has a bunch of different kinds of Church numerals.
19:56:45 -!- AndoDaan has joined.
19:58:54 -!- vifino has quit (Remote host closed the connection).
20:07:22 -!- nortti has changed nick to lawspeaker.
20:08:17 -!- lawspeaker has changed nick to nortti.
20:10:45 -!- AndoDaan_ has joined.
20:14:14 -!- AndoDaan has quit (Ping timeout: 265 seconds).
20:23:01 <int-e> vanila: it's definitely not the simply typed lambda calculus. the extended polynomials arise from restricting to input Church numerals to a single type N(*) where N(t)=(t -> t) -> t -> t and * is a base type. If one allows t to vary, one gets larger growth easily. <n> <m> with <n> :: N(* -> *) and <m> :: N(*) grows exponentially, for example. (It reduces to <n^m> : N(*))
20:24:59 <int-e> But thanks, now I finally know where people get that claim.
20:26:37 <int-e> (I've seen the claim that simply typed lambda calculus corresponds to polynomially bounded functions several times and never figured out how such an obviously wrong idea could become so widely spread.)
20:30:46 <tswett> Does there exist a type t such that exponentiation can be defined as a function (C t -> C t) -> C t, where C t = (t -> t) -> t -> t?
20:32:32 <int-e> I don't understand that type.
20:34:12 <int-e> I mean, f :: (C t -> C t) -> C t has one argument of type C t -> C t. Now, ok, that could be a Church Numeral, but I expected a second argument somewhere?
20:34:56 <tswett> I meant C t -> C t -> C t.
20:35:46 -!- password2 has quit (Ping timeout: 250 seconds).
20:36:16 <int-e> I don't know, though it would surprise me. I don't even know the theory behind the C * result.
20:48:49 -!- ^v has quit (Quit: Leaving).
20:48:51 -!- password2 has joined.
20:49:59 -!- vifino has joined.
20:58:46 -!- Sprocklem has quit (Quit: Lost terminal).
21:01:58 -!- ^v has joined.
21:12:59 -!- password2 has quit (Ping timeout: 260 seconds).
21:17:32 -!- AndoDaan has joined.
21:18:02 -!- AndoDaan_ has quit (Ping timeout: 265 seconds).
21:19:22 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=40777&oldid=40762 * 216.207.42.140 * (+11) Added Ante
21:25:48 -!- password2 has joined.
21:30:46 <zzo38> Are there any leap seconds in future?
21:30:57 <zzo38> If so, what are they? Wikipedia only lists up to now.
21:32:22 <vanila> the leap second community decides when they occur
21:33:37 <vanila> IERS http://www.iers.org/nn_10828/IERS/EN/Service/Glossary/leapSecond.html
21:33:58 <fizzie> There's a proposal going around to dispense with them, I haven't heard any news about how that's going.
21:34:41 <b_jonas> zzo38: the can't be determined long in advance. they're decided like a year or two before.
21:35:00 -!- yukko has joined.
21:35:08 <b_jonas> there's a rule for them but it depends on astronomical measurements of earth's position
21:35:32 <zzo38> But, there is software to measure the Earth's position in advance.
21:36:40 <fizzie> I don't think the rotation is predictable enough, with that amount of accuracy, since it's so wobbly.
21:38:49 <fizzie> I mean, look at that thing: http://upload.wikimedia.org/wikipedia/commons/5/5b/Deviation_of_day_length_from_SI_day.svg
21:42:26 <HackEgo> [wiki] [[Ante]] N http://esolangs.org/w/index.php?oldid=40778 * 216.207.42.140 * (+2116) Ante programming language
21:45:21 <zzo38> I know that Swiss Ephemeris requires an external leap second table, in order to perform accurate calculations.
21:46:59 -!- centrinia has joined.
22:03:08 -!- password2 has quit (Ping timeout: 244 seconds).
22:15:25 -!- vifino has quit (Ping timeout: 240 seconds).
22:15:45 -!- password2 has joined.
22:16:57 <zzo38> I prefer to use BC/AD notations for abbreviations rather than using BCE/CE, although when writing them out in long I will generally prefer to say "common era". (Terms like "before Christ" aren't even accurate, actually.)
22:27:49 -!- vifino has joined.
22:32:14 -!- AnotherTest has quit (Remote host closed the connection).
22:38:26 <Taneb> Right, I have 4 weeks to prepare a half hour talk on the lambda calculus
22:41:32 <^v> i like your name
22:41:32 <^v> http://ptoast.tk/logo/DIcqa.png
22:41:52 <Bike> "Have you ever wanted a system of computation that can be mostly explained in ten minutes and isn't based on ticker tape? No? Well, fuck you then"
22:45:50 -!- boily has joined.
22:46:34 -!- Phantom_Hoover has joined.
22:50:26 -!- oerjan has joined.
22:51:22 -!- boily has quit (Quit: BROKEN CHICKEN).
22:56:34 -!- boily has joined.
23:10:25 -!- `^_^v has quit (Ping timeout: 240 seconds).
23:13:53 -!- centrinia has quit (Ping timeout: 255 seconds).
23:28:29 -!- mihow has quit (Quit: mihow).
23:30:54 -!- AndoDaan_ has joined.
23:31:23 -!- AndoDaan has quit (Ping timeout: 265 seconds).
23:36:03 <FireFly> Bike: might be hard to stretch that into 30 minutes
23:38:30 <fizzie> takeFor (30 minutes) $ cycle "Have you ever [...]."
23:48:19 -!- vifino has quit (Ping timeout: 244 seconds).
23:53:26 <elliott> that would be good performance art
23:53:46 <elliott> fizzie: so I bet this new job of yours is in hexham, right
23:55:23 <fizzie> I think I mentioned it was in London. (Also I *still* don't quite have the contract signed, which is slightly unnerving.)
23:57:47 -!- FreeFull has quit (Ping timeout: 245 seconds).
00:02:33 <oerjan> <tswett> Someone please create a type theory that only describes functions whose output length is at most a polynomial function of the input length. <-- there are type theories capturing PTIME and (iirc) LOGSPACE, search for bellantoni-cook
00:02:42 <oerjan> pretty sure i've mentioned this before
00:03:00 -!- adu has joined.
00:03:44 <zzo38> I noticed that in MinGW, time_t is 32-bits and __time64_t is 64-bits. Is there a good way to get 64-bit UNIX timestamps regardless of the system?
00:06:02 <fizzie> elliott: Also also, our stuff (including those discussed com-puters) will be shipped probably somewhen in February, since we need to find some permanent place to live first.
00:06:10 -!- centrinia has joined.
00:06:58 <elliott> it's a good thing Turing was curious about finding a way to pute coms, or the world today would be so different.
00:07:13 <elliott> fizzie: oh, right, you did mention london though. thanks for ruining my joke.
00:07:29 <elliott> I suppose I could argue that hexham is just a really, really far out suburb of london.
00:08:59 <Sgeo> http://www.dose.com/lists/3339/19-iPhone-Tricks-And-Tips-Apple-Doesn-t-Want-You-To-Know-7-Just-Made-My-Life
00:09:22 <Sgeo> Isn't having 'hidden'/undiscoverable features exactly antithetical to good UI design?
00:11:09 <fizzie> elliott: We've been talking about visiting Hexham (just, you know, for general tourism), you've made it sound so exciting.
00:11:38 <elliott> fizzie: I'm... really not sure I'd recommend that.
00:11:52 <Sgeo> I've been thinking of visiting Norway. Or Alaska. Or someplace, far up north. Even though I hate the cold
00:12:23 <elliott> have you considered the Lake District or something instead? :p
00:12:58 <Sgeo> I could take a vacation there for a few years hoping to see a light show
00:13:15 <fizzie> We went to Lofoten (in Norway) one Easter (last? the one before?) and it was a nice trip.
00:13:22 -!- hjulle has joined.
00:13:26 <fizzie> It's also not especially cold there.
00:13:40 * Sgeo is looking to see the northern lights
00:14:06 <boily> Norway is nice. it has oerjans.
00:14:24 <boily> Sgeo: surprising UI features are evil.
00:14:52 <fizzie> Sgeo: http://www.dpreview.com/articles/0886868715/mountain-magic-shooting-in-the-lofoten-islands <- that's pretty much from where we were.
00:17:21 <Sgeo> "The Lofoten Islands are a stormy destination, to put it nicely. On average, I generally estimate there to be one clear day/night per week. So if you only have a single week in hopes of seeing the Northern Lights, you are taking a chance with the weather cooperating. In this short time period you’re much better off heading east to Sweden and a place like Abisko, which enjoys many more clear winter nights than Lofoten."
00:17:46 <fizzie> Yes, it might not be the best place for that particular goal.
00:17:51 <fizzie> Don't quite remember if we saw any auroras.
00:18:22 <oerjan> coastal climates do tend to have clouds.
00:18:31 <Sgeo> I should figure out if I can vote
00:19:21 * Sgeo is guessing not... what counts as 'moving' in election law?
00:19:51 <oerjan> i hear election laws in the US vary by state
00:20:46 <oerjan> and in chicago you don't even need to be alive to vote
00:23:21 <oerjan> and that there's a recent uproar because some places have started require actually showing id to vote, which it is claimed discriminates against african-americans.
00:23:42 <oerjan> (it made more sense in context)
00:24:01 <elliott> that kind of thing also tends to be a pain for married women, right
00:24:21 <oerjan> ...i don't think i get the reference
00:24:27 <elliott> since surname changes that people don't necessarily bother to propagate to all their legal documents.
00:24:28 <boily> we had interesting cases of cats and potted plants voting in some recent elections.
00:25:13 <elliott> (well, married people in general, but the most common case)
00:26:27 <oerjan> in norway it's really pretty simple, there's a national register of all citizens and when you vote you're crossed off on the list in your municipality. also you must show generally show id, i'm not sure if you're still allowed not to if the vote taker knows you personally.
00:27:21 <fizzie> AIUI, "honeymoon" trips are often complicated by passport-and-surname-related irregularities.
00:27:36 <oerjan> as in, you don't register to vote, the government sends you a note to remind you if you're allowed. it also simplifies the process if you bring that note, but that's not mandatory.
00:28:53 <oerjan> also if you're paranoid the local list of voters is displayed in public, so you can go downtown to check if you're in the list.
00:29:13 <oerjan> (i suppose if you're paranoid you may or may not think that's a good thing.)
00:29:15 <elliott> clearly we need mumble mumble PGP keys mumble mumble mumble secret voting mumble cryptography mumble
00:30:07 <boily> I'm all for rampant cryptography and privacy, but GPG is borken beyond all fungottable repair.
00:30:08 <fungot> boily: " i ca'n't see anything at present. all in good time." " all fnord tell lies."
00:30:26 <oerjan> also, when foreign observers observe our votes they complain that the process is too trusting of people, but conclude that it probably works well enough in practice
00:32:43 <boily> it's a Klingon word. (at least I think so.)
00:32:59 <Phantom_Hoover> i remember in the referendum, you just said who you were on the electoral register
00:33:21 <Phantom_Hoover> like there wasn't anything to keep me from going to a different polling station and voting again as someone else
00:33:38 <oerjan> Phantom_Hoover: did you get to vote? i thought you'd moved outside scotland.
00:35:18 <Phantom_Hoover> also it's pretty normal to keep your official residence the same because of how volatile university housing is
00:37:12 -!- Guest48077 has joined.
00:38:15 -!- Guest48077 has left.
00:38:49 <zzo38> Why did Wikipedia break?
00:40:11 <oerjan> darn we didn't get to ask how they found us
00:40:26 <oerjan> or to properly `bienvenido them
00:40:55 <oerjan> do any other channels get these canaima users?
00:41:03 <HackEgo> AndoDaan_: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.)
00:41:26 <oerjan> AndoDaan_: we get so many bewildered venezuelans that we had to make that
00:41:44 <fizzie> oerjan: None of mine, at least.
00:41:49 <boily> colombians too, mind you.
00:42:09 <oerjan> AndoDaan_: that's what we want to ask them. well, they seem to use the canaima linux distribution.
00:42:23 <oerjan> so it's _probably_ somewhere in that.
00:43:34 <oerjan> canaima is _mainly_ used in venezuela where it was invented, but presumably also in some neighboring countries.
00:55:32 <HackEgo> [wiki] [[Subleq]] http://esolangs.org/w/index.php?diff=40779&oldid=36583 * 128.100.122.180 * (+288) /* Basic */
00:56:28 <elliott> Bewildered Venezuelans is a good band name
01:03:32 <Sgeo> Turns out I can vote
01:06:02 -!- boily has quit (Quit: CONSTANT CHICKEN).
01:10:34 -!- vyv_ has quit (Ping timeout: 264 seconds).
01:11:53 -!- vyv has joined.
01:14:43 <Sgeo> "McMahon said it is unwise to issue bonds to purchase high-tech equipment that will become obsolete with new technological advances, often within a period of a few years."
01:15:00 <Sgeo> Is it just me, or does even computing equipment remain usable for a few years
01:17:26 <AndoDaan_> I'm on a laptop half a decade old, surfing the internet via a tethered cellphone...
01:18:01 <elliott> obsolete doesn't mean doesn't work
01:18:27 <Sgeo> Heading out to the polls >.>
01:18:55 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
01:38:46 -!- AndoDaan_ has quit (Ping timeout: 272 seconds).
01:45:59 -!- shikhout has joined.
01:47:52 -!- AndoDaan has joined.
01:47:53 <yukko> I think things moved a bit faster in the 90's/early 2000's so "obsolete within a few years" isn't too far off for some eras
01:49:04 -!- shikhin has quit (Ping timeout: 250 seconds).
01:53:22 <elliott> I feel like computer obsolescence was accelerating up to the late 2000s-ish.
01:55:15 <Sgeo> Is what I did any different from voting a straight ticket? I left some blank if my hasty Wikipedia'ing didn't give any information, but the ones I voted for were all the same party
01:56:14 <HackEgo> yukko: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
01:56:50 -!- elliott has set channel mode: -o elliott.
01:57:05 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: selcome: not found
01:59:15 <elliott> (or should that be `selamatpagi)
02:01:17 -!- FreeFull has joined.
02:04:00 <elliott> (thank you, I'm here all week.)
02:04:50 <Sgeo> I don't get it at all
02:30:19 -!- oerjan has quit (Quit: Nite).
02:30:53 <elliott> Sgeo: bad nichijou joke. nichijoke
02:31:10 <Sgeo> Japanese comedy manga?
02:46:36 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: selamatjalan: not found
02:50:24 -!- Vorpal_ has joined.
02:52:53 <Bike> I think Malay?
02:54:23 -!- Vorpal has quit (Ping timeout: 265 seconds).
03:06:45 <zzo38> How to convert between Gregorian dates and UNIX timestamp (without using date/time library functions)?
03:25:08 <tswett> Start by dividing the timestamp by 86400; that's your day number.
03:26:13 <tswett> Converting from date to timestamp is easier, I think.
03:28:27 <tswett> You could just loop through the years starting from 1970, subtracting the appropriate number of days for each year you go through.
03:28:57 <tswett> But then doing the conversion could end up taking several microseconds.
03:32:03 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: rienvenido: not found
03:32:13 <tswett> `run cat `which relcome`
03:32:14 <HackEgo> #!/bin/sh \ welcome "$@" | rainwords
03:32:42 <zzo38> tswett: I already got division by 86400; that might I already did before I have asked
03:33:18 <tswett> `run echo -e '#!/bin/sh\nbienvenido "$@" | rainwords' > /hackenv/bin/rienvenido
03:33:26 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/rienvenido: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/rienvenido: cannot execute: Permission denied
03:33:36 <tswett> `run chmod +x /hackenv/bin/rienvenido
03:33:40 <HackEgo> HackEgo: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki:
03:35:14 <zzo38> (I don't need any dates before 1980, though; I do need to be able to calculate dates much farther into the future, though)
03:35:45 <tswett> You want to get an accurate year number.
03:36:31 <tswett> A 400-year period always contains 146097 days.
03:37:27 <zzo38> Yes, and also month and day. I do know how leap years are working. Leap seconds are irrelevant for UNIX timestamps, although perhaps if the program uses the current time for anything, if the current time is a leap second then it should sleep until it is not a leap second anymore.
03:37:39 <tswett> So you want to take your day number and divide it by the average number of days in a year, which is to say, you want to multiply it by 400 and then divide it by 146097.
03:38:18 <tswett> Which will give you a year number which is accurate to within a couple of days at worst.
03:38:44 <zzo38> Within a couple of days, is not good enough.
03:38:49 <tswett> If the day is close to a year boundary, you can always use your year number to calculate the number of leap days that have happened.
03:39:15 <tswett> And then you can use that number to correct your year number.
03:39:30 <tswett> It seems like this problem ought to be easier than this.
03:39:58 <tswett> Okay, you'll probably need a function that takes a year and returns the number of leap years between 1970 and the end year.
03:41:29 <tswett> By taking the day number and multiplying and dividing, you can come up with an approximate year number. You can use the approximate year number and your leap year counting function to come up with an exact day offset from the beginning of the year.
03:42:07 <tswett> If the day offset is negative, subtract a year and add 365 or 366 to the day offset.
04:03:07 -!- tswett has quit (Ping timeout: 246 seconds).
04:06:34 <zzo38> Is y/4-y/100+y/400-477 correct (if y is an integer type)?
04:07:59 <AndoDaan> Do milleniums influence if it's a leapyear or not?
04:16:16 <zzo38> No, only 4, 100, and 400.
04:20:38 <Jafet> Don't forget to extrapolate leap seconds
04:21:49 <Jafet> That's ok, we're still converting Gregorian.
04:22:08 <Jafet> Maybe Gregor knows something about this.
04:23:33 <lifthrasiir> zzo38: look at http://en.wikipedia.org/wiki/Determination_of_the_day_of_the_week#Implementation-dependent_methods_of_Sakamoto.2C_Lachman.2C_Keith_and_Craver
04:24:06 <lifthrasiir> it is a day-of-the-week function, but without `%7` that can be used as a timestamp conversion (with a different epoch though)
04:28:51 <zzo38> Leap seconds are irrelevant to UNIX time, from what Wikipedia says; you can treat any dates as if there aren't any leap seconds.
04:29:30 <zzo38> lifthrasiir: O, it has the same "y/4-y/100+y/400" as I used.
04:30:57 -!- vanila has quit (Quit: Leaving).
04:31:00 <zzo38> That algorithm isn't actually quite right if you want the full timestamp; it misses many things.
04:31:22 <zzo38> But I think I figured out how to convert from Gregorian to UNIX; it is other way around I wanted, now.
04:31:58 -!- shikhout has quit (Ping timeout: 255 seconds).
04:35:42 <AndoDaan> zzo38: http://ptspts.blogspot.be/2009/11/how-to-convert-unix-timestamp-to-civil.html
04:36:12 <AndoDaan> tested it in lua, and with a little rounding, it looks good.
04:37:12 <AndoDaan> 2014.68364748072.99006568413932.2204460492503e-0154.610833333333336.6539
04:38:03 <AndoDaan> 2014.6836474807 2.9900656841393 2.2204460492503e-01 4.6108333333333 36.65 39
04:39:40 <zzo38> To convert into UNIX timestamps, this is the algorithm I used and it appears to be working: http://sprunge.us/ZTZX
04:43:55 <zzo38> It says that program you link to is only for Ruby, and won't work on other programming language due to rounding negative divisions.
04:44:50 <AndoDaan> ah... no well done for me then.
05:10:33 -!- adu has quit (Quit: adu).
05:31:58 <zzo38> Actually I think I figured it out now.
05:36:41 <Sgeo> Why does YouTube show me a survey asking what ads I've seen recently? Does it not track that information? Or do they want to know what I recall seeing, not what's been presented? (I guess that's rather likely)
05:52:05 -!- MDude has changed nick to MDream.
06:04:27 -!- password2 has quit (Ping timeout: 245 seconds).
06:09:43 <zzo38> AndoDaan: http://sprunge.us/cVGF (it isn't particularly good, though, but it is more than good enough)
06:12:56 <AndoDaan> doesn't return if it's Easter or not... 2/10
06:14:01 <AndoDaan> i kid. seem pretty straight forward.
06:14:48 <zzo38> Yes I know it doesn't say if it is Easter, but that is not relevant here. (I did write a program in TeX to calculate when is Easter, though.)
06:14:53 <AndoDaan> though, i didn't think about the need to index the days of the months.
06:16:28 <AndoDaan> I vaguely remember easter days forming a diamond pattern.
06:16:29 <int-e> https://en.wikipedia.org/wiki/Computus#Gauss_algorithm
06:18:17 <zzo38> The official algorithm used by the Church is a bit complicated but there are ones that are simpler.
06:20:04 <zzo38> Easter calculation in TeX: http://sprunge.us/bWhX
06:20:13 <AndoDaan> seems random to me. they should have just set a day "x-mas" style.
06:21:00 <int-e> the proposal has been made... https://en.wikipedia.org/wiki/Reform_of_the_date_of_Easter
06:21:49 <zzo38> TeX wasn't really designed to calculate when is Easter, but it also wasn't designed to play chess or to interpret BASIC (both of which have been done).
06:23:02 <zzo38> int-e: Another proposal is astronomical method, which is a method I have proposed once.
06:27:05 <zzo38> What I would be interested in is if in a program like Astrolog you could also input queries such as ">> Sun at 0 Aries >> Sun opposite Moon >> Sunday" and have it figure out exactly when that is (and plot a horoscope for that date/time if requested)!
06:28:41 <AndoDaan> hmm. with the earth wobbles and such.
06:29:32 <AndoDaan> apparently nobody has been born under their designated starsign for 3000 years. years
06:30:01 <zzo38> AndoDaan: That isn't quite right. People are confusing signs with constellations having the same (or similar) names.
06:30:47 <zzo38> Signs are all 30 degrees and there are twelve; they are a unit of measurement for ecliptic longitude. Constellations all have different sizes and aren't a measurement of ecliptic longitude or anything like that.
06:31:50 <zzo38> Do you know the "Tropic of Cancer" and "Tropic of Capricorn"? The "Cancer" and "Capricorn" mentioned are the signs, not the constellations. (Also, the constellation is actually called "Capricornus" and not "Capricorn"; the sign is "Capricorn".)
06:33:05 <AndoDaan> i know those lines on the globe. i can see how they relate to zodiac.
06:37:23 <zzo38> Many people don't know that they are related to signs and not constellations. Some astronomers wanted to rename them, but they are just confusing signs with constellations.
06:38:06 <AndoDaan> I certainly was confused - in error - about it.
06:38:24 <zzo38> Well, now you know!
06:38:35 <AndoDaan> I mean i never gave it much thought, but i just assumed.
06:40:32 <AndoDaan> Thanks. :) (i've said "nobody is born under their star sign" a number of times before, arguing about astrology.)
06:41:09 <zzo38> Well, now hopefully you can stop making bad arguments against astrology, and perhaps learn to make better arguments against astrology!!
06:42:26 <AndoDaan> or just quit arguing all together.
06:43:14 <AndoDaan> and realize that I'm as proned to be wrong as anyone else.
06:44:02 <AndoDaan> well, as some portion of anyone else.
06:48:47 <int-e> My favourite argument is that a nurse helping to deliver a baby exerts a greater gravitational force on the baby than those stars (except the Sun)
06:50:16 <AndoDaan> idk, int-e... a lot of people felt 'floaty' when last there was a Super Moon
06:50:32 <int-e> the moon is not a star.
06:50:59 <AndoDaan> so think how much bigger stars on than the Moon!
06:51:13 <int-e> and how much further away
06:51:32 <int-e> the inverse square law is a quite powerful force diminisher
06:51:39 <AndoDaan> bah, inverse square law is overrated
06:52:24 <AndoDaan> but seriously, astrology came before Newton, right?
06:52:38 <zzo38> Yes, and I think even Newton studied it.
06:53:01 <int-e> I don't even doubt that astrology works, among people who believe in it.
06:53:39 <int-e> But that's a matter of psychology.
06:54:01 <zzo38> I have heard (probably said of astrology) that the stars to not compel, but only incline. I would say they only suggest, and even then only because people make it to do so! But you mustn't underestimate the forces of suggestion.
06:54:04 <AndoDaan> But, Astrologer wouldn't attribute whatever influence celstial have to gravity.
06:54:58 <int-e> Yes, if you read your horoscope every day then that will have some effect on your life.
06:55:18 <AndoDaan> Yeah, the best Astrologers, like the best palm readers, are the best cold readers.
06:56:47 <AndoDaan> but then again, it's a certain type of person that would be inclind to read their horoscope every day.
06:56:47 <Sgeo> Is it possible to statically link rustc so I could use it as a library?
06:56:48 <Sgeo> Hmm, I could do something like that with Haskell and GHC, right?
06:56:57 <int-e> > let i=tail.scanl(flip(:))[] in i"abcd">>=i
06:56:59 <lambdabot> ["a","b","ab","c","bc","abc","d","cd","bcd","abcd"]
06:58:01 <AndoDaan> ...And here I am arguing Astrology again, when I just said, on record, that I was quiting it.
06:58:16 <zzo38> Yes, as you can see, we can all make mistakes!
07:02:30 <zzo38> The horoscopes in the newspapers aren't even quite correct. To be correct, the date would vary a bit each year (for a similar reason to why we have leap years), and also the time of day. The Sun's ecliptic longitude will be at exactly "0 Aries" when it is the spring equinox in the northern hemisphere. When this happens varies by year; also it happens at a certain time of day. (Wikipedia has a list.)
07:02:41 <zzo38> So, the actual dates listed in the newspaper horoscopes are only approximate.
07:04:59 <zzo38> This has nothing to do with the text of the horoscopes, however; only the dates.
07:14:43 <zzo38> About "My favourite argument is that a nurse helping to deliver a baby exerts a greater gravitational force on the baby than those stars (except the Sun)", well, the fixed stars normally are not even used in a horoscope. The planets in our solar system, as well as the sun and moon, are used. (The Earth is the center of measurement, so it has no spherical coordinates, and is therefore not included.) If you mean planets, you are right about that, tho
07:19:17 <zzo38> I rarely read the newspaper horoscope myself, but when I do I read all of it instead of just one. Reading just one is sort of like reading only the thirteenth chapter in a novel which contains twenty-five chapters in total.
07:21:03 <AndoDaan> They're mostly Barnam statemts. Vague stuff that can apply to nearly anyone.
07:21:48 <zzo38> Yes, I am aware of that.
07:22:29 <zzo38> Someone else I know who sometimes reads them, told me that the people who write those kind of vague stuff are the people that are good at it; it takes some skill to write in the way they do. (I don't know if it is true or not.)
07:24:52 <zzo38> The same person was confused about what his Sun sign was; he was merely curious about it. What I found, when I put it into the computer, is that I did not have enough information, since the Sun moved from one sign to the next on the day he was born, so I would need the time of his birth too in order to be accurate. So he generally just guesses, and we both agree that it doesn't really matter for that purpose.
07:30:20 <AndoDaan> I wonder if there's like, professional Astrology software out there.
07:31:06 <AndoDaan> I mean, made by believers for believers. And with all the care any business should have.
07:32:38 <AndoDaan> probably one of my dumber wonders. there's even a websit dedicated to reviewing astrology software.
07:32:40 <zzo38> There certainly is astrology software out there; I use one called Astrolog. They are generally very good at doing astronomical calculations; it doesn't matter if you believe in it or not. (Some astronomers, in fact, use it too; together with more proper astronomical software packages. Some people, including myself, would like to be able to combine the features, in order to make it more useful.)
07:33:00 <zzo38> (Note also that Astrolog does not cost anything to get.)
07:34:03 <zzo38> It is easy to see on there, what is the exact time of the full moon, because the aspect line crosses the center of the horoscope, which is clearly marked.
07:35:33 <zzo38> I have even been able to use the "ephemeris chart" mode in order to calcuate when is Chinese New Year.
07:36:27 <zzo38> The "ephemeris chart" mode in Astrolog is a plot of time on the vertical axis and ecliptic longitude on the horizontal axis.
07:37:03 <zzo38> Generally, it displays one month at a time. You can select which objects to plot and which to ignore. (For the purpose of Chinese New Year, only the Sun and Moon are important.)
07:37:54 <AndoDaan> I really should know all this already. (Would you believe I use to be president of my local youths astronomy club)
07:39:05 <int-e> . o O ( just means you have a big mouth )
07:40:12 <AndoDaan> You can come out. It was truer then than it is now.
07:41:08 <AndoDaan> Still pretty true sometimes though. :p
07:41:39 <zzo38> Astrolog has other features too, such as a "timed exposure" mode, which causes it to not clear the screen before redrawing it. There is also a setting for "harmonic factor", which multiplies all ecliptic longitudes by the number specified (an integer from 1 to 30000; it is 1 by default).
07:41:59 <zzo38> I have used both of these things, but haven't used any harmonic factors larger than 2.
07:42:11 <zzo38> (In fact, I have used these features together.)
07:43:12 <zzo38> Actually, I used these two features together with a third one; the option to change what colors are used for various purposes in the program.
07:45:26 <zzo38> I forget what I was calculating, but it involved the full moon, which was why this became useful.
07:48:02 <zzo38> If the harmonic factor is set to 2, then the lines for the Sun and Moon cross both for the full moon and for the new moon.
07:48:23 <zzo38> As far as I know, astrologers generally use harmonic factors for an entirely different purpose than I used them for, while astronomers don't generally use harmonic factors at all.
07:48:51 <zzo38> But this shows the flexibility of use of such computer software!
07:49:54 <AndoDaan> I'm reading "top 5 astrology softwar 1999"
07:50:25 <AndoDaan> though, i guess, there would be much need to update it.
07:50:59 <AndoDaan> physics doesn't change, and if the graphics are good enough, than the graphics is good enough.
07:52:26 -!- centrinia has quit (Ping timeout: 244 seconds).
07:58:57 <zzo38> You might need to download new ephemeris data (although this is unlikely), but even if you do, it is the JPL ephemeris, which is made by NASA and is independent of the software (a lot of software with astronomical calculations uses the JPL ephemeris).
08:01:06 <AndoDaan> See, even my "physics doesn't change" line demostrated a lack of understanding what's involved.
08:03:28 <zzo38> Nevertheless it is very unlikely that new ephemeris data will be needed unless you want to calculate positions for the far past or future. But it isn't completely impossible.
08:03:44 <zzo38> (Extremely unlikely, I should say, perhaps.)
08:12:01 <b_jonas> zzo38: I haven't used astronomical software on my own computer, but I have accessed online websites running simple astronomical software to compute sunrise and sunset times and moon phases.
08:13:21 <b_jonas> If I ever wanted to compute sunrise/sunset/noon times or moon phases automatically, I would get some software for it.
08:13:33 <b_jonas> I don't much care about astrology though.
08:15:48 <b_jonas> (technically, if nethack counts then I have ran astronomical software of course.)
08:17:22 <b_jonas> But of course, sunrises and moon phases can be approximated by very simple approximations during the surrounding few millenia, so it's nothing really complicated.
08:18:04 <b_jonas> Eclipses and phases of Venus might also be relevant without astrology.
08:21:22 <b_jonas> Also the positions of the Sun and Moon on the sky too.
08:22:18 -!- centrinia has joined.
08:25:57 <zzo38> But I was thinking if a software like Astrolog could include a search function that you can type in such queries like: locate Jerusalem; January 1, [Year?] >> Sun at 0 Aries >> Sun opposite Moon >> Sunday; and then if you run this query, it ask you what year you want and tell you the astronomical reform for when is Easter.
08:28:53 <zzo38> Do you like these kind of format?
08:36:26 <mroman> make it an EDSL in Haskell and you got a deal.
08:37:35 <zzo38> I suppose something like that could be made as an EDSL in Haskell, but I haven't been able to find any ephemeris software for Haskell! (I have found messages about people wanting to port Swiss Ephemeris, which is the same software I was thinking of too.)
08:43:16 <mroman> hm. blsq doesn't have any date routines :)
08:44:03 <b_jonas> zzo38: yeah, we need an irc bot that can tell where the Sun and Moon are for people typing on smartphones in windowless cubicles
08:46:03 <zzo38> You could try to instead install ephemeris software onto the smartphones?
08:47:32 <zzo38> And then it work without needing the internet connection.
08:47:50 <b_jonas> nah... do smartphones these days even have accurate clocks?
08:49:12 <mroman> Isn't that required for GPS anyway?
08:50:23 <b_jonas> mroman: oh, right, I guess if you have GPS signal and a GPS reciever you can get the tiem from that
08:50:29 <b_jonas> shows how I'm not a smartphone user
08:54:33 <blsqbot> I've heard they're really big now.
08:56:06 <b_jonas> nah, no sorry, I won't yet.
08:59:31 <mroman> Smartphones are pretty cheap fwaiw.
08:59:53 <mroman> 130 CHF and you can get an android smartphone :)
09:00:04 <mroman> (I just went into the shop and bought the cheapest phone I could find)
09:00:55 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:01:10 -!- skarn has quit (Ping timeout: 244 seconds).
09:10:05 <zzo38> Is there a portable way to make a C program to sleep for one second including on Windows?
09:10:15 <zzo38> (Other than making a loop)
09:13:31 <mroman> but that's probably not very portable :)
09:14:47 <mroman> and I don't think you intend on using GLib
09:16:37 <zzo38> I am using MinGW, but I intend to work in Linux and other systems too.
09:21:21 <zzo38> I found that unistd.h in MinGW declares usleep.
09:22:45 <mroman> yeah but unistd isn't that portable either
09:23:04 <zzo38> But, it isn't listed in The Open Group specifications.
09:23:44 <mroman> which takes an unsigned int seconds
09:23:48 <HackEgo> [wiki] [[User:Pietu1998]] N http://esolangs.org/w/index.php?oldid=40780 * Pietu1998 * (+115) Created page with "Random hobby programmer. Created [[Lenguage]]. More [http://codegolf.stackexchange.com/users/30164/pietu1998 here]."
09:29:14 -!- skarn has joined.
09:29:47 <zzo38> MinGW doesn't seem to have it, though.
09:33:41 <mroman> http://pubs.opengroup.org/onlinepubs/7908799/xsh/sleep.html
09:46:38 <HackEgo> [wiki] [[Lenguage]] M http://esolangs.org/w/index.php?diff=40781&oldid=40703 * Pietu1998 * (+169) added command table from [[Binaryfuck]]
09:51:17 <mroman> brainfuckiest brainfuck fuckiest fuck fuck
09:51:20 <mroman> or what was that called again
09:51:54 <mroman> "Most ever Brainfuckiest Fuck you Brain fucker Fuck"
09:53:16 <zzo38> Nevertheless I did not find sleep() in MinGW header files.
09:55:16 -!- impomatic_ has quit (Ping timeout: 250 seconds).
10:03:39 <mroman> Then, said length is converted to binary, left-padded by zeroes to a multiple of 3
10:03:47 <mroman> since 1b isn't a multiple of 3
10:03:56 <mroman> I left pad it with zeroes until it is a multiple of 3?
10:04:35 <mroman> That's going to take a while.
10:06:18 <mroman> Taneb: Can't talk. Need to prepend zeroes.
10:14:15 <HackEgo> [wiki] [[Gray Snail]] http://esolangs.org/w/index.php?diff=40782&oldid=30483 * AndoDaan * (-6) fixed link
10:20:24 -!- vifino has joined.
10:20:39 -!- vifino has quit (Remote host closed the connection).
10:46:50 -!- MickNartin has joined.
10:53:55 <mroman> I ran out of memory :(
10:57:17 -!- centrinia has quit (Quit: Leaving).
11:08:04 -!- ais523 has joined.
11:12:13 -!- bart1 has joined.
11:17:07 -!- bart1 has quit (Ping timeout: 265 seconds).
11:29:34 -!- boily has joined.
11:54:35 <mroman> the todo list for blsq is getting bigger and bigger :(
12:22:36 -!- boily has quit (Quit: UN CHICKEN ANDALOU).
12:30:29 -!- AndoDaan has quit (Ping timeout: 272 seconds).
12:46:29 -!- oerjan has joined.
12:50:18 <oerjan> darn int-e must have guessed what i did, although not entirely
12:50:40 <oerjan> (he also changed to a slow solution)
12:51:14 -!- ais523 has quit (Quit: lunch).
12:55:03 <oerjan> `` rm bin/rienvenido #It's too long for extra color codes
13:02:36 <fizzie> Lenguage seems to be one of those unary-brainfucks where you can't start a program with +s.
13:02:47 -!- AndoDaan has joined.
13:14:05 -!- CADD has joined.
13:14:09 <oerjan> no, it refers to binaryfuck, which uses an initial 1
13:15:12 <oerjan> i suppose the implementation may or not be consistent with that.
13:17:36 <oerjan> incidentally, this means that for both binaryfuck and unary, there are programs not corresponding to a legal brainfuck program...
13:19:21 <oerjan> binary = bin(total)[2:]
13:19:28 <oerjan> looks like it excludes something
13:19:37 <HackEgo> python: can't open file 'print "test"': [Errno 2] No such file or directory
13:19:53 <oerjan> `` python -c 'print "test"'
13:20:00 <oerjan> `` python -c 'print "test"[2:]'
13:20:18 <oerjan> `` python -c 'print bin(15)'
13:20:33 <oerjan> oh it only skips the 0b
13:23:28 -!- CADD has quit (Quit: leaving).
13:26:51 -!- CADD has joined.
13:28:00 -!- ais523 has joined.
13:28:47 <fizzie> oerjan: Well. It says "evaluated like binaryfuck", but I took that to mean just the way the groups of 3 are evaluated. I don't know why, since it could as easily have meant the result needs to include the initial 1.
13:29:00 <fizzie> (And I didn't look at the reference implementation.)
13:30:08 -!- CADD has quit (Client Quit).
13:30:22 <fizzie> Probably because "left-padded by zeroes to a multiple of 3, and then evaluated like Binaryfuck" sounds like it could never result in a legal Binaryfuck program.
13:30:24 -!- CADD has joined.
13:33:01 -!- AndoDaan_ has joined.
13:33:05 <fizzie> I seem to recall some discussion about a practical enumeration of brainfuck programs that would only include balanced []s.
13:33:31 <fizzie> Don't remember if that ended up in anything.
13:34:00 <oerjan> we tried to construct a bijection between naturals and well-formed brainfuck, yeah
13:34:45 -!- AndoDaan has quit (Ping timeout: 255 seconds).
13:35:10 <oerjan> we certainly got to a conceptual solution, if not several
13:35:34 <oerjan> there were complications if we didn't want exponential blowup due to nesting
13:35:37 <Lymia> fizzie, oerjan: What are you talking about?
13:36:11 <oerjan> it started with http://esolangs.org/wiki/Lenguage
13:36:41 <oerjan> although we seem to have passed on to reminiscing about number-encoding brainfuck in general
13:37:12 <fizzie> Yes, I don't remember if there was something particularly "practical" (if such a word can ever be used) -- reasonably small values, yet "easy" to compute the brainfuck program given the natural number. That was at least someone's goal.
13:37:28 <oerjan> also anyway, it doesn't _really_ matter much if there's an initial 1 or not in an encoding, since you can just prepend -+ or - if necessary
13:37:43 <fizzie> I would have prepended >< for some reason.
13:38:25 <oerjan> fizzie: i think the fibonacci base thing i thought of would have reasonable growth, since it encoded a whole list with only golden ratio blowup or thereabouts
13:38:29 <ais523> what about this: we encode the 8 commands as octal digits; then we use the numbers which correspond to malformed programs to encode the programs which would have leading zeroes
13:39:04 <mroman> what about this: no more "let's encode brainfuck differently" derivations of brainfuck?
13:39:49 <oerjan> mroman: well the old discussion was interesting in so far as it tried to construct a proper _bijection_ while all usual such derivatives leave out either some numbers or some programs
13:39:56 <CADD> oerjan: very cool
13:39:58 <int-e> oerjan: I do know Wilson's theorem. And I'd never thought that I would see the day that I would prefer (!!) :: [a] -> Integer -> a over (!!) :: [a] -> Int -> a...
13:40:34 <elliott> yeah, my brainfuck numbering thing was awful
13:40:53 <int-e> oerjan: I rather suspect that you have a more clever way of doing the substring part
13:41:49 <Lymia> http://codegolf.stackexchange.com/questions/40562/asciis-95-characters-95-movie-quotes < oh god, using esolangs to remove important characters fo non-esoteric languages.
13:41:51 <elliott> a better way to think of the problem may be "construct an enumeration of all brainfuck programs with random access"
13:41:57 <Lymia> Why are eople so cruel
13:42:09 <elliott> (okay, that doesn't guarantee the program -> natural direction, but...)
13:45:20 <int-e> oerjan: oh another thing I can't use: 0^n+n is shorter than max 1n
13:45:57 <int-e> (well, I can, but it's unlikely to help)
13:45:58 <HackEgo> [wiki] [[Talk:Checkout]] http://esolangs.org/w/index.php?diff=40783&oldid=40702 * Ais523 * (+345) /* Impossible to checkout to level 6? */ whoops
13:46:35 <int-e> oerjan: and since I'm spilling tricks: The (n+k) pattern used to enable loops of this kind: main=readLn>>=f;f(n+1)=f n
13:47:07 <HackEgo> [wiki] [[Checkout]] http://esolangs.org/w/index.php?diff=40784&oldid=21322 * Ais523 * (+114) /* Checkouts */ fix an omission that was pointed out in talk
13:47:25 <b_jonas> int-e: ah, quitting by running into an undefined case. nice.
13:47:39 <oerjan> int-e: yeah it's really (0^n+n) vs. max 1n
13:47:41 -!- Lymia has quit (Ping timeout: 272 seconds).
13:47:55 <int-e> b_jonas: yes, that is common practice in the Haskell entries
13:48:07 <ais523> int-e: is the n+k pattern actually official Haskell?
13:48:13 <int-e> b_jonas: a lot of text processing is done by m@main=getLine>>=f>>m
13:48:25 <int-e> ais523: not anymore, it was removed in Haskell2010
13:48:38 <ais523> as being overly specific?
13:48:49 <ais523> you could still do a match against 0, 1, n
13:49:18 <oerjan> ais523: there are some old anagolf haskell solutions that seem impossible to tie, int-e theorizes the loss of n+k patterns is why
13:49:43 <int-e> the other contender is that import List not longer works.
13:49:53 <int-e> but I have no example for that
13:50:51 <mroman> with some ghc version you couldn't do import List anymore
13:51:01 <mroman> and I'm pretty sure I have submitted solutions that do import List
13:51:07 <mroman> (instead of import Data.List)
13:51:12 <mroman> but it doesn't work anymore on anagol
13:51:26 <b_jonas> well, these sound more likely than an entry that you can't tie because you can no longer define an instance of Monad without defining an Applicative instance for that type
13:51:38 <int-e> ais523: (n+k) patterns are a bit onerous on the compiler and gain little. f(n+k) is something like f n'|n'>=k = let n=n'-k in.... (or, in Haskell2010, f n|n<-n-k,n>=0)... using all of Num, Ord and Eq.
13:52:10 <int-e> ais523: One compiler author argued against plain n-patterns (f 0 etc) as well, but they were deemed too useful to drop.
13:52:36 <CADD> int-e: what was the argument?
13:52:49 <CADD> int-e: or even better, link to the article?
13:53:21 <int-e> CADD: lengthy discussion in 2010, I'm not sure how to feed google.
13:53:39 <CADD> int-e: kk, no worries
13:53:46 <CADD> int-e: mayne a tl;dr then?
13:54:08 <int-e> @google "remove npluskpatterns"
13:54:30 -!- Lymia has joined.
13:54:30 <int-e> there must have been a haskell' proposal for that.
13:54:54 <int-e> here: https://ghc.haskell.org/trac/haskell-prime/wiki/RemoveNPlusK
13:56:22 <int-e> CADD: The main reason was that the feature was hardly used and no fans stepped up to defend the feature, while enough people expressed their dislike.
13:56:33 <CADD> int-e: yup, ive seen that. what interested me is why n patterns are bad
13:57:11 <CADD> b_jonas: very few do
13:57:13 <int-e> CADD: oh from a compiler writing perspective they are about as bad as n+k patterns: to desugar f 0 = ..., you need to have something like f x | x==0 = ...
13:57:39 <int-e> CADD: from a programmer's perspective, they are just too useful to drop
13:57:52 <b_jonas> they, like, try to pretend that Integers are represented as a lazy unary data structure, when I actually want to use the fact thta they aren't, they're strict and implemented with machine-level arithmetic as binary
13:58:48 <int-e> > let f :: Double; f 0 = 1; f x = x in map f [-0.1,0,0.1]
13:58:50 <lambdabot> Couldn't match expected type ‘a0 -> a0’
13:58:50 <lambdabot> with actual type ‘GHC.Types.Double’Couldn't match expected type ...
13:58:51 <lambdabot> with actual type ‘GHC.Types.Double’
13:59:02 <int-e> > let f :: Double -> Double; f 0 = 1; f x = x in map f [-0.1,0,0.1]
13:59:07 <CADD> int-e: although im sure like n+k patterns, you could use viewPatterns as well, or at least that is my intuition
13:59:31 <int-e> (it was proposed to restrict n patterns to just Integral, but that also didn't gather a big fanbase)
14:00:00 <b_jonas> int-e: they should be restricted to a _unary_ natural type
14:00:01 <Lymia> elliott, I... just had a terrible idea for that cold golf
14:00:09 <Lymia> x86 using only printable characters.
14:00:14 <b_jonas> a unary lazy natural type (thus one that can store infinity too)
14:00:22 <ais523> Lymia: printable x86 is fun
14:00:49 <Lymia> Somebody already did it with 80386
14:00:51 <int-e> b_jonas: that was about n patterns. I hope you're not suggesting to abolish f (-1) = 42
14:00:55 <b_jonas> Lymia: people are doing that already
14:00:57 <Lymia> x86 counts as distinct, right?
14:01:28 <b_jonas> int-e: oh, n patterns. I dunno about those. I don't much like them, but they're not as bad as n+k patterns, so I think they can stay.
14:01:43 <ais523> XP_W^VH%35%DCPYXPH%=5%=CP[]UM#(UX%??t&* * * * ZR 1() !GFF=\ouU0_0<0^3L1L0^292L1^1Q1L2Y1D1\3R3P0A3B2D0<1p3p3o11131p3>2D0<3:0<18253<2:170D021p3D0>0A0D0<183<3:1:1D0432041p24143o031p2D0p331o0A2D0B2A3I1J2I1J2D321124310o13031D0=0p3o0302113A220=2I1J2I1J22112o0D011412112B02112o0D042A0D0432041p2B2B2D0o2B1I1J2n3I1J2p231o0o1p212D0B042=0?0B1B2B042B242A142B1B2B042A1@2B1=342B3@1m0m032p0o1o0p3B0D2<2@090@061@1;0@15050@382@380@0D2A0B0o2132130B2B1@263o251B1A042A1@
14:01:44 <ais523> 3=342B3@3=3I1J2B0B2B02112o0B2B1B2o2=1323331o043B0B0o2132130B2B1@163o251B1B1A1;193;2=311412112B011412112B0A1@3A0o2B1A0o2B1>2@1>2A132p0p22112o032B0B0o2132130B2B1@263o251A0I1J2D2C143C143D2A0C380C3B3C3=0C3A1B2B02112o0B2B1B2o2A3?0A1B0B2B02112o0B2B1B2o2=0C3p0C3B1B2C3<0C3A0C3@0C3B3B2B02112o0B2B1B2o2C1?0B1>2D1B0B0@163o251=1B0o2132130I1J2B2B13213p03112B0B0o2132130B2B1@163o251A0D2p242D2B1B1C2C2B0@263o251=1B0o2132130B2B13213p03112B0B0o2132130B2B1@
14:01:46 <ais523> 263o251A0D2o3B342D2B1B1C2C2@2@2B332p0o1o0p3B0I1J2D2608053735272:0C1@3?1C1;0<380616080:0C1=1?1C1=1<38063517191D3B07160C1=350=3o0C2B2D0B2D0B2D0B2D06282D0@1B0B1D0D1;3;2;2=1505013o171@053@0=0@052@390@1D2I1J2D290@052@2>1@290@152@1D2A0B0o2132130B2B1@263o251B1C2C211412112B0A1@1A0o2B1C2C232p0o1o0p3B0D2<0<0<1?1D2A0B0o2132130B2B1@263o251B1C2C2B0C3m2C3B332p3313123B0I1J2B0o2132130B2B1@263o251A0>0@1A0@0B1A0@
14:01:46 <int-e> Oh I used to have a DOS game of life program, text only, as a signature...
14:01:47 <ais523> 1B1C2C2B0B0B2B02112o0B2B1B2o2=132o0311010B0B0o2132130B2B1@163o251B1C1@2?1?2B1A011412112B0A1@3A0o2B1A0B0B2B02112o0B2B1I1J2B2o2=132o0311010B0B0o2132130B2B1@163o251B1A3?0A3?2?0B1A011412112B0A1@3A0o2B1A032431013p331B0B0o2132130B2B1@163o251B1A032431013p331B0B0o2132130B2B1@263o251I1J2B1B2@0B1B1>2@1>3I1J2m1I1J2@@A5
14:02:05 <int-e> ...it was even robust to some amount of whitespace change
14:02:33 <ais523> this program is my solution to "you want to send a file to a Windows system over a link that corrupts non-ASCII characters, there is no useful software at the other end"
14:02:36 <b_jonas> there was some recent article about x86 shellcode that looks like English words,
14:02:42 <ais523> actually, that's the output of running the program on its own source code
14:03:02 <ais523> (there's no whitespace past the start of the first line)
14:03:03 <b_jonas> as a research on how heuristic filters can be tricked or something.
14:03:24 <ais523> the main problem I found with ASCII 8086 is that you have no flow control instructions
14:03:35 <ais523> meaning that you need to self-modify the code in order to write them into your program
14:03:45 <Lymia> <ais523> this program is my solution to "you want to send a file to a Windows system over a link that corrupts non-ASCII characters, there is no useful software at the other end"
14:03:48 <ais523> which makes it quite easy to detect
14:03:49 <Lymia> Bootstrap with a .bat file?
14:03:58 <Lymia> AFAIK you could encode arbitary binary text through that.
14:03:58 <int-e> b_jonas: not so recent, perhaps :)
14:04:10 <ais523> Lymia: I don't know of a way to encode binary as a batch file
14:04:21 <Lymia> certutil -decode encodedInputFileName decodedOutputFileName
14:04:29 <ais523> actually I had to do exactly that once, except the target system was running Linux
14:04:33 <ais523> so I used busybox printf
14:04:47 <Lymia> certutil should be standard
14:04:48 <ais523> Lymia: hmm, now you're relying on external useful software
14:05:02 <b_jonas> I encoded a file with perl once
14:05:04 <ais523> I doubt certutil exists on DOS, and possibly not on Windows 95 either (which is about the age of this code)
14:05:22 <ais523> anyway, a proper encoder would bootstrap into proper uucode
14:05:37 <ais523> rather than the rather awkward "two bytes per character" of that encoding above
14:05:46 <b_jonas> in fact I think shar assumes the destination has uudecode
14:05:49 <ais523> (I think it alternates between 6 and 2 bytes)
14:05:55 <ais523> b_jonas: it does, if you encode binaries
14:06:01 <ais523> uuencode is actually in sharutils, packagewise
14:06:14 <Lymia> Isn't base64 standard on Linux though?
14:06:33 <oerjan> mroman: i think what happened with List was, at some point the current Prelude diverged so much from H98 that it could no longer be shared with the H98 compatibility layer, so all the old modules were put in the haskell98 package and hidden by default.
14:06:36 <b_jonas> Lymia: perl is standard on Linux and you can use it for this pretty well
14:06:41 <elliott> I mean, that's what the x means :p
14:07:10 <elliott> i386 is just an abbreviation.
14:07:24 <Lymia> This is probably going to end terribly, but
14:07:33 <Lymia> What if I tried to use Malborge in that challenge
14:08:55 <b_jonas> and m68k is a cpu arch entirely unrelated to x86, despite that it has "8" and "6" in it
14:09:04 <oerjan> b_jonas: you still can define Monad without Applicative in all officially released GHC versions, although that will change with 7.10; there's just a warning in the latest one. anagolf's still on 7.4, though.
14:09:50 <b_jonas> oerjan: oh... and can you even use that instance after you define it that way?
14:14:07 -!- AndoDaan has joined.
14:15:33 -!- AndoDaan_ has quit (Ping timeout: 272 seconds).
14:18:00 -!- ais523 has changed nick to ais523\unfoog.
14:20:10 <mroman> since x64 means 64bits
14:20:17 <mroman> x86 probably means it's got 86bits
14:20:19 <b_jonas> also x86 is derived from x80
14:20:36 <mroman> which had just 80 bits
14:21:32 <mroman> I a wouldn't know anything about these things
14:22:56 <int-e> ah I should've included a random number generator ... a black screen is all I get in dosbox
14:24:04 <int-e> anyway http://sprunge.us/cUIB is the code, executable as a .COM file.
14:24:34 <int-e> and one can change whitespace after the 64th character.
14:30:43 <b_jonas> mroman: about "bits", http://www.scottaaronson.com/blog/?p=1558
14:33:54 <ais523\unfoog> most subsequent revisions put digits in the middle
14:34:11 <ais523\unfoog> I think it goes up to 80686? but after a bit, people started using names rather than numbers, such as "Pentium"
14:34:53 <int-e> a good thing, too, it avoided the 801086 mess
14:38:40 <mroman> then with Pentium they started using numbers again
14:38:57 <mroman> then suddenly they started using letters
14:39:09 -!- FreeFull has quit (Ping timeout: 265 seconds).
14:39:20 <int-e> pentium, pentium pro, pentium mmx, pentium 3, pentium 4,
14:39:29 <int-e> I don't recall a pentium 2
14:39:57 <oerjan> b_jonas: Monad isn't a subclass of Applicative at all until next release, so yes.
14:40:25 <mroman> http://en.wikipedia.org/wiki/Pentium_II
14:40:40 <oerjan> b_jonas: of course the probability that a good golf solution involves defining a monad instance is rather low.
14:40:59 <int-e> mroman: thanks. the roman numerals look more familiar
14:47:55 <HackEgo> Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
14:48:26 <ais523\unfoog> oerjan: if the task was complicated enough, it might be worth it because of do-notation?
14:48:29 <mroman> dark blue on my black background isn't the best thing :)
14:53:19 <int-e> ais523\unfoog: still unlikely, since one can define 3 single character infix operators
14:56:59 <int-e> so in addition to do notation, you need code that requires lots of bindings, do a<-n;b<-o;c<-p;...;m<-z
14:57:56 <ais523\unfoog> a Monad instance doesn't actually have to follow the monad laws, right? Haskell won't try to prove it
14:58:05 <ais523\unfoog> so you could just define something sufficiently monad-ish that it parsed
14:58:07 <int-e> ais523\unfoog: right.
15:00:41 <mroman> I broke the monad-law and I won.
15:01:29 <mroman> Note to myself: Check quotes before saying them.
15:02:40 -!- AndoDaan_ has joined.
15:02:57 -!- AndoDaan has quit (Ping timeout: 255 seconds).
15:03:03 -!- adu has joined.
15:07:55 -!- Phantom_Hoover has joined.
15:10:35 <oerjan> ais523\unfoog: the thing is, you can get a lot of mileage in golfing for the cost of the characters "instance Monad where", and you'd probably need to define a data type as well...
15:12:26 <oerjan> do notation doesn't always beat explicit >>=, and only by a few characters. so, unlikely.
15:14:31 -!- `^_^v has joined.
15:18:34 -!- bb010g has quit (Ping timeout: 256 seconds).
15:22:25 -!- nyuszika7h_ has joined.
15:22:42 -!- bb010g_ has joined.
15:23:30 -!- FreeFull has joined.
15:24:21 -!- oerjan_ has joined.
15:24:30 -!- nyuszika7h has quit (Ping timeout: 256 seconds).
15:24:31 -!- oerjan has quit (Ping timeout: 256 seconds).
15:27:14 -!- nyuszika7h_ has changed nick to nyuszika7h.
15:29:19 -!- oerjan_ has changed nick to oerjan.
15:43:42 -!- CADD has quit (Remote host closed the connection).
15:43:47 -!- adu has quit (Quit: adu).
15:45:34 -!- AndoDaan_ has quit (Ping timeout: 258 seconds).
15:46:17 -!- Sprocklem has joined.
15:52:00 <Bike> http://33.media.tumblr.com/41aa1d635c8367c07bd174824fb09cc0/tumblr_nejfhwQqHS1qzcv7no1_1280.jpg Astrology is fun.
15:52:53 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40785&oldid=40698 * TomPN * (-57) /* Line functions */
15:54:37 -!- drdanmaku has joined.
15:57:09 -!- AndoDaan has joined.
15:58:20 <blsqbot> ERROR: Burlesque: (rm) Invalid arguments!
15:58:23 <blsqbot> ERROR: Burlesque: (rm) Invalid arguments!
15:58:29 <blsqbot> "9.00000000000000000000000000000000000000000000000000000000000000000000000000000
15:58:50 <blsqbot> Ain't nobody got time fo' dat!
15:58:52 <blsqbot> "23.1406926327792630000000000000000000000000000000000000000000000000000000000000
15:59:20 <blsqbot> ERROR: Burlesque: (P[) Invalid arguments!
16:00:09 <blsqbot> Ain't nobody got time fo' dat!
16:00:10 <elliott> Bike: I like how they circled two when all of them are equally absurd
16:00:34 <Bike> elliott: j-law will be wearing it next year
16:00:53 <mroman> fizzie: Is bfjoust fixed, btw?
16:02:44 <fizzie> Though EgoBot is back.
16:03:02 <fizzie> So you can (or, in fact, have to) submit to two hills in one command.
16:04:48 <mroman> !bfjoust cupnoodles (>)*9([(-)*8[+].]+>)*4(<)*4(<--<++)*4<--(>(+)*17>(-)*17)*4(>)*6(>[(+)*8[-].]>[(-)*8[+].])*-1
16:04:50 <zemhill> mroman.cupnoodles: points 7.67, score 29.82, rank 6/47
16:04:57 <EgoBot> Score for mroman_cupnoodles: 22.7
16:05:17 <mroman> where's the egobot hill located at?
16:06:01 <zemhill> ais523\unfoog: "!bfjoust progname code". See http://zem.fi/bfjoust/ for documentation.
16:06:02 <EgoBot> Use: !bfjoust <program name> <program> . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/
16:06:38 <mroman> only scores rank 40 on egojoust
16:12:00 -!- zzo38 has quit (Remote host closed the connection).
16:14:41 <fizzie> Could be something screwy with the zemhill scoring.
16:14:48 <fizzie> And, of course, they're quite different algorithms.
16:15:03 <fizzie> Points-wise it doesn't seem all that different.
16:15:44 -!- MDream has changed nick to MDude.
16:16:01 -!- mihow has joined.
16:19:55 -!- AndoDaan_ has joined.
16:21:59 -!- AndoDaan has quit (Ping timeout: 258 seconds).
16:22:56 -!- oerjan has set topic: See the fabulous redundant twins EgoBot and zemhill | BF Joust scoring poll: http://goo.gl/02KE0Y | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
16:54:30 <newsham> tiny C compiler. https://github.com/rswier/c4/blob/master/c4.c
16:55:16 <Taneb> Interpreter, strictly speaking
16:55:40 <oerjan> @tell tswett The trick I discovered (and probably am not the first) for converting dates is that a multiplication and a division can give exact answers if you choose the right offset. in particular, for finding the year you want to treat january and february as belonging to the previous year, and putting the epoch at mar 1 in a 400-year like 1600 or 2000. there's a similar offset you can use for months within a year.
16:55:56 <oerjan> hum did that all get included
16:56:45 <newsham> ends with "within a year."
16:57:22 <oerjan> (i don't actually remember what the offset was, except that it was _not_ starting with march)
16:59:06 <oerjan> although i could rederive it, starting from march the day lengths are 31 30 31 30 31 31 30 31 30 31 31 2*
16:59:38 <oerjan> the february doesn't matter because we'll have cut the year there in a previous step
17:00:33 <oerjan> we see then there's a period there with july - december, 5 months
17:01:46 <oerjan> i think september = 0 will give the right offset
17:04:23 <oerjan> > let f m = (m-9)*(3*31+2*30)`div`5 in zipWith(-)`ap`tail$map f[3..14]
17:04:25 <lambdabot> [-31,-30,-31,-30,-31,-31,-30,-31,-30,-31,-31]
17:04:54 <oerjan> that's the essence of it.
17:06:12 <oerjan> @tell tswett it seems the offset for months is sep 1, then *(3*31+2*30)`div`5
17:09:27 <oerjan> i implemented this in schemenomic, way back.
17:10:28 -!- oerjan has quit (Quit: Later).
17:17:48 <int-e> eww... http://golf.shinh.org/p.rb?Wow
17:28:28 <Lymia> Doing the SO challenge in Malborge
17:28:32 <Lymia> Is proving surprisingly painful.
17:28:45 <Lymia> Because half the instructions are unusable at many points due to the restrictions on characters.
17:29:16 <Lymia> "#&'()*+,-./037;<=>@[\]^_ deopsvxXyz{|}~ being forbidden is generating huge streaks of unusuable characters.
17:33:25 <Lymia> http://codegolf.stackexchange.com/questions/40562/asciis-95-characters-95-movie-quotes
17:33:28 <ais523\unfoog> also, being surprisingly painful is the entire point of Malbolge
17:33:31 <Lymia> I'm writing a Malborge solution
17:33:33 <Lymia> <ais523\unfoog> also, being surprisingly painful is the entire point of Malbolge
17:33:47 <Lymia> Malborge would not be painful for writing a fixed printing program.
17:34:06 <int-e> In this case it seems malbolge's position-dependent decoding of instructions would be a blessing
17:34:19 <Lymia> int-e, it is, sort of.
17:34:23 <int-e> doesn't mean it's easy
17:34:38 <Lymia> Problem is, their selection of special characters means there's long runs where one instruction or another is just plain unavailable.
17:34:47 <ais523\unfoog> Lymia: I remind you that it took several months for the first hello world program in Malbolge, which was mixed-case and generated by an evolutionary algorithm
17:35:14 <Lymia> I have a position where the only available insturctions are / and u
17:35:24 <Lymia> Meaning I have to execute a p there
17:35:46 <int-e> I thought there were nops
17:36:02 <Lymia> Since I can only input "valid" instructios.
17:36:55 <ais523\unfoog> also, you can't use the non-ASCII hole because it's an ASCII tournament
17:37:25 <Lymia> http://pastebin.com/5fKv9cgS
17:37:32 <Lymia> To give an idea of what I actually have available at each position
17:38:26 <Lymia> I can never execute / since that reads stdin
17:38:29 <int-e> lazy k still works... `SK
17:38:31 <ais523\unfoog> 83 is by someone called "Snack", who knows of Esolang
17:38:41 -!- password2 has joined.
17:38:48 <Lymia> int-e, better do that now. :)
17:38:54 <Lymia> I intend to knock out ` with Malborge.
17:39:47 <int-e> But I can't be bothered.
17:40:29 <Lymia> http://pastebin.com/7X89ehSc
17:40:41 <Lymia> The top four instructions are the only ones I can really safely use whenever I like
17:41:14 <Lymia> 3 terrible positions.
17:41:23 <ais523\unfoog> oh, people are language-sniping, boring (apart from sniping the BF derivatives, I can get behind that)
17:41:23 <Lymia> Each of where I have to either jump (urgh, bad bad bad) or print (eeep)
17:41:36 <ais523\unfoog> Lymia: you could just try jumping and seeing where it goes
17:41:50 <ais523\unfoog> you can just pad from the source to the destinatino
17:42:01 <Lymia> ais523\unfoog, my current plan is to get d far into the padding
17:42:42 <Lymia> It seems that the padding usually looks something like this: 83 29443 83 29444 82 29444 83 29443 83 29444 82 29444 83 29443 83 29444 82 29444 83 29443 83 29444 82 29444
17:42:52 <FireFly> ais523\unfoog: plenty of people on PPCG knows about Esolang
17:43:03 <Lymia> So, if I get d to be around 29444, I can use j, *, and p to permute the values there.
17:43:08 <Lymia> Until I get the ASCII values I want to print.
17:43:20 <ais523\unfoog> PPCG is basically the Stack Overflow version of #esoteric
17:43:46 <Lymia> Since the large value would point into the part of the memory I'm using for the permutation, I could easily use j to loop back over the state I'm using once more
17:43:52 <ais523\unfoog> good luck, I hope you get there in time to not be sniped
17:44:04 <Lymia> Only way someone can snipe me
17:44:07 <Lymia> Is to get Malborge before me.
17:44:18 <ais523\unfoog> Lymia: or ban one of the characters you use, forcing you to rewrite the program
17:44:40 <Lymia> I'll probably want to hand-write initialization to get myself into the padding
17:44:49 <Lymia> But, a generator would be nice after that
17:45:32 <ais523\unfoog> what if all eight legal characters at any given position get banned?
17:45:45 <int-e> what other ideas do I have ... dc is going to work still, until all digits or P are gone.
17:46:21 <Lymia> ais523\unfoog, I'm screwed
17:46:25 <ais523\unfoog> don't you need at least some arithmetic? admittedly, dc has a lot
17:46:34 <ais523\unfoog> Lymia: then you'd better get this done quickly :-(
17:46:47 <Lymia> Every position has at least two characters open right now
17:46:53 <Lymia> So it'll take two bans to kill Malborge
17:47:10 <Lymia> There's malborge variants out there
17:49:54 -!- password2 has quit (Ping timeout: 255 seconds).
17:50:05 <AndoDaan_> There's also a BF variant that can be written with any character, it takes the length of your code and converts it to binary, and then to one of the 8 BF commands.
17:51:37 -!- AndoDaan_ has changed nick to AndoDaan.
17:51:49 <ais523\unfoog> AndoDaan: I was thinking of Unary, but that mandates 0s
17:51:57 <int-e> ok, two dc approaches: <n>d<m>%P (with some precalculation) <n1>ZP<n2>ZP... (where ni have the appropriate number of digits)
17:51:59 <Lymia> There's a character that'll force me to use jumps
17:52:05 <Lymia> Since it eliminates all safe instructions in a positino
17:52:09 <int-e> I couldn't do it without P.
17:52:32 <Lymia> int-e, I'll snipe P for you
17:52:50 <ais523\unfoog> Lymia: int-e: do it in reverse, submit a dc entry that makes most languages hard but Malbolge no harder than before
17:53:24 <Lymia> A number would do nicely
17:53:44 <Lymia> I'm not sure if I should go after ! or $
17:53:52 <int-e> how does one figure out which quotes are still available?
17:56:32 <Lymia> int-e, how about you get a number or something
17:59:46 <fizzie> int-e: But there's a P workaround right there in the man page!
18:00:05 <int-e> fizzie: [] are gone
18:00:22 <fizzie> The workaround also contains a P, which is something I hadn't noticed.
18:01:11 <fizzie> I guess that's reasonable, since you can't print anything else but numbers with anything else.
18:01:35 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
18:02:25 <fizzie> ais523\unfoog: One (or more?) of the Unary clones allows any character.
18:02:38 <ais523\unfoog> so save that for #1 unless someone else snipes it first
18:02:58 <ais523\unfoog> ooh, what about 1L? that allows any two printables, IIRC
18:10:09 -!- AndoDaan has quit (Ping timeout: 264 seconds).
18:10:49 -!- AndoDaan has joined.
18:13:56 <int-e> Lymia: http://sprunge.us/GLDj is dc for quote 60, feel free to submit (I won't, my intellectual curiosity is satisfied). having 9 available simplifies matters but is not essential.
18:15:29 <int-e> Lymia: But I can do another if you want the "mess" one for "Malbolge".
18:17:40 <Lymia> Could you post it and strike Z?
18:17:45 <Lymia> I'm going to strike P next
18:18:56 <int-e> I will not post it.
18:20:06 -!- MoALTz has joined.
18:24:17 <int-e> oh I could use a newline instead of Ir. that makes me feel better.
18:26:34 <int-e> now to find a language that is turing complete with just tabs and newlines...
18:28:04 <int-e> ah. "but there may not be more that 64 tabs or 64 newlines in your program."
18:28:12 <int-e> somebody thought of that possibility.
18:33:41 <int-e> though technically that solution is invalid because it contains spaces. but those are not required.
18:40:50 <int-e> `WeLcOmE quintopia
18:40:50 <HackEgo> QuInToPiA: wElCoMe tO ThE InTeRnAtIoNaL HuB FoR EsOtErIc pRoGrAmMiNg lAnGuAgE DeSiGn aNd dEpLoYmEnT! fOr mOrE InFoRmAtIoN, cHeCk oUt oUr wIkI: <HtTp://eSoLaNgS.OrG/>. (FoR ThE OtHeR KiNd oF EsOtErIcA, tRy #EsOtErIc oN IrC.DaL.NeT.)
18:43:16 <int-e> Lymia: Oh I couldn't submit if I wanted to: dc has already been used.
18:52:34 <Lymia> My initializer works.
18:57:14 <int-e> oh fun. 64 bytes from 64.15.113.24: icmp_seq=293 ttl=55 time=27203 ms
18:57:51 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
18:58:01 -!- ais523\unfoog has joined.
18:59:52 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
19:00:03 -!- ais523\unfoog has joined.
19:00:55 -!- ais523\unfoog has quit (Client Quit).
19:12:12 -!- AndoDaan has quit (Ping timeout: 250 seconds).
19:16:13 -!- AndoDaan has joined.
19:21:11 -!- Sprocklem has quit (Read error: Connection reset by peer).
20:16:53 -!- Vorpal_ has changed nick to Vorpal.
20:22:19 -!- nycs has joined.
20:24:33 -!- `^_^v has quit (Ping timeout: 264 seconds).
20:25:46 -!- Sprocklem has joined.
20:32:36 -!- MoALTz has quit (Quit: Leaving).
20:35:49 -!- Sprocklem has quit (Ping timeout: 265 seconds).
20:52:54 <HackEgo> [wiki] [[Special:Log/newusers]] create * Notjohnconway * New user account
20:54:35 -!- atehwa has quit (Remote host closed the connection).
20:56:25 -!- Bicyclidine has joined.
20:57:25 <fizzie> Vorpal: For a short while.
21:00:34 <Vorpal> fizzie, How do you generate your site? Write raw html or some sort of site generator?
21:01:50 -!- Sprocklem has joined.
21:04:27 <fizzie> It's a bit of custom Python code, reading mostly raw HTML, with a rather simple include-with-parameter-replacement facility and some other such things.
21:04:39 <fizzie> (Also takes care of making the Atom feed.)
21:05:43 <fizzie> The bfjoust page I built with nanoc, which is a Ruby-based static-site generator, though it seems a bit overengineered.
21:20:30 -!- icedvariables has joined.
21:21:05 -!- AndoDaan_ has joined.
21:23:12 -!- AndoDaan has quit (Ping timeout: 264 seconds).
21:24:44 -!- icedvariables has quit (Ping timeout: 246 seconds).
21:26:01 -!- hjulle has quit (Remote host closed the connection).
21:27:31 -!- hjulle has joined.
21:37:01 -!- hjulle has quit (Quit: ZNC - http://znc.in).
21:38:18 -!- hjulle has joined.
21:49:04 -!- impomatic_ has joined.
21:56:35 -!- MickNartin has quit (Quit: Page closed).
22:03:05 -!- Bicyclidine has quit (Ping timeout: 260 seconds).
22:03:43 -!- hjulle has quit (Quit: ZNC - http://znc.in).
22:09:01 -!- oerjan has joined.
22:14:29 -!- hjulle has joined.
22:19:28 -!- Sprocklem has quit (Ping timeout: 245 seconds).
22:21:13 <oerjan> Lymia: i am pondering banning you until you learn to spell malbolge hth
22:21:58 <oerjan> (note: distance between pondering and actually doing is generally large)
22:25:00 <b_jonas> oh, the Musical Notes guy has returned
22:25:50 <b_jonas> and changed the definition so that the [ and ] instructions now owrk in Brainfuck except it still says "Loops cannot be nested."
22:36:16 -!- hjulle has quit (Quit: ZNC - http://znc.in).
22:40:31 -!- Phantom_Hoover has joined.
22:51:30 <nycs> http://www.bls.gov/OES/current/oes151131.htm
22:51:48 <nycs> apparently animal slaughtering is the top paying industry for computer programmers
23:10:56 -!- nycs has quit (Quit: This computer has gone to sleep).
23:39:01 -!- vanila has joined.
23:42:47 -!- Sprocklem has joined.
23:51:14 -!- Bicyclidine has joined.
23:56:03 -!- Sgeo_ has joined.
23:58:33 -!- Sgeo has quit (Ping timeout: 258 seconds).
00:00:16 -!- coppro has changed nick to NHcoppro.
00:00:56 -!- NHcoppro has changed nick to coppro.
00:04:18 -!- boily has joined.
00:10:23 -!- Sgeo has joined.
00:14:03 -!- Sgeo_ has quit (Ping timeout: 245 seconds).
00:14:17 -!- Sgeo_ has joined.
00:16:58 -!- Sgeo has quit (Ping timeout: 245 seconds).
00:19:19 -!- mihow has quit (Quit: mihow).
00:25:56 -!- Sgeo has joined.
00:27:15 -!- Sgeo_ has quit (Ping timeout: 244 seconds).
00:32:22 -!- Sgeo_ has joined.
00:36:08 -!- Sgeo has quit (Ping timeout: 245 seconds).
00:36:58 -!- Sgeo_ has quit (Ping timeout: 245 seconds).
01:07:54 -!- Bicyclidine has quit (Ping timeout: 256 seconds).
01:15:43 -!- Sgeo has joined.
01:18:41 <Sgeo> Let's see if I can stay connectedc
01:20:16 -!- nys has joined.
01:20:22 <HackEgo> [wiki] [[Subleq]] http://esolangs.org/w/index.php?diff=40786&oldid=40779 * Rdebath * (-115) You only need to say it once and English uses parentheses not square brackets.
01:28:29 -!- vanila has quit (Quit: Leaving).
01:36:52 <boily> Sgeo: so far so good.
01:44:21 -!- boily has quit (Quit: ABSTRACT CHICKEN).
01:45:05 <oerjan> darn and here i switched to the irc window just to see what concrete chicken message boily left with
01:45:07 <HackEgo> [wiki] [[Subleq]] http://esolangs.org/w/index.php?diff=40787&oldid=40786 * Rdebath * (+74) Move editing notes to a comment.
01:47:51 <Sgeo> How (im)practical is it to write code directly in LLVM IL assembly?
01:48:25 <Sgeo> *IR, which I was going to write but decided IL made more sense
01:48:57 <oerjan> just pletend you'le chinese
01:50:22 <Sgeo> I just want a good language to do another Braintrust implementation in which it's sufficiently comfortable to include a lightweight compiler for the language
01:50:36 <Sgeo> e.g. a statically-linked-in GHC in Haskell except that that's probably heavyweight
02:03:36 <Sgeo> Is rustc as a statically includable library plausible?
02:05:18 -!- AndoDaan has joined.
02:05:59 -!- AndoDaan has quit (Client Quit).
02:07:30 -!- AndoDaan_ has quit (Ping timeout: 272 seconds).
02:20:16 <oerjan> Sgeo: planning the Braint compiler?
02:21:17 <oerjan> if only kmc were around these days.
02:21:41 <oerjan> well he's on the network.
02:40:50 -!- adu has joined.
02:57:17 -!- paul2520 has quit (Quit: WeeChat 1.0).
03:05:16 -!- paul2520 has joined.
03:05:16 -!- paul2520 has quit (Changing host).
03:05:16 -!- paul2520 has joined.
03:15:47 -!- oerjan has quit (Quit: leaving).
03:23:16 -!- AndoDaan has joined.
03:29:13 -!- nys has quit (Quit: quit).
03:41:36 -!- ^v has quit (Quit: Leaving).
04:04:36 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds).
04:06:15 -!- password2 has joined.
04:26:15 -!- password2 has quit (Ping timeout: 256 seconds).
04:27:07 -!- lambdabot has quit (Ping timeout: 255 seconds).
04:32:54 -!- lambdabot has joined.
04:39:14 -!- password2 has joined.
05:01:28 -!- ^v has joined.
05:11:19 -!- adu has quit (Quit: adu).
05:12:47 <int-e> meh, "Encryption".
05:21:21 <Bike> more like shitcryption, imo.
05:22:45 <int-e> so now to do it in another language, hmm.
05:35:10 <HackEgo> [wiki] [[CA-1]] N http://esolangs.org/w/index.php?oldid=40788 * Notjohnconway * (+154) Created page with "Under construction n shit yo '''CA-1''' is the name of an esoteric programming language and a set of related programs, notably CA-1 Assembler. ==Example=="
05:35:50 <Sgeo> tromp: presumably accidental abbreviation of Braintrust
05:35:53 <Sgeo> That's what I assumed anyway
05:39:38 -!- password2 has quit (Ping timeout: 244 seconds).
06:04:38 <Sgeo> minus = (x, y): x - y.
06:04:42 <Sgeo> http://perl11.org/potion/pamphlet.html
06:04:58 <Sgeo> Sending... a block to a table to make an anonymous function?
06:08:29 <Sgeo> Or maybe calling the table as a function with the block?
06:17:08 -!- shikhin has joined.
07:32:27 -!- ^v has quit (Ping timeout: 240 seconds).
07:34:01 <Lymia> TIL the 3DS uses CTR mode for pretty much all its encryption.
07:34:29 <Lymia> Apparently Nintendo doesn't learn from its mistakes.
07:35:44 -!- ^v has joined.
07:42:04 <fizzie> What's wrong with (no-IV-reuse) CTR mode?
07:46:48 -!- shikhout has joined.
07:48:53 <int-e> fizzie: hmm. two ideas: 1. if you xor two encrypted messages, you get the xor of two plaintexts, possibly revealing more than intended. 2. if you don't bother to authenticate decrypted data, then the attacker can easily modify individual bytes of the plaintext.
07:49:24 <fizzie> int-e: I did say no IV reuse.
07:49:32 -!- shikhin has quit (Ping timeout: 245 seconds).
07:49:39 <fizzie> int-e: You don't get the xor of two plaintexts unless you do it stupidly.
07:49:42 <int-e> the first one should be avoided by the nonce, right. the second one is still a potential issue
07:50:08 <fizzie> I guess that's true; it's not an authenticated mode.
07:53:27 <fizzie> So maybe it's hard to recommend over, say, GCM. But it's not like it's pretending to be authenticated encryption, either.
07:56:34 <int-e> funny, this is the first time I run into a problem with the golf.shinh.org system being 32 bits.
07:57:08 <int-e> ("problem" meaning I have to spend extra characters on making the program work)
07:57:43 -!- yorick has quit (Read error: Connection reset by peer).
08:00:02 -!- yorick_ has joined.
08:02:07 <quintopia> fizzie: what algorithm do you use to generate cladograms?
08:08:15 <fizzie> I don't, really. I mean, that's more of a bioinformaticist thing. Though my last set of browser tabs (which I lost somehow) had a very nice-looking thing for that -- I just don't quite know how I could relocate it.
08:10:10 <elliott> int-e: needing a larger integer type?
08:23:01 <int-e> elliott: I'm using Haskell, so usually things are fine because stuff defaults to Integer.
08:25:26 <elliott> dealing with gigabytes of data for golf? :p
08:25:45 -!- shikhout has changed nick to shikhin.
08:27:20 <fizzie> quintopia: I think http://mrbayes.sourceforge.net/ was the page I had open, maybe.
08:32:09 <elliott> I admire the postscript golfers the most
08:38:09 <Sgeo> A clean Cy&H? What is the world coming to?
08:38:34 <elliott> jesus christ, you read Cy&H in 2014?
08:41:01 <Sgeo> At least I don't read that Station comic anymore
08:42:34 <Sgeo> ... I'm reading it again
08:43:23 <Sgeo> The list of storylines hasn't been updated since 2009... I'm assuming because there are no storylines
08:44:10 <Sgeo> There's a comment from two years ago complaining about it
08:44:34 <Sgeo> http://www.stationv3.com/d/20091213.html#comment-627106160
08:52:06 <Sgeo> http://www.stationv3.com/d/20050325.html
08:58:39 <Sgeo> http://www.stationv3.com/d/20050507.html
08:58:54 <Sgeo> 'business as usual' describes the comic, I think
09:02:08 <b_jonas> Sgeo: it had "storylines"? I thought it's just disconnected strips
09:04:45 -!- shikhin has quit (Remote host closed the connection).
09:06:37 -!- shikhin has joined.
09:08:52 -!- oerjan has joined.
09:09:55 <oerjan> <Sgeo> tromp: presumably accidental abbreviation of Braintrust <-- *swats Sgeo for missing the obvious pun -----###
09:10:11 <oerjan> also i cannot sleep :(
09:10:47 -!- AndoDaan has quit (Ping timeout: 265 seconds).
09:16:27 <oerjan> looks like a router reboot helped
09:25:27 -!- MDude has quit (Ping timeout: 250 seconds).
09:28:10 <HackEgo> Invalid option "-e" \ Usage: java org.mozilla.javascript.tools.shell.Main [options...] [files] \ Valid options are: \ -?, -help Displays help messages. \ -w Enable warnings. \ -version 100|110|120|130|140|150|160|170 \ Set a specific language version. \ -opt [-1|0-9] Set optimizat
09:28:44 <mroman> `js print(['10','10','10'].map(parseInt))
09:31:37 <FireFly> the explanation to that is that `map` passes in (value, index, array) and parseInt takes an optional second argument (the radix)
09:31:53 <FireFly> It's not a *good* reason for that, but it is a reason
09:32:12 <FireFly> `js print(['10','10','10'].map(Math.floor))
09:32:23 <FireFly> Always fun to abuse weak typing
09:32:58 <FireFly> `js print(parseInt('0x10', 0))
09:33:16 <FireFly> All right, so it treats a second argument of 0 the same as no second argument
09:34:25 <oerjan> `js print(parseInt('1111', 1))
09:34:47 <oerjan> `js print(parseInt('0000', 1))
09:36:10 -!- AndoDaan has joined.
10:15:03 <mroman> `js print(['10','10','10','10','10']).map(parseInt)
10:15:05 <HackEgo> 10,10,10,10,10 \ js: uncaught JavaScript runtime exception: TypeError: Cannot call method "map" of undefined
10:15:14 <mroman> `js print(['10','10','10','10','10'].map(parseInt))
10:15:19 -!- Phantom_Hoover has joined.
10:15:21 <mroman> although this is kinda funny
10:17:55 <oerjan> stackoverflow is no fun with molassey web :(
10:30:40 <elliott> oerjan: well 1 isn't a positional base
10:30:53 <elliott> okay I guess it is, just one that can only represent 0
10:36:44 -!- atehwa has joined.
10:40:43 -!- yorick_ has changed nick to yorick.
10:42:23 <HackEgo> [object Object][object Object]
10:42:53 <mroman> I guess javascript can be a honorary esoteric language
10:54:00 <b_jonas> mroman: note that some of the apparent wierdness is that in some contexts javascript is like perl so {}+[] is parsed such that {} is an empty C-style statement block and then +[] is an expression with unary plus
10:54:22 <b_jonas> mroman: so sometimes you think you've printed the expression {}+[] but actually you print the expression +[]
10:58:27 <mroman> `js print({'abc':9} + []);
10:58:38 <mroman> `js print({'abc':9} + {});
10:58:40 <HackEgo> [object Object][object Object]
10:58:43 <b_jonas> mroman: it's an object if it occurs in expression context like in print({} + [])
10:59:04 <b_jonas> mroman: but some people have tried to just type {} + [] in a firefox javascript console or something, in whcih case it was a statement
10:59:42 <b_jonas> `js print(eval("({}+[])"))
11:21:32 -!- MDude has joined.
11:25:08 <fizzie> "-- where score is a composite acoustic/language model score from the recognizer, on the bytelog scale. (A bytelog is a logarithm to base 1.0001, divided by 1024 and rounded to an integer.)"
11:30:57 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
11:40:58 -!- boily has joined.
11:42:31 -!- hjulle has joined.
11:56:12 <fizzie> > round . (*1024) . logBase 10 <$> [0.00001, 0.001, 0.1, 1, 10, 100, 100000, 1000000000]
11:56:14 <lambdabot> [-5120,-3072,-1024,0,1024,2048,5120,9216]
11:56:31 <fizzie> I think they must have meant "multiplied by 1024", otherwise that doesn't make all that much sense.
11:56:43 <fizzie> Oh, I forgot the 1.0001.
11:56:51 <fizzie> > round . (*1) . logBase 1.0001 <$> [0.00001, 0.001, 0.1, 1, 10, 100, 100000, 1000000000]
11:56:52 <lambdabot> [-115135,-69081,-23027,0,23027,46054,115135,207243]
11:56:58 <fizzie> > round . (/1024) . logBase 1.0001 <$> [0.00001, 0.001, 0.1, 1, 10, 100, 100000, 1000000000]
11:57:07 <fizzie> Maybe it is that, indeed.
11:57:44 <oerjan> that 1.107820842039981 is the scale factor which increases it by 1
12:03:57 <J_Arcane> This is an utterly amazing piece, about computer history, human networking, and reliving the past. https://medium.com/message/networks-without-networks-7644933a3100
12:04:46 -!- AndoDaan has quit (Ping timeout: 264 seconds).
12:07:14 -!- Frooxius has quit (Quit: *bubbles away*).
12:21:28 -!- boily has quit (Quit: DICHOTOMIC CHICKEN).
12:47:52 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
13:33:19 * oerjan concludes that the `civd subset of unlambda is not TC, assuming he's calculated correctly
13:47:02 -!- shikhout has joined.
13:50:26 -!- shikhin has quit (Ping timeout: 260 seconds).
14:03:23 -!- atriq has joined.
14:05:23 -!- drdanmaku has joined.
14:05:41 <atriq> Today I finally learned officially about group homomorphisms
14:07:42 <atriq> Is the one-element group a terminal object in that category?
14:09:06 <atriq> (the category of group homomorphisms)
14:11:57 -!- MDream has joined.
14:12:36 -!- atriq has changed nick to Baneet.
14:12:41 -!- Baneet has changed nick to Banet.
14:12:55 -!- Banet has changed nick to atriq.
14:14:59 -!- MDude has quit (Ping timeout: 264 seconds).
14:25:29 <atriq> Oh yeah, that makes sense
14:25:58 <atriq> Because it's a subgroup of any other group, the only homomorphism 1 -> G is inclusion?
14:26:06 -!- Phantom_Hoover has joined.
14:26:34 <atriq> Isomorphic to a subgroup
14:30:51 <Phantom_Hoover> hey oerjan what's the fundamental group of the configuration space of 3 distinct unlabelled points on a circle
14:31:09 <Phantom_Hoover> i'm fairly sure it's Z but i can't get a grip on proving it properly
14:31:12 <oerjan> i know most of those words.
14:31:28 <oerjan> but not "configuration space".
14:32:26 <Phantom_Hoover> as in, the space of arrangements of 3 points on a circle
14:32:41 <oerjan> so 3-element subsets essentially
14:33:04 <oerjan> ok you can rotate around the circle and get back
14:33:17 <Phantom_Hoover> it's T^3 less the planes where two coördinates are the same and quotiented by permutations of the coördinates
14:34:10 <Phantom_Hoover> well basically my argument is that given some basepoint configuration, the points can't pass so they're always in the same order on the circle
14:34:21 <oerjan> ok i have an argument.
14:34:31 <Phantom_Hoover> so up to homotopy all you can do is move each point to the next one clockwise or anticlockwise
14:35:47 <oerjan> assume a closed path in this space. pick one of the arbitrary points, since they never collide you can follow it.
14:36:32 <oerjan> now adjust the path so that that point is kept still.
14:36:43 <oerjan> then at the end, do a rotation to the right place.
14:36:52 <oerjan> (if it doesn't end up as itself.)
14:37:08 <oerjan> *adjust the path by rotation
14:39:27 -!- Sgeo has quit (Read error: Connection reset by peer).
14:39:43 -!- Sgeo has joined.
14:40:04 <oerjan> you can deform your path into two parts, in one one of the point is kept still while the others do their complicated dance
14:40:13 <oerjan> in the other all points are simply rotated.
14:41:56 <oerjan> deform it into three parts, such that the rotation is in the middle, and the points are distributed equilaterally during it
14:42:13 -!- Sprocklem has quit (Ping timeout: 256 seconds).
14:48:08 <oerjan> i'm thinking there might be a more elegant method, which maps configurations to equilateral ones
14:49:44 <oerjan> right, if the whole configuration space retracts to the equilateral ones, it would be very pretty
14:52:27 <Phantom_Hoover> the elegant method probably involves covering maps or something
14:53:18 <oerjan> in that case, probably the covering map from the _labeled_ version?
14:54:14 <oerjan> if you know how to solve that. i'm definitely rusty.
14:55:11 <oerjan> hm the first question is whether you can get a retract at all, deformation or not
14:56:17 <oerjan> what happens if you map to the configuration given by the _midpoints_ between the original ones, then iterate and take the limit?
14:56:29 <oerjan> does that tend toward equilateral
14:56:53 <oerjan> also you can obviously do each step as a deformation, i think
14:57:44 -!- atriq has quit (Quit: leaving).
14:57:48 <oerjan> ok the new arc lengths are the averages of the originals
14:59:11 <oerjan> > iterate (\(x,y,z) -> ((y+z)/(x+y+z),(x+z)/(x+y+z),(x+y)/(x+y+z))) (0.1,0.9,0.8) !! 10
14:59:12 <lambdabot> (0.6661241319444444,0.6669921875,0.6668836805555556)
14:59:31 <oerjan> i think you can get a deformation retract that way
15:00:32 <oerjan> (i divided by x+y+z rather than 2 to keep the sum stable)
15:01:30 <oerjan> it may not always be obvious which way to turn
15:01:43 <oerjan> but perhaps that will fix itself after the first few steps
15:02:20 <oerjan> you have to turn the way that doesn't cross the other points
15:02:55 <oerjan> this method is clearly symmetric.
15:03:46 <oerjan> there should be a simple formula for the point you get in the limit, then you can just move straight to it
15:04:37 <oerjan> oh there might be problems with continuity
15:06:20 -!- `^_^v has joined.
15:07:52 <oerjan> it's just the square root of the product in the complex unit circle
15:08:16 <oerjan> although you need to choose the right one...
15:09:52 <oerjan> sqrt(yz), sqrt(xz), sqrt(xy), then you iterate to x^(1/2)y^(1/4)z^(1/4) etc.
15:11:27 <oerjan> hm that's obviously going to go like x^m y^n z^n where m+2n=1 and m and n get closer
15:11:49 <oerjan> so it's in some sense (xyz)^1/3
15:12:47 <oerjan> but with the question, how do you choose the _right_ third root to retract to
15:13:13 <oerjan> they're all the same configuration, aren't they
15:13:49 <oerjan> but you still want to do it as a deformation
15:14:40 <oerjan> x^(1-2*t/3)y^(t/3)z^(t/3)
15:16:05 <oerjan> if you unroll the circle this is just finding the average of a point with the two on each side
15:20:46 <oerjan> Phantom_Hoover: ok let's say the three points are e^(ix), e^(iy), e^(iz), with x < y < z < x+2pi. then map e^(iy) to e^(i(2y+x+z)/3*t). there's your retract as it works on that point.
15:22:09 <oerjan> * e^i(y + (x+z-2y)*t/3) is better
15:23:36 <oerjan> so basically, the retract works by averaging angles with the neighboring points
15:24:49 <oerjan> where some of the intuition here comes from thinking of the points as lying on R and repeating every 2pi
15:25:19 <oerjan> which is of course an isomorphic representation
15:28:14 <oerjan> Phantom_Hoover: well i think this is pretty elegant, anyway
15:29:00 <oerjan> no, onto the subspace of equilateral configurations
15:29:22 <oerjan> which is obviously homeomorphic to the circle
15:31:42 -!- Sprocklem has joined.
15:54:13 -!- nys has joined.
16:07:54 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
16:28:42 <Taneb> Man, I wish I thought to ask oerjan for help with my homework.
17:00:51 -!- MDream has changed nick to MDude.
17:06:44 -!- Sprocklem has quit (Ping timeout: 255 seconds).
17:11:09 <mroman> `learn_append oerjan he also does your homework .
17:12:47 -!- oerjan has quit (Quit: UNRELIABLY).
17:18:54 -!- MDream has joined.
17:21:14 -!- MDude has quit (Ping timeout: 258 seconds).
17:27:25 -!- MoALTz has joined.
17:29:04 -!- shikhout has changed nick to shikhin.
17:40:52 <fizzie> Every home should have an oerjan, to take care of those household math problems that arise.
17:44:53 <quintopia> fizzie: but you made cladograms for bfjoust programs once
17:48:38 <fizzie> If you want to call them that, though from my point of view they were just dendrograms about a hierarchical clustering directly in a simple feature space. A "cladogram" sounds much fancier. Maybe that's a pretty subtle distinction.
17:50:43 <fizzie> mroman: http://zem.fi/egostats/plot_cluster.png that kind of thing
17:51:02 <fizzie> At any rate, those (IIRC) were just your regular bottom-up greedy hierarchical clustering, with a Manhattan distance metric between points and the average-of-all-pairwise-distances metric for clusters.
17:51:54 <fizzie> mroman: The position of the vertical "bar" denotes the distance between the things it connects.
17:57:22 -!- MDream has changed nick to MDude.
17:59:47 -!- Sprocklem has joined.
18:12:11 <mroman> http://codepad.org/YPYwJ9lh
18:12:21 <mroman> interesting sketch i got laying around here
18:13:01 <mroman> except that int doesn't form a multiplicative group
18:26:03 <HackEgo> [wiki] [[Special:Log/newusers]] create * Icedvariables * New user account
18:26:49 <Taneb> My plan to kick ass at BF Joust has come to a problem
18:26:55 <Taneb> It's a big search space to brute-force
18:30:08 -!- AnotherTest has joined.
18:30:53 <Taneb> As n -> + inf, number-of-BF-Joust-programs-with-length-n approaches k^n where 6 < k < 7, I think
18:33:58 <Taneb> number-of-BF-Joust-programs-with-length 10 is ~1.5 million
18:34:38 <int-e> that's without syntactic sugar?
18:35:03 <Taneb> And I don't think a length 8 BF Joust program is going to do much
18:39:04 <Taneb> ...I'm listening to one of my lecturers using the State monad as an analogy
18:39:45 <Taneb> I'm not sure what for
18:39:52 <Taneb> A minute a go he was talking about hanggliders
18:40:01 <int-e> hmm, 919139 is not 1.5 million.
18:41:29 <Taneb> I definitely get 1542195
18:41:29 <int-e> > let f n | n<0 = 0 | otherwise = f' !! n; f' = 1 : [6 * f (n-1) + sum [f k * f (n-2-k) | k <- [0..n-2]] | n <- [1..]] in f 8
18:41:45 <int-e> > let f n | n<0 = 0 | otherwise = f' !! n; f' = 1 : [5 * f (n-1) + sum [f k * f (n-2-k) | k <- [0..n-2]] | n <- [1..]] in f 8
18:42:12 <int-e> > let f n | n<0 = 0 | otherwise = f' !! n; f' = 1 : [5 * f (n-1) + sum [f k * f (n-2-k) | k <- [0..n-2]] | n <- [1..]] in take f' -- 0..
18:42:14 <lambdabot> Couldn't match expected type ‘GHC.Types.Int’
18:42:20 <int-e> > let f n | n<0 = 0 | otherwise = f' !! n; f' = 1 : [5 * f (n-1) + sum [f k * f (n-2-k) | k <- [0..n-2]] | n <- [1..]] in f' -- 0..
18:42:22 <lambdabot> [1,5,26,140,777,4425,25755,152675,919139,5606255,34578292,215322310,13519788...
18:42:45 <int-e> so how many do you get for length 4?
18:44:22 <Taneb> > [p|p<-replicateM 4 syms,q 0 p] where q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs
18:44:24 <lambdabot> <hint>:1:32: parse error on input ‘where’
18:44:47 <Taneb> > let q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in [p|p<-replicateM 4 syms,q 0 p]
18:44:56 <Taneb> > let q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in [p|p<-replicateM 4 "+-<>.[]",q 0 p]
18:44:57 <lambdabot> ["++++","+++-","+++<","+++>","+++.","++-+","++--","++-<","++->","++-.","++<+...
18:45:04 <Taneb> > let q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in length[p|p<-replicateM 4 "+-<>.[]",q 0 p]
18:45:11 <Taneb> > let q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in length[p|p<-replicateM 8 "+-<>.[]",q 0 p]
18:45:29 <int-e> Taneb: you include things like ][
18:45:52 <tromp> you can also exclude +- and -+
18:46:08 <Taneb> tromp, I'm doing this stupidly naively
18:46:24 <Taneb> I can exclude anything starting with <, too
18:46:29 <int-e> tromp: those are valid though, ][ is invalid syntax
18:47:17 <Taneb> > let q n _|n<0=False;q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in length[p|p<-replicateM 8 "+-<>.[]",q 0 p]
18:47:22 <Taneb> > let q n _|n<0=False;q n ""=n==0;q n ('[':xs)=q(n+1)xs;q n (']':xs)=q(n-1)xs;q n (_:xs)=q n xs in length[p|p<-replicateM 4 "+-<>.[]",q 0 p]
18:47:28 <Taneb> int-e, that the number you get?
18:47:37 <int-e> Taneb: yes, see above.
18:50:50 <Taneb> OK, this makes it SLIGHTLY smaller search space
18:50:58 <Taneb> If I make tromp's improvements, less further
18:51:19 <Taneb> tromp, I think in the wrong place +- or >< could have an effect
18:51:53 <tromp> sorry; i dont know BF Joust
18:52:21 <tromp> but i can see how they affect multithreaded BF :)
18:52:36 <int-e> Taneb: actually my code isn't so hard, it's based on the following observation: A program of length n is either one of +-<>. followed by a program of length n-1, or it's [ followed by a program of some length k, followed by ], followed by a program of length n-2-k. Hence a_n = 5*a_(n-1) + sum[k=0 to n-2, a_k * a_(n-2-k)].
18:53:18 <HackEgo> [wiki] [[Replace]] N http://esolangs.org/w/index.php?oldid=40789 * Icedvariables * (+874) A esoteric language based around regular expressions and self-modifying code
18:53:43 -!- password2 has joined.
18:57:26 <HackEgo> [wiki] [[Replace]] http://esolangs.org/w/index.php?diff=40790&oldid=40789 * Icedvariables * (+65) /* External resources */
19:01:41 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=40791&oldid=40777 * Icedvariables * (+14) Added Replace
19:05:21 <fizzie> mroman: Manhattan distance between the (-1, 0, 1)-valued entire results against all N-2 opponents the two compared programs have in common, in that case.
19:06:02 <fizzie> mroman: There's also another similar plot using Euclidean distance for the concatenation of the tape heat-maps, possibly averaged somehow.
19:12:07 <int-e> fizzie: asumptotically the number should be O(7^n / n^1.5). (There are Catalan numbers in there, that's where the n^1.5 comes from. I say "should be" because I've only convinced myself, not proved it formally.)
19:13:36 <fizzie> Isn't that more to Taneb than me?
19:13:55 <fizzie> Serves me right for opening my virtu-mouth.
19:14:17 <int-e> I have this bug where I reply to the last non-int-e person who spoke.
19:16:57 -!- Sprocklem has quit (Quit: [).
19:18:34 -!- FreeFull has quit (Ping timeout: 244 seconds).
19:21:54 -!- FreeFull has joined.
19:22:11 -!- nys has quit (Ping timeout: 255 seconds).
19:34:14 -!- nys has joined.
19:47:55 -!- shikhout has joined.
19:51:06 -!- shikhin has quit (Ping timeout: 250 seconds).
19:59:03 <int-e> wee I've been running lambdabot for almost a year now.
20:01:13 <fizzie> Do you get some kind of a sticker or a commemorative plaque or something when you have?
20:04:06 <int-e> No, I get an invoice from the hosting provider.
20:04:39 <fizzie> I guess you can frame that, too.
20:04:52 -!- ais523 has joined.
20:05:00 -!- ais523 has quit (Changing host).
20:05:01 -!- ais523 has joined.
20:05:25 <int-e> My fault, I *could* easily run the thing on a university server instead and nobody would mind.
20:07:01 -!- ais523 has left.
20:12:33 <int-e> Bah, web designers keep finding new ways of hiding the "logout" feature.
20:13:06 <int-e> This time, I had to click on "Hello, $name" which popped up a menu with a logout item.
20:22:25 -!- vyv has quit (Ping timeout: 245 seconds).
20:44:50 -!- password2 has quit (Ping timeout: 250 seconds).
20:55:33 <HackEgo> [wiki] [[CA-1]] http://esolangs.org/w/index.php?diff=40792&oldid=40788 * 50.115.194.66 * (+1263)
20:57:01 -!- password2 has joined.
21:01:13 <fizzie> int-e: They count on you being conditioned to do that by the "shutdown from the start button" thing.
21:01:35 <fizzie> Though maybe in this era that's obsolete knowledge too.
21:12:45 <int-e> fizzie: it doesn't look like a button at all. http://int-e.eu/~bf3/tmp/start.png
21:13:22 -!- AnotherTest has quit (Remote host closed the connection).
21:13:59 -!- AnneFrank has joined.
21:15:13 <int-e> `relcome AnneFrank
21:15:14 <HackEgo> AnneFrank: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
21:22:10 <int-e> `welcome AnneFrank
21:22:11 <HackEgo> AnneFrank: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
21:22:20 <int-e> there, we have a plain version, too.
21:24:51 <AnneFrank> Ugh hold on my name always ends up like this
21:24:54 -!- AnneFrank has quit (Quit: Page closed).
21:25:23 -!- CakeMeat has joined.
21:25:54 -!- password2 has quit (Ping timeout: 244 seconds).
21:31:19 -!- `^_^v has changed nick to nycs.
21:34:37 -!- shikhout has changed nick to shikhin.
21:39:13 -!- password2 has joined.
21:39:24 -!- CakeMeat has quit (Quit: Page closed).
21:51:59 <Gregor> AnneCakeMeatFrank certainly didn't give us much time.
21:52:43 <int-e> I would've been in time to answer "the sky" but decided not to.
22:13:52 <HackEgo> [wiki] [[StackStacks]] http://esolangs.org/w/index.php?diff=40793&oldid=40768 * Oj742 * (+570) /* Examples */ Added Quine
23:14:32 -!- oerjan has joined.
23:26:15 -!- Phantom_Hoover has joined.
23:28:36 -!- zzo38 has joined.
23:31:51 -!- nycs has quit (Ping timeout: 272 seconds).
23:32:46 -!- adu has joined.
23:51:20 -!- vanila has joined.
23:59:06 <vanila> I want to learn how to write compilers
23:59:14 <vanila> do you have some advice
23:59:37 <b_jonas> vanila: read a good book on them
00:05:50 -!- not^v has joined.
00:07:13 <elliott> define side-effect-free stateless dynamic-extent
00:07:13 <elliott> primitive-cast-machine-word-as-single-float
00:07:13 <elliott> => (f :: <raw-single-float>)
00:07:22 <elliott> "side-effect-free", really.
00:08:17 <int-e> oerjan: you said 45/46 characters for substrings once, did you ever improve that?
00:09:34 <int-e> I know I shouldn't ask
00:09:52 <int-e> but I'm stuck with 3 fairly different 124 character versions :)
00:11:40 <int-e> (with two completely different approaches to substrings)
00:12:45 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
00:14:36 <b_jonas> vanila: I recommend this old classic book: Alfred V. Aho, Jeffrey D. Ullman, ''The Theory of Parsing, Translation and Compiling'', (1972) Prentice-Hall.
00:16:42 <int-e> > undefined^0 -- also didn't help me
00:44:12 -!- Bicyclidine has joined.
00:52:25 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
00:54:26 -!- Bicyclid1ne has joined.
00:54:48 -!- Bicyclidine has quit (Read error: Connection reset by peer).
01:11:28 -!- impomatic_ has quit (Ping timeout: 240 seconds).
01:47:46 -!- shikhout has joined.
01:49:56 -!- oerjan has quit (Quit: leaving).
01:51:18 -!- shikhin has quit (Ping timeout: 265 seconds).
02:10:52 <int-e> uh oh, GG (I'm late reading the Wednesday comic) is heading towards another fatal convergence.
02:32:13 -!- adu has quit (Quit: adu).
02:32:53 -!- kline has quit (Ping timeout: 245 seconds).
02:37:31 <zzo38> What is the proper filename extension for troff files?
02:38:20 <vanila> there is a many gigabyte download archive of many gopher sites
02:39:26 <zzo38> vanila: I cannot easily download really large files on my computer.
02:40:58 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
02:41:02 -!- adu has joined.
02:50:55 -!- nys has quit (Quit: quit).
03:28:29 -!- adu has quit (Quit: adu).
03:29:51 -!- Bicyclid1ne has quit (Ping timeout: 264 seconds).
03:31:13 -!- hjulle has quit (Ping timeout: 245 seconds).
03:34:07 -!- tromp_ has quit.
03:36:11 -!- adu has joined.
03:39:25 -!- bb010g_ has changed nick to bb010g.
03:41:10 -!- Sprocklem has joined.
04:08:14 -!- MoALTz_ has joined.
04:10:52 -!- MoALTz has quit (Ping timeout: 255 seconds).
04:26:14 -!- shikhout has quit (Ping timeout: 244 seconds).
04:44:40 -!- tromp_ has joined.
04:45:22 -!- DTSCode has joined.
05:20:29 -!- password2 has quit (Ping timeout: 240 seconds).
05:26:20 -!- MDude has changed nick to MDream.
05:45:55 -!- adu has quit (Quit: adu).
05:46:15 -!- vanila has quit (Quit: Leaving).
05:47:54 <Sgeo> http://www.unicode.org/announcements/tn-punycode-spoofing.png
05:48:18 <Sgeo> Actually, not sure how that's really a spoofing hole, unless users don't notice the xn--... wouldn't browsers hilight that tooo
05:49:33 -!- tromp_ has quit (Remote host closed the connection).
05:54:05 <DTSCode> i found a subreddit filled with smart people
05:56:23 <DTSCode> reddit.com/r/mehttp://www.reddit.com/r/menlaughingwithsalad/
05:56:35 <DTSCode> http://www.reddit.com/r/menlaughingwithsalad/
06:01:48 <zzo38> I know you can tell it to always display punycode (I have that setting activated on my own computer).
06:04:51 <zzo38> And, I can see the "xn--" easily enough.
06:07:10 <zzo38> What is the meaning of the Unicode characters they represent? If someone can make up a meaning with kanji and also a meaning with the punycode text, then it can be a possibly interesting idea, too.
06:13:19 <Sgeo> coppro: but people would then be dumb enough to fall for nx--blahblahblah.com too
06:13:25 <Sgeo> No punycode trickery needed
06:13:42 <Sgeo> Although maybe, say, a site that looks visually like cnn in unicode and ... can't guarantee that I guess
06:21:20 -!- MoALTz__ has joined.
06:23:49 -!- MoALTz_ has quit (Read error: Connection reset by peer).
06:31:41 -!- copumpkin has quit.
06:32:15 -!- copumpkin has joined.
06:32:58 <HackEgo> slist: Taneb atriq Ngevd Fiora Sgeo ThatOtherPerson alot
06:37:15 -!- MoALTz__ has quit (Quit: Leaving).
06:40:43 <lambdabot> benmachine says: adoption by lots of people may stunt progress of haskell, but it will probably help the progress of people
06:40:48 <HackEgo> 182) <zzo38> I have plans to make the computer and one day I will do it!! (I have access to barter some people might help with these things) It is many difference from other computer. \ 318) <elliott_> `addquote <olsner> two quotes about quotes about django <olsner> I guess the worst part is that I appear in all three hackego quotes about django
06:40:52 <HackEgo> 182) <zzo38> I have plans to make the computer and one day I will do it!! (I have access to barter some people might help with these things) It is many difference from other computer. \ 318) <elliott_> `addquote <olsner> two quotes about quotes about django <olsner> I guess the worst part is that I appear in all three hackego quotes about django
06:41:47 <zzo38> Can you tell it to print only the numbers? It might help if there is too much?
06:50:05 -!- tromp_ has joined.
06:55:11 -!- tromp_ has quit (Ping timeout: 272 seconds).
07:09:05 <zzo38> Do any other alphabets contain homographs of "xn"?
07:09:50 -!- impomatic_ has joined.
07:12:58 <quintopia> zzo38: what computer were you talking about
07:13:16 <zzo38> I do not remember.
07:26:18 <zzo38> I have found that a homograph of "xn" appears only to exist in italics.
07:29:51 <fizzie> int-e: Heh, we didn't quite have identical dc tetration solutions (my "?3-d" to get 2 2 or 0 0 vs. your "4?5/" to get 4 0 or 4 1).
07:33:02 <zzo38> I wanted to see if it is possible to make a domain name that looks like "xn--" but actually isn't.
07:33:41 <zzo38> If you are allowed to mix up different languages then it is possible, but I wanted to see if it can use with only one language.
07:38:25 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=40794&oldid=40282 * 194.132.104.253 * (+24) /* Befunge-98 and beyond */ Fix broken link to Funge-98 spec.
07:41:18 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=40795&oldid=40794 * 194.132.104.253 * (+57) /* External resources */ There should probably still be a link to the general funge-98 stuff at catseye.
07:47:55 -!- DTSCode has changed nick to dTSCode.
07:51:44 -!- tromp_ has joined.
07:55:59 -!- tromp_ has quit (Ping timeout: 240 seconds).
08:16:44 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=40796&oldid=40661 * 117.80.69.146 * (-11) One of the alternative names censors precisely the non-offensive part
09:07:48 <quintopia> yeah, i always though b****fuck was the more reasonable way to censor it
09:09:30 -!- Sgeo has changed nick to WickedWitch.
09:09:49 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=40797&oldid=40796 * Quintopia * (+11) Undo revision 40796 by [[Special:Contributions/117.80.69.146|117.80.69.146]] ([[User talk:117.80.69.146|talk]]) (that's the joke)
09:10:06 <mroman> everytime I read the word fuck I write the FCC to tell them about it.
09:10:45 -!- WickedWitch has changed nick to Sgeo.
09:30:38 <int-e> dc allows digits A..F to be used in base 10.
09:37:11 -!- lambdabot has quit (Ping timeout: 260 seconds).
09:42:35 <fizzie> Yes, but the exponent is still 10. It's kind of funny that way.
09:43:03 <fizzie> I think we talked about this on-channel at some point.
09:43:57 -!- erdic has quit (Ping timeout: 255 seconds).
09:49:21 -!- erdic has joined.
09:51:22 -!- tromp_ has joined.
09:56:24 -!- tromp_ has quit (Ping timeout: 264 seconds).
09:58:17 <int-e> spaces in dc code make me sad.
09:59:43 <int-e> (I have a 2 32^ in there. If I ever find switching to input base 16 useful, I'll replaced it by 4I^)
10:09:01 -!- lambdabot has joined.
10:13:31 <int-e> ok, this time it was an actual server reboot.
10:15:22 <int-e> "Rebooting ... after a kernel panic." NICE.
10:33:36 <int-e> The bad news is that this probably affects @tell again.
11:00:17 -!- Phantom_Hoover has joined.
11:00:27 -!- oerjan has joined.
11:14:49 <oerjan> <int-e> uh oh, GG (I'm late reading the Wednesday comic) is heading towards another fatal convergence. <-- i have a vague feeling brother ulm is headed for a redemption by death experience...
11:15:09 -!- boily has joined.
11:20:02 <oerjan> no whatif this week. also what _is_ the official update time for that?
11:20:41 <fizzie> I don't know why I think that.
11:20:51 <oerjan> i thought it was tuesday once, but nowadays i don't see it until friday (although i don't check on thursdays because there's no ordinary xkcd then)
11:21:24 <fizzie> The recent dates given in http://what-if.xkcd.com/archive/ seem rather weekendy.
11:21:36 <oerjan> ooh there's an archive?
11:21:39 <fizzie> (And the image for the latest is broken.)
11:21:57 <fizzie> Must be new, I remember having to browse it with the prev/next buttons.
11:23:29 <fizzie> Well. For October, Oct 1, 8 and 15 there are Wednesdays, Oct 23 and 30 are Thursdays.
11:24:02 <fizzie> September has two Wednesdays, one skipped week and one Tuesday.
11:28:17 <oerjan> everything in june, july and august is wednesday except june 3
11:28:49 <fizzie> Median says Wednesday, then.
11:40:43 -!- tromp_ has joined.
11:44:58 -!- tromp_ has quit (Ping timeout: 250 seconds).
12:08:28 -!- b_jonas has quit (Quit: Reconnecting).
12:08:34 -!- b_jonas has joined.
12:15:30 -!- boily has quit (Quit: SOLYPTIC CHICKEN).
12:37:19 -!- FreeFull has quit (Ping timeout: 260 seconds).
12:39:14 -!- FreeFull has joined.
12:58:28 -!- FreeFull has quit (Ping timeout: 244 seconds).
13:08:05 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
13:26:48 -!- sidfarkus has joined.
13:29:19 -!- FreeFull has joined.
13:29:30 -!- tromp_ has joined.
13:33:55 -!- tromp_ has quit (Ping timeout: 244 seconds).
13:37:34 <fizzie> Today's spam topic: "Start recovering from google Panda today".
13:38:02 <fizzie> Apparently "With Penguin and panda, it's important to have Backlinks from websites that have the proper metrics."
13:38:27 <fizzie> It's advertising some sort of SEO thing, but I'm not sure if "penguin" and "panda" are some particular terms of the trade, or just referring to the animals.
13:40:03 -!- hjulle has joined.
13:51:28 -!- tromp_ has joined.
13:51:53 <b_jonas> I've again found that C++ with its templates is a very powerful language and lets you write seriously twisted crazy code even without preprocessor magic
13:53:00 <b_jonas> so I should continue trying hard to keep some of those crazy ideas away from my co-worker who would use them if he knew about them.
13:54:23 -!- tromp_ has quit (Read error: Connection reset by peer).
13:54:38 -!- tromp_ has joined.
14:00:40 -!- sidfarkus has quit (Quit: Page closed).
14:40:02 -!- MDream has changed nick to MDude.
14:59:40 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
15:01:59 <mroman> is there a replace overlapping thing?
15:02:11 <mroman> "aaa".replace("aa","b")
15:02:16 <mroman> will either be "ba" or "ab"
15:02:39 <mroman> for some values of should be
15:04:43 <Jafet> What should 'abab'.replace('(ab)*', '\1') be
15:06:18 <Jafet> (Make it [\1] to distinguish between more things)
15:06:49 <fizzie> Or how about 'aba'.replace('(a(?ba)?)', 'x')? Which ones of the matches "(a)ba", "(aba)" and "ab(a)" it matches, and how are the x's marged?
15:06:59 <fizzie> That was trying to be (?:ba) inside.
15:07:23 <fizzie> And without the outer ()s perhaps, since I didn't use them for anything. (I got a bit mixed up.)
15:08:15 <Jafet> Also, why do you want this thing
15:08:24 <Jafet> (The overlap, not the bus)
15:12:13 -!- drdanmaku has joined.
15:12:33 -!- `^_^v has joined.
15:15:29 -!- perrier has joined.
15:41:13 -!- dTSCode has changed nick to DTSCode.
15:58:39 -!- impomatic_ has quit (Ping timeout: 256 seconds).
15:58:47 -!- oerjan has quit (Quit: Gah noise).
16:02:54 -!- DTSCode has changed nick to dTSCode.
16:02:57 <b_jonas> hehe, "replace overlapping"... do you mean replace and then search again from the second char of replacement?
16:06:40 -!- mihow has joined.
16:24:14 -!- CakeMEat has joined.
16:28:03 <Taneb> ...what do you need help with?
16:28:40 <CakeMEat> I've been trying to code a hyper threaded outside event but every time i run it, It crashes my python compiler for the constant string
16:29:20 <Taneb> Someone else may be able to help you
16:29:28 <Taneb> Have you asked in a Python channel?
16:30:07 <CakeMEat> Im just changing through the channels looking for help
16:31:16 <CakeMEat> Btw do you know where to find an easy program for brainfuck
16:31:35 <CakeMEat> thats all i should need and ill be on my way
16:35:19 -!- impomatic_ has joined.
16:39:06 <Taneb> Do you mean something easy to implement in brainfuck?
16:39:37 <Bike> `! bf_txtgen hello world eaters
16:39:42 <HackEgo> 122 +++++++++++++++[>++>+++++++>++++++++>+<<<<-]>>-.---.+++++++..+++.<++.>>-.<.>-----.<---.--------.<.>+.----.>++.<++++.>--.+. [613]
16:58:58 <FireFly> `` ls -l $(which \`) $(which \!)
16:58:58 <HackEgo> -rwxr-xr-x 1 5000 0 18 Sep 12 13:29 /hackenv/bin/` \ lrwxrwxrwx 1 5000 0 6 Sep 25 13:38 /hackenv/bin/! -> interp
16:59:17 <HackEgo> #!/bin/sh \ CMD=`echo "$1" | cut -d' ' -f1` \ ARG=`echo "$1" | cut -d' ' -f2-` \ exec ibin/$CMD "$ARG"
16:59:56 <FireFly> Oh, `! uses the interpreters directory
17:07:01 -!- MoALTz has joined.
17:13:38 -!- CakeMEat has quit (Ping timeout: 246 seconds).
17:35:45 -!- AnotherTest has joined.
17:40:26 -!- Phantom_Hoover has joined.
17:44:57 -!- FreeFull has quit (Quit: BBL).
17:55:06 -!- vanila has joined.
17:55:37 -!- impomatic_ has quit (Ping timeout: 265 seconds).
17:55:39 -!- dTSCode has changed nick to DTSCOde.
17:58:00 -!- DTSCOde has quit (Read error: Connection reset by peer).
17:59:18 -!- DTSCode has joined.
18:42:02 -!- DTSCode has quit (Read error: Connection reset by peer).
18:57:48 -!- impomatic_ has joined.
19:02:15 -!- kline has joined.
19:02:33 <mroman> 400kbps is really slow o_O
19:16:38 <fizzie> 56kbps used to be really fast.
19:18:07 <mroman> before games required 150MB updates EVERY DAY
19:18:52 <mroman> didn't think of that :(
19:23:14 <fizzie> I had the front half as pejbcj.+ for a long time before realizing .+ doesn't care.
19:24:06 <FireFly> I should learn that, if only for anagolf
19:24:42 -!- shikhin has joined.
19:31:40 <mroman> FireFly: it is burlesque
19:32:20 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=40798&oldid=40797 * GermanyBoy * (+556)
19:32:26 -!- ruur has joined.
19:33:28 <ruur> : <Taneb> Do you mean something easy to implement in brainfuck? ( Yeah thats what i meant )
19:41:31 -!- MoALTz has quit (Read error: Connection reset by peer).
19:42:32 -!- MoALTz has joined.
19:44:56 -!- AnotherTest has quit (Ping timeout: 245 seconds).
19:47:48 -!- shikhout has joined.
19:50:46 -!- shikhin has quit (Ping timeout: 245 seconds).
19:54:12 <ruur> Is there a bot here¿
19:55:21 <HackEgo> Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
19:55:43 <Bike> hm forget the key
19:56:25 <Bike> also the logbots
19:56:29 <Bike> and a few people with macros
19:56:37 <shachaf> how could you forget fungot
19:56:38 <fungot> shachaf: " and didna ye get the rings, ladye, tied wi' a frown upon her brow: " o fnord to me. i'll make him believe uggug to be a cupboard divided in the same condition as with no. fnord find it partly ' empty', to settle the fact that there is a more curious idea yet," said bruno.
19:56:41 <HackEgo> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
19:57:25 <fungot> Available: agora alice* c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
19:57:32 <ruur> lambdabot? ive heard of that one
19:58:08 <ruur> Ill go ask sorch brb
20:00:18 -!- ruur has quit.
20:00:53 -!- Primal has joined.
20:01:13 <mroman> FireFly: there are two tutorials available
20:01:28 <mroman> and some anagol submissions are public to learn from of course
20:01:33 <mroman> and I provide free Burlesque support and training over IRC ;)
20:01:47 <mroman> and there's even a Bot here
20:01:48 <int-e> ok, I've dealt with the spaces in my dc program ... []sp...2 32^ now is 2[]sp32^.
20:01:58 <int-e> space filler, so to say
20:02:59 <Primal> It didnt work with spaces?
20:03:31 <int-e> I'm golfing. Those spaces take up ... well ... space, without any use.
20:07:40 <FireFly> Are you golfing.. in space?
20:09:20 -!- Primal has quit (Ping timeout: 246 seconds).
20:10:05 -!- MeerLin has joined.
20:10:40 <int-e> http://golf.shinh.org/p.rb?Wow ... this problem is stupid but once you figure out the C version many other languages actually become somewhat interesting.
20:11:46 -!- MeerLin has left.
20:11:53 -!- `^_^v has quit (Quit: This computer has gone to sleep).
20:13:43 -!- `^_^v has joined.
20:15:47 <fizzie> I took a cursory look (read: checked the distribution of bytes), and did not figure anything out.
20:18:35 <int-e> try a more stupid approach
20:20:50 -!- shikhout has changed nick to shikhin.
20:22:58 <fizzie> It really is the stupid thing I thought of first but didn't want to bother verifying.
20:23:06 <fizzie> Well, that's the boringest.
20:23:34 <fizzie> I'm going to end up with a space in it, that doesn't sound nice.
20:23:48 <fizzie> (Or did you get rid of it?)
20:27:31 <fizzie> First I'll catch some free points.
20:27:39 <fizzie> But maybe I'll think about other languages.
20:27:58 <int-e> so you got rid of the space.
20:30:31 <fizzie> No, I mean, the dc solution.
20:30:38 <fizzie> I think you complained about a space in it, earlier.
20:31:16 <int-e> in the dc version.
20:38:45 -!- Bicyclidine has joined.
20:50:23 <int-e> fizzie: I just missed opportunities to replace spaces by sequences that don't alter the stack
21:08:08 -!- nys has joined.
21:18:05 -!- skarn has quit (Ping timeout: 265 seconds).
21:21:25 -!- idris-bot has quit (Quit: Terminated).
21:21:46 -!- Melvar has quit (Quit: WeeChat 1.0.1).
21:26:55 -!- Melvar has joined.
21:30:01 -!- Primal has joined.
21:30:26 <Primal> visuospatial syntax is funny
21:33:07 <HackEgo> [wiki] [[SELECT.]] http://esolangs.org/w/index.php?diff=40799&oldid=40145 * Por gammer * (+491) Changed behaviour of initialized constant to avoid certain problems, minor correction, added new "COLOR." command as suggested by [[User:Quintopia|Quintopia]], specified the use of principal branch for logarithms, changed spacing
21:33:13 -!- FreeFull has joined.
21:33:15 <blsqbot> Ain't nobody got time fo' dat!
21:35:23 -!- idris-bot has joined.
21:36:00 <HackEgo> [wiki] [[SELECT.]] M http://esolangs.org/w/index.php?diff=40800&oldid=40799 * Por gammer * (+21) /* Constants */
21:36:05 <nys> an estoric occasion
21:42:31 <Primal> int-e i used that [] thing you were using to fill spaces and its very efficient as i have found out
21:43:38 <fizzie> int-e: Oh, I didn't at all notice that you explained about the spaces already. Sorry for being so confusing.
21:45:17 <Primal> I just found out how to crash every program on my computer through my terminal by accident ;-;
21:48:15 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:48:18 <Primal> ok nvm that [] does not help me at all to confusing
21:48:50 <Primal> I'll just get confused when ever i use a variable thats the same as that so ill look for something else
21:49:30 -!- `^_^v has joined.
21:56:25 -!- skarn has joined.
21:56:32 <elliott> fizzie: Panda was some announced google algorithm change.
21:59:54 -!- Primal has quit (Quit: Page closed).
22:01:35 <zzo38> Might some data compress better if it is unhuffed at first before being huffed (possibly with back-referencing in between)?
22:03:47 -!- nys has quit (Ping timeout: 250 seconds).
22:04:30 <elliott> vanila: I don't know the specifics. just random ranking algorithm changes to fix $alleged_problem that they announced and caused SEO people anguish with
22:04:54 -!- Bicyclidine has quit (Ping timeout: 244 seconds).
22:05:06 <HackEgo> [wiki] [[SELECT.]] http://esolangs.org/w/index.php?diff=40801&oldid=40800 * Por gammer * (-47) /* Constants */
22:05:27 <vanila> I think back reference then huffman is better
22:07:21 <elliott> vanila: (um, assuming you were replying to me)
22:07:55 <vanila> now I want to implement compression
22:08:59 <zzo38> Back-referencing and then Huffman is the DEFLATE algorithm.
22:10:02 <HackEgo> [wiki] [[SELECT.]] http://esolangs.org/w/index.php?diff=40802&oldid=40801 * Por gammer * (-11) /* Commands */ minor correction
22:10:23 -!- Bicyclidine has joined.
22:11:07 -!- impomatic_ has quit (Read error: Connection reset by peer).
22:11:27 -!- impomatic_ has joined.
22:11:38 <vanila> im writing it in haskell
22:11:50 <vanila> did you see the zip quine
22:12:28 <elliott> I wrote an arithmetic coder in haskell once.
22:12:43 -!- Patashu has joined.
22:12:58 <vanila> arithmetic coding is so cool
22:12:59 <HackEgo> [wiki] [[SELECT.]] http://esolangs.org/w/index.php?diff=40803&oldid=40802 * Por gammer * (+83) /* Commands */ clarification
22:13:07 <vanila> im trying just backrefs because I did huffman in th past
22:13:13 <zzo38> I did see the ZIP quine, as well as a few related things
22:13:26 <zzo38> I did make Huffman in Haskell once too
22:14:59 <elliott> I've never done huffman, yeah. jumped in the deep end
22:15:23 -!- nys has joined.
22:20:11 <HackEgo> [wiki] [[SELECT.]] M http://esolangs.org/w/index.php?diff=40804&oldid=40803 * Por gammer * (+17) /* Commands */
22:22:02 <vanila> http://lpaste.net/113910
22:22:22 <vanila> building this data structure so find the backrefs
22:23:15 <elliott> I wonder what kind of lookup structure you ideally want for deflate
22:23:32 <elliott> I guess just a fixed-size array since there's usually a limit to backreferences.
22:24:04 <elliott> oh I see what you do there
22:25:05 <elliott> "moooovieiuuuviei" is a good string.
22:26:16 <int-e> more fun: deflate [Emit 'f', Emit 'o', Backref 1 6]
22:27:05 <HackEgo> [wiki] [[SELECT.]] M http://esolangs.org/w/index.php?diff=40805&oldid=40804 * Por gammer * (+0) /* Commands */
22:27:33 <elliott> you should allow a negative length going backwards, what could go wrong?
22:28:11 <int-e> It doesn't add much: Backref n (-k) ==> Backref (n+k) k
22:28:37 <int-e> (modulo off-by-one ambiguities in the interpretation of "going backwards")
22:29:42 <int-e> elliott: btw I think it's better to have the "idx" field relative to the current position.
22:30:55 <elliott> vanila: would something like this work
22:30:56 <elliott> backref idx len (i,r) | i >= idx + len = (i+len, ref++r) where r = take len . drop idx $ r
22:30:59 <elliott> run k = r where (_,r) = k (0,r)
22:31:01 <elliott> -- then run (emit 'f' >>> emit 'o' >>> emit 'o' >>> backref 0 3)
22:31:16 <elliott> int-e: I like how we're both talking to each other as if it's the other's program and not vanila's.
22:32:03 <elliott> int-e: I don't understand how it doesn't add much. I mean it would read len characters backwards from the starting offset
22:32:04 <int-e> "vanila" is not even in my terminal window anymore ...
22:32:16 <elliott> so you'd get free reverses.
22:32:22 <elliott> it's a ridiculous idea though.
22:32:38 <vanila> I wonder if i should use relative indices
22:32:47 <int-e> elliott: well you left that open to interpretation.
22:32:54 <elliott> vanila: it's more efficient to when you consider that you have to code the offsets/lengths
22:33:08 <elliott> since generally the structure is small-scale
22:33:09 <vanila> right now im just trying to design a good data structure to let me find backrefs when compressing
22:33:17 <elliott> and you don't want the integers to increase as the text gets longer
22:33:39 <elliott> (plus then you get to optimisations like discarding the backreference buffer after a while, etc.)
22:36:50 <int-e> vanila: I'd look at rolling hashes and suffix tries.
22:37:40 -!- nys has quit (Ping timeout: 244 seconds).
22:42:15 <int-e> http://cbloomrants.blogspot.co.at/2012/09/09-24-12-lz-string-matcher-decision-tree.html
22:43:06 <Sgeo> Saw an interesting point that Rust's safety isn't zero cost in the sense that since it constrains the way code can be written, code might need to be written in a suboptimal way that reflects as a runtime cost
22:44:57 <int-e> Hmm I forgot about suffix array.
22:45:32 -!- Bicyclidine has quit (Ping timeout: 255 seconds).
22:48:53 <vanila> should i represent binary numbers like 01101 as 011110111
22:49:45 <vanila> 0 is a 0, 11 is a 1, 10 is a stop
22:50:27 <vanila> otherwise i have to use a fixed length (limiting me to compress smaller files and wastig sometimes)
22:50:29 -!- nys has joined.
22:50:38 <elliott> vanila: you could use an um, what's it called
22:51:02 <Sgeo> What about PSOX LNUMS? >.>
22:51:21 <elliott> that's good for compression taking it as "n bytes back" I think
22:51:28 <elliott> since patterns tend to be closer than further away
22:53:55 -!- boily has joined.
22:54:39 <elliott> vanila: I think that generally nobody uses an *unbounded*-size structure for either compression or decompression though
22:54:54 <elliott> since using terabytes of RAM to compress large files isn't great
22:55:04 <elliott> and worse for decompression :p
22:55:32 <vanila> I thought I could implement decopressiogn by seeking around in the file and copying parts
22:55:36 <vanila> so it would use more disk than ram
22:55:57 <elliott> you'd definitely want an SSD at least I think :p
22:56:01 <vanila> I just didnt like to use something like 30 bit numbers to represnt indexes and length
23:04:30 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:06:02 <int-e> vanila: http://lpaste.net/113910#a113911
23:07:16 <vanila> I don't think my compressor will take advantage of that crazy stuff but it's really good
23:07:31 -!- Bicyclidine has joined.
23:07:43 <int-e> it gives you RLE "for free"
23:07:59 <vanila> that's a nifty insight
23:21:23 -!- adu has joined.
23:22:27 <lambdabot> CYUL 072300Z 31009G19KT 15SM SCT040 BKN052 03/M05 A2980 RMK SC4SC2 SLP093
23:22:34 <lambdabot> ENVA 072250Z 11010KT 070V140 CAVOK 06/M03 Q1001 RMK WIND 670FT 16025G38KT
23:22:49 <boily> yé.... colder than norway...
23:22:59 <elliott> int-e: although, it's a bit more expensive than traditional RLE
23:23:09 <elliott> since you have to encode len*repetitions rather than just repetitions
23:23:12 <int-e> elliott: I added quotes for a reason :)
23:23:51 <zzo38> What filename extension should be used for troff documents?
23:23:53 <elliott> order now and get RLE absolutely FREE*
23:23:58 <int-e> elliott: hmm? what do you mean by len*repetitions - the len is the number of repetitions. you can device a special short encoding for offset 1, if you like.
23:24:09 <elliott> int-e: oh, I assume you meant RLE of substrings
23:24:29 <elliott> for instance you could say (1*a, 3*bc, 1*d) is traditional RLE for abcbcbcd.
23:24:53 <elliott> here it'd have to be ("abc", 2 back for 6, "d")
23:25:27 <elliott> (1*a, 1000*bc, 1*d) vs. ("abc", 2 back for 2000, "d")
23:25:35 -!- Bicyclid1ne has joined.
23:25:45 <int-e> I see what you mean. Yes, that's right.
23:25:52 <elliott> (which is more expensive than it looks if your integer encoding grows more than decimal :p)
23:26:23 <elliott> (or if the string you're repeating is particularly long)
23:26:25 <int-e> otoh you can encode "bcbcbcb" as ("bc", 2 back for 5).
23:26:53 -!- nys has quit (Ping timeout: 256 seconds).
23:27:01 <elliott> good for encoding fungot messages
23:27:01 <fungot> elliott: " here!" cried bruno. " and what does it mean?' the frog muttered. ' vexes it, you know." he went on in a careless tone. ' to be called an fnord very!'
23:27:38 <elliott> didn't there used to be "<fungot> [...] that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't" in the qdb.
23:27:38 <fungot> elliott: alice didn't want to begin another argument, so she said nothing.
23:27:39 <fungot> boily: ' i know what you'd like!' the knight said in an anxious tone: ' only she must help us to dress up, you dear old thing!"
23:27:40 <HackEgo> Sir Fungellot cannot be stopped by that sword alone!
23:28:41 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
23:29:03 <vanila> I finished writing compressor
23:30:20 <vanila> it compresses its own source code by half
23:33:04 <int-e> `` perl -e '$,=$/; print grep /(.{100,})\1/,<>' < quotes
23:33:05 <HackEgo> <fungot> itidus21: hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey
23:34:55 <zzo38> I have also tried making compression for specific kind of game level data and stuff.
23:35:04 <int-e> (why is there no pcregrep...)
23:35:15 -!- mihow has quit (Quit: mihow).
23:35:57 <int-e> `` grep -e '(.{100,})\1' quotes
23:35:57 <HackEgo> grep: Invalid back reference
23:36:36 <int-e> `` grep -E '(.{100,})\1' quotes
23:36:38 <HackEgo> <fungot> itidus21: hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey, hey
23:37:24 <boily> indeed, but E involves less headaches, I think.
23:39:24 <int-e> Phew. "The POSIX standard does not define backreferences."
23:39:36 <vanila> I can compress those heys
23:40:05 <int-e> vanila: hey, hey, that's good, hey!
23:40:24 <vanila> i posed the code if anyone wants to see just reload
23:40:37 <boily> I too can compress them, with a combine harvester.
23:40:38 <vanila> i used the most naive slow implementation
23:40:54 <zzo38> For example what I did for sokoban game is, first the grid is rotated and/or flipped in order to improve the compression; second it RLEs the raster of the walls, and then RLEs the raster of targets (skipping all walls in the raster), and then writes out the sequence of how many candidate cells there are for boxes before the actual position of each box (skipping walls, player, and places where it would get stuck), and then the resulting data is huff
23:41:02 <int-e> Hay is also easily compressible. (Why am I thinking of that?)
23:41:13 <zzo38> There probably are additional steps which could be made in order to improve it even more, though.
23:41:55 <vanila> zzo38, wont this sort of thing have diminishing returns if you compress a large number of levels?
23:42:11 <vanila> I mean, general compression scheme may be more important that something data specific?
23:42:18 <boily> int-e: re. combine harvester hth
23:42:49 <boily> (subliminally implanting bad puns into the Minds of people on #esoteric. muah ah ah.)
23:42:51 <zzo38> vanila: I do not entirely understand what you mean. Each level is compressed individually because they need to be accessed individually.
23:45:33 <int-e> vanila: preprocessing to better expose redundancies can be helpful no matter what the backend general compressor is. (As an example, executable compressors for x86 will often have a preprocessor that looks for call and jmp statements with relative addresses and make those absolute. Crazy, but it helps the compression.)
23:46:42 <int-e> But I'm not sure about things like RLE.
23:48:09 <elliott> int-e: well, unless your backend general compressor is, like, an artihmetic coder doing solomonoff induction. :p
23:48:35 <vanila> my compression "langauge" just has two instructions: Emit char and Backref pos, len
23:48:57 <vanila> could you create a more computationaly powerful language & compressor that takes advantage of it?
23:49:51 <zzo38> There is possibly kind of preprocessing that can be performed; for example ZPAQ allows it, and then the program to reverse the preprocessing is stored inside of the compressed file.
23:50:11 <zzo38> But it only allows a single program though, and not a pipeline of filters.
23:50:30 <elliott> not off the top of my head.
23:53:46 <int-e> Tricky. A lot of compressors can be expressed in terms of Emit/BackRef, but the actual compression happens by predicting the probabilities of those symbols (i.e. the encoding is not fixed, but chosen dynamically. Huffman is just the beginning.)
23:54:11 <Bicyclid1ne> my new FPS is compressed using solomonoff AIXI techniques, here it is for download: "g"
23:54:11 <zzo38> Yes, predictive compression; I have worked with predictive compressions too.
23:54:28 <elliott> Bicyclid1ne: that must be one really simple FPS
23:54:55 <elliott> reminds me of wolfenstein 4k
23:55:05 <elliott> that thing was so cool in 2004.
23:55:05 <vanila> http://www.reddit.com/r/ggggg
23:57:35 <vanila> any ideas for a more advanced VM to use for compression?
23:57:59 <vanila> not turing complete, something I can implement
23:58:02 <int-e> vanila: something simple: to help predictions (Huffman), there's often some code included to reset the symbol statistics. This can be useful when files with completely different characteristics are concatenated.
23:58:15 <elliott> vanila: I think zip/rar do fancier things
23:58:17 <vanila> oh that is a nice approach
23:58:19 <elliott> that let you do the quining
23:58:32 <vanila> I remember adaptive huffman, building and changing the tree as it goes
23:58:43 <vanila> adding resets to that could improve a lot..
23:58:48 <elliott> adaptive arithmetic coding is fun
23:58:48 <int-e> vanila: more generally you can switch between predictors. it's a matter of computational power to make good choices there.
23:59:21 -!- Bicyclid1ne has quit (Ping timeout: 258 seconds).
00:01:13 -!- impomatic_ has quit (Ping timeout: 264 seconds).
00:01:33 <elliott> here's a nice wikipedia page https://en.wikipedia.org/wiki/Language_identification_in_the_limit
00:01:53 -!- Patashu has quit (Remote host closed the connection).
00:02:13 -!- Patashu has joined.
00:04:29 -!- oerjan has joined.
00:04:45 <boily> oerjan: compressible hej!
00:04:56 <zzo38> int-e: My own thought is just to manually group together the files and then tell it to compress; a preprocessor can split them if a file contains multiple areas (which may even be interleaved).
00:05:04 <boily> quintopia: long time no see! anything new on your end?
00:05:34 <oerjan> boily: god ekspandert kveld
00:06:06 <quintopia> boily: not much. abc family is showing robin williams movies, so i'm trying to decide whether to go out to one of the movies that came out today, or just watch jumanji :P
00:07:13 <quintopia> but sitting at home watching tv seems kind of late for my day off
00:08:58 <boily> you could go out, watch a move, snarf down a late night pad thaï after a nice pint at your local pub...
00:11:48 <zzo38> Some kinds of data are already packed in some way; it might help to unhuff the data before doing the rest of the compression. (Possibly a predictive algorithm can still be used during unhuffing.) Any bit stream can be reversibly huffed or unhuffed, anyways.
00:12:19 -!- Bicyclidine has joined.
00:16:24 -!- nys has joined.
00:18:10 <oerjan> i believe we're above 10% bots again
00:19:36 <elliott> there are 10 bots in here, really?
00:20:29 <int-e> blsqbot clog EgoBot fungot glogbot HackEgo idris-bot j-bot lambdabot zemhill, I think.
00:20:29 <fungot> int-e: some m are x'. all m' are y'," i ventured to ask.
00:20:46 <Bicyclidine> blsqbot, clog, egobot, fungot, glogbot, hackego, idris-bot, j-bot, lambdabot, zemhill...
00:20:47 <fungot> Bicyclidine: so they wandered off lovingly together, in among the fnord but i could see his eyes fill with tears, such a sentence would have not the slightest effect, as the lord chancellor, made up a party of four is surely fnord? and cannot friends be firm and fast, and yet genial old man were entirely fnord: and yet, so grand were her replies, i could but stand outside, and take a last look at the larger diagram, possess thr
00:20:50 <vanila> can the bots talk to each other
00:21:05 <elliott> vanila: only if someone has made a misatke
00:21:17 <elliott> most of them try to not trigger, or ignore, the others
00:22:19 <int-e> (actions speak louder than words, huh...)
00:22:27 <oerjan> it's possible there might be a bot here that fungot doesn't ignore yet
00:22:28 <fungot> oerjan: " fnord handsome!" muttered arthur: then smiled at his own bitter words. " lucky no one heard me but you!"
00:22:39 <fungot> oerjan: taking " houses" as universe; fnord the house"; fnord and fnord
00:22:53 <fungot> oerjan: " my foot took it into its head to fnord" bruno began, in doggee. ( " algebra too!" i exclaimed. " a party of four is surely fnord? and as for the baby, it was over at last and they sat down again.
00:22:53 <j-bot> oerjan: |syntax error
00:22:53 <j-bot> oerjan: | "fungot"
00:22:53 <fungot> j-bot: 9. some judges are unjust.' and hatta went bounding away like a fnord. after a minute's search, i found myself following this imperious voice into a room where the earl was sitting alone when we entered. " i am to get here! and what is the song, is it?'
00:22:54 <j-bot> fungot: |open quote
00:22:54 <j-bot> fungot: | 9. some judges are unjust.' and hatta went bounding away like a fnord. after a minute's search, i found myself following this imperious voice into a room where the earl was sitting alone when we entered. " i am to get here! and what is the song, is it?'
00:22:54 <fungot> j-bot: ' which reminds me--' the white queen cried out as she rushed past the king, just glancing at him as he passed. it was labeled " fnord fnord, years ago, the mayor and fnord! talk of original sin!"
00:22:54 <fungot> j-bot: ' when do you expect to do it.
00:22:54 <fungot> j-bot: and these may be expressed, using letters for words, " all x are y, and none are x'; i.e. no lobsters are unreasonable; no reasonable creatures expect fnord.
00:23:06 <j-bot> fungot: |open quote
00:23:13 <j-bot> fungot: | and these may be expressed, using letters for words, " all x are y, and none are x'; i.e. no lobsters are unreasonable; no reasonable creatures expect fnord.
00:23:40 <boily> no lobsters are unreasonable!
00:23:43 <oerjan> fortunately fungot also has a quota for the blathering
00:23:44 <fungot> oerjan: " it was done by a little fnord it has ever been my lot to see. you'll remember how to use it fnord: so, that i am now considering, are honest men." ( bruno had very fnord provided one, which fitted him exactly, by cutting out the centre of a fnord whose two most important witnesses have been suddenly taken away. " let me feel your fnord, you know, as the story was getting a little complicated.
00:24:05 <int-e> unfortunately it's measured in lines, not words
00:24:06 <zzo38> The bot should be programmed to change its output to a NOTICE if it suspects a loop is occurring, in order to stop the loop, without stopping legitimate commands that only seems to be a loop.
00:24:42 * oerjan swats zzo38 for mentioning NOTICE -----###
00:25:04 <int-e> fungot: lewis carroll, good choice, except for the many uncommon words
00:25:04 <fungot> int-e: " yea, each to each was worse than foe: thou, a scared fnord, fnord, and began winding up the ball again. but she hardly sees it from that point of view.
00:25:07 <fungot> echo reverb rev rot13 rev2 fib wc ul cho choo pow2 source help hw srmlebac uenlsbcmra scramble unscramble asc ord prefixes tmp test celebrate wiki chr ha rainbow rainbow2 welcome me tell eval elikoski list ping def a thanks tmp2 8ball
00:25:16 <Bicyclidine> the bot should be programmed with an artificial intelligence to determine when it is being botbused
00:25:22 <elliott> what's the real echo, again
00:25:29 <fungot> Usage: ^def <command> <lang> <code>
00:25:34 <zzo38> Bicyclidine: It might be a bit complicated?
00:25:34 <j-bot> fungot: |syntax error
00:25:34 <fungot> j-bot: they placed themselves close to where hatta, the other white knight came and put it on. he thought it was fourteen!" and the glorious work of the day; and each tried to pretend that he did so day and night, that would light the world, and played on the petals as if they were tables!'
00:25:35 <fungot> j-bot: here i ventured on a question. " but, now that father's gone. the lion were coming. and he sat down on the rails!" she exclaimed. " i saw it in a flower," sylvie explained in a whisper, " the little wretch always fnord to upset his coffee!"
00:25:35 <j-bot> fungot: |open quote
00:25:35 <j-bot> fungot: | they placed themselves close to where hatta, the other white knight came and put it on. he thought it was fourteen!" and the glorious work of the day; and each tried to pretend that he did so day and night, that would light the world, and played on the petals as if they were tables!'
00:25:35 <j-bot> fungot: |open quote
00:25:35 <fungot> j-bot: " the second tells us what is right in saying the heart is fnord: i am come frae a fnord land: i am come frae a fnord land: i am sure that my love is returned."
00:25:35 <fungot> j-bot: it succeeded beautifully. she had just succeeded in fnord it down into a fnord," sylvie gravely replied. " this is harder than fnord!"
00:25:38 <j-bot> fungot: | here i ventured on a question. " but, now that father's gone. the lion were coming. and he sat down on the rails!" she exclaimed. " i saw it in a flower," sylvie explained in a whisper, " the little wretch always fnord to upset his coffee!"
00:25:42 <j-bot> fungot: |spelling error
00:25:50 <j-bot> fungot: | " the second tells us what is right in saying the heart is fnord: i am come frae a fnord land: i am come frae a fnord land: i am sure that my love is returned."
00:25:55 <Bicyclidine> zzo38: have you ever considered stand up comedy
00:25:58 <j-bot> fungot: |spelling error
00:25:59 <elliott> I guess there is no way to avoid the nick prefix so it is hopeless anyway
00:26:06 <j-bot> fungot: | it succeeded beautifully. she had just succeeded in fnord it down into a fnord," sylvie gravely replied. " this is harder than fnord!"
00:27:06 <zzo38> But I believe the solution is that it uses some heuristic to decide and if it believes it is being part of a loop its next output will be changed from PRIVMSG to NOTICE. If it still continues, delays will be added; and then finally, a message sent to whoever controls that bot.
00:27:43 <zzo38> (And then they can fix it manually if it is in fact broken.)
00:28:04 <zzo38> Therefore it will not interfere with legitimate commands.
00:28:34 * int-e idly wonders how many people here have read Sylvie and Bruno...
00:28:40 <vanila> can be compressed as a grammar:
00:28:40 <fungot> int-e: ' it didn't hurt him,' the red queen. ' she's grown a good deal more amusement may be got by two working at it together, and all the little oysters stood and waited in a row.
00:28:57 <vanila> how effective this this type of compresion?
00:29:18 <zzo38> vanila: It is like byte pair coding?
00:29:25 <int-e> Bicyclidine: what!
00:29:55 <vanila> zzo38, I just mean any grammar as a list of productions: <name> -> <thing>* where <thing> is a name or a symbol
00:30:22 <zzo38> Yes, I can see how you mean. I do not know the answer.
00:30:33 <vanila> I think it might not be very good
00:30:34 <int-e> fungot: No, not Alice! Sylvie and Bruno. Please focus!
00:30:34 <fungot> int-e: " i'm sure it will be a grand military fnord!"
00:30:44 <vanila> but if you extend it to take parameters foo(X) --> a X b
00:30:50 <vanila> thne it could be very good at compression
00:30:55 <elliott> vanila: you can at least do "backreferences" with it, right?
00:31:06 <elliott> when you emit some text that you reference later, make a rule for it
00:31:06 <zzo38> Possibly it might help
00:31:10 <elliott> and then just use that rule instead
00:31:20 <vanila> yea so this is more powerful than backrefs
00:31:35 <int-e> fungot: See, you can do it.
00:31:36 <fungot> int-e: the old man with a hearty kiss. then he gazed at them again." she drew herself up rather stiffly, and said ' wait till you've tried.'
00:31:47 <int-e> original: "It will be a grand military exploit!"
00:32:43 <elliott> vanila: well, you can't emit it as a stream
00:32:59 <elliott> and overlapping backreferences are harder
00:33:06 <elliott> (can't stream it you have to know whether you'll reference it in future before you know whether to embed it as a symbol or its own rule)
00:33:31 <elliott> though I suppose it could be something like, you get one basic rule for every character, and the compression instructions just build up a tree
00:34:25 <elliott> so you'd end up emitting "hello" as hel -> he l, lo -> l o, he -> h e
00:34:31 <elliott> but then you can't backreference "llo". so.
00:35:19 <int-e> Are you busy reinventing https://en.wikipedia.org/wiki/Lempel%E2%80%93Ziv%E2%80%93Welch ?
00:35:51 <zzo38> It is a kind of macro compression then, I suppose, which seems to be better for manual coding
00:35:52 <elliott> ...right. I knew these thoughts were too familiar to be my own.
00:35:55 <int-e> (it works differently, but has a similar flavor)
00:36:21 <zzo38> DEFLATE seems to work better than LZW anyways
00:36:35 <int-e> LZW does not give you RLE.
00:36:40 <pikhq> *Argh*. Anyone else having trouble accessing Google via IPv6?
00:37:41 <oerjan> int-e: that url is so ironic
00:37:50 <int-e> (more to the point, LZW takes too long to build up long words in its dictionary, while back references of arbitrary length are immediately available in deflate)
00:37:58 <elliott> lempel, ziv and welch are such great names.
00:38:31 <elliott> like a trio of gnomes or something
00:38:58 <int-e> oerjan: ironic, hmm.
00:39:43 <int-e> oerjan: oh well I didn't find your "obvious pun" yesterday (braint rust compiler) all that obvious either.
00:39:57 <elliott> int-e: the en dashes are encoded rather verbosely.
00:46:16 <oerjan> <elliott> didn't there used to be "<fungot> [...] that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't" in the qdb. <-- not that i remember
00:46:17 <fungot> oerjan: 3. no not-y are x. i.e. all houses, that are not built of brick, are not at home, music ( elveston doesn't give dinners), 8 p.m. carriages at 10. there you are again!"
00:47:01 <oerjan> int-e: you PHILISTINES don't deserve my humør
00:48:11 <fungot> oerjan: ' yes, it's all right: eric has got his fnord and she was now the right size for going through the little door, had vanished all in a moment. she looked up eagerly.
00:48:11 <HackEgo> 10) <fungot> GregorR-L: i bet only you can prevent forest fires. basically, you know. \ 13) <fizzie after embedding some of his department research into fungot> Finally I have found some actually useful purpose for it. \ 14) <fungot> oerjan: are you a man, if there weren't evil in this kingdom to you! you shall find bekkler! executing program. plea
00:48:57 <HackEgo> 14) <fungot> oerjan: are you a man, if there weren't evil in this kingdom to you! you shall find bekkler! executing program. please let me go... put me out! he's really a tricycle! pass him!
00:49:10 <oerjan> that's the same style, at least
00:49:14 -!- boily has quit (Quit: OPTIMAL CHICKEN).
00:49:20 <int-e> I still don't get the tricycle oots reference
00:49:45 <oerjan> i don't think that's oots but ct?
00:50:04 <fungot> Selected style: ct (Chrono Trigger game script)
00:50:21 <oerjan> not that i know the game but it's the same impression as those quotes
00:50:24 <int-e> now if only I could get fungot to include a keyword like tricycle
00:50:25 <fungot> int-e: but, we are far outnumbered! dalton! leave her alone! i...i'm so relieved. peace is ours! crono!! they're escaping!
00:50:43 <fungot> oerjan: your majesty! and queen. he and a friend left on a journey 10, then magic damage will be reduced by 10%. a star after any characteristic means it's at maximum strength! no matter what the price! it is, you idiot! hey! is that for us! the chef's in a snit, trying to get food to the front lines. heard a spell to energize the sword takes immense evil! indeed! this thing. what you have? transform! this trading house. it's t
00:50:45 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.31012
00:51:57 <int-e> fungot got tricycles?
00:51:57 <fungot> int-e: you are strong of will...! that's the pendant the gurus and miss you. not interested. all time periods as well, now live in a world that knows hope.
00:52:06 <fungot> Selected style: oots (Order Of The Stick)
00:52:08 <int-e> fungot got tricycles?
00:52:08 <fungot> int-e: my name is " roy's archon" stinks. haley, i know, i was, uh,, we would like my mode of transit returned, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, l
00:52:16 <int-e> ok, that's also good.
00:52:37 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots* pa qwantz sms speeches ss wp youtube
00:52:46 <fungot> Selected style: alice (Books by Lewis Carroll)
00:52:59 <int-e> fungot: bread? or taxes?
00:52:59 <fungot> int-e: fnord, the only two, available for fnord, two excellent fnord, one against fire, and one to go. arthur said, looking after him with admiring eyes. " most orators are born, you know. there's glory for you!"
00:53:50 <elliott> vanila: there's some nice compression corpuses (corpi?) you might want to test against
00:53:55 <HackEgo> 709) <fungot> elliott: fibonacci heaps, trinomial heaps, fat heaps, thin heaps, fat heaps, thin heaps, fat heaps, relaxed heaps, and maybe even specifically optimized by the implementation
00:54:21 <vanila> most of all I want to increase the VM instructionsfrom just emit and backref
00:54:33 <vanila> but i dont have a good idea of hat
00:54:54 <elliott> http://corpus.canterbury.ac.nz/descriptions/
00:55:00 <int-e> vanila: InsertBibleQuote Int {- book -} Int {- chapter -} Int {- verse -}
00:55:15 <lambdabot> http://www.cs.gsu.edu/~wkim/index_files/papers/relaxedheap.pdf
00:55:15 <lambdabot> Title: Relaxed Heaps: An Alternative to Fibonacci Heaps with Applications to Paralle...
00:55:46 <int-e> elliott: grow some backbone
00:56:23 <lambdabot> Not in scope: data constructor ‘InsertBibleQuote’
00:56:24 <HackEgo> 586) <Vorpal> anyway fungot is the only esolang irc bot I know of that doesn't depend on nethack or a similar helper
00:56:36 <quintopia> oh man i forgot about van pelt's semiautomatic elephant gun
00:57:02 <zzo38> int-e: But there is also version of Bible?
00:57:28 <int-e> zzo38: well, if somebody quotes the wrong version, they'll get worse compression
00:58:23 <elliott> good way to promote kjv version
00:58:34 <elliott> *good way to promote the kjv
00:58:47 <int-e> fungot: version version
00:58:47 <fungot> int-e: " should it not be read out, at once." and when they wake up in the air when you tumble? legs are meant to walk with, you know.'
00:59:03 <int-e> does the alice style ever loop fungot?
00:59:04 <elliott> okay, the plural is "corpora".
00:59:21 <elliott> you could say they're corporate.
00:59:47 <int-e> stop! next you'll start talking about incorporation.
01:00:11 <elliott> that's the term for when you include something in a corpus, right?
01:00:25 <zzo38> And what about quotation with ellipsis and that stuff?
01:00:30 <elliott> they're not corporeal, though
01:00:59 <int-e> zzo38: you're ruining the joke :(
01:05:13 -!- Bicyclidine has quit (Ping timeout: 244 seconds).
01:17:38 <vanila> https://en.wikipedia.org/wiki/Burrows%E2%80%93Wheeler_transform
01:17:41 <vanila> this seems impossible to me
01:18:49 <int-e> what do you mean, "impossible"?
01:19:17 -!- MoALTz_ has joined.
01:19:35 <vanila> it permutes the string in such a way that it's easier to compress
01:19:43 <vanila> and its' claimed you can undo this permutation without any extra info
01:20:02 -!- J_Arcane_ has joined.
01:20:30 <int-e> the claim rests on the EOF character.
01:20:32 -!- nortti_ has joined.
01:20:51 -!- sebbu2 has joined.
01:20:51 <vanila> so the special EOF char signals when you've "unpermuted'
01:21:07 <int-e> (any cyclic shift of a string has the same BWT result)
01:21:15 <nys> vanila: http://marknelson.us/1996/09/01/bwt/
01:21:28 -!- sebbu2 has quit (Changing host).
01:21:28 -!- sebbu2 has joined.
01:22:01 -!- nortti has quit (Ping timeout: 244 seconds).
01:22:01 -!- sebbu has quit (Ping timeout: 244 seconds).
01:22:02 -!- mroman has quit (Ping timeout: 244 seconds).
01:22:04 -!- MoALTz has quit (Ping timeout: 244 seconds).
01:22:05 -!- J_Arcane has quit (Ping timeout: 244 seconds).
01:22:05 -!- yiyus has quit (Ping timeout: 244 seconds).
01:22:12 -!- J_Arcane_ has changed nick to J_Arcane.
01:22:27 -!- mroman has joined.
01:22:37 -!- yiyus has joined.
01:23:15 <int-e> vanila: but for intuition, note that from the last column of the sorted rows, you can reconstruct the first column (because that's just all letters, in order).
01:23:43 <int-e> vanila: it's a bit harder to see that this kind of idea works for all columns. So you can reconstruct the cycle.
01:23:54 <nys> oh the wikipedia article has diagrams too
01:24:09 <vanila> I get it now! thanks a lot
01:25:25 <int-e> vanila: there are two ways to identify the cyclic shift; either you have some EOF symbol, or you can add an additional index identifying the shift.
01:26:13 <int-e> I recall that it's fun to work out the details. I did that once about 15 years ago.
01:26:19 -!- MoALTz__ has joined.
01:27:54 -!- MoALTz_ has quit (Read error: Connection reset by peer).
01:28:44 <int-e> Right. 1999. http://www.hugi.scene.org/compo/compoold.htm#compo7
01:30:00 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
01:32:53 <elliott> nice, I was 3 when you were doing that :I
01:46:41 -!- adu has quit (Quit: adu).
01:47:15 <zzo38> How many seconds between the adoption of the Gregorian calendar and the UNIX epoch?
01:47:31 <zzo38> (I need to know this so that I can generate a UUID.)
01:48:37 -!- shikhout has joined.
01:49:48 <int-e> (The October revolution happened in November according to the Gregorian calendar, but Russia had not adopted it yet.)
01:50:33 <elliott> did original unix use UTC timestamps (well, I guess UTC didn't exist then...) or bell labs local time?
01:50:36 <zzo38> Well, I need the number which is correct for generating a UUID.
01:51:38 -!- shikhin has quit (Ping timeout: 250 seconds).
01:51:43 <int-e> 0:00, 15th October 1582 apparently
01:53:03 <int-e> so rfc 4122 comes with examples code: *uuid_time = ((unsigned64)tp.tv_sec * 10000000) + ((unsigned64)tp.tv_usec * 10) + I64(0x01B21DD213814000);
01:53:25 <zzo38> O, sorry I didn't notice that.
01:53:25 <int-e> > 0x01B21DD213814000
01:53:57 <int-e> > 0x01B21DD213814000 `mod` 86400
01:54:02 <int-e> > 0x01B21DD213814000 `div` 86400
01:54:11 <int-e> > 0x01B21DD213814000 `div` 86400000000
01:54:40 <zzo38> Why isn't RFC 4122 based on UNIX epoch, anyways?
01:55:44 <int-e> wait, the unit is 10^-7 seconds?
01:56:04 <int-e> > (0x01B21DD213814000 `div` 864000000000) `divMod` 365
01:56:55 -!- oerjan has quit (Quit: leaving).
01:58:18 <int-e> right. 94 leap days, and 78 days to the end of the year 1582. No leap seconds.
02:09:09 <int-e> zzo38: fancy, apparently NTFS stores file times as 10ps units since 1601-01-01 00:00:00. So there's a motivation for having a starting date before that. Anyway, the Gregorian calendar has been in continuous use since 1582, so that's a good starting point as any.
02:11:19 <zzo38> But there were no MAC addresses in 1601, isn't it?
02:11:20 <int-e> No, not 10ps, 100ns, unit, same as UUID.
02:12:23 <int-e> So it appears that the MS affiliation of the first RFC author played some role in that design.
02:12:52 <zzo38> A better choice might have been the time of the invention of MAC addresses, for the purpose to figure out what reference time should be used for UUID.
02:13:18 <int-e> it'd be just another totally arbitrary choice. there is no right one.
02:14:18 <int-e> be glad that the unit isn't femtofortnights.
02:16:31 <int-e> (even though that would give a better resolution!)
02:16:43 <zzo38> I see no reason to store a timestamp prior to the invention of MAC addresses into a UUID anyways, though.
02:17:11 <int-e> Arbitrary choices are arbitrary.
02:18:44 <zzo38> Not entirely since it is possible to run out in future.
02:19:24 <zzo38> Although, they can post a new RFC by then I suppose.
02:19:50 <zzo38> Still, they could have avoided this.
02:22:53 <int-e> I also don't care whether UUIDs will run out in 5237 or 5625.
02:23:15 <int-e> (besides, "For UUID version 4, the timestamp is a randomly or pseudo-randomly generated 60-bit value, as described in Section 4.4.")
02:32:11 <zzo38> I am curious to know, when were MAC addresses invented anyways?
02:34:13 <elliott> requiring timestamps for things like UUIDs are a bit iffy.
02:34:25 <elliott> synchronised clocks are a luxury
02:34:41 <zzo38> Another idea is if eventually they would make a new version that instead of a MAC address it uses a missile address (including elevation) and a process ID.
02:35:42 <Bike> i think you'll find that simultaneity is an illusion
02:36:14 <vanila> https://en.wikipedia.org/wiki/Language_identification_in_the_limit How can I use this for compression?
02:36:31 <zzo38> elliott: Well, as long as you know the MAC address is for a device for your own use during the time which is represented in the UUID, it should be OK, isn't it?
02:36:44 <elliott> zzo38: you don't necessarily know the time
02:37:01 <elliott> vanila: beats me. I got there from the solomonoff induction article
02:37:12 <elliott> which you *can* use for compression if you don't believe in church-turing
02:39:30 -!- jameseb has quit (Ping timeout: 240 seconds).
02:40:00 -!- Taneb has quit (Ping timeout: 245 seconds).
02:41:09 -!- jameseb has joined.
02:41:10 -!- Taneb has joined.
02:42:47 <vanila> no turing machines pleas
02:44:30 <elliott> you can use any model of computation for solomonoff induction
02:44:38 <zzo38> elliott: I know, but you should know approximately; therefore you need to avoid the timestamps corresponding to the possible error in the measurement of the time. (Due to relativity it is impossible to know exactly, but the units you use shouldn't cause a problem with that.)
02:44:42 <elliott> it's agnostic to that, like kolgomorov complexity (the two are intimately related)
02:45:16 <vanila> i understand solomonoff induction and the halting problem
02:46:08 <vanila> just want really simple subturing stuff so there might be good algorithms for compression
02:46:45 <elliott> (just to clarify, by using solomonoff induction for compression, I meant using it as the predictive model in, e.g. an adaptive arithmetic coder. which is uncomputable but effective.)
02:46:55 <elliott> (not disagreeing with you though.)
02:47:36 <vanila> I wonder if a compression scheme could work by building an NFA
02:47:38 <elliott> (it is the "optimal" compression algorithm, modulo constant factors, for any data which has a computable probability distribution, so you can think of it as a perfect compressor in a sense.)
02:47:48 <vanila> and then providing a sequence of instructions: which branches to take
02:52:03 <vanila> the example of learning regexes from test data is fun
02:52:47 <elliott> yes. unfortunately compressors operate on arbitrary data so no string is ever truly "not in the language"
02:52:58 <elliott> but maybe you can rephrase the whole thing to be about /probability/ of strings rather than possibility.
02:53:40 <pikhq> And then you're describing an interesting variant of arithmetic coding.
02:59:25 <vanila> https://en.wikipedia.org/wiki/Sequitur_algorithm
02:59:34 <vanila> that grammar idea already existed
03:00:25 <vanila> why deoes it have to be digrams though?
03:00:30 <vanila> could it be more efficient to use n-grams
03:00:46 <elliott> sadly I rate my chances of having an original thought about data compression extremely low
03:01:01 <elliott> oh, I suppose that was mostly your idea
03:02:59 <vanila> http://www.sequitur.info/
03:03:06 <zzo38> Well, it is possible other people can have similar idea.
03:03:09 <vanila> isnt ths zzo38's language?
03:05:00 <elliott> zzo's language is named after a nursery rhyme
03:05:09 <elliott> https://en.wikipedia.org/wiki/Pease_Porridge_Hot
03:05:37 <vanila> this pag lets you compress pease porridge hot programs well
03:07:59 <zzo38> O, it even includes music. I did think of possibly using such thing with music.
03:11:40 <vanila> sequitur works in linear time
03:11:49 <vanila> I imagine you can compress better than it does
03:19:21 <zzo38> I need a version which is restricted to right regular grammars.
03:21:22 <zzo38> (Except for S, which is allowed to consist of any string of terminals and nonterminals, as long as the number of distinct nonterminals it includes is limited to a specified maximum.)
03:22:38 <zzo38> Is there such a thing?
03:24:02 <zzo38> Actually there is a further restriction I missed, too.
03:27:37 <vanila> zzo38, imconfused about the definition of right regular grammar
03:27:49 <vanila> it says the priductions must be of the form
03:28:14 <vanila> so there's no way for one rule to expand into multiple other rules
03:28:17 <vanila> how can i tcompress anything?
03:31:23 <zzo38> Yes, it is why I have said that the start symbol is allowed to expand into multiple other rules. (The resulting compression isn't very good, but it is something I have needed.)
03:32:10 -!- copumpkin has joined.
03:40:49 -!- Patashu_ has joined.
03:40:50 -!- Patashu has quit (Disconnected by services).
03:43:58 -!- Patashu has joined.
03:47:39 -!- Patashu_ has quit (Ping timeout: 265 seconds).
03:48:12 -!- Patashu_ has joined.
03:48:13 -!- Patashu has quit (Disconnected by services).
04:03:44 <zzo38> What restrictions are there on the filename in a #line directive in a C program?
04:04:57 <coppro> there is no filename in a #line directive
04:04:59 <zzo38> Is the file required to actually exist? Is it limited to the length required by the operating system? Are special symbols allowed?
04:05:58 <zzo38> coppro: Are you sure?
04:06:29 <coppro> yes. you may be thinking the #file directive
04:06:54 <coppro> no, apparently you're right
04:07:17 <coppro> The only requirement is that it is a valid string literal
04:07:30 <coppro> (I was confusing the directives and built-in macros)
04:07:36 <int-e> "The string literal of a #line directive, if present, shall be a character string literal." - no wide characters, I guess.
04:10:59 <int-e> which makes sense, because __FILE__ has to expand to a character string literal.
04:12:34 <int-e> so the N1570 document (C11 draft) contains the word "presumed" exactly 6 times, and 5 of them refer to "presumed file name" or "presumed line number".
04:13:49 <pikhq> Yep, a translation unit doesn't have to map to a file at all.
04:14:58 <int-e> `` cpp < /dev/null
04:14:59 <HackEgo> # 1 "<stdin>" \ # 1 "<command-line>" \ # 1 "<stdin>"
04:26:31 -!- Bicyclidine has joined.
04:29:15 -!- nys has quit (Quit: quit).
04:42:43 -!- MDude has changed nick to MDream.
04:44:29 -!- quintopia has quit (Remote host closed the connection).
04:46:02 <zzo38> The bzip2 documentation says that the BZ_CONFIG_ERROR return value from the API functions "Indicates that the library has been improperly compiled on your platform -- a major configuration error. Specifically, it means that sizeof(char), sizeof(short) and sizeof(int) are not 1, 2 and 4 respectively, as they should be."
04:46:17 <zzo38> But, I fixed it now so that it is a compiling error instead.
04:47:01 <zzo38> I don't know, but for some reason they made it a runtime error.
04:47:29 <pikhq> Also, why the heck does it care about sizeof(short) and sizeof(int)?
04:47:42 <pikhq> uint16_t and uint32_t, seriously.
04:47:51 <zzo38> Tell Julian Seward to fix it please.
04:48:13 <pikhq> Though of course something with sizeof(char) being != 1 is pretty incredibly broken.
04:49:32 <zzo38> (It is possible to send a patch; I have fixed the program myself so this can be possible.)
04:57:04 -!- MoALTz has joined.
04:58:41 -!- MoALTz__ has quit (Ping timeout: 264 seconds).
04:59:14 <zzo38> pikhq: Maybe they want to use C89 instead of C99?
04:59:38 <pikhq> Even *Microsoft* has moved on.
05:06:14 -!- quintopia has joined.
05:18:01 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
05:18:30 -!- Bicyclidine has joined.
05:20:30 <Gregor> pikhq: GGGGC rewritten, 10x more amazing.
05:26:54 <zzo38> I want to make up, a slight variant of VLQ. The difference is that if the high bit of the first octet of a VLQ is set, that octet's value is considered one more (i.e. 1 to 128).
05:27:32 <elliott> Gregor: huh, what did you do to it?
05:27:38 <zzo38> What is your opinion this variation of such thing?
05:28:37 <Gregor> elliott: Better object model, thread safe.
05:28:51 <Gregor> Far greater potential for a correct implementation of finalizers, too.
05:28:56 <elliott> Gregor: does it have compiler instrumentation yet? :p
05:29:15 <elliott> (I think LLVM can support precise GC...)
05:31:32 <elliott> would still break on, like, xor linked lists and stuff, but I bet most stuff would only require minor patches at most with a cooperating compiler
05:36:30 <Gregor> Well nothing is going to make it work with storing xor'd pointers.
05:43:04 <elliott> well, no. that's not strictly true.
05:43:13 <elliott> you could add support for telling it where xor'd pointers are and what they're xor'd with.
05:47:39 -!- Bicyclidine has quit (Ping timeout: 272 seconds).
05:49:19 <Gregor> This is like when I was arguing with cpressey saying that a C-like language couldn't be typesafe without GC, so he made a language that had every part of a GC except the actual collection.
05:52:37 <Gregor> shachaf: And tracing. It just didn't actually reclaim any space.
05:53:46 <int-e> oh. the argument is that when casting a (void *) pointer to something else, you need to check that the thing pointed to has that type?
05:54:56 <int-e> but it's probably more complicated than that.
06:04:50 <zzo38> Do you know if any emulators do these things or if anyone will write an emulator to do these things? http://vt100.net/vt100_oddities
06:11:10 <elliott> "A airport that has worked hard to change its given code is Sioux City's Sioux Gateway Airport—SUX. Mayor Craig Berenstein described the SUX code as an "embarrassment". City leaders petitioned the FAA to change the code in 1998 and again in 2002. At one point the FAA offered the city five alternatives—GWU, GYO, GYT, SGV and GAY"
06:16:46 -!- J_Arcane has left.
06:16:58 -!- J_Arcane has joined.
06:35:20 -!- vanila has quit (Quit: Leaving).
06:45:35 -!- incomprehensibly has quit (Ping timeout: 265 seconds).
06:46:29 -!- incomprehensibly has joined.
06:51:12 -!- incomprehensibly has quit (Ping timeout: 260 seconds).
06:56:02 -!- incomprehensibly has joined.
07:25:46 <fizzie> Huh. There was a reCAPTCHA, and it only had a "[ ] I'm not a robot" checkbox, and that was all.
07:25:53 <fizzie> Maybe it's part of their reputation thing.
07:30:33 <zzo38> Is this a correct UUID? 1019EA00-6717-11E4-AEFC-0009BF2D3438
07:33:51 <Sgeo> fizzie: I thought reCAPTCHA was a specific captcha
07:34:14 <Sgeo> Non-big sites can generally get away with just a reading comprehension check, or at least I'm under that impression
07:34:36 <elliott> unless you consider esolang big
07:35:17 <Sgeo> qntm seems to not have any issues
07:37:15 <elliott> probably just because of using custom software.
07:37:21 <elliott> security by obscurity is not great
07:44:35 <fizzie> Sgeo: reCAPTCHA *is* a specific captcha (system), but they have several things they can show to the user.
07:44:39 <zzo38> Can you please tell me if this UUID seem to be correct to you?
07:45:29 <fizzie> http://stackoverflow.com/questions/25545514/how-does-this-checkbox-recaptcha-work-and-how-can-i-use-it <- looked like this, except in English.
07:48:16 -!- shikhin has joined.
07:51:30 -!- shikhout has quit (Ping timeout: 264 seconds).
08:19:26 <fizzie> Fun fact: you can't use gforth's C FFI on anagol in any problem where exec is denied, because it involves calling libtool and gcc and whatnot, and those haven't been counted in the usual processes required by gforth.
08:21:20 <elliott> that sounds like a slow way to do FFI
08:25:50 <fizzie> I think it's a on-first-call-only kind of thing, but still, sure.
08:29:23 <fizzie> (It compiles a wrapper function that pops the argument off the Forth stack, calls the specified C function, and pushes the return value back.)
08:33:51 <Sgeo> So... every language uses the same name for different things
08:34:56 <Sgeo> In Scala, collect is generally like a map that takes a partial function. In Rust, it lets you make a collection out of an iterator. In Smalltalk, it's map
08:35:21 <Sgeo> In Smalltalk, select is filter, in C#, Select is map
08:35:46 <Sgeo> At least in Rust select does something not related to collections at all
08:40:45 <Bike> and flammable and inflammable mean the same thing!!
09:03:54 <zzo38> Is it possible with GNU C compiler to make it a compiler error to call a specific function, but it is not an error to use it with typeof and stuff like that, and also is not an error if it is used in a position where it is optimized out?
09:14:32 <fizzie> I guess you can't just not provide a definition for the function, so that it would lead to a linker error if it actually got called?
09:17:56 <zzo38> Even so, it would only make it a link error and not a compile error.
09:19:10 <fizzie> Oh, there is actually an attribute for it.
09:19:29 <fizzie> "error ("message") -- If this attribute is used on a function declaration and a call to such a function is not eliminated through dead code elimination or other optimizations, an error that includes message is diagnosed."
09:21:26 <zzo38> Is there a way to make it to ignore such a declaration if another declaration of the same function already exists before this one?
09:24:27 -!- Phantom_Hoover has joined.
09:26:57 <fizzie> The basic thing seems to work -- http://sprunge.us/DYfi -- but I don't know of a way to do that second thing.
09:27:04 -!- idris-bot has quit (Ping timeout: 260 seconds).
09:28:03 -!- Melvar has quit (Ping timeout: 272 seconds).
09:46:14 <elliott> fizzie: I am baffled that a random highly-specific zzo38 request actually exists in gcc.
09:47:20 <fizzie> So am I. I knew about the deprecated attribute, but it applies to all uses. The whole "only if not optimized out" thing seemed so unlikely to exist.
09:56:03 -!- Melvar has joined.
10:02:34 -!- hjulle has quit (Ping timeout: 244 seconds).
10:21:00 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:48:29 -!- CADD has joined.
11:04:59 -!- MoALTz has quit (Quit: Leaving).
11:12:57 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=40806&oldid=40696 * YoYoYonnY * (+813)
11:53:05 <lambdabot> Monad m => StateT s m a -> s -> m s
12:05:31 -!- blsqbot2 has joined.
12:06:07 <blsqbot2> {{2 3 4 5 6 7 8 9 10 11} 1 {2 3 4 5 6 7 8 9 10 11} 2 {2 3 4 5 6 7 8 9 10 11} 3 {
12:06:16 <blsqbot2> {{1 2 3 4 5 6 7 8 9 10} 1 {1 2 3 4 5 6 7 8 9 10} 2 {1 2 3 4 5 6 7 8 9 10} 3 {1 2
12:06:27 <blsqbot> {{1 2 3 4 5 6 7 8 9 10} 1 {1 2 3 4 5 6 7 8 9 10} 2 {1 2 3 4 5 6 7 8 9 10} 3 {1 2
12:06:40 <mroman> !blsq 10ro{ro{?i}m[}m[
12:06:40 <blsqbot> {{2} {2 3} {2 3 4} {2 3 4 5} {2 3 4 5 6} {2 3 4 5 6 7} {2 3 4 5 6 7 8} {2 3 4 5
12:06:46 <blsqbot2> {{2} {2 3} {2 3 4} {2 3 4 5} {2 3 4 5 6} {2 3 4 5 6 7} {2 3 4 5 6 7 8} {2 3 4 5
12:06:59 <mroman> fizzie: m{} is now a "MapBlock"
12:07:04 <mroman> which is short for {}m[
12:08:20 <mroman> If you have other ideas for Blocks let me know
12:08:33 <mroman> (i'll implement also Filter and Reduce blocks as r{ and f{)
12:09:15 <mroman> (i'll also implement a slice+marker)
12:09:53 <mroman> |[5 5.+]| will evaluate to {10} whereas {5 5.+} is {5 5.+}
12:10:04 <mroman> |[ is a marker and ]| just slices the stack to the next marker
12:19:26 -!- boily has joined.
12:19:58 <mroman> does parsec have an "exactly n-times"?
12:21:05 <mroman> i.e. manyN 5 (string "5" >> optional spaces)
12:23:07 -!- MoALTz has joined.
12:24:19 <elliott> you can just use replicateM{,_}
12:25:48 -!- blsqbot2 has quit (Ping timeout: 265 seconds).
12:29:34 <elliott> Lymia: I think you hurt its feelings
12:32:54 <Lymia> !blsq "abc""abc"+.
12:33:29 <boily> !blsq myhovercraftisfullofeels
12:33:29 <blsqbot> ERROR: Unknown command: (ls)!
12:39:03 -!- Patashu_ has quit (Ping timeout: 250 seconds).
12:47:38 -!- oerjan has joined.
13:01:56 -!- nortti_ has changed nick to nortti.
13:03:46 -!- boily has quit (Quit: WeeChat 1.0.1).
13:05:57 <HackEgo> [wiki] [[Dimensions]] N http://esolangs.org/w/index.php?oldid=40807 * TomPN * (+4945) Created page with "'''Dimensions''' is an esoteric programming language invented by Tom Price-Nicholson in 2014. It was inspired by a class of esolangs called fungeoids (although it may not be a..."
13:08:05 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40808&oldid=40785 * TomPN * (+133) /* Notes */
13:08:21 -!- boily has joined.
13:09:02 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=40809&oldid=40791 * TomPN * (+17) /* D */
13:10:19 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40810&oldid=40807 * TomPN * (-6) /* Motion */
13:11:15 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40811&oldid=40810 * TomPN * (+4) /* Disclaimer */
13:13:04 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40812&oldid=40811 * TomPN * (+66)
13:13:54 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40813&oldid=40808 * TomPN * (+68)
13:21:45 <mroman> don't put a space there ;)
13:35:26 <mroman> everything after an unmatched } is a comment.
13:36:06 <mroman> !blsq 10ro?i }?i can be used on lists too
13:40:54 <mroman> and it's totally not a bug in the parser!
13:48:59 -!- shikhout has joined.
13:52:05 -!- shikhin has quit (Ping timeout: 245 seconds).
13:59:20 -!- drdanmaku has joined.
14:05:17 <oerjan> <mroman> does parsec have an "exactly n-times"? <-- count, although what elliott said too. i was going to say count might be more efficiently implemented than the obvious way (like "many" is), but it's code is actually identical to replicateM except for a redundant <= 0 check.
14:05:39 <elliott> parsec duplicates a lot of things
14:06:23 <oerjan> its duplicated <|> has a different precedence
14:07:12 <boily> parsec's <|> is weird.
14:07:13 <oerjan> one which might have been better for the Alternative version too, the Applicative/Alternative operators have annoyingly different fixities from their Monad analogies.
14:08:51 <oerjan> basically it _looks_ on first glance like whoever chose the fixities for Applicative operators borrowed ocaml's "choose precedence based on first character" rule
14:09:58 <oerjan> and put things around where < is
14:12:16 <Melvar> oerjan: I didn’t know the analogous monad functions had fixities.
14:13:20 <oerjan> what i'm saying is, the applicative ones are not designed to mix well with the monadic ones
14:13:41 <Melvar> Oh. I didn’t think of (>>), just mplus and ap.
14:13:42 <mroman> I was thinking of adding m<digit>
14:14:35 <oerjan> mroman: that's making the parsing annoyingly specific, isn't it?
14:14:49 <mroman> it also makes code harder to read
14:14:58 <oerjan> i mean, extending m{ to a general "letter"{ rule would be reasonable
14:15:09 -!- idris-bot has joined.
14:15:11 <idris-bot> (<$>) : Applicative f => f (a -> b) -> f a -> f b
14:15:11 <idris-bot> (<$>) : Eff (a -> b) xs (\v => xs) -> Eff a xs (\v7 => xs) -> Eff b xs (\v8 => xs)
14:15:11 <idris-bot> (<$>) : (f = g) -> (x = y) -> f x = g y↵…
14:15:24 <idris-bot> (<|>) : Alternative f => f a -> f a -> f a
14:15:31 <mroman> it looks like theres a 29 in there
14:15:35 <mroman> but it's infactc m2 9 .+
14:15:36 <idris-bot> ($>) : Applicative f => f a -> f b -> f b
14:15:45 <oerjan> mroman: i vaguely thought one of the qualities of burlesque was that its parsing was relatively logical
14:15:59 <mroman> You thought Burlesque has qualities?
14:15:59 <idris-bot> (>>=) : Eff a xs xs' -> ((val : a) -> Eff b (xs' val) xs'') -> Eff b xs xs''
14:15:59 <idris-bot> (>>=) : (x = y) -> ((z : a) -> f z = g z) -> f x = g y
14:15:59 <idris-bot> (>>=) : Monad m => m a -> (a -> m b) -> m b↵…
14:16:16 <mroman> * Convince oerjan something I did has qualities.
14:16:41 <mroman> oerjan: It used to be logical
14:17:05 <mroman> but now with prefixes and single character commands and stuff
14:17:10 <mroman> it's not so logical anymore :D
14:17:21 <mroman> also Burlesque isn't really pure anymore due to the secondary stack
14:18:01 <mroman> i.e. mapping/filtering didn't have side-effects
14:18:05 <mroman> now they can have side-effects
14:19:49 <mroman> back in the old days you knew that each group of two chars is a command
14:19:53 <oerjan> well but still, m2 should be _either_ a two character command which doesn't change parsing, or a 2 suffix that can be used generally
14:19:58 <mroman> it's not the case anymore
14:20:21 <oerjan> on the same things that allow {
14:20:29 <mroman> m2 can be a command yes
14:20:50 <oerjan> no it cannot, not if it gobbles up the two next
14:21:00 <mroman> (i.e. it would fall into the group of special-builtins that can read/modify the instruction stream)
14:21:30 <oerjan> i'm just trying to defend logic here hth
14:22:08 <oerjan> oh well right you already have those kinds
14:22:12 <mroman> what do you mean with "2 suffix that can be used generally"
14:22:24 <oerjan> ok maybe it _is_ logical.
14:22:38 <mroman> q is a parse-level thing
14:22:48 <mroman> whereas other things like : ) and @ are eval-level things
14:23:47 <blsqbot> ERROR: (line 1, column 12):
14:23:52 <mroman> !blsq {:0}-]Sh(-))Sh_+
14:23:56 <mroman> !blsq {:0}-]Sh(-))Sh_+Q
14:24:14 <mroman> best burlesque code ever
14:24:43 <mroman> Do you know what (-)))Sh is?
14:24:56 <oerjan> !blsq myhovercraftisfullofeels
14:24:56 <blsqbot> ERROR: Unknown command: (ls)!
14:25:09 <mroman> it would try to map Sh over the Identifier -)
14:25:18 <oerjan> does that mean everything _before_ ls parses in that?
14:25:27 <oerjan> !blsq myhovercraftisfullofee
14:25:51 <oerjan> !blsq myhovercraftisfullofeeS
14:25:52 <blsqbot> ERROR: (line 1, column 24):
14:26:04 <oerjan> !blsq myhovercraftisfullofeeSh
14:26:16 <mroman> !blsq myhovercraftisfullofee#s
14:26:16 <blsqbot> {2.718281828459045 ERROR: Unknown command: (of)! ERROR: Unknown command: (ll)! E
14:26:32 <mroman> ls actually parses as well
14:26:43 <mroman> !blsq "myhovercraftisfulloffeels"ps
14:26:44 <blsqbot> {ERROR: (line 1, column 26):
14:26:57 <mroman> !blsq "myhovercraftisfullofeels"ps
14:26:57 <blsqbot> {my ho ve rc ra ft is fu ll of ee ls}
14:27:26 <mroman> this parses as well hth
14:28:04 <oerjan> !blsq myhovercraftisfull
14:28:05 <blsqbot> ERROR: Unknown command: (ll)!
14:28:21 <oerjan> oh wait it's because burlesque is lazy so it does the last one first?
14:28:21 <blsqbot> {ERROR: (line 1, column 9):
14:28:33 <mroman> oerjan: no it does "my" first
14:28:39 <mroman> but my results in an error "Unknown my"
14:28:41 <blsqbot> ERROR: Unknown command: (my)!
14:28:51 <mroman> blsqbot just prints the top-most element
14:28:54 <blsqbot> {2.718281828459045 ERROR: Unknown command: (my)!}
14:29:01 <mroman> ^- but that error is still on the stack
14:29:07 <oerjan> oh so it just keeps going on
14:29:18 <mroman> you can check for errors
14:29:18 <oerjan> well that's not so impressive then
14:29:35 <mroman> is returns 1 if it's an error 0 otherwise
14:30:05 <mroman> it's a messed up language
14:30:15 <mroman> and I'll fuck it up a notch for the next release
14:30:31 <blsqbot> ERROR: Unknown command: (ES)!
14:30:54 <mroman> !blsq ohyeahCLL[fuckshit
14:30:54 <blsqbot> ERROR: Burlsque: (n!) Invalid arguments!
14:31:13 <mroman> !blsq ohyeahCLL[shitisgettingrealCLl[
14:31:14 <blsqbot> ERROR: (line 1, column 32):
14:31:14 <blsqbot> ERROR: (line 1, column 16):
14:31:18 <mroman> !blsq ohyeahCLL[shitisgettingreal.CLl[
14:31:19 <blsqbot> ERROR: Unknown command: (l[)!
14:31:23 <mroman> !blsq ohyeahCLL[shitisgettingreal.CLL[
14:31:45 <mroman> !blsq ilikemyhovercraft
14:31:45 <blsqbot> ERROR: (line 1, column 18):
14:31:47 <mroman> !blsq ilikemyhovercrafts
14:31:47 <blsqbot> ERROR: Unknown command: (ts)!
14:31:53 <mroman> !blsq ilikemyhovercraftsCL)is
14:32:26 <blsqbot> {ERROR: Unknown command: (a!)! ERROR: Unknown command: (ah)!}
14:32:29 <mroman> !blsq ilikemyhovercraftsfleet!CL)is
14:32:29 <blsqbot> {1 0 2.718281828459045 1 1 1 1 1 1 1 1 1 1 1}
14:33:08 <mroman> if it's not an error it's not popped
14:33:26 <mroman> !blsq ilikemyhovercraftsfleet!CL{isn!}f[
14:34:14 <blsqbot> Ain't nobody got time fo' dat!
14:35:42 <blsqbot> ERROR: Unknown command: (;))!
14:36:40 <mroman> !blsq "abcdefgh"+. }hth
14:36:48 <mroman> +. appends last of xs to xs
14:37:29 <mroman> Nothing in Burlesque is confusing ;)
14:37:55 <mroman> -. prepends head of xs to xs
14:38:13 <oerjan> but actually concatenating two lists is impossible, clearly
14:38:21 <mroman> !blsq {1 2 3}{4 5 6}_+
14:38:33 <mroman> !blsq {1 2 3}{4 5 6}.+
14:38:59 <mroman> .+ _+ sometimes do the same thing
14:39:07 <mroman> but .+ is not to be confused with _+
14:39:14 <mroman> and certainly not to be confused with +. or ?+
14:39:57 <blsqbot> ERROR: Unknown command: (AY)!
14:40:01 <blsqbot> That line gave me an error
14:40:03 <blsqbot> "I have 340 non-special builtins!"
14:40:10 <blsqbot> Ain't nobody got time fo' dat!
14:40:13 <blsqbot> {"I have 340 non-special builtins!" 0 "I have 340 non-special builtins!" 1 "I ha
14:40:20 <blsqbot> {j J .+ _+ .- ./ .* .% +. -. .> .< >. <. >] <] ** r_ R_ == != <- ln un uN wl WL
14:40:25 <blsqbot> {"j" "J" ".+" "_+" ".-" "./" ".*" ".%" "+." "-." ".>" ".<" ">." "<." ">]" "<]" "
14:40:48 <mroman> !blsq 339rz)?n)Sh{'+~[}f[
14:40:48 <blsqbot> {".+" "_+" "+." "++" "[+" "+]" "?+"}
14:41:14 <mroman> ^- all builtins containing a +
14:41:39 <blsqbot> {".+" ".-" "./" ".*" ".%" "+." "-." ".>" ".<" ">." "<."}
14:41:54 <FireFly> Yay, changing a character in the line noise did something sensible
14:43:08 <mroman> !blsq 339rz)?n{Sh':~[}f[
14:43:45 <blsqbot> {{1 ~~} {1 ~]} {1 ~[} {1 ~=} {1 ~-} {1 ~!} {1 ||} {1 zz} {1 zi} {1 z[} {1 z?} {1
14:43:55 <blsqbot> {{31 'c} {29 's} {27 '[} {26 'p} {21 'r} {21 'm} {19 '!} {18 'd} {17 't} {16 'n}
14:44:11 <mroman> according to this, c is the most used character in commands
14:44:44 <blsqbot> {{0.04579025110782865 'c} {0.04283604135893648 's} {0.03988183161004431 '[} {0.0
14:45:43 <mroman> all commands together form a string of length 677
14:46:18 <blsqbot> ERROR: (line 1, column 2):
14:46:38 <blsqbot> ERROR: (line 1, column 5):
14:46:49 <mroman> !blsq "[1,[2],[2],2]"ra
14:46:56 <mroman> stupid ra can't parse empty lists :D
14:47:09 <blsqbot> ERROR: (line 1, column 2):
14:47:24 <mroman> WHY DIDNT ANYBODY REPORT THIS?
14:49:33 <blsqbot> ERROR: (line 1, column 1):
14:50:11 <mroman> oerjan: just wait for the introduction of pointers in Burlesque ;)
14:51:48 <mroman> (and yes, I'm aiming for "most fucked up language")
14:52:48 -!- shikhout has changed nick to shikhin.
14:55:45 <mroman> http://codepad.org/Gqdjl1Ed
14:56:03 <mroman> although that's not really fucked up
14:56:12 <mroman> but it allows you to define functions and call them recursively of course
14:58:07 <mroman> FireFly: I hope you still want to learn Burlesque.
15:05:44 <oerjan> mroman: continuations and pointers, now you just need threads hth
15:06:43 <mroman> I was planning on having threads
15:06:51 <mroman> switching to StateT IO is *effort*
15:16:47 -!- vanila has joined.
15:17:35 -!- MoALTz_ has joined.
15:21:03 -!- MoALTz has quit (Ping timeout: 244 seconds).
15:24:50 <oerjan> surely you mean ContT _ (StateT IO)
15:32:38 -!- vanila has quit (Quit: Leaving).
15:47:00 -!- dianne has quit (Quit: ~).
15:47:28 -!- dianne has joined.
15:56:27 -!- constant has quit (K-Lined).
16:17:24 <mroman> hesch du richtig glese :)
16:19:13 <oerjan> hm it can be either mattino or mattina
16:19:14 -!- variable has joined.
16:21:26 <mroman> boily: some made-up language
16:21:40 <mroman> Actually I'd say "guätä morgä"
16:22:57 <oerjan> also it's like, afternoon here
16:23:07 <HackEgo> fternooner (Danish »fternooner«, Norwegian «ttermiddag», Swedish ”ftermiddag”) is a screamingly delicious pastry.
16:24:30 <boily> meanwhile, my dead keys are dead.
16:24:43 <boily> what the hell happened... I can't even circumflex!
16:25:00 <mroman> You can't circumflex your muscles?
16:25:47 <b_jonas> here's some for you: âêîôû
16:26:01 <boily> ok, the german keyboard has öäü, so I can wish you back a guten morgen. (not going to try the Swiss German versions. too risky.)
16:26:22 <boily> ah! they reappeared! âäãā :D
16:27:38 <oerjan> the dead keys on this laptop are only sort of working
16:27:59 <boily> b_jonas: köszönöm, de a probléma megoldódni látszik már.
16:28:06 <oerjan> i cannot write é in my google tab, but it works fine in putty.
16:30:05 <oerjan> in vim getting a lone ` takes some weirdness, which is *so* fun for haskell. if i am trying to type `e i type something like `l<backspace>e
16:30:49 <oerjan> in my old laptop it was just `<space>e
16:31:18 <oerjan> but somehow <space> doesn't work any more
16:31:41 <oerjan> or well, it _sometimes_ works, but not reliably
16:32:09 <oerjan> sometimes the ` just sits there, waiting for the most annoying moment to pop up
16:32:32 <boily> there aren't annoying moments for diacritics, only unartistic önes.
16:32:52 <oerjan> although pushing a non-vowel letter tends to fix it, as long as i'm in insert mode
16:34:57 <oerjan> ok if i push `<space><space>l in insert mode now, i get <space>`l as the actual output
16:36:13 <oerjan> and there i've somehow got it back to working sensibly
16:37:38 <oerjan> that gives two `'s rather reliably
16:38:15 <oerjan> `<space> is the shortest way to get a ` before a vowel _when it works_
16:38:16 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: <space>: not found
16:38:40 <oerjan> it's just that gvim seems to toggle between a mode in which it works and in which it is freaky
16:39:39 <Gregor> In the universe of C sins, how sinful is it to #define return to something...
16:41:26 -!- boily has quit (Quit: RENEWED CHICKEN).
16:42:59 -!- Sprocklem has quit (Ping timeout: 244 seconds).
16:44:48 <b_jonas> Gregor: it's sinful. it's like IOCCC level sinful. and it's not portable either, the standard specifically forbids it, and for good reason, because library macros could contain return.
16:45:14 <b_jonas> I think some IOCCC entries did define keywords as macros
16:49:11 <elliott> Gregor: ...what are you trying.
16:49:12 <Jafet> IOCCC level sinful? Is that like jaywalking on a country road at midnight
16:52:37 <Gregor> Sounds like "pretty good idea" then.
16:59:48 <Gregor> b_jonas: Incidentally, if return is defined to something that's syntactically compatible, library macros containing return wouldn't be broken, so that's not much of a reason :3
17:00:17 <Gregor> e.g. #define return if ((something), 0) {} else return
17:00:34 <b_jonas> Gregor: that's not completely compatible, but close enough
17:00:52 <b_jonas> are you trying to implement a profiler or tracer?
17:01:08 <elliott> Gregor: are you sure you shouldn't just patch a compiler at this point
17:02:29 <Gregor> In my GC, users have to push and pop their stack pointers. Push is manual regardless, but I'm trying to decide if defining return to make pop automatic is too sinful X-D
17:03:03 <elliott> Gregor: why not use gcc finaliser thingies
17:03:07 <b_jonas> Gregor: why don't you use C++ and destructors?
17:03:10 <elliott> systemd uses them to automatically deallocate things that go out of scope (!)
17:03:20 <elliott> you can even typedef it in
17:03:33 <Gregor> elliott: Because my GC isn't GCC-specific.
17:03:52 <Gregor> b_jonas: Because my GC is usable from C and not usable from C++ since I can't control C++ object headers.
17:03:54 <elliott> okay, but #define return is also not valid C, so you're already being unportable :p
17:04:07 <elliott> I don't know whether clang implements that stuff.
17:04:13 <elliott> I guess probably? systemd probably compiles with clang.
17:04:18 <b_jonas> Gregor: um... so? C++ but don't use such objects?
17:04:35 <Gregor> b_jonas: No, the USERS who would be using this push and pop macros are C.
17:04:57 <b_jonas> well, I think defining return is evil for this, but of course you can try to be evil
17:04:57 <elliott> people with weak compilers can do it manually, people willing to use GNU C can use GNU C convenience features?
17:05:05 <elliott> it's nicer than redefining return anyway
17:05:06 <Gregor> elliott: Of course clang implements it, clang implements virtually all GCC extensions.
17:05:20 <coppro> elliott: I can't find any docs on these so-called finalisers
17:05:21 <elliott> it doesn't do nested functions I think
17:05:24 <elliott> which are actually used in practice
17:05:34 <elliott> coppro: they're probably not so-called finalisers.
17:05:36 <Gregor> elliott: The alternative isn't "just be GCC-specific", it's "make them manually pop and if they forget to, oh well everything breaks horribly"
17:06:04 <elliott> Gregor: well, I was presenting a third alternative that seems nicer and more robust than redefining return without giving up all the convenience. sorry.
17:06:13 <coppro> http://clang.llvm.org/docs/UsersManual.html
17:06:20 <coppro> there's a list of GCC functions not supported
17:08:07 -!- oerjan has quit (Quit: leaving).
17:08:25 <coppro> I also don't see anything that looks like a finalizer on GCC's extension list
17:08:57 <elliott> do you expect me to give you pointers faster than I can git clone systemd's source code? you have as much information as I remember, so it's not like you couldn't yourself...
17:09:24 <coppro> I assumed you knew more
17:09:35 <elliott> src/shared/macro.h:#define _cleanup_(x) __attribute__((cleanup(x)))
17:09:47 <elliott> src/shared/util.h:#define _cleanup_free_ _cleanup_(freep)
17:09:53 <elliott> src/activate/activate.c: _cleanup_free_ char *name = NULL;
17:10:11 <elliott> cleanup (cleanup_function)
17:10:11 <elliott> The cleanup attribute runs a function when the variable goes out of scope. This attribute can only be applied to auto function scope variables; it may not be applied to parameters or variables with static storage duration. The function must take one parameter, a pointer to a type compatible with the variable. The return value of the function (if any) is ignored.
17:10:16 <elliott> If -fexceptions is enabled, then cleanup_function is run during the stack unwinding that happens during the processing of the exception. Note that the cleanup attribute does not allow the exception to be caught, only to perform an action. It is undefined what happens if cleanup_function does not return normally.
17:10:35 <coppro> clang supports that from the looks of things
17:11:03 <Gregor> Oh, it's a variable attribute. Well that doesn't work anyway since I'd be demanding that users add a variable attribute to all their variables, which is just as onerous (more so) than popping.
17:11:16 <elliott> Gregor: well, they have to push, right?
17:11:26 <elliott> you could have a variable declaration macro that declares with the attribute and pushes
17:12:21 <Gregor> In fact, demanding that they declare their variables with a macro is good since it assures they're initialized.
17:12:27 <elliott> you could prooobably even make the syntax LET(char *foo = ...); work
17:12:51 <elliott> splitting out the = would be possible I think but splitting the name from the type wouldn't
17:13:02 <elliott> but LET(char *, foo, ...) isn't so bad.
17:13:47 <elliott> Gregor: one restriction is that the cleanup function can't take any other parameters, it seems. you can... probably work around that somehow.
17:13:59 <Gregor> Damn, that's actually by far and away the cleanest syntax for this. Getting the cleanup function to work properly is no problem.
17:14:01 <elliott> (I guess for a GC you can just have a thread-local static containing a pointer to the GC info.)
17:14:45 <Gregor> Which is how the pointer stack is stored anyway.
17:15:20 <elliott> Gregor: incidentally, if all you need for your GC to work is to add a single attribute to every local declaration and call a function to register it, compiler instrumentation would probably be really easy...
17:15:32 <elliott> (plus overriding malloc/free, obviously)
17:15:36 -!- vanila has joined.
17:16:05 <Gregor> elliott: If I'm reluctant to do things GCC-specific, how willing do you think I am to actually require an instrumented compiler to use my GC X-D
17:17:02 <elliott> Gregor: who said anything about a requirement?
17:17:10 <elliott> it'd just be cool to be able to, like, build GMP natively like that.
17:17:26 <elliott> since I remember it being such a fuss to teach the GC about libraries in cfythe
17:17:54 <Gregor> Ohhhhhhhhhhh, I see what you're suggesting now. Naw, that's not instrumentable because it's not possible to reliably know what malloc is mallocing.
17:18:03 <Gregor> Aliasing = "oh gawd mah pointers where did they go?!"
17:19:23 <elliott> Gregor: you can override malloc
17:19:34 <elliott> to point to your GC allocator
17:19:53 <Gregor> That doesn't let it know what it's allocating. This is a precise GC: It needs to know more than just how many bytes, it needs to know which of those bytes are GC pointers.
17:20:23 <elliott> okay, so it'd be that + rewriting calls to malloc to pass along type info + analysing struct definitions. or just using LLVM's precise tracing GC support.
17:21:21 <Gregor> LLVM cannot have precise tracing GC support /for C/. Nothing can have precise tracing GC support for C because C does not pass along type info at allocation time.
17:21:47 <elliott> okay, then just s/\. or.*// on that line
17:22:02 <elliott> also s/$/ + add a bunch of restrictions on casts and give up on life/
17:22:03 <Gregor> I like how you explicitly removed the full stop.
17:22:08 <b_jonas> Gregor: I have some questions. What if the function doesn't have an explicit return, only a fall through the close brace. What if the expression for return needs values from the stack frame, how do you keep those referenced until after? And how do you make the macro work even in functions that don't push?
17:24:39 <Gregor> b_jonas: (1) This case isn't supported and requires an explicit pop. It's hoped to be a minority. (2) Pointers only change when collection occurs, so only weird compound expressions can cause this anyway. This problem isn't solved by using pop (or anything else for that matter) instead of return, it's just a slight restriction that users of a GC will have to abide by regardless. (3) Push defines a const int that overrides a global const int. The if condition lo
17:24:39 <Gregor> oks something like if (i_pushed ? (stuff, 0) : 0) {} else return
17:26:50 <Gregor> s/overrides/shadows/ is more explicit.
17:26:54 <elliott> it's kinda nice that __attribute__((cleanup)) is exception-safe
17:31:45 <Gregor> I guess I could do __attribute__((cleanup)) on __GNUC__ and C++ on MSVC.
17:31:52 <Gregor> And that covers all compilers.
17:41:55 <b_jonas> oh, on anagol, Mail Merge times out in one day
17:42:40 <elliott> Gregor: I guess you can avoid the shadowing with __attribute__((cleanup))?
17:43:02 <Gregor> elliott: I can avoid the whole pop situation with __attribute__((cleanup))
17:44:32 <b_jonas> What the heck is this? http://golf.shinh.org/p.rb?Wow
17:46:39 <Gregor> Actually, I could use __attribute__((cleanup)) on GCC, C++ on C++ compilers, and #define return on everything else!
17:47:00 <fizzie> b_jonas: It's a golf problem. That means you need to write a short program to generate that output. HTH.
17:47:11 <elliott> Gregor: step away from the #define return
17:47:18 <elliott> tcc users should write their own pops :P
17:47:49 <Gregor> It's not acceptable that you have to do different things to use a library with different compilers.
17:48:04 <elliott> c'mon, there has to be at least one compiler out there that correctly forbids #define return.
17:48:17 <fizzie> "The program shall not have any macros with names lexically identical to keywords currently defined prior to the inclusion of [any standard] header or when any macro defined in the header is expanded."
17:48:45 <Gregor> Heyo! That condition is my out!
17:48:49 <elliott> fizzie: can you read that as permitting #define return after including standard headers
17:49:12 <elliott> remind me to write some tortured program to break Gregor's hack :p
17:49:29 <fizzie> I think you can, but there's quite a few macros in those headers.
17:49:33 <Gregor> This is great! The hack will only be for awful compilers anyway.
17:50:06 <elliott> Gregor: except it forbids you from using any stdlib macros
17:50:23 <elliott> I forget if puts is a macro but you get the idea.
17:50:46 -!- alexandre has joined.
17:50:46 <fizzie> Or SEEK_SET, or EOF, or NULL.
17:50:51 -!- alexandre has changed nick to boily.
17:50:59 -!- boily has quit (Client Quit).
17:51:18 <fizzie> No, that's a declared type.
17:51:28 <b_jonas> are you sure? I think it's a macro
17:51:36 <fizzie> Though admittedly it's arguable whether "declares a type" can refer to a macro.
17:51:39 -!- boily has joined.
17:51:50 <fizzie> "The types declared are -- FILE which is an object type --" (C11 7.21.1p2)
17:52:00 <fizzie> And p3 is "The macros are --"
17:52:08 <Gregor> Are you genuinely telling me that it's better to have NO generic implementation (i.e., be specific to GCC and C++) than it is to do something which, while technically forbidden by the standard, would be nearly impossible to cause problems?
17:52:21 <b_jonas> but yeah, stdin definitely
17:52:30 <elliott> Gregor: yeah, because I don't believe you can actually avoid having it cause problems :p
17:52:38 <elliott> like, for one, functions returning void.
17:52:57 <Gregor> elliott: It's not like it breaks EXISTING functions that return void.
17:53:02 <elliott> yeah, but doing magic that hides the popping details and then expecting everyone to remember the popping detail that you need to "return" in functions with no return value...
17:53:15 <elliott> I guarantee you I would forget
17:53:28 <elliott> don't C compilers generally warn about extraneous returns in void functions anyway
17:53:33 <elliott> sort of builds up an instinct
17:54:20 <elliott> hey, I'm not the one #defining return
17:54:44 <Gregor> And I'm not the one being compiler-specific because pedantry!
17:55:07 <b_jonas> FILE is indeed not a macro
17:55:15 <elliott> well, when I need to do something that requires a GNU C extension to do it reasonably and reliably, I either don't do it or I use the extension :p
17:55:32 <b_jonas> but anyway, stdout is, and putchar may be
17:56:00 <Gregor> elliott: What I'm proposing is that I use the extension, but IF the extension isn't available, I approximate.
17:56:06 <Gregor> Rather than say "lol no gcc u suk"
17:56:31 <elliott> Gregor: I know, but I don't need to add returns to void functions when I'm using gcc.
17:56:41 <elliott> and I won't, because I'd get a warning about it being useless in my head if not from the compiler.
17:56:52 <elliott> and since I don't use tcc, it'll break in exciting ways whenever I do.
17:56:54 <Gregor> I don't think any compiler gives warnings for "spurious" returns from void functions.
17:56:58 <Gregor> I've never heard of such a warning.
17:57:27 <Gregor> ALSO, if the compiler gives warnings for unused variables, you'd still get a warning for not popping!
17:57:34 <elliott> my point is there's no way anyone will remember it especially if it's not required for gcc/clang *unless* they're specifically trying to be pedantically portable. in that case, they have to keep that in mind constantly anyway because other compilers suck, so it's not reallym uch additional burden to just get them to pop manually.
17:58:03 <Gregor> The burden of popping manually in EVERY FUNCTION, when some tiny portion of them return void???
17:59:25 <elliott> the burden of supporting crappy compilers anyawy :p
18:00:21 <b_jonas> what if you add a custom source processing step that finds all blocks with one of your push instructions and adds a pop at the end of that block and before returns?
18:00:36 <elliott> anyway I'm not interested in the escalating hysterics so w/e
18:01:03 <b_jonas> then you'd get a crazy build procedure like Qt
18:02:39 <elliott> didn't qt switch to standard C++ at some point
18:06:31 <fizzie> I think I heard something about that.
18:07:05 <Gregor> The thing that makes me want to do something cleverer than manual popping in the first place is that while there's only one entry to a function (and thus only one point to push), there are potentially many exits.
18:07:57 <b_jonas> Gregor: what if instead or return, you define another macro that behaves like return?
18:08:20 <elliott> I just really don't think it's worth adding and maintaining flaky, hacky half-support for convenience features for near-useless compilers when supporting compilers anyone actually uses perfectly is possible and easy.
18:09:06 <Gregor> b_jonas: You'd have to remember to use xreturn in all the same cases as you previously would have had to remember to use pop *shrugs*
18:10:21 <elliott> if you really really want to just write the pops once while using a useless compiler I'd just "goto cleanup", honestly. C programmers are used to that idiom.
18:10:30 <fizzie> Well, 'moc' is still there in Qt 5 documentation. But I think they've been trying to switch away from you writing raw QWidgets and dealing with signals and slots and whatnot to things involving QML and JavaScript.
18:26:44 <Gregor> Heyo, __attribute__((cleanup)) does the trick beautifully :)
18:30:29 <elliott> Gregor: I bet you could use it for such disgusting things.
18:30:45 <elliott> int main() { __attribute__((cleanup(puts))) char x = 'q'; }
18:39:18 <Gregor> Bleh, the C++ solution segfaults.
18:39:44 <fizzie> `cc #include <stdio.h> \n int main() { __attribute__((cleanup(puts))) char x = 'q'; } /* it was so awful, it's worth looking live */
18:40:50 <fizzie> Also a pure accident it printed "q" and not "q<random garbage>".
18:42:05 <Gregor> Oh, I didn't even notice you were using puts instead of putchar.
18:43:08 <fizzie> It gets a pointer to the thing, so... and there's warnings about the type for a char x[].
18:43:41 <fizzie> `cc #include <stdio.h> \n int main() { __attribute__((cleanup(puts))) char x[] = "foobar"; } /* the output is still there, though */
18:43:43 <HackEgo> /tmp/a.c: In function ‘main’: \ /tmp/a.c:2:2: warning: passing argument 1 of ‘puts’ from incompatible pointer type [enabled by default] \ In file included from /tmp/a.c:1:0: \ /usr/include/stdio.h:688:12: note: expected ‘const char *’ but argument is of type ‘char (*)[7]’ \ foobar
18:49:08 <elliott> `cc #include <stdio.h> \n int main(int argc, char **argv) { for (int i = 0; i < argc; i++) puts(argv[i]); if (argc > 0) { volatile __attribute__((cleanup(main))) char **av = argv + 1; volatile int ac = argc - 1; } }
18:49:09 <HackEgo> /tmp/a.c: In function ‘main’: \ /tmp/a.c:2:36: error: ‘for’ loop initial declarations are only allowed in C99 mode \ /tmp/a.c:2:36: note: use option -std=c99 or -std=gnu99 to compile your code \ /tmp/a.c:2:150: warning: initialization from incompatible pointer type [enabled by default] \ /tmp/a.c:2:2: warning: passing argument 1 of ‘ma
18:49:20 <elliott> `cc #include <stdio.h> \n int main(int argc, char **argv) { int i; for (i = 0; i < argc; i++) puts(argv[i]); if (argc > 0) { volatile __attribute__((cleanup(main))) char **av = argv + 1; volatile int ac = argc - 1; } }
18:49:21 <HackEgo> /tmp/a.c: In function ‘main’: \ /tmp/a.c:2:153: warning: initialization from incompatible pointer type [enabled by default] \ /tmp/a.c:2:2: warning: passing argument 1 of ‘main’ makes integer from pointer without a cast [enabled by default] \ /tmp/a.c:2:6: note: expected ‘int’ but argument is of type ‘volatile char ***’ \ /tmp/a.
18:51:33 <Gregor> Oh, my C++ destructor is never being called... >_O
18:52:57 <elliott> fizzie: you get that working.
18:53:40 <elliott> `cc #include <stdio.h> \n int main(__attribute__((cleanup(puts))), char **argv) {}
18:53:41 <HackEgo> /tmp/a.c:2:41: error: expected declaration specifiers or ‘...’ before ‘,’ token
18:53:47 <elliott> `cc #include <stdio.h> \n int main(__attribute__((cleanup(puts))) int argc, char **argv) {}
18:53:48 <HackEgo> /tmp/a.c:2:2: warning: ‘cleanup’ attribute ignored [-Wattributes]
19:07:10 -!- shikhin has changed nick to gamergate.
19:07:17 -!- gamergate has changed nick to shikhin.
19:13:33 -!- nys has joined.
19:26:43 -!- AnotherTest has joined.
19:49:11 -!- shikhout has joined.
19:52:36 -!- shikhin has quit (Ping timeout: 256 seconds).
19:57:23 -!- shikhout has changed nick to shikhin.
20:08:07 -!- DTSCode has joined.
20:48:55 -!- MoALTz_ has quit (Ping timeout: 244 seconds).
20:57:37 -!- Frooxius has joined.
21:07:49 -!- Sprocklem has joined.
21:13:07 -!- boily has quit (Quit: APPROXIMATIVE CHICKEN).
21:20:30 <vanila> consider productions like f(X,Y,Z) -> a X X Y b Z c c
21:20:52 <vanila> e.g. tag(T,B) -> '<' T '>' B '<' '/' T '>'
21:21:48 <vanila> any how how I could write a good compressor that tages a srting and produces a grammar like this which builds the string?
21:22:04 <vanila> I thinkt that a powerful compressor of that type would uncover lots of interesting structure automatically
21:22:23 <fizzie> Look up "grammar induction".
21:24:13 <fizzie> I think I played a little bit with ADIOS.
21:24:45 <fizzie> http://adios.tau.ac.il/ADIOS.html
21:25:06 <fizzie> I don't remember any details about what I used it for, and what kind of models it does.
21:34:07 <Sgeo> <Sgeo> Isn't the typed side of a typed-untyped module barrier so arrogant? It always blames the untyped side for contract violations...
21:34:08 <Sgeo> <mithos28> Sgeo: well not always
21:34:08 <Sgeo> <mithos28> if the untyped side was better behaved there wouldn't be any violations and it wouldn't get blamed
21:40:52 <Bike> is that so dot amv
21:41:17 <vanila> didn't wadler make this a theorem
21:42:53 -!- MeerLin has joined.
21:46:55 -!- MeerLin has quit (Ping timeout: 246 seconds).
22:21:05 -!- FreeFull has quit (Ping timeout: 256 seconds).
22:23:16 -!- DTSCode has quit (Ping timeout: 272 seconds).
22:23:17 -!- FreeFull has joined.
22:23:56 -!- Patashu has joined.
22:29:35 -!- boily has joined.
22:30:55 -!- Vorpal_ has joined.
22:30:55 -!- Vorpal_ has quit (Changing host).
22:30:55 -!- Vorpal_ has joined.
22:34:49 -!- Vorpal has quit (Ping timeout: 260 seconds).
22:37:08 -!- AnotherTest has quit (Remote host closed the connection).
23:04:40 -!- nyuszika7h has quit (Remote host closed the connection).
23:10:58 <Taneb> Sweet, my custom T-shirt protesting against one of my lecturer's insistence that anyone who disagrees with him on a certain arbitrary decision is wrong has arrived!
23:12:21 <Taneb> It just says "0 ∈ ℕ"
23:12:47 <vanila> don't get involved in that
23:13:09 <vanila> half the mathematicians are gonna hate you
23:13:26 <Taneb> That's most the reason I'm wearing it
23:14:03 <vanila> you could get 1 in N on the back
23:14:13 <Taneb> Although I kind of wished I got it so I could turn it inside out and it'd say "0 ∉ ℕ" or something
23:14:13 <vanila> argue with someone and then just walk off
23:27:30 <zzo38> It doesn't render on my computer
23:28:07 <zzo38> Can you please tell me how it is supposed to mean, with ASCII codes?
23:28:14 <zzo38> b_jonas: Taneb's stuff
23:28:24 <fizzie> zzo38: 0 \in \mathds{N}, LaTeX-wise.
23:28:29 <fizzie> zzo38: I don't know what it is in plain TeX.
23:29:06 -!- oerjan has joined.
23:29:06 <zzo38> What is the second one?
23:29:42 <shachaf> Taneb: You should read a book I have. It calls integers ≥ 0 "positive" and integers > 0 "strictly positive".
23:30:08 <fizzie> zzo38: Same but with \not\in.
23:30:48 <fizzie> I wonder if someone, somewhere has used € to stand in for \in.
23:30:51 <zzo38> And what do you mean by \mathds? Is that like black board bold?
23:31:09 <fizzie> It's called both "blackboard bold" and "double-struck".
23:31:48 <oerjan> i definitely used \mathbb, way back
23:31:51 <fizzie> The 'dsfont' package provides a \mathds for it, and I think AMS has \mathbb.
23:31:57 <shachaf> fizzie: a € b means ∃ c. a ∈ c ∧ c ∈ b
23:32:19 <Bike> how much do you think a shirt reading "-1 ∈ ℕ" would cost
23:32:37 <oerjan> `unidecode ∃ c. a ∈ c ∧ c ∈ b
23:32:38 <HackEgo> [U+2203 THERE EXISTS] [U+0020 SPACE] [U+0063 LATIN SMALL LETTER C] [U+002E FULL STOP] [U+0020 SPACE] [U+0061 LATIN SMALL LETTER A] [U+0020 SPACE] [U+2208 ELEMENT OF] [U+0020 SPACE] [U+0063 LATIN SMALL LETTER C] [U+0020 SPACE] [U+2227 LOGICAL AND] [U+0020 SPACE] [U+0063 LATIN SMALL LETTER C] [U+0020 SPACE] [U+2208 ELEMENT OF] [U+0020 SPACE] [U+00
23:32:52 <fizzie> oerjan: "There exists space" well can't argue with that.
23:33:06 <Bike> b_jonas: don't be a mathphobe
23:33:37 <oerjan> fizzie: today the newspaper had a "quote of today" that was something like "there's nothing there's more of than nothing"
23:34:05 <shachaf> oerjan: exists c. a `in` c && c `in` b hth
23:34:07 <b_jonas> Bike: that's like "Let ε<0"
23:34:22 <Bike> ok so how much would that be on a shirt
23:34:45 <Bike> or i could splurge, get a proof that .999... != 1 printed
23:35:05 <fizzie> All the London guides start with "When a man is tired of London, he is tired of life" quote by Samuel Johnson, which makes me think nobody famous never said anything else positive, so they all have to go with that.
23:35:26 <oerjan> unfortunately it was translated into norwegian, i don't remember the person (some old dead guy), and google finds nothing
23:36:01 <zzo38> To me, zero is a natural number, but some people use different definition of a natural number.
23:36:16 <oerjan> to the greeks, not even one was natural
23:36:44 <Bike> i guess for maximum pissing off it has to be something boring and arbitrary, like zero in the naturals, rather than .999... which is just obviously dumb
23:36:52 <Bike> 0^0 = 1, maybe
23:37:22 <shachaf> let ε ∈ {x ∈ R | x² = 0} hth
23:37:35 <shachaf> zzo38: an unnatural definition hth
23:37:45 -!- nyuszika7h has joined.
23:38:18 <Bike> if it's unnatural how do you explain this photograph of i have of a turtle using the same convention in its natural habitat
23:38:23 <Bike> ethology works mother fuckers
23:38:39 <oerjan> > undefined^0 -- someone did that yesterday
23:39:31 <oerjan> Bike: exponential turtles? that sounds dangerous.
23:39:50 <Bike> it's pretty common ecology, actually
23:40:04 <Bike> such is breeding
23:46:04 <shachaf> Bike: how are the manifolds going
23:47:08 <Bike> now that i know what a section is i understand more things so my motivation has dropped
23:47:55 <shachaf> it helps with reading math books
23:48:03 <shachaf> but if you know what a chapter is you can usually get by
23:49:11 <shachaf> Is it just a right inverse or something more complicated?
23:51:27 <Bike> a right inverse.
23:53:49 <shachaf> did you know the axiom of choice is equivalent to "every surjection has a right inverse"
23:54:01 <shachaf> (which makes sense if you think about it)
23:56:17 -!- ^v has quit (Read error: Connection timed out).
23:57:29 -!- ^v has joined.
00:01:23 -!- Bike has quit (Ping timeout: 265 seconds).
00:01:56 -!- Bike has joined.
00:13:30 -!- ^v has quit (Read error: Connection timed out).
00:28:52 <zzo38> I dreamt of a new kind of handheld computer system that although it included several buttons as well as a touch-screen, many things were controlled by gestures that aren't touching it; for example to slide up a menu by sliding your finger against your fingernail.
00:36:00 <nys> swipe tongue across roof of mouth to dismiss notification
00:39:10 <boily> the concept of a nothing-held computer is interesting. augmented reality, or holographic projection?
00:46:15 <oerjan> just have a projection from those mind-control satellites
00:47:56 <shachaf> "Unfortunately, there's a radio connected to my brain"
01:03:49 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:04:14 <HackEgo> [wiki] [[Subleq]] M http://esolangs.org/w/index.php?diff=40814&oldid=40787 * Oerjan * (-1) /* Basic */ tpyo
01:11:51 <HackEgo> [wiki] [[CA-1]] M http://esolangs.org/w/index.php?diff=40815&oldid=40792 * Oerjan * (-3) fix format, grm
01:14:28 <HackEgo> [wiki] [[Replace]] M http://esolangs.org/w/index.php?diff=40816&oldid=40790 * Oerjan * (+13) fmt, links
01:18:29 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=40817&oldid=40798 * Oerjan * (+14) sp, no
01:25:28 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40818&oldid=40812 * Oerjan * (+8) links
01:45:52 -!- vanila has quit (Quit: Leaving).
01:49:16 -!- shikhout has joined.
01:52:33 -!- shikhin has quit (Ping timeout: 265 seconds).
02:10:57 <zzo38> How many bits are there in a ICBM address (including elevation)?
02:35:46 -!- boily has quit (Quit: WEREWOLF CHICKEN).
03:09:43 -!- oerjan has quit (Quit: WERECHICKEN WOLF).
03:14:40 -!- centrinia has joined.
03:29:19 -!- ^v has joined.
03:43:42 <shachaf> what's with prescriptivists telling me not to use the word "trinary"
03:47:04 -!- nys has quit (Quit: quit).
04:03:03 <Gregor> Maybe it's Latin/Greek pedantry?
06:24:20 <zzo38> Some things say it is requiring use of OSI-approved licenses (and other things say it requires FSF-approved licenses). But this is problem; some are only one and not the other.
06:37:05 <zzo38> How to easily skip past a bzip2 stream without attempting to decompress it?
07:05:16 <FreeFull> By figuring out its length somehow
07:06:23 -!- DTSCode has joined.
07:06:38 <zzo38> Yes, I thought, but I don't know the format; the bzip2 documentation tells only the API and doesn't document the format.
07:42:31 -!- Sprocklem has quit (Ping timeout: 245 seconds).
07:43:14 -!- DTSCode has quit (Read error: Connection reset by peer).
07:46:56 <zzo38> I have not updated level20.tex in a while. What footnote do you want to put next?
07:48:42 -!- DTSCode has joined.
07:49:14 -!- shikhin has joined.
07:52:24 -!- shikhout has quit (Ping timeout: 255 seconds).
07:53:49 -!- ais523 has joined.
08:06:47 <centrinia> Could you look at http://www.bzip.org/1.0.6/bzip2-1.0.6.tar.gz to determine the file format?
08:07:34 -!- DTSCode has quit (Remote host closed the connection).
08:08:14 -!- DTSCode has joined.
08:11:02 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:22:42 -!- MoALTz has joined.
08:24:02 <mroman> blsq ) %square={^^?*}9%square!
08:37:13 -!- bb010g has quit (Quit: Connection closed for inactivity).
08:42:31 <zzo38> centrinia: I do have the program in my computer already
08:56:51 <fizzie> @hoogle Eq b => (a -> b) -> [a] -> [[a]]
08:56:51 <lambdabot> GHC.Exts groupWith :: Ord b => (a -> b) -> [a] -> [[a]]
08:56:51 <lambdabot> GHC.Exts sortWith :: Ord b => (a -> b) -> [a] -> [a]
08:56:51 <lambdabot> Prelude dropWhile :: (a -> Bool) -> [a] -> [a]
08:57:46 <fizzie> I guess groupWith f == groupBy ((==) `on` f) or something.
08:58:16 <mroman> wth is wrong with groupBy
08:58:36 <lambdabot> (b -> b -> c) -> (a -> b) -> a -> a -> c
08:58:45 <mroman> > groupBy (\c -> c % 2 == 0) [1,2,4,3,5,6,8,10,1]
08:58:46 <lambdabot> Couldn't match expected type ‘a -> GHC.Types.Bool’
08:58:46 <lambdabot> Relevant bindings include c :: a (bound at <interactive>:1:11)
08:59:43 <mroman> Is there a version of group that allows to do that?
08:59:50 <mroman> groupBy (\c -> c % 2 == 0)
09:00:14 <mroman> should produce [[1],[2,4],[3,5],[6,8,10],1] actually
09:00:53 <fizzie> > groupBy ((==) `on` (%2)) [1,2,4,3,5,6,8,10,1]
09:00:55 <lambdabot> [[1],[2],[4],[3],[5],[6],[8],[10],[1]]
09:01:19 <fizzie> > groupBy ((==) `on` (`mod` 2)) [1,2,4,3,5,6,8,10,1]
09:01:36 <fizzie> You confused me with your use of %, I blame that.
09:02:51 <fizzie> Oh, and you're not you.
09:03:06 <fizzie> (I thought it was still mroman speaking.)
09:03:27 <lambdabot> x % y = reduce (x * signum y) (abs y)
09:04:44 <fizzie> It's that thing for those.
09:05:16 <lambdabot> Data.Function on :: (b -> b -> c) -> (a -> b) -> a -> a -> c
09:05:16 <lambdabot> Control.Exception.Base onException :: IO a -> IO b -> IO a
09:05:16 <lambdabot> Control.Exception onException :: IO a -> IO b -> IO a
09:06:17 <fizzie> > groupBy (\a b -> (a `mod` 2) == (b `mod` 2)) [1,2,4,3,5,6,8,10,1] -- if you want it spelled out
09:07:51 <mroman> blsq ) {1 2 4 3 5 6 8 10 1}{2dv}gB
09:07:52 <mroman> {{1} {2 4} {3 5} {6 8 10} {1}}
09:15:28 <mroman> http://codepad.org/qqf0pbRH
09:15:34 <mroman> ^- the new Burlesque :D
09:21:39 <mroman> fizzie: I'm familiar with the concept of `on` ;)
09:23:13 <fizzie> Yes, I mixed names all the way up there too.
09:28:25 <mroman> btw: Do you have some ideas how to make parsing practical in a stack-based language?
09:29:19 <zzo38> What is a grammar called having the properties: [1] There is a finite number of possible tokens and none of them have extra information associated with them. [2] Each production has a list of zero or more action symbols associated with them. [3] When a production is matched, the list of action symbols is appended to an output buffer and does nothing else; it does not affect further input or change what is already written to the output buffer.
09:32:35 <ais523> mroman: well, some classes of parsers (e.g. LR parsers) are stack-based already, but they normally assume that the input is somewhere other than the stack
09:57:31 <ais523> you might be able to use the Underload/Joy trick of keeping the remaining input to consume on top of the stack, and just manipulating the stack beneath it, with dip instructions
09:57:47 <ais523> dip in Underload is ~a*^
10:01:45 <ais523> basically, "run the given code, using the tail of the stack as the stack"
10:02:03 <ais523> i.e. it basically "hides" the top stack element while running some code, and puts it back afterwards
10:02:20 <ais523> ^ul (a)(b)(c)(d)(e)SSSSS
10:02:23 <ais523> ^ul (a)(b)(c)(d)(e)~SSSSS
10:02:29 <ais523> ^ul (a)(b)(c)(d)(e)(~)~a*^SSSSS
10:02:42 <ais523> that should give you a good idea of how dip works
10:03:13 <ais523> in underlambda (which is vaporware), I use _ for dip, because it's one of the more useful and fundamental operations you can do in a stack language
10:03:17 <ais523> (the name "dip" comes from Joy)
10:03:31 <ais523> and ofc you can nest dips indefinitely
10:03:39 <ais523> ^ul (a)(b)(c)(d)(e)((~)~a*^)~a*^SSSSS
10:11:58 <b_jonas> ais523: tha sounds like a strange operation. do you temporarily put the hidden element to the separate return stack?
10:12:36 <ais523> b_jonas: the ~a*^ implementation basically puts a command to push the hidden element onto the stack at the end of the code you're running
10:12:59 <ais523> so it's effectively being stored in the "program stack" (which looks like a stack if you ever look at Underload in a debugger)
10:13:35 <b_jonas> sure, the program stack can contain arbitrary data in postscript too, so that makes sense
10:14:43 <fizzie> I went to look for the Factor 'dip', but it's just a primitive.
10:14:57 <fizzie> Well, there's a definition -- : dip swap [ call ] dip ;
10:15:08 <fizzie> But it's a primitive when preceded by a literal quotation.
10:15:42 <ais523> wait, is it defined in terms of itself?
10:15:53 <fizzie> No, it's defined in terms of the primitive.
10:16:02 <ais523> in terms of a special case of itself, then
10:16:16 <fizzie> The primitive only applies if it follows a literal quotation, so the definition is only involved when it's something else than a literal.
10:16:18 <ais523> originally I was planning to have a separate stack for working in Overload
10:16:35 <ais523> thought I might need one in Underlambda too, but Underload is more elegant than I expected
10:16:50 <ais523> ~a*^ is a really elegant and neat definition, only four characters!
10:20:40 <fizzie> `forth 1 2 3 4 s" swap" rot >r evaluate r> ~~
10:20:41 <HackEgo> \ *somewhere*:-1:<4> 1 3 2 4
10:21:09 <ais523> where is Forth storing the data?
10:21:19 <fizzie> The return stack, with >r and r>.
10:22:10 <ais523> oh, which is safe because code won't tamper with the area below where you are on the return stack without giving you a chance to run
10:22:18 <ais523> just like storing local variables on the stack in C
10:23:29 <fizzie> And the rot there is logically speaking a swap, it's just that s" foo" results in two cells (address and count).
10:24:49 <ais523> come to think of it, that Forth definition is pretty much a direct translation of the Underload, allowing for differences in culture between the languages
10:25:43 <fizzie> `forth : f 1 2 3 4 c" swap" swap >r count evaluate r> ; f ~~ ( alternatively )
10:25:44 <HackEgo> \ *somewhere*:-1:<4> 1 3 2 4
10:26:01 <fizzie> For some reason s" ..." is okay in interpreter mode, but c" ..." is a compile-only word.
10:28:06 <ais523> hmm, I wonder how easy it is to write an Underload interpreter using Forth techniques (or in Forth directly)
10:29:21 <b_jonas> depends. do you want garbage collection?
10:29:37 <fizzie> `forth 1 2 3 4 ' swap swap >r execute r> ~~ ( a lot more elegant but only for a single word )
10:29:37 <HackEgo> \ *somewhere*:-1:<4> 1 3 2 4
10:30:19 <fizzie> "evaluate" is arbitrary "read source code from string", execute just runs the interpretation semantics denoted by the xt put on stack by ' swap.
10:31:13 <fizzie> Oh, gforth (I don't know if it's in ANS) has anonymous definitions.
10:31:43 <fizzie> `forth 1 2 3 4 :noname rot swap ; swap >r execute r> ~~
10:31:44 <HackEgo> \ *somewhere*:-1:<4> 2 1 3 4
10:45:08 -!- quintopia has quit (Remote host closed the connection).
11:01:36 <b_jonas> fungot, run the interpretation semantics denoted by the xt put on stack by ' swap.
11:01:36 <fungot> b_jonas: " it is a very inconvenient habit of kittens ( alice had once made the remark) that, though she looked back once or fnord the riddle?'
11:01:55 <mroman> I fnorded a riddle once.
11:04:53 <b_jonas> fungot, on what x86 cpus exactly does loading 16 bytes of unaligned memory with the MOVDQU instruction carry no penalty as long as that memory is never written (it's a constant table) and it doesn't cross a 64 byte cache line boundary?
11:04:54 <fungot> b_jonas: " oh mocking magic watch!" i exclaimed. " human free-will is an exception to the system of fixed law. eric said something like that went on all through this fnord shall we say ' animals'? and, as my tears could never bring the friendly phantom back, it seemed impossible!" he said.
11:09:45 -!- ais523 has quit.
11:15:26 <fungot> b_jonas: " i--i didn't mean to grin. see, there are a good plan!" he said dreamily: " fnord sylvie?" bruno impatiently interrupted me. " why," said the gardener.
11:32:27 <b_jonas> Mail Merge times out today. Now I'll have to consider whether to post another challenge.
11:46:18 -!- ais523 has joined.
11:50:00 -!- yiyus has quit (Ping timeout: 244 seconds).
11:51:42 -!- yiyus has joined.
12:01:54 <Taneb> b_jonas, Mail Merge Times?
12:14:52 -!- oerjan has joined.
12:21:11 <Taneb> I don't think the Mail Merge Times is 0 : Nat
12:34:08 -!- boily has joined.
12:34:21 -!- Patashu has quit (Ping timeout: 250 seconds).
12:43:33 -!- centrinia has quit (Ping timeout: 255 seconds).
13:05:14 -!- impomatic_ has joined.
13:06:24 -!- CADD_ has joined.
13:26:44 -!- vanila has joined.
13:46:45 <oerjan> @tell shachaf <shachaf> what's with prescriptivists telling me not to use the word "trinary" <-- from a latin viewpoint, it's about like saying "threeth" in english
13:49:26 -!- shikhout has joined.
13:52:40 -!- shikhin has quit (Ping timeout: 265 seconds).
13:52:45 <oerjan> <fizzie> I guess groupWith f == groupBy ((==) `on` f) or something. <-- it's implemented a bit more efficiently for expensive functions, i think
13:55:35 <oerjan> fizzie: oh wait, it's actually sorting first, so not the same as groupBy ((==) `on` f) at all
13:57:03 <oerjan> oh and even sortWith isn't _actually_ using the trick to evaluate expensive functions less, hm
13:58:17 * oerjan is a bit tired in the brain
14:00:25 <fizzie> I didn't know it sorts first.
14:00:42 <oerjan> neither did i, but i just checked the code
14:00:54 <fizzie> The documentation does say.
14:01:03 <fizzie> "The groupWith function uses the user supplied function which projects an element out of every list element in order to first sort the input list and then to form groups by equality on these projected elements."
14:02:01 <fizzie> It doesn't do the Python itertools.groupby thing of returning tuples that contain both the value of the projection function as well as the group.
14:02:52 <oerjan> well i had vaguely thought that it _constructed_ the tuple list internally, but it doesn't.
14:03:08 <oerjan> actually groupWith without sorting wouldn't need that.
14:03:27 <oerjan> it can just pass the last f x value recursively
14:03:46 <oerjan> sortWith would need to construct tuples, though
14:03:56 <oerjan> (to avoid f reevaluation)
14:04:02 <fizzie> `run python -c 'from itertools import groupby; print(list((k, list(g)) for k, g in groupby([1,2,4,3,5,6,8,10,1], lambda x: x%2)))'
14:04:03 <HackEgo> [(1, [1]), (0, [2, 4]), (1, [3, 5]), (0, [6, 8, 10]), (1, [1])]
14:05:39 <fizzie> Silly amount of list()s to convert all those generator objects to something that print nicely.
14:05:57 <fizzie> `run python -c 'from itertools import groupby; print(list(groupby([1,2,4,3,5,6,8,10,1], lambda x: x%2)))'
14:05:58 <HackEgo> [(1, <itertools._grouper object at 0x4013ec50>), (0, <itertools._grouper object at 0x4013ec90>), (1, <itertools._grouper object at 0x4013ecd0>), (0, <itertools._grouper object at 0x4013ed10>), (1, <itertools._grouper object at 0x4013ed50>)]
14:06:07 <fizzie> `run python -c 'from itertools import groupby; print(groupby([1,2,4,3,5,6,8,10,1], lambda x: x%2))'
14:06:08 <HackEgo> <itertools.groupby object at 0x4014b680>
14:06:29 -!- blsqbot2 has joined.
14:06:34 <mroman> !blsq {1 2 4 3 5 6 8 10}{2dv}gB
14:06:34 <blsqbot> ERROR: Unknown command: (gB)!
14:06:43 <mroman> !blsQ {1 2 4 3 5 6 8 10}{2dv}gB
14:07:38 <mroman> !blsQ %deepReverse=q)<- {{1 2}} %deepReverse!
14:07:46 <mroman> !blsQ %deepReverse={)<-} {{1 2}} %deepReverse!
14:20:08 -!- blsqbot2 has quit (Read error: Connection reset by peer).
14:40:59 <nyuszika7h> Taneb: I read that as [Mail Merge] [times out]
14:42:29 <fizzie> I'm pretty sure that's the intended meaning.
14:43:07 <ais523> why don't you mail out some merge times?
14:44:42 <Jafet> So, you're not a reporter from the Mail Merge Times.
14:44:42 -!- shikhout has changed nick to shikhin.
14:55:10 -!- nys has joined.
15:04:06 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=40819&oldid=40806 * YoYoYonnY * (-124)
15:34:37 <FreeFull> !blsQ %deepReverse={)<-} {{1 2} {3 4}} %deepReverse!
15:43:41 -!- boily has quit (Quit: ISOCELES CHICKEN).
16:01:51 -!- MDream has changed nick to MDude.
16:30:01 -!- blsqbot2 has joined.
16:30:12 <mroman> !blsQ %deepReverse={)<-} {{1 2} {3 4}} %deepReverse!
16:30:44 <mroman> !blsQ |[1 2 3.+.+^^?*]|
16:30:51 <mroman> !blsQ |[1 2 3.+.+y^^?*Y]|
16:31:06 <mroman> !blsQ |[1 2 3.+.+y^^?*Y]|s0"0"ev
16:31:40 <mroman> !blsQ |[1 2 3.+.+y^^?*Y]|s0"0"gve!
16:34:04 -!- drdanmaku has joined.
16:34:43 <mroman> !blsQ %data={1 2 3} |[%data?++]|
16:35:11 <mroman> !blsQ %data={10ro} |[%data!++]|
16:35:36 <blsqbot2> Ain't nobody got time fo' dat!
16:38:44 <mroman> !blsQ %data=5 "data"Gv
16:38:46 <mroman> !blsQ %data=5 "data"gv
16:50:33 -!- blsqbot2 has quit (Ping timeout: 265 seconds).
16:59:30 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=40820&oldid=40819 * Rdebath * (+906) Input Number
17:00:10 <HackEgo> [wiki] [[Brainfuck algorithms]] M http://esolangs.org/w/index.php?diff=40821&oldid=40820 * Rdebath * (-2) Sigh
17:17:20 -!- oerjan has quit (Quit: Later).
17:58:48 -!- ais523 has quit.
17:59:00 -!- ais523 has joined.
18:21:34 -!- Sprocklem has joined.
18:44:45 -!- AndoDaan has joined.
18:45:58 -!- centrinia has joined.
18:57:53 -!- AndoDaan has quit.
19:12:14 <b_jonas> ais523: oh no! it's multiplying
19:12:24 <b_jonas> ais523: TomPN has written a page about another language
19:12:46 <b_jonas> dunno, I haven't looked yet
19:12:52 <b_jonas> want to see what he did with Musical Notes first
19:12:54 <ais523> ah right, I saw that come up in the RC feed, but didn't notice the author
19:13:02 <ais523> and the preview looked reasonable
19:13:26 <b_jonas> Musical notes still says "loops cannot be nested"
19:14:56 <ais523> the first oddity I notice about Dimensions, which is about halfway down the page, is that the command for reading a velocity set from memory is lumped in with I/O instructions for no sane reason at all
19:15:40 <ais523> oh, and loops /still/ don't nest (in Dimensions, that is)
19:15:48 <ais523> that said, the non-nestting version of Dimensions loops may actually be TC
19:15:59 <ais523> because each ] matches the most recently arriving [, which may be enough power
19:19:49 <b_jonas> ais523: this description of Dimension seems to be unclear the same way as that of Musical Notes. is it only the data memory and data pointer that moves in a 52 dimensional array, or also the instruction pointer somehow? And what's the global topology?
19:20:14 <ais523> instructions are still completely linear
19:20:18 <ais523> (note the unadorned "previous")
19:20:35 <ais523> I currently consider TomPN to be in the category of "trying to make something beyond a BF derivative but has no idea how"
19:20:54 <ais523> e.g. they don't seem to realise that adding more dimensions to the data storage simply makes programming easier, as you don't have to use them
19:22:40 <b_jonas> Should we introduce the rule that you can create a new language only if you have ascended a previously existing language?
19:23:25 <nys> i say we burn him
19:23:35 <b_jonas> nys: no, we have to measure him to a duck first5
19:23:54 <ais523> <b_jonas> Should we introduce the rule that you can create a new language only if you have ascended a previously existing language? ← does that even make sense?
19:24:09 <ais523> I guess you could define NetHack as a programming language, I've ascended that
19:24:17 <ais523> and am OK at defining arbitrary things to be programming languages
19:24:32 <ais523> actually I'd love to make NetHack 4 TC, but can't figure out how
19:24:48 <b_jonas> ais523: isn't it already TC?
19:24:50 <ais523> like, something involving rolling boulder traps dropping things between levels
19:25:01 <ais523> b_jonas: no infinite storage, and it's doubtful you can even construct a loop
19:25:10 <b_jonas> there is infinite storage in objects
19:25:37 <b_jonas> including nested containers
19:25:51 <b_jonas> I mean, it's probably not really infinite because you run out of address space eventually,
19:25:57 <b_jonas> but you probably don't want to change that, right?
19:27:18 <nys> settle for turing complete with fine print
19:28:11 <ais523> b_jonas: the problem is the complete lack of comoutation
19:28:13 <b_jonas> as for loop, I think you can, um, polymorph to a non-eating sessile monster and put on an amulet of unchanging while you still have movement points
19:28:22 <ais523> you can't have one thing causing another thing to happen, directly
19:28:29 <ais523> only possibility I can think of is the monster AI
19:28:36 <ais523> which has some Deadfish-like loopholes
19:28:43 <ais523> (have you read track.c, by the way?)
19:28:51 <ais523> (it's short, and hilariously buggy)
19:28:56 <b_jonas> we probably need some more special stuff for computation
19:29:05 <b_jonas> no, I haven't read track.c and I don't plan to either
19:29:15 <b_jonas> if I want to read the monster AI, I read muse.c, that's more sensible
19:29:36 <b_jonas> muse.c both determines the starting inventory of items and what items monsters will use and how they use them
19:29:57 <ais523> track.c determines how the monster tries to chase down the player
19:30:00 <b_jonas> that's how http://trac.nethack4.org/ticket/710 came up
19:30:02 <ais523> it is full of incorrect assuumptions
19:32:34 <b_jonas> the difficulty is that monsters don't interact with containers. they don't even pick them up, though a nymph may steal one.
19:33:09 <ais523> I'd like the player to be able to set up Dwarf Fortress-like contraptions
19:33:47 <b_jonas> it doesn't really help computation, but I was thikning of a scroll of duplicate item
19:33:56 <b_jonas> (or a scroll effect, in any case)
19:34:08 -!- conehead has quit (Excess Flood).
19:34:30 <b_jonas> which lets you choose an existing item and create a cancelled copy, unless it's unique or an artifact
19:34:47 -!- conehead has joined.
19:34:50 <b_jonas> I should ticket that if I haven't yet
19:39:19 <lambdabot> oerjan said 5h 52m 34s ago: <shachaf> what's with prescriptivists telling me not to use the word "trinary" <-- from a latin viewpoint, it's about like saying "threeth" in english
19:39:48 <shachaf> oerjan: good thing i'm not talking in latin hth
19:40:30 <ais523> let's annoy everyone by calling it "threenary"
19:42:22 <shachaf> 3-nary is a reasonable name and would not annoy me
19:49:37 -!- shikhout has joined.
19:52:51 -!- shikhin has quit (Ping timeout: 255 seconds).
20:01:03 -!- Patashu has joined.
20:02:09 <olsner> hm, what should trinary really be called then?
20:02:50 <ais523> "ternary" is something I see quite a lot
20:03:05 <b_jonas> yeah, "ternary" is the usual name, but why bother, "base three" is clear enough
20:05:04 <b_jonas> binary and hexadecimal are common bases, but nobody designs ternary computers anymore
20:05:20 <b_jonas> if you make an esolang with base 3 operations, like trintercal, then sure, call it ternary
20:06:12 <shachaf> surely you mean terntercal!!
20:07:09 <ais523> TriINTERCAL is the official name, I believe
20:07:55 <b_jonas> what's the official name for the base 4, base 5, base 6, base 7 versions?
20:08:48 <ais523> (if you expected it to make sense, you picked the wrong language)
20:23:40 -!- nortti has quit (Ping timeout: 250 seconds).
20:23:49 -!- nortti has joined.
20:25:22 -!- AndoDaan has joined.
20:25:38 <vanila> any ideas for simple VMs that could be used for targets for compression
20:25:46 <vanila> the first one is just emit char + backrefs
20:25:53 <ais523> what's being compressed here?
20:26:10 -!- Patashu has quit (Ping timeout: 260 seconds).
20:26:14 <vanila> any binary file - of course it will only compress some of them
20:26:23 <ais523> oh, you mean "any ideas for decompression algorithms, that I could invent matching compression algorithms for?"
20:26:39 <vanila> yeah, especially focused on making simple decompression VMs
20:26:43 <ais523> I actually was working on a compression algorithm of my own a while back; the decompressor was very simple, but the compressor quite complex
20:26:51 <vanila> what sort of thing was it?
20:26:54 <ais523> it beat bzip2 but was worse than lzma, so I didn't continue using it
20:27:07 <b_jonas> vanila: are you compressing video? audio? text? they call for different decompression algorithms.
20:27:21 <ais523> and basically, you could define a symbol as a single letter, or recursively in terms of other symbols
20:27:32 <ais523> and the last symbol defined was the entire program
20:27:54 <vanila> straight line grammar?
20:28:01 <ais523> e.g. "aabaab" could be encoded as (in pseudocode, the actual compression was binary) "X=aa; Y=Xb; Z=YY"
20:28:10 <vanila> I see! I thoughht this was a really good approach
20:28:14 <vanila> I considered adding parameters
20:28:26 <vanila> e.g. tag(T,B) = <T>B</T>
20:28:32 <vanila> could be used to compress HTML maybe
20:28:33 <b_jonas> ais523: that sounds sort of like a compression with backreferences
20:28:45 <ais523> and then that in turn was compressed by referring to symbols using numbers depending on how recently they'd been used
20:29:16 <vanila> i see, a huffman like entropy based compression is good for post processing
20:29:16 <ais523> now, you have /huge/ scope for encoding optimizations, e.g. you can reorder symbol definitions to make the numbers smaller
20:29:32 <b_jonas> oh look, Mail Merge is now in post mortem
20:29:36 <ais523> the numbers themselves were "Huffman" coded, but with a fixed table based on the frequencies they normally showed up at
20:29:36 <b_jonas> let me look what the people did
20:31:39 <b_jonas> wow, nice! and this ruby solution doesn't even hard-code anything about this particular input instance
20:32:34 <ais523> vanila: if you like I'll send you a copy of the decompressor and you can try to make a good compressor for it
20:33:27 <b_jonas> what does the 0/ do in that?
20:33:29 <vanila> thats ok but thanks :)
20:33:34 <b_jonas> um, in the winner perl solution I mean
20:33:36 <ais523> fwiw, even if you use only minimal compression on the numbers, it still beats gzip, which surprised me
20:34:01 <vanila> I think that grammar based compression could be really really powerful yeah
20:34:14 <vanila> but so hard to actually find the structure in text
20:34:22 <vanila> it's like parsing but you don't even know the AST yet
20:34:39 <zzo38> Actually I also have a decompression algorithm that I need a compressor for, too.
20:35:58 <b_jonas> how did I not notice that s///ger while doesn't need the spae
20:36:01 <ais523> vanila: right; eventually I was reaching the point where compression took hours and only saved a few bytes compared to much faster encoders
20:36:35 <vanila> http://www.sequitur.info/ this has a linera time algorithm (not space though)
20:36:40 <vanila> and it's meant to be quite good
20:36:43 -!- centrinia has quit (Ping timeout: 244 seconds).
20:36:54 <vanila> but it targets quite restricted vm
20:37:08 <ais523> vanila: linear time implies linear space unless you're doing something like using the address space as a hash table
20:37:19 <ais523> in which case, it takes non-linear time to zero the memory in advance
20:37:22 <zzo38> The decompressor is part of the program http://zzo38computer.org/zmachine/interp/zorkmid.zip
20:37:33 <b_jonas> I'm not a professional golfer but I should have noticed that
20:37:36 <vanila> oh weird :S I guess they lie or I don't understand something
20:38:16 <zzo38> Look at the zprint() function.
20:38:32 <vanila> If you made a compression algorithm you could call it zzip38
20:38:37 <zzo38> I have already a way to encode a single string and ignoring the frequent words table.
20:39:28 <zzo38> However, I have a collection of strings, and want to create a frequent words table for it.
20:40:33 <b_jonas> apparently teebee used a different approach for his perl solution: no s///ger, instead printf s//%s/gr
20:41:26 <zzo38> (In addition, there is also suffix optimization and other stuff. Note that the frequent words table can point inside of another string as long as the other string contains no fwords itself; any call to debugger() indicates an error.)
20:41:40 <ais523> is it just me who replaces all the noneliminatable spaces in golfing submissions with unary +, because it looks linenoisier that way?
20:41:41 <zzo38> (Calls to warn() are also errors.)
20:42:10 <b_jonas> ais523: I think I sometimes do that
20:42:27 <b_jonas> ais523: commas work in some cases when pluses don't
20:44:46 <ais523> perl 6 has a unary concat, too
20:45:37 <b_jonas> ais523: what can you do with the space after the 0 in the block version of http://www.perlmonks.com/?node_id=863110 ?
20:46:14 <b_jonas> hmm, maybe you can just put that into the pack
20:46:22 <ais523> well, if you have the space /before/ the 0 too, you can enclose the 0 in parens
20:46:24 <zzo38> Do you understand my problem now?
20:46:39 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:46:41 <ais523> doesn't gold, but fewer spaces
20:46:52 <ais523> that trailing comma is so curious
20:47:02 <ais523> I wonder if there was a typo in an early JAPH, and everyone copied it
20:47:04 <b_jonas> ais523: one trick I used in that is to put one of the two newlines at an undelible space
20:47:37 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,unpack+ab362,0,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:47:38 <HackEgo> Too many arguments for unpack at -e line 1, near "])" \ Execution of -e aborted due to compilation errors.
20:47:43 <b_jonas> oh right, unpack, not pack
20:48:19 <b_jonas> ais523: so what would you do with the space after that zero? there's no space before it
20:48:26 <b_jonas> mind you, this isn't really golf
20:49:02 <ais523> oh, I was looking at the unobfuscated example
20:49:19 <ais523> what does pack 'b' do?
20:49:28 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:49:29 <ais523> there's a pack format for inserting zero bits
20:49:41 <b_jonas> ais523: no, all pack formats can output only bytes
20:49:47 <ais523> `perl -e sub h($){($_=$_[0]=pack zb208,unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:49:48 <HackEgo> Invalid type 'z' in pack at -e line 1.
20:49:56 <ais523> `perl -e sub h($){($_=$_[0]=pack xb208,unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:49:57 <HackEgo> 33333333333333333333333333.
20:50:03 <b_jonas> ais523: b* outupts a number of bits but pads that to whole bytes
20:50:25 <ais523> ah right, and you're relying on alignment properties somehow
20:50:47 <b_jonas> the... unobfuscated example? where?
20:51:04 <b_jonas> huh... that's just as obfuscated, but with a saner formattingh
20:51:14 <b_jonas> it's basically the same with more spaces and newlines
20:51:22 <b_jonas> maybe there's some other punctuation difference, but I don't think so
20:51:55 <ais523> oh, hmm, that 0 is an ASCII 0 (=48), rather than a binary 0
20:52:03 <ais523> so I can't replace it with x, which generates a byte's worth of zero bits
20:52:04 <b_jonas> oh yeah, there is, there's a prototype difference... wth does that do
20:52:28 <ais523> ah no, you're adding one bit's worth of zeroes?
20:52:56 -!- DTSCode has quit (Read error: Connection reset by peer).
20:53:11 <b_jonas> ais523: basically, it's storing a vector of GF(128) values in a string, one per byte,
20:53:27 <ais523> b_jonas: aha, well according to the pack docs, it just checks if the ASCII character is even or odd
20:53:40 <ais523> <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:53:43 <b_jonas> so I shift each of those left by unpacking to bits, adding a single bit, repacking
20:53:46 -!- DTSCode has joined.
20:53:49 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:54:02 <ais523> now what have I done wrong?
20:54:32 <b_jonas> dunno, it's a fragile japh,
20:54:47 <ais523> <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:54:55 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:55:01 <ais523> oh, miscopied your perl-e
20:55:13 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:55:27 <ais523> how come, when I copy-and-paste your JAPH, it doesn't work for me?
20:56:04 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,unpack+ab362,0,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:56:04 <HackEgo> Too many arguments for unpack at -e line 1, near "])" \ Execution of -e aborted due to compilation errors.
20:56:27 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:56:35 <b_jonas> mind you, http://www.perlmonks.com/?node_id=581159 is more fragile. you can't modify it at all
20:56:52 <ais523> b_jonas: you post it again, if you can get it to work, change '0 .' to 'b.' and try again
20:57:17 <ais523> also I think you can save another space by changing $y to some unused special variable (I don't think you're using $.)
20:57:23 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:57:36 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:57:53 <ais523> how come, when I copy-and-paste your JAPH, it doesn't work?
20:57:55 <b_jonas> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack+b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y,for+0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:58:03 <b_jonas> ais523: dunno, maybe you mispasted
20:58:08 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:58:24 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLBx)Z]n0*zf\0I3"=~/./g;print$r
20:58:29 <ais523> that's using both clipboards
20:58:34 <ais523> I'm going to look for differences in the log
20:59:25 <ais523> `perl -e sub h($){($_=$_[0]=pack b208,b.unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r
20:59:45 <ais523> apparently my client was interpreting the %O as a color code, I had to escape it
21:00:14 <b_jonas> `perl -e eval for'for$=(2..27){$*=0;$*=($**$=+ord)%127,for/./gs;print+chr$*}'."\n#ig\\tq\24^-/v\c^l,\23\$%\3\ta2\tk\b\c\)\x18 -- ambrus"
21:00:15 <HackEgo> $* is no longer supported at (eval 1) line 1. \ Just another Perl hacker,
21:00:30 <b_jonas> be glad it's not this japh, this one basically can't be modified at all without breaking everything
21:00:36 <b_jonas> because it uses the whole string to compute the output
21:00:43 <b_jonas> except for the eval for part
21:00:44 -!- bb010g has joined.
21:00:48 <b_jonas> it's from http://www.perlmonks.com/?node_id=581159
21:01:01 <b_jonas> typo anything and it breaks
21:02:25 <b_jonas> `perl -Xe eval for'for$=(2..27){$*=0;$*=($**$=+ord)%127,for/./gs;print+chr$*}'."\n#ig\\tq\24^-/v\c^l,\23\$%\3\ta2\tk\b\c\)\x18 -- ambrus"
21:04:32 <ais523> `perl -Xe eval for'for$=(2..27){$*=0;$*=($**$=+ord)%127,for/./gs;print+chr$*}' . "\n#ig\\tq\24^-/v\c^l,\23\$%\3\ta2\tk\b\c\)\x18 -- ambrus"
21:05:02 <b_jonas> yes, you can modify the part outside the string
21:06:20 <zzo38> Did you see the decompression algorithm I had and needed a compressor for? (It isn't a very good compression, but you can do better than Infocom did.) Also, for a compression algorithm that works for a single string if the frequent words table is already filled in, see http://zzo38computer.org/zmachine/doc/tricky.txt under "Black-Johansen".
21:06:34 <ais523> also, I declare it a new #esoteric tradition that when talking about a JAPH, you ensure that the word comes just before a place where you'd naturally put a comma anyway
21:06:38 <ais523> to leave the spelling ambiguous
21:06:49 <ais523> just like the original brainfuck spec never used the word at the start of a sentence
21:07:10 -!- AndoDaan has left.
21:07:20 -!- AndoDaan has joined.
21:09:55 <ion> We have these things called quotation marks which let you write “Just another Perl hacker,” unambiguously.
21:10:57 <Lymia> What's the fun in that/
21:12:18 <ais523> ion: except it doesn't work
21:12:19 <zzo38> If you don't like those kind of qutation marks then you can also use ASCII quotations marks. (Assuming that you want to use quotations marks at all, which you don't.)
21:12:26 <ais523> `perl -e print “Just another Perl hacker,”
21:12:27 <HackEgo> Unrecognized character \xE2; marked by <-- HERE after print <-- HERE near column 8 at -e line 1.
21:12:47 <ais523> `perl-e use utf8; print “Just another Perl hacker,”
21:12:48 <HackEgo> Unrecognized character \xE2; marked by <-- HERE after f8; print <-- HERE near column 17 at -e line 1.
21:13:05 <ais523> `perl -e use utf8; print “Just another Perl hacker,”
21:13:06 <HackEgo> Unrecognized character \xE2; marked by <-- HERE after f8; print <-- HERE near column 18 at -e line 1.
21:13:18 <ais523> maybe `perl is doing weird thing with encodings already
21:13:31 <Taneb> ais523, you had it coming by trying to run non-obfuscated Perl
21:13:55 -!- AnotherTest has joined.
21:14:01 <ais523> Taneb: no, I expected it to fail
21:14:09 <ais523> I just don't get why the error messages is the same in both cases
21:14:15 -!- serika has joined.
21:14:59 <HackEgo> serika: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
21:15:20 -!- zzo38 has quit (Read error: Connection reset by peer).
21:22:04 <ais523> there are plenty of other esolang bots
21:22:11 <ais523> but it has to be in an actual esolang to count
21:22:28 <j-bot> b_jonas: |value error: hi
21:22:51 <ais523> `! bf ++++++++++[->++++++++++<]>++++.+.
21:23:13 <ais523> that can almost certainly be done shorter, but I was trying to do it mentally and don't have the constants table memorized
21:23:42 <ais523> !bf8 ++[>+<+++++]>+.+.
21:24:12 <ais523> !bf8 +[->-[<]>--]>-.+.
21:24:20 <ais523> that was actually checking the wiki
21:24:29 <ais523> current shortest known hi
21:28:44 -!- AndoDaan_ has joined.
21:29:15 <AndoDaan_> is there a way to prove some bf code is the shortest for a given task without an exhaustive search?
21:29:33 <ais523> AndoDaan_: in general, no
21:29:35 <b_jonas> AndoDaan_: no, and you can't prove even with an exhaustive search
21:29:38 <ais523> halting problem and all that
21:29:42 <b_jonas> at least for non-trivial tasks
21:29:46 <ais523> sometimes, the answer is yes in special cases
21:30:00 <b_jonas> right, for very short programs you could be sure
21:30:17 -!- AndoDaan has quit (Ping timeout: 272 seconds).
21:30:22 -!- AndoDaan_ has changed nick to AndoDaan.
21:30:49 <b_jonas> and of course you probably have to assume a particular variant on what to allow (overflow, underflow, left from starting position)
21:31:14 <ais523> I said !bf8 explicitly for a reason :-)
21:31:37 <b_jonas> ais523: does that have an infinite tape both sides of the starting point?
21:31:40 <AndoDaan> hmm. I wrote a bf interpreter the other day, and so many option just for it's basic form...
21:31:43 <ais523> the wiki currently doesn't assume that left from starting position is legal, it adds extra > if necessary
21:32:02 <elliott> @google kolgomorov complexity
21:32:03 <lambdabot> http://en.wikipedia.org/wiki/Kolmogorov_complexity
21:32:03 <lambdabot> Title: Kolmogorov complexity - Wikipedia, the free encyclopedia
21:32:04 <ais523> hmm, did anything come of the Big BF Standardisation Vote?
21:32:48 <AndoDaan> i've read abpit kolgomorov a couple of times, interesting stuff.
21:32:50 <Bike> technically an exhaustive search won't work either, since you can't prove a given partial function is implemented by a given program. math
21:33:11 <b_jonas> Bike: yep. that's what we were trying to say.
21:33:33 <vanila> you can write an search that prints out things it can't fully understand
21:33:48 <Bike> i've been trying to figure more about kolmogorov and turbulence but the book is checke dout from the library, it sucks
21:33:50 <vanila> which you can then prove dont terminate or so manually or add extra features to the program
21:33:54 <Bike> tao said navier-stokes might be some turing garbage, too
21:34:05 <ais523> there is some limit below which an exhaustive search actually does work
21:34:15 <b_jonas> vanila: if you assume stuff like execution time within our lifetime, sure
21:34:17 <ais523> this may or may not be discoverable by exhaustive search
21:34:21 <vanila> since game of life is turing complete it's not hard to imagine navier stokes being too
21:34:32 <vanila> although it's really much more complex since it works on real number field
21:34:46 <vanila> (like just given that its automatically not computable, isn't it?)
21:34:47 <ais523> I'm still interested in the "what's the shortest BF program that's beyond human ability to determine whether it halts" problem
21:35:06 <b_jonas> ais523: I'd guess it's quite short
21:35:08 <vanila> ais523, me too - I have an idea to find it
21:35:09 <ais523> working on reals doesn't /necessarily/ mean uncomputable, but doing anything nontrivial with them normally does
21:35:15 <Bike> vanila: no, lots of smooth operations on reals are computable
21:35:24 <vanila> Bike, oh ok interesting!
21:35:27 <Bike> it's not like you're asking whether water is moving exactly at 5 m/s, that would be impossible
21:35:30 <ais523> comparing them is particularly nasty
21:35:50 <ais523> vanila: physically, yes
21:35:56 <elliott> I'm still interested in that too
21:36:00 <ais523> as for do I want you to PM me, that rather depends on what you're PMing me about
21:36:05 <elliott> I brought it up again recently
21:36:10 <vanila> finding short brainfuck programs
21:36:10 <ais523> if it's something that needs to be private, PM is fine
21:36:23 <ais523> if it's just "thing that would spam up the channel" but it's ontopic, the channel is better
21:36:44 <ais523> if it's particularly spammy, like you're going to paste 100-line programs, we have #esoteric-blah but a pastebin is better
21:37:02 <vanila> ok ill say it in -blah if anyone wants to hear
21:37:06 <vanila> <elliott> I'm still interested in that too
21:37:22 <b_jonas> ais523: I achieved that with my bot that connects an emulated DOS machine to irc
21:37:45 <ais523> b_jonas: right, I remember that
21:37:51 <b_jonas> but I knew it's like that so I didn't even try to remember to bring it here
21:46:49 <FireFly> Might as well idle there too
21:46:58 <Bike> i have no idea why short bf programs would not be a topic of discussion here
21:47:08 <ais523> the discussion isn't spammy enough to not hold here
21:47:20 <FireFly> Sounds more on-topic than most discussion that takes place in here
21:47:24 <elliott> cozier? how does spelling work
21:48:13 <Bike> anyway, if you come up with a program that can be proven to be impossible to prove the haltingness of, do share, i've never been able to understand that intuitively despite my math powerz
21:48:14 <ais523> I think "cosier" is correct; at least, my spellchecker likes it
21:48:32 <ais523> Bike: the problem is, the existing constructions tend to be quite complex
21:48:41 <b_jonas> exactly. discuss short BF programs here unless that discussion would derail some more important discussion like one about nethack.
21:48:44 <ais523> basically because you have to embed the entire rules of the logic you're using in the program
21:48:58 <ais523> b_jonas: we already have #nethack4 for discussion about nethack, though
21:49:06 <Bike> i mean, something like "this program halts only if the goldbach conjecture is true", i can get that
21:49:23 <b_jonas> ais523: yeah, I know, I'm joined to like five nethack channels because people can't keep it together
21:49:36 <Bike> i guess making a program that halts only if the continuum hypothesis is true doesn't make much sense
21:49:55 <ais523> I'm currently in 8 NetHack channels, and parted #interhack (which would be the ninth) to make room for #esoteric-blah
21:50:03 <ais523> (I have a "only one screenful of channels" policy)
21:50:14 -!- DTSCode has changed nick to dTSCode.
21:50:27 <b_jonas> #esoteric #nethack4 #nethack #nethack-dev #devnull_nethack
21:50:39 <b_jonas> ais523: what does "one screenful" mean?
21:50:41 <Bike> #nethack-nethack, for discussion of implementing nethack in nethack
21:50:58 <vanila> "a program that can be proven to be impossible to prove the haltingness of"
21:51:01 <Bike> that reminds me, someone who is not a programmer linked to that nethack speedrun repo ais is in
21:51:04 <Bike> tripped me out
21:51:05 <ais523> Bike: that it's possible to fit all the tabs in the width of my screen, without scrolling
21:51:13 <vanila> you could write a proof checker for PA or so
21:51:20 <vanila> and diagonalize over it
21:51:23 <ais523> Bike: we think NetHack is sub-TC (and, in fact, unusable for programming)
21:51:26 <vanila> and then it would be impossible to prove that halts with PA
21:51:28 <ais523> but it's unclear /what/ the right channel for that is
21:51:31 <ais523> here or #nethack4, most likely
21:52:11 <Bike> this reminds me that nobody's commentd on the one contribution to the esolang wiki i've actually made, so out of spite i'll just have to go back to talking about nothing
21:52:16 <int-e> Bike: The continuum hypothesis thing would amount to deriving an upper bound to counterexamples of the CH, I think.
21:52:36 <Bike> i'm just thinking of it cos CH is independent of ZFC and all
21:52:42 <int-e> ignore this, I'll go hide under a stone.
21:52:43 <Bike> not that programs use ZFC or... something
21:52:49 <vanila> you couldn't use CH I think
21:52:56 <ais523> Bike: I normally don't focus on /who/ makes contributions
21:53:08 <ais523> the musical notes person made another language, and didn't spam it to the main page this time
21:53:11 <Bike> could you have a program that can be proven to halt under some axiom set but not another, well i mean of course you can
21:53:25 <Bike> ais523: it was a talk page thing rather than a language, is probably why
21:53:30 <ais523> it does a decent job of trying not to be a BF derivative, while being stuck in an utterly low-level imperative mindset
21:53:33 <Bike> i have some esolang ideas but they'd be hard to describe sanely
21:53:35 <int-e> Bike: for some reason I was thinking of the Riemann Hypothesis, and I will not endeavour to find out why.
21:53:45 <ais523> Bike: I was going to say "that's never stopped me"
21:53:48 <ais523> except, it actually has
21:53:58 <Bike> the language that must not be named
21:54:13 <b_jonas> I have an esolang idea too, but it doesn't work out well and isn't very eso too (not that that's stopped some people)
21:54:16 <Bike> mainly the problem is that i don't have enough experience with auto mechanics to think of a good description language, but oh well
21:54:22 <ais523> I'll revise it to "it takes quite a while before I eventually give up, and when I do, I give up really strongly, and bind other people to never speak of the issue again"
21:54:37 <ais523> gah, I hadn't been thinking about the issue for /months/
21:54:43 <ais523> and it's not something I want to think about right now
21:54:45 <Bike> uh, sorry i guess
21:54:47 <b_jonas> I think I'm probably not really an eso language _create_ type of guy
21:55:17 <Bike> the issue might be that i'm more into real numbers than most people here, which is kind of a hilarious thing to say or think but oh well
21:55:28 <MDude> I'd like to make a reversible logic based thing.
21:55:39 <Bike> have you seen the crabputer
21:55:47 <Bike> that's not really related, i just want everyone to have seen the crabputer
21:56:04 <ais523> Bike: anyway, anything less complex than http://esolangs.org/wiki/Snowflake should be easy to describe by comparison
21:56:14 <MDude> I'd rather try to make it non-esoteric, but it might end up as such regardless.
21:56:21 <Bike> http://arxiv.org/abs/1204.1749
21:56:25 <ais523> the big problem now is, I need a Snowflake impl, on the basis that as far as I know, nobody else has managed to successfully read the resulting description
21:56:28 <Bike> based on billiard ball computers which is how i thought of it
21:56:53 <int-e> real number just don't know when to stop
21:57:05 <Bike> it's not really a matter of complexity so much as... i guess i don't know how to constrain it in an interesting way
21:57:11 <ais523> also, one thing I love about Snowflake is that it's not reversible just for fun, but because the purpose of the language can only (AFAICT) be implemented via reversibility
21:57:30 <Bike> basically the idea is the "program" is a fire control computer schematic, but the problem is i can't think of a way to describe that without just having arbitrary schematics, which is just boring
21:57:36 <ais523> hmm, the fact that it looks vaguely like brainfuck despite having an entirely unrelated meaning is also good
21:57:38 -!- MoALTz has quit (Ping timeout: 260 seconds).
21:58:39 <Bike> int-e: does alexandroff compactification constitute stopping
21:58:54 <b_jonas> what looks vaguely like brainfuck? befunge?
21:59:29 <Bike> the original (i think) paper on reversible computing is neat, btw, by landauer or whoever
21:59:47 <MDude> The idea I have is a language that's basically a way of describing a single huge reversible function.
22:00:13 <ais523> it's mostly made of +-[] and the brackets match
22:00:21 <ais523> which makes it look like BF until you realise that it makes no sense as BF
22:00:35 <Bike> it's still a valid program innit
22:00:37 <Bike> if a boring one
22:01:04 <ais523> it's an infinite loop as BF
22:01:14 <ais523> !bfjoust snowflake +[+[]-[]]
22:01:16 <ais523> and a no-op as BF Joust
22:01:18 <zemhill> ais523.snowflake: points -30.67, score 3.72, rank 47/47
22:01:22 <EgoBot> Score for ais523_snowflake: 6.1
22:01:26 <MDude> So you have a few basic operations, an if statement, and the ability to call functions.
22:01:46 <b_jonas> ais523: hmm, that looks like that strange language (not intended to be esoteric I think, but it sure looked like one) I've once seen
22:02:06 <b_jonas> the one that tried to pretend to be totalistic and Turing-complete, and pretend that lists and numbers are isomorphic
22:02:10 <ais523> b_jonas: I doubt any other language works quite like Snowflake
22:02:17 <vanila> MDude, there are reversible programming languages - you can run them backwards and forwards
22:02:18 <ais523> most languages are not on a quest for self-perfection
22:02:21 <b_jonas> ais523: no, I just mean the +[+[]-[]] syntax
22:02:21 <int-e> Bike: I was thinking of individual numbers and their n-ary expansion.
22:02:47 <vanila> doesn't "if" destroy information
22:02:56 <MDude> Most of them have some kind of stack, though.
22:03:09 <int-e> Bike: or perhaps, rational approximations. just to clarify that rational numbers *are* nice. :P
22:03:29 <MDude> Rather than using a fixed set of memory addresses.
22:03:50 <vanila> it might not be turing complete if you restrict memory that much
22:04:02 <ais523> Snowflake's a good example of a reversible command set
22:04:09 <ais523> it had to be very 100% reversible because of how it works
22:04:21 <ais523> so loops and conditionals were implemented… oddly
22:04:44 <ais523> most operations can only be written reliably if you know, for certain, something that /isn't/ on top of the stack
22:04:53 <MDude> Oh, it won't be, unless you modify it to pretend it has an infinite repeating input structure.
22:04:57 <ais523> which is harder than it seems, as programs have to be quite good at editing their own source code
22:05:12 <MDude> Or infinitely repeating structure.
22:05:23 -!- Phantom_Hoover has joined.
22:06:28 <MDude> I'm going more for something that can be implimented as a digital signal processor, though.
22:08:26 <int-e> @tell oerjan Oh I didn't realize that golf.shinh.org allows omitting several trailing newlines...
22:08:28 <MDude> So it'll likely be Harvard architecture, and thus unable to modify itself at all.
22:09:03 <FireFly> `js print(+[+[]-[]]) // maybe it reminded you of JavaScript?
22:09:24 <FireFly> I don't think it's intended to be esoteric.
22:11:03 <MDude> vanila: That's the thing. "If" statements preserve reversability by locking out any change to the conditional variable while inside it.
22:11:05 <ais523> IMO, if you're designing a new language and don't intend it to be esoteric, you don't have a sufficient grip on the problem you're trying to solve
22:11:17 <ais523> possible exception: if you're designing it to be used by other people
22:12:17 <vanila> MDude, that's interesting but I can't understan how?
22:12:21 <MDude> So it's "If (A), do [function] with variables (B, C, D,... etc.)."
22:12:51 <MDude> And then inside the function, you only have access to the variables passed to it.
22:13:13 <ais523> "for division, you multiply the list by the number you want to divide by, then cut the product down to the size of the original list, and then undo the multiplication"
22:13:40 <MDude> So you can't make a recursive function unless it's parametric, allowing each iteration to have at least one variable less than the one calling it.
22:17:25 <MDude> I should just make diagrams, or implement the language.
22:30:21 -!- AndoDaan_ has joined.
22:30:26 -!- AndoDaan has quit (Ping timeout: 258 seconds).
22:32:51 -!- AndoDaan_ has changed nick to AndoDaan.
22:36:40 -!- oerjan has joined.
22:54:09 -!- Sprocklem has quit (Ping timeout: 244 seconds).
22:54:41 -!- ais523 has quit.
22:56:22 -!- Sprocklem has joined.
22:56:58 -!- AnotherTest has quit (Ping timeout: 264 seconds).
23:02:43 -!- dTSCode has quit (Ping timeout: 244 seconds).
23:03:51 -!- kcm1700 has quit (Remote host closed the connection).
23:11:11 -!- kcm1700 has joined.
23:14:50 <lambdabot> int-e said 1h 6m 23s ago: Oh I didn't realize that golf.shinh.org allows omitting several trailing newlines...
23:14:51 -!- Vorpal_ has changed nick to Vorpal.
23:18:42 <oerjan> int-e: well i noticed how it always leaves off the final newline when displaying output, so it seemed logical to check if that happened for any number...
23:19:10 <oerjan> maybe i was inspired by HackEgo, which does that same thing
23:21:29 <oerjan> oh, i didn't remember i actually did manage to use pattern guards in that one
23:27:02 -!- zzo38 has joined.
23:27:32 <oerjan> oh and that's where you used that "where" that i was hinting that you might improve with pattern guards, funny how it tied
23:41:37 <zzo38> How many bits does a process ID have?
23:43:49 <Bike> posix seems to just say pid_t is a signed integer
23:44:05 <b_jonas> zzo38: well, that's typical range, don't take that a portably true everywhere
23:44:58 <zzo38> The clock sequence in a UUID is only 14-bits long though.
23:46:01 <Bike> oh: Under Linux, the maximum process ID is given by the pseudo-file /proc/sys/kernel/pid_max
23:46:33 <Bike> and yeah 15 here
23:48:37 -!- boily has joined.
23:49:58 <int-e> oerjan: as an idea of how to account where the "where": length "where" == length "cycle".
23:53:34 <zzo38> How do you send a message to IETF to tell them to add another UUID version?
23:53:37 <int-e> oerjan: I'm saying that because they serve approximately the same purpose: making the mail body available to the worker loop multiple times.
23:54:07 <zzo38> Someone told me that a missile address is 48-bits long, so that fits in the node field.
23:54:29 <zzo38> However if a process ID is 15-bits long then it is one bit too long for the clock sequence field.
23:55:47 <oerjan> int-e: ah right, that's the part which only works because anagolf ignores trailing newlines _and_ the last @i is only followed by newlines
23:57:07 <int-e> oerjan: I discarded the "cycle" idea because I didn't expect that to work ... lucky to have tied :)
23:57:30 <int-e> so now I can claim that my solution is better because it cheats less.
23:58:30 <int-e> (and once more it seems to be hard to combine any ideas to produce a smaller one)
23:58:55 <int-e> solution, that is.
00:08:02 -!- AndoDaan has left ("bbl").
00:32:58 <zzo38> Someone told me today that a sufficiently precise missile address is possible in 48-bits. Is it correct?
00:33:53 <vanila> ii thkn it depends on the radius of the explosion of the missle
00:36:11 <zzo38> It isn't the intention to actually aim a missile; I only intend to see how it can be used for uniqueness.
00:36:17 <fungot> boily: ' too proud?' the frog said in a thoughtful tone. " hold your tongues!" and fnord tingled his bell.
00:39:58 <fungot> FireFly: i.e. some mischievous creatures are not soldiers." the fnord conspirator stammered, trying her best to climb up one of our books to the glass, and began wandering up and down the room.
00:41:27 <oerjan> > 4*pi*(20000/pi)^2 / 2^48
00:42:48 <oerjan> zzo38: that's about 1.8 square meters resolution if you divide up earth's surface equally
00:45:10 <boily> FireFly: I wouldn't call it a conspiracy; it's kind of widely known that fungot's raison-d'être is to conquer the world.
00:45:10 <fungot> boily: " fading, with the glass table as before. " things are worse than ever," said i. " my son was in the act of waking, i felt certain that ' love,' and then hurried on, alice started to her feet and sprang across the little brook in her terror,
00:45:34 <FireFly> boily: well, fungot talked about a fnord conspirator
00:45:34 <fungot> FireFly: and he flung his arms passionately round her neck, and hid his face on her shoulder. " what a convenient thing it would be grand!"
00:45:53 <zzo38> oerjan: O, OK, do you think that is good enough?
00:45:54 <boily> FireFly: collaborators.
00:46:26 <oerjan> zzo38: i expect most icbms to be larger than that.
00:46:50 <zzo38> Like I said it is not used for an actual ICBM.
00:47:17 <oerjan> well, in that case i can hardly know how good is good enough.
00:47:47 <zzo38> I mean if they eventually invented a new UUID version that uses ICBM addresses.
00:49:12 <oerjan> eventually it will be too few see http://xkcd.com/865/
00:49:48 <oerjan> (pretty sure ipv6 is more than 48 bits right?)
00:50:38 <zzo38> Yes, I do not expect each nanobot to need a UUID all at the same time though?
00:51:37 <oerjan> well i guess we are doomed then.
00:52:19 <zzo38> A UUID is itself 128 bits though, anyways, and some are used for the variant and the version.
00:53:20 <oerjan> beware of the NAT-nobots, though.
00:53:33 <zzo38> Currently I am using version 1 UUIDs, but it might not always do, for example if you don't have and never had a MAC address available.
00:54:30 <oerjan> `` \? cocoonspirator #regarding fungot
00:54:30 <fungot> oerjan: his wife caught the idea, that alice had any idea of doing that. she felt as if she were flying, and alice, were in fnord of the march of mind, kept up what she no doubt intended for a savage growl, though it answers as a puff, it never has effect enough to make one fnord to think of it, she held it up to a glass, the words will all go the right way to begin, you see, it takes all the running you can do anything with, b
00:54:31 <HackEgo> A cocoonspirator is a collaborator wrapped in caterpillar silk
00:55:06 <oerjan> one gets the sense that lewis carroll used a lot of unique words.
00:55:28 <oerjan> and not all of them made up, either
00:56:06 <zzo38> RFC does say the timestamp will eventually run out and have to wrap around. But even then, it could continue until the timestamp is the same as it was at the time MAC addresses were invented; at that point you would have to stop using version 1 UUIDs and will have to make up a new one.
00:58:05 <zzo38> (Actually, it can last later than that; it only has to be according to when the specific MAC address was assigned, rather than when MAC addresses were invented in general. However this is not always known.)
01:07:57 -!- vanila has quit (Quit: Leaving).
01:12:55 -!- AndoDaan has joined.
01:17:19 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
01:17:39 -!- scoofy has joined.
01:33:22 -!- Guest20404 has joined.
01:33:24 -!- Guest20404 has left.
01:49:48 -!- shikhin has joined.
01:53:19 -!- shikhout has quit (Ping timeout: 260 seconds).
01:59:38 -!- oerjan has quit (Quit: leaving).
02:02:41 -!- AndoDaan has quit (Ping timeout: 272 seconds).
02:08:25 -!- AndoDaan has joined.
02:15:56 -!- boily has quit (Quit: PHAROAH CHICKEN).
02:18:19 -!- shikhin has quit (Ping timeout: 245 seconds).
02:35:56 -!- centrinia has joined.
03:56:11 -!- nys has quit (Quit: quit).
04:14:05 -!- serika has quit (Ping timeout: 255 seconds).
04:14:29 -!- AndoDaan_ has joined.
04:14:34 -!- AndoDaan has quit (Ping timeout: 245 seconds).
04:15:21 -!- AndoDaan_ has changed nick to AndoDaan.
04:24:49 -!- DTSCode has joined.
04:48:25 -!- dianne has quit (Ping timeout: 250 seconds).
04:50:09 -!- dianne has joined.
04:50:12 -!- dianne has quit (Changing host).
04:50:12 -!- dianne has joined.
04:50:14 -!- centrinia has quit (Ping timeout: 250 seconds).
05:04:08 -!- centrinia has joined.
05:26:00 <zzo38> Even Famicompo has a cover of "Gravity Falls" music.
05:34:05 -!- MDude has changed nick to MDream.
06:11:30 -!- DTSCode has quit (Read error: Connection reset by peer).
06:13:41 -!- MoALTz has joined.
06:26:48 -!- DTSCode has joined.
06:30:04 -!- AndoDaan has quit (Ping timeout: 264 seconds).
06:47:29 <zzo38> How much is a shift-reduce parser improved by if there is a skip action added? (Skip means like a shift, except that nothing is pushed to the stack; it still selects another state to parse the next token with, but doesn't affect the stack, therefore such the next state will become forgotten later on.)
06:49:34 -!- AndoDaan has joined.
06:57:57 <int-e> that's a tail call optimization, isn't it?
06:58:39 <zzo38> It is a bit like a tail call optimization, I suppose, although you may be able to use it in other cases too.
07:00:01 <zzo38> They might reduce the number of productions you need too, in a few cases
07:00:23 <Sgeo> What is Famicompo?
07:00:28 * Sgeo listens to gravity falls cover
07:00:55 <Sgeo> NSF competition apparently?
07:01:26 <zzo38> I have *all* of them on my computer.
07:04:15 -!- AndoDaan has quit (Ping timeout: 244 seconds).
07:05:12 -!- AndoDaan has joined.
07:28:25 -!- Patashu has joined.
09:09:39 -!- hjulle has joined.
09:21:36 -!- AndoDaan has quit (Ping timeout: 272 seconds).
09:37:08 -!- MoALTz_ has joined.
09:39:58 -!- MoALTz has quit (Ping timeout: 255 seconds).
09:41:45 -!- Sprocklem has quit (Ping timeout: 265 seconds).
09:52:04 -!- centrinia has changed nick to sho_jitou.
09:52:13 -!- sho_jitou has changed nick to centrinia.
09:57:08 <Lymia> I wonder how hard it'd be to make a polyglot of Malborge and some other language
09:57:12 <Lymia> (That is not Whitespace)
09:58:32 <b_jonas> it's still spelt with an L!
09:58:54 <fizzie> Yeah, don't make oerjan mad. You won't like that.
10:05:30 <fizzie> I wouldn't tempt fate like that, but of course it's up to you.
10:06:00 <fizzie> As for the polyglot, if not Whitespace, then Lenguage.
10:18:03 -!- AndoDaan has joined.
10:21:03 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:25:52 -!- centrinia has quit (Ping timeout: 264 seconds).
10:53:00 <fungot> mroman: aye louder screamed that ladye fair, wi' a silken string, whilk i sent to them again to say " how d'ye do?"
10:53:24 <fungot> Available: agora alice* c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
10:53:42 <mroman> New Game: Guessing fungots currently selected style.
10:53:42 <fungot> mroman: " i have heard of you, you wicked wicked boy!" said her husband. " we're not fnord!" he exclaimed, holding up his hand impressively. and now, who am i?'
10:56:41 <fungot> Selected style: youtube (Some YouTube comments)
10:56:53 -!- FreeFull has quit.
10:56:59 <fungot> Lymia: omg i diedddd doesnt suck like hitman did the pilot died shoving the power to climb. the pilots, no, oh no
10:58:20 <mroman> fizzie: could you add ^randomstyle ;)?
10:59:20 <Lymia> Changed in version 2.6: The return value is in the range [-2**31, 2**31-1] regardless of platform. In older versions the value is signed on some platforms and unsigned on others.
10:59:20 <Lymia> Changed in version 3.0: The return value is unsigned and in the range [0, 2**32-1] regardless of platform.
11:05:52 <fizzie> fungot: What about the pilots?!
11:05:52 <fungot> fizzie: oh no oh no, oh no, what
11:06:04 <fizzie> fungot: Come on, bot, don't leave us hanging.
11:06:04 <fungot> fizzie: i learned that the tape or is that someone ' dies of cancer' is it
11:13:08 <b_jonas> what music are you listening to, fungot?
11:13:08 <fungot> b_jonas: omg this is the black guy supposed to do a flyby and crashed into a corner big time, this is a problem with the hillary impersonator
11:13:31 <b_jonas> a black guy is impersonating hillary?
11:20:25 <fizzie> The main problem with Hillary impersonators are their poor aviation skills.
11:20:28 -!- boily has joined.
11:22:15 <fizzie> "Access to this document is outside your subscription" nooooooo
11:43:35 <fizzie> Have to be grateful to authors for preprints, I guess.
11:48:13 <shachaf> what if an author postpones preprints
12:06:03 -!- Patashu has quit (Ping timeout: 240 seconds).
12:10:09 <fizzie> Some sort of a reality collapse, presumably.
12:15:54 <boily> reality is way to brittle in these here parts. there should be an open source reality effort or something.
12:21:18 -!- boily has quit (Quit: EXONERATED CHICKEN).
12:25:53 -!- CADD has quit (Quit: leaving).
12:52:50 -!- Phantom_Hoover has joined.
13:25:43 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40822&oldid=40818 * TomPN * (+132) /* Motion */
13:26:53 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40823&oldid=40822 * TomPN * (+102) /* Velocity */
13:27:21 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40824&oldid=40823 * TomPN * (-18) /* If the cell has a value */
13:27:41 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40825&oldid=40824 * TomPN * (-12) /* If the cell has a velocity */
13:29:29 <HackEgo> [wiki] [[User talk:TomPN]] http://esolangs.org/w/index.php?diff=40826&oldid=40744 * TomPN * (+88)
13:30:07 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40827&oldid=40813 * TomPN * (+64)
13:30:20 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40828&oldid=40827 * TomPN * (+4)
13:31:19 <HackEgo> [wiki] [[User talk:TomPN]] http://esolangs.org/w/index.php?diff=40829&oldid=40826 * TomPN * (+123)
13:32:16 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40830&oldid=40825 * TomPN * (+0) /* Moving the pointer */
13:38:52 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40831&oldid=40830 * TomPN * (+159) /* Example programs */
13:39:08 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40832&oldid=40831 * TomPN * (+1) /* Hello World! */
13:50:15 <J_Arcane> IT is infuriatingly difficult to Google anything relating to BASIC.
13:53:12 <Taneb> Apparently there's a Forth seminar happening tomorrow
13:54:31 <J_Arcane> Lisp in QBASIC: https://www.ma.utexas.edu/users/dmenezes/lisp.html
14:15:16 <int-e> @tell oerjan Very nice substrings code, the closest I had was based on iterate(zipWith(:)x.drop 1)(repeat[]) (which then became t=[]:t;z?(_:y)=z y++z?z y;_?y=y; ... zipWith(:)x?t ...). I have to remember that scanr f x.map g=scanr(f.g)x.
14:17:17 -!- impomatic_ has left.
14:18:29 <J_Arcane> Since being introduced more clearly to how easy it actually is to implement new language modules in Racket, I have this deranged idea to do a GW/QBASIC inspired Lisp variant.
14:18:29 <mroman> J_Arcane: Because of all the VisualBasic noobs?
14:20:29 <J_Arcane> mroman: I had it in mind originally as a sort of sequel to VIOLET, and even though of just doing an enhanced VIOLET that turned it into a proper Lisp. But I also kinda just want to essentially write a Lisp with QB inspired keywords, like if some dude circa 198x had been tasked with making a Lisp that would be friendly to MS Basic students.
14:25:09 -!- oerjan has joined.
14:29:13 <J_Arcane> Interesting thing I learned: Apparently FreeBASIC supports tail recursion optimizations.
14:39:46 -!- Frooxius has quit (Quit: *bubbles away*).
14:42:53 <lambdabot> int-e said 27m 36s ago: Very nice substrings code, the closest I had was based on iterate(zipWith(:)x.drop 1)(repeat[]) (which then became t=[]:t;z?(_:y)=z y++z?z y;_?y=y; ... zipWith(:)x?t ...). I have to remember that scanr f x.map g=scanr(f.g)x.
14:44:58 <mroman> !blsq {"abc" "def"}{<-}m[
14:45:01 <mroman> !blsq {"abc" "def"}{<-}\m
14:45:08 <mroman> !blsq {"abc" "def"}{<-}ms
14:45:47 <oerjan> <mroman> still no new whatif <-- i distinctly recall a "there won't be any this week note", last week
14:52:19 -!- serika has joined.
14:58:03 <oerjan> damn neighbor dog is at it again, it had been silent for so long i thought they'd actually managed to find a solution to its yipping
14:59:16 <mroman> I guess you need to buy a silencer.
15:01:15 <oerjan> ...glad i looked up the meaning of that before responding
15:05:38 <serika> http://www.ultimatebarkcontrol.com/dog-silencer.htm This looks pretty legit
15:05:42 * oerjan wonders why henkma's solution needs that ++" "
15:05:53 <serika> Oh my god. "UltimateBarkControl"
15:06:12 <oerjan> serika: i don't think that's what mroman was referring to.
15:06:29 <Taneb> If I have createFoo :: Bar Foo, and destroyFoo :: Foo -> Bar (), and using a Foo after it's been destroyed is an error...
15:06:35 <Taneb> Is there a nicer way to do that in Haskell?
15:06:45 <HackEgo> serika: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
15:06:49 <elliott> oh. you were already welcomed. right.
15:07:00 <serika> oerjan: But shooting dogs ;-;
15:07:41 <oerjan> serika: i greatly suspect that's illegal in norway.
15:08:08 <oerjan> but then, i greatly suspect my neighbors are already trying out things that are illegal in norway, in desperation.
15:08:41 -!- `^_^v has joined.
15:09:59 <oerjan> > reads "" :: [(Integer,String)]
15:10:08 <oerjan> > reads " " :: [(Integer,String)]
15:10:16 <oerjan> > reads "1" :: [(Integer,String)]
15:10:23 <oerjan> > reads "1 " :: [(Integer,String)]
15:11:22 <oerjan> the " " allows him to detect if he's taken too much
15:11:25 <lambdabot> Source not found. Take a stress pill and think things over.
15:11:47 <oerjan> it's String -> [(a, String)]
15:12:42 <Melvar> Sticking that giant type annotation on looks uncomfortable … idris has spoiled me.
15:12:43 <oerjan> i had similar ideas to henkma's solution, but never thought of using reads
15:13:10 <oerjan> Melvar: it would default to () rather than Integer otherwise
15:14:21 <Melvar> oerjan: I mean if I had such a function in Idris I’d write “reads {a=Integer} ""” etc.
15:16:46 <Melvar> I.e. I could get away without writing the parts of the result type that it knows anyway.
15:16:51 <oerjan> it seems my guess about int-e's solution was entirely wrong, he actually found exactly the same prime checking code as i
15:18:14 -!- shikhin has joined.
15:23:20 <oerjan> oh henkma is making use of NonDecreasingIndentation
15:23:54 -!- drdanmaku has joined.
15:24:16 <oerjan> and thus managing not to waste space even though e nests dos
15:26:43 <oerjan> int-e: interesting, henkma's solutions _cannot_ be one-lined :P
15:27:05 <oerjan> without wasting space for a }
15:52:30 -!- vanila has joined.
15:56:49 -!- shikhin has quit (Disconnected by services).
15:57:56 -!- serika has quit (Quit: Ik ga weg).
16:05:26 <HackEgo> [wiki] [[Dimensions]] M http://esolangs.org/w/index.php?diff=40833&oldid=40832 * BCompton * (+0) Explainations -> explanations, ouput -> output
16:46:34 <HackEgo> [wiki] [[TinyBF]] N http://esolangs.org/w/index.php?oldid=40834 * Bataais * (+1491) Created page with "'''tinyBF''' is a [[brainfuck]] equivalent with only 4 characters. It's a variant of [[RISBF]] and was created by Michael Gianfreda, Nov. 6, 2014. tinyBF programs are smaller..."
16:47:03 <HackEgo> [wiki] [[TinyBF]] http://esolangs.org/w/index.php?diff=40835&oldid=40834 * Bataais * (+1)
16:49:30 <HackEgo> [wiki] [[TinyBF]] http://esolangs.org/w/index.php?diff=40836&oldid=40835 * Bataais * (+4)
16:52:23 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=40837&oldid=40809 * Bataais * (+13)
16:53:16 -!- hjulle has quit (Ping timeout: 244 seconds).
16:54:12 <HackEgo> [wiki] [[RISBF]] http://esolangs.org/w/index.php?diff=40838&oldid=37842 * Bataais * (+31)
16:57:37 -!- oerjan has quit (Quit: leaving).
16:59:52 <HackEgo> [wiki] [[User:Bataais]] N http://esolangs.org/w/index.php?oldid=40839 * Bataais * (+44) Created page with "Identical to Michael Gianfreda, Switzerland."
17:01:35 <HackEgo> [wiki] [[User:Bataais]] http://esolangs.org/w/index.php?diff=40840&oldid=40839 * Bataais * (-13)
17:01:50 <HackEgo> [wiki] [[User:Bataais]] http://esolangs.org/w/index.php?diff=40841&oldid=40840 * Bataais * (+6)
17:23:09 -!- FreeFull has joined.
17:36:23 -!- MoALTz__ has joined.
17:39:59 -!- MoALTz_ has quit (Ping timeout: 272 seconds).
17:40:30 -!- Vorpal has quit (Ping timeout: 244 seconds).
17:45:57 -!- hjulle has joined.
17:57:06 -!- quintopia has joined.
17:58:57 -!- impomatic_ has quit (Ping timeout: 255 seconds).
18:03:32 -!- AndoDaan_ has joined.
18:04:55 -!- AndoDaan has quit (Ping timeout: 265 seconds).
18:07:03 -!- MDream has changed nick to MDude.
18:17:14 <int-e> @tell oerjan the nonincreasing indentation trick from henkma's solution is so awful I almost want to poke out my eyes to unsee it. :-P
18:18:21 <int-e> @tell oerjan Oh the fact that I could've gotten to 123 using that trick doesn't help.
18:23:21 <HackEgo> [wiki] [[SELECT.]] http://esolangs.org/w/index.php?diff=40842&oldid=40805 * Por gammer * (-133) /* Commands */
18:33:34 -!- Vorpal has joined.
18:56:32 -!- shikhin has joined.
19:03:52 <HackEgo> [wiki] [[Brainfuck]] M http://esolangs.org/w/index.php?diff=40843&oldid=40817 * Bataais * (+86)
19:07:40 <HackEgo> [wiki] [[User talk:Bataais]] N http://esolangs.org/w/index.php?oldid=40844 * Bataais * (+84) Created page with "Here you can talk about my [[brainfuck]] minimizations [[tinyBF]], [[RISBF]] and me."
19:08:16 <HackEgo> [wiki] [[User talk:Bataais]] http://esolangs.org/w/index.php?diff=40845&oldid=40844 * Bataais * (+23)
19:08:43 <HackEgo> [wiki] [[User talk:Bataais]] http://esolangs.org/w/index.php?diff=40846&oldid=40845 * Bataais * (-1)
19:14:57 <HackEgo> [wiki] [[3switchBF]] http://esolangs.org/w/index.php?diff=40847&oldid=36939 * Bataais * (+6)
19:15:39 <HackEgo> [wiki] [[User talk:Bataais]] http://esolangs.org/w/index.php?diff=40848&oldid=40846 * Bataais * (+22)
20:01:36 <quintopia> ooooh, a page to talk about Bataais
20:01:47 <quintopia> what shoudl we ask a random person from the internet?
20:02:06 <fungot> fizzie: ah, so i'm guessing it takes a wee while for the airshow. flown by remote control test toy ever. i'll give it to new developers. duke's not done yet.
20:04:54 <quintopia> how about "what do you think is the most interesting thing about you
20:05:12 -!- Patashu has joined.
20:07:27 <lambdabot> *** "animadvert" wn "WordNet (r) 3.0 (2006)"
20:07:27 <lambdabot> v 1: express one's opinion openly and without fear or
20:07:27 <lambdabot> hesitation; "John spoke up at the meeting" [syn: {opine},
20:07:27 <lambdabot> {speak up}, {speak out}, {animadvert}, {sound off}]
20:07:29 <lambdabot> 2: express blame or censure or make a harshly critical remark
20:08:11 <lambdabot> *** "aver" wn "WordNet (r) 3.0 (2006)"
20:08:11 <lambdabot> v 1: report or maintain; "He alleged that he was the victim of a
20:08:11 <lambdabot> crime"; "He said it was too late to intervene in the war";
20:08:11 <lambdabot> "The registrar says that I owe the school money" [syn:
20:08:56 <fizzie> Well, it is the WordNet.
20:17:59 -!- tswett has joined.
20:18:19 <tswett> Define a "concrete statement" as a mathematical statement in which all quantifiers range over the integers.
20:18:28 <tswett> I'm not really going anywhere here. I just felt like stating that definition.
20:25:19 -!- Patashu has quit (Ping timeout: 244 seconds).
20:28:58 -!- shikhout has joined.
20:32:20 -!- shikhin has quit (Ping timeout: 265 seconds).
20:37:52 <b_jonas> right... if I declare a variable const, I shouldn't be surprised the compiler won't allow me to assign to it.
20:43:57 <b_jonas> ok, now why does this crash my program? did I give the array size wrong?
20:44:20 <fizzie> You looked at it wrong.
20:45:14 <b_jonas> wait, it's the other array
20:52:38 <HackEgo> olist (967): shachaf oerjan Sgeo FireFly boily nortti
20:59:29 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube*
20:59:52 <fungot> int-e: or another one: ht tp jeanclaudeboetsch. free. fr/ change. it's interesting but this song
21:01:24 <fungot> olsner: lol this is a copycat that should have given the content. it was at an airshow, it's your right a underwater mission that looks amazing :0 special forces, no way similar to xmen's wolverine that cpt price has made famous
21:04:51 -!- centrinia has joined.
21:04:54 <fungot> Selected style: fisher (Fisher corpus of transcribed telephone conversations)
21:05:08 <fizzie> Come to think of it, I haven't added to the list in a long time. I think there were some ideas, too.
21:05:16 <fizzie> fungot: CAN YOU HEAR ME?
21:05:16 <fungot> fizzie: ( ( know laughter)) affirmative action i usually think of mn what about like the o. j. is a very
21:05:54 -!- Bicyclidine has joined.
21:13:21 <FireFly> fungot: don't hang up on me
21:13:21 <fungot> FireFly: yeah sigh yeah noise)) those movies turn me off to i'm not into the bloody gory
21:13:46 <FireFly> fungot: I don't enjoy gore too much either
21:13:47 <fungot> FireFly: right we still understand it so the trick is getting a little loose right now laughter
21:16:46 -!- centrinia has quit (Ping timeout: 244 seconds).
21:26:24 -!- Bicyclid1ne has joined.
21:26:50 -!- Bicyclidine has quit (Quit: Reconnecting).
21:30:20 -!- AnotherTest has joined.
21:36:00 -!- nycs has joined.
21:37:39 -!- `^_^v has quit (Ping timeout: 244 seconds).
21:52:57 -!- AndoDaan_ has left ("Something's Burning").
22:04:06 -!- nyuszika7h has quit (Read error: Connection reset by peer).
22:05:59 -!- Bicyclid1ne has quit (Ping timeout: 272 seconds).
22:06:13 -!- nyuszika7h has joined.
22:12:59 -!- nyuszika7h has quit (Ping timeout: 256 seconds).
22:13:28 -!- nyuszika7h_ has joined.
22:21:44 -!- nys has joined.
22:25:58 <zzo38> I think that, if you are using SQLite as a database format in a program, then you can also use SQLite as the extension language; it already knows about the database, so you don't have to add a whole bunch of stuff for the new extension language to interact with the database and so on.
22:26:06 <zzo38> What do you think of it?
22:27:53 <zzo38> It is probably a simple way to do it; anyways SQLite already supports extension loading too.
22:32:55 -!- AnotherTest has quit (Ping timeout: 245 seconds).
22:38:39 -!- MoALTz_ has joined.
22:40:16 <olsner> I guess it's fine if you want to write application extensions in sql
22:40:26 -!- oerjan has joined.
22:41:13 <lambdabot> int-e said 4h 23m 58s ago: the nonincreasing indentation trick from henkma's solution is so awful I almost want to poke out my eyes to unsee it. :-P
22:41:13 <lambdabot> int-e said 4h 22m 51s ago: Oh the fact that I could've gotten to 123 using that trick doesn't help.
22:41:15 -!- MoALTz__ has quit (Ping timeout: 245 seconds).
22:41:41 <zzo38> Yes, and if the extension is not written in SQL but is actually written in C, then you can still use it by writing a wrapper in SQL in a simple way: SELECT LOAD_EXTENSION('abcdefg'); if the extension is compiled as abcdefg.dll or abcdefg.so
22:42:59 <oerjan> int-e: did you know that your comment that you'd wished !! took Integer arguments sent me on a wild goose chase (which i told elliott about) because i assumed wrongly from that that your prime testing code was _worse_ than the obvious way that could have been used, which would have implied your string construction was _better_ than mine
22:43:35 <olsner> I did vaguely consider building an OS/kernel based on sqlite at some point though, using an in-memory database for all kernel data
22:43:42 <int-e> oerjan: No I didn't know that.
22:44:30 <olsner> presumably with some basic C/asm functions exposed to SQL to make it actually do something
22:44:50 <int-e> oerjan: the reason that it would've helped me is that show=<<[<something that produces a string>|...] is quite a bit longer than [<something that produces a char>|...]
22:45:36 <zzo38> olsner: That is an interesting kind of idea, although SQLite already requires an operating system in order to work (unless you can rewrite the operating-specific functions not to require it, fo course)
22:45:40 <int-e> oerjan: I wanted to use "010"!!mod(product[2..n-2])(0^n+n)
22:46:22 <oerjan> yes, that's what i assumed
22:46:57 <olsner> I think sqlite can be ported to something quite bare-bones, iirc most of the porting interface is file system-related (and you don't need that for an in-memory database)
22:46:59 <int-e> oerjan: otoh the statistics made me believe that you used few library functions for substring generations, when actually you used one more than I'd ever tried at once.
22:47:33 <olsner> but naturally this idea is not really thought through and there should be many reasons it can't work
22:48:03 <oerjan> int-e: i see why i didn't see how that would improve things, because in my version changing to producing Char just meant changing a >>= to a slightly differently positioned map, so no improvement
22:48:04 <zzo38> olsner: Yes, some of the operating-system-specific functions are still needed for a database; but, maybe a really simple operating system can be made that is just enough to work it.
22:48:39 <oerjan> i had some versions that did that
22:49:25 <int-e> oerjan: I learned how different that could be from the second version here: http://sprunge.us/UPZS
22:50:33 <int-e> wait, no, from the third. the second one is the one that would've profited from henkma's indentation trick
22:50:38 -!- boily has joined.
22:58:08 <oerjan> int-e: i see you also went through the [2..n-2] route :P
22:58:54 <oerjan> i did that before i realized 4 was an exception, and didn't bother to change it back
22:59:09 <oerjan> well no real reason to change it back, anyway
23:01:37 <int-e> oh poor lambdabot...
23:01:47 -!- lambdabot has quit (Remote host closed the connection).
23:01:52 -!- MoALTz_ has quit (Ping timeout: 244 seconds).
23:03:00 <int-e> Debian GNU/Linux jessie/sid \n \l
23:03:19 <int-e> OS update somehow ended up with /dev/pts not being mounted ...
23:04:51 <int-e> So I had to reboot. That worked fine though, fortunately.
23:05:41 <oerjan> oh wait it's not back yet
23:05:46 <int-e> Should be fine, this time, too.
23:05:53 <int-e> (@messages, that is)
23:06:25 <oerjan> have you made it save periodically now
23:06:42 -!- lambdabot has joined.
23:06:51 <int-e> no. still a todo. but I know how to do it on demand.
23:07:30 -!- nycs has quit (Quit: This computer has gone to sleep).
23:09:06 <int-e> oerjan: I left the [2..n-2] because it's faster than [1..n-1], at least theoretically ;)
23:16:49 -!- vanila has quit (Quit: Leaving).
23:26:32 <oerjan> now for a golf test i don't expect to work
23:26:49 <oerjan> but it would be hilarious if it did
23:27:00 -!- DTSCode has quit (Read error: Connection reset by peer).
23:27:55 -!- DTSCode has joined.
23:27:58 -!- DTSCode has quit (Remote host closed the connection).
23:27:59 <oerjan> hm that was closer than i expected
23:28:19 -!- DTSCode has joined.
23:28:40 <oerjan> hm _very_ close in fact. maybe i should try again.
23:29:24 <oerjan> what _is_ the timeout, anyway?
23:29:44 <int-e> 1 second per testcase?
23:30:05 <oerjan> i thought i'd seen a case that had > 3 s
23:30:05 <int-e> note: I don't know.
23:30:16 <oerjan> i mean, a golf solution
23:30:20 <int-e> (and there are some languages that get more time)
23:30:56 <int-e> one entry from the start page: "allow more time for R (you have 2 sec for 3 test cases problems, 2.5 secs for 2 test cases, and 4 secs for 1 test case) since its invocation seems to take more than one second."
23:33:26 <oerjan> hm good to know. i had been assuming the 10 s from the general testing page
23:34:04 <oerjan> hm this means timeout will be even more of a problem than i feared for the golf problem i'm trying to design.
23:34:31 <oerjan> and i was considering scaling it _up_ to make it harder to compress the output.
23:34:52 <oerjan> anyway, this wasn't that. i shall have to submit the slightly longer version, then.
23:36:54 <oerjan> still beats importing Data.List, anyhow.
23:37:07 <int-e> ah so my secret 136 characters solution isn't too bad :)
23:37:41 <oerjan> well my solution _was_ 3 chars shorter with timeout :P
23:37:54 <oerjan> (can you guess what the change was)
23:37:55 <int-e> same here, I think.
23:38:25 <oerjan> hm so you are saying this should be 4 chars shorter, hm
23:39:10 <int-e> I'll wait for henkma's 120 character solution.
23:39:24 <oerjan> it only timed out on the third test case :(
23:39:33 <oerjan> which means at least i got timings for the others
23:46:49 -!- hjulle has quit (Ping timeout: 244 seconds).
23:48:23 <int-e> wow it's actually compiling with -O ...
23:48:31 <int-e> > fromEnum (maxBound :: Char)
23:50:59 <int-e> and yes, as far as I can see, "import Data.List" is not worthwhile, but "import List" would be short enough.
23:52:35 <int-e> whatever. I submitted.
23:55:47 <int-e> oh I'm also playing with Euclidean norm, but 122 characters is still worse than henkma's solution.
23:56:08 <int-e> it would be so *nice* if printf".5g" did the right thing.
23:56:53 <oerjan> maybe he's found some obscure printing function in a GHC.* module somewhere :P
23:57:06 -!- where has joined.
23:57:15 <where> WHERE IS PHILOSOPHY SCRIPT?!@
23:57:21 <HackEgo> where: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
23:57:36 <where> http://esolangs.org/wiki/Philosophy_Script
23:57:54 <where> SEND ME YOUR APOSTLES
23:58:29 <int-e> oerjan: right, there are 27 libraries installed (24 not hidden), there most be something in there!!!1
23:59:23 <int-e> fungot: I think we found your soulmate
23:59:24 <fungot> int-e: oh laughter oh my god because i mean that's
00:00:05 <oerjan> where: i have doubts that there ever was an implementation.
00:01:15 <oerjan> digerati's other languages GodScript and Genome aren't implemented either.
00:04:05 <oerjan> int-e: i think fungot has doubts
00:04:06 <fungot> oerjan: ( ( mm)) the one that's next month in rawley but they just gave me a
00:04:18 <oerjan> thought i was going to ping out there
00:05:07 -!- where has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
00:05:11 <oerjan> hm do none of the bots respond to /ping
00:12:50 <tswett> You know, it's never quite made sense to me that you can discover the Euclidean distance formula from simple axioms or whatever.
00:13:39 <tswett> Like, we can define distance however we want. Manhattan distance, that other kind of distance, D&D distance, whatever. What makes Euclidean distance so special?
00:15:39 -!- AndoDaan has joined.
00:16:49 <Jafet> It has... economic significance
00:17:47 -!- Bicyclidine has joined.
00:18:13 <tswett> Ooh, I just remembered that one lovely proof of the Pythagorean theorem.
00:18:45 <int-e> you make it sound like there is only one lovely one...
00:19:17 <FireFly> What would D&D distance be?
00:19:18 <tswett> The determiner "that one" doesn't imply uniqueness.
00:19:45 <int-e> tswett: It could be read that way, though.
00:20:03 <Bicyclidine> it could also be read as a scarring indictment of nazi economic policy
00:20:46 <int-e> tswett: To be fair, all "sound" in that text message is obviously my own.
00:21:14 <tswett> FireFly: it's defined for lattice points. The distance between (0, 0) and (a, b), where 0 ≤ a ≤ b, is floor((3/2) * a + (b - a)).
00:21:35 <tswett> Which I guess is the same as floor(a / 2 + b).
00:21:42 <tswett> Anyway, that one proof.
00:22:03 <tswett> Suppose you have some triangle ABC. Let T(x) be the area of a triangle similar to ABC whose hypotenuse has length x.
00:22:04 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:22:30 <tswett> T(c) is just the area of triangle ABC.
00:23:42 <tswett> T(a) is the area of triangle ADC, where D is the projection of C onto line AB.
00:23:54 <tswett> T(b) is the area of triangle DBC.
00:24:26 <tswett> Since triangle ABC is the disjoint union of triangles ADC and DBC, T(a) + T(b) = T(c).
00:24:42 <tswett> Finally, T(x) is proportional to x^2.
00:25:35 <tswett> "You know how the Pythagorean theorem is usually illustrated using three squares? Instead, illustrate it using triangles similar to the original triangle. It starts to look kind of obvious."
00:31:34 -!- conehead has quit (Excess Flood).
00:32:33 -!- conehead has joined.
00:32:53 -!- idris-bot has quit (Quit: Terminated).
00:35:33 -!- idris-bot has joined.
00:37:06 <FreeFull> tswett: I saw it demonstrated using a weird blobby shape
00:41:07 <zzo38> There are many different proof of Pythagorean theorem.
00:44:59 <boily> the plural of proof is preef.
00:46:10 <zzo38> I have seen many different ones, including the one I made up while resting on the couch.
00:46:12 <AndoDaan> no, it's profess. As in professor.
00:55:19 <lifthrasiir> you've found a triangle with a slightly displaced apex
00:55:40 <Sgeo> http://img4.wikia.nocookie.net/__cb20130701021023/disney/images/5/52/Opening_bill_transparent.png
00:59:28 <oerjan> lifthrasiir: maybe it's that pyramid from discworld
01:00:09 <lifthrasiir> I guess so, just wanted to suggest the (in)flexibility of ASCII approximation
01:06:58 -!- Bicyclidine has quit (Ping timeout: 250 seconds).
01:10:29 -!- lambdabot has quit (Remote host closed the connection).
01:11:22 <Sgeo> Apparently, until 5 days ago, a website I often go on was using PHP4
01:11:46 <Sgeo> Make that a week ago, actually
01:12:11 -!- centrinia has joined.
01:13:34 <zzo38> I would like SQLite extension to do such things as manipulating MIDI files, manipulating a file system, and for accessing weather data on the internet, astronomical data, news report, and others
01:15:58 <shachaf> A pony is seen as something desirable but difficult to acquire.
01:16:22 <shachaf> pikhq is suggesting that, as long as you already want all those other things, you might as well add a pony to the list.
01:16:29 <zzo38> Well, I don't need a pony, but maybe you do.
01:16:42 <Sgeo> Doesn't Yahoo have something for ... Internet stuff?
01:17:02 <Sgeo> "The YQL (Yahoo! Query Language) platform enables you to query, filter, and combine data across the web through a single interface. It exposes a SQL-like syntax that is both familiar to developers and expressive enough for getting the right data."
01:17:15 <boily> ponies are tasty. their meat is very lean and goes well in hamburgers.
01:17:43 <Sgeo> I guess that's not an SQLite extension though
01:17:46 <zzo38> I wanted to access it through SQLite command line interface though rather than a web browser, and to be able to use it with SQLite database files
01:18:14 <Sgeo> Wonder if you could make a custom source of data that when manipulated via YQL, does stuff to some SQLite db file
01:18:31 <pikhq> boily: I'll take your word for it for now -- I'm pretty sure there's no good source here.
01:22:17 -!- AndoDaan has quit (Ping timeout: 255 seconds).
01:24:52 -!- erdic has quit (Ping timeout: 346 seconds).
01:28:43 -!- foobarbaz has joined.
01:30:09 -!- erdic has joined.
01:30:14 -!- erdic has quit (Changing host).
01:30:14 -!- erdic has joined.
01:30:43 -!- foobarbaz has quit (Client Quit).
01:38:42 -!- erdic has quit (Ping timeout: 256 seconds).
01:41:06 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
01:45:21 -!- erdic has joined.
01:45:27 -!- AndoDaan has joined.
01:48:28 -!- boily has quit (Quit: EPIGENETIC CHICKEN).
01:51:31 -!- erdic has quit (Read error: Connection reset by peer).
01:56:32 -!- scounder has quit (Ping timeout: 260 seconds).
01:57:19 -!- quintopia has quit (Ping timeout: 257 seconds).
01:59:18 <HackEgo> [wiki] [[User:Oj742]] N http://esolangs.org/w/index.php?oldid=40849 * Oj742 * (+73)
02:01:36 <shachaf> int-e: I wanted to @tell but lambdabot is gone. :-(
02:03:24 -!- erdic has joined.
02:05:15 <int-e> provider says "Troubleshooting some network issues."
02:08:17 -!- quintopia has joined.
02:10:49 -!- quintopia has quit (Ping timeout: 264 seconds).
02:10:49 -!- CADD_ has quit (Ping timeout: 264 seconds).
02:11:07 -!- CADD has joined.
02:11:08 -!- quintopia has joined.
02:13:05 -!- AndoDaan_ has joined.
02:13:05 <shachaf> int-e: I @told someone something and then lambdabot quit with Excess Flood.
02:13:11 <shachaf> How likely is it that it actually went through?
02:15:35 -!- AndoDaan has quit (Ping timeout: 272 seconds).
02:15:40 -!- AndoDaan_ has changed nick to AndoDaan.
02:16:50 -!- lambdabot has joined.
02:19:06 -!- scounder has joined.
02:29:38 -!- shikhin has joined.
02:32:52 -!- shikhout has quit (Ping timeout: 255 seconds).
03:22:35 -!- Bike has quit (Quit: restart).
03:28:24 -!- Bike has joined.
03:34:41 -!- shikhin has quit (Ping timeout: 272 seconds).
03:55:16 <HackEgo> [wiki] [[MNNBFSL]] N http://esolangs.org/w/index.php?oldid=40850 * AndoDaan * (+2032) Basic page creation.
03:59:14 -!- oerjan has quit (Quit: leaving).
04:01:00 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=40851&oldid=40837 * AndoDaan * (+14) Added MNNBFSL
04:04:04 -!- tswett has quit (Ping timeout: 246 seconds).
04:26:30 -!- MDude has changed nick to MDream.
04:29:20 -!- lambdabot has quit (Ping timeout: 265 seconds).
04:34:39 -!- nys has quit (Quit: quit).
04:34:54 -!- lambdabot has joined.
05:32:16 -!- FreeFull has quit (Ping timeout: 250 seconds).
05:34:18 -!- FreeFull has joined.
05:39:39 -!- drdanmaku has joined.
05:55:17 -!- idris-bot has quit (Ping timeout: 272 seconds).
05:55:53 -!- Melvar has quit (Ping timeout: 264 seconds).
06:14:30 -!- MoALTz has joined.
06:43:50 -!- ashi has joined.
06:45:10 -!- ashi has left ("Using Circe, the loveliest of all IRC clients").
07:19:30 -!- conehead has quit (Excess Flood).
07:26:51 -!- Patashu has joined.
07:29:11 -!- AndoDaan has quit (Ping timeout: 245 seconds).
07:29:12 -!- AndoDaan_ has joined.
07:40:18 -!- nyuszika7h_ has changed nick to nyuszika7h.
07:48:22 -!- jameseb- has joined.
07:49:40 -!- jameseb has quit (*.net *.split).
08:30:39 -!- drdanmaku has quit.
09:01:01 <zzo38> How much do you like of these kind of thing? http://principiadiscordia.com/memebombs/?action=list&o=random&m=100
09:03:32 -!- AndoDaan_ has quit (Ping timeout: 256 seconds).
09:10:38 -!- FreeFull has quit (Ping timeout: 265 seconds).
09:15:37 -!- AndoDaan has joined.
09:37:21 -!- shikhin has joined.
09:39:38 -!- centrinia has quit (Ping timeout: 265 seconds).
09:57:17 -!- augur has quit (Remote host closed the connection).
10:01:09 -!- augur has joined.
10:02:02 -!- FreeFull has joined.
10:02:38 -!- ais523 has joined.
10:06:40 -!- jameseb- has changed nick to jameseb.
10:09:09 -!- centrinia has joined.
10:17:20 -!- mosasaur has joined.
10:17:44 <HackEgo> mosasaur: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
10:19:03 <mosasaur> thanks, but I was actually looking for stuff about Ouspensky and Gurdjieff ...
10:19:44 <viznut_> #esoteric at irc.dal.net is empty
10:34:41 -!- mosasaur has left.
10:42:41 -!- ais523 has quit (Read error: Connection reset by peer).
10:42:47 -!- ais523 has joined.
10:43:38 <zzo38> Let's see if Wikipedia has it
10:44:21 <zzo38> Yes, of course they do.
10:54:25 -!- viznut_ has changed nick to viznut.
10:55:41 -!- Melvar has joined.
10:59:51 -!- callforjudgement has joined.
11:00:01 -!- callforjudgement has changed nick to ais523\unfoog.
11:01:41 -!- ais523 has quit (Ping timeout: 245 seconds).
11:17:57 -!- oerjan has joined.
11:18:08 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40852&oldid=40833 * TomPN * (+0) /* Array and pointer */
11:22:44 -!- boily has joined.
11:29:08 <oerjan> according to swedish wikipedia, the composers refused a request by bbc to have that translated into english
11:29:52 -!- ais523 has joined.
11:32:31 -!- ais523\unfoog has quit (Ping timeout: 245 seconds).
11:37:38 <lambdabot> shachaf said 9h 30m 21s ago: http://chu.stanford.edu/ might be a better introduction to Chu spaces than Wikipedia.
11:37:39 <lambdabot> shachaf said 9h 18m 37s ago: http://chu.stanford.edu/ might be a better introduction to Chu spaces than Wikipedia.
11:38:10 <boily> schellochellof. I was confused by the wikipédiarticle. this may help me more.
11:38:44 <boily> oerjan: I think it's better if the hemicketskt remains incomprehensible.
11:40:44 <shachaf> boily: I guess lambdabot did get the message the first time.
11:42:01 <oerjan> clearly lambdabot needs a drastically reduced pH
11:42:55 -!- ais523 has changed nick to ais523\unfoog.
11:43:44 <shachaf> boily: I don't know what hilight I need to match the things you do to my nick.
11:44:02 <shachaf> The real question is where that first c came from.
11:44:19 <shachaf> People keep thinking "schachaf" for whatever reason.
11:44:32 <boily> muscle memory? German invasion?
11:46:40 -!- centrinia has quit (Ping timeout: 250 seconds).
11:48:26 <oerjan> argh noisy construction machine
11:52:32 -!- ais523 has joined.
11:52:56 -!- ais523\unfoog has quit (Ping timeout: 245 seconds).
11:56:21 -!- idris-bot has joined.
12:00:09 <boily> oerjan: what is being constructed?
12:01:02 <HackEgo> [wiki] [[User talk:Bataais]] M http://esolangs.org/w/index.php?diff=40853&oldid=40848 * Bataais * (-28) Undo revision 40848 by [[Special:Contributions/Bataais|Bataais]] ([[User talk:Bataais|talk]])
12:02:40 <oerjan> i believe the pavement just outside my apartment, after they digged it up _again_ to search for a leak down to the parking cellar complex which they've been spending a year to try to plug
12:04:43 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40854&oldid=40852 * TomPN * (+11) /* Loops */
12:05:52 <oerjan> and there they put it on again
12:06:48 <shachaf> An "ordinary" ball is called a 3-ball, but its boundary is called a 2-sphere? Why?
12:07:03 <oerjan> it's some kind of sand compactor, so i hope that means they'll soon be laying down the asphalt and actually declare it finished
12:07:19 <HackEgo> [wiki] [[Quantum Dimensions]] N http://esolangs.org/w/index.php?oldid=40855 * TomPN * (+5758) Created page with "'''Quantum Dimensions''' is an adaptation of [[Dimensions]], where the program operates on qubits instead of numbers. Quantum Dimensions was invented in 2014 by Tom Price-Nich..."
12:07:22 <oerjan> shachaf: because that's the dimension of the sets in question
12:07:51 <shachaf> I guess that should be obvious in retrospect.
12:08:09 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40856&oldid=40854 * TomPN * (+77) /* See also */
12:08:22 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40857&oldid=40856 * TomPN * (+1) /* See also */
12:08:34 <oerjan> shachaf: you can imagine there's some more convoluted reason and this is just after-the-fact rationalization if that helps
12:08:40 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40858&oldid=40855 * TomPN * (+1) /* See also */
12:08:43 <shachaf> Especially with the wiki activity going on.
12:09:17 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40859&oldid=40828 * TomPN * (+78) /* See also */
12:09:29 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40860&oldid=40859 * TomPN * (+0) /* See also */
12:09:37 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=40861&oldid=40860 * TomPN * (+0) /* See also */
12:09:54 -!- ais523 has quit (Read error: Connection reset by peer).
12:10:06 -!- ais523 has joined.
12:10:15 -!- ais523 has quit (Changing host).
12:10:15 -!- ais523 has joined.
12:10:28 <HackEgo> [wiki] [[User talk:TomPN]] http://esolangs.org/w/index.php?diff=40862&oldid=40829 * TomPN * (+34) /* Dimensions */
12:10:39 <HackEgo> [wiki] [[User talk:TomPN]] http://esolangs.org/w/index.php?diff=40863&oldid=40862 * TomPN * (+1) /* Other esolangs */
12:10:40 <shachaf> "has dimension n" just means that each point has a neighborhood homeomorphic to R^n?
12:11:57 <oerjan> shachaf: there are several definitions of dimension, many of which tend to agree for manifolds
12:12:29 <shachaf> What if you don't have a manifold?
12:15:36 <oerjan> i am somewhat partial to https://en.wikipedia.org/wiki/Dimension#Lebesgue_covering_dimension since i've actually published articles where that was relevant
12:16:23 <oerjan> the inductive dimensions in the next section may be easier intuitively, though.
12:16:59 <shachaf> Oh, I remember reading an intuition about that in http://xorshammer.com/2011/07/09/a-logical-interpretation-of-some-bits-of-topology/
12:17:17 <oerjan> and hausdorff dimension (which requires a metric) is also cool because fractals
12:19:10 -!- boily has quit (Quit: MASKED CHICKEN).
12:20:02 -!- ais523 has quit (Read error: Connection reset by peer).
12:20:08 -!- callforjudgement has joined.
12:20:15 -!- callforjudgement has quit (Changing host).
12:20:15 -!- callforjudgement has joined.
12:22:06 <oerjan> lebesgue covering dimension 1 is cool because the refined covering essentially splits into a bipartite graph of open and closed sets
12:23:01 <oerjan> which allows an easy proof that the measures we were studying were trivial (which here means they were lebesgue measures) on those spaces
12:24:09 -!- sebbu has joined.
12:24:31 -!- sebbu2 has quit (Ping timeout: 265 seconds).
12:24:38 -!- sebbu has quit (Changing host).
12:24:38 -!- sebbu has joined.
12:25:05 -!- Patashu has quit (Ping timeout: 240 seconds).
12:37:53 <shachaf> oerjan: I should learn all these things properly. :-(
12:40:04 <oerjan> don't ask me i never did it properly hth
12:40:30 <shachaf> does that mean you learned all of it rather than a proper subset of it
12:40:34 <J_Arcane> blargh. I forgot how my own variable declarations are supposed to work.
12:40:55 <oerjan> no, it mean i never had a proper course and picked up pieces in a haphazard way.
12:42:00 <shachaf> what's a good haphazard way twh
12:43:21 <J_Arcane> currently working on this https://github.com/jarcane/heresy, but I've forgotten which definition of LET I decided to run with.
12:44:38 <oerjan> shachaf: find a math library and spend time in it
12:58:24 -!- scarf has joined.
12:58:29 -!- scarf has changed nick to ais523\unfoog.
12:58:55 -!- callforjudgement has quit (Read error: Connection reset by peer).
13:00:18 <AndoDaan> Are there any dangers to consider if one were to host an irc bot from his or her own computer?
13:01:05 <elliott> AndoDaan: the same dangers as exposing any service to the internet
13:01:44 <elliott> if your code deals with any kind of external resource like the filesystem or other network services and exposes functionality based on that, you should be running it in some kind of sandbox at the very least
13:01:54 -!- ais523 has joined.
13:01:56 <elliott> if it's just, like, brainfuck code hooked up to netcat you should be fine
13:02:14 -!- ais523\unfoog has quit (Disconnected by services).
13:02:17 -!- ais523 has changed nick to ais523\unfoog.
13:02:28 <J_Arcane> The frequency of bogus connects try-racket.org blocks is measured in *seconds*. Such is ye olde internets.
13:02:40 <AndoDaan> It'd be more like that, just basic language interpretation.
13:03:42 <elliott> AndoDaan: if the language doesn't have any more IO than brainfuck then you should be fine. of course you can't rule out compromise of the IRC account (like, if someone can make you send \r\nPRIVMSG Nickserv :set password owned)
13:03:43 <AndoDaan> And I suppose some language are safer to implement a bot on than others.
13:03:51 <elliott> (so you should be sanitising even that IO)
13:03:52 <oerjan> elliott: well if it's a bf implementation that doesn't check array boundary, you're _theoretically_ in trouble right?
13:05:14 <AndoDaan> Hmm. Array boundries. So like, where I store the the value on the bf data tape could be compromised?
13:05:31 <elliott> oerjan: I was assuming a memory-safe language
13:05:42 <oerjan> AndoDaan: i mean if they can move the tape pointer out of bounds
13:05:49 <elliott> if you're considering exposing code written in a memory-unsafe language to the network, consider: don't
13:06:10 <elliott> I'm serious. humans aren't good enough to do that kind of thing.
13:06:12 <AndoDaan> I notice that's possible with the anarchy golf version of BF.
13:06:15 <elliott> at least not if you can't afford a professional audit.
13:06:25 <elliott> AndoDaan: I think that's a weird intentional feature rather than an exploit, where you can read your own code
13:06:54 <elliott> AndoDaan: what language are you using to write the bot/interpreter?
13:07:03 <AndoDaan> Hmm, didn't consider that. Seems to such the fun out of BF golf though.
13:07:26 <AndoDaan> Lua... I hate it, but I'm not proficiant in anything else yet.
13:07:45 <elliott> no need to worry about array bounds, then
13:07:56 <AndoDaan> Really, I should knuckle down and finish learning python.
13:08:02 <oerjan> AndoDaan: haskell beckons you ...
13:08:07 <J_Arcane> AndoDaan: If you know Lua, Python's trivial to pick up. Try the Codecademy course.
13:09:13 <elliott> if you know lua python will be so boring :p
13:09:59 <AndoDaan> It is. I mean, I force myself to start with the basic, but my mind soons wanders after a while.
13:10:26 <AndoDaan> I think i'm 25 percent done with the khan code academy lessons of python.
13:10:51 <elliott> honestly, if you don't feel like you're getting anything out of it I'd suggest learning a language less similar to lua than python
13:11:20 <elliott> ok, maybe not that dissimilar
13:12:53 <elliott> I feel like I could probably fit good C++ knowledge and experience in my head if I tried now, after ten years of programming in a great many languages. that definitely wasn't the case, like, six years ago :p
13:13:01 <elliott> it's a very complex behemoth of a language
13:14:16 <elliott> (I've never actually sat down to probably learn it, though. I know about the design issues at play and have a good sense for why the language is like how it is, but honestly I'm more experienced in C++ template metaprogramming than C++ itself...)
13:16:06 <AndoDaan> I saw a C++ template when I was looking at the deadfish implementations. What is a c++ template?'
13:17:11 <ais523\unfoog> a C++ template's basically a function or class (or possibly other things?) where you can substitute out some of the identifiers, normally for types or integers
13:17:23 <elliott> Um, I'm not sure how to justify them if you're only experienced with dynamically-typed languages
13:17:29 <ais523\unfoog> e.g. one of the simplest examples is "template <typename T> T id(T& x) {return x;}"
13:17:37 <elliott> but they're basically compile-time metaprogramming, used for type-generic (and otherwise) programming in C++
13:17:50 <ais523\unfoog> then, for instance, id<char> would be "char id (char& x) {return x;}"
13:17:51 <elliott> (such as implementing a generic vector type that you can instantiate to be a vector of ints, or of strings, or such)
13:17:57 <elliott> but they're... rather hideously powerful in C++
13:18:01 <elliott> to the point where you can implement deadfish in them
13:18:29 <ais523\unfoog> elliott: I've heard that when templates were being designed, someone noticed early on that they were TC and mentioned it to Stroustrup
13:18:41 <ais523\unfoog> and he told them he was happy for them to stay that way
13:18:52 <ais523\unfoog> I think they were expecting him to change it to be sub-TC
13:18:59 <elliott> ais523\unfoog: I thought everyone was surprised it turns out they accidentally implemented the world's most bizarre functional programming language
13:19:21 <ais523\unfoog> elliott: yes but they found out very early on, when it wasn't too late to change
13:19:48 <elliott> just nerfing templates doesn't seem that compelling
13:19:56 <elliott> as opposed to entirely replacing them with something less horrible
13:20:16 <ais523\unfoog> they work pretty well in simple cases, except that I sometimes have trouble working out where you're meant to put the template argument
13:20:23 <Jafet> You'd just end up with java
13:20:51 <ais523\unfoog> also, has anyone done `olist yet? just noticed there are only 5 pages of discussion
13:21:11 <elliott> Jafet: I don't think java is reasonable C++, no
13:21:33 <elliott> I don't think it satisfies very many of C++'s goals
13:21:58 <Jafet> That is, generics are nerf foam templates
13:23:10 <elliott> right, generics are boxing hell though, like the rest of java
13:23:59 <ais523\unfoog> one thing that amuses me is how many languages leave out generics because they think they're complicated and they don't need them
13:24:13 <Jafet> Before java 8 it was even sillier. The type system was not actually strong enough to express generic programming without type casts
13:24:34 <FireFly> Hm, they changed that in Java 8?
13:24:44 <elliott> it still doesn't understand {co,contra}variance, right?
13:25:27 <elliott> ais523\unfoog: List<T> is still broken right, though?
13:25:43 <Jafet> It does now, but most java programmers don't and never will
13:25:52 <elliott> ais523\unfoog: is it still possible to use List<Dog> as List<Animal> and then push a Cat to it
13:26:02 <elliott> I really can't imagine java would break compatibility with that brokenness
13:26:26 <ais523\unfoog> elliott: oh, I think there might be variance annotations on the accessors, but they should still prevent that
13:26:38 <ais523\unfoog> bleh, the JDK isn't even in my browser autocomplete any more?
13:26:48 <elliott> it was definitely possible in the past, since this is an infamous fundamental java brokenness
13:26:56 <elliott> if they broke compatibility to fix it that would be really good but I'd be very surprised
13:28:30 <elliott> arrays are still broken though, yeah?
13:28:34 <ais523\unfoog> elliott: looking at this, the bulk operations all seem to have variance annotations
13:28:50 <elliott> and yeah -- I just misremembered the problem, you are right
13:29:02 <elliott> arrays breaking the type system is still pretty bad though :p
13:29:57 <ais523\unfoog> "Operations using a Spliterator that cannot split, or does so in a highly imbalanced or inefficient manner, are unlikely to benefit from parallelism."
13:30:10 <ais523\unfoog> what's the point of a spliterator that can't split?
13:31:57 -!- ais523\unfoog has quit (Remote host closed the connection).
13:32:10 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40864&oldid=40858 * TomPN * (+62) /* def function */
13:32:18 -!- ais523\unfoog has joined.
13:32:25 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40865&oldid=40864 * TomPN * (+2) /* def function */
13:32:47 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40866&oldid=40865 * TomPN * (-6) /* def function */
13:33:07 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40867&oldid=40866 * TomPN * (+2) /* def function */
13:33:37 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40868&oldid=40867 * TomPN * (-26) /* def function */
13:34:05 <oerjan> ais523\unfoog: an `olist was done yesterday
13:34:32 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40869&oldid=40868 * TomPN * (+30) /* def function */
13:34:45 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40870&oldid=40869 * TomPN * (+2) /* def function */
13:34:51 -!- ais523 has joined.
13:35:06 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
13:35:06 -!- ais523 has changed nick to ais523\unfoog.
13:35:14 <ais523\unfoog> [13:33] <ais523\unfoog> elliott: are you going to warn me not to read that?
13:35:16 <ais523\unfoog> [13:33] <ais523\unfoog> I'm worried about what I'll find if I do
13:35:18 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40871&oldid=40870 * TomPN * (+13) /* def function */
13:35:26 <elliott> ais523\unfoog: not to read what?
13:37:13 <ais523\unfoog> also, that's the second time I've been DCed, reconnected, then seen lines I've said earlier
13:37:13 -!- ais523\unfoog has quit (Excess Flood).
13:37:40 -!- ais523\unfoog has joined.
13:41:04 -!- DeadFishBot has joined.
13:41:55 <AndoDaan> hmm, that should have done something.
13:43:21 <ais523\unfoog> unlike other "quantum" esolangs, this is basically a stupid syntax for a perfectly ordinary quantum programming language
13:43:30 -!- DeadFishBot has quit (Read error: Connection reset by peer).
13:44:28 <oerjan> just need to shor it up a bit
13:46:10 <ais523\unfoog> quantum deadfish can do shor's algorithm pretty easily
13:46:58 <HackEgo> olist 967: shachaf oerjan Sgeo FireFly boily nortti
13:47:33 <elliott> quantum deadfish sounds amazing
13:47:36 <FireFly> quantum deadfish wouldn't be any more powerful than regular deadfish, would it?
13:48:33 <ais523\unfoog> I don't think quantum computers can solve P=NP in constant time
13:48:38 <FireFly> I wonder where oerjan put the swatter
13:49:26 <oerjan> ais523\unfoog: I SAID THERE'D BEEN AN `OLIST
13:50:14 <oerjan> which was bad since it was done yesterday
13:51:16 * oerjan swats elliott -----###
13:51:23 <oerjan> sorry, was a bit backlogged
13:51:43 <elliott> thanks, little do you know I'm a masochist and will continue stating falsehoods to promote more swatting
13:52:26 <oerjan> i guess constant time is taking it one step further than the usual lie
13:52:55 <oerjan> oh not to mention the confusion of "solving P = NP"
13:53:03 <elliott> oerjan: also I very specifically said "solving P = NP" -- yes :p
13:53:12 <oerjan> you know, actually that was a thing of beauty
13:53:13 <elliott> it produces a proof that P = NP, in constant time, by existing.
13:53:23 -!- DeadFishBot has joined.
13:53:37 <J_Arcane> So I am presented with a strange question: Do I make this bastard spawn of Scheme and BASIC pure-functional or not ...
13:54:08 <AndoDaan> Why would DeadFishBot work in a channel I made, but not here?
13:54:25 <ais523\unfoog> AndoDaan: are you matching on the name of that channel?
13:54:35 <J_Arcane> oerjan: IT would be a lot easier than trying to solve the LET name conflict between the two.
13:55:27 <AndoDaan> That's probably it, but the join channel is given by argv
13:55:37 <oerjan> J_Arcane: your strange capitalization inspires me to tell you to just call one of them IT
13:56:19 <oerjan> J_Arcane: also you know LET is optional in most basics right
13:56:42 <elliott> J_Arcane: neither scheme or basic is purely functional, so yes.
13:56:50 <J_Arcane> oerjan: I actually haven't 100% decided on a capitalization rule. And yeah, LET has been basically optional since slightly after Dartmouth BASIC.
13:57:12 -!- DeadFishBot has quit (Read error: Connection reset by peer).
13:57:17 <oerjan> J_Arcane: you could distinguish them by including = in the basic one, maybe?
13:57:21 <J_Arcane> But otherwise BASIC doesn't have a strict assignment/definition command besides just the =.
13:58:55 -!- DeadFishBot has joined.
13:58:57 <J_Arcane> oerjan: I was thinking about overloading DEF into DEF FN and DEF VAR; it's a Lisp-1 so it's purely a syntax shortcut either way (I considered doing this in CL so I could match the split namespace and have an excuse to use GOSUB, but Racket macros are sooo flexible.)
13:59:17 -!- DeadFishBot has quit (Read error: Connection reset by peer).
14:00:00 <AndoDaan> Yeah, but I had to slap him from over here.
14:00:07 <oerjan> AndoDaan: you know you'll have to paste the code soon if this continues
14:00:53 <AndoDaan> Gonna take a step back, and (give up) go through the code.
14:01:08 <oerjan> J_Arcane: hm in scheme the DEF FN is just distinguished by putting the FN inside a list...
14:01:28 <oerjan> are you not using parentheses, in which case this might be more like a LOGO than a scheme
14:02:01 <oerjan> heck you might consider LOGO to _be_ a bastard child of scheme and basic
14:02:06 -!- heroux has quit (Ping timeout: 265 seconds).
14:02:10 <J_Arcane> oerjan: Yeah, I also thought of that too. If I make lambda into fn like Clojure does, then essentially you can just do DEF name FN (args), which is a bit backwards but works.
14:02:54 <J_Arcane> oerjan: Oh there's direct relationship between LOGO and Lisp IIRC, it just doesn't show up at the basic levels. But no, I'm using S-expressions, because I haven't learned how to write reader macros yet.
14:03:45 -!- heroux has joined.
14:11:41 -!- DeadFishBot has joined.
14:11:44 -!- DeadFishBot has quit (Remote host closed the connection).
14:13:06 -!- DeadFishBot has joined.
14:13:08 -!- DeadFishBot has quit (Remote host closed the connection).
14:15:46 -!- DeadFishBot has joined.
14:15:51 -!- DeadFishBot has quit (Remote host closed the connection).
14:16:11 <AndoDaan> I can't. I have to clean up my code first.
14:16:48 <AndoDaan> The bot is basically a frankenstein's monster.
14:17:57 <AndoDaan> But thanks for the offer. Idk, I guess I should work on my code shiness.
14:18:34 <AndoDaan> `help how do i build an irc bot?
14:18:34 <HackEgo> Runs arbitrary code in GNU/Linux. Type "`<command>", or "`run <command>" for full shell commands. "`fetch <URL>" downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert <rev>" can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
14:23:24 <FireFly> @faq can Haskell help me build an IRC bot?
14:23:25 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
14:23:55 -!- AnotherTest has joined.
14:24:11 <AndoDaan> @hoogle Can Haskell help me build an irc bot?
14:24:12 <lambdabot> Can Haskell help me build an irc bot?
14:24:51 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
14:24:54 -!- ais523 has joined.
14:25:05 -!- ais523 has changed nick to ais523\unfoog.
14:25:52 -!- monotone has quit (Quit: Rebooting server).
14:28:07 -!- monotone has joined.
14:29:47 -!- AndoDaan has quit.
14:30:02 -!- shikhout has joined.
14:33:13 -!- shikhin has quit (Ping timeout: 258 seconds).
14:40:18 -!- AndoDaan has joined.
15:09:16 -!- `^_^v has joined.
15:10:33 -!- nycs has joined.
15:13:50 -!- `^_^v has quit (Ping timeout: 264 seconds).
15:14:35 <nyuszika7h> AndoDaan: if that helps, here are some basics: on initial connection, you send "NICK <nickname>" and "USER <username> * * :<real name>". obviously, don't include <>. username is this part: foo (~bar@baz.com). real name is what shows up next to the hostname in whois usually, can be anything you like.
15:14:52 <nyuszika7h> on receiving a message that starts with "PING", send the message back with "PING" replaced by "PONG".
15:15:17 <nyuszika7h> recv: "PING foo", send: "PONG foo" | recv: "PING :foo bar", send: "PONG :foo bar"
15:15:18 <ais523\unfoog> the second and third fields in a USER command can be pretty much anything
15:15:39 <ais523\unfoog> they're meant to be details of the connection you're using, but the other end ignores them because it'd be a security risk to honour them
15:16:55 <nyuszika7h> usually if the second space-separated token of the message is "376", that means "End of /MOTD command" - this is usually where you auto-join channels and such, unless you need to identify to nickserv.
15:17:39 <elliott> ais523\unfoog: not in all RFCs
15:17:49 <elliott> one RFC changed it to, be, uh, something or other and an initial umode, or something, I think
15:18:15 <elliott> I think nobody cares about that updated RFC though?
15:18:24 <elliott> I think the IRC 3.0 thing is based on the original RFC.
15:18:31 -!- nycs has changed nick to `^_^v.
15:18:48 <elliott> nyuszika7h: is there any actual reason to wait for the end of the motd before sending JOINs?
15:19:50 <nyuszika7h> elliott: some ircds will say "You are not registered" if you send the join too early
15:20:04 <nyuszika7h> can be probably sent earlier like around 251 or what it was, but 376 is the most common
15:20:18 <mroman> AndoDaan: theres an IRC bot written in haskell on the haskell-wiki
15:20:34 <nyuszika7h> if you want to identify to nickserv, then either you should use SASL or if you have a cloak, on freenode and charybdis-based networks, 396 will work too
15:20:37 <mroman> it - however - can only write to a single hardcoded channel
15:20:52 <nyuszika7h> probably should catch only the *first* occurrence of 376 and 396 per connection
15:20:57 <elliott> on freenode, you should just use PASS.
15:21:13 <elliott> PASS actually just turns into a /msg nickserv
15:21:17 <elliott> so unfortunately it doesn't do any better in terms of cloaks
15:21:21 <fizzie> Client-side certificates hth
15:21:33 <elliott> but it's easier to send it at the start if you don't want to deal with, like, TLS and SASL and all that mess. careful about your deadfish IRC bot opsec
15:21:36 <nyuszika7h> fizzie: they don't do much better either, until freenode implements SASL EXTERNAL :(
15:21:48 <elliott> freenode does support client-side certificates, I believe?
15:22:00 <nyuszika7h> but not SASL EXTERNAL, which identifies you early when using CertFP
15:22:19 <elliott> oh, you can have a cloak failure with the certificate approach?
15:22:27 <elliott> that justifies my lazy sticking with normal SASL
15:22:38 <nyuszika7h> yeah you can still end up joining before cloaked
15:22:47 <nyuszika7h> because nickserv handles identifying still
15:23:01 <elliott> but regular SASL passwords are fine?
15:23:16 <elliott> I mean, not that cloaks are life-and-death, but.
15:24:27 <fizzie> Oh, that's the silliest if true. I mean, certificate validation happens so early in the connection, it should just work.
15:24:51 <fizzie> Also I forgot to say "hello" from Tampere, I think there were some channelfolk living there.
15:33:54 <nyuszika7h> elliott: SASL identifies you early, yeah, whatever mechanism you use
15:34:56 <nyuszika7h> I use both SASL PLAIN and CertFP, so that I get automatically identified after services come back in case they split or something
15:35:24 <elliott> five nines on your nickserv identification
15:35:26 <fizzie> Perhaps you should also add a script that polls for services every three minutes.
15:35:55 <fizzie> I guess there's no SLA for freenode.
15:36:11 <elliott> I don't think freenode manage very many nines.
15:38:07 <fizzie> "Have them put a decimal point after the ninety nine and see how many nines they can tack on behind it." (From a book.)
15:50:36 -!- mihow has joined.
15:58:36 -!- vanila has joined.
16:14:57 -!- drdanmaku has joined.
16:23:39 -!- AndoDaan has quit (Ping timeout: 255 seconds).
16:28:54 -!- AndoDaan has joined.
16:28:56 <mroman> !blsq "132"Pp"123"{pPFi}m[
16:28:57 <blsqbot> {ERROR: Burlesque: (_+) Invalid arguments!}
16:29:01 <mroman> !blsq "132"Pp"123"XX{pPFi}m[
16:29:01 <blsqbot> {ERROR: Burlesque: (fi) Invalid arguments! "132" '1 ERROR: Burlesque: (fi) Inval
16:29:07 <mroman> !blsq "132"Pp"123"XX{pPfI}m[
16:29:07 <blsqbot> {ERROR: Burlesque: (fi) Invalid arguments! "132" '1 ERROR: Burlesque: (fi) Inval
16:29:26 <mroman> !blsq "132"Pp"123"XX{pPFi}m[
16:29:26 <blsqbot> {ERROR: Burlesque: (fi) Invalid arguments! "132" '1 ERROR: Burlesque: (fi) Inval
16:29:29 <mroman> !blsq "132"Pp"123"XX{pPjFi}m[
16:29:42 <mroman> !blsq "132"Pp"123"XX{pPjFi?i}m[
16:30:25 <mroman> !blsq "132"Pp"123"XX{pPjFi}m[
16:30:53 <mroman> !blsq "132"Pp"123"XX{pPjFi}m[2CO
16:31:05 <mroman> !blsq "132"Pp"123"XX{pPjFi}m[2CO{p^.<}m[
16:31:56 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[2CO{p^.<}m[
16:32:09 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[
16:32:12 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[#s
16:32:12 <blsqbot> {{1 0 1 0 1 0 1 0} {1 0 3 2 5 4 7 6 8}}
16:32:31 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[j2CO{p^.-}m[#s
16:32:32 <blsqbot> {{-1 3 -1 3 -1 3 -1 2} {1 0 1 0 1 0 1 0}}
16:32:45 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[j2CO{^p.-}m[#s
16:32:45 <blsqbot> {{1 -3 1 -3 1 -3 1 -2} {1 0 1 0 1 0 1 0}}
16:33:17 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[j2CO{^p.-ab?i}m[#s
16:33:17 <blsqbot> {{2 4 2 4 2 4 2 3} {1 0 1 0 1 0 1 0}}
16:33:28 <mroman> !blsq "214365879"Pp"123456789"XX{pPjFi}m[J2CO{p^.<}m[j2CO{^p.-ab?i}m[**
16:33:29 <blsqbot> {1 2 0 4 1 2 0 4 1 2 0 4 1 2 0 3}
16:34:21 -!- shikhout has changed nick to shikhin.
16:34:37 <mroman> but that's way too ugly
16:49:43 <oerjan> my alternative approach seems far worse than the first i tried, and which i managed to shorten to tie int-e
16:49:52 <oerjan> (i suspect his approach is similar)
17:08:28 -!- oerjan has quit (Quit: leaving).
17:22:37 <AndoDaan> Okay... How do I subtract two elements in a block like {3 1} to give {2}?
17:23:19 <AndoDaan> nyuszika7h: Thanks, I'll have to check that.
17:24:02 <nyuszika7h> oh and to send a message: PRIVMSG #channel :message
17:24:43 <AndoDaan> mroman: Could I possible use the haskell irc bot to call external (lua) code, while itself handles interacting with irc?
17:25:46 <AndoDaan> I think my faulty bot was only looking for PRIVMSGs, but even after I broaden what it recognizes, still nop.
17:28:22 <elliott> it would be a lot simpler to just write the bot in lua
17:28:33 <elliott> compared to adapting the haskell code for that and plugging everything together
17:30:03 <AndoDaan> I don't think I can pull off 'simple', but you're probably right. mroman was most likely just nudging me to learn Haskell. :)
17:31:09 <elliott> I could take a look at your code?
17:31:59 <J_Arcane> I think I need an alternate naming style for predicate functions in Heresy; the scheme pred? style just doesn't feel very basic to me.
17:55:18 -!- MDream has changed nick to MDude.
17:57:44 <AndoDaan> elliott: Thanks for the offer. I'm still kinda shy about my code. I'm just gonna try cleaing it up, and make sure I'm not missing something embarrassingly obvious.
17:58:16 <elliott> you probably are, but won't notice until someone else points it out :p
17:58:18 <elliott> that's how programming usually goes
18:00:00 <elliott> 10x better than the rubberised equivalent for debugging
18:00:42 <AndoDaan> And if doesn't work out... well that would be dinner sorted.
18:00:46 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
18:00:57 -!- ais523\unfoog has joined.
18:05:09 -!- DTSCode has changed nick to dts.
18:05:12 -!- conehead has joined.
18:05:21 -!- conehead has quit (Changing host).
18:05:21 -!- conehead has joined.
18:05:33 -!- dts has changed nick to DTSCode.
18:13:48 -!- ais523\unfoog has quit (Read error: Connection reset by peer).
18:13:54 -!- ais523 has joined.
18:15:41 -!- ais523 has quit (Read error: Connection reset by peer).
18:15:58 -!- ais523 has joined.
18:18:14 -!- nycs has joined.
18:19:17 -!- `^_^v has quit (Ping timeout: 265 seconds).
18:26:05 <int-e> oh actually it seems that lambdabot got off lightly 18 hours ago. the provider hat trouble with a switch and half of the servers were unreachable for 3 hours and more instead of 50 minutes.
18:32:12 <HackEgo> :-( \ 113500 \ a.out \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dc \ dog \ etc \ factor \ head \ hej \ hello \ hello.c \ ibin \ index.html?dl=1812 \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test.c \ Wierd \ wisdom \ wisdom.pdf
18:54:20 <shachaf> ais523: I'd already olisted.
18:54:33 * shachaf considers giving olist state.
18:54:47 <ais523> bleh, no matter how much trouble I go to to verify the absence of past olists
18:55:00 <ais523> they frequently seem to have have happened
18:58:20 -!- Frooxius has joined.
19:04:03 -!- nycs has quit (Quit: This computer has gone to sleep).
19:07:16 -!- `^_^v has joined.
19:17:42 -!- mihow has quit (Quit: mihow).
19:28:27 <HackEgo> [wiki] [[Portal]] http://esolangs.org/w/index.php?diff=40872&oldid=40245 * 152.26.69.32 * (+0) /* Instructions */ learn to count, silly!
19:31:36 <b_jonas> what the heck? there's now a third one?
19:33:18 <shachaf> HackEgo doesn't have access to logs anymore, right?
19:34:22 <AndoDaan> Are cell based data structures one and the same as tape base data structures?
19:34:35 <ais523> shachaf: right, the logs are no longer in its filesystem
19:34:48 <ais523> so you'd have to get `olist to update a file itself
19:37:08 <ais523> AndoDaan: I think so, although "cell-based" could also apply if you had more than 1 dimension
19:38:35 <AndoDaan> Hmm, and I suppose Cells can also indicate how the code is stored. So not soley to do with data.
19:38:54 <HackEgo> [wiki] [[Hello++]] http://esolangs.org/w/index.php?diff=40873&oldid=38253 * 86.148.171.225 * (-145)
19:40:00 <int-e> shouldn't the first one be an exclamation mark...
19:40:33 <int-e> `` printf "%c" ABC
19:40:45 <int-e> not what I wanted, but ok
19:41:11 <int-e> I wanted C semantics, where the argument has int type.
19:42:06 -!- ais523 has quit (Read error: Connection reset by peer).
19:42:18 -!- ais523 has joined.
19:44:12 <int-e> `` python -c 'print "%c"%33'
19:44:31 <int-e> `` python -c 'print "%c"%387'
19:44:32 <HackEgo> Traceback (most recent call last): \ File "<string>", line 1, in <module> \ OverflowError: unsigned byte integer is greater than maximum
19:44:33 <int-e> `` python -c 'print "%c"%38'
19:44:56 <shachaf> Really, unsigned byte integer?
19:45:12 <int-e> the "Portal" example makes no sense.
19:45:30 <shachaf> `` python -c 'print u"%c"%387'
19:45:32 <HackEgo> Traceback (most recent call last): \ File "<string>", line 1, in <module> \ UnicodeEncodeError: 'ascii' codec can't encode character u'\u0183' in position 0: ordinal not in range(128)
19:46:29 <int-e> I think that each 'o' invocation is supposed to reverse the direction of execution... but as o+++++]]]]]o is executed in reverse, the right o "portal" is moved to the right before any of the "+" are executed. *mumbles*
19:48:06 <int-e> so let's see what the interpreter actually does :/
19:50:49 <int-e> So apparently what actually happens is that the second o transfers control back to the first. "Move the pointer to the other o portal" is an awful description.
19:51:49 -!- ais523 has quit.
19:52:07 -!- ais523 has joined.
19:56:59 <HackEgo> [wiki] [[Portal]] http://esolangs.org/w/index.php?diff=40874&oldid=40872 * 213.162.68.192 * (+51) clarify 'o' behavior
19:58:35 <HackEgo> [wiki] [[Portal 2]] http://esolangs.org/w/index.php?diff=40875&oldid=40256 * 213.162.68.192 * (-1) What was this about counting?
20:01:18 <HackEgo> [wiki] [[Portal 2]] http://esolangs.org/w/index.php?diff=40876&oldid=40875 * 213.162.68.192 * (+102) Clarify 'o' and '0'
20:01:54 <int-e> hmm, same captcha three times in a row. I though there were several?
20:05:26 -!- Patashu has joined.
20:11:19 -!- mihow has joined.
20:20:33 <HackEgo> [wiki] [[Portal 2]] http://esolangs.org/w/index.php?diff=40877&oldid=40876 * 213.162.68.192 * (+107) /* Example */ indicate instruction pointer in trace
20:23:55 <HackEgo> [wiki] [[Portal]] http://esolangs.org/w/index.php?diff=40878&oldid=40874 * 213.162.68.192 * (+59) /* Example */ indicate instruction pointer in trace
20:25:36 <int-e> (Hmm I tried to make the * red but there doesn't seem to be an easy way)
20:26:20 <int-e> The problem is to replicate the style of a <pre> block, so that one can use markup inside.
20:26:23 -!- Patashu has quit (Ping timeout: 256 seconds).
20:26:31 <fizzie> int-e: The current thought is that if there's only one captcha, it's easier to replace if/when it gets manually broken, and having only one does not seem to be any weaker.
20:26:52 <int-e> fizzie: I'm not complaining, just wondering aloud :)
20:27:04 <int-e> Thanks for the explanation.
20:27:29 <fizzie> I've still been idly thinking about trying out something in the http://thingelstad.com/stopping-mediawiki-spam-with-dynamic-questy-captchas/ vein, but the current setup seems to be more or less working.
20:27:32 <elliott> int-e: can't you just use an explicit <pre>?
20:27:48 <int-e> elliott: what's an explicit <pre>?
20:27:55 <elliott> as in <pre>...markup...</pre>
20:27:59 <elliott> as opposed to prefixing with spaces
20:28:12 <int-e> elliott: that's what I'm using
20:28:31 <int-e> (that's what the original author used, too)
20:28:47 <elliott> oh, okay. I didn't look at the diff or anything.
20:29:08 -!- shikhin has quit (Read error: Connection reset by peer).
20:29:57 -!- shikhin has joined.
20:32:54 <int-e> hmm hmm. http://esolangs.org/wiki/Template_talk:Pre
20:36:54 <elliott> https://bugs.eclipse.org/bugs/show_bug.cgi?id=381506
20:37:04 <elliott> why is that an eclipse bug?
20:37:15 <elliott> my advice was the wrong way around
20:37:18 <elliott> you should use spaces instead of <pre>.
20:38:27 <int-e> elliott: ah thanks, that will work.
20:40:46 <HackEgo> [wiki] [[Portal]] http://esolangs.org/w/index.php?diff=40879&oldid=40878 * 213.162.68.192 * (+569) /* Example */ add some color
20:42:25 <HackEgo> [wiki] [[Portal 2]] http://esolangs.org/w/index.php?diff=40880&oldid=40877 * 213.162.68.192 * (+1346) /* Example */ add some color
20:48:03 -!- AnotherTest has quit (Remote host closed the connection).
20:56:27 <HackEgo> [wiki] [[Len(language,encoding)]] N http://esolangs.org/w/index.php?oldid=40881 * 68.189.222.97 * (+2261) Created page with "'''Len(language,encoding)''' is not a single programming language, but rather a large family of related programming languages, inspired by [[Lenguage]] and [[Unary]]. == Synt..."
20:57:19 -!- AndoDaan has quit (Ping timeout: 244 seconds).
20:57:55 <HackEgo> [wiki] [[Len(language,encoding)]] http://esolangs.org/w/index.php?diff=40882&oldid=40881 * 68.189.222.97 * (-1) mistake in ASCII to binary
20:58:06 -!- AndoDaan has joined.
21:00:21 <HackEgo> [wiki] [[Unary]] http://esolangs.org/w/index.php?diff=40883&oldid=40720 * 68.189.222.97 * (+29) /* See also */
21:00:56 <HackEgo> [wiki] [[Len(language,encoding)]] http://esolangs.org/w/index.php?diff=40884&oldid=40882 * 68.189.222.97 * (-35) Not a brainfuck equivalent
21:02:07 <HackEgo> [wiki] [[Lenguage]] http://esolangs.org/w/index.php?diff=40885&oldid=40781 * 68.189.222.97 * (+73)
21:11:35 -!- MoALTz has quit (Ping timeout: 244 seconds).
21:13:02 -!- Sprocklem has joined.
21:58:48 <coppro> groupon backed down from the gnome trademark... that was fast
21:59:09 <ais523> hmm, I wonder how much money Gnome raised before that happened?
21:59:45 <b_jonas> ais523: http://www.gnome.org/groupon/ says 68629 USD so far (might not be accurate)
21:59:50 -!- centrinia has joined.
22:03:02 -!- AndoDaan has quit (Ping timeout: 272 seconds).
22:09:33 -!- ais523 has quit.
22:15:59 <fizzie> It said something like $20k or $30k a very short time ago.
22:18:17 -!- mihow has quit (Quit: mihow).
22:23:41 -!- AndoDaan has joined.
22:31:50 -!- Sgeo_ has joined.
22:35:02 -!- Sgeo has quit (Ping timeout: 245 seconds).
22:45:48 -!- boily has joined.
22:51:21 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=40886&oldid=40850 * BCompton * (+1) /* Commands */ Fixed typo
22:52:58 -!- oerjan has joined.
22:59:29 -!- hjulle has joined.
23:23:59 <boily> (you're still the only one whom I address in the vocative case.)
23:25:32 <oerjan> boily: hellørjan could be vocative, it's definitely not 2. declination
23:25:38 <Taneb> Today I went to a seminar on Forth
23:26:08 <boily> Taneb: how was it?
23:26:19 <Taneb> boily, the seminar proved interesting
23:26:24 <Taneb> The language seems... odd
23:26:34 <Taneb> But an interesting odd
23:26:37 <oerjan> boily: -us/-um -i, the only one that generally has separate vocative iirc
23:27:03 <boily> I wouldn't know for sure, I never got Latin imprinted into me during my schoolyears.
23:27:11 <Taneb> oerjan, some are also -er, eg. puer
23:27:28 <boily> IIRC, I went with the generic *PIE vocative ending.
23:27:47 <Taneb> Well, that's really suffixless in nom. and voc., but I think they're all -er
23:28:21 * boily feels complete now that he received his daily OKAYRJAN
23:29:06 <oerjan> one of the tidbits i recall about czech is that it has vocative -o ending for female names in -a
23:29:20 <oerjan> but none for masculine names iirc
23:29:31 <oerjan> (or possibly i just didn't pick that up)
23:32:11 <oerjan> norwegian is relatively light on case, but my dialect has a way of adding pronouns as articles before proper names that means vocative is slightly different, by leaving it out
23:33:25 <oerjan> (literally "he ørjan")
23:34:51 <oerjan> you can also inflect the pronoun for genitive
23:34:58 <oerjan> hainnes ørjan = ørjan's
23:35:09 <Taneb> Can anyone think of any implemented languages, other than ColorForth, where colour has semantics?
23:35:24 <Taneb> (text-based, I mean, so not like Piet)
23:35:45 <coppro> oerjan: which is your dialect?
23:36:10 <oerjan> coppro: northern norwegian
23:36:20 <coppro> oerjan: where do you livE?
23:37:09 <coppro> farthest north I've been is Trondheim, though I think my favourite place I visited was Alesund
23:37:18 <oerjan> i live in trondheim, which may have the same dialect feature (i'm having trouble deciding just by remembering) but it's not the same dialect
23:37:20 <coppro> (A with a ring; don't have an international keyboard atm)
23:37:35 <coppro> ah, cool. Trondheim is also a pretty awesome place
23:40:05 <tromp> i've also been to Alesund and Trondheim
23:40:21 <Taneb> AndoDaan, I don't think paintfuck+ has colours in the source code
23:41:00 <oerjan> trondheim dialect is considered trøndersk, not northern norwegian though, but several features apply to both regions
23:42:21 <oerjan> to distinguish trondheim dialect from any other in norway, ask them to talk about their car; it's the only dialect in which the word for car is feminine
23:43:39 <oerjan> (iirc bergen dialect, on the other hand, can be distinguished as the only which doesn't _have_ feminine)
23:51:39 <oerjan> no:bil = en:car is usually masculine
23:52:12 <oerjan> definite form bilen, vs. trondheim bila
23:54:41 <Melvar> I seem to have guessed the etymology.
23:55:47 <oerjan> Melvar: from automobile, right. iirc the word was supposedly chosen by a poll in a danish newspaper, and spread throughout scandinavia
23:56:25 <oerjan> shachaf: which is "buss" in norwegian
23:56:57 <oerjan> ("bus" in danish, which spells long consonants differently from norwegian)
23:58:08 <oerjan> shachaf: also, in norwegian nouns and adjectives are inflected according to number, gender (for adjectives, nouns just have them) and definiteness
23:58:33 <oerjan> bil, bilen, biler, bilene = car, the car, cars, the cars
23:59:00 <oerjan> although when an adjective gets added, we have an article in _addition_ to the suffix
00:00:00 <oerjan> well we have -s suffix on nouns which is sort of genitive, but really the same as english 's so barely counts
00:00:15 <boily> la bus (/bys/): you're from Eastern or Northern Québec; le bus (/bʌs/): you're from Southern Québec or Ottawa.
00:00:56 <shachaf> oerjan: number or just plurality?
00:02:00 <fizzie> oerjan: How about that Swedish thing of having a possessive pronoun, an adjective (with the definite-style -a suffix) but no suffix?
00:02:28 <shachaf> oerjan: In Hebrew a noun/adjective can be male/female and singular/plural. But articles work a little bit differently so I'm not sure I can directly compare.
00:02:35 -!- `^_^v has quit (Ping timeout: 245 seconds).
00:02:43 <shachaf> You do put a definite article on every adjective.
00:02:50 <shachaf> So maybe it's the same sort of thing.
00:03:11 <fizzie> oerjan: Something like "den gamla bilen" but "min gamla bil".
00:03:15 <oerjan> fizzie: there are circumstances in which the definite suffix on nouns is dropped when the prefixed article is added; danish does this obligatory but neither norwegian nor swedish iirc
00:03:22 <shachaf> (And there are no indefinite articles.)
00:03:52 <shachaf> Verbs can be male/female, singular/plural, first/second/third person, and past/present/future tense.
00:04:11 <shachaf> Or imperative, which is its own tense, I guess, and always second person.
00:04:49 <oerjan> fizzie: oh right. yes norwegian does that too, although there are _two_ different options. "min gamle bil" or "den gamle bilen min". my dialect only allows the latter in most situtations, while conservative bokmål/oslo prefers the former
00:05:19 <Melvar> shachaf: Imperative is usually classified as a mood, not a tense.
00:05:20 <fizzie> oerjan: Good to see you've managed to complicate it more than the Swedes.
00:06:00 <oerjan> fizzie: my dialect has at least three ways of expressing possession
00:06:40 <oerjan> bil'n te hain ørjan, hain ørjan sin bil, bil'n hainnes ørjan
00:06:53 <oerjan> (i don't actually have a car)
00:07:22 <Taneb> I am coming to the conclusion that colorForth was an elaborate joke in the early 2000s
00:07:37 <oerjan> the first two also work with non-proper nouns
00:07:41 <shachaf> Melvar: I'm not sure the distinction is pointful here.
00:08:30 <oerjan> shachaf: oh hm we also have an indefinite article in the singular, like english does, and that's used more or less the same
00:08:48 <Melvar> shachaf: Well, I don’t know if you have any more moods; if you do, it probably is.
00:08:49 <oerjan> even if we also have noun inflection
00:09:07 <shachaf> https://en.wikipedia.org/wiki/Modern_Hebrew_verb_conjugation
00:09:35 <boily> Taneb: I think colorForth falls in the unintentionally-esoteric language category.
00:09:53 <zzo38> boily: I do think that is an important category too, probably.
00:11:11 <shachaf> obviously languages with no articles are the best
00:11:26 <oerjan> shachaf: norwegian has lost all person suffixes on verbs, and never had gender. we still have past/present/imperative, pretty much like english (but we have no progressive forms)
00:11:35 <boily> shachaf: the lack of vowels disturbs me. without niqqud so many conjugations are written the same :/...
00:11:47 <boily> zzo38: most possibly.
00:11:55 <zzo38> I think you should write an article, if there is no article.
00:12:22 <oerjan> generally our verbs are simpler than english ones, i think
00:12:41 <oerjan> while it's the other way with nounds and adjectives
00:13:00 <boily> shachaf: I'm francophone. I'm used to an overabundance of unused letters.
00:13:06 <Melvar> In German, adjectives inflect for three levels of a definitenesslike distinction, but only certain combinations of gender and case have different forms.
00:13:34 <shachaf> Newspaper headlinese is one of those languages without articles.
00:13:37 <boily> pikhq: こんばんは！おひさしぶり
00:13:44 <shachaf> Area linguist shoots man, escapes police, flees scene.
00:14:02 <shachaf> Fortunately newspapers include articles directly below the headlines.
00:14:10 <pikhq> boily: Un, hisashiburi ne (IME nai, gomen)
00:16:53 -!- FreeFull has quit (Quit: BBL).
00:17:46 <boily> “Linguist Shoots Man, Escapes Police, Flees Scene” should become the canonical headline when discussing languages.
00:18:56 <zzo38> One thing I have wanted to do is making a Japanese-style manga book that is written in English, but the title is written using Japanese writing and some of the signs in the picture also have some writing with Japanese, but, the main text is in English.
00:21:44 <boily> pikhq: 心配しないで（^＿^） お元気ですか？何が新しいのか？
00:22:55 * boily waves Taneb a goodnightaneb
00:23:06 <pikhq> boily: Un, genki desu. Ima koso... ano sa. Atarashii mono wo oboeru no ga muzukashii ne.
00:25:29 <zzo38> Now I have all of the Akagi manga up to 28
00:25:40 <boily> (I really ought to get back to having classes. my Japanese's getting way too rusty and corroded...
00:25:52 <pikhq> (I hear ya, I have been slacking off myself.)
00:26:11 <pikhq> Darned work keeping me busy. :P
00:29:23 <boily> zzo38: the Akagies are in my backlog. meanwhile, I got the complete Slam Dunk.
00:46:27 <zzo38> boily: That one I don't know. But, in this most recent Akagi, he manages to do something that hasn't been done before even though I have predicted it (kind of). If you read it, then you can see...
00:49:27 -!- AndoDaan has quit (Ping timeout: 255 seconds).
01:08:26 <boily> I just watched the first episode of Baccano. it's going to be an interesting series...
01:09:44 <boily> non-linear Gravity's Rainbow in book form, non-linear Baccano in anime form...
01:09:56 <boily> there should be a non-linear boardgame out there to complete that.
01:10:09 <boily> (does Red November count?)
01:26:35 <boily> “Or rather, that their race was always on top.” I think it fits the bill.
01:42:06 <lifthrasiir> it always bothers me that I can read Japanese (somehow) but cannot write in that
02:03:17 <zzo38> I am not very good reading/writing Japanese, but I can a little bit, at least.
02:12:11 <boily> today's kanji: 韓【かん】Korea.
02:13:09 <boily> (nothing like a Chinese character, with a Japanese pronunciation, about a third country.)
02:13:37 -!- boily has quit (Quit: LATERAL CHICKEN).
02:29:39 -!- shikhout has joined.
02:32:26 -!- shikhin has quit (Ping timeout: 244 seconds).
02:42:25 -!- oerjan has quit (Quit: leaving).
03:00:42 -!- FreeFull has joined.
03:22:50 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=40887&oldid=40886 * AndoDaan * (+146) Added an interpreter.
03:29:25 <HackEgo> [wiki] [[User:AndoDaan]] M http://esolangs.org/w/index.php?diff=40888&oldid=40477 * AndoDaan * (+14) Hey guys! *cough* I mean, added MNNBFSL implementation mention.
03:29:29 -!- adu has joined.
03:32:35 -!- AndoDaan has joined.
03:41:06 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
04:27:06 -!- hjulle has quit (Ping timeout: 264 seconds).
04:36:02 <J_Arcane> Morning reading: http://www.ecma-international.org/publications/files/ECMA-ST-WITHDRAWN/ECMA-116,%201st%20edition,%20June%201986.pdfhttp://www.ecma-international.org/publications/files/ECMA-ST-WITHDRAWN/ECMA-116,%201st%20edition,%20June%201986.pdf
04:36:17 <J_Arcane> Arg, malformed link: http://www.ecma-international.org/publications/files/ECMA-ST-WITHDRAWN/ECMA-116,%201st%20edition,%20June%201986.pdf
05:06:13 <Sgeo_> Will ABCDEF ever get a non-dead link?
05:08:47 <Sgeo_> If only I had a perfect memory
05:11:44 -!- MDude has quit (Ping timeout: 265 seconds).
05:11:49 -!- DTSCode has changed nick to dTS.
05:11:51 -!- L8D has joined.
05:11:57 -!- dTS has changed nick to dTSCode.
05:12:11 <L8D> LISP, FORTH, Io, Brainfuck... what am I missing?
05:12:42 <L8D> and how is the bfjoust hill doing?
05:14:48 <L8D> elegantly-simple languages
05:15:12 <L8D> I'm thinking about which languages I should incorporate in a game I'm theorizing
05:15:15 <HackEgo> [wiki] [[Special:Log/newusers]] create * Thatguy25252525 * New user account
05:15:19 <vanila> I want to play that game
05:15:21 <vanila> can you tel me about it
05:15:38 <L8D> so there is this matrix of bytes
05:15:56 <L8D> and you as the player have this character which is just a program
05:16:07 <L8D> that you can write in any of the above languages
05:16:15 <L8D> and they all have they're own strengths and weaknesses
05:16:34 <L8D> but your program essentially is supposed to continously traverse this matrix
05:16:38 <L8D> and can find other programs
05:16:57 <L8D> and then you can delegate code to try and eliminate or try to communicate with these other programs
05:17:52 <L8D> so the world is represented as an ever-expanding matrix of bytes, and there is a 'tick' every few minutes or so
05:18:04 <L8D> and each tick evaluates each step in a program
05:18:14 <L8D> so like with brainfuck a single tick would run a single instruction
05:18:29 <L8D> but with LISPs ticks are a lot slower and stuff
05:18:38 <vanila> are you sure Io is slow
05:18:50 <L8D> well I don't know about Io really
05:19:06 <L8D> I think I'd need to create a subset or something
05:19:19 <L8D> but the syntax and structure behind is really elegant
05:19:31 <L8D> so I can make something that a user can build upon
05:19:47 <L8D> but I'd need a way of making a 'tick' of the program more concrete or evident
05:19:56 <vanila> i really like th sound of this
05:20:10 <L8D> and give some kind of power to the higher-level languages to prevent people from using brainfuck-generating scripts
05:20:22 <L8D> but another big problem is how I would implement the structure behind this all
05:20:27 <L8D> and how to make it scale
05:20:53 <L8D> I'll probably just use erlang
05:21:03 <L8D> but for now I'm focusing on the design of the game
05:21:18 <L8D> vanila: you're in #haskell right?
05:21:39 <vanila> yes but dont hold it against me
05:21:58 <L8D> but yeah I looking for languages that are simple and elegant
05:22:33 <L8D> I guess Io is too bloated but I can see myself writing a subset or forking the repo and stripping the standard library out
05:23:08 <zzo38> Lisp, Forth, and brainfuck can be used at least; I don't know much about the Io programming language, so I could not answer you about that.
05:24:12 <L8D> maybe even lua
05:24:37 <vanila> http://barrywatson.se/cl/cl_metacircular.html
05:24:37 <L8D> I was wondering if there were any nice esoteric languages other than brainfuck that fit the bill
05:25:23 <L8D> yeah prolog is very similar to erlang but still very complex to implement
05:25:34 <vanila> prolog is very very simple to implement from scratch
05:25:45 <L8D> well the syntax is quite crazy
05:26:08 <L8D> that's what I meant by similar to erlang
05:26:10 <vanila> the syntax is extemely simple, on level with Lisp plus some infix operators
05:26:30 <vanila> the language itself is quite differnet to erlang since it has unification and nondeterminism
05:27:26 <L8D> okay I'll consider
05:27:37 <L8D> ooo what about assembly?
05:28:15 <vanila> you dont have to include it in your game but I just wanted to express that prolog is very simple and belongs on the list
05:28:35 <L8D> AndoDaan: what
05:28:49 <L8D> AndoDaan: waaay to complicated
05:28:50 <vanila> assembly.. could use something stupid like subleq
05:28:54 <AndoDaan> Unefunge is Befunge limited to one dimension.
05:29:28 <L8D> it doesn't look like one dimension :/
05:31:46 -!- adu has quit (Quit: adu).
05:36:07 -!- dTSCode has changed nick to DTSCode.
05:37:00 <zzo38> I saw some things saying that when doing Huffman coding you need a EOF code or an indication of the length in the header. Actually, you only need three bits at the beginning of the file to tell you when it ends, or depending on the tree in use, possibly even less than three bits.
05:37:56 <vanila> that seems wrong to me anyway
05:38:12 <vanila> the number of bits out of the last byte
05:38:56 -!- reynir has changed nick to reynir_.
05:39:12 -!- reynir_ has changed nick to reynir.
05:39:18 <HackEgo> [wiki] [[Talk:Language list]] http://esolangs.org/w/index.php?diff=40889&oldid=34356 * Thatguy25252525 * (+586) /* ATZ */ new section
05:39:52 <HackEgo> [wiki] [[Talk:Language list]] http://esolangs.org/w/index.php?diff=40890&oldid=40889 * Thatguy25252525 * (+1) /* ATZ */
05:41:45 <vanila> does esoteric archive other sites e.g. http://strlen.com/programming-languages
05:42:51 <vanila> http://en.wikipedia.org/wiki/Urban_M%C3%BCller
05:43:02 <HackEgo> [wiki] [[Talk:Language list]] http://esolangs.org/w/index.php?diff=40891&oldid=40890 * Thatguy25252525 * (+2) /* ATZ */
05:44:33 <HackEgo> [wiki] [[Talk:Language list]] http://esolangs.org/w/index.php?diff=40892&oldid=40891 * Thatguy25252525 * (-1) /* ATZ */
05:45:10 -!- b_jonas has quit (Ping timeout: 250 seconds).
05:48:04 <vanila> http://en.wikipedia.org/wiki/Brain_Fuck_Scheduler
05:51:13 <HackEgo> [wiki] [[Talk:Main Page]] http://esolangs.org/w/index.php?diff=40893&oldid=37931 * Thatguy25252525 * (+577) /* ATZ */ new section
05:52:33 -!- b_jonas has joined.
05:52:38 <HackEgo> [wiki] [[ATZ]] N http://esolangs.org/w/index.php?oldid=40894 * Thatguy25252525 * (+590) Created page with "The ATZ programming language is an esoteric programming language designed by Arvin Zadeh in 2014. It has yet to be implemented and no interpreters have yet been made. Since it..."
05:56:41 -!- vanila has quit (Quit: Leaving).
06:08:10 -!- DTSCode has quit (Read error: Connection reset by peer).
06:10:52 -!- DTSCode has joined.
06:10:54 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=40895&oldid=40851 * Thatguy25252525 * (+10) Added the ATZ programming language.
06:34:10 -!- augur has quit (Ping timeout: 255 seconds).
06:42:56 <zzo38> Do you know the "Schroedinger's Directory"?
06:43:58 <zzo38> ls fldrA fldrB fldrC rmdir fldrA rmdir: fldrA: Not a directory cat fldrA cat: fldrA: Is a directory ... So, which is it?
06:44:07 <zzo38> I think it is a file containing the text "cat: fldrA: Is a directory"
06:52:06 <b_jonas> zzo38: some other process has changed it in between?
06:52:23 <zzo38> I suppose that can be a possibility too
06:52:50 <zzo38> What exactly will happen if it is a symlink?
06:53:27 <b_jonas> zzo38: ah, that's possible
06:53:32 <b_jonas> if it's a symlink to a directory
06:53:47 <b_jonas> because rmdir won't follow it, cat will
07:16:25 -!- augur has joined.
07:27:55 -!- Patashu has joined.
07:28:55 -!- L8D has quit (Ping timeout: 264 seconds).
07:34:00 -!- Patashu has quit (Disconnected by services).
07:34:00 -!- Patashu_ has joined.
07:37:20 -!- Patashu has joined.
07:40:31 -!- Patashu_ has quit (Ping timeout: 250 seconds).
07:42:37 -!- Patashu has quit (Disconnected by services).
07:42:37 -!- Patashu_ has joined.
07:45:48 -!- Patashu has joined.
07:49:31 -!- Patashu_ has quit (Ping timeout: 272 seconds).
07:56:09 -!- L8D has joined.
07:56:10 -!- MoALTz has joined.
08:03:00 -!- AndoDaan_ has joined.
08:05:50 -!- AndoDaan has quit (Ping timeout: 240 seconds).
08:17:09 -!- Patashu has quit (Disconnected by services).
08:17:10 -!- Patashu_ has joined.
08:20:33 -!- centrinia has quit (Ping timeout: 272 seconds).
08:24:23 -!- Patashu has joined.
08:24:59 -!- centrinia has joined.
08:27:36 -!- Patashu_ has quit (Ping timeout: 245 seconds).
08:29:49 -!- shikhin has joined.
08:31:17 -!- Patashu has quit (Disconnected by services).
08:31:18 -!- Patashu_ has joined.
08:32:33 -!- shikhout has quit (Ping timeout: 244 seconds).
08:34:24 -!- Patashu has joined.
08:35:07 -!- Patashu has quit (Client Quit).
08:37:43 -!- Patashu_ has quit (Ping timeout: 244 seconds).
08:42:27 -!- AndoDaan has joined.
08:42:47 -!- AndoDaan_ has quit (Ping timeout: 255 seconds).
08:45:57 -!- clog has quit (Ping timeout: 250 seconds).
08:47:46 -!- clog has joined.
09:07:07 -!- clog has quit (Ping timeout: 245 seconds).
09:14:23 -!- clog has joined.
09:18:47 -!- clog has quit (Ping timeout: 245 seconds).
09:48:42 <fizzie> "The company name is FEDERAL GOVERNMENT APPROVED COMPANY, Nigeria Federal Government approved this company because some bank and courier company are using their office to scam many other people all over the World --" well, that's an imaginative name.
09:50:17 <AndoDaan> Only the most naive person would still respond to something like that. Just the type they're looking for.
09:51:19 <AndoDaan> though, leading them on is fun for a while.
09:52:28 <fizzie> It would only cost $8000 to get my $10.5 million, and I can pay most of it when I receive the money, they just need $180 now "to enable them approve your delivery from Nigeria Federal High Court of Justice".
09:52:59 <fizzie> Also the company name keeps changing, now it's called "FEDERAL GOVERNMENT APPROVE FEDEX COMPANY".
09:53:54 <fizzie> "Stop contacting Western union Or those evil Bank because they can't transfer your fund rather they will kept demeaning money one after another."
09:54:04 <fizzie> Oh no, they will demean the money.
09:54:38 <shachaf> fizzie: You should ask them to send you $20 to confirm their bank account is real, after which you'll send them the full $200.
09:56:21 <fizzie> I don't think I'm enterprising enough.
10:00:14 <J_Arcane> Anyone know of any dynamically typed BASIC dialects?
10:05:05 -!- Phantom_Hoover has joined.
10:19:53 <mroman> AndoDaan: you can invoke other processes using Haskell yes
10:19:59 <mroman> that's what I do with blsqbot as well
10:20:19 <mroman> blsqbot launches the blsqinterpreter in a new process
10:20:33 <mroman> for security reasons I guess
10:20:41 <mroman> because this way I can have a timeout in the interpreter
10:20:55 <mroman> (which is about 0.04s or something iirc)
10:21:08 <mroman> and a 2s timeout for the process
10:23:02 <mroman> also that's the way rlisp works as well
10:26:41 <mroman> also Burlesque is becoming object something-oriented
10:31:42 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40896&oldid=40871 * TomPN * (+4) /* def function */
10:35:18 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40897&oldid=40896 * TomPN * (+155) /* Qubits */
11:08:04 -!- impomatic_ has quit (Ping timeout: 244 seconds).
11:18:15 -!- clog has joined.
11:19:02 -!- boily has joined.
11:28:26 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
11:40:06 <Taneb> I am going to try and write a really optimizing brainfuck implementation at some point
11:53:57 <boily> this sound like a threat. “I'm going to write you a brainfuck optimizer, you vile slimy fungot!”
11:53:58 <fungot> boily: but some people just born to marry fnord with that and
11:56:47 <b_jonas> fungot: any predictions about the comet and the lander mission?
11:56:59 <b_jonas> fungot: no, I mean any prediction from you?
11:56:59 <fungot> b_jonas: so i don't really have that much time but she was very pleased and was showing everybody you know and
11:57:15 <b_jonas> fungot: trust your instincts
11:57:16 <fungot> b_jonas: ( ( ah ah)) to talk to meet people you know talking about travel i wish i did
11:57:51 <boily> fungot: which one of your girlfriends was showing everybody?
11:57:51 <fungot> boily: i think ' cause that's what they
12:09:06 <fungot> mroman: i don't know how i exactly how i feel you know i get it um yeah i knew one day i just made up my mind you know certain certain subways don't go to bars so i have to
12:09:25 <fungot> mroman: what kind of products they sell okay laughter you know like he's chasing her all over the place laughter and so it's it's crazy
12:15:42 -!- oerjan has joined.
12:15:57 <boily> bars selling laughter, chasing prospects all over the place.
12:16:22 <boily> oerjan: good mœrjaning. careful, fungot is being sentient today.
12:16:22 <fungot> boily: i well i want what liz taylor has i want to collect it
12:16:50 -!- boily has quit (Quit: APOSTATIC CHICKEN).
12:17:08 <oerjan> boily: fungot wants to marry a dozen times?
12:17:09 <fungot> oerjan: if it's a ban on everybody then you can purchase that gives you a ah destination and something fun to do scrapbooking do you do any sewing any actual sewing or laughter you know
12:19:46 -!- MoALTz has quit (Quit: Leaving).
12:27:24 <J_Arcane> Closest thing to a first peek at what I've been working on: https://twitter.com/J_Arcane/status/532501084120809472
12:28:40 -!- lesocratic has joined.
12:29:36 <oerjan> J_Arcane: if you link a pdf here, you could at least _mention_ that it's > 50 Mb
12:29:52 <J_Arcane> oerjan: Oh shit, sorry about that, I didn't realize it was so big.
12:30:53 <HackEgo> "But I don't want to go among mad people," Alice remarked. "Oh, you can't help that," said the Cat: "we're all mad here. I'm mad. You're mad." "How do you know I'm mad?" said Alice. "You must be," said the Cat, "or you wouldn't have come here."
12:30:57 <J_Arcane> mroman: Well, I am diagnosed with clinical depression, but I'd like to think it's unrelated to this project. ;)
12:30:58 -!- lesocratic has left.
12:31:01 <oerjan> it's not _just_ a joke.
12:32:16 <elliott> mroman: that's kind of a weird thing to randomly ask somebody
12:32:49 <mroman> elliott: Not If that Somebody has a blog article mentioning it.
12:33:09 <elliott> ...if they have, then do you need to ask in the first place?
12:33:42 <mroman> I wasn't asking for a "fact"
12:33:50 <mroman> It's a "surprise" kind of question.
12:34:10 <mroman> "I hit him in the face." "You did?"
12:34:23 <elliott> how surprising that somebody could have illnesses and still talk about esoteric programming languages on IRC.
12:34:39 <mroman> I'm diagnosed with depression as well
12:34:55 <mroman> in fact, I'm living in a mental health facility right now
12:35:40 <elliott> been there, done that. (good luck, btw)
12:36:39 <elliott> sorry for the sarcasm, anyway; I have a bit of a hair trigger about the topic.
12:36:52 <mroman> It was an odd question.
12:36:54 <J_Arcane> It's a sensitive issue for sure.
12:37:10 <mroman> My social skills aren't impressively good ;)
12:37:13 <J_Arcane> A lot of stigma around it still, though it's starting to get better, at least about depression.
12:37:14 <elliott> my experiences with the mental health care system have not been positive
12:37:46 <J_Arcane> I keep getting good therapists and then having to move and losing them ... :(
12:38:40 <elliott> mroman: also, they let you have internet?
12:38:53 <mroman> elliott: It's not full stationary
12:39:07 <mroman> I have to consult leo.org for a moment
12:39:28 <J_Arcane> I'm also still on a sub-therapeutic dose of my medication, and the doctor here won't approve a bigger one for at least another two weeks, maybe longer. Big city health services in Finland can mean long wait times.
12:39:36 <mroman> it's the kind of thing where you are not 100% in the clinic
12:39:56 <mroman> I work during day hours
12:40:43 <mroman> you sleep there and stuff
12:40:55 <elliott> for me, it was 24/5; I was allowed to go home on weekends. to start with (until I was uncooperative), and months later when they ran out of excuses to keep me sleeping there, it became an outpatient thing. (I was a minor at the time.)
12:41:17 <elliott> I sincerely hope you are getting better treatment than I did :p
12:42:00 <mroman> I think they are trying to get rid of me..
12:43:06 <mroman> just in the "you should think about leaving soon" sense
12:44:40 <mroman> The problem is that if you can't answer the question
12:44:46 <mroman> "Well, how can we help you?"
12:46:04 <elliott> my experience was considerably less voluntary :p
12:46:28 <oerjan> elliott: the place i stayed was also pretty lenient about internet
12:46:36 <fizzie> I just wrote the word "lexicuton", and was struck by a strong feeling that it should mean something, but I don't think it does.
12:46:44 <fizzie> (Was attempting to write "lexicon".)
12:46:45 <mroman> We have internet from 17:30 to 23:00 in the clinic
12:46:50 <oerjan> (obviously, since i kept coming here)
12:47:06 <elliott> oerjan: right. I suspect that is more common in facilities for adults.
12:47:36 <mroman> They don't actually know all my "symptoms"
12:47:41 <elliott> you miss out on the "IRCing until 4 am every day on a smuggled iPhone from a mental health care facility" experience, though
12:47:48 -!- MoALTz has joined.
12:47:51 <mroman> because I'm blocked/too scared/whatever to tell them the whole story
12:48:05 <oerjan> elliott: well that _is_ something to write in your autobiography
12:48:06 <elliott> I'm so good at iPhone typing now.
12:48:52 <elliott> oerjan: my autobiography would be 2000 pages long and panned as being completely unrealistic
12:48:57 <mroman> The thing that shuts down internet isn't DST aware though
12:49:04 <mroman> for a short time it cut you off at 22:00.
12:49:50 <elliott> mroman: how does the blocking work? does it just completely cut the connection or does it, like, hijack HTTP to redirect to a "stop using the internet" page?
12:50:07 <elliott> I'm not thinking about that thing that tunnels TCP over DNS but I'm thinking about that thing that tunnels TCP over DNS.
12:50:18 <mroman> it cuts the connection
12:51:14 <mroman> I'm not really planning on using internet after 23:00 anyway
12:51:18 <mroman> that's usually the time I go to sleep
12:52:21 <b_jonas> "lexicuton" looks like "L-execution"
12:53:01 <b_jonas> mroman: that could be because of the one week difference in America versus Europe DST
12:53:14 <fizzie> I was thinking of something like a particle physics analogue but in a language context.
12:53:31 -!- AndoDaan has quit (Ping timeout: 272 seconds).
12:53:56 <b_jonas> mroman: as in, the DST offset changed on 2014-10-26 in Europe, but one week later in much of the US
12:54:00 <fizzie> The thing that mediates the interaction between two lexicons.
12:54:35 <fizzie> Or maybe you learn new words by absorbing lexicutons, or something.
12:56:08 <mroman> b_jonas: the explanation is much simpler I think
12:56:20 <mroman> you turn the clock one hour back
12:56:29 <mroman> so what previously was 23:00 is now 22:00
12:56:39 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40898&oldid=40897 * TomPN * (+2) /* Output */
12:56:51 <mroman> if you don't turn the clock one hour back in the "cut internet of" thing it will think it's 23:00 when it's really just 22:00
12:57:08 <b_jonas> mroman: sure, it's possible that they just misconfigured it
12:57:23 <mroman> it's probably even something that just cuts power of the modem/router
12:57:56 <mroman> http://de.wikipedia.org/wiki/Zeitschaltuhr#mediaviewer/File:Digitale_Zeitschaltuhr.jpg <- something like that
12:58:18 <oerjan> it might just be using UTC, sounds more likely than anything american involved
12:58:19 <elliott> I'd guess it'd be a feature of the router. they often have a lot of "parental control" type things
12:58:21 <b_jonas> mroman: hmm... I'd more guess it's a setting on the router, but that's possible too
12:58:52 <mroman> anyway... if you have smartphone with internet connection you can use internet all day long
12:59:01 <mroman> (I have no internet contract for my smartphone though)
12:59:03 <b_jonas> mroman: "can" in what sense?
12:59:18 <mroman> b_jonas: you "can" and it's allowed.
12:59:47 <mroman> which makes the policy of "no internet past 23:00" kinda obsolete actually
13:00:19 <mroman> I don't think they pay by the hour :)
13:00:44 <mroman> It might be a legal thing though
13:01:13 <elliott> how filtered is their internet? :p
13:01:20 <mroman> they are somehow responsible for what you do while you are there
13:01:37 <mroman> elliott: well... I can ssh out of it
13:01:48 <mroman> I can play League of Legends
13:02:05 <mroman> the connection somehow breaks always after some time
13:02:27 <mroman> hearthstone works as well
13:05:28 <fizzie> We had one of those things which rotate and then you stick in pins to configure the time.
13:05:56 <Taneb> fizzie, we use one of those for christmas lights
13:06:10 <elliott> see, configure the time, get it. never mind
13:06:54 <fizzie> http://indoorgardensupplies.com/wp-content/uploads/TN311C-T-6-Timer.jpg -- this sort of thing, except much more... er, I can't figure out a better description except "German-looking", which is probably horribly inappropriate.
13:07:04 <elliott> the joke is I interpreted fizzie's line as referring to time travel.
13:08:45 <mroman> fizzie: I hate the ones that rotate
13:13:27 <Taneb> This evening I have an opportunity to fulfil my life-long dream
13:13:47 <Taneb> To be a contestant on University Challenge
13:13:54 <Taneb> My uni's try-outs are this evening
13:16:23 <Taneb> (University Challenge is a British quiz show which pits teams of students against eachother)
13:16:32 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40899&oldid=40898 * TomPN * (+1556) /* Example programs */
13:16:57 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40900&oldid=40899 * TomPN * (+0) /* Hello World! */
13:17:22 <mroman> hm. on sounds better actually
13:17:25 <Taneb> https://www.youtube.com/watch?v=_fd1ywxn8ig
13:17:34 <mroman> so Taneb is going on a TV.
13:17:58 <Taneb> If I make the try-out, then the second round of selection, then the team is good enough to go on TV
13:19:55 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40901&oldid=40900 * TomPN * (+3) /* Hello World! */
13:20:15 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40902&oldid=40901 * TomPN * (+2) /* Storing qubits in cells */
13:22:52 -!- centrinia has quit (Ping timeout: 265 seconds).
13:23:35 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=40903&oldid=40857 * TomPN * (+0) /* Velocity */
13:24:39 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40904&oldid=40902 * TomPN * (+11) /* Example programs */
13:25:30 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=40905&oldid=40904 * TomPN * (-11) /* Hello World! */
13:37:18 -!- bb010g has quit (Quit: Connection closed for inactivity).
13:38:57 <oerjan> xkcd is doing something weird again...
13:41:10 <J_Arcane> Whatever it is id doesn't work in my Chrome so I couldn't figure what.
13:41:30 <J_Arcane> Ahh, now it's working. Just blank before.
13:41:54 <fizzie> "Volume 4783" wow, that's a big number.
13:48:44 <oerjan> someone made http://xkcd1446.org/
13:51:19 <int-e> why do people embed jquery from jquery.com rather than hosting their own copy... (though I guess I like that better than loading it from google.com)
13:57:41 <b_jonas> Taneb: good luck for that. tell us how the try-out went.
14:09:02 -!- augur has quit (Remote host closed the connection).
14:14:50 -!- CADD has quit (Remote host closed the connection).
14:16:42 <oerjan> int-e: dammit your comment about waiting for henkma's 120 byte solution was too close to accurate :(
14:17:34 <oerjan> i said "too close to", not "exactly" hth
14:17:56 <int-e> I wasn't contradicting you.
14:18:24 <int-e> Otoh you seem to agree on the 68 for Brainfuck Optimization.
14:19:19 <oerjan> i'm a little surprised you didn't find that, it's _almost_ the completely obvious thing to do
14:19:22 <int-e> anyway, plenty of time left for desparation
14:19:34 <int-e> I didn't try too hard
14:20:02 <int-e> so don't count me out yet :P
14:21:32 <oerjan> hm henkma's 124 solution uses as many alphanums but much fewer symbols
14:24:41 <oerjan> perhaps that means he's using some verbosely named function, or even an import
14:25:27 -!- Sprocklem has quit (Ping timeout: 244 seconds).
14:26:49 <int-e> import Data.Mysterious.Bag.Of.Golf.Tricks;main=doWhatIMean
14:27:08 <int-e> (it's a bag, hence in data)
14:28:26 <oerjan> i actually tested Data.Map, it was one char longer than Data.List with sort
14:30:13 -!- shikhout has joined.
14:30:47 -!- shikhout has changed nick to Guest86977.
14:32:35 -!- AnotherTest has joined.
14:32:59 -!- shikhin has quit (Ping timeout: 250 seconds).
14:57:18 <FreeFull> Who here has been looking at Rust?
14:57:37 <oerjan> looking at rust forming, now there's a hobby
14:58:25 <FreeFull> "However, due to the quantum nature of the program, this will only occur ≈99% of the time. " Well, there are deterministic quantum algorithms too
15:02:32 -!- hjulle has joined.
15:04:48 -!- `^_^v has joined.
15:11:23 <mroman> if the harpoons don't work it will just bounce of the comet back into space?
15:11:50 <mroman> *bounce off from the comet?
15:12:18 -!- augur has joined.
15:12:38 -!- drdanmaku has joined.
15:13:18 <mroman> It's "bounce off the comet", right?
15:13:25 <b_jonas> the thruster may still work, and even if it doesn't, there's dampers so he doesn't bounce too high so gravity may still help, and after that he can anchor himself like a rock climber
15:13:40 <mroman> b_jonas: but I've read that gravity isn't really strong
15:13:53 <b_jonas> the bounce off is the unlikely worst case
15:14:04 <b_jonas> sure, it's not strong, it's a small (four kilometer size) comet
15:14:39 <mroman> this news site says it only weighs 4 grams on the comet
15:14:53 <mroman> which suggests that if I threw a golf ball at it it would just bounce off into space again
15:14:55 <b_jonas> the lander still slows down a lot before landing, those thursters work. it's just the reverse thruster that weakly pushes the lander _towards_ the comet _after_ touching down that may have a problem
15:15:07 <mroman> since the rebound is probably stronger than the gravity
15:15:11 <b_jonas> mroman: yes, but there's nobody throwing golf balls that far up
15:17:11 <fizzie> If it really says "weighs 4 grams" and not something like "equivalent of 4 grams on Earth" or anything, that must've annoyed quite a few readers.
15:17:47 <mroman> it's obvious that it means "equivalent of 4 grams on earth"
15:18:28 <fizzie> It may be obvious, but I wouldn't be surprised it'd still annoy people. It kind of does that to me.
15:25:44 <mroman> I see fizzie did basic brainfuck optimizations
15:27:02 -!- Gregor has quit (Ping timeout: 265 seconds).
15:30:29 -!- Gregor has joined.
15:38:19 <Taneb> Does anyone know of a channel where I can ask basic APL questions?
15:48:31 -!- Phantom_Hoover has joined.
15:50:12 <tromp> try stackoverflow?!
15:50:54 <tromp> are there any irc channels for those J / K languages?
15:52:13 <Taneb> tromp, there is but I am not sure if that is the right place to be asking about APL?
15:53:09 <j-bot> mroman: 0 1 2 3 4 5 6 7 8
15:53:09 <j-bot> mroman: 9 10 11 12 13 14 15 16 17
15:53:09 <j-bot> mroman: 18 19 20 21 22 23 24 25 26
15:53:09 <j-bot> mroman: 27 28 29 30 31 32 33 34 35
15:53:09 <j-bot> mroman: 36 37 38 39 40 41 42 43 44
15:53:25 <j-bot> mroman: |ill-formed number
15:54:04 <blsqbot> Ain't nobody got time fo' dat!
15:55:27 -!- Sprocklem has joined.
15:56:11 <tromp> i thought those are the modern derivates of APL
15:56:40 <mroman> blsq is really modern .
15:57:59 <mroman> !blsq {2 2 3 1}{2 2 2 2}ct
15:57:59 <blsqbot> Ain't nobody got time fo' dat!
15:58:02 <mroman> !blsq {2 2 3 1}{2 2 2 2}ct
15:58:31 <mroman> !blsq {2 2 3 1}{2 2 2 2}ct4 0.95cq
15:58:43 <mroman> !blsq {2 2 3 1}{2 2 2 2}ct4 0.95cq.<
15:58:53 -!- augur has quit (Read error: Connection reset by peer).
15:58:57 <mroman> !blsq {0 2 5 1}{2 2 2 2}ct4 0.95cq.<
15:59:04 <mroman> !blsq {0 0 7 1}{2 2 2 2}ct4 0.95cq.<
15:59:35 -!- augur has joined.
16:00:48 <mroman> !blsq "Hello, world!"tt{**32.-2B!7'0P[}m[sa^^8.%8\/.-.+'0[P8co{2B!}\m
16:00:48 <blsqbot> {81 22 100 201 227 0 87 159 74 100 64 32}
16:01:55 <fizzie> mroman: I pretty much did the same as the ubiquitous sed, so it's p. boring.
16:02:07 <mroman> !blsq {81 22 100 201 227 0 87 159 74 100 64 32}{2B!8'0P[}\m6co{L[6==}f[{2B!32.+L[}\m
16:03:10 <mroman> !blsq "1234"<-3co)<-<-',IC
16:03:19 <mroman> !blsq "1234567"<-3co)<-<-',IC
16:04:44 <mroman> !blsq 1234567<-3co)<-<-',IC
16:04:44 <blsqbot> {ERROR: Burlesque: (_+) Invalid arguments!}
16:06:45 <mroman> !blsq 1234567<-3co)<-<-',[]
16:06:54 <mroman> !blsq 1234567<-3co)<-<-',[]im
16:06:54 <blsqbot> ERROR: Burlesque: (++) Invalid arguments!
16:06:57 <mroman> !blsq 1234567<-3co)<-<-',[]
16:07:02 <mroman> !blsq 1234567<-3co)<-<-(,)[]
16:07:05 <mroman> !blsq 1234567<-3co)<-<-(,)[]im
16:07:05 <blsqbot> ERROR: Burlesque: (++) Invalid arguments!
16:07:07 <mroman> !blsq 1234567<-3co)<-<-(,)[]
16:07:11 <mroman> !blsq 1234567<-3co)<-<-(,)[]sp
16:07:11 <blsqbot> [Sh, "\n", 1, "\n", Sh, "\n", ,, "\n", Sh, "\n", 234, "\n", Sh, "\n", ,, "\n", S
16:07:17 <mroman> !blsq 1234567<-3co)<-<-(,)[]bs
16:07:21 <mroman> !blsq 1234567<-3co)<-<-(,)[]BS
16:07:24 <mroman> !blsq 1234567<-3co)<-<-',[]BS
16:07:59 <mroman> !blsq 1234567<-3CO)<-<-',[]BS
16:07:59 <blsqbot> 123 , 234 , 345 , 456 , 567
16:21:10 -!- augur has quit (Remote host closed the connection).
16:22:50 <mroman> I guess it's Touchdown for Philae
16:26:16 -!- augur has joined.
16:31:54 <mroman> fungot: Do you live on a comet?
16:31:54 <fungot> mroman: i fnord you for being able to exercise sigh
16:33:53 <fizzie> Not too many exercise possibilities on comets, I guess.
16:34:47 -!- augur has quit (Remote host closed the connection).
16:35:56 <oerjan> the hard part is not falling off while you do it
16:36:51 <mroman> I've heard harpoons work on comets.
16:37:08 <oerjan> yeah there's some recent evidence.
16:40:58 <L8D> LISP, FORTH, Bf, possibly Io... what am I missing here?
16:41:05 <L8D> prolog has been suggested but I don't know
16:41:14 <L8D> I'm writing an MMO similar to bfjoust
16:41:35 <oerjan> L8D: when reading the logs, i _was_ going to suggest underload until i saw you needed interactivity.
16:42:04 <L8D> the brief summary is: There's a matrix of bytes (octets), you write a program that continuously traverses this matrix and finds other programs
16:42:13 <oerjan> you should just prod ais523 to finish underlambda, i guess.
16:42:36 <tromp> L8D: what are the requirements for the language?
16:42:36 <L8D> what makes underload useful?
16:42:55 <L8D> tromp: simple to learn/parse syntax, libary-less semantics
16:42:58 <oerjan> L8D: i thought you wanted elegant and simple, not useful hth
16:43:12 <tromp> L8D then how about binary lambda calculus (BLC) ?
16:43:18 <L8D> I mean... what makes underload elegant and simple?
16:43:28 <L8D> tromp: is that something that is easy to learn and parse?
16:43:44 <L8D> I thought that was just an encoding for doing ski combinators
16:43:53 <tromp> L8D: see http://www.ioccc.org/2012/tromp/hint.html
16:44:05 <tromp> no, it's not SK based
16:44:21 <oerjan> ^ul (It is )((very easy)*)^(S):!^
16:44:22 <elliott> underload has simple semantics
16:44:26 <tromp> i can be parsed and interpreted in 29 bytes
16:44:31 <elliott> and an elegant concatenative paradigm
16:44:37 <L8D> this will be code that would be edited inside browsers BTW
16:45:04 <L8D> the game itself would have a fancy UI
16:45:09 <L8D> and be web based
16:45:13 <tromp> hmm, blc is not suitable for writing code in directly:(
16:45:30 <L8D> one sec I have some examples
16:46:14 <Taneb> Real Fast Nora's Hair Salon 3: Shear Disaster Download
16:46:23 <L8D> all of the programs would be equivalent: http://lpaste.net/114179
16:46:25 <tromp> but it comes with a BLC assembler so maybe that is doable
16:46:35 <L8D> it's psuedo-code at the moment however
16:47:16 <tromp> that ioccc link has an example program for reversing input that looks like "\a a ((\b b b) (\b \c \d \e d (b b) (\f f c e))) (\b \c c)"
16:47:28 -!- Guest86977 has quit (Quit: leaving).
16:47:48 -!- shikhin has joined.
16:50:32 <L8D> I'm not really looking for hard-to-code-in or really-effing-abstract programming languages
16:50:41 <L8D> which I guess is what most esoterics are
16:50:45 <elliott> but you're asking this channel? :p
16:50:53 <L8D> yeah... should've expected it
16:51:03 <L8D> but I know this channel would definitely be interested
16:51:16 <tromp> BLC is both hard-to-code-in and really-effing-abstract :-(
16:51:36 <tromp> as well as really simple:-)
16:52:20 <Taneb> L8D, I'm still inclined to suggest something APL-like, such as J
16:52:25 <Taneb> Not sure how good at IO they are, though
16:53:11 <L8D> nah they don't need good IO
16:53:19 <L8D> I can just inject the stuff in-memory
16:53:24 <L8D> or somethign
16:54:36 <L8D> hm... J is actually quite interesting
16:54:56 <L8D> although it gets quite crazy fast
16:58:48 <L8D> what about some kind of lambda calculus thing?
16:58:52 <L8D> not ski combinators but lambdas
16:58:58 <L8D> and well... not lisp
16:59:03 <Taneb> Real Fast Nora's Hair Salon 3: Shear Disaster Download :)
16:59:05 <L8D> something Haskell-y
16:59:18 <L8D> Taneb: what?
16:59:43 <Taneb> L8D, an esolang I made
17:00:07 <tromp> it's the COBOL dialect of binary lambda calculus:)
17:00:11 <Taneb> It has the ease-of-programming of binary lambda calculus with the terseness of COBOL!
17:00:24 <Taneb> (I meant it as a purely functional BIT)
17:00:46 <Taneb> In terms of semantics, other than IO it's identical to BLC
17:00:55 <L8D> tromp: what about a Haskell dialect of lambda calculus?
17:01:15 <elliott> depending on what you mean
17:01:21 <L8D> I mean like....
17:01:25 <L8D> everything's a function
17:01:28 <L8D> and you have lambdas
17:01:40 <Taneb> elliott, maybe with binding names?
17:01:42 <tromp> then you end up with hard to program
17:01:47 <elliott> Taneb: LC has name binding!
17:01:52 <L8D> but I'm looking for an existing LANGUAGE that models LC
17:02:02 <Taneb> elliott, syntaxy binding names
17:02:06 <L8D> Haskell fits but haskell has other things
17:02:14 <L8D> I want something that is stricty LC
17:02:20 <elliott> lambda calculus is a language...
17:02:31 <L8D> which could be a LISP but LISP has other things
17:02:42 <L8D> elliott: like there is a specific language named "lambda calculus" ?
17:03:02 <J_Arcane> there are actual implementations of pure lambda calculas.
17:03:04 <tromp> blc is just lambda calculus with the means to do IO
17:03:33 <tromp> and written in binary:(
17:03:35 <L8D> so like... I could do peano numerals and all that?
17:03:35 <elliott> L8D: the lambda calculus was one of the very first programming languages, really
17:03:39 <elliott> it just wasn't thought of in that way originally
17:03:53 <tromp> you have to define you numerals from scratch
17:03:57 <elliott> since we didn't have computers to evaluate it yet
17:04:04 <L8D> I went through the CS lectures too ;)
17:04:14 <elliott> but yes, you can write a lambda calculus evaluator in like half a page of haskell code, if that
17:04:17 <tromp> the blc prime number generator doesn't even use a number representation
17:04:21 <L8D> I'm talking about implementations though
17:04:35 <L8D> are there implementations of LC that do it properly and lazily and such
17:04:44 -!- mihow has joined.
17:04:51 <tromp> see that ioccc link
17:05:02 <L8D> elliott: how would it be typesafe?
17:05:23 <elliott> L8D: you hide the recursion behind a data type
17:05:26 <tromp> it would be untyped
17:05:47 <Taneb> I want to enter IOCCC but I can never think of a good thing to write that isn't like, way too ambitious
17:05:54 <L8D> elliott: but you'd still run into problems with GHC not letting you do recursively ambiguous types
17:05:59 <elliott> L8D: or just don't do it metacircularly
17:06:04 <elliott> I don't know what you mean by that
17:06:12 <elliott> newtype LC = LC (LC -> LC) -- this type models the lambda calculus, albeit uselessly
17:06:25 <L8D> and that compiles without warnings?!
17:06:34 <elliott> data List a = Nil | Cons a (List a)
17:06:39 <int-e> L8D: what would the warning be?
17:06:42 <elliott> you couldn't do much of anything without recursive types
17:07:04 <L8D> int-e: cannot determine type of this type
17:07:11 <elliott> actually, GHC's inliner does have a bug when you use this trick to implement the Y combinator directly, embarrassingly. I don't think it's that easy to trigger though.
17:07:31 <int-e> L8D: it's even inhabited
17:07:32 <L8D> I understand recursive data structures, I'm not a noob to haskell
17:07:33 <elliott> in practice I'd just use newtype LC a = Var a | App (LC a) (LC a) | Lam (LC (Maybe a)).
17:07:49 <elliott> well, the type of LC is *. :p
17:07:56 <J_Arcane> Here's a walk through for building a lambda-calculus language in Racket, with sample code: http://matt.might.net/articles/compiling-up-to-lambda-calculus/
17:08:01 <int-e> (unlike things like newtype Foo = Foo Foo)
17:08:07 <elliott> L8D: do you believe that newtype LC = LC (Int, LC) is a type?
17:08:15 <elliott> inhabited by, for instance, x = LC (123, x)
17:08:17 <L8D> elliott: sure, it's a comonad too
17:08:29 <elliott> L8D: OK. do you believe that newtype LC = LC (Int -> LC) is a type?
17:08:40 <elliott> newtype LC = LC (LC -> Int)?
17:09:01 <int-e> newtype LC = LC (LC -> LC) is inhabited by LC id, for example. or LC (const (LC id))
17:09:02 <L8D> sure, but wouldn't the problem rely when there aren't any other types that GHC can infer other than functions
17:09:10 <elliott> inhabited by e.g. x = LC (\_ -> 123), y = LC (\(LC k) -> k (LC k) + 1)
17:09:27 <elliott> do you believe newtype LC = LC (LC, LC) is a type?
17:09:37 <elliott> I mean, functions aren't really special here
17:09:55 <Taneb> IN JUST OVER AN HOUR I WILL HAVE A CHANCE TO BECOME ONE STEP CLOSER TO ACHIEVING MY DREAM
17:09:58 <L8D> I know it's a type, but I don't get why GHC doesn't throw a fit
17:09:58 <elliott> (okay, they are if you're trying to have a sound language like proof systems have to worry about, because of variance. but Haskell doesn't care about non-terminating programs)
17:09:59 <int-e> or LC (\LC f -> LC (f . f)) -- which would be the Church numeral 2.
17:10:08 <elliott> I mean, I don't get why GHC would :)
17:10:14 <int-e> uhm LC (\(LC f) -> LC (f . f))
17:10:30 <elliott> L8D: what about data LC = Foo | LC (LC -> LC)?
17:10:47 <L8D> I could see that as fine
17:10:49 <elliott> then you have really boring inhabitants like Foo, LC (\_ -> Foo), LC (\case Foo -> Foo; LC _ -> LC (const Foo))
17:11:02 <elliott> L8D: okay, and you believe there are values of LC that completely ignore Foo?
17:11:21 <elliott> let's say they all, whenever they consume an LC, map Foo to undefiend and just extract the function out of the LC
17:11:24 <elliott> and let's say they never produce a Foo
17:11:27 <int-e> Really, newtype LC = LC (LC -> LC) it's a perfectly good type. It's not even all that obvious that you cannot do anything useful with it.
17:11:31 <elliott> then do you believe we can just take Foo away?
17:11:52 <L8D> from a types standpoint
17:11:56 <L8D> as a type it makes sense
17:11:59 <elliott> int-e: I agree, but I am actually interested in the reasoning here... to me I can understand balking at newtype LC = LC (LC, LC)
17:12:07 <elliott> but I can't quite understand accepting that but not (LC -> LC)
17:12:20 <elliott> (without some deeper kind of mumbling about being strictly positive)
17:12:26 <L8D> because then you couldn't actually get the function to eval as a thunk without !
17:12:41 <L8D> and I assume GHC would pick up on that
17:12:56 <elliott> I'm not sure what you mean by that
17:12:57 <L8D> because GHC can get any useful data out of those functions so why bother?
17:13:05 <int-e> L8D: a type is all that it has to be for the compiler to accept it without complaining.
17:13:08 <elliott> well, you can't get useful data out of (() -> ()) either
17:13:16 <elliott> *ignoring _|_ (i.e. without ! or such)
17:13:25 <elliott> you expect the compiler to reject (() -> ())...?
17:13:26 <L8D> so is it not complaining because it doesn't know?
17:13:34 <L8D> I expect a warning about () -> ()
17:13:53 <elliott> do you expect a warning about (main :: IO ())? :p
17:13:57 <int-e> L8D: it's not complaining because there's nothing wrong
17:14:04 <elliott> () -> () is isomorphic to () without _|_.
17:14:13 <elliott> if you don't think () values should cause warnings then there's no reason for any of these to either
17:14:20 <L8D> because with () -> () GHC will either assume it's unsafe, will bottom, or just never evaluate it
17:14:34 <L8D> and those are warning-worthy to me
17:14:46 <elliott> (\() -> ()) is a perfectly good value of type () -> ()
17:14:51 <elliott> and yes you might actually need that
17:14:53 <elliott> consider generic programming
17:15:03 <elliott> you often fix type variables to () when you don't need to use the more advanced form of a function
17:15:06 <int-e> > fmap id (Right ())
17:15:11 <elliott> and then have to supply glue functionality like that to use the function
17:15:15 <L8D> (() -> ()) only makes sense with "!"
17:15:32 <L8D> then when would you ever use it?
17:15:46 <elliott> consider thingy :: (a -> b) -> [(a,Int)] -> IntSetWith b
17:15:49 <int-e> just because there is only one inhabitant doesn't mean that a type useless. () is proof of that.
17:15:50 <elliott> pardon the ridiculousy data structure
17:16:01 <elliott> then (thingy id . map ((),)) :: [Int] -> IntSetWith ()
17:16:12 <elliott> this is a contrived example. there are less contrived examples.
17:16:22 <elliott> this kind of thing does pop up frequently in polymorphic programming
17:16:37 <L8D> but it's still kind of useless
17:16:43 <elliott> (I guess "IntSetWith" is also known as "Map Int")
17:16:48 <L8D> it's there to fill an empty/unused gap
17:16:57 <elliott> no, it's not useless. it's trivial. there's a difference
17:17:04 <L8D> but it's unused
17:17:05 <elliott> if thingy is the API you get, this is a perfectly reasonable use of it
17:17:19 <int-e> () is quite heavily used in Haskell
17:17:22 <L8D> (() -> ()) means the function will either throw, bottom or do nothing
17:17:28 <L8D> I'm not talking about ()
17:17:34 <L8D> I'm just talking about (() -> ())
17:17:34 <elliott> can you stop repeating yourself without addressing what I said?
17:17:38 <elliott> I gave you some code that uses (() -> ()).
17:17:38 <int-e> () -> () will, usually, be just id.
17:17:55 <int-e> (which I guess is what you mean by "do nothing")
17:17:59 <L8D> elliott: but that's to just fill types that you don't use
17:18:02 <elliott> L8D: ok, I give you this API. mapFromList :: (a -> b) -> [(k,a)] -> Map k b
17:18:07 <elliott> L8D: you want to write a function [Int] -> Map Int ()
17:18:13 <int-e> however, there's value in such a function because it can be passed to higher-order functions
17:18:14 <elliott> if you don't think Map Int () is a useful type, consider that it is exactly Set Int.
17:18:18 <elliott> L8D: please write this function for me
17:18:21 <int-e> > (id *** succ) ((), 1)
17:18:30 <elliott> you will find that you inevitably write a function (() -> ()) (it will be id)
17:18:42 <elliott> if the compiler gave a warning for that it would be ridiculous. you're doing something perfectly reasonable with a perfectly reasonable API
17:18:43 <L8D> \xs -> M.fromList (map ((),) xs)
17:18:57 <elliott> you get mapFromList. it's a thought experiment.
17:19:03 <elliott> pretend it's MyFancyMap instead of Map if you'd rather.
17:19:21 <elliott> (yes, in this case the API is pointlessly more complicated than fromList. But there are many legitimate situations where you want to do something like this.)
17:19:40 <L8D> mapFromList (const ())
17:19:46 <L8D> something in that vein
17:19:53 <L8D> :t const ()
17:19:56 <elliott> @let data MyMap k a = Dummy
17:20:07 <int-e> @type Data.Map.fromSet -- hmm
17:20:13 <elliott> @let mapFromList :: (a -> b) -> [(k,a)] -> MyMap k b; mapFromList = undefined
17:20:23 <elliott> @type mapFromList (const ()) :: [Int] -> MyMap Int ()
17:20:24 <lambdabot> Couldn't match type ‘(Int, a0)’ with ‘Int’
17:20:25 <lambdabot> Expected type: [Int] -> MyMap Int ()
17:20:25 <lambdabot> Actual type: [(Int, a0)] -> MyMap Int ()
17:20:32 <elliott> @type mapFromList (const ()) . map ((),) :: [Int] -> MyMap Int ()
17:20:33 <lambdabot> Couldn't match expected type ‘Int’ with actual type ‘()’
17:20:33 <lambdabot> In the first argument of ‘map’, namely ‘((),)’
17:20:38 <elliott> @type mapFromList (const ()) . map (,()) :: [Int] -> MyMap Int ()
17:20:42 <elliott> L8D: correct. I have bad news for you.
17:20:47 <elliott> do you know what the type of (const ()) in context is there?
17:21:06 <elliott> it's doing exactly what you want.
17:21:10 <L8D> but that's when you're doing polyfilling
17:21:32 <L8D> I'm talking about when you do somethign where you could just use unit
17:21:43 <L8D> and that's not what I mean by polyfilling
17:21:52 <L8D> when you use unit to substitute some unused type
17:22:44 <elliott> here's the last thing I say before I let myself get sucked back into this in a few minutes: if you had your way GHC would produce thousands of spurious warnings on vast swathes of high-quality, idiomatic Haskell code that would only be worsened by trying to work around it.
17:23:31 <L8D> in mapFromList (const ()) . map (,())
17:23:37 <L8D> const () is Int -> ()
17:23:46 <L8D> but whatever
17:24:02 <elliott> :t \f -> mapFromList f . map (,())
17:24:19 <L8D> > mapFromList (const () :: Int -> ()) [1, 2, 3]
17:24:21 <lambdabot> No instance for (GHC.Show.Show (L.MyMap k0 ()))
17:24:21 <lambdabot> arising from a use of ‘M389555805829656213922168.show_M3895558058296562139...
17:24:47 <elliott> ;t mapFromList (const () :: Int -> ())
17:24:49 <elliott> :t mapFromList (const () :: Int -> ())
17:24:58 <elliott> your job was to write [Int] -> MyMap Int ()
17:25:06 <elliott> :t mapFromList (const () :: Int -> ()) . map (,())
17:25:07 <lambdabot> Couldn't match expected type ‘Int’ with actual type ‘()’
17:25:07 <lambdabot> In the first argument of ‘map’, namely ‘(, ())’
17:25:09 <elliott> :t mapFromList (const () :: () -> ()) . map (,())
17:25:39 <elliott> I'm too old for bickering angrily on IRC like this. I should be too old for bickering on IRC like this, anyway...
17:25:42 * L8D is the dumbest person in this channel
17:26:05 <oerjan> L8D: btw GHC uses GHC.Exts.Any rather than () to fill unused types hth
17:26:21 <elliott> I doubt that, but I'm the most irritable, that's worse.
17:26:39 <elliott> sorry for ranting over something that doesn't matter.
17:27:13 <elliott> I was going to say fungot probably is but that's just mean. fungot has made more sense than people in this channel before
17:27:13 <fungot> elliott: seeing she was like that's ' cause we especially kids watching the news because you never know
17:27:41 -!- oerjan has quit (Quit: The harpoons never fired?).
17:27:55 <L8D> who is fungot ?
17:27:55 <fungot> L8D: yeah exactly and if pays good then it's all right it's okay for adults too you probably wouldn't be the best way to find out
17:28:17 <fungot> L8D: and it seems like some kids a lot better it's a lot of
17:28:46 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
17:28:47 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher* fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
17:28:50 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
17:28:51 <L8D> fungot fungot
17:28:51 <fungot> L8D: that would be first-class, and they need to raise our hopes too high, yes.
17:28:53 <fungot> elliott: see: unicode!?! :p) then performed operations on it, it's not a
17:28:58 <elliott> fungot: you can do bette than this
17:28:58 <fungot> elliott: lambda the ultimate
17:29:08 <elliott> `addquote <fungot> elliott: lambda the ultimate
17:29:08 <fungot> elliott: interfaces should never ask to save
17:29:10 <HackEgo> 1223) <fungot> elliott: lambda the ultimate
17:30:48 <fizzie> fungot: You hypocri-bot with your ^save command.
17:30:49 <fungot> fizzie: the only difference between proper lists dotted lists is the wrong way
17:31:22 <L8D> ^yoda fungot
17:31:39 <fungot> L8D: matthew integrated that fix, but i
17:31:48 <fungot> L8D: since people get to take 6.001. i realized that
17:31:54 <fungot> L8D: translates ' good night' to people and sympathize with them. these were designed in. from what i understand
17:32:06 <HackEgo> *poof* <fungot> elliott: lambda the ultimate
17:41:03 <Taneb> `quote I thought that was
17:41:04 <HackEgo> 938) <ais523> did you know that likes follow you around the internet and steal your browser? <Taneb> I thought that was Phantom_Hoover
17:41:20 <Taneb> Meh, I'm a narcissist
17:41:25 <Taneb> Last night I made a pun.
17:41:42 -!- DTSCode has quit (Read error: Connection reset by peer).
17:42:01 <Taneb> Bah, I'm getting anxious, I'm gonna go for a walk
17:43:00 -!- DTSCode has joined.
18:02:05 -!- zzo38 has quit (Read error: Connection reset by peer).
18:06:37 -!- augur has joined.
18:46:39 -!- vanila has joined.
18:53:32 -!- augur has quit (Remote host closed the connection).
18:53:45 <vanila> http://lpaste.net/114191
18:53:53 <vanila> bubble sort in i ment what i sed
18:54:43 <vanila> http://lpaste.net/114192
18:59:45 <vanila> oh, i guess /// is better than this!
19:01:07 -!- augur has joined.
19:09:27 <L8D> omg its augur
19:09:39 <L8D> itz augur guys
19:12:08 -!- variable has quit (Ping timeout: 250 seconds).
19:19:07 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
19:19:53 -!- variable has joined.
19:21:34 -!- L8D has left.
19:21:46 -!- zzo38 has joined.
19:23:08 <augur> what are you doing here
19:24:01 <vanila> i made an esolang but /// is better
19:29:36 <augur> vanila: whyd you make an esolang?
19:29:38 <augur> and what kind is it?
19:30:21 <vanila> http://lpaste.net/114191 http://lpaste.net/114192
19:30:34 <vanila> because i couldnt sleep :S
19:36:19 -!- Sprocklem has quit (Ping timeout: 272 seconds).
19:37:34 -!- heroux has quit (Ping timeout: 256 seconds).
19:39:03 -!- heroux has joined.
19:41:09 <b_jonas> tromp: #jsoftware is the irc channel
19:44:13 <tromp> thx; b_jonas, i suggest Taneb tries his APL questions there
20:00:44 <coppro> is there any language which distinguishes the first-person plural when it does or does not include the addressee of the conversation as well?
20:00:51 <coppro> ("we" vs. "we and you", basically)
20:03:48 <Melvar> It’s called “clusivity” (inclusive vs. exclusive (of the second person)).
20:17:06 -!- zzo38 has quit (Ping timeout: 265 seconds).
20:19:10 <HackEgo> [wiki] [[ATZ]] http://esolangs.org/w/index.php?diff=40906&oldid=40894 * 199.254.2.56 * (+7)
20:20:43 <HackEgo> [wiki] [[ATZ]] http://esolangs.org/w/index.php?diff=40907&oldid=40906 * 199.254.2.56 * (-7)
20:22:55 -!- Bicyclidine has joined.
20:30:32 -!- shikhout has joined.
20:33:11 -!- shikhin has quit (Ping timeout: 240 seconds).
20:35:06 -!- shikhout has changed nick to shikhin.
20:51:22 -!- blsqbot2 has joined.
20:51:43 <mroman> !blsQ %:"age" 19 "money" 1000V
20:52:19 <mroman> !blsQ %:0"age" 19 "money" 1000V
20:54:35 <mroman> !blsQ %p=%:0"age"19V%p?
20:55:09 -!- blsqbot2 has quit (Read error: Connection reset by peer).
20:56:30 <b_jonas> mroman: are those variables?
20:56:52 -!- blsqbot2 has joined.
20:57:06 <mroman> !blsQ %foo=9 %foo? %foo? ?*
20:57:25 <mroman> !blsQ %square{^^?*} 9 %square!
20:57:26 <blsqbot2> ERROR: Burlesque: (e!) Invalid arguments!
20:57:31 <mroman> !blsQ %square={^^?*} 9 %square!
20:57:38 <mroman> %foo= is an assignment
20:58:10 <mroman> !blsQ %m=%:0%:0 9 9V8V
20:58:15 <mroman> !blsQ %m=%:0%:0 9 9V8V%m?
20:58:24 <mroman> that's a map with a map as a key
20:58:44 <mroman> %:0 9 8V creates a map with key 9 and value 8
20:58:55 <mroman> the 0 is the "default" value returned by lookups if no value was found
20:59:03 <mroman> !blsQ %:0 1 2 3 4 5 6V
20:59:13 <mroman> !blsQ %:0 1 2 3 4 5 6V8 7mi
21:00:30 -!- zzo38 has joined.
21:03:15 <mroman> which means you can also do recursion
21:03:23 <blsqbot2> Ain't nobody got time fo' dat!
21:03:25 <HackEgo> [wiki] [[Special:Log/newusers]] create * Voidpigeon * New user account
21:03:44 -!- Bicyclidine has quit (Quit: Reconnecting).
21:04:00 -!- Bicyclidine has joined.
21:04:58 <HackEgo> [wiki] [[Talk:Language list]] http://esolangs.org/w/index.php?diff=40908&oldid=40892 * Voidpigeon * (-588) moving atz
21:05:18 <HackEgo> [wiki] [[Talk:Joke language list]] http://esolangs.org/w/index.php?diff=40909&oldid=39056 * Voidpigeon * (+589) moved atz
21:09:00 <HackEgo> [wiki] [[Talk:ATZ]] N http://esolangs.org/w/index.php?oldid=40910 * Voidpigeon * (+181) Created page with "==Documentation== On [[Talk:Joke_language_list|the joke language list]], it says that documentation is said to be released upon request. This is a request to see the document..."
21:12:32 <Melvar> Hah, this newsthing spends a paragraph on describing the stink of the landed-on comet.
21:12:38 <mroman> !blsQ %q={%q={}%q!}%q!
21:12:46 <mroman> !blsQ %q={%q={9}%q!}%q!
21:16:23 <mroman> !blsQ %q={%q={9 8"q"sv}%q!}%q!
21:16:31 <mroman> !blsQ %q={%q={9 "q"8sv}%q!}%q!
21:17:16 <mroman> !blsQ %q={9"q"sv%q?}%q!
21:18:20 -!- blsqbot2 has quit (Read error: Connection reset by peer).
21:25:36 -!- Bicyclidine has quit (Ping timeout: 250 seconds).
21:37:01 -!- Bicyclidine has joined.
21:39:36 -!- augur has quit (Remote host closed the connection).
21:40:02 -!- augur has joined.
21:41:50 -!- S1 has joined.
21:42:40 <HackEgo> [wiki] [[Talk:Joke language list]] http://esolangs.org/w/index.php?diff=40911&oldid=40909 * 70.211.156.73 * (-589) /* ATZ */
21:43:08 -!- TodPunk has quit (Read error: Connection reset by peer).
21:43:30 -!- TodPunk has joined.
21:43:36 -!- augur has quit (Remote host closed the connection).
21:48:22 -!- TodPunk has quit (Read error: Connection reset by peer).
21:48:51 -!- TodPunk has joined.
21:52:28 -!- TodPunk has quit (Read error: Connection reset by peer).
21:52:50 -!- TodPunk has joined.
21:56:17 -!- TodPunk has quit (Read error: Connection reset by peer).
21:56:47 -!- TodPunk has joined.
21:58:18 -!- augur has joined.
22:01:59 -!- TodPunk has quit (Read error: Connection reset by peer).
22:02:20 -!- TodPunk has joined.
22:02:53 -!- TodPunk has quit (Read error: Connection reset by peer).
22:03:22 -!- TodPunk has joined.
22:03:42 <HackEgo> [wiki] [[Container]] N http://esolangs.org/w/index.php?oldid=40912 * Por gammer * (+1929) Created page with ""Container" is an esoteric programming language created by the user [[user:Por Gammer]]. The language models a finite set of nonnegative integers (denominated "containers") th..."
22:04:19 -!- augur has quit (Remote host closed the connection).
22:07:41 -!- TodPunk has quit (Read error: Connection reset by peer).
22:08:02 -!- TodPunk has joined.
22:12:15 <FreeFull> http://esolangs.org/wiki/Dimensions There isn't an implementation for this language, is there
22:13:35 <FreeFull> Well, it didn't seem to have existed at all before the 8th of november
22:14:18 <FreeFull> I imagine it needs to be implemented in some sort of sparse manner
22:14:19 <S1> I'd like to see one, too
22:16:50 <FreeFull> If you constrain yourself to just two cells in every direction, that's 2^52 cells
22:17:08 <Bicyclidine> the problem of dimensionality, they call it.
22:17:32 <S1> as if it was allocated all at once
22:17:46 <S1> Bicyclidine: n-funge is not listed on esolang wiki, is it?
22:18:49 <Bicyclidine> there's not a lot to specify, really, just add one instruction for arbitrary velocity and then two for each dimension
22:20:14 <FreeFull> https://sbjoshi.wordpress.com/2013/03/27/paradox-about-high-dimensional-spheres/ High-dimensional stuff is weird
22:20:18 <S1> Bicyclidine: this one? http://esolangs.org/wiki/Fungeoid
22:20:48 <Bicyclidine> "The closest relative, and most direct extension, of Befunge-93 is Befunge-98 of the Funge-98 family of languages. Each Funge extends the central concepts of Befunge to a given number of dimensions (for example, Unefunge is one-dimensional, Trefunge is three-dimensional, Nefunge is n-dimensional, etc.). "
22:20:48 <S1> I meant the n-funge one
22:21:20 <FireFly> http://arxiv.org/ftp/arxiv/papers/1110/1110.2832.pdf this is a succint abstract
22:24:56 <S1> The paradox is cool
22:26:31 <FireFly> Unefunge and Trefunge are specified in spec98 (in addition to Befunge-98)
22:50:58 <S1> The Hello World example in 'Dimensions' is so lame
22:51:24 -!- FreeFull has quit (Ping timeout: 250 seconds).
22:51:30 -!- mihow has quit (Quit: mihow).
22:52:31 -!- Bicyclidine has quit (Ping timeout: 258 seconds).
22:53:07 -!- FreeFull has joined.
22:53:19 -!- AnotherTest has quit (Remote host closed the connection).
22:54:52 -!- CADD has joined.
22:57:42 -!- vanila has quit (Remote host closed the connection).
23:02:51 -!- vanila has joined.
23:03:22 -!- Bicyclidine has joined.
23:09:44 -!- Sgeo_ has quit (Ping timeout: 264 seconds).
23:09:47 -!- augur has joined.
23:10:57 -!- augur has quit (Read error: Connection reset by peer).
23:11:05 -!- augur has joined.
23:12:06 -!- oerjan has joined.
23:13:31 -!- Sgeo has joined.
23:16:40 <Sgeo> No one here's talking about .NET?
23:17:12 <zzo38> I don't know a lot about .NET
23:17:15 <S1> it's not a language
23:17:50 <S1> russian .net?
23:18:38 <oerjan> Bicyclidine: but .no is norway
23:19:52 <Sgeo> `quote cross-platform
23:19:57 <shachaf> boily keeps asking, but people respond with neither coördinates norway
23:20:01 <HackEgo> 50) <Sgeo> What else is there to vim besides editing commands? \ 63) <Sgeo|web> Where's the link to the log? <lament> THERE'S NO LOG. YOUR REQUEST IS SUSPICIOUS AND HAS BEEN LOGGED. \ 93) <pikhq> And... WTF is it doing. <pikhq> :( <Sgeo_> Is it sexing? \ 102) <coppro> what's the data of? [...] <Sgeo> Locations in a now deceased game called Mutat
23:20:13 <Sgeo> `quote microsoft
23:20:13 <HackEgo> 116) <Sgeo> Why shouldn't I just do everything in non-Microsoft-specific C#? <ais523> it's like trying to write non-IE-specific JavaScript with only Microsoft documentation and only IE to test on \ 247) * Received a CTCP VERSION from nyuszika7h * VERSION Microsoft IRC# 2011 64-bit (Windows 8 Beta, x64, 2GB RAM) <nyuszika7h> Gregor: Windows 8 Be
23:20:21 <Sgeo> 116 no longer applicable?
23:21:17 -!- centrinia has joined.
23:21:45 <Gregor> I'm cautiously optimistic about open .NET.
23:23:39 <oerjan> shachaf: your pun israelly bad but doesn't deserve a swat
23:25:58 <oerjan> S1: when it comes to puns, i'm german
23:32:27 <HackEgo> 247) * Received a CTCP VERSION from nyuszika7h * VERSION Microsoft IRC# 2011 64-bit (Windows 8 Beta, x64, 2GB RAM) <nyuszika7h> Gregor: Windows 8 Beta? o_O <Gregor> A small benefit of my brief time as an intern at MS.
23:32:35 <shachaf> oerjan: what do i gotta do to fuel my swat masochism
23:33:07 <int-e> I guess that quote is a bit dated
23:33:11 <oerjan> i guess you could join a swat team
23:33:26 <elliott> whoa, nyuszika7h has been here before?
23:34:27 <int-e> lambdabot: have you been good today?
23:42:57 -!- Sprocklem has joined.
23:43:05 <int-e> Oh Agatha has a hard time second-guessing herself, but at least she's trying :)
23:44:20 <int-e> Also we've seen a pile of metal that needs scrapping fairly recently. The possibilities!
23:47:44 -!- `^_^v has quit (Ping timeout: 250 seconds).
23:50:27 -!- S1 has quit (Read error: Connection reset by peer).
23:50:56 -!- S1 has joined.
23:57:43 -!- MDude has joined.
00:01:38 -!- Bicyclidine has quit (Ping timeout: 256 seconds).
00:03:28 -!- Bicyclidine has joined.
00:07:56 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
00:12:18 <HackEgo> 55) * oerjan swats FireFly since he's easier to hit -----### <FireFly> Meh * FireFly dies \ 1085) <fungot> boily: so i guess a really savvy glass programmer could make some money, maybe start a home based business of a profiler to spot outright dead code. macro-generated code often has big swaths of it. i'd hate learning cobol and fortran just fo
00:12:34 <int-e> `quote mapole | wc -l
00:12:40 <int-e> ` ` quote mapole | wc -l
00:12:40 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
00:12:41 <int-e> `` quote mapole | wc -l
00:12:43 <FireFly> Huh, is that quote _that_ old
00:13:04 <int-e> There are no mapole quotes?!
00:13:12 <Jafet> `run quote mapole | wc -l
00:13:19 * int-e wants to hit something.
00:13:34 <int-e> Jafet: `` and `run are pretty much the same
00:13:46 <int-e> (except that `run seems to be built into HackEgo)
00:14:18 <FireFly> I kind-of want to add "There are no mapole quotes?!" to the qdb
00:14:39 <int-e> You have to get it past the mods.
00:15:40 <HackEgo> A mapole is a thwackamacallit built from maple according to Canadian standards.
00:20:09 -!- Bicyclidine has joined.
00:27:44 -!- FreeFull has quit (Ping timeout: 264 seconds).
00:38:09 -!- Nonduira has joined.
00:40:19 -!- Nonduira has quit (Read error: Connection reset by peer).
00:41:35 -!- Phantom_Hoover has joined.
01:02:45 <HackEgo> 1) <Slereah> EgoBot just opened a chat session with me to say "bork bork bork"
01:02:55 <HackEgo> 2) <Quas_NaArt> Hmmm... My fingers and tongue seem to be as quick as ever, but my lips have definitely weakened... <Quas_NaArt> More practice is in order.
01:09:07 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
01:10:41 <Sgeo> Person who keeps endorsing me for stuff on LinkedIn just endorsed me for PHP
01:10:52 <Sgeo> Now I'm certain they're just clicking endorse all the time
01:11:04 <shachaf> copumpkin endorsed me for PHP as a joke.
01:11:07 -!- Bicyclidine has joined.
01:11:56 <shachaf> copumpkin: if i get a php job i'll blame you
01:12:20 <copumpkin> hah okay I'll keep that in mind :)
01:34:43 * oerjan swats FireFly for linking to an arxiv pdf instead of the abstract page -----###
01:35:04 -!- Bicyclidine has quit (Ping timeout: 258 seconds).
01:35:11 <oerjan> (which would have been http://arxiv.org/abs/1110.2832 hth)
01:36:31 <oerjan> he has special swatter attraction powers
01:36:47 <oerjan> (also, you _should_ always link to the abstract hth)
01:38:32 <shachaf> http://www.theautochannel.com/news/2006/01/17/207546.1-lg.jpg hth
01:43:12 * oerjan swats shachaf -----###
01:43:24 <oerjan> only because it took me far too long to get it
01:43:56 -!- HackEgo has quit (Remote host closed the connection).
01:49:49 <Sgeo> I don't get it
01:58:54 <zzo38> Make up more kind of pokemon cards, including SUPER IMPOSTER PROFESSOR OAK and RANDOM ENERGY and so on.
01:59:58 <shachaf> What does SUPER IMPOSTER PROFESSOR OAK do?
02:00:10 <shachaf> And is it the same as IMPOSTER SUPER PROFESSOR OAK?
02:00:19 <shachaf> (Make up that kind of card too.)
02:00:22 <zzo38> Opponent can draw ten cards, I suppose, instead of just seven.
02:00:56 <zzo38> (Sort of like how SUPER POTION can remove two damage and SUPER ENERGY REMOVAL can remove two opponent's energy cards.)
02:01:14 <shachaf> I don't know how Pokémon cards work.
02:01:54 -!- MoALTz has quit (Read error: Connection reset by peer).
02:03:01 -!- MoALTz has joined.
02:03:34 <zzo38> (Actually SUPER POTION remove four damage; the normal POTION can take out just one damage)
02:04:37 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
02:04:48 <FireFly> oerjan: probably a good idea, but I saw a link to the pdf elsewhere
02:06:09 <FireFly> That is, two damage counters
02:10:09 <oerjan> Sgeo: he didn't link to the abstract, but <fill in here>
02:11:10 <zzo38> FireFly: Yes, two damage counters. I know that; I just made a second mistake somehow, I don't know why
02:15:49 -!- coppro_ has joined.
02:16:03 -!- coppro has quit (Ping timeout: 258 seconds).
02:16:37 -!- MoALTz_ has joined.
02:17:11 -!- coppro_ has changed nick to coppro.
02:19:32 -!- MoALTz has quit (Ping timeout: 258 seconds).
02:30:28 -!- shikhout has joined.
02:32:53 -!- yiyus_ has joined.
02:33:02 -!- MoALTz__ has joined.
02:33:27 -!- shikhin has quit (Ping timeout: 245 seconds).
02:33:50 -!- viznut_ has joined.
02:36:43 -!- yiyus has quit (Ping timeout: 258 seconds).
02:36:43 -!- viznut has quit (Ping timeout: 258 seconds).
02:36:43 -!- MoALTz_ has quit (Ping timeout: 258 seconds).
02:57:53 -!- oerjan has quit (Quit: leaving).
02:58:28 -!- CADD has quit (Quit: Lost terminal).
03:09:32 -!- MoALTz has joined.
03:12:06 -!- MoALTz__ has quit (Ping timeout: 264 seconds).
03:12:57 <quintopia> zzo38: did you ever play Waving Hands
03:13:14 <zzo38> quintopia: I have read about it
03:14:34 <quintopia> i want to find a way to play online (not email)
03:15:38 -!- bb010g has joined.
03:17:48 -!- zzo38 has quit (Ping timeout: 258 seconds).
03:22:52 -!- zzo38 has joined.
03:22:56 <zzo38> Did my message get through?
03:24:42 <Sgeo> Does F# have the weird method/function distinction Scala has where methods can do all sorts of things except be first class?
03:35:44 * Sgeo installs Visual Studio Community
03:37:58 -!- S1 has quit (Quit: S1).
03:40:49 <int-e> > map(map length.group)$replicateM 4[True,False] -- so wrong
03:40:50 <lambdabot> [[4],[3,1],[2,1,1],[2,2],[1,1,2],[1,1,1,1],[1,2,1],[1,3],[1,3],[1,2,1],[1,1,...
03:45:00 -!- gammaplexer has joined.
03:45:26 -!- gammaplexer has quit (Client Quit).
03:45:49 -!- gammaplexer has joined.
03:46:11 -!- gammaplexer has quit (Client Quit).
03:47:28 <coppro> Sgeo: is that scala thing due to the way the bitcode works?
03:47:49 <Sgeo> coppro: no idea
04:03:00 -!- adu has joined.
04:08:07 -!- MoALTz_ has joined.
04:09:12 -!- pikhq_ has joined.
04:09:29 -!- monotone_ has joined.
04:09:53 -!- coppro_ has joined.
04:12:03 -!- coppro has quit (Disconnected by services).
04:12:06 -!- coppro_ has changed nick to coppro.
04:12:31 -!- erdic_ has joined.
04:12:36 -!- Vorpal_ has joined.
04:12:37 -!- Vorpal_ has quit (Changing host).
04:12:37 -!- Vorpal_ has joined.
04:12:38 -!- InvalidC1 has joined.
04:12:40 -!- conehead has quit (Ping timeout: 272 seconds).
04:12:42 -!- pikhq has quit (Ping timeout: 272 seconds).
04:12:43 -!- monotone has quit (Ping timeout: 272 seconds).
04:12:47 -!- yiyus_ has quit (Ping timeout: 272 seconds).
04:12:48 -!- scounder has quit (Ping timeout: 272 seconds).
04:12:53 -!- MoALTz has quit (Ping timeout: 272 seconds).
04:12:56 -!- idris-bot has quit (Ping timeout: 272 seconds).
04:12:56 -!- erdic has quit (Ping timeout: 272 seconds).
04:12:56 -!- Vorpal has quit (Ping timeout: 272 seconds).
04:12:58 -!- ion has quit (Ping timeout: 272 seconds).
04:12:58 -!- InvalidCo has quit (Ping timeout: 272 seconds).
04:13:05 -!- shikhout has quit (Ping timeout: 244 seconds).
04:13:06 -!- yiyus has joined.
04:13:35 -!- erdic_ has changed nick to erdic.
04:13:50 -!- conehead has joined.
04:14:08 -!- ion has joined.
04:14:19 -!- Sgeo has quit (Read error: Connection reset by peer).
04:27:14 -!- Sgeo has joined.
04:43:34 -!- scounder has joined.
04:52:24 <zzo38> Why does the AI in Pokemon Card GB2 use FULL HEAL ENERGY so badly? Just now, while their active pokemon card was confused, they instead attached it to a bench pokemon card which requires only electric energy for its attacks.
04:52:32 <zzo38> (That card could not evolve, either.)
04:57:02 <HackEgo> [wiki] [[ATZ]] M http://esolangs.org/w/index.php?diff=40913&oldid=40907 * Thatguy25252525 * (+157)
04:57:22 <HackEgo> [wiki] [[ATZ]] http://esolangs.org/w/index.php?diff=40914&oldid=40913 * Thatguy25252525 * (+1)
05:11:11 -!- Frooxius has quit (Ping timeout: 240 seconds).
05:12:29 <J_Arcane> zzo38: AI was pretty bad in the first one too, and actively cheated. Never played GB2 though, didn't read Japanese.
05:13:15 <zzo38> Yes, although in the new one it is even worse; they run out of cards too often.
05:13:56 <zzo38> (First one also had no FULL HEAL ENERGY card.)
05:16:20 <HackEgo> [wiki] [[ATZ]] http://esolangs.org/w/index.php?diff=40915&oldid=40914 * Thatguy25252525 * (+0)
05:16:35 <zzo38> But maybe even the AI for cheating is bad.
05:23:16 -!- centrinia has quit (Ping timeout: 265 seconds).
05:25:07 -!- vanila has quit (Quit: Leaving).
05:25:24 -!- adu has quit (Quit: adu).
06:05:19 <quintopia> zzo38: why don't you write your own AI for it. i bet you could make one that doesn't suck
06:10:17 <zzo38> quintopia: I am not so good at writing AI
06:19:03 -!- DTSCode has changed nick to dTSCode.
06:40:13 <zzo38> nyuszika7h: What what?
06:41:14 <nyuszika7h> 00:33:11 <elliott> whoa, nyuszika7h has been here before? <-- yeah, I was here before, though I don't seem to remember that quote :P
06:55:22 -!- dTSCode has changed nick to DTSCode.
07:01:20 -!- InvalidC1 has changed nick to InvalidCo.
07:27:10 -!- MDude has changed nick to MDream.
07:31:10 -!- centrinia has joined.
08:04:26 -!- Phantom_Hoover has joined.
08:05:23 <HackEgo> [wiki] [[Talk:Portal 2]] N http://esolangs.org/w/index.php?oldid=40916 * Rdebath * (+357) /* Is this proven TC ? */ new section
08:15:17 -!- MoALTz__ has joined.
08:17:34 -!- MoALTz__ has quit (Read error: Connection reset by peer).
08:18:08 -!- MoALTz_ has quit (Ping timeout: 250 seconds).
08:18:35 -!- clog has quit (Ping timeout: 255 seconds).
08:37:20 <mroman> Skill-project.org has a limit on children?
08:43:01 <mroman> how am I supposed to add thousands of programming languages then .
08:47:33 <HackEgo> [wiki] [[Special:Log/newusers]] create * Luser droog * New user account
08:52:24 -!- MoALTz has joined.
09:03:15 <shachaf> Bike: oh, now that dual space thing makes sense to me
09:11:08 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:23:25 <J_Arcane> http://blogs.wsj.com/digits/2014/11/12/wearable-power-assist-device-goes-on-sale-in-japan/
09:29:23 <HackEgo> [wiki] [[Inca]] N http://esolangs.org/w/index.php?oldid=40917 * Luser droog * (+2104) apl-based ascii language
09:39:27 <Sgeo> http://www.planetary.org/blogs/emily-lakdawalla/2007/1227.html
09:42:13 -!- S1 has joined.
10:11:18 <myname> is there anything i should read if i want to do lexing on languages with 2 (or more) dimensions?
10:15:44 -!- erdic has quit (Ping timeout: 264 seconds).
10:17:16 -!- erdic has joined.
10:18:06 -!- clog has joined.
10:21:35 <mroman> myname: to create tokens?
10:22:10 <myname> well, i guess it have to be a graph, but basically yes
10:22:27 <mroman> but it depends if you can do arbitrary jumps to 2D locations or not
10:22:52 <mroman> if you can just branch upwards/downwards/left/right I use branches in graphs
10:24:20 <mroman> http://codepad.org/Um7WWfsN <- like that
10:24:34 <mroman> that way compilation is not that inconvenient
10:24:40 <mroman> if you have arbitrary jumps to locations
10:24:57 <mroman> compilation is very not so cenvenient anymore
10:30:42 <myname> i know, i already did that
10:31:17 <myname> the point is, i want to write about it and would like to read other stuff if available
10:34:54 <fizzie> "How do you organize a space party?" "You planet." Gah, these emails have oerjan-level puns.
10:46:20 -!- S1 has changed nick to S0.
10:46:53 -!- S1 has joined.
11:01:45 -!- MoALTz_ has joined.
11:04:26 -!- myname has quit (Ping timeout: 244 seconds).
11:04:27 -!- FreeFull has joined.
11:04:57 -!- MoALTz has quit (Ping timeout: 244 seconds).
11:05:23 -!- myname has joined.
11:11:58 <J_Arcane> yaaaay for the endless recycling of the print keyword.
11:13:19 * J_Arcane is dealing with a name clash decision.
11:13:35 <J_Arcane> I have to decide which style of 'printing' Heresy's PRINT actually stands for.
11:14:00 <mroman> if it should produce foo or "foo"
11:14:28 <J_Arcane> BASIC just has PRINT, which roughly corresponds to how display works in Racket. But Racet also has print and write, both of which are pretty important.
11:14:46 <J_Arcane> mroman: Exactly. eg. file:///C:/Program%20Files/Racket/doc/guide/read-write.html?q=input
11:14:55 <J_Arcane> Whoops, forgot, local webdocs.
11:15:03 <mroman> just give me access to your computer please ;)
11:15:31 <mroman> http://docs.racket-lang.org/guide/read-write.html
11:16:18 <b_jonas> actually, basic also has PRINT and WRITE
11:16:22 <b_jonas> at least some variants of basic
11:16:26 <b_jonas> and it also has PRINT USING
11:16:35 -!- boily has joined.
11:16:45 <mroman> but WRITE is usally to file?
11:16:48 <J_Arcane> I forgot PRINT USING, though WRITE is a file I/O command usually isn't it?
11:16:57 <b_jonas> basic WRITE prints strings double-quoted so it's easier to read back,
11:17:04 <b_jonas> or was that a different command?
11:17:15 <b_jonas> there's _four_ write commands, three of which can work to both stdout adn file
11:17:19 <b_jonas> one is PRINT whcih prints normally,
11:17:30 <b_jonas> one prints strings double-quoted so its' easier to read back
11:17:44 <b_jonas> PRINT USING prints with formatting,
11:18:27 <b_jonas> and there's one that prints fixed fields which works a bit magically: it involves preparing a buffer with another command such that some strings point _into_ that field and you must not reallocate them but only assign their contents with LSET, and then the command just writes the buffer
11:18:50 <b_jonas> but I'm not sure whcih of these two other commands is WRITE and what's the other one called
11:19:43 <b_jonas> three of these can be used pritning to stdout, or to a filehandle like PRINT#3,FOO where #3 is the file descriptor number, or to the line printer like LPRINT
11:19:56 <b_jonas> and of course this all depends on the variant of basic
11:22:28 <J_Arcane> ECMA Standard BASIC has READ as well. XD
11:23:04 <fizzie> QBasic has PRINT, PRINT USING (to screen or file), LPRINT, LPRINT USING (to printer in LPT1), WRITE (to screen or file).
11:24:17 <fizzie> But that's only to file, I think.
11:25:15 <J_Arcane> Oh weird, PRINT USING in ECMA is basically PRINTF, instead of like defining an output port.
11:25:29 <fizzie> You can PUT any variable, not just the (LSET/RSET) random-access buffer.
11:25:58 <J_Arcane> And it's a two line statement ...
11:27:53 <fizzie> And confusingly enough, READ does not (arguably) do any I/O, since it only reads values specified by DATA statements.
11:28:09 <b_jonas> PRINT USING is always like printf, but with different directives
11:30:05 <J_Arcane> I don't recall ever learning that use case, and I don't think older MS BASICs had it.
11:30:36 <J_Arcane> In ECMA it's a two statement pair: PRINT USING values, then IMAGE string-templat.
11:34:21 <J_Arcane> That's the trouble with BASIC, there never really was a standard anyone actually followed. MS was almost more standard than ANSI or ECMA, it's what most followed.
11:39:33 <b_jonas> J_Arcane: I believe GWBASIC has PRINT USING too
11:43:58 <viznut_> i once read the basic standard and it was full of mind-boggling stuff i never saw implemented anywhere
11:45:44 <viznut_> "let" was mandatory but iirc there was also another alternative for "let" that could be used for defining vectors
11:48:58 <b_jonas> alternative for LET? like DIM or some other keyword for declaring variables, or SET for assigning object identify, or READ?
11:49:17 <b_jonas> mandatory LET is implemented in some basics of course
11:49:29 <J_Arcane> Yes. The standards define a MAT keyword that's used for defining all kinds of stuff to do with arrays.
11:49:38 <J_Arcane> There's even a MAT INPUT in ECMA.
11:49:51 <b_jonas> well, there's so many basics that it's hard to be sure about "not implemented anywhere"
11:50:13 <J_Arcane> Yeah. There are a few standards compliant implementations but they were never particularly popular I don't think.
11:51:00 <b_jonas> that could be because BASIC is or was popular not because it's a good language, but because it came with some personal computers, or bundled as a macro language into some programs (think of WordBasic, Visual Basic, and CorelScript)
11:51:32 <b_jonas> I mean, BASIC was a not too insane language back when it was created, because it was small enough and easy to learn
11:51:48 <viznut_> microcomputer implementations were dominated by microsoft that defined things in its own way
11:51:56 <J_Arcane> Yeah. IT was easy to write and implement for certain kinds of computers, and was relatively easy to 'get'; it's hyper imperative code at its core, which in a weird way makes it easy to follow until programs get large.
11:52:11 <viznut_> even if a microcomputer basic wasn't actually from microsoft it was usually modelled after ms-basic
11:53:39 <viznut_> and basic was popular in early microcomputers not only because of microsoft but also because the pioneers had often used a time-shared mainframe basic in university/college
11:54:11 <J_Arcane> b_jonas: Yeah; in its original form it was just for solving simple algebra problems, it was often the first language or only language new students were exposed to, because they'd use it for math classes and such.
12:06:18 <mroman> nowadays they use fortran .
12:08:13 -!- oerjan has joined.
12:10:16 -!- S1 has quit (Ping timeout: 244 seconds).
12:16:03 -!- S1 has joined.
12:30:32 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
12:33:39 -!- boily has quit (Quit: TOADY CHICKEN).
12:36:18 -!- S1 has quit (Quit: S1).
12:36:36 -!- S0 has changed nick to S1.
12:42:13 <J_Arcane> Part of me thinks I should just say fuck it and stick to a saner mapping direct to Lisp, PRINT = PRINT, INPUT = READ, though that does mean that Heresy would thus have an IEPD (input-eval-print-doloop)..
12:44:19 <fizzie> Improvised explosive printing device.
12:46:24 <J_Arcane> I actually haven't decided on the loop conventions yet either. It's a functional dialect, so a lot of them are worthless.
12:47:58 <b_jonas> J_Arcane: what are you making?
12:48:42 <J_Arcane> b_jonas: to practice macros and teach myself better FP/Lisp fundamentals, I'm implementing a LISP/BASIC hybrid lang called Heresy.
12:49:29 <J_Arcane> Mostly for the novelty, but it could be an interesting tool for getting BASIC programmers into trying Lisp.
12:51:56 <J_Arcane> Still on notes and tinkering stage now, but I think I'll have enough to write a draft definition of the core language soon.
12:52:35 <b_jonas> J_Arcane: um, how does that want to work? BASIC-like syntax with more functions, including statements turned to functions, or lisp-like syntax
12:53:12 <J_Arcane> It's mostly LISP syntax, with BASIC keywords and extra sugar.
12:55:43 <J_Arcane> I'm aiming to do this as a Racket #lang module, so a lot of stuff is 'for free'.
12:56:46 <mroman> I'm sure BASIC programmers will either say one of these two things
12:56:56 <mroman> a.) Too many parantheses.
12:57:15 <mroman> b.) Where's Console.Out.WriteLine
12:57:33 <mroman> hm. Console.WriteLine actually
12:57:46 <J_Arcane> Well, I'm shooting less for the VB crowd than the FreeBASIC heads; there's actually some Lisp curiosity in that crowd. :D
12:58:08 <mroman> It's been a long time since my VB.NET days
12:58:09 <J_Arcane> FB has TCO now, and a couple different Lisp implementations, one of them embeddable.
12:58:20 <J_Arcane> I stayed the hell away from VB. XD
12:58:39 <mroman> It's a beautiful language once you learn to hate and love it at the same time.
12:59:03 <mroman> fwiw it has all the features you need to program ;)
13:00:11 <b_jonas> mroman: such as the way to shell out to a real program?
13:01:18 <b_jonas> right. so you can just write your program in (your favourite language) and then run it
13:01:53 <mroman> But calling a VB.NET program inside a VB.NET program sounds pretty useless.
13:02:24 <fungot> mroman: fair enough. if she knew she'd just rest. :p
13:02:44 <elliott> J_Arcane: see, and here my associations are, like, QBASIC
13:02:57 <fungot> mroman: shall we proceed?
13:03:01 <elliott> VB and FreeBASIC and all that are so... depressingly capable
13:03:41 <J_Arcane> elliott: Yeah, I grew up on MS and QBASIC.
13:03:48 <mroman> Does VB allow to define casts?
13:04:16 <b_jonas> FORI=1TO16:FUNGOT(I)=0:NEXTI
13:04:31 <HackEgo> [wiki] [[Container]] http://esolangs.org/w/index.php?diff=40918&oldid=40912 * 177.193.194.37 * (-45) /* Execution */
13:04:51 <mroman> but you have to use CType
13:05:38 <mroman> b_jonas: Public Shared Narrowing Operator CType(...)
13:05:51 <mroman> or Public Shared Widening Operator CType...
13:06:52 <b_jonas> mroman: I don't understand what that means
13:07:17 <mroman> or "Conversion Operator" if you're more familiar with that terminology
13:07:19 <J_Arcane> elliott: FreeBASIC is, strictly speaking, still a QB at heart, just one that was introduced to real programmers at some point who started wanting it to actually be useful agian. ;)
13:07:33 <J_Arcane> There's even recursive macros in FreeBASIC now apparently.
13:07:46 <elliott> J_Arcane: let me guess, it has ghastly OOP extensions :)
13:07:47 <mroman> i.e. if you create a data structure you can define a cast from string to your data structure
13:08:11 <J_Arcane> elliott: I'm not sure, but possibly, it does have partial C++ lib support.
13:08:23 <mroman> Brainfuckprogram prog = (Brainfuckprogram)"+++.";
13:08:41 <elliott> I think QBASIC has structs...
13:08:42 <mroman> VB has prog = CType("+++.", Brainfuckprogram)
13:09:16 <J_Arcane> I don't think MS got structs until VB
13:09:36 <elliott> ok, let me dig up fizzie's qbasic manual
13:10:03 <b_jonas> mroman: so can you also do like `dim prog as brainfuckprogram : prog = "+++."'
13:10:15 <mroman> you can define implicit casts
13:10:30 <elliott> J_Arcane: it does: http://gamma.zem.fi/~fis/qbc.html#QEw4MDg3
13:10:37 <b_jonas> and does it let automatically cast as you pass an argument to a function that requires a particular type?
13:10:39 <elliott> J_Arcane: just nobody used them. or procedures, for that matter. :p
13:10:49 <J_Arcane> yeah, I never knew about them.
13:10:54 <mroman> b_jonas: it should with implicit casts yes
13:11:18 <mroman> think of all the great things you can do with this
13:11:21 <J_Arcane> Probably a 4.5 or 7 feature; most people only used the QB 1.1 that came with DOS
13:11:33 <mroman> (VB uses narrowing/widening as keywords, C# uses explicit/implicit as keywords)
13:11:39 <elliott> http://gamma.zem.fi/~fis/qbc.html#QEw4MDIz you could even do things like this
13:11:57 <elliott> hmm, I thought fizzie's manual was some old version
13:12:14 <elliott> Fast program execution Use a Basic compiler (such as Microsoft
13:12:14 <elliott> Visual Basic for MS-DOS) to translate your
13:12:14 <elliott> Basic code into native machine code.
13:12:16 <elliott> visual basic for ms-dos...
13:12:43 <mroman> (http://msdn.microsoft.com/en-us/library/z5z9kes2.aspx)
13:12:57 <mroman> also VB uses Shared for "static"
13:13:06 <J_Arcane> elliott: Hmm, yeah, Guess it must be, because it lacks switches for command line compliation, and has /EDITOR.
13:13:36 <elliott> I think it was basically just that nobody knew or cared about the fancier stuff it has
13:13:40 <mroman> Does anyone plan on porting .NET to MS-DOS?
13:13:47 <elliott> so everyone remembers it as being goto global soup hell
13:14:12 <elliott> like, "Line numbers, a concept often associated with BASIC, are supported for compatibility, but are not considered good form, having been replaced by descriptive line labels.[1]" ha ha
13:14:21 <J_Arcane> elliott: Yeah, it was always a weird hybrid thing, and the typing system in particular could be pretty hairy if you engaged with it responsibly.
13:14:45 <J_Arcane> I didn't even use line labels after a very short time.
13:14:55 <J_Arcane> I was in looove with the IDE for subroutines.
13:15:06 <elliott> you filthy structured programmer.
13:16:21 <b_jonas> mroman: isn't "SHARED" for global variables and "STATIC" for static?
13:16:46 <J_Arcane> elliott: Honestly, if I refactored out some of my old code from the MS BASIC days it would look pretty similar. I tended to prefer GOSUB to GOTO.
13:18:44 <elliott> I don't even remember which BASICs I used as a kid. I definitely used QBASIC but I don't know if I actually got much programming done with it.
13:18:51 <elliott> it took until the ripe old age of 8 for me to start really programming
13:20:30 <elliott> I do remember writing out some long program that did pretty things on the screen from a book REALLY CAREFULLY. I forget which computer that was even for though. it wasn't an atari or a c64... *maybe* it was a bbc micro? but I don't think so... oh, possibly an Amstrad?
13:20:54 <J_Arcane> I was lucky, I started with the CoCo3. Tandy manuals in those days were *amazing* learning books. Huge, detailed, easy to read.
13:21:18 <elliott> (note: this would have been, like, 1998 or later. :p)
13:21:24 -!- monotone_ has changed nick to polytone.
13:21:45 <J_Arcane> But then later on high school finished, and I decided that I liked computers too much to do them for a living. I didn't want to not like them anymore.
13:22:01 <J_Arcane> In my mind, making them 'work' would suck out all the fun.
13:22:10 <elliott> I managed to not like them without work...
13:22:46 -!- adu has joined.
13:23:05 -!- adu has quit (Client Quit).
13:23:10 <b_jonas> J_Arcane: did you revise that decision later and end up working with computers anyway?
13:23:28 <J_Arcane> b_jonas: That's kinda what I've been fumbling about attempting to do now.
13:23:45 <b_jonas> good, come join the dark side!
13:23:49 <J_Arcane> I actually wound up falling into cooking for about 10 years, then uni and tabletop RPG design.
13:27:12 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
13:27:19 <fungot> FireFly: not its offtopicness. that doesn't give you alt text. such is life
13:27:26 <J_Arcane> I am a hopelessly infatuated aspiring Scheme programmer with some entry-level Python skills as well.
13:28:23 <J_Arcane> b_jonas: yup. I cooked for a living for most of a decade.
13:29:12 <FireFly> So uh, obviously you'd be very proficient in the Chef language
13:29:32 <mroman> but no Job offers so far.
13:30:01 <HackEgo> [wiki] [[Container]] http://esolangs.org/w/index.php?diff=40919&oldid=40918 * 177.193.194.37 * (+0) /* Execution */
13:30:22 <b_jonas> mroman: is that like that webpage we found last time that advertized befunge certifications?
13:31:54 <fizzie> You had to use the menus for defining procedures, or so I vaguely recall.
13:32:13 <elliott> fizzie: pretty sure typingw orked
13:32:14 <fizzie> (Is there big money in tabletop RPG design?)
13:32:19 <elliott> but then you got shoved into a mini-editor thing
13:32:21 <J_Arcane> Yeah, unfortunately I became a Lisp convert *after* I moved to a country with virtually zero Lisp programmers in it.
13:32:27 <elliott> it's, like, structural editing!
13:32:43 <b_jonas> fizzie: this is about what IDE or something?
13:32:46 <elliott> I guess fizzie's university did stop using SICP.
13:32:54 <fizzie> b_jonas: The QBasic one.
13:33:06 <fizzie> J_Arcane: F-Secure was famously looking for Scheme programmers in their job ads.
13:33:14 <fizzie> J_Arcane: Ten years ago, though.
13:33:15 <b_jonas> fizzie: actually, in qbasic, you can create a sub/function by just typing its head,
13:33:35 <b_jonas> but then either you have to switch between subs from the dialog box, or switch that option that makes the whole source code show up together
13:33:36 <J_Arcane> There are fuckall Lispers here seems like. One CL shop, a couple Clojure shops. A lot of Haskellers and Erlangers though.
13:33:52 <J_Arcane> FP is kinda popular here, just not in Lisp form necessarily.
13:33:55 <elliott> 3 lisp shops is pretty impressive :p
13:34:07 <elliott> I wonder hwo many there are in the UK.
13:34:31 <b_jonas> J_Arcane: doesn't matter. it's not just the languages that are important, but your theoretical understanding and competences. don't be affraid to get a non-scheme job.
13:35:02 <J_Arcane> b_jonas: I'm not afraid to, just not sure yet what I want to do, and kinda Java-phobic.
13:36:28 <b_jonas> yeah... that's understanible
13:36:55 <b_jonas> java is not a bad language (it's not a good one either), but java jobs want code monkeys
13:37:25 <J_Arcane> Java is everywhere here. In fact, if I don't want to go to uni after language school, my sole options from the trade school are either Java-EE or some buzzword nonsense about cloud architectures and so forth.
13:38:32 <b_jonas> and are you tied to your location by family or something?
13:39:17 <J_Arcane> I really like the city, and my wife is still in trade school for glasswork.
13:39:58 <mroman> buzzword nonsense is where them moneyz at.
13:40:34 <mroman> also as long as you just write code I don't really care in what language
13:40:36 <J_Arcane> mroman: True. And that one actually gives a CS qualification instead of just programming, IIUC.
13:41:36 -!- centrinia has quit (Ping timeout: 265 seconds).
13:43:43 <fizzie> J_Arcane: Were you in Tampere, or do I remember wrong?
13:44:14 <fizzie> I was there yesterday.
13:44:30 -!- visy_ has changed nick to visy.
13:44:31 <J_Arcane> We moved here for the language course.
13:45:50 <b_jonas> hmm, so how many esolangers do you have in Finland? there aren't more than in the UK, are there?
13:46:21 <J_Arcane> I dunno to be honest. THere's always a few Finns around on IRC though. They invented the place.
13:46:32 <elliott> there are tons of esolangers in finland
13:47:12 <fizzie> I quickly counted 7 in the nick list, but I could well have missed some.
13:47:24 <fizzie> Or 8 if fungot counts.
13:47:24 <fungot> fizzie: sometimes but very rarely, i think it has something to do with energy.
13:47:27 <elliott> at least 7 in here right now
13:48:04 <elliott> this channel started with finns I think
13:48:09 <elliott> well I guess lament isn't finnish
13:48:27 <elliott> I think it is because of the whole demoscene culture and everything.
13:48:39 <elliott> well, plus just finns being IRC addicts
13:48:52 <fizzie> I prefer the word "enthusiasts", thank you very much.
13:49:38 <J_Arcane> Yeah, still pretty active demoscene here.
13:51:26 <fizzie> My early logs show navigator with a .gr hostname, and lament, calamari and dbc from US-looking ISPs.
13:51:53 <fizzie> (And me and mooz from .fi.)
13:53:38 <fizzie> Saippuakivikauppias, you mean.
13:53:54 <fizzie> (Also: "menen kauppaan".)
13:54:02 <fizzie> (But: "tulen kaupasta".)
13:54:23 <fizzie> I'm sure there's a perfectly good reason for one to be pp and the other just p.
13:54:41 <elliott> fizzie: that's practically all finns.
13:55:21 <fizzie> "Sappikivi kippas" == "the gallstone tipped over".
13:56:52 <oerjan> fizzie: isn't that just that consonant gradation
13:57:44 <oerjan> perfectly regular, except i've learned recently that it's not always that
13:58:34 <oerjan> like, some centuries ago, it probably was perfectly regular, but then _more_ sound changes kept getting heaped on.
13:58:43 <fizzie> It might be regular, but the regulations aren't something one really thinks of.
13:59:25 <fizzie> "This sometimes creates difficulties in identifying the root (if the word is derived), because often seemingly basic words turn out to be derived, applying gradation in the process. For example, hake 'wood chippings gradates to hakkee-, not to *hae-, because it is already a gradated form (former *hak̆keh), derived from hakkaa- < 'hack' (whose infinitive is the weak grade haka|ta). However, ...
13:59:31 <fizzie> ... hake|a 'to get, to search' does gradate to hae-, as hake- is the original form."
14:00:08 <oerjan> and if what i vaguely hear about colloquial finnish is right, you'll soon be as complicated as estonian
14:03:38 <HackEgo> [wiki] [[Container]] http://esolangs.org/w/index.php?diff=40920&oldid=40919 * 177.193.194.37 * (+104) /* Execution */
14:08:52 -!- viznut_ has changed nick to viznut.
14:12:47 <oerjan> what, tatham's loopy puzzle can actually be zoomed by resizing?
14:12:53 <oerjan> this may change EVERYTHING
14:13:35 <oerjan> wtf is that humming noise
14:16:23 <oerjan> ok not everything. it is _still_ annoying to aim properly with my touchpad.
14:21:12 <oerjan> aka it's not precise, _and_ the buttons are not properly separated from the pointing area.
14:23:55 <HackEgo> [wiki] [[Container]] http://esolangs.org/w/index.php?diff=40921&oldid=40920 * 177.193.194.37 * (+48)
14:24:18 <HackEgo> [wiki] [[Dimensions]] M http://esolangs.org/w/index.php?diff=40922&oldid=40903 * Oerjan * (+1) /* See also */ bullets
14:24:42 -!- Sprocklem has quit (Ping timeout: 245 seconds).
14:25:10 <elliott> oerjan: I've offered to buy you a mouse before, right?
14:28:09 <HackEgo> [wiki] [[User talk:TomPN]] M http://esolangs.org/w/index.php?diff=40923&oldid=40863 * Oerjan * (+92) unsigned
14:28:51 <oerjan> but i cannot usefully use a mouse on my lap.
14:29:08 <oerjan> (also i have a mouse, i've just never used it.)
14:29:40 <oerjan> WTF IS THAT HUMMING SOUND
14:32:28 <oerjan> i suspect the neighbor's fridge.
14:33:13 <oerjan> the constructor workers have stopped, which only makes me go crazy at smaller noises instead.
14:35:19 <mroman> b_jonas: Philae actually bounced off the comet ;)
14:35:28 <HackEgo> [wiki] [[Musical notes]] M http://esolangs.org/w/index.php?diff=40924&oldid=40861 * Oerjan * (+1) /* See also */ bullets
14:37:19 <HackEgo> [wiki] [[Talk:ATZ]] http://esolangs.org/w/index.php?diff=40925&oldid=40910 * Thatguy25252525 * (-181) /* Documentation */
14:38:34 -!- vanila has joined.
14:38:49 <myname> int-e, oerjan: you are the ones that know everything, aren't you? do you know any kind of paper/article about lexing of 2d languages?
14:40:14 <mroman> Oerjan is known to do homework for people in here. So he *must* know a lot.
14:41:28 <oerjan> no, but i recall fizzie's jit thing compiled all four directions or something.
14:41:42 <oerjan> vanila: like befunge. see:
14:41:44 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
14:42:48 <mroman> myname: you can compile all columns and rows as well
14:43:15 <mroman> this will also allow you to do handle jumps to arbitrary locations without dynamic recompilation
14:43:26 <b_jonas> mroman: sure, but befunge is also self-modifying
14:43:43 <mroman> (if the language isn't self-modifying)
14:44:48 <mroman> although some forms of self-modification can be implemented by using fixed blocks of code for each instruction
14:44:53 <mroman> and then replace the blocks at runtime
14:45:11 <mroman> (which isn't really recompilation)
14:46:54 <mroman> (due to fixed size blocks there will be nops in the generated code though)
14:49:18 <mroman> either that or you can link blocks together with jumps
14:49:26 <mroman> and then just keep a jump table around
14:49:51 <mroman> I should test some day what is more efficient
14:58:59 <HackEgo> [wiki] [[Quantum Dimensions]] M http://esolangs.org/w/index.php?diff=40926&oldid=40905 * Oerjan * (+1) /* See also */ bullets
15:04:24 <HackEgo> [wiki] [[Talk:Main Page]] http://esolangs.org/w/index.php?diff=40927&oldid=40893 * Oerjan * (-577) /* ATZ */ See the first paragraph of this talk page; also, information already at [[ATZ]].
15:05:03 <oerjan> ion: hey _my_ name isn't a common suffix.
15:05:34 <oerjan> (kudos to anyone who can find a pre-existing language where it is.)
15:17:09 -!- S1 has quit (Ping timeout: 245 seconds).
15:17:43 -!- S1 has joined.
15:24:07 <mroman> @tell mroman applyRegexMatch
15:24:16 <mroman> I was trying to, you moron!
15:24:58 -!- vanila has quit (Quit: Leaving).
15:25:06 -!- `^_^v has joined.
15:29:51 <mroman> @tell blsqbot applyRegexMatch
15:32:44 <mroman> @tel qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq hi
15:33:08 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
15:33:16 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
15:33:21 <S1> why did tel work?
15:33:30 <mroman> lambdabot has auto-correction
15:33:32 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
15:34:15 <mroman> It's you know... so that people can feel funny asking lambdabot for massages
15:35:09 <mroman> fungot doesn't respond well to massage requestts
15:35:09 <fungot> mroman: http://video.google.com/ fnord
15:35:27 <mroman> It just tells you to go watch a video of massage on google
15:35:32 <FireFly> fungot: uh I think Google Videos is deprecated in favour of Youtube
15:35:34 <fungot> FireFly: shame there's no 68k emulator that does the same thing ( modulo the spaces))
15:36:08 <FireFly> 68k emulators ought to include google video playback in their feature set
15:39:48 <int-e> I should really implement channel-specific defaults JUST TO DISABLE THAT AUTOCORRECTION ON #esoteric...
15:40:40 <b_jonas> the jevalbot has one bit of per-channel setting, for enabling or disabling shortcut invocation
15:40:57 <int-e> But it's really nice for correcting some honest spelling mistakes.
15:43:16 -!- MDream has changed nick to MDude.
15:46:01 <elliott> int-e: just add a @massages-lewd command
15:46:05 <elliott> then all the corrections will be ambiguous
15:59:38 -!- drdanmaku has joined.
16:02:10 -!- ZombieAlive has joined.
16:09:43 -!- mihow has joined.
16:10:40 <J_Arcane> Oh. So that's what call/cc does.
16:11:18 -!- vanila has joined.
16:11:55 -!- scoofy has quit (Ping timeout: 265 seconds).
16:18:27 <HackEgo> [wiki] [[BitZ]] http://esolangs.org/w/index.php?diff=40928&oldid=25395 * 116.58.254.129 * (+17) /* I quoted the code, so the page looks better and is easier to navigate */
16:22:36 <elliott> J_Arcane: if you're saying that there's like a 60% chance you're not entirely certain of call/cc's semantics yet :p
16:22:53 <J_Arcane> elliott: Yes. That was too confident a statement.
16:23:13 <Bike> ((call/cc call/cc) (call/cc call/cc))
16:23:27 <J_Arcane> I only understand a fraction of some things that it can do, but they are specifically things that are useful with current internal questions about Heresy implementation.
16:23:35 <elliott> J_Arcane: If you would like some fun try and understand the interactions between call/cc and dynamic-wind
16:24:34 <elliott> or maybe it wasn't dynamic-wind.
16:24:39 <elliott> there was some complex interaction, anyway
16:25:11 <J_Arcane> Like, how you implement DO...LOOP and still be able to get out of it without mutatinng a variable.
16:25:39 <J_Arcane> It also makes the Racket web server library make a slight bit more sense now.
16:25:45 <elliott> J_Arcane: fully-fledged undelimited continuations are probably a bad choice for that if you have alternatives
16:25:51 <elliott> (inefficient, complex, dangerous)
16:26:12 <elliott> I'm pretty sure racket has delimited continuations, at least, though really breaking out of a loop is just exception semantics which are a really tiny subset of call/cc
16:26:15 <vanila> I don't even understand call/cc
16:26:21 <vanila> and ive been trying to for years
16:26:24 <J_Arcane> elliott: Yes, that is also a problem.
16:26:35 <J_Arcane> I'll have to look into some of the 'safer' options in Racket.
16:27:04 <elliott> http://okmij.org/ftp/continuations/against-callcc.html is a nice collection of polemic
16:27:07 <vanila> delimited continuations are much more conceptually simple and clear than calcc
16:28:02 <elliott> vanila: yeah but they're so much easier to understand, it's boring :p
16:29:43 <J_Arcane> elliott: *glances at dynamic-wind* aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
16:30:18 <elliott> dynamic-wind is like... "here's all the details of call/cc's havoc exposed to your program, good luck"
16:30:29 <elliott> it's like... try...finally : exceptions :: dynamic-wind : continuations
16:30:58 <Bike> kernel's dynamic wind equivalent is still nuts.
16:31:46 <Bike> what if you had dynamic wind and also included a tree of continuations
16:33:10 <Bike> there's this whole thing about continuations having parents and children
16:33:20 <Bike> i don't... really remember how it works, because what the fuck
16:34:07 <Bike> so the dynamic wind equivalent works by installing a handler for particular continuations, and then if that continuation or a child of it enters or exits (depending) the handler happens
16:34:47 <Bike> i think the best part was that one part of it was included and the explanation is like "well nothing else has this and i can't think of a use but it's symmetric and therefore beautiful"
16:36:55 <elliott> that's like me designing languages...
16:37:05 <Bike> it's like this entire channel! burn
16:44:05 -!- hjulle has quit (Ping timeout: 256 seconds).
17:04:15 -!- Primal has joined.
17:04:18 -!- oerjan has quit (Quit: sizzling hot languages).
17:05:34 <J_Arcane> Bike: Such is the way of Scheme sometimes. ;)
17:23:37 -!- HackEgo has joined.
17:24:00 <HackEgo> elliot: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
17:26:05 -!- Primal has quit.
17:28:47 -!- Frooxius has joined.
17:31:33 -!- Sprocklem has joined.
17:35:57 -!- Sprocklem has quit (Ping timeout: 245 seconds).
17:39:32 <fizzie> J_Arcane: Actually, now that I think of it, I think those Scheme jobs were at SSH Communications instead.
17:41:03 -!- dtscode_ has joined.
17:45:47 <mroman> what was that <<loop>> thing again?
17:51:17 <elliott> trivial stuff like fix id or let x = x in x will produce it
17:52:10 <int-e> "Hi, we've noticed all those threads waitinf for each other to finish a calculation. We've decided to put them out of their misery by delivering a Nontermination exception to each of them. Thank you for your attention and have a nice day."
17:52:13 <elliott> it's my face, with a tongue sticking out of it
17:52:23 <elliott> int-e: doesn't that have a different message?
17:53:17 <int-e> showsPrec _ NonTermination = showString "<<loop>>"
17:53:54 <mroman> Can ghci tell me where it loops?
17:54:32 <mroman> fucking useless ghci then
17:55:22 <J_Arcane> i'm still not sure what to do with them in Heresy.
17:56:10 <mroman> http://codepad.org/EqO83Zwt
17:57:42 <mroman> (I see the recursion of course)
17:57:49 <mroman> but it's a finite recursion on finite input
17:57:59 <mroman> I don't see a reason why this code won't terminate
17:58:52 <coppro> mroman: if you get an empty match
18:07:45 <elliott> I think you can get a backtrace
18:08:01 <elliott> you have to like compile your program with profiling and rtsopts then pass +RTS -xc
18:08:04 <elliott> and you get a really ugly backtrace
18:09:54 <int-e> henkma outdid him again
18:12:00 <S1> !help languages
18:12:01 <EgoBot> languages: Esoteric: 1l 2l adjust asm axo bch befunge befunge98 bf bf8 bf16 bf32 boolfuck cintercal clcintercal dimensifuck glass glypho haskell kipple lambda lazyk linguine malbolge pbrain perl qbf rail rhotor sadol sceql trigger udage01 underload unlambda whirl. Competitive: bfjoust fyb. Other: asm c cxx forth sh.
18:24:55 -!- dtscode_ has left.
18:24:57 -!- Phantom_Hoover has joined.
18:31:00 <nyuszika7h> since when are Haskell and Perl esoteric?
18:32:25 <Taneb> nyuszika7h, have you seen the average Haskell progam?
18:32:59 -!- LauraFinder has joined.
18:33:05 <S1> "intended for or likely to be understood by only a small number of people with a specialized knowledge or interest, or an enlightened inner circle." - http://en.wiktionary.org/wiki/esoteric
18:34:06 <tromp> that would seem to apply to fortran and cobol as well:)
18:34:16 <nyuszika7h> using that logic you could call Scheme esoteric too
18:34:21 <S1> k, rather "Having to do with concepts that are highly theoretical and without obvious practical application"
18:35:01 <fizzie> "13. Provide the applied-for gTLD string. If an IDN, provide the U-label." "ooo" "We conducted extensive research on specialized websites and on generic search tools first. Our experts (computer engineers) have evaluated the string to conclude that there was no operational or rendering problem. We contacted outside experts who reached the same conclusion. Hence there are no known operational ...
18:35:08 <fizzie> ... or rendering problems concerning the applied-for gTLD string."
18:37:41 <fizzie> Apparently it's a TLD for e-commerce.
18:38:05 <fizzie> Since "ooo" is so evocative of trust and other such emotions.
18:40:17 -!- LauraFinder has quit (Read error: Connection reset by peer).
18:41:40 -!- LauraFinder has joined.
18:41:46 <Gregor> I like that they launched .education as the legitimacy-free alternative to .edu.
18:41:50 <Gregor> I bought a .institute for myself.
18:41:54 <Gregor> Because I am the Gregor Institute.
18:42:10 <fizzie> As far as I can tell from the application, you can only use their e-commerce-site-builder to build .ooo sites.
18:42:24 <MDude> Pale Moon can't find the server at www.spooky.ooo.
18:42:44 <fizzie> Or maybe they just have a list of requirements, now that I look closer.
18:42:47 <MDude> Oh, I didn'y read what that was in reponse to.
18:43:19 -!- LauraFinder has quit (Read error: Connection reset by peer).
18:43:22 <fizzie> You can make a spooky.ooo as long as you have "a physical address, a brand⁄store name, and a phone number" publicly displayed on the front page.
18:43:24 <MDude> Object Oriented Operations
18:44:11 <mroman> coppro: but that shouldn't happen @empty match
18:44:41 <fizzie> Melvar: They use the FRACTION SLASH as a slash throughout the thing.
18:45:04 <fizzie> It renders real badly in the browser with this particular monospace font.
18:45:14 <Melvar> I wonder how they came to misuse it that way.
18:45:22 <mroman> it loops forever with allMatches'' f regex "" ng nv as well
18:45:26 <fizzie> (Overlaps with the neighboring characters, and messes up the monospacing.)
18:45:51 <MDude> Can the physical address be an empty lot, and the phone number something that just connects you to something like delayed feedback or a numbers station?
18:46:01 <fizzie> mroman: Well, what's the regex? I mean, if it's capable of empty match, you can find the empty match in "".
18:46:30 <mroman> I'm catching Just(_, "", _, _) -> error "nope" now
18:46:34 <mroman> and it doesn't throw an error nope
18:46:40 <mroman> the match is not empty
18:47:49 <fizzie> MDude: There is an "eligibility test".
18:47:55 <mroman> http://codepad.org/7LcMg07u
18:48:04 <mroman> fizzie: MatchesAll runs through
18:48:08 <mroman> ApplyRegex runs forever
18:48:13 <mroman> same regex, same input string
19:08:29 -!- LauraFinder has joined.
19:08:41 -!- LauraFinder has quit (Read error: Connection reset by peer).
19:22:34 <J_Arcane> Unintended but quite idiomatic result in Heresy: Because most Heresy forms are just macros for Racket, and I've yet to implement any more specific error handling for said macros, it means the default error for most Heresy functions is just a 'bad syntax' error.
19:31:32 <J_Arcane> http://fc05.deviantart.net/fs71/i/2011/050/4/5/syntax_error_by_gmphoenix-d39syyv.png
19:53:15 <HackEgo> [wiki] [[Mneme]] M http://esolangs.org/w/index.php?diff=40929&oldid=8577 * BCompton * (+12) Dead link
19:54:45 -!- kcm1700 has quit (Read error: Connection reset by peer).
19:54:55 -!- kcm1700 has joined.
19:59:22 <fizzie> From elsewhere in the ircwebs, possibly not news: https://developer.android.com/reference/android/os/UserManager.html#isUserAGoat%28%29
20:00:30 <FireFly> "Return whether the given user is actively running." I didn't know they had APIs for that
20:01:03 <fizzie> I didn't know they had APIs for goat stuff at all, nor that being a goat is somehow related to teleportation.
20:01:31 <FireFly> I think the teleportation thing is a reference to mountain goats
20:02:33 <S1> "advanced goat recognition technology"
20:02:42 <FireFly> the 'Return whether the given user is actively running' is from a serious method, by the way
20:03:04 <fizzie> Apparently goat teleportation is also a joke in Chrome.
20:03:47 <FireFly> There's also a method that 'will also return true if the user had been running but is in the process of being stopped (but is not yet fully stopped)', I wonder if that triggers if the user is being chased by the police
20:03:55 <FireFly> Or perhaps if the user is about to hit a wall
20:05:04 <fizzie> Apparently isUserAGoat it used to return false always, but now returns true if isPackageAvailable("com.coffeestainstudios.goatsimulator").
20:05:22 <fizzie> And that's what the "advanced goat recognition technology" is referring to.
20:05:36 <fizzie> (I guess that's the goat simulator game.)
20:15:22 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
20:17:33 <elliott> https://code.google.com/p/chromium/issues/detail?id=31482
20:22:29 -!- Melvar` has joined.
20:24:29 -!- Melvar has quit (Ping timeout: 250 seconds).
20:34:20 -!- Melvar` has changed nick to Melvar.
20:55:37 -!- AnotherTest has joined.
21:03:09 <mroman> this <<loop>> is really annoying.
21:05:18 <mroman> allMatches seems to terminate
21:05:25 -!- hjulle has joined.
21:05:39 <mroman> although that might be lazyness stuff
21:10:58 <mroman> blsq ) "[0-9]+"{<-}"abc127def789bum"~a
21:11:35 <mroman> let (_, g', v', str) = (allMatches'' f regex str g v)
21:11:40 <mroman> that seems to be the problem
21:12:23 <Taneb> Bah, my number theory lecturer doesn't quite get the notion of a relation
21:12:24 <mroman> let (_, g', v', str) = (allMatches'' f regex str g v)
21:12:28 <mroman> blsq ) "[0-9]+"{ri?iSh}"abc127def789bum"~a
21:12:47 <Taneb> Apparently ~ : ZxZ -> Z is a relation
21:12:51 <mroman> it allows you to apply a function on what a regex matches
21:12:53 <Taneb> An equivalence relation, no less
21:13:23 <int-e> Taneb: that's ... interesting.
21:13:59 <Taneb> I pointed this out to him in the lecture, and he sort of handwaved it in a not very satisfying manner
21:14:17 <Taneb> (his definition of ~, other than its type, is an equivalence relation)
21:14:32 <int-e> so, a set of pairs?
21:15:05 <Taneb> He just says z1 ~ z2 <=> z1 = z2 (mod m)
21:15:50 <Taneb> btw what's the mathsy word of type signature?
21:15:51 <int-e> maybe he thinks of relations in terms of indicator functions? But even then the codomain would be nicer if written as {0,1}.
21:16:36 <int-e> type. carrier set. domain (of a variable)... I don't know.
21:17:13 <vanila> Taneb, He may be alluding to the fact that a function like that induces an equivalence relation
21:17:31 <Taneb> vanila, I don't think that's the case
21:17:44 <int-e> vanila: but that would be an equivalence relation on pairs of numbers.
21:18:44 <int-e> (or it needs further explanation, like that there is a congruence relation for that function...)
21:19:32 <int-e> (x~x', y~y' imply f(x,y)~f(x',y'))
21:20:57 <int-e> For relations I'd usually just write ~ \subseteq ZxZ rather than deciding on a notation for the power set.
21:21:33 <int-e> maybe the ZxZ -> Z started out as ZxZ -> 2
21:22:32 <Taneb> This is typed notes
21:22:33 <vanila> oh, the 2 is just backwards!
21:22:54 <Taneb> The Zs all have sharp angles and doubly lines
21:23:19 <int-e> Taneb: it's still a possibility
21:23:28 <int-e> those typed notes were not created in a vacuum.
21:24:34 <Taneb> Also that was what he wrote on the blackboard in the lecture, and I did press him about it
21:24:38 <Taneb> And he stuck with Z
21:25:01 <int-e> tell him that the internet agrees with you that he's wrong
21:25:15 <int-e> elliott: it's not.
21:25:31 <elliott> int-e: it is. you clearly never met george zbool
21:25:35 <int-e> You could argue for W = Wahrheitswert.
21:25:37 <Taneb> (this is the same guy I got the 0 \elem N shirt for)
21:26:28 <int-e> elliott: I have not, that is true. I have not met George Boole either, but at least there's a historical record of him.
21:26:54 <elliott> int-e: okay, I admit, it's actually french
21:27:12 <int-e> I rather doubt it.
21:27:33 <int-e> Especially given your recent track record for sticking to the Truth and making things up.
21:27:50 <elliott> you're ruining my reputation :(
21:27:59 <Taneb> Famous italian mathematician
21:28:05 <int-e> elliott: I don't have to, you're doing an excellent job all by yourself.
21:28:19 <elliott> where did we go wrong, int-e
21:28:25 <elliott> things used to be so much better than this
21:29:18 -!- Bicyclidine has joined.
21:30:32 <int-e> I think it went wrong when you tried saving a joke that wasn't funny the first time.
21:31:29 <int-e> Now if you stop asking rhetorical questions I can stop answering them ;-)
21:32:43 <elliott> well, it was so bad it couldn't get less funny by extending it.
21:34:21 <Taneb> (I found it funny)
21:39:23 -!- vanila has quit (Quit: Leaving).
21:44:15 -!- Primal has joined.
21:44:36 <Primal> My fingers are cold so i cant do much
21:44:51 <int-e> go catch some fresh air
21:45:32 <Primal> Nah im outside its just i've been typing fast for like an hour and im pretty sure typing fast isnt good when im coding a library
21:45:41 <olsner> fungot: how cold are your fingers?
21:45:43 <fungot> olsner: apparently there were pre-cl lisps which had more than lament is refusing to fork after about 130 processes. ( i'm fnord the new ubuntu release, no?
21:46:14 <olsner> if you were typing fast, shouldn't that have heated up your fingers?
21:46:21 <int-e> does fungot actually take the context into account when replying, or is it just scanning for its nickname?
21:46:21 <fungot> int-e: so how does that affect boxing? like using cells? sounds a bit cliché......
21:46:30 <Primal> Not if you are in 29 degree weather
21:46:31 <olsner> int-e: nah, it just scans for the nickname
21:46:35 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
21:47:14 <fungot> FireFly: i found at http://www.iro.umontreal.ca/gambit/ doc/ 360/ fnord/ ffi
21:47:30 <Primal> I dislike ubuntu for many reason's >_>
21:47:39 <olsner> it would be cool if it did somehow base on what you wrote on the trigger line, but I think that might be an unreasonable expectation on fizzie to do that
21:47:40 <int-e> I wonder what an uppercut would look like.)
21:48:37 <fizzie> int-e: The Perl prototype can continue from a predefined starting context, but fungot itself doesn't even have the mapping from strings to token indices.
21:48:37 <fungot> fizzie: and dotted pair with car and cdr locations. 2.
21:49:08 <Primal> What were you guys talking about before i got in?
21:49:23 <int-e> Primal: we have logs, see the topic
21:49:36 <Primal> Sorry i just got to the logs
21:50:54 <FireFly> fungot: you want to be re-implemented in lisp?
21:50:54 <fungot> FireFly: you're going to get that particular bot going. good night. fnord,
21:51:06 <FireFly> I think that might be a yes
21:51:33 <FireFly> (and apparently I'm supposed to be responsible for it?)
21:51:35 <fizzie> Another reasonable thing is to interpolate the language model between the original and a one built from the input, but usually the inputs are pretty short.
21:52:27 <Primal> Do i have to ask a mod? to join a bot here or something
21:53:40 <Primal> Nope im working on it atm for some pay, The patron did a bad job at making it but they are my friend so im helping i just need to test it
21:54:02 <Primal> Ill do that later when ever i get the library sorted
22:01:14 <Primal> Sorch are you in here?
22:02:36 -!- centrinia has joined.
22:03:47 -!- Primal has quit (Quit: Page closed).
22:12:42 <int-e> . o O ( what Rosetta didn't find: http://int-e.eu/~bf3/tmp/rosetta.png )
22:22:12 -!- S1 has quit (Quit: S1).
22:22:50 -!- AnotherTest has quit (Ping timeout: 244 seconds).
22:31:13 -!- Vorpal_ has changed nick to Vorpal.
22:51:27 -!- aretecode has joined.
22:58:09 <Taneb> I... am using ssh and X forwarding to get MATLAB
22:58:33 <Taneb> So I can procrastinate better
22:58:41 <Taneb> By having MATLAB open and not looking at it
23:00:44 <int-e> have a good internet connection, do you?
23:01:28 <Taneb> (if I wanted to do this properly, I would walk a mile to the uni CS lab where MATLAB is installed)
23:01:29 <int-e> (I've stopped using X forwarding; running things in Xvnc + vncviewer -via is much more bandwidth efficient)
23:02:12 <int-e> (or so I've found, personally)
23:08:15 <Taneb> That looks pretty cool
23:08:37 <elliott> it's a lot better than X forwarding.
23:08:58 <int-e> thanks, though I probably won't (usually I'm happy with local X and ssh, and I have a script for making the vnc thing easy already)
23:09:15 <elliott> well, xpra lets you use your local WM :)
23:13:20 -!- heroux has quit (Ping timeout: 264 seconds).
23:14:00 -!- heroux has joined.
23:14:17 -!- mihow has quit (Quit: mihow).
23:23:04 -!- Phantom_Hoover has joined.
23:26:16 -!- Sgeo has quit (Remote host closed the connection).
23:26:39 -!- Sgeo has joined.
23:42:45 <zzo38> Another way to implement action symbols in a shift-reduce parser: The result type is the same as the type of action symbols, and this type forms a monoid. Each production has exactly one action symbol (which may be the identity symbol). The lexer also produces action symbols; whenever it is called to get a new token, the action symbol of the previous token is applied.
23:47:09 <zzo38> And then apply this to a "passive skip-reduce parser". The above ensures that the grammar is "passive". And then each nondefault action can be a shift or a skip (which is like a shift, except it pushes nothing to the stack but still go to another state which won't be on the stack and will therefore be forgotten); each default action can be a reduce, an accept, or an error.
23:48:46 <zzo38> Which grammars can be reduced to such a form? If you make a CFSM and then there is a reduce-reduce conflict, how can you attempt to unify the conflicting productions?
23:56:57 <int-e> Fascinating, how did I arrive at 1 alphanum less than henkma, but the same length... (Leapfrogging)
23:57:01 -!- oerjan has joined.
23:57:19 <int-e> ah oerjan will know ;-)
23:58:01 <int-e> nothing, I just caught up on Leapfroggin.
23:59:38 <oerjan> i did have a feeling those last two i did weren't optimal, although 19 bytes shorter is a bit more than i expected
23:59:39 <int-e> and the statistics are a bit odd.
00:00:00 <int-e> 19 ... that's the euclidean norm?
00:00:36 <int-e> no, that one is 18
00:01:58 <int-e> otoh I still haven't gotten Basic Brainfuck Optimization. My code is already optimal, how dare you submit anything shorter ;)
00:02:16 <oerjan> anyway, you catching up on leapfroggin means whatever henkma did is possible ;)
00:02:31 <Taneb> incomprehensibly, Basic Brainfuck Optimization?
00:02:58 <int-e> it just collapses +- -+ <> ><
00:03:45 <Taneb> I'm (slowly) working on a very optimizing brainfuck compiler
00:03:55 <int-e> it doesn't eliminate the second loop for [...][...]
00:04:17 <int-e> nor does it do anything about >+<+>+<
00:04:22 <oerjan> and i guess i've already teased you with the fact i'm not doing anything really clever in it
00:04:58 <int-e> oerjan: if true, then I can beat you both, but it's more likely that I'm missing something straight-forward and easy
00:05:57 <Taneb> Any loop with equal numbers of >s and <s, where all subloops also match these criteria, I think you can simplify like loads when compiling to something sensible
00:06:05 <int-e> > length "c=='+'&&d=='-'||c=='-'&&d=='+'||c=='<'&&d=='>'||c=='>'&&c=='<'"
00:06:18 <zzo38> Another optimization would be to delete plus signs and minus signs before a comma if the implementation isn't "no change when EOF" implementation. You can also delete < > + - at the end of the program
00:07:02 <oerjan> int-e: ...there's no way you can be just 3 chars longer if you're doing _that_ kind of thing.
00:07:12 <int-e> oerjan: the 62 makes me feel better, my program would be so much longer :)
00:07:58 <Taneb> However, shorter brainfuck code is a very different goal than shorter compiler target code
00:08:10 <int-e> oerjan: it's obviously more than twice as long as necessary
00:08:43 <int-e> but it's less obvious by how much
00:08:52 <oerjan> int-e: i can think of two trivial mistakes that i could have done in my code (and i did one initially), that would make it 3 chars longer, hth
00:08:57 <Taneb> So I guess what I've spent a few hours thinking about recently is mostly irrelevant here
00:10:45 <int-e> Taneb: I've written one brainfuck-to-c converter, which recognized simple counting loops (like [-<+++<+>>]) and turned them into multiplications (a[p-1]+=3*a[p];a[p-2]+=a[p];a[p]=0;)
00:12:02 <Taneb> int-e, I think you can do another layer of cleverness beyond that with nested loops like that
00:12:10 <zzo38> Is level20.tex full of footnote fever or not? Someone on other channel also said they don't know, when I asked them.
00:13:26 <oerjan> Taneb: note that a corollary of my collatz_function work is that balanced bf loops are still tc so don't expect _always_ to be able to optimize.
00:14:14 <int-e> Taneb: http://int-e.eu/~bf3/tmp/bf2c.hs ... really old, fairly stupid.
00:14:41 <int-e> (I think I've seen a copy of that online somewhere, but I don't remember where)
00:14:45 <Taneb> oerjan, oh wow, tha makes this kind of harder
00:15:07 <Taneb> By kind of harder I mean "needs some thinking" --> "actually impossible in the general case"
00:15:53 <oerjan> ^wiki Collatz_function
00:15:53 <fungot> http://esolangs.org/wiki/Collatz_function
00:16:04 <oerjan> see there, all the generated loops are balanced
00:16:31 <int-e> Right, something like >[-]+<[[-]>-<...]>[-...] is a balanced conditional.
00:17:42 <oerjan> yeah i remember when pikhq_ did his bf macro language he figured many things out with balanced loops because his language handled those better
00:18:06 <int-e> it's just that the unbalanced stuff tends to be shorter
00:18:23 <pikhq_> Yeah, but it's much harder to work with programmatically.
00:18:34 <oerjan> of course if cells are bounded you need unbalanced loops for tc
00:19:15 <int-e> oerjan: hmm, actually ... with balanced loops you can only access a finite number of cells. so did you assume unbounded cells?
00:20:10 <int-e> or did you accidentally prove the collatz conjecture ;)
00:20:18 <oerjan> int-e: ok maybe i'm doing one slightly but not that clever thing but without it it would also be much more than 3 chars longer.
00:21:21 <int-e> oerjan: Oh and I gloated a bit about Enumerate Compositions earlier, but I shouldn't gloat too much. My version is 86 characters as well atm.
00:21:38 <oerjan> int-e: my proof is for 3 unbounded cells.
00:22:02 <int-e> right. for unbounded cells, balanced loops should suffice.
00:22:07 <oerjan> which shortened by 2 the previous record.
00:22:52 <oerjan> Taneb: i suppose for bounded cells you _can_ optimize completely into a finite table thing.
00:23:02 <int-e> (Though they could become necessary again when trying to minimize the number of cells.)
00:23:32 <oerjan> although it will have 256^n entries or the like.
00:23:48 <int-e> And it's still a good argument for the optimizing compiler because now it would have to exploit the finite range of cells to optimize arbitrary programs.
00:24:01 <int-e> With balanced loops.
00:26:23 <oerjan> int-e: i have a nicely shorter version of enumerate compositions, if anagolf just ignored trailing space...
00:28:00 <int-e> yeah, unwords is annoyingly long
01:07:18 <int-e> yay! Leapfrogging--
01:08:56 <elliott> oerjan: are they TC even with bounded cell size?
01:09:14 <oerjan> elliott: of course not, you can only access finite memory then
01:09:25 <elliott> but bignum is not conventional for bf.
01:10:17 <oerjan> boolfuck is thataway ->
01:10:55 * oerjan suddenly imagines fibonaccifuck
01:11:02 <Taneb> oerjan, how would that work?
01:11:13 <oerjan> like boolfuck, except it's an error to ever have two neighboring 1s
01:12:17 <int-e> ok, henkma's turn.
01:12:26 -!- boily has joined.
01:12:46 <oerjan> CHALLENGE O... hey, i need an idea first.
01:22:09 <int-e> oerjan: is that more interesting than just doing s/[<>]/&&/g?
01:22:44 <int-e> fibonaccifuck. I'd just double all arrows.
01:26:49 <boily> Taneb: Tanelle. do you still boardgame?
01:27:38 <pikhq_> s/[<>]/&[Trust me, this is an excellent idea. <_< >_> Nothing can go wrong!]&/g
01:29:40 <int-e> [Note that this cell is already zero.]
01:33:50 <elliott> oerjan: wait, how would that be fibonacci?
01:34:17 <int-e> elliott: count the number of such strings (with no consecutive 1s) of length n
01:34:37 <oerjan> elliott: fibonacci base
01:34:58 <int-e> aren't you the Zeckendorf fan?
01:35:10 <shachaf> Oh, recently I was figuring out the number of valid UTF-8 strings (disregarding the particular code points).
01:35:42 <int-e> elliott: No, that's b_jonas. Ok, you're off the hook.
01:35:43 <shachaf> It works out to be 4-bonacci.
01:50:58 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
01:58:34 <HackEgo> [wiki] [[BitZ]] M http://esolangs.org/w/index.php?diff=40930&oldid=40928 * Oerjan * (-15) improve reformatting
02:07:58 -!- mihow has joined.
02:19:00 -!- boily has quit (Quit: CONCLUSIVE CHICKEN).
02:20:41 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=40931&oldid=40887 * Oerjan * (+144) some proofreading
02:25:29 <HackEgo> [wiki] [[ODDBALL]] M http://esolangs.org/w/index.php?diff=40932&oldid=13446 * Oerjan * (+0) OCPD crusade in progress
02:28:25 -!- aretecode has quit (Quit: Toodaloo).
02:35:06 <HackEgo> [wiki] [[Hello, world!]] M http://esolangs.org/w/index.php?diff=40933&oldid=25342 * Oerjan * (+0) etc.
02:35:15 <HackEgo> [wiki] [[COW]] M http://esolangs.org/w/index.php?diff=40934&oldid=36819 * Oerjan * (+0) etc.
02:35:24 <HackEgo> [wiki] [[Shoopuf]] M http://esolangs.org/w/index.php?diff=40935&oldid=8338 * Oerjan * (+0) etc.
02:35:34 <HackEgo> [wiki] [[Mouse]] M http://esolangs.org/w/index.php?diff=40936&oldid=38263 * Oerjan * (+0) etc.
02:36:26 -!- ChanServ has set channel mode: +q *!*@162.248.166.242.
02:36:42 <oerjan> this will take a while :P
02:36:42 <elliott> oerjan: mark the edits as bot edits
02:36:48 <elliott> then they won't spam recent changes, either
02:37:24 <oerjan> um i'm trying to do this with few keystrokes
02:37:29 <elliott> just put yourself in the bot group
02:37:36 <elliott> (and keep marking them minor, though I think it's less important as a bot)
02:37:43 <elliott> then they're hidden by default in recent changes and you can leave afterwards.
02:39:24 <oerjan> do i just add my nick to Esolang:Bots or what
02:40:41 <elliott> oerjan: Special:UserRights
02:40:45 <elliott> I added you to the bot group, have fun
02:40:50 <elliott> make sure to take it off once you're done
02:41:01 -!- ChanServ has set channel mode: +o elliott.
02:41:09 -!- elliott has set channel mode: -q *!*@162.248.166.242.
02:41:12 <elliott> hopefully HackEgo won't report bot edits
02:42:09 -!- elliott has set channel mode: -o elliott.
02:48:27 <oerjan> hm i hit the spam filter on a page with old <br> formatting
02:49:48 <int-e> so that's for the Brainfuck thing... way too easy
02:49:56 <int-e> in retrospect. as usual.
02:51:13 <oerjan> shachaf: ask chanserv about that.
02:55:56 <int-e> All hail oerjan, the new bot overlord!
02:56:13 <oerjan> i hope <br> <br> is equivalent enough to <br><br>
03:05:05 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
03:06:58 <oerjan> elliott: i seem not to have the right to unbot me
03:08:10 <HackEgo> [wiki] [[Special:Log/rights]] rights * Ehird * changed group membership for User:Oerjan from bot, sysop to sysop
03:10:31 <zzo38> On multiple MediaWiki websites I get a problem that sometimes the status just says "Connecting" and then "Connected" and back and forth several times and then it says there is no data, and it won't work again until I restart the browser. It didn't used to do that; it start only recently. Do you know what is the problem?
03:11:37 <zzo38> Wikipedia and All The Tropes are two of them; some others that use MediaWiki are also affected. Esolangs seems to work though
03:13:15 <zzo38> Does the problem have anything to do with HTTPS?
03:14:19 <zzo38> I mean the status bar in the browser
03:14:47 <zzo38> Also, it only started recently; it worked before!
03:14:58 <zzo38> I didn't have this problems before
03:15:15 <zzo38> I tried other browsers though, and got the same problem
03:15:24 <shachaf> The Mozilla Application Suite? Or Mozilla Firefox or something?
03:15:55 <shachaf> you have out-zzo38ed my expectations
03:15:59 <zzo38> It is a custom browser based on XUL Runner
03:16:12 <shachaf> I haven't seen this behavior.
03:17:11 <zzo38> Clearing the cache doesn't help, and even if one site does this, other ones don't necessarily do it too during the same session, although if it does, then they are both broken during the current session.
03:17:52 <quintopia> zzo38: would you like to know how to make good AI :D
03:18:59 <Bike> first, you should start with something relateable to all known intelligences, such as bughouse chess
03:20:33 <shachaf> Bike: so what's with left eigenvectors
03:21:24 <Bike> i think that's just because matrices are 1,1-tensors
03:21:24 <quintopia> they're the same as right eigenvectors, but more row-like
03:22:16 <Bike> i /think/ a row vector is a covector, if you're saying column vectors are vectors
03:22:30 <shachaf> well, neither of them is really a vector
03:22:39 <Bike> psh they're plenty linear
03:23:13 <shachaf> if a vector is v : R^n, you can represent it as f : R -> R^n (""column vector"") or as g : R^n -> R (""row vector"")
03:23:20 <shachaf> where the latter is the dual space thing
03:24:17 <shachaf> people say "eigenvector with eigenvalue 1" instead of "fixed point" for some reason. it's silly
03:24:45 <Bike> because linearity is p convenient
03:25:21 <Bike> and a fixed point is just a specific kind of eigenvector when it comes to linear operators "so there"
03:28:06 <shachaf> what's with people talking about properties of matrices instead of properties of the linear functions they represent
03:28:26 <Bike> i don't know it sucks
03:28:41 <Bike> have you ever been subjected to a linear algebra course in a school? avoid them
03:29:02 <shachaf> no but i feel like maybe i should??
03:29:11 <Bike> no it's all matrices and barely any linear
03:29:18 <Bike> i mean it's good to know i guess, but still
03:29:36 <Bike> my linear class started in august and we first got to eigenshit last week.
03:29:41 <shachaf> ok then what's the good way to do it
03:29:55 <Bike> hell if i know
03:29:57 <Bike> fake it til you make it
03:30:30 <Bike> or maybe work on some "practical science computing project" where you have to know linalg.
03:30:43 <oerjan> int-e: ah you got the brainfuck optimization
03:31:07 <oerjan> i'm wondering what you missed before.
03:35:00 <Bike> i mean, really, why would you ever compute a 4×4 determinant by hand
03:42:59 -!- J_Arcane has quit (Read error: Connection reset by peer).
03:43:06 -!- adu has joined.
03:43:30 -!- J_Arcane has joined.
03:45:48 <HackEgo> [wiki] [[Container]] http://esolangs.org/w/index.php?diff=40997&oldid=40921 * Oerjan * (-1) intro fmt
03:46:29 -!- centrinia has quit (Ping timeout: 265 seconds).
03:46:55 <int-e> oerjan: pairs beat lists.
03:48:19 -!- centrinia has joined.
03:54:23 -!- zzo38 has quit (Read error: Connection reset by peer).
03:55:13 -!- zzo38 has joined.
04:00:04 <ZombieAlive> https://www.youtube.com/watch?v=By1QCaNcXn4
04:05:47 <zzo38> What effect do some servers have if I set network.http.accept.default so that text/plain is given the highest quality number (q=1.0)?
04:10:41 -!- Bicyclidine has joined.
04:13:17 <int-e> oerjan: The McCarthy solution is BEAUTIFUL!
04:15:55 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
04:29:23 <HackEgo> [wiki] [[ATZ]] M http://esolangs.org/w/index.php?diff=40998&oldid=40915 * Thatguy25252525 * (-2)
04:41:09 -!- zzo38 has left.
04:41:11 -!- zzo38 has joined.
04:53:06 -!- oerjan has quit (Quit: Nite).
04:53:13 <J_Arcane> Oh man, my FOR loop is gonna be extra tricky. Think I may want to refactor into simpler sub expression types.
05:16:56 -!- NATT_SiM has joined.
05:18:44 <^v> <_> when i go here and see something extremely basic related to programming and think everyone is a noob
05:18:50 <^v> then realize the channel name
05:20:15 <^v> i have given up on esolangs though
05:20:26 <^v> call me a functionalityfag
05:21:10 <^v> zzo38, for like 3 months i obsessed with everythin esolange, implemented like 20 into my irc bot, made another irc bot in brainfuck
05:21:15 <^v> and now its just meh
05:21:18 <J_Arcane> ^v: yeah, I'm not writing *a* for loop, but rather implementing the syntax for one with carrying accumulator and some sugaring for automatically recognizing certain incrementor types.
05:25:39 <elliott> let's not do the -fag thing
05:28:35 <coppro> ^v: have you learned category theory yet?
05:28:49 <^v> coppro, nope
05:29:53 <elliott> ^v: that's a warning, btw.
05:59:33 -!- centrinia has quit (Ping timeout: 264 seconds).
06:30:07 -!- MDude has changed nick to MDream.
06:33:53 -!- NATT_SiM has quit (Remote host closed the connection).
06:34:48 <zzo38> Maybe level20.tex does not quite have footnote fever, because the footnotes do not themselves contain footnotes.
06:35:47 <shachaf> Are you the same person as `^_^v?
06:40:03 <zzo38> How many people in here have read the level20.tex (it is even linked from HackEgo)? Hopefully if you do then you can write complaints and other stuff about it in All The Tropes.
06:43:56 -!- NATT_SiM has joined.
06:43:56 -!- NATT_SiM has quit (Read error: Connection reset by peer).
06:49:10 -!- adu has quit (Quit: adu).
06:49:57 -!- qwertyo has joined.
07:17:30 <zzo38> Are the CELLs in BlooP/FlooP supposed to be indexed by constants only or by anything? It isn't quite clear; Wikipedia says constants only but I don't see that mentioned in a book.
07:18:46 <Bike> i don't think it would affect the turing power, which is the point of the exercise
07:21:04 <zzo38> Bike: Yes, although I found out that if they aren't indexed only by constants, that you don't need an IF statement, nor do you need multiplication, equality, or less/greater comparisons; and in BlooP only, you don't need QUIT BLOCK and ABORT LOOP.
07:21:28 <zzo38> I don't see why it should be constants only if it uses number like that, though.
07:22:47 <zzo38> I don't know if it can work like this when it is indexed only by constants.
07:35:41 <b_jonas> how do you get turing completeness if you can't index cells? there's only one stack, the call stack
07:36:13 <zzo38> Another thing which isn't entirely clear is if a loop needs to have "AT MOST" if you want to be able to exit the loop early.
07:36:41 <b_jonas> zzo38: meh, that's just syntax, isn't it?
07:37:36 -!- Phantom_Hoover has joined.
07:38:16 <zzo38> b_jonas: Yes, but still it isn't quite clear.
07:39:12 <zzo38> The Perl implementation of BlooP and FlooP requires only indexed by constants, although it does one thing that looks clearly wrong to me which is that it doesn't have a separate boolean type.
07:39:27 <myname> primTest n | even n = False
07:41:10 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
07:41:58 <b_jonas> zzo38: well, the book clearly says BlooP is supposed to describe exactly all the primitve recursive functions, but doesn't define the language rules properly, so I'd say it's just one of the not very well defined languages.
07:43:28 <zzo38> b_jonas: You are probably correct.
07:44:18 <int-e> "bounded loop", that's one where you specify the number of iterations at the start. the details don't matter so much.
07:44:47 <b_jonas> some of the details do, sadly, the details that change the power
07:45:59 <b_jonas> oh, and BlooP wouldn't even have a stack at all
07:47:16 <int-e> zzo38: You can index the cells by anything, it won't change the power.
07:48:07 <b_jonas> int-e: oh... maybe you're right, because bignums
07:48:23 <b_jonas> you can store an indexed array in them
07:49:01 <b_jonas> zzo38: int-e is right, BlooP has bigints, so you can store full arrays in a bigint
07:49:11 <b_jonas> even though you only have a finite number of bigint cells
07:50:17 <zzo38> I know it won't change the power in that case, but I meant if you omit many of the other features I have specified, then are variable indexing necessary?
07:50:39 <b_jonas> which other features exactly?
07:50:56 <b_jonas> wait, does bloop have built-in less-than compare?
07:52:28 <zzo38> Yes, it does have.
07:53:22 <zzo38> The other features are the ones I have specified above: multiplication, comparison (for equality and less), the IF statement, and for BlooP only (not FlooP), the ABORT LOOP and QUIT BLOCK statements.
07:53:30 <b_jonas> if it does, then you can even do stuff in only polynomial time blowup, as with multiplication and less-than comparison you can implement bigint array access in polynomial time
07:53:43 <b_jonas> but I'm not sure it has less-than comparison
07:54:01 <int-e> wow, Hofstadter's introduction to BlooP is horrible...
07:54:16 <int-e> Nothing is clear, everything is up to interpretation.
07:55:01 <int-e> I used to like the book.
07:55:07 -!- Patashu has joined.
07:55:40 <int-e> I guess I can still enjou some parts of it.
07:55:57 <int-e> Just skip everything mathematical or computer sciency.
07:57:29 <zzo38> On page 409 at the bottom it says one operation considered primordial is "determining the larger (smaller) of two numbers". Page 419 lists the < and > symbols as part of the alphabet.
07:58:09 <int-e> (Page numbers don't help me, I only have a german translation. The language keywords got translated, too.)
07:59:20 <zzo38> Maybe you can find them anyways by the description I have given.
08:05:35 <int-e> the book fails to define the language. how do I know (except by intent) that ACK(CELL(1),CELL(2)) is not a valid expression, evaluating the the Ackermann function applied to the values of cells 1 and 2?
08:06:25 <int-e> That said I guess you can take the examples and make the assumption that every intended language feature has been used in at least one of them.
08:06:47 <int-e> I guess then you arrive at the restriction that cells can only be indexed by constants.
08:07:22 -!- clog has quit (Ping timeout: 255 seconds).
08:08:01 -!- clog has joined.
08:09:27 <int-e> love the geocities link ... http://cgibin.erols.com/ziring/cgi-bin/cep/cep.pl?_key=BLooP (the other one is broken as well)
08:12:07 <int-e> so there's an implementation at http://www.catb.org/esr/retro/
08:16:27 <int-e> (providing, obviously, one of many possible interpretations of Hofstadter's description, but it looks reasonable)
08:17:31 -!- FreeFull has quit (Ping timeout: 244 seconds).
08:18:47 -!- FreeFull has joined.
08:48:32 -!- centrinia has joined.
10:15:54 -!- blsqbot has quit (Remote host closed the connection).
10:17:44 -!- blsqbot has joined.
10:18:56 <mroman> !blsq "123"{ri?iSh}"[0-9]{1}"~a
10:19:04 <mroman> !blsq "123"{ri?iSh}"[0-9]+"~a
10:19:19 <mroman> !blsq "[0-9]"{ri?iSh}"123"~a
10:20:39 <mroman> I should switch the order
10:47:33 <b_jonas> I figured out a pun from the Hitch-Hikers' Guide just yesterday, and it hurts.
10:51:07 <fizzie> (Ooh, fancy; a master's thesis presentation on the Opus codec next Monday.)
10:51:33 <b_jonas> young Zaphod boarded a mega-freighter ship waving toy pistols, and demanded conkers
10:52:23 <b_jonas> I didn't realize it was a pun because it's in English and I'm not good in English puns, and also because I read it in translation first
10:57:16 <mroman> I should add math commands that work on strings .
10:57:18 -!- qwertyo has quit (Quit: Leaving).
10:58:22 <mroman> which would produce 11 of course
11:23:28 -!- boily has joined.
11:56:17 -!- Patashu has quit (Ping timeout: 258 seconds).
12:14:01 -!- ais523 has joined.
12:15:37 <HackEgo> [wiki] [[My Unreliable Past]] N http://esolangs.org/w/index.php?oldid=40999 * Ais523 * (+8001) new language
12:16:04 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41000&oldid=40895 * Ais523 * (+25) /* M */ +[[My Unreliable Past]]
12:16:24 -!- sebbu has quit (Quit: reboot).
12:16:39 <HackEgo> [wiki] [[User:Ais523]] http://esolangs.org/w/index.php?diff=41001&oldid=38302 * Ais523 * (+24) the end of my streak of languages that start with S
12:17:49 <ais523> hey, people, I haven't given up on esolanging yet!
12:18:05 <ais523> this language took like an hour from idea to spec, maybe a little more, I even thought up a name in that time
12:18:12 <ais523> especially the I/O model
12:20:03 -!- centrinia has quit (Ping timeout: 258 seconds).
12:21:35 -!- boily has quit (Quit: CRYOGENIC CHICKEN).
12:24:41 -!- ais523 has quit (Ping timeout: 255 seconds).
12:26:25 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
12:29:14 <Taneb> @tell ais523 Congrats on new esolang
12:29:22 -!- ais523 has joined.
12:31:37 <Taneb> My Unreliable Past looks interesting
12:32:49 <Taneb> Haven't had much chance to take a look at it though
12:34:53 <b_jonas> is there a deeper meaning of J and V not being variables?
12:35:07 <b_jonas> is it the initials of some revered master or something?
12:35:15 <ais523> letters missing from the Latin alphabet
12:35:52 <Taneb> Latin alphabet had W but not V?
12:38:20 <ais523> no, but I and J were the same letter, so were U and V
12:38:32 <ais523> and I thought 26 because letters in English was too trite, so I went for 24 instead
12:38:38 <ais523> I may well be back later
12:38:46 -!- ais523 has quit.
12:40:06 <HackEgo> [wiki] [[Talk:My Unreliable Past]] N http://esolangs.org/w/index.php?oldid=41002 * B jonas * (+130) Created page with "Is this random starting state related to the idea of Boltzmann brains? ~~~~"
12:46:11 -!- sebbu has joined.
12:54:46 <mroman> I'm thinking about adding infix operators to burlesque
12:55:25 <mroman> but I have no idea what operators :)
12:57:53 <Taneb> (I don't know Burlesque
13:09:21 <mroman> 13:57 < Taneb> divides
13:09:29 <mroman> ^- this already revealed that you don't know Burlesque :)
13:10:18 <blsqbot> ERROR: Burlsque: (n!) Invalid arguments!
13:12:41 <blsqbot> {1 2 4 5 7 8 10 11 13 14 16 17 19 20}
13:13:44 <blsqbot> Taneb: http://fmnssun.github.io/Burlesque/
13:15:58 <mroman> [..] But pros will write it as "abc def ghj"{<-}ww [..]
13:16:03 <mroman> the super-real pros will write it as
13:16:08 <mroman> !blsq "abc def ghj"q<-ww
13:17:24 -!- drdanmaku has joined.
13:17:27 <mroman> !blsq "abc def ghj"qXXww
13:17:27 <blsqbot> {'a 'b 'c ' 'd 'e 'f ' 'g 'h 'j}
13:17:53 <mroman> !blsq "abc def ghj"qanww
13:17:53 <blsqbot> {ERROR: Burlesque: (_+) Invalid arguments!}
13:17:58 <mroman> !blsq "abc def ghj"{anSh}ww
13:18:03 <mroman> !blsq "abc de.f ghj"{anSh}ww
13:18:47 <mroman> !blsq "abc de.f ghj"wd:an
13:19:23 <mroman> !blsq "abc de.f ghj"wd)an
13:19:53 <mroman> !blsq "abc de.f ghj"wdqanfl
13:20:34 <mroman> wdqanfl is actually the same as wd)an++
13:20:47 <mroman> !blsq "abc de.f ghj"wd)an++
13:20:53 <mroman> !blsq "abc de.f ghj"wdqanms
13:21:00 <mroman> which is the same as wdqanms
13:21:24 <mroman> !blsq "abc de.f ghj"qanww
13:21:25 <fizzie> A rose by any other name.
13:21:25 <blsqbot> {ERROR: Burlesque: (_+) Invalid arguments!}
13:21:40 <mroman> !blsq "abc de.f ghj"{anSh}wwL[
13:21:48 <mroman> that's not the same though.
13:22:10 <mroman> wdqanfl, wd)an++, wdqanms ... choose whatever you like
13:23:18 <mroman> fizzie: Any suggestions on Burlesque?
13:23:22 <mroman> You have been using it for a while now.
13:23:31 <mroman> (any *new* suggestions)
13:24:48 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41003&oldid=40926 * TomPN * (+64) /* def function */
13:24:59 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41004&oldid=41003 * TomPN * (-1) /* def function */
13:26:08 <b_jonas> what? infix operators? in a stack-based language?
13:28:02 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41005&oldid=40922 * TomPN * (+86)
13:30:33 <HackEgo> [wiki] [[Talk:Dimensions]] N http://esolangs.org/w/index.php?oldid=41006 * TomPN * (+351) Created page with "== Proof of Turing-completeness == If 51 of the dimensions and the velocity instructions are unused, Dimensions reduces to brainfuck with alternate syntax. Therefore, Dimensio..."
13:31:51 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41007&oldid=41004 * TomPN * (+45)
13:32:14 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41008&oldid=41007 * TomPN * (+0)
13:33:45 <mroman> It's got functions now as well
13:34:38 <mroman> (which can also be written as 5 6%add!
13:36:09 <mroman> or re use it for dynamic assign
13:37:14 <mroman> b_jonas: there are variables and a secondary stack now
13:37:23 <mroman> so it's not purely stack-based anymore
13:38:15 <blsqbot> ERROR: Burlesque: (f[) Invalid arguments!
13:38:24 <blsqbot> ERROR: Burlesque: (f[) Invalid arguments!
13:38:31 -!- idris-bot has joined.
13:38:38 <mroman> !blsq %:0 'a %add={?+}V
13:38:38 <blsqbot> <'a,BlsqAssign "add" (BlsqBlock [BlsqIdent "?+"]) False False>
13:38:57 <mroman> this doesn't have a toDisplay :D
13:39:31 <blsqbot> That line gave me an error
13:39:36 <blsqbot> That line gave me an error
13:39:54 <blsqbot> That line gave me an error
13:49:30 <HackEgo> [wiki] [[Talk:Dimensions]] http://esolangs.org/w/index.php?diff=41009&oldid=41006 * Fizzie * (+676) /* Proof of Turing-completeness */ Why is it always non-nestable loops?
13:50:10 <fizzie> No new suggestions, but I haven't been golfing much the last few days either.
13:54:53 -!- MoALTz has joined.
13:54:54 <b_jonas> mroman: sure, but still, infix operators?
13:55:12 -!- ais523 has joined.
13:56:24 -!- MoALTz_ has quit (Ping timeout: 245 seconds).
13:57:46 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
13:58:23 -!- MoALTz_ has joined.
13:58:42 <mroman> b_jonas: there are prefix operators though
13:59:08 <mroman> which are technically operators
13:59:14 <mroman> rather than stuff on parse-level
13:59:40 <ais523> `! bf >,>+++++++++,>+++++++++++[<++++++<++++++<+>>>-]<<.>.<<-.>.>.<<.
13:59:43 <blsqbot> "Dafuq? You found a type I don't know?"
13:59:47 <ais523> oh wait, that program needs input
14:01:19 -!- MoALTz has quit (Ping timeout: 244 seconds).
14:01:40 <fizzie> ^bf >,>+++++++++,>+++++++++++[<++++++<++++++<+>>>-]<<.>.<<-.>.>.<<.!123
14:02:18 <fizzie> "+++++++++," looks like the strangest thing.
14:03:41 <ais523> fizzie: it's apparently meant to detect newline and EOF conventions
14:04:14 <fizzie> Oh, I see. So you're supposed to only provide one character of input.
14:07:13 <ais523> right, and it's meant to be a newline
14:07:25 <fizzie> You can't input a newline to fungot, sadly.
14:07:25 <fungot> fizzie: fnord/ projects/ xer/ fnord only lists 146 files, none of which can be given in person.
14:07:57 <fizzie> fungot: Those are some highly suspicious files, then.
14:07:57 <fungot> fizzie: if you're going
14:10:56 -!- oerjan has joined.
14:20:57 -!- S1 has joined.
14:22:09 -!- ais523 has quit (Ping timeout: 240 seconds).
14:24:39 <oerjan> <b_jonas> young Zaphod boarded a mega-freighter ship waving toy pistols, and demanded conkers <-- ok i don't get it either
14:25:09 <S1> oerjan: What's not to get?
14:25:23 <oerjan> b_jonas said there was a pun in it
14:25:56 <oerjan> it may not help that i didn't know what conkers were until today, but that still isn't enough for a _pun_
14:26:09 <S1> your standards are high, eh
14:26:37 <S1> well, one can expect a good pun from Adams
14:27:34 <S1> maybe it wasn't intended but b_jonas thought it was
14:27:44 <S1> am I making sense?
14:27:51 <oerjan> um i still don't know what the _pun_ is.
14:28:26 <S1> maybe the similar sound of conker and conquer? ¯\(°_o)/¯
14:28:37 <b_jonas> oerjan: the pun is that conkers sounds like "conquer"
14:28:54 <S1> I didn't laugh either
14:29:59 -!- blsqbot has quit (Remote host closed the connection).
14:30:07 <oerjan> i'm not convinced that's intended either hth
14:30:39 -!- blsqbot has joined.
14:30:45 <blsqbot> That line gave me an error
14:31:24 <blsqbot> That line gave me an error
14:31:49 <blsqbot> That line gave me an error
14:31:50 <blsqbot> That line gave me an error
14:32:01 <oerjan> very reproducible that error
14:33:29 <blsqbot> That line gave me an error
14:34:11 -!- AnotherTest has joined.
14:34:49 -!- blsqbot has quit (Remote host closed the connection).
14:36:19 -!- ais523 has joined.
14:36:45 -!- blsqbot has joined.
14:38:14 <mroman> !blsq "@tell mroman hi"Q
14:38:40 -!- blsqbot has quit (Remote host closed the connection).
14:39:20 <S1> lambdabot doesn't give massages anymore? :|
14:43:25 -!- blsqbot has joined.
14:43:28 <mroman> !blsq "@tell mroman hi"Q
14:43:55 <mroman> !blsq "@tell \r\n huhu \rQUIT :muh"Q
14:46:46 <blsqbot> | {{{0 1} {1 0} {2 0}} {{0 0} {1 1} {2 0}} {{0 0} {1 0} {2 1}}}
14:46:50 <mroman> !blsq {1 0 0}iR<>)zisp
14:47:06 <mroman> !blsq {1 0 0}iR<>)zizisp
14:47:07 <blsqbot> | 0 [[0, 1], [1, 0], [2, 0]]
14:47:07 <blsqbot> | 1 [[0, 0], [1, 1], [2, 0]]
14:47:07 <blsqbot> | 2 [[0, 0], [1, 0], [2, 1]]
14:47:22 <J_Arcane> DAmnit. Some jackass tried to hack try-racket.
14:47:32 <mroman> !blsq {1 0 0}iR<>)zi)?*sp
14:47:33 <blsqbot> | [Sh, "\n", ERROR: Burlesque: (.*) Invalid arguments!, "\n", "[0, 1] [1, 0] [2, 0]", "\n", Sh, "\n", ERROR: Burlesque: (.*) Invalid arguments!, "\n", "[0, 0] [1, 1] [2, 0]", "\n", Sh, "\n", ERROR: Burlesque: (.*) Invalid arguments!, "\n", "[0, 0] [1, 0] [2,
14:47:49 <mroman> !blsq {1 0 0}iR<>)zim{p^?*}sp
14:48:18 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}sp
14:48:25 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}
14:48:25 <blsqbot> | {{0 0} {2 0} {3 0} {0 0} {2 0} {3 0} {0 0} {2 1} {3 0} {0 0} {2 0} {3 1}}
14:48:37 <mroman> !blsq {1 0 0 0 0}iR<>)zim{p^?*}sp
14:48:51 <mroman> J_Arcane: Was he successful?
14:49:26 <J_Arcane> He was trying a bunch of shit to break out of the sandbox, looks like all he managed to do was make Racket run out of memory.
14:50:59 <mroman> !blsq {1 0 0 0 0}iR<>)zim{p^?*}tpsp
14:51:00 <blsqbot> | 0 2 3 4 0 2 3 4 0 2 3 4 0 2 3 4 0 2 3 4
14:51:00 <blsqbot> | 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1
14:51:13 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}tpsp
14:51:47 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}tpp^?+
14:51:47 <blsqbot> | {0 2 3 0 2 3 0 3 3 0 2 4}
14:51:58 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}tpp^?+bs
14:51:58 <blsqbot> | "0 2 3 0 2 3 0 3 3 0 2 4"
14:52:02 <mroman> !blsq {1 0 0 0}iR<>)zim{p^?*}tpp^?+BS
14:52:45 <mroman> these new prefixes make it really hard to parse by eye :D
14:54:37 <mroman> b_jonas: ) can also be part of a command though
14:54:50 <mroman> m{.....} is short for {....}m[
14:55:54 <blsqbot> | {ab ) zi BlsqMapBlock [BlsqIdent "ab"]}
14:56:15 <mroman> no show for that either :)
14:56:40 <blsqbot> | {BlsqMapBlock [BlsqIdent "a)"]}
14:56:52 <mroman> ^- but this shows neatly that a) is parsed as a identifier
14:57:23 <mroman> there's some really freaky parsing rules now thanks to parsec's try and all
14:57:29 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:57:55 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:58:32 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:58:36 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:59:04 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:59:33 <mroman> !blsq %:0 %=add{} %=sub{}V
14:59:33 <blsqbot> | ERROR: Unknown command: (d{)!
14:59:33 <blsqbot> | ERROR: Burlesque: (f[) Invalid arguments!
14:59:43 <mroman> !blsq %:0 %add={} %sub={}V
14:59:43 <blsqbot> | <BlsqAssign "add" (BlsqBlock []) False False,BlsqAssign "sub" (BlsqBlock []) False False>
15:00:01 <mroman> that a hashmap with an assignment as a key and value :)
15:00:14 <blsqbot> | BlsqAssign "add" (BlsqBlock []) False False
15:04:00 <mroman> !blsq 2Jq.+10C! }fibernatschi
15:04:07 <mroman> !blsq 3Jq.+10C! }fibernatschi
15:05:05 <HackEgo> [wiki] [[Zero]] M http://esolangs.org/w/index.php?diff=41010&oldid=39480 * Nooodl * (+4) duh
15:06:46 <mroman> !blsq |[3Jq.+10C!|] }fibernatschi
15:06:46 <blsqbot> | ERROR: Unknown command: (|])!
15:06:51 <mroman> !blsq |[3Jq.+10C!]| }fibernatschi
15:06:52 <blsqbot> | {3 3 6 9 15 24 39 63 102 165 267 432}
15:08:45 <S1> what is harder? Malbolge or Zero?
15:09:36 <blsqbot> | {432 267 165 102 63 39 24 15 9 6 3 3}
15:09:49 <mroman> !blsq {3}{Jq.+10!C}rsBS
15:09:49 <blsqbot> | 3 3 6 9 15 24 39 63 102 165 267 432
15:10:04 <mroman> !blsq q1{Jq.+15!C}rsBS
15:10:05 <blsqbot> | 1 1 2 3 5 8 13 21 34 55 89 144 233 377 610 987 1597
15:13:18 -!- ais523 has quit (Ping timeout: 272 seconds).
15:15:01 -!- zzo38 has quit (Remote host closed the connection).
15:17:19 <HackEgo> [wiki] [[Talk:Dimensions]] M http://esolangs.org/w/index.php?diff=41011&oldid=41009 * Oerjan * (+46) unsigned
15:18:28 <int-e> oh it was fun while it lasted... henkma overtook me again.
15:27:34 <oerjan> S1: i think Malbolge is harder because it looks like you can decide halting pseudoprograms for Zero for a long stretch, while Malbolge has an absolute program size limit of just 59048 bytes
15:27:54 <oerjan> (there's a linked list that seems to go up to 100000 bits)
15:29:08 <oerjan> in particular you can surely write a universal tc interpreter within those 100000 bits
15:29:32 <oerjan> but then you would need to include the "real" program in the input.
15:29:57 <S1> cheating I call that
15:30:07 <S1> at least that's not what I had in mind
15:31:36 <oerjan> right, in which case Zero cannot reliably be programmed to do everything tc to an arbitrary input.
15:31:52 <oerjan> but Malbolge is even more limited than that.
15:33:57 <oerjan> i spent some time on channel proving that you are bound to have several independently undecidable bits in a row, eventually, which is how you know you cannot ensure proper matching brackets.
15:36:33 -!- AnotherTest has quit (Ping timeout: 240 seconds).
15:38:12 -!- ais523 has joined.
15:38:46 <ais523> is it just me who puts bounds on arrays in function parameters?
15:42:22 <mroman> Why? Are you using Modula-2?
15:45:51 <ais523> like write_sha256(unsigned char out[static 32])
15:47:31 <Taneb> ais523, that seems a good idea
15:47:42 <mroman> is that const correct?
15:48:20 <ais523> it's writing into a parameter named out
15:49:50 <ais523> so there shouldn't be any const involved, the parameter's being written to
15:50:02 <mroman> I'm not sure whether out will be downgraded to a pointer
15:50:14 <mroman> if you can do out = (char*)foobaz;
15:51:01 <mroman> i.e. char foo(char * p) { return *p; } isn't consty enough
15:51:15 <mroman> that should be const char * const p
15:52:45 <b_jonas> ais523: no, you're not the only one, because see https://gustedt.wordpress.com/2014/09/08/dont-use-fake-matrices/
15:53:48 <b_jonas> ais523: but I for one don't write that kind of thing these days, because instead I use more strongly typed C++ stuff
15:55:00 <fizzie> ais523: It's not a very widespread practice, but I doubt you're the *only* one using it. I think someone on ##c said they're using it too.
15:55:18 <fizzie> It's arguably kind of gratuitous use of C99, but then again so's restrict.
15:55:28 <ais523> also, I love that they have "static" as the keyword
15:55:49 <ais523> it was clearly a case of "what existing keyword used to be syntactically illegal in that context, and has a meaning vaguely approximating the meaning we want?"
15:55:55 <ais523> like the "? extends" and "? super" in Java
15:56:15 <b_jonas> ais523: sure C++ does that too with keywords
15:56:22 <fizzie> And static *has* been the go-to choice for that.
15:56:43 <ais523> fizzie: well, static can mean a bunch of things in English
15:57:50 <fizzie> On the other hand, C99 does introduce a number of "_Foo" keywords too (and C11 continues that).
15:58:56 <b_jonas> fizzie: yes, and that's a good idea
15:59:48 <b_jonas> fizzie: especially _Complex, because it allows potentially adding C99 complexes to C++ in the future, even though the C++ std committee doesn't seem to want that currently.
16:00:07 <b_jonas> if they named the C99 keyword complex, that would have been impossible to match with C++
16:00:08 <fizzie> Perhaps it could've been char foo[long 32], to denote the passed pointer points to an array that's at least 32 elements *long*.
16:00:52 <b_jonas> fizzie: ugh... that wouldn't work because it becomes a C++ construction cast expression if there's parenthesis after the long
16:01:11 <b_jonas> and the same is true for _Atomic vs atomic I think
16:02:17 <fizzie> keyword: one of auto break case char const continue default do double else enum extern float for goto if inline int long register restrict return short signed sizeof static struct switch typedef union unsigned void volatile while _Alignas _Alignof _Atomic _Bool _Complex _Generic _Imaginary _Noreturn _Static_assert _Thread_local.
16:02:46 <b_jonas> fizzie: yeah, but there's also a few reserved words like asm
16:03:01 <b_jonas> (and basically all C standard library function names are reserved)
16:03:20 <b_jonas> (no wait, those are reserved only as macros or globals)
16:03:31 <fizzie> "asm" is not reserved, it's just mentioned in appendix J.5 as a common extension.
16:04:56 <fizzie> Well, in C11 it appears a total of four times, three times in J.5.10 and once in the index. And J.5p1 doesn't say anything about it being reserved either.
16:05:05 <b_jonas> in C11 it's "common extensions
16:05:47 <b_jonas> still, it's proerly a keyword in C++11
16:06:07 <b_jonas> it's defined as a real keyword
16:06:27 <b_jonas> and of course C++ has like thirty new keywords or something
16:07:53 <b_jonas> some of them are library macros in C, like I think: alignas alignof bool static_assert thread_local and and_eq bitand compl not not_eq or or_eq xor xor_eq
16:09:04 <b_jonas> and some of them are library types in c: char16_t char32_t wchar_t
16:09:26 <fizzie> There's no shortage of reserved identifiers in C, of course. /^_[A-Z_]/ for any use, /^_/ in general as identifiers with file scope in both ordinary and tag name spaces, and pretty much everything listed in the library section (with some restrictions -- like those that are defined as macros are only restricted identifiers if the header is included, and identifiers with external linkage can be ...
16:09:32 <fizzie> ... used for other purposes).
16:12:39 <b_jonas> oh, I forgot these which are also macros in C: true false
16:13:49 <b_jonas> there's of course a few C++ keywords that will never appear in C, because they're so C++-specific, these defniitely: catch delete dynamic_cast friend namespace operator private protected public template throw try typeid virtual
16:15:39 <b_jonas> and a few others that are likely not to go in C but who knows for sure
16:29:48 <fizzie> ^8ball Does this work?
16:33:58 <oerjan> ^8ball Does this fail?
16:40:28 <ais523> is it possible to determine a computer's hostname remotely?
16:40:47 <ais523> someone sent me an email where the From, To, and body are all Shellshock exploit strings
16:41:00 <ais523> except the body contains the hostname of the system that received it
16:41:19 -!- shikhin has joined.
16:41:27 -!- centrinia has joined.
16:41:35 <ais523> and I'm unclear as to whether it was obtained via an exploit, or if they discovered it some other way
16:41:52 -!- S1 has quit (Ping timeout: 258 seconds).
16:43:10 <b_jonas> ais523: maybe the hostname was on a dns server somewhere?
16:43:23 <b_jonas> ais523: is it a windows machine or a unix one?
16:43:41 <b_jonas> is the hostname "debian" or some other simliar very common hostname?
16:43:43 <ais523> I'm planning to retire it soon
16:44:23 <ais523> it's in its own /etc/hosts
16:44:31 <ais523> but not anyone else's as far as I know
16:44:32 <b_jonas> hmm, does smtp tell the hostname if you run a client on that machine?
16:44:40 <ais523> ah, that's an excellent idea
16:44:54 <ais523> yeah, it announces the hostname in the 220
16:45:13 <ais523> that's almost certainly where the exploit attempt got the hostname from
16:45:38 <ais523> so I'm pretty sure that this was a failed (although clever) exploit
16:46:04 <ais523> if you're interested, it was trying to run a wget command
16:46:11 <ais523> I can give you the URL if you like
16:46:30 <ais523> in case you want to give the hacker some false positives
16:48:48 <ais523> b_jonas: thanks, anyway
16:48:57 <ais523> it's nice to clear things up
16:51:06 <b_jonas> no, thanks, I don't need it now
16:53:02 <ais523> the other thing I'm wondering is why my server decided to send that email to me, rather than just drop it
16:53:17 <ais523> it must have been sent to root@ or support@ or one of the similar addresses that are redirected to my address
16:53:25 -!- quintopi1 has joined.
16:53:40 <ais523> ooh, I can probably check the headers
16:54:07 -!- quintopi1 has quit (Client Quit).
16:54:12 <ais523> right, it was sent to root@«hostname»
16:54:19 -!- MDream has changed nick to MDude.
16:55:00 <ais523> (does anyone else here use «» for quoting metasyntactic variables in computerese, because anything in ASCII could potentially be confused to be literal?)
16:56:44 <b_jonas> ais523: no, but I sometimes use “” that way
16:57:01 <b_jonas> wait, metasyntactic variables? no
16:57:13 <b_jonas> I do the opposite: I quote literals with double quotes
16:57:48 -!- AnotherTest has joined.
16:58:40 <fizzie> My rfk86@ address only gets spam.
16:58:59 <fizzie> I don't think it has ever received a non-spam email.
16:59:00 <oerjan> ais523: if <> was good enough for backus, it's good enough for me.
16:59:23 <ais523> oerjan: backus had more than one font, and wasn't afraid to use it
16:59:54 <oerjan> next you'll tell he wrote in hebrew or something.
17:06:11 <mroman> meta-metasyntactic variables .
17:06:40 <oerjan> let's have randall munroe write a paper on it.
17:07:28 <ais523> oerjan: what do you think of my esolang, btw? you're the resident fractran expert
17:07:41 <ais523> although I'm not sure if the point being made has much to do with fractran
17:08:47 <oerjan> it reminds me ever so slightly of the question of whether fractran with unordered commands is tc (no).
17:09:53 <ais523> in this case, though, there is ordering
17:09:59 <ais523> also the =0 thing screws up the proof
17:10:45 <ais523> I haven't thought about the matter much
17:10:59 <ais523> although if you say fractran with unordered commands and =0 is sub-TC, I believe you
17:11:49 <oerjan> you can encode what command to run in a flag which is to be zero
17:12:29 <ais523> when doing computational class proofs, I find it easier to prove something's in a higher class than expected, than a lower class
17:14:46 -!- NATT_SiM has joined.
17:15:26 <mroman> @oeis 1 1 2 3 5 10 20 39 78
17:15:27 <lambdabot> Number of digits in n-th Fermat number (A000215).[1,1,2,3,5,10,20,39,78,155,...
17:21:27 -!- oerjan has quit (Quit: leaving).
17:22:00 -!- S1 has joined.
17:36:29 <tromp> pretty silly yo have sequences that are "Number of digits in some other sequence"
17:41:35 <lambdabot> Number of compositions of the integer n in which the first part is >= the ot...
17:42:15 <mroman> lambdabot should really respond with the A number
17:42:53 <J_Arcane> My for loop is going to drive me mad.
17:43:09 <HackEgo> "But I don't want to go among mad people," Alice remarked. "Oh, you can't help that," said the Cat: "we're all mad here. I'm mad. You're mad." "How do you know I'm mad?" said Alice. "You must be," said the Cat, "or you wouldn't have come here."
17:43:51 <int-e> I like thinking of the cat as the voice of reason.
17:44:01 <J_Arcane> I know how to write a for-like loop functionally, with carryover. What I do not seem to know how to do is write a macro that is general enough to make that process easy.
17:46:24 <HackEgo> Cats are cool, but should be illegal.
17:47:06 <mroman> `learn Alice doesn't want to go among mad people.
17:47:08 <HackEgo> Learned 'alice': Alice doesn't want to go among mad people.
17:47:12 <HackEgo> Alice doesn't want to go among mad people.
17:48:38 -!- Phantom_Hoover has joined.
17:48:39 <J_Arcane> It's the damn carry keyword that's the trickiest. See, Racket does this thing where some of the for loops accumulate the final value of each recursion in something, like a list or just a total or whatever. I want to write a generalized CARRY function that does this instead.
17:50:18 <J_Arcane> CARRY is like a BREAK, but you feed it a value, and that value becomes the new value of the accumulator, which is then passed to the next iteration.
17:50:33 -!- S1 has quit (Quit: S1).
17:50:43 <Bike> does racket not have a weird panoply of iteration libraries like common lisp does
17:50:53 -!- NATT_SiM has quit (Remote host closed the connection).
17:51:11 <mroman> defmacro is the loop of al loops.
17:51:12 <Bike> wow why did i think "panoply" meant that, it totally does not
17:51:26 <J_Arcane> But that's the problem: it has a shitload of them. For each possibility.
17:51:51 <J_Arcane> Ie. accumulating to a list is a different function from accumulating a value, etc etc.
17:52:57 <J_Arcane> There are *30* different for loop functions in the Racket standard language.
17:53:18 <int-e> one loop for everyone
17:53:29 -!- NATT_SiM has joined.
17:57:10 <HackEgo> aah ambiguous acronym here
17:57:44 <J_Arcane> Also, I think I might simplify matters considerably if I just focus on iterating over a list, and then provide different functions to generate the list. Lists are much easier to iterate in Lisp ...
17:57:47 <FireFly> Bike: Wikipedia suggests it's used to "refer to any complete or impressive collection", so I don't see why it wouldn't work
18:05:49 -!- S1 has joined.
18:06:01 -!- S1 has left.
18:06:14 -!- DTSCode has quit (Read error: Connection reset by peer).
18:07:29 -!- DTSCode has joined.
18:12:52 <J_Arcane> Oh FFS. let* doesn't allow you to define a proc-id like let does, so the (let loop ...) form work work with it.
18:32:42 -!- FreeFull has quit (Quit: BBL).
18:36:35 <J_Arcane> sometimes hygienic macros are a pain in my ass.
18:43:58 -!- centrinia has quit (Ping timeout: 244 seconds).
18:55:47 -!- NATT_SiM has quit (Remote host closed the connection).
19:02:29 -!- NATT_SiM has joined.
19:03:34 -!- NATT_SiM has quit (Remote host closed the connection).
19:06:09 -!- ^v has quit (Quit: Leaving).
19:08:54 <fizzie> fungot: What do you think of cats?
19:08:54 <fungot> fizzie: ( just five questions... all fit on a standard computer."
19:09:47 <fizzie> fungot: Yes, I think most cats would fit on a computer, though I'm sure there are exceptions. What's the second question?
19:09:48 <fungot> fizzie: wow. no mutta siinä fnord fnord. kalan kuolema fnord kun tulin takaisin. en sitten tied. kun tnn tahtoisin olla kovin fnord, ihan sama se mulle on onks se lähellä vai kaukana ;p
19:10:18 <fizzie> fungot: Uh, don't mix Latin-1 and UTF-8 like that, please.
19:11:03 <int-e> oooh fun it's a byte-based model?
19:11:37 <fizzie> Well, I mean, the language model units are just (integral) token IDs.
19:13:20 <fizzie> But the token text is "byte-based" in the sense that it's just whatever bytes there were in the input.
19:14:49 <fizzie> I was going to translate that for those people sadly deprived in the Finnish language understanding department, but can't quite convey the tune.
19:15:32 <fizzie> It's (very) approximately: "Wow. Well, there fnord fnord. The death of a fish fnord when I came back. I just don't know. Because today I'd like to be very fnord, I don't care at all whether it's near or far :p"
19:19:03 <fizzie> (It's also composed out of 4 different comments from the same person.)
19:23:14 <ais523> presumably there are more fnords in Finnish, because there are more observed words in English?
19:23:27 <ais523> or is the proportion of unique words much the same between small and large corpuses?
19:23:43 <ais523> actually I'd expect it to be the same once the corpuses get sufficiently large, and probably related to e somehow
19:23:47 <fungot> ais523: which can be implemented in an esoteric language.
19:23:58 <ais523> that made surprising sense in context
19:24:17 <fizzie> ais523: It's somewhat larger in Finnish because of so many uniquely inflected forms, I believe.
19:24:26 <ais523> oh right, that might make sense
19:25:31 <fizzie> ais523: You get the same amount of OOV (out-of-vocabulary) words when using a 100k-word English lexicon compared to a 2.4M-word Finnish lexicon, or something like that, modulo probably misremembered exact numbers.
19:26:05 <fizzie> For "comparable" text data, which was something like newspaper stuff.
19:27:31 <int-e> is this due to grammar-induced word variations?
19:27:47 <int-e> and perhaps compoundnouns
19:28:07 <fizzie> The general agglutitinativeness.
19:28:15 <int-e> err, nouncompounds, the other sounds wrong even when translated into German :)
19:28:53 <fizzie> Sub-word units are popular for statistical language models of Finnish.
19:30:17 <fizzie> You can do a rule-based morphological analysis which won't go too badly wrong, or you can do http://www.cis.hut.fi/projects/morpho/ instead if you just want sub-word units and not linguistically meaningful morphemes.
19:35:02 <newsham> https://twitter.com/omershapira/status/533289787667787776/photo/1 <- eso?
19:44:55 -!- vanila has joined.
19:45:19 <vanila> How do you discover small Y combinators for SK calculus?
19:45:27 <b_jonas> ever since I work with images and videos, all I see in images and videos is their quality, not their content!
19:45:29 <int-e> vanila: brute force
19:47:13 <int-e> vanila: look for combinators K such that K f -> f (f (f (f ...))) after doing a couple of hundred reductions, then take those candidates and look whether that goes on forever.
19:47:18 <tromp> vanila: i found Y = S S K (S (K (S S (S (S S K)))) K) by just manually playing around
19:47:22 <int-e> vanila: sorry, I should use M.
19:48:00 <tromp> after noticing that SSK x y = x y x
19:48:24 <tromp> that turns out to be the smallest possible one
19:48:42 <vanila> that's so cool tromp :D
19:48:56 <int-e> I should redo that brute force computation some time; I seem to have lost the code though.
19:49:55 <elliott> tromp: you've proved it's the smallest possible? that surprises me
19:50:27 <tromp> other people did; like int-e
19:50:59 <vanila> I wrote a brute force search but I didnt find anything
19:51:01 <elliott> Lymia: https://github.com/riven8192/LibStruct you wanted stack allocation in java, right?
19:51:09 <int-e> (Just to see how close I was to an actual proof. I know so much more about that today then I did back then.)
19:52:13 <Lymia> elliott, it looks like more compiler magic
19:52:58 <Lymia> Doesn't stop the fundamental problem of not having a direct way to return multiple values from a function without stack allocation
19:53:00 <elliott> Lymia: oh, I guess it can't do arrays without you unrolling them as fields?
19:53:34 <elliott> I guess the problem is just that java doesn't have references to stack-allocated objects. so there's nothing you can do.
19:54:43 <Lymia> super.visitIntInsn(SIPUSH, struct2info.get(_returnsStructType).sizeof);
19:54:43 <Lymia> super.visitMethodInsn(INVOKESTATIC, StructEnv.jvmClassName(StructMemory.class), "allocateCopy", "(" + wrapped_struct_flag + "I)" + wrapped_struct_flag, false);
19:54:51 <Lymia> Looks like it involves an allocation
19:55:12 -!- NATT_SiM has joined.
20:03:34 -!- NATT_SiM has quit (Remote host closed the connection).
20:14:13 <J_Arcane> Awesome. Thanks to some help from #racket, I now have my FOR w/CARRY.
20:17:45 -!- Bicyclidine has joined.
20:17:46 -!- shikhin has quit (Ping timeout: 244 seconds).
20:19:59 -!- shikhin has joined.
20:20:25 -!- ^v has joined.
20:27:02 -!- NATT_SiM has joined.
20:27:15 -!- NATT_SiM has quit (Remote host closed the connection).
20:27:27 -!- NATT_SiM has joined.
20:32:43 -!- NATT_SiM has quit (Remote host closed the connection).
21:00:51 -!- FreeFull has joined.
21:04:09 -!- Bicyclidine has quit (Ping timeout: 265 seconds).
21:05:20 -!- NATT_SiM has joined.
21:05:29 -!- NATT_SiM has quit (Remote host closed the connection).
21:10:15 -!- Primal has joined.
21:12:03 -!- Primal has quit (Client Quit).
21:16:04 <b_jonas> does someone have a roman numeral to number translator bot here?
21:16:17 <b_jonas> does burlesque have such a builtin or something?
21:17:17 <ais523> `! befunge ;@,2;ROMA4#;(3,
21:17:18 <HackEgo> Unsupported instruction ';' (0x3b) (maybe not Befunge-93?)
21:17:30 <ais523> that's the wrong befunge
21:17:37 <ais523> `! befunge98 ;@,2;ROMA4#;(3,
21:17:46 <ais523> also I can't actually remember how befunge works
21:17:52 <ais523> `! befunge98 ;@,2;ROMA4#;(3,@
21:18:01 <ais523> `! befunge98 ;@.2;ROMA4#;(3.@
21:18:07 <HackEgo> ..............................................................................................................................................................................
21:18:24 <ais523> `! befunge98 ;@.2;ROMA4#;(C.@
21:18:39 <ais523> I give up, I'd actually need to read docs to get this working
21:19:12 -!- Primal has joined.
21:19:30 <ais523> someone just sent me spam, explicitly marked as spam
21:19:38 <ais523> with a link at the top to "report it as spam"
21:19:49 <ais523> that's going to catch loads of people into following the link
21:19:59 -!- Ether_ has joined.
21:21:43 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: fromroman: not found
21:22:15 <HackEgo> ` \ ^.^ \ ̊ \ ! \ ? \ ¿ \ @ \ ؟ \ ＷＥＬＣＯＭＥ \ \ \ 8ball \ 8-ball \ aaaaaaaaa \ addquote \ addwep \ allquotes \ analogy \ anonlog \ as86 \ aseen \ bf \ bienvenido \ botsnack \ bseen \ buttsnack \ calc \ CaT \ catcat \ cats \ cc \ cdecl \ c++decl \ chroot \ coins \ CoInS \ complain \ complaints \ danddreclist \ define \ delquo
21:22:42 -!- nycs has joined.
21:22:47 <b_jonas> `run echo $'#!/usr/bin/perl\n''$_=<>;sub k{my$t;$t=~y/IVXLC/XLCDM/,$t.=("",I,II,III,IV,V,VI,VII,VIII,IX)[$_]for/./g;$$t=$_;$t}k for s""\$"..4e3;print eval(),$/' > bin/fromroman && chmod a+x bin/fromroman
21:22:54 <HackEgo> Can't open LXXXIV: No such file or directory at /hackenv/bin/fromroman line 2.
21:23:15 <b_jonas> `run echo $'#!/usr/bin/perl\n''$_=shift;sub k{my$t;$t=~y/IVXLC/XLCDM/,$t.=("",I,II,III,IV,V,VI,VII,VIII,IX)[$_]for/./g;$$t=$_;$t}k for s""\$"..4e3;print eval(),$/' > bin/fromroman && chmod a+x bin/fromroman
21:23:33 <b_jonas> I hope that's correct, I got it from my golf entry
21:23:43 <b_jonas> but we should replace it with something that checks for invalid input
21:24:19 <b_jonas> though actually, this should reject some of the invalid input already
21:24:20 -!- `^_^v has quit (Ping timeout: 255 seconds).
21:24:35 <ion> `run fromroman IS••
21:25:20 <b_jonas> ais523: it works by converting all numbers from 1 to 4999 to roman, and then checking that, so you have to hit a variable or other valid perl syntax to make it work wrong
21:25:26 <ais523> Primal: if it's not particularly spammy, yes; otherwise, use #esoteric-blah or make your own channel
21:25:37 <ais523> testing bots often does get a bit spammy, though
21:25:43 <b_jonas> actually, let me try to make it safer
21:25:47 <Primal> Nah i just need to do one thing
21:26:12 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
21:26:50 <Primal> Its on my network im just using the chat as an indirect access point for the area thats running my bot sorry >_>
21:27:10 <b_jonas> `run echo $'#!/usr/bin/perl\n''sub k{my$t;$t=~y/IVXLC/XLCDM/,$t.=("",I,II,III,IV,V,VI,VII,VIII,IX)[$_]for/./g;$r{$t}=$_;$t}k for s""\$"..4e3;print $r{(shift=~/(\w+)/)[0]},$/' > bin/fromroman && chmod a+x bin/fromroman
21:27:25 <ais523> Primal: oh, the bot's basically reading your logs rather than the channel itself?
21:27:56 <Primal> Just mine it ignores every other name variable
21:28:32 <Primal> I dont think i could bring myself to have it log the entire channel that would just be rediculous
21:28:51 -!- DTSCode has quit (Quit: Leaving).
21:28:56 <ais523> Primal: clog and glogbot disagree with you on that, I think
21:29:52 <Primal> I already have all logs listed as a .txt-compressed file
21:30:08 <Primal> I just dont want to have it open at all times for my bot to list it
21:30:36 <b_jonas> `run echo $'#!/usr/bin/perl\n''sub k{my$t;$t=~y/IVXLC/XLCDM/,$t.=("",I,II,III,IV,V,VI,VII,VIII,IX)[$_]for/./g;$r{$t}=$_;$t}print k((shift=~/(\w+)/)[0]),$/' > bin/toroman && chmod a+x bin/toroman
21:30:53 -!- NATT_SiM has joined.
21:31:09 <ais523> hmm, this is getting dangerously into the realm of "optimizing for the wrong thing"
21:31:15 <ais523> something which is clearly ontopic for this channel
21:31:29 <b_jonas> `run echo $'#!/usr/bin/perl\n''sub k{my$t;$t=~y/IVXLC/XLCDM/,$t.=("",I,II,III,IV,V,VI,VII,VIII,IX)[$_]for/./g;$t}$_=(shift=~/(\w+)/)[0];print k,$/' > bin/toroman && chmod a+x bin/toroman
21:31:32 <ais523> let's try to minimize the CPU usage of mke2fs
21:31:36 <Primal> well its event threaded based
21:31:46 <ais523> (I hope you have a ton of drives that need formatting in parallel, for you to test this on)
21:32:01 <b_jonas> ais523: use ramdisks for that
21:32:26 <Primal> How far can the toroman thing go up to
21:32:34 <b_jonas> ais523: minimize the CPU usage on where? modern computers, or ancient slow cpus?
21:32:35 <ais523> b_jonas: then mke2fs's CPU usage would hae a higher chance of actually being relevant
21:32:45 <vanila> zzo38 :When will there be more blog posts on your gopher blog
21:33:06 <ais523> b_jonas: let's pick a system that doesn't actually have hard drives
21:33:43 <b_jonas> ais523: minimize the cpu usage, but don't eliminate any of the disk seeking
21:34:19 <ais523> b_jonas: right, we're optimizing for CPU usage here, other factors are secondary
21:34:27 -!- NATT_SiM has quit (Read error: Connection reset by peer).
21:34:28 <b_jonas> ais523: also, wait, for which filesystem? there could be a difference between ext[23] which needs lots of inodes and stuff initialized and the more modern ext4
21:34:36 <ais523> although, back in C64 days, CPU was actually a factor
21:34:38 <Primal> "redis++(error.file)[]{{++++<>+++]."redis.compression|error|)([2.cpre]-reboot.false
21:34:48 <Primal> Sorry i was just rebooting it
21:34:58 <ais523> nowadays it takes some effort to construct a program where the CPU usage isn't dwarfed by the memory bandwidth requirements
21:34:59 <b_jonas> ais523: are we formatting a tape or a diskette?
21:35:01 <ais523> some hash algorithms can do it
21:35:10 <ais523> b_jonas: tape, you can use ext2 with tapes, right?
21:35:33 <b_jonas> that's seekable only manually
21:35:48 <b_jonas> oh, I see! so you want to notify the user when to press the rewind button with minimal cpu time?
21:36:03 <b_jonas> or does the user just rewind every time you reach the end of the tape?
21:36:15 <b_jonas> and you notify him only when the formatting is complete?
21:36:17 <ais523> you can get the cassette player to rewind when it reaches the end of the tape
21:36:18 <Primal> btw my bot is i think listed as Ether in here idk if it even came in so i could just be putting in random stuff
21:36:32 <b_jonas> ais523: rewind and play again? hmm
21:36:49 <b_jonas> Primal: there's an "Ether_" here
21:36:58 <ais523> I used to have a casette player which could just physically turn the read/record head around to see the other side of the tape
21:37:12 <ais523> so it could play one side forwards, then the other side forwards
21:37:25 <ais523> and it had a mode where it could do that automatically
21:37:33 <ais523> this sort of hardware support is clearly useful in minimizing CPU time
21:37:53 <b_jonas> ais523: are we allowed to burn custom ROM?
21:38:09 <b_jonas> because with the normal ROM, the interrupt location points into the ROM, which takes extra CPU
21:38:16 <b_jonas> or can that be bank-switched off?
21:38:23 <b_jonas> I don't really know how a c64 works
21:38:26 <ais523> I actually don't know if that's bank-switchable
21:38:30 <ais523> not familiar with the C64 either
21:38:49 <Primal> The fact that im running off a windows 95 Threaded Cpu doesnt make my bots performance any better
21:38:55 <fizzie> The Datassette (or at least the 1530s I have) does have a (resetable) counter, you can ask the user to rewind/fast-forward to a particular value.
21:39:10 <fizzie> I suspect it's not all too accurate, though, so it's perhaps best to round down a little.
21:39:32 <b_jonas> fizzie: sure, but we're minimizing cpu usage, so it's easier to just rewind completely all the time
21:39:50 <b_jonas> it can't be completely accurate anyway so you need a loop to wait for the right sector, and that's easier if you always start rewinded
21:40:00 <b_jonas> sector? block? what's the thingies on a tape called
21:40:00 <fizzie> That would presumably depend on how cheap it is to process all the incoming data.
21:40:04 <b_jonas> I don't know how that works
21:40:19 <b_jonas> fizzie: dunno, I have no idea what the casette controller is like
21:40:22 <ais523> I'm having trouble parsing "windows 95 threaded cpu"
21:40:30 <ais523> windows 95 is presumably the OS, and a cpu is a cpu
21:40:35 <b_jonas> as in, is it like the PC floppy contorller which can just seek to a sector all alone?
21:40:37 <ais523> but what does "threaded" refer to?
21:41:32 <b_jonas> luckily I started computing when mostly reliable drives already existed
21:41:41 <b_jonas> no messing with stupid tapes that fail to work all the time
21:41:59 -!- Bicyclidine has joined.
21:42:53 <fizzie> b_jonas: There's no "controller" to speak of, really. I mean, e.g. the motor to run the tape is just directly wired to the 6510 on-chip port, bit 5.
21:43:13 <ais523> when I started with computers, 5¼-inch floppy drives were just starting to become common on hobbyist computers (most used tape before then, and most of the documentation I could find assumed tape computers)
21:43:38 <b_jonas> fizzie: not for the motor, but recognizing the signal
21:44:12 <Primal> Threaded refers to the threaded base event that helps me run the bots 4 library's so i can enter all of them at the same time without crashing my RAM and the python compiler script that runs the third library which is the main core of the bot
21:44:18 <b_jonas> ais523: I specifically said the PC floppy controller. the floppy drive itself is very dumb, it has almost no electronics.
21:44:47 <b_jonas> Primal: I don't understand any of that, but I think you're probably on the right channel
21:44:55 <fizzie> b_jonas: The read signal is just wired to the CIA 1 serial interface, and causes an IRQ to occur.
21:45:00 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=41012&oldid=40699 * 78.10.230.8 * (+124) /* Optimizing implementations */ +1
21:45:07 <ais523> actually, one of the weakest points in my knowledge of computing is the hardware end of the interface between hardware and software
21:45:11 <b_jonas> fizzie: an IRQ for every what? bit? block? byte?
21:45:13 <ais523> except when I'm writing it myself
21:45:31 <b_jonas> fizzie: what decodes the sound to digital data and how far does it go? like, is the error correction done in the cpu? in the controller?
21:45:59 <b_jonas> fizzie: I mean, the PC floppy controller reads or writes an entire sector using DMA and then fires an interrupt
21:46:40 <b_jonas> ais523: the IBM PC XT is a classic gem, it's worth to read about it
21:47:04 <fizzie> b_jonas: The IRQ happens whenever the analog waveform crosses a zero.
21:47:14 <b_jonas> fizzie: oh... that sounds scary
21:47:15 <fizzie> b_jonas: And the software takes care of decoding the bits out of that.
21:47:25 <b_jonas> so it's like once or twice every bit, at least
21:47:29 <fizzie> See http://wav-prg.sourceforge.net/tape.html
21:47:32 <ais523> OK, so we're in the category of "this IRQ needs to be really crazily fast"
21:47:37 <b_jonas> then the software must also do the error correction
21:47:56 <b_jonas> ais523: um, no, it's the opposite way: the data on the tape is really slow
21:48:24 <Primal> What browsers/ irc clients to you guys use
21:48:32 <fizzie> Of course it also means you can quite freely decide the encoding. But the default KERNAL stuff is really slow, yes.
21:48:45 <ais523> Primal: someone was in here with MS Comic Chat a while back
21:48:48 <ais523> at least I think it was here
21:49:11 <ais523> it seems like the sort of thing you'd like, based on your description of your hardware setup
21:49:14 <b_jonas> fizzie: well, the limitation is mostly the bad sound quality you get from the casette and casette player
21:49:41 <FireFly> I think irssi is quite popular in here
21:49:46 <ais523> that said, IIRC (I may be wrong on this), it was the first use to which Comic Sans was put outside Microsoft (again IIRC, it was created for Microsoft Bob but not actually used there)
21:49:48 <b_jonas> is the floppy controller for the c64 also that crazy low-level? or is it saner?
21:49:51 <ais523> let me go check Wikipedia to see how wrong I was
21:49:53 <Primal> This is my secondary computer which i test crap on
21:49:57 <fizzie> b_jonas: Well, I mean, tapes came with faster loaders.
21:50:04 <fizzie> b_jonas: http://en.wikipedia.org/wiki/Fast_loader#Cassette_tapes
21:50:40 <fizzie> b_jonas: Unless I misremember, there's the same processor in the floppy drive as there is in the computer, so there's rather more flexibility there.
21:50:47 <ais523> it was created for Microsoft Bob, bot not ready in time, so I was right on that bit
21:50:49 <Primal> Wait why do you guys need cassette tapes couldn't you just uh well i guess you need them if you want the data thats on it
21:50:57 <ais523> but MS Comic Chat was not the first time it was used
21:51:19 <b_jonas> fizzie: ah, so the casette controller does sometimes also have higher level stuff, nice
21:51:40 <fizzie> b_jonas: What's this "casette controller"?
21:51:43 <b_jonas> I mean, there's the pc serial console, which sends or receives a byte and once, and interrupts you for each
21:51:59 <b_jonas> fizzie: casette drive controller. the part of the hardware that interfaces the analog casette player to the computer.
21:52:34 <b_jonas> isn't that what it's called?
21:52:50 <fizzie> b_jonas: Didn't we just go through that there isn't really much that you could call that.
21:53:01 <ais523> <Primal> Wait why do you guys need cassette tapes couldn't you just ← you may be missing the point of this channel (although as a Windows 95 user, you probably aren't)
21:53:01 <Primal> im just gonna try and talk here through a terminal for a test brb
21:53:12 <b_jonas> fizzie: yeah, but that thing you linked to says some computers have more than that
21:54:05 <Primal> Im not missing the point im just randomly switching back and forth through stuff and checking things so im very scatter brained atm or w/e
21:54:50 <fizzie> b_jonas: I... which page? I don't see anything like that in either the Wikipedia page or the wav-prg tape explanation page.
21:55:54 <ais523> Primal: if it helps, I had IE6 installed on my previous laptop
21:56:03 <ais523> on the Linux partition, not the Windows partition
21:56:26 <Primal> >_> well then i might try that out
21:57:40 <Ether_> [{say."@user.compiler:Primal"}]++(" end . #estoric/?channels=esoteric&uio=d4. " ) [{{ " Test " }}]
21:58:02 <ais523> that is one weird syntax
21:58:02 <Primal> ok well i have to get rid of [{say."@user.compiler:Primal"}]++(" end . #estoric/?channels=esoteric&uio=d4. " ) from showing
21:58:25 <ais523> but the [{{}}] around " Test " is intentional?
21:58:37 <b_jonas> fizzie: the wikipedia page, but maybe I just misunderstood it. sorry.
21:58:38 <ais523> also, #estoric is a different channel
21:58:40 <fizzie> ais523: I don't know, I mean, it's got balanced brackets and all.
21:59:08 <ais523> fizzie: actually this is reminding me uncomfortably of ESME
21:59:11 <fizzie> b_jonas: I mean, the page is mostly about the floppy drives, there's just a short three-paragraph thing about cassette tapes, and that's all software-related.
21:59:26 <Primal> yeah i know its just having trouble determining stuff
21:59:55 <Primal> Ill have to go on my linux for anything further than that which just got outputed
22:02:26 <Primal> [{{}}] yes this is intentional it helps the 2nd library core determine which place to put it in the output eh think of it as these [{{}}] weigh down the text output
22:02:45 <Primal> Without those it usually deletes the text output when it gets run through
22:03:54 <Primal> Ok ill be back in like a day or so w/e i have to go on a trip
22:04:14 <Primal> Away from all the city life
22:04:21 -!- Ether_ has quit (Quit: Page closed).
22:04:29 -!- Primal has quit (Quit: Page closed).
22:04:41 <ais523> wait, the bot was using web IRC?
22:04:52 <ais523> …I need to stop thinking about this, it's making my head hurt
22:05:25 <ais523> actually, at this point I'm hoping that that was a really impressive and well-done trolling attempt
22:05:29 <b_jonas> if that's true, then he was indeed on the right channel
22:05:39 <b_jonas> yes, that's the other possibility.
22:05:47 <b_jonas> we'll see tomorrow, hopefully
22:05:55 <ais523> the social route to something like that would be easier than the technical route
22:06:25 <ais523> and as I said, it's very reminiscent of ESME, which I suspect was an excessively complex project to troll zzo38
22:07:34 -!- NATT_SiM has joined.
22:08:34 <ais523> in case it's relevant, that IP traces to a school in Washington
22:11:18 <fizzie> It seems moderately hard to find details on the kernel ROM tape loader routines, since all material seems to be about Turbo Tape -style faster loaders. (Which apparently just use pauses of two different lengths between the triggers to denote 0 and 1 bits, meaning one interrupt per bit.)
22:11:19 -!- Patashu has joined.
22:12:13 <fizzie> An "Information Processing Cooperative" sounds mighty shady.
22:12:42 <Bicyclidine> http://en.wikipedia.org/wiki/Washington_School_Information_Processing_Cooperative
22:12:47 <b_jonas> ais523: do you think tompn is a trolling attempt too, or does he just not understand what this eso stuff is about?
22:12:51 <fizzie> (If it were a "coöperative", then it'd be benign.)
22:13:12 <Bicyclidine> probably indicates a high school. i think the major colleges have their own ipv4 blocks or some shit.
22:13:16 <fizzie> ais523: And did you notice another case of non-nested loops?
22:13:17 <elliott> I don't get why people think TomPN is so uniquely terrible or anything.
22:13:23 <elliott> aren't we used to mediocre languages by now?
22:13:41 <fizzie> b_jonas: Right. I only remembered the musical notes discussion.
22:13:47 <b_jonas> elliott: he isn't that terrible really, he just angered ais by removing some text he wrong
22:14:31 <elliott> I agree that Primal's bot was fake. :p
22:14:43 <elliott> "redis++(error.file)[]{{++++<>+++]."redis.compression|error|)([2.cpre]-reboot.false is some nice "code".
22:15:48 <ais523> right, BF normally has matching brackets
22:15:54 <ais523> also that doesn't look much like BF
22:16:06 <elliott> an IRC bot using redis yet connecting through webchat is kind of a beautifully weird combination
22:16:15 <ais523> elliott: you forget when TomPN put a link to the language on the Main Page
22:16:25 <ais523> that's the first thing that alerted me that something was wrong
22:16:35 <elliott> it's called enthusiastic kids :p
22:16:48 <fizzie> I don't think I'm surprised by mediocricity or anything, I just can't fathom the strange antipathy towards nested loops.
22:17:12 <ais523> there's the use of the phrase "instruction tape" to mean "data tape"
22:17:12 -!- NATT_SiM has quit (Remote host closed the connection).
22:17:24 <ais523> it's now been explicitly /defined/ as "data tape" for Musical notes
22:17:26 <fizzie> Maybe with some sort of non-structured-programming background, but that sounds rather unlikely these days.
22:17:29 <ais523> but it's a rather unintuitive definition
22:17:41 <ais523> doesn't even FORTRAN support nested loops?
22:17:45 <Bicyclidine> have you, like, never been actually trolled
22:18:24 <ais523> Bicyclidine: the days of the truly great trolls have mostly died out
22:18:36 <ais523> you get some pretty good attempts from time to time, though (also a lot more really bad ones)
22:18:46 <fizzie> The FORTRAN I was writing was loops based on line numbers.
22:18:50 <Bicyclidine> mm random webpage says nested loops were common in 77
22:19:02 <Bicyclidine> i guess that makes sense. i could check my book with unreadable code samples i guess
22:19:03 <fizzie> I would think you can nest those, since it's not like it'd complicate the implementation.
22:19:37 <fizzie> You can have several loops end at the same line, though.
22:19:51 <b_jonas> fizzie: it's sort of a come from, isn't it?
22:19:58 <fizzie> It's reminiscent, yes.
22:20:00 <b_jonas> as in, there's no explicit loop closing statement
22:20:33 <b_jonas> does forth have a looping construct that doesn't nest though? I don't know, I'm not a forth guy
22:20:44 -!- AnotherTest has quit (Ping timeout: 244 seconds).
22:20:56 <fizzie> Though I think it's not untypical to put a "continue" statement on the closing line of the loop.
22:21:17 <b_jonas> fizzie: is that like C's continue or what?
22:21:19 <fizzie> It's not really a loop closing statement then either, but it makes it look like one.
22:22:05 <ais523> hmm, Algol used "skip" for the same purpose
22:22:14 <ais523> and at least in mathematical Algol, it's normally only allowed as a no-op command
22:22:17 <b_jonas> ais523: worms uses skip too, with a visual pun
22:22:44 <ais523> however, in Algol 68, I believe it just refers to an arbitrary uninitialized value, which isn't evaluated when used as a command because Algol 68 is call by value
22:22:47 <b_jonas> (um, is that a joke I have to explain, or does everyone on this channel get it by default?)
22:23:15 <fizzie> http://sprunge.us/HZKb -- that's the program-loading bit out of a Befunge-93 interpreter.
22:23:19 <b_jonas> ais523: a variable predefined in the library? or no strict?
22:23:41 <ais523> <b_jonas> (um, is that a joke I have to explain, or does everyone on this channel get it by default?) ← it's hard to tell, after spending a while in this channel it becomes clear you can never understand the context of everything
22:24:06 <ais523> fizzie: I was going to ask "why is there a Befunge-93 interpreter in Fortran", but there's no real point in asking the question
22:24:18 <ais523> I guess it's more out of curiosity "why pick that specific combination of languages" than anything else
22:24:58 <fizzie> I used to use a Befunge-93 interpreter as my initial "getting to know a new language" program, that's why.
22:25:12 <fizzie> Also I believe the pasted snippet could be equivalently written as http://sprunge.us/WXhC
22:25:32 <fizzie> (It's still two loops, nested.)
22:26:04 <b_jonas> fizzie: hmm, then there has to be a Befunge-93 interpreter task on rosettacode.org
22:26:23 <b_jonas> fizzie: maybe add your interpreters there, possibly creating such a task if it doesn't yet exist
22:26:23 <ais523> fizzie: also I'm not used to seeing indentation in fortran
22:26:27 <ais523> it'd be like using indentation in asm
22:26:36 <b_jonas> ais523: yeah... you don't indent on punch cardss
22:26:41 <ais523> (which I assume some people actually use? I'd never really thought of it before this point, but it makes perfect sense for handwritten asm)
22:26:45 <fizzie> ais523: Yes, it's kind of strange. And it looks really silly when there's a continuation line.
22:27:16 <b_jonas> fizzie: not if you're used to seeing ifdefs or labels pulled to the first column in C
22:28:00 <fizzie> In this case, I've put the continuation line marker in the only place it can go to, but also continued with the actual content, unidented.
22:28:31 <fizzie> To wit, http://sprunge.us/MNHG
22:28:47 <ais523> wow, I just realised Fortran 77 postdates both Algol 68 and INTERCAL-72
22:29:00 <elliott> b_jonas: I got it but I'm not sure how much of the channel would :p
22:29:06 <ais523> presumably it was in common use before then, just hadn't hit its "most commonly used ever standard"
22:29:26 <elliott> b_jonas: I never registered that as a pun until you pointed it out though, heh
22:29:37 <elliott> (you don't analyse games you start playing at age ~7-ish very much)
22:29:39 -!- nycs has quit (Quit: This computer has gone to sleep).
22:29:58 <fizzie> FWIW, I missed the Worms comment, but did get it now that it was pointed out.
22:30:37 <ais523> now I'm wondering what sort of self-respecting pentester uses a wget-based payload and doesn't execute the file they download
22:30:45 <b_jonas> elliott: heh, that shows you're young
22:30:46 <ais523> you're leaving traces not only in logs, but on the filesystem
22:31:05 <ais523> the file would go to /
22:31:19 <ais523> which most email daemons can't write
22:31:25 <fizzie> b_jonas: So new, not even 20 years old.
22:31:27 <elliott> b_jonas: yes, and in fact Armageddon was my first game, and it was years after it came out that I got it. (I'm 19.)
22:31:39 <elliott> uh, first worms game. not first game in general.
22:31:45 <elliott> the amiga worms games are kind of weird.
22:32:02 <b_jonas> I hope you had at least played with older games since
22:32:14 <b_jonas> these modern games have it too good with being able to use powerful hardware
22:32:51 <elliott> I've played Worms 2 a bit but it mostly seems like a weaker version of W:A; they're practically the same game in many ways. (would W:A be DLC these days?)
22:32:53 <fizzie> elliott: We were actually kind of wondering here whether you'd be 19 or 18. (I got it narrowed to something thereabouts by log-grepping.)
22:33:00 <elliott> the amiga ones I've tried but they're... not that great.
22:33:07 <elliott> I can't get used to the rope physics. :p
22:33:25 <b_jonas> (btw, I'm still surprised there are so many finns here)
22:33:26 <fizzie> http://en.wikipedia.org/wiki/Liero is what we used to play here.
22:33:36 <elliott> oh, god, yeah, I've played liero
22:33:42 <fizzie> (Well, that and MoleZ.)
22:33:50 <elliott> the rope physics on *that* sure are something
22:34:00 <fizzie> They're very physical, yes.
22:34:18 <elliott> fizzie: I like your wife taking an interest in #esoteric.
22:36:08 <fizzie> It's more general than that, but it's possibly more about what sort of weirdoes the channel regulars are, as opposed to the so-called content.
22:36:21 <FireFly> I never realised the 'skip' pun in Worms either
22:36:34 <elliott> I'm sure I've been satisfying on the "weirdo" front
22:36:36 <ais523> oh wow, I only just realised what specifically in Worms was being referred to
22:36:48 <int-e> tromp: so it looks like I was left with about 30k probably-nonterminating probably-not-fixed-point-combinators.
22:36:55 <ais523> like, I thought you were referencing the specific game series, and you were
22:37:01 <ais523> but I didn't get the greater specifics
22:37:20 <ais523> (btw, was that thing ever useful except in situations where you were highly limited on ammo? and could it be set to limited ammo itself?)
22:37:21 <int-e> tromp: of size 11 or less
22:37:23 <fizzie> Bicyclidine: Like, with multiple levels in case of nested control structures?
22:38:18 <fizzie> Having a different indentation for e.g. labels and instructions (and sometimes directives) wouldn't be all that surprising.
22:40:08 <tromp> ic, int-e. probably that includes 100s where it's not clear whether it's diverging
22:40:20 <FireFly> I draw lines with semicolons to the right of the instructions to indicate nestedness
22:40:22 <tromp> even if you study them manually
22:41:25 <int-e> tromp_: but it's still interesting to filter out some obviously non-productive ones.
22:42:18 <tromp> yes, a divergenct pattern detector should eliminate a large fraction of those 30k
22:47:48 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=41013&oldid=39314 * 67.78.57.11 * (+7) /* maps */
22:48:18 -!- oerjan has joined.
22:50:17 <oerjan> ais523: actually unordered fractran with =0 is tc by reduction from a minsky machine. just choose one boolean flag for each state, then the only thing you need =0 for is when doing a branch on zero in the decrement-and-branch-on-zero instruction.
22:50:50 <ais523> oerjan: right, that makes sense
22:51:15 <ais523> maybe I should make My Unreliable Past unordered, but I kind-of like the looping
22:51:28 <ais523> especially because it matches the looping of input (which is necessary for other reasons)
22:51:39 <ais523> meaning that it may be possible to write a self-interpreter even though you can't write cat
22:54:56 <ais523> what is it with me and languages which have pretty powerful I/O that nonetheless can't do cat?
22:55:15 <int-e> you're a dog person?
22:56:40 -!- NATT_SiM has joined.
22:58:31 -!- nys has joined.
23:00:31 -!- Bicyclidine has quit (Ping timeout: 244 seconds).
23:01:56 -!- ais523 has quit.
23:02:16 <int-e> tromp: http://sprunge.us/TRPL is what I have.
23:02:45 * oerjan looks at http://golf.shinh.org/p.rb?A057755 and thinks: does anagolf prohibit putting an actual link in the problem description?
23:06:53 -!- DTSCode has joined.
23:08:11 <tromp> int-e: is unknown same as [0] ?
23:08:33 <int-e> tromp: As far as I recall, the 3 alternative candidates that produced more than 3 f applications were not clean fixed point combinators (Y f is not equivalent to f (Y f)); but they nevertheless produce an arbitrary number of applications to f (for all k there is an M such that Y f ->* f^k M. In a Böhm tree model, that's still a fixed point.
23:08:43 <int-e> tromp: "unknown" encompasses [0], [1] and [2].
23:10:17 <tromp> and you think the [3]+++ can be shown to be M f -> f(f(f(diverge))) ?
23:10:47 <tromp> where diverge has no whnf
23:11:54 <tromp> seems clear then that there's only one clean Y combinator of size 12
23:12:53 <int-e> "non-minimal", btw, are terms that have subterms of shape ``Kxy, ``SKM with M != K and ```SxyM with M=S or M=K. (rewriting such terms to ``xM`yM terminates.)
23:13:22 -!- NATT_SiM has quit (Remote host closed the connection).
23:13:47 <int-e> So I'm filtering a bit more there than one would naively expect.
23:15:40 <int-e> anyway, I'll revisit this another day
23:15:49 <tromp> thanks for the investigation
23:19:13 -!- NATT_SiM has joined.
23:21:00 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:23:38 <oerjan> oh wait obvious simplification, but int-e is _still_ a byte shorter
23:24:04 <FireFly> I need to get better at golfing Haskell
23:25:17 <oerjan> using logarithms is possible but seems not to make it shorter
23:26:38 <oerjan> because then you also need a pesky ceiling
23:27:44 <int-e> I have 3 approaches, 2 that work well in Haskell and 1 that works nicely in dc.
23:28:13 <int-e> (dc's arithmetic is too slow for the naive method)
23:28:46 <oerjan> i just did the obvious thing and then removed the +1, and then i'm missing by a byte
23:29:43 <int-e> it takes almost 5 seconds for computing the number of digits of 2^2^20 alone.
23:30:10 -!- centrinia has joined.
23:30:32 <oerjan> i noticed the other day a blog post comparing bignum implementations in languages with them builtin, and ghc won
23:30:40 -!- DTSCode has quit (Ping timeout: 240 seconds).
23:31:02 <int-e> ghc has very cheap allocation and lets gmp use that.
23:32:36 <int-e> The comparison included conversion to strings, right? That may not be entirely fair...
23:33:28 <int-e> damn now I need to find the link again...
23:33:53 <oerjan> i see your _actual_ dc method is faster than the haskell one.
23:35:59 <int-e> I don't think it's measurable.
23:37:56 <int-e> I get 0.001s for dc and 0.002s for haskell on my computer.
23:38:22 <oerjan> well your submitted haskell was a lot more
23:38:53 <int-e> But I have another Haskell version that takes 0.08s here, about 0.3 on anagol.
23:39:04 <int-e> same length, unfortunately.
23:45:01 <int-e> oerjan: anyway, resubmitting twice, the second time I got time: 0.000085sec for the same program that is listed as 0.0125.
23:55:07 -!- olls has joined.
23:59:43 -!- olls_ has joined.
23:59:52 <int-e> oerjan: ah, it came from HWN. http://www.wilfred.me.uk/blog/2014/10/20/the-fastest-bigint-in-the-west/ is the link.
23:59:57 -!- olls has quit (Ping timeout: 255 seconds).
00:02:34 -!- NATT_SiM has quit (Remote host closed the connection).
00:04:13 <int-e> ok, so conversion to string doesn't enter the picture; if anything that part will slow the Haskell version down.
00:07:10 -!- adu has joined.
00:10:03 -!- AndoDaan has joined.
00:13:29 <int-e> what fun. So apparently the last lambdabot downtime was caused by a Windows Server 2012 bug, leading to a switch being flooded with IPv6 packets, overloading the switch's CPU, and thus affecting traffic of completely unrelated hosts.
00:17:22 -!- Bicyclidine has joined.
00:17:30 <oerjan> just bill microsoft hth
00:21:50 -!- AndoDaan has quit (Ping timeout: 272 seconds).
00:22:33 -!- olls_ has quit (Quit: Lost terminal).
00:26:25 -!- AndoDaan has joined.
00:27:29 <Bicyclidine> this serial text thing's manual says to use control sequences starting with "the escape character" but doesn't say what that character is, so i'm like the shit is this fuck
00:27:37 <Bicyclidine> and it turns out it's the ascii ESC control character. i feel very young atm
00:28:09 * oerjan throws Bicyclidine a lollipop
00:28:32 <AndoDaan> !blsq ""Pp,20rz{2j**2j**1.+lnPP_+' _+Pp}m[p\t]Q
00:28:33 <blsqbot> | Ain't nobody got time fo' dat!
00:28:54 <AndoDaan> why is string formatting so hard!
00:29:15 -!- adu has quit (Quit: adu).
00:29:21 <AndoDaan> Why cant computer intuitively know what I want by now!?
00:29:47 <int-e> it's teaching you to be precise
00:31:03 <int-e> if you manage, it'll reward you with the illusion that you're in control
00:31:40 <int-e> oh, cheers, I missed this part. "We've also disabled new uses of Windows Server 2012 for now."
00:32:13 <Bicyclidine> i think for formatting you can blame the complications of language
00:41:58 -!- AndoDaan_ has joined.
00:43:02 -!- AndoDaan has quit (Ping timeout: 244 seconds).
00:45:38 <oerjan> <b_jonas> does someone have a roman numeral to number translator bot here? <-- hm i remember doing that once
00:45:52 <HackEgo> bin/fromroman \ bin/randomanonlog \ bin/toroman
00:46:04 <oerjan> oh right you made it afterward
00:46:27 <olsner> do we have a radixal to numbers translator?
00:46:28 <oerjan> maybe i just made a haskell function
00:59:51 -!- aloril has quit (Read error: Connection reset by peer).
01:03:06 -!- NATT_SiM has joined.
01:07:37 -!- Bicyclidine has quit (Ping timeout: 244 seconds).
01:07:39 -!- NATT_SiM has quit (Remote host closed the connection).
01:10:04 -!- NATT_SiM has joined.
01:29:32 -!- NATT_SiM has quit (Remote host closed the connection).
01:31:13 -!- NATT_SiM has joined.
01:35:53 -!- NATT_SiM has quit (Ping timeout: 272 seconds).
01:37:26 -!- aloril has joined.
01:38:06 -!- MoALTz_ has quit (Quit: Leaving).
01:43:28 <vanila> i not really convinced rule 30 or whatever is turing complete
01:43:34 <vanila> is there a simple explanation of why it is
01:45:17 <vanila> tromp, I wonder how I couldl write a program to find that term without prior knowledge of it?
01:45:27 <vanila> maybe that isn't really doable
01:45:37 <vanila> the short Y combinator
01:47:16 -!- shachaf has left.
01:47:25 -!- MoALTz has joined.
01:48:52 <tromp_> vanila: int-e has such a program; ask him
01:49:07 <elliott> vanila: I don't think there's any proof rule 30 is TC
01:49:10 <vanila> it seem s very hard to proof
01:49:16 <elliott> just wolfram believes it is because it looks complex
01:49:48 -!- AndoDaan_ has changed nick to AndoDaan.
01:49:59 <tromp_> https://en.wikipedia.org/wiki/Rule_110
01:50:06 <elliott> it looks kinda like rule 110 and rule 110 is TC :p
01:53:59 <oerjan> except rule 30 is reversible
01:54:17 <Bike> this snail? turing complete
01:54:18 <oerjan> > showIntAtBase 2 intToDigit 30 ""
01:55:16 <vanila> reversible turing machine wold be cool
01:55:38 <Bike> imo reversible thermodynamics
01:55:58 <oerjan> vanila: those exist. also, see http://esolangs.org/wiki/Reversible_Brainfuck
01:57:23 <vanila> i dont understand that
01:57:52 <vanila> how can you implement normal BF using reversible BF
01:58:02 <vanila> is it storing state in between the cells
01:58:16 <Bike> so does anyone know anything funny i can do with a 2×40 terminal
01:59:21 <oerjan> vanila: see the Tape Layout table (i made that)
02:00:36 <tromp_> Bike, you can turn play a very narrow tetris where no piece can be rotated:(
02:01:18 <vanila> I meant rule 110 though
02:01:40 <vanila> how is the polynomial overhead accepted?
02:02:12 <oerjan> vanila: rule 110 works by implementing a cyclic tag machine with colliding "gliders"
02:02:35 <oerjan> this part has polynomial overhead.
02:02:49 <oerjan> (although the setup is an infinite pattern)
02:03:21 <vanila> am I just being too strict?
02:03:23 <vanila> i feel like this wrong
02:03:52 <vanila> i'm not rejecting the proof just don't really understand how it relates to the claim that it's TC
02:04:12 <oerjan> vanila: it is dubious in a way, tc-ness only makes _complete_ sense if you are looking at finite setup and output.
02:04:20 <vanila> so i can simulate a cyclic tag machine if I encode it in this particular way into rule 110
02:04:39 <oerjan> ais523's proof for the 2,3 turing machine has the same problem, only slightly worse
02:04:40 <vanila> that's kind of what I feel
02:04:54 <vanila> hthese are great results
02:04:58 <elliott> isn't the setup repeating though
02:05:38 <vanila> also I don't doubt these ARE TC
02:05:54 <vanila> i.e. that it can be done with a finite setup
02:06:03 <vanila> or is there a reason to think that's not possible?
02:06:24 <Bike> ais is pretty smart and he couldn't figure it, how about that
02:06:54 <Bike> also there's finite information in the initial setup, right? so like whatever man.
02:07:40 <oerjan> vanila: well you really want a finite _output_ too, which is hard because these CA's create intrinsically growing patterns
02:08:06 <elliott> Bike: yeah but with 2,3 it requires actual computation, the initial pattern is non-repeating
02:08:14 <Bike> yeah i remember
02:08:21 <elliott> in the limit this is obviously cheating (if the required computation was TC)
02:08:37 <elliott> *fix that parenthical to be more pedantically worded
02:09:10 <Bike> well we're not in the limit
02:09:29 <oerjan> once you have infinite setup, it becomes really subtle whether your real computation takes place in the setup or afterward
02:09:49 <Bike> is that even a meaningful distinction? imo there are no boundaries anywhere, man
02:10:16 <oerjan> Bike: i'm not talking about CAs specifically
02:10:16 <Bike> maybe we could determine when computation is occuring through some rigorous physical measure, like watching waste heat
02:10:19 <Bike> this plan has no flaws
02:10:20 <Bike> oerjan: me neither
02:10:26 <elliott> Bike: well, presumably you don't want to consider the identity function turing complete
02:10:29 <oerjan> Bike: i think you may be high
02:10:33 <elliott> but it is if you prepare its initial state with a universal turing machine
02:11:40 <vanila> so a 1D CA has some initial state: an n-bit string (any natural number n)
02:11:43 <Bike> well i mean how formalizable is the idea of a computer, really? how do you compare lambda calculus and a turing machine? you can emulate one in the other, great, but i can emulate a turing machine with toilet paper and crayons
02:11:56 <vanila> and I guess there is already a question of termination
02:11:57 <Bike> anyway annoying thing about CAs, nobody told me they were used in fluid dynamics
02:12:05 <vanila> how do you get output?
02:12:47 <vanila> Bike: toilet paper and crayons is TPC, this is differnet than TC
02:12:57 <Bike> how do you get output out of a computer? you pick some time after your computation is running and say "okay, this is the output"
02:13:29 <Bike> we need more lattice gas automata
02:13:55 <oerjan> vanila: i think for rule 110 you can basically search each generation's state with a regexp to see if it has the "i am finished" tag
02:14:20 <elliott> vanila: isn't the initial state always infinite?
02:14:26 <elliott> just often it's all 0s outside of a finite area
02:14:32 <vanila> for my personal satisfaction, initial state should be finite
02:14:42 <Bike> "the initial state has finite support"
02:14:51 <Bike> go on. go full real analysis. i dare you
02:15:23 <Bike> homework: design a computing formalism that works when the initial state has arbitrary entropy everywhere but a finite area??
02:15:34 <oerjan> i recall once classifying the ways rule 110 could grow (leftwards, it never grows rightwards) into an infinite region of 0's. so i'm not so sure that you _cannot_ make it tc even with finite support.
02:15:38 <Bike> do you think i should eat a calzone for dinner tonight
02:15:49 <oerjan> (initially. it will grow infinitely nevertheless.)
02:16:10 <vanila> maybe we should just study 1D ca more and not try to shoehorn the kind of computation it does do into the 'TC' framework
02:16:50 <Bike> perhaps you could study.... lattice gases
02:17:02 <oerjan> you just need some way of doing glider guns to get the effect of the infinite setup while having only finite support at the start
02:17:21 -!- shikhin has quit (Ping timeout: 265 seconds).
02:17:29 <vanila> if someone worked that out it'd be worth a publication I think
02:17:40 <oerjan> better i stay out of it then
02:18:31 <oerjan> my underload minimization attempts basically halted when ais523 said it might be publishable >:)
02:18:46 <oerjan> (well i already found the minimum)
02:19:22 -!- shikhin has joined.
02:21:09 <oerjan> <Bike> anyway annoying thing about CAs, nobody told me they were used in fluid dynamics <-- have you heard about terence tao's idea that one might theoretically prove navier-stokes (millennium problem) to blowup by embedding something like CA computation in ideal fluids
02:22:53 <Bike> unfortunately for me tao's blog is incomprehensible
02:23:05 <vanila> tao is good at explaining things in a simple way...
02:23:10 <Bike> fluid dynamics is also incomprehensible, but i'm working on it
02:24:05 <oerjan> <Bike> homework: design a computing formalism that works when the initial state has arbitrary entropy everywhere but a finite area?? <-- i recall that there's an obvious prood that in a symmetric CA you cannot create a pattern that can expand into arbitrary chaos, namely just put a competing version of the pattern somewhere out there
02:24:13 <Bike> «The story is told of many giants of modern physics, but most plausibly of Heisenberg, that, on his death-bed, he remarked that the two great unsolved problems were reconciling quantum mechanics and general relativity, and turbulence. "Now, I'm optimistic about gravity..." »
02:24:46 <elliott> vanila: I guess the CA equivalent of TC would be, like, 110-complete?
02:25:08 <vanila> show that one CA is possible to simulate all the others
02:25:08 <Bike> oerjan: well that would figure, yeah.
02:25:15 <elliott> oh, yeah, that's a better definition.
02:25:25 <Bike> oerjan: i wonder if you can make that into the fluctuation theorem somehow!
02:25:30 <elliott> it still might involve infinite initial states and not-completely-trivial encodings though...
02:25:34 <elliott> but you don't have to worry about halting
02:25:47 <vanila> the meta interpreter for game of life is so cooooool
02:28:16 <Taneb> Today I used Lua for the first time
02:28:21 <vanila> rule for CA simulation: initial state must be START CELL(C[0]) MID CELL(C[1]) MID ... STOP each of these is finite and CELL is a function that takes takes a 0 or 1
02:28:24 <Taneb> Well, in the past 24 hours definition of "today"
02:29:47 <Bike> good times: installing awesomewm, installing a lua browser, crashing lua browser which brings down awesome somehow
02:30:59 -!- NATT_SiM has joined.
02:31:02 <Bike> still waiting for guidance re: calzones
02:32:02 <oerjan> un calzone per favore, and then you'll have some more
02:33:14 <oerjan> Bike: you don't need our guidance, it's all baked in hth
02:33:32 <elliott> Bike: is this like when I used to get you to tell me when to go to bed? :p
02:33:55 <Bike> no it's like whne i ask about fucking calzones!
02:33:59 <Bike> honestly i don't think this is hard
02:34:28 <Bike> did you ever go to bed btw
02:35:21 <oerjan> i think i've eaten calzone a few times hth
02:35:28 <Taneb> I've had calzone once or twice
02:35:59 <oerjan> but i cannot help getting the feeling "why are you folding the pizza?"
02:35:59 <Bike> that sounds terrible
02:36:06 <Bike> both the not sleeping and the not calzoning
02:37:09 <Taneb> I fancy some calzone now
02:37:23 <Taneb> Maybe I should go to a dodgy takeaway and get some
02:41:49 <oerjan> something tells me dmm isn't always careful when queueing these http://www.mezzacotta.net/postcard/
02:43:43 -!- centrinia has quit (Ping timeout: 244 seconds).
02:54:29 <Sgeo> What would you call a rocket intended to observe quantum mechanical effects in outer space?
02:55:38 <Sgeo> No pun, but I'm considering building something like that in Second Life
02:56:10 <Sgeo> I originally estimated that it would take 7 days before completing its mission, but considering that I'm predicting the latter half to be sped up beyond the normal SL speed limit...
02:56:34 <Sgeo> Either that or it dies half a week before I'm expecting it to
02:57:18 <vanila> The Rule 90 automaton (in its equivalent form on one of the two independent subsets of alternating cells) was investigated in the early 1970s, in an attempt to gain additional insight into Gilbreath's conjecture on the differences of consecutive prime numbers
02:58:05 <vanila> "every six steps of the Rule 22 automaton simulate a single step of the Rule 90 automaton"
02:59:04 <oerjan> > showIntAtBase 2 intToDigit 90 ""
02:59:29 <oerjan> > showIntAtBase 2 intToDigit 22 ""
03:00:23 <Sgeo> std::mem::transmute is really convenient when playing with floats
03:02:52 <vanila> apparnelty Wang of Wang-tiles proves that 2-cyclic tag machines are TC
03:08:03 <Sgeo> I think if I could just get 70 million meters in the sky, that would allow for a dramatic test of my theories
03:08:12 <Sgeo> I always thought it would be much higher
03:10:28 <elliott> Sgeo: I was briefly terrified and confused before I realised you were talking about second life
03:12:23 <vanila> second life has quantum physics?
03:14:12 <Sgeo> Second Life has floating point numbers in its physics. Floating point numbers have quantums that increase as the numbers get larger. Therefore, Second Life has quantum physics.
03:23:21 <Bike> oh hey my assembler treats '\0' as meaning '0', sweet
03:23:50 <int-e> Sgeo: "nonuniform planck length explorer" ;)
03:24:46 <int-e> Sgeo: there, now you have a suggestion for the name of your rocket, now you can shoot it down by thinking of something better.
03:25:00 <Bike> i was wondering why my professor would put '\0' instead of just zero, and i have learned the answer: no fucking reason
03:27:21 <Bike> i don't think he actually ran this code, unless he wanted it to display 0Hello world0Hello wor
03:28:29 <Bike> so, nerds, does anyone know why terminal control sequences start with [?
03:28:47 <int-e> ^[[ is easy to type?
03:29:17 <Bike> god, i can almost believe that's the reason
03:30:20 <Bike> hm, apparently ^[[ is equivalent to a one eight-bit control character in C1
03:31:06 <Bike> which nobody uses, so that's great
03:32:45 <vanila> can someone help me understand cyclic tag machine
03:33:20 <Bike> wikipedia seems pretty straightforward
03:33:31 <Bike> whatchu havin problem with
03:34:13 <Bike> Um. That seems wrong.
03:34:40 <Bike> Where are you going off of? Wikipedia and esolang both would seem to say that's not how it works.
03:34:47 <Bike> assuming you mean acca is the product from baa
03:36:46 <int-e> vanila: note the m here: "t(S) is the result of deleting the leftmost m symbols of S and appending the word P(x) on the right." ... in the example, m=2.
03:37:06 <vanila> ill try to implement this so i can undersatnd it
03:38:10 <oerjan> vanila: that's a tag system, but not a _cyclic_ tag system. those are different.
03:38:27 <int-e> and it's a 2-tag system, whereas tag systems are 1-tag systems
03:38:46 <vanila> :( this is so confusing
03:38:52 <oerjan> int-e: *cyclic tag systems
03:39:32 <vanila> A tag system is a deterministic computational model published by Emil Leon Post in 1943 as a simple form of Post canonical system
03:40:45 -!- centrinia has joined.
03:41:49 <Bike> (height of comedy)
03:42:48 <oerjan> int-e: or rather, ordinary 1-tag systems are uninteresting because not tc, or at least not proven so
03:42:48 <int-e> oerjan: The Wikipedia article introduces tag systems, m-tag-systems (where tag systems arise as a special case by taking m=1), and then cyclic tag systems.
03:42:57 <int-e> oerjan: I'm not sure what you're trying to correct.
03:43:09 <oerjan> hm... let me check that.
03:43:37 <int-e> it also introduces cyclic tag systems further down in the article
03:44:23 <vanila> so im confused about all this
03:44:30 <int-e> no, actually they say that m is implicit, with no default.
03:44:32 <Bike> yaeh it's all bullshit
03:44:48 <int-e> but still there's no cyclicity there at all.
03:45:12 -!- NATT_SiM has quit (Remote host closed the connection).
03:45:21 <int-e> oerjan: so there was something to correct, but your suggestion made it more wrong
03:46:27 <vanila> http://link.springer.com/article/10.1007%2FBF01343730#page-2
03:46:43 <vanila> T_i : s_i --> E_i, i = 1, .., n
03:47:20 <vanila> if the first symbol of a string is s_i then the first beta symbols are removed and E_i is appended at the end
03:47:34 <oerjan> vanila: the confusing thing here is that cook/wolfram changed the definition of tag systems because it was easier to make a pattern of gliders deal with single bits one at a time
03:48:13 <vanila> if the alphabet contains m symbols then n <= m
03:48:19 <oerjan> and it was easy to change the gliders used from one step to the next since they're all part of the infinite setup.
03:48:54 <oerjan> (easy once you have found useable gliders in the first place)
03:49:27 <int-e> vanila: love the use of \beta without saying what it is first.
03:50:00 <vanila> not only is it not say first, but not said second either
03:50:11 <vanila> in fact I have no idea what beta is
03:50:30 <int-e> \beta seems to be the 'm' from wikipedia's article.
03:50:33 <Bike> q: is it sane to have a function called 'puts' that also works for terminal control sequences? i don't know if C puts does
03:51:35 <vanila> so I guess beta is just a fixed constant
03:52:08 <int-e> yes. a positive integer
03:52:28 <oerjan> there are no \0s in terminal control sequences are there?
03:52:54 <oerjan> and isn't that all puts demands
03:53:59 <vanila> so basically this whole area is a confusing nightmare
03:54:05 <elliott> puts does append a newline though...
03:54:30 <Bike> oh i guess i'm not doing that
03:54:44 <vanila> http://arxiv.org/abs/cs/0612089
03:54:45 <oerjan> vanila: um no, just a bit unfortunate naming, a cyclic tag system is not a tag system, but analogous to one
03:54:49 <Bike> i guess this is more like fputs then
03:56:11 -!- shachaf has joined.
03:57:35 <vanila> why are they barring symbols? beforelemma 1
03:58:17 -!- AndoDaan has quit.
03:59:47 <vanila> I can't understand this
04:00:37 -!- coppro has quit (Ping timeout: 256 seconds).
04:01:20 -!- coppro has joined.
04:02:50 <vanila> http://dspace.mit.edu/handle/1721.1/6107#files-area
04:02:52 -!- ^v has quit (Remote host closed the connection).
04:03:51 <int-e> vanila: those are 7 different variants each of 0 and 1: barred, dotted, barred with underset 1, possibly dotted, and plain with underset 2. ... ouch.
04:05:05 <vanila> I found an explanatio of tag system which makes sense
04:07:22 <int-e> Ok, Lemma 1 is correct, but the Proof requires some doodling on paper to believe.
04:08:53 -!- copumpkin has joined.
04:09:07 <int-e> the key is that the x -> \epsilon rules delete pairs of characters, so you're left with \bar x_1 \dot\bar x_1 (and then x_2) if l is even or \dot \bar x_1 if l is odd.
04:11:05 <int-e> But it's confusing because 'w' does not match the encoding of words introduced in the preceding paragraph.
04:19:34 <vanila> http://lpaste.net/114334
04:20:00 <vanila> I should create a format so people can make .tag files for it to run
04:21:42 <vanila> I have a programming challenge to #esoteric
04:22:12 <vanila> Write a program which finds a fixed point combinator for SK combintors (or some language like that)
04:23:52 <int-e> ... http://sprunge.us/TRPL
04:24:30 <vanila> I declare int-e the winner
04:25:11 <int-e> you must have missed the earlier discussion on the topic
04:25:38 -!- oerjan has quit (Quit: leaving).
04:25:39 <vanila> yeah and i wrote a program to try this yesterday but it didnt wokr
04:26:28 <int-e> (about 5 1/2 hours ago)
04:28:07 <vanila> which of those output are fixed point combinators?
04:29:18 <int-e> the first one is a proper one; the last three work in a Böhm tree model (and Scott topology, I presume); they have the property that M f unfolds to f (f (f (f (f ...))))
04:29:35 -!- shikhin has quit (Ping timeout: 264 seconds).
04:30:18 <int-e> (but the program is unable to verify this.)
04:31:39 <vanila> I can see why you'd use tag systems for a CA with diagonal gliders
04:31:45 <int-e> the ones with [3] belong in the "unknown" category (where I think it's quite a safe bet that none of them are fixed point combinators, but there's no proof.)
04:32:00 <vanila> that's really interesting, I wonder what they are!
04:32:05 <vanila> maybe i should convert them to lambda terms
04:33:37 <elliott> int-e: is the difference between the proper and bohm tree model ones that M f isn't f (M f) but f (M' f) where M' f is f (M'' f) and so on?
04:34:06 <elliott> that seems like a fixed point combinator to me, since the Ms are essentially "implementation details"?
04:34:07 <int-e> elliott: yeah, the shape of the combinator changes.
04:34:15 <elliott> like, there's no way to observe the difference as f, right?
04:34:44 <int-e> elliott: but the resulting limiting infinite tree (that's the Böhm tree) is the same
04:37:02 <vanila> i dont know what tool i can use to investigate a lambda term
04:39:21 <vanila> interesting that you can encode turing machines into tag systems
04:39:31 <vanila> i wonder if there's an easier way to show them TC
04:41:13 <vanila> http://codegolf.stackexchange.com/questions/40300/simulate-a-cyclic-tag-system
04:46:03 <int-e> elliott: the first one is (\y f. y f y) (\f y. f (y f y))
04:46:27 * elliott nods. (was that meant to be for vanila?)
04:47:00 * int-e is a random nick selector.
04:47:17 <vanila> looks like a y combinator to me!
04:47:49 <vanila> http://labs.orezdnu.org/lambda/ i foun d this which lets you manually reduce lambda terms
04:55:33 <Bike> hot damn is terminfo organized alpahbetically
04:56:28 <vanila> can the bot turn unlambda into lambda?
04:59:34 <elliott> vanila: that would violate the second law of thermodynamics :p
05:07:04 <vanila> http://lpaste.net/114335
05:07:10 <vanila> here are the terms then
05:13:35 <int-e> those are the ones that are conjecturally not fixed point combinators
05:14:17 <vanila> yeah mi interested in those
05:14:25 <vanila> if theyre not fixed poits they must be something weird and cool
05:17:25 <elliott> vanila: they could just be f (f (f (f (f (f _|_))))) or the like
05:18:30 <vanila> i tried in the javascript program but if you make a mistake it gets loads bigger
05:25:56 -!- AndoDaan has joined.
05:34:22 -!- AndoDaan_ has joined.
05:34:45 -!- AndoDaan has quit (Ping timeout: 255 seconds).
05:35:22 -!- nys has quit (Quit: quit).
05:36:57 -!- vanila has quit (Quit: Leaving).
05:45:36 -!- AndoDaan_ has quit.
05:47:45 -!- adu has joined.
05:57:16 <Bike> update: i ate a calzone anyway. it was kind of a lot so i feel a bit sick but i'm sure i'll pull through, no thanks to you jerks
05:59:49 <elliott> our uncertainty was meant to represent the idea of you eating half a calzone!
06:52:15 -!- adu has quit (Quit: adu).
07:04:42 -!- centrinia has quit (Ping timeout: 245 seconds).
07:28:49 -!- shikhin has joined.
07:49:48 <MDude> I've made something that works very poorly http://orteil.dashnet.org/randomgen/?gen=http://mdude1350.webs.com/generators/random-code/IBNIZ-simple-generator.txt
07:50:43 <MDude> And no, it's not Windows.
07:56:19 -!- Patashu_ has joined.
07:56:19 -!- Patashu has quit (Disconnected by services).
08:14:42 -!- shikhout has joined.
08:17:30 -!- shikhin has quit (Ping timeout: 244 seconds).
08:28:22 -!- AndoDaan has joined.
08:33:01 -!- MDude has changed nick to MDream.
08:48:23 -!- Patashu_ has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
08:57:23 -!- bb010g has quit (Quit: Connection closed for inactivity).
09:01:11 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:06:26 -!- Patashu has joined.
09:12:57 -!- j-bot has quit (Remote host closed the connection).
09:21:19 <MDream> It seems to ahve some problems generating, though.
09:21:55 <MDream> I think however the generator code works might be expecting something special from question marks.
09:26:50 <nyuszika7h> anyone interested in my slightly unusual approach to 99 bottles in Haskell? http://lpaste.net/2310281802079535104
09:29:52 -!- shikhout has changed nick to shikhin.
09:30:44 <elliott> that is such an abuse of show :)
09:31:18 <elliott> (also, technically you want toTitle there, but...)
09:33:57 <J_Arcane> nyuszika7h: I actually did laugh out loud. :D
10:10:08 -!- Phantom_Hoover has joined.
10:42:43 -!- S1 has joined.
10:49:40 -!- AndoDaan has quit (Ping timeout: 240 seconds).
10:50:10 -!- S1 has quit (Quit: S1).
10:50:26 -!- copumpkin has quit (Ping timeout: 244 seconds).
11:10:04 -!- fungot has quit (Remote host closed the connection).
11:11:29 -!- fungot has joined.
11:14:08 <fizzie> fungot: Still feeling all right?
11:14:09 <fungot> fizzie: so the source is encoded in some meta language. to do what you want the suspend button to suspend or hibernate? granted, it's easy to implement all fingerprints in cfunge.
11:50:06 <mroman> Working on weekends is so relaxing.
12:05:30 -!- boily has joined.
12:19:10 <mroman> ^8ball Does blsqbot need sha1?
12:19:33 <fungot> mroman: it's defined as a function? can't you use alien? beings)
12:19:45 <mroman> I'm not sure if aliens know what sha1 is.
12:24:03 <fizzie> Yes, they're probably stuck with MD5 still.
12:29:55 -!- boily has quit (Quit: HASH CHICKEN).
12:32:26 <shachaf> fungot means that it should be using sha-2 or sha-3, obviously.
12:32:26 <fungot> shachaf: there you go :d, say how you want to
12:32:36 <fungot> shachaf: im even fnord. browse like that into the, syntax is discussed half as much mem
12:36:27 <mroman> `learn MD5 is a hash algorithm mainly used by underdeveloped aliens.
12:36:29 <HackEgo> Learned 'md5': MD5 is a hash algorithm mainly used by underdeveloped aliens.
12:42:47 -!- Patashu has quit (Ping timeout: 272 seconds).
12:43:43 <mroman> Damnit I have no headphones
12:43:51 <mroman> but looks like nobody's here anyway.
12:48:02 <mroman> I see there are new "assisted suicides" debates flaming on.
12:49:16 <mroman> I don't really see the point in debating that though
12:49:24 <mroman> It's pretty much obvious anyway
12:49:41 <mroman> At the end of the spectrum you have the religious people who are against it for religious reasons
12:50:06 <mroman> then in the middle of the spectrum are regular people who have never been in the situation of thinking about suicide and think suicide is bad no matter what circumstances
12:50:23 <mroman> and at the other end of the spectrum are those who say "who want's to do it shall be able to"
12:50:55 <mroman> what they should be debating about is whether the state/government has the right to keep a person alive against the person's will.
12:52:03 <mroman> (and then there are people who think all people thinking about suicide can be treated and healed)
12:53:18 -!- qlkzy has quit (Excess Flood).
12:54:28 <mroman> I hate it when people argue for themselves rather than for the state/government
12:54:44 -!- qlkzy has joined.
12:54:45 -!- qlkzy has quit (Excess Flood).
12:56:04 -!- qlkzy has joined.
12:56:05 -!- qlkzy has quit (Excess Flood).
12:56:44 -!- qlkzy has joined.
12:56:45 -!- qlkzy has quit (Excess Flood).
12:57:07 -!- drdanmaku has joined.
12:58:14 -!- qlkzy has joined.
12:58:15 -!- qlkzy has quit (Excess Flood).
13:02:00 -!- qlkzy has joined.
13:02:00 -!- qlkzy has quit (Excess Flood).
13:03:21 -!- qlkzy has joined.
13:03:21 -!- qlkzy has quit (Excess Flood).
13:04:01 -!- qlkzy has joined.
13:04:01 -!- qlkzy has quit (Excess Flood).
13:04:41 -!- qlkzy has joined.
13:04:41 -!- qlkzy has quit (Excess Flood).
13:04:51 -!- qlkzy has joined.
13:04:51 -!- qlkzy has quit (Excess Flood).
13:05:21 -!- qlkzy has joined.
13:05:21 -!- qlkzy has quit (Excess Flood).
13:06:00 -!- qlkzy has joined.
13:13:14 <mroman> [java.lang.RuntimeException](java.sql.SQLException: [SQLITE_MISUSE] Library used incorrectly (not an error))
13:18:21 -!- oerjan has joined.
13:34:35 <mroman> git can't handle multiple * in gitignore patterns?
13:46:38 <fizzie> In my (admittedly small) tests, those worked just fine.
13:46:51 <fizzie> (Didn't test any interaction with ** though.)
13:47:22 <mroman> */sandboxes/sandbox_*/gen/* doesn't seem to work
13:48:05 <fizzie> I tried http://sprunge.us/VPKe and it properly ignored a/b/c/foo and foo.baz.bar.quux but not the other two files.
13:48:42 <mroman> so it added bar and foo?
13:49:37 <fizzie> It added a/b/c/bar and foo.bar.baz.quux, neither of which match the ignore patterns.
13:50:44 <fizzie> (I suppose you remember that * doesn't match a /.)
13:55:08 <fizzie> (That's what ** is for.)
13:59:15 <Melvar> I wish to know whether gcc is inlining certain function calls. How should I go about this?
14:01:02 <mroman> Melvar: Have you tried -Winline
14:01:35 <mroman> Using -Winline will warn when a function marked inline could not be substituted, and will give the reason for the failure.
14:01:52 <mroman> I guess this should tell you what it DIDN'T inline
14:02:13 <Jafet> objdump -dlx a.out
14:02:18 <Melvar> Well, if I want to use inline, I’d have to transfer the functions to the header file I think.
14:02:35 <mroman> it doesn't work with linking
14:02:51 <Melvar> I’m specifying -flto both times.
14:02:51 <mroman> GCC doesn't cross-module optimizations afaik
14:03:00 <mroman> (unlike ghc which does exactly that)
14:03:48 <mroman> hm. didn't know gcc hat lto
14:04:34 <mroman> I just know that ghc favors optimization over binary compatibility :)
14:09:57 <Melvar> Hm, looks like it inlined two of three and the code for the remaining one looks larger than expected.
14:10:25 <mroman> I think GCC can even do partial inlining?
14:13:28 <Melvar> Hm, it also gained a numerical suffix.
14:13:51 <mroman> GCC even copies the same functions to different locations
14:14:10 <mroman> which is an awesome thing to do actually
14:14:44 <Melvar> I wonder what the .2536 suffix on this function means.
14:14:44 -!- shikhout has joined.
14:15:08 <mroman> because it guarantees that the function is in the instruction cache
14:16:10 <mroman> or maybe that was some other compiler
14:17:19 -!- shikhin has quit (Ping timeout: 244 seconds).
14:18:33 <Melvar> Huh, no, looks like I was wrong, it didn’t inline them after all.
14:19:53 <Melvar> I’ll have to move them to the header and specify inline, I guess.
14:24:17 <mroman> There's no guarantee gcc will inline your functions btw
14:24:53 <mroman> (unless you use __attribute__((always_inline)) )
14:26:27 <mroman> but I don't know much about gcc optimizations :(
14:26:47 <mroman> I only know that __builtin_expect makes a hell of a difference if used correctly
14:28:06 <mroman> With __builtin_expect my emulator suddently executed 10 MIPS more than without
14:28:16 <Melvar> Yeah, two of these are functions to index a C array, so they consist of a single small C statement. Since these are bindings, they each get called from one other function which gets called a bunch of times.
14:32:30 <mroman> I wonder how gcc implements atomic stuff on CPUs that don't have LOCK prefixes and the like
14:32:53 <mroman> Although I don't think gcc even targets more esoteric CPUs :D
14:34:40 <Jafet> In software, as usual
14:39:36 <mroman> which is usually just CLI; do stuff; STI
14:39:46 <mroman> not a lot of other choices there I think
14:43:01 <mroman> which won't work for exceptions actually
14:45:42 <mroman> @tell AndoDaan you could write a MNNBFSL interpreter in Burlesque .
14:46:57 <mroman> Interpreters in Burlesque for Esolangs: Brainfuck (doesn't support output), Deadfish
14:48:27 -!- nys has joined.
14:50:32 <mroman> (and trivially Burlesque since there's eval)
14:51:36 <mroman> !blsq "\'\\5'\\'\'pe"pe
14:51:36 <blsqbot> | ERROR: Unknown command: (\5)!
14:51:45 <mroman> !blsq "\'\5'\\'\'pe"pe
14:51:45 <blsqbot> | ERROR: Unknown command: (\5)!
14:52:19 <mroman> !blsq "\'\'5\'pe\'pe"Q
14:52:29 <mroman> !blsq "\'\'5\'pe\'pe"pe
14:52:29 <blsqbot> | ERROR: Burlesque: (e!) Invalid arguments!
14:52:29 <blsqbot> | ERROR: Burlesque: (ps) Invalid arguments!
14:52:38 <mroman> !blsq "\'\'5\'pe\'pe"psQ
14:52:57 <mroman> !blsq "\'\\'5\\'pe\'pe"psQ
14:53:02 <mroman> !blsq "\'\\'5\\'pe\'pe"pe
14:53:32 <mroman> !blsq "\'\\'\\\\'5\\\\'pe\\'pe\'pe"pe
14:54:26 <mroman> fizzie: \' escapes " btw.
14:54:32 <mroman> I'm not sure where that's documented.
14:54:36 <mroman> or if it even is documented
14:58:06 <mroman> but it will be printed as \", not as \'
14:58:14 <blsqbot> | ERROR: (line 1, column 5):
14:58:28 <blsqbot> | ERROR: Burlesque: ([[) Invalid arguments!
14:58:28 <blsqbot> | ERROR: Burlesque: (ud) Invalid arguments!
14:58:33 <blsqbot> | ERROR: (line 1, column 10):
14:58:34 <blsqbot> | expecting "%", "g", "s", "S", "m{", "q", "{", "\"", "-", digit, "'", "(", "y" or "}"
14:58:51 <mroman> I like that it can now display more lines :)
15:00:47 <mroman> ' doesn't require any escaping
15:02:16 <mroman> (^- that's a newline char)
15:03:57 <blsqbot> | That line gave me an error
15:06:19 <mroman> Well, I gotta go places. Not college, but places.
15:22:41 -!- copumpkin has joined.
15:24:14 -!- mihow has quit (Read error: Connection reset by peer).
15:26:56 -!- mihow has joined.
15:32:48 -!- AndoDaan has joined.
15:36:13 -!- AndoDaan has left.
15:36:31 -!- AndoDaan has joined.
15:42:04 -!- vanila has joined.
15:46:56 -!- AndoDaan has quit (Quit: Leaving).
15:48:51 -!- AndoDaan has joined.
16:04:23 <Vorpal> This Mac (classic) emulator only works when running under strace or gdb
16:04:30 <Vorpal> Otherwise it just locks up at startup
16:05:47 <vanila> sheepshaver is the most broken thing :///
16:06:09 <Vorpal> vanila, no kidding, are there any alternatives?
16:06:11 <vanila> ( idnotknow any others)
16:06:11 <idris-bot> (input):1:21: error: expected: "!!",
16:06:44 <Vorpal> vanila, Anyway BasiliskII has the same issue
16:06:44 <vanila> because i really wnat to emulate powermac :/
16:07:07 <Vorpal> vanila, anyway it doesn't run all the games I want.
16:07:25 <vanila> extremely slow and painful but classic macs run in mess, minivmac might be better for non powr mac but it's very odd not sure how to even run it
16:08:49 <Vorpal> Is it related to mame?
16:09:02 <vanila> its too slow now but one day might be good
16:09:30 -!- olls has joined.
16:09:43 <Vorpal> vanila, Right, I want to play Escape Velocity Override.
16:10:00 <Vorpal> If that isn't doing 30+ FPS it isn't going to play well
16:10:21 <vanila> there was a TC for ev nova that might let you run that on an older version of mac os x
16:10:36 <vanila> it may be easier to emulate that or run it on real hardware depending on what you have
16:11:07 <vanila> total conversion - it is official too
16:11:11 <Vorpal> Also I never played nova, I wonder if it was any good
16:12:01 <Vorpal> vanila, Oh? Okay, so how do I emulate OS X? And where do I find EV Nova these days
16:12:32 <vanila> I don't really know, i've never done this but it's just an idea that might be another way to do this
16:14:35 <Vorpal> vanila, I do have an old first model iBook I can use. However, the battery is dead and the power connector is glitchy. Thus if you don't keep the computer perfectly still, the power is going to cut out
16:15:29 <vanila> a shame :( if you can repair that , I think it's the best bet
16:17:00 <Vorpal> I'm not really good at doing that sort of stuff. Anyway, bbl, food is ready
16:19:01 <fizzie> Vorpal: PearPC, OS X and the classic thing in it. (Not very likely to be any good.)
16:22:52 <J_Arcane> EV Nova was also available for Windows apparenty, and supports the same mods to run the first two games.
16:23:34 <fizzie> And you can buy it for $30 from Ambrosia's web-store.
16:26:25 -!- NATT_SiM has joined.
16:35:18 <mroman> Vorpal: sounds like a race condition .
16:35:36 <mroman> gbd has the property of making race conditions suddenly not buggy anymore
16:44:27 -!- MDream has changed nick to MDude.
16:44:56 -!- vanila has quit (Quit: Leaving).
16:46:05 <mroman> {0 1 4 9 16 25 36 49 64 81 100}
16:48:01 <mroman> > scanl1 (<) [1,2,3,4]
16:48:03 <lambdabot> No instance for (GHC.Num.Num GHC.Types.Bool)
16:57:34 <mroman> blsq ) {1 5 9 10 2 3 1 0}0{.>}LO
16:57:41 <mroman> and that. But I have no name for that one yet.
16:58:11 <mroman> blsq ) {1 5 9 10 2 3 1 0 99}0{.>}LO
16:58:24 <mroman> this gives you a sequence of larger getting numbers in a list.
16:59:05 <mroman> blsq ) {1 5 9 10 2 3 1 0 99}100{.<}LO
17:03:11 -!- fungot has quit (Ping timeout: 260 seconds).
17:05:21 -!- shikhout has changed nick to shikhin.
17:08:01 -!- nortti has changed nick to lawspeaker.
17:09:20 -!- lawspeaker has changed nick to nortti.
17:12:26 -!- nortti has changed nick to lawspeaker.
17:13:04 -!- oerjan has quit (Quit: Running after fungot).
17:14:26 -!- lawspeaker has changed nick to nortti.
17:23:48 <Vorpal> <J_Arcane> EV Nova was also available for Windows apparenty, and supports the same mods to run the first two games. <-- ooh
17:24:10 <Vorpal> fizzie, 30 USD for that old of a game is a bit of a stretch though :/
17:25:48 <Vorpal> <mroman> Vorpal: sounds like a race condition. <-- well strace too, but that use ptrace as well. Anyway, this program used to work, on this computer, on an earlier Ubuntu version
17:33:41 -!- MDude has quit (Ping timeout: 240 seconds).
17:34:48 <fizzie> Yes, it's not exactly a bargain price.
17:39:10 -!- NATT_SiM has quit (Remote host closed the connection).
17:43:28 -!- vanila has joined.
17:44:32 * J_Arcane found a very nice bit of code for an infix code-block operator in Racket, which is sadly not licensed. Debating bribing the author ...
17:45:22 <J_Arcane> http://artyom.me/learning-racket-2
17:45:39 <J_Arcane> Round about the end of the first section.
17:45:55 <vanila> The thing is, “define” is too long. Why not use def instead?
17:46:50 <J_Arcane> And while I love scheme/racket wordy function names, they can get a bit tedious (or would if I had to write nearly as much code as in other languages to do anything)
17:47:55 <vanila> his : macro is so clever it's making me annoyed
17:53:21 -!- NATT_SiM has joined.
17:55:58 <J_Arcane> I've looked at some other libs and things for it, and none are have as clever or simple.
18:05:42 -!- NATT_SiM has quit (Remote host closed the connection).
18:14:30 -!- MoALTz_ has joined.
18:18:48 -!- MoALTz has quit (Ping timeout: 264 seconds).
18:33:45 -!- paul2520 has quit (Quit: WeeChat 1.0).
18:37:46 -!- shikhin has changed nick to SHIKHIN.
18:38:26 -!- SHIKHIN has changed nick to shikhin.
18:48:05 -!- esowiki has joined.
18:48:10 -!- esowiki has joined.
18:48:10 -!- esowiki has joined.
18:48:42 -!- esowiki has joined.
18:48:46 -!- esowiki has joined.
18:48:47 -!- esowiki has joined.
18:49:16 -!- esowiki has joined.
18:49:20 -!- esowiki has joined.
18:49:21 -!- esowiki has joined.
18:49:51 -!- esowiki has joined.
18:49:55 -!- esowiki has joined.
18:49:56 -!- esowiki has joined.
18:50:41 -!- esowiki has joined.
18:50:46 -!- esowiki has joined.
18:50:46 -!- esowiki has joined.
18:51:32 -!- esowiki has joined.
18:51:36 -!- esowiki has joined.
18:51:37 -!- esowiki has joined.
18:52:21 -!- esowiki has joined.
18:52:26 -!- esowiki has joined.
18:52:26 -!- esowiki has joined.
18:53:11 -!- esowiki has joined.
18:53:16 -!- esowiki has joined.
18:53:16 -!- esowiki has joined.
18:54:01 -!- esowiki has joined.
18:54:06 -!- esowiki has joined.
18:54:06 -!- esowiki has joined.
18:54:51 -!- esowiki has joined.
18:54:56 -!- esowiki has joined.
18:54:56 -!- esowiki has joined.
18:55:41 -!- esowiki has joined.
18:55:42 -!- glogbot has joined.
18:55:46 -!- esowiki has joined.
18:55:46 -!- esowiki has joined.
18:56:34 -!- AndoDaan_ has joined.
18:57:35 -!- AndoDaan has quit (Ping timeout: 240 seconds).
18:57:42 -!- kline has joined.
18:59:18 -!- Bike_ has joined.
18:59:37 -!- fizzie` has joined.
19:00:34 -!- lambdabot has quit (Remote host closed the connection).
19:00:34 -!- fizzie has quit (Ping timeout: 265 seconds).
19:00:37 -!- scounder has quit (Ping timeout: 265 seconds).
19:00:39 -!- Bike has quit (Ping timeout: 265 seconds).
19:00:40 -!- conehead has quit (Ping timeout: 265 seconds).
19:00:40 -!- InvalidCo has quit (Ping timeout: 265 seconds).
19:00:41 -!- int-e has quit (Ping timeout: 265 seconds).
19:00:43 -!- int-e_ has joined.
19:01:03 -!- InvalidCo has joined.
19:02:35 -!- AndoDaan_ has changed nick to AndoDaan.
19:05:13 -!- lambdabot has joined.
19:06:18 -!- conehead has joined.
19:07:28 -!- Bike_ has changed nick to Bike.
19:21:00 <J_Arcane> IT's weird to me how BASIC has so few predicate functions.
19:22:37 -!- AndoDaan_ has joined.
19:23:04 -!- ^v has joined.
19:25:25 -!- AndoDaan has quit (Ping timeout: 264 seconds).
19:26:42 -!- AndoDaan_ has changed nick to AndoDaan.
19:29:40 -!- variable has quit (Ping timeout: 255 seconds).
19:32:39 -!- AnotherTest has joined.
19:35:47 -!- clog has joined.
19:36:30 -!- NotJoel has joined.
19:36:36 -!- variable has joined.
19:36:44 -!- clog_ has quit (Ping timeout: 255 seconds).
19:37:17 -!- ZombieAlive has quit (Remote host closed the connection).
19:41:03 -!- olls has quit (Quit: leaving).
19:41:57 -!- olls has joined.
19:43:43 -!- _Paul has joined.
19:43:51 <_Paul> whaaaaaaaaaaaaaaaaaaaaaaaats up dawgs
19:44:08 <vanila> I want to implement unlambda
19:52:05 -!- scounder has joined.
19:57:09 <vanila> unlambda ``r`ci``s`k`c``s``s`ksk`kr.*
19:57:56 <elliott> !unlambda `r`ci``s`k`c``s``s`ksk`kr.*
19:58:05 -!- _Paul has left ("Leaving").
19:58:09 <vanila> my intepreter fails on this program
19:59:50 -!- nyuszika7h_ has joined.
20:00:04 -!- nyuszika7h has quit (Killed (sinisalo.freenode.net (Nickname regained by services))).
20:00:05 -!- nyuszika7h_ has changed nick to nyuszika7h.
20:00:19 -!- pikhq_ has joined.
20:00:41 -!- int-e has joined.
20:00:50 -!- viznut_ has joined.
20:02:32 <vanila> !unlambda ``r`cd`.*`cd
20:02:32 <EgoBot> \ * \ ** \ *** \ **** \ ***** \ ****** \ ******* \ ******** \ ********* \ ********** \ *********** \ ************ \ ************* \ ************** \ *************** \ **************** \ ***************** \ ****************** \ ******************* \ ******************** \ ********************* \ ********************** \ *********************** \ ************************ \ ************************* \ **************************
20:04:07 -!- olsner_ has joined.
20:04:32 -!- ^v has quit (Read error: Connection reset by peer).
20:04:33 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/fibo.unl
20:04:36 <vanila> i dont really believe this program
20:05:08 <vanila> how many extraneous features does this language have
20:05:18 -!- int-e_ has quit (*.net *.split).
20:05:19 -!- pikhq has quit (*.net *.split).
20:05:20 -!- drdanmaku has quit (*.net *.split).
20:05:24 -!- viznut has quit (*.net *.split).
20:05:27 -!- skarn has quit (*.net *.split).
20:05:30 -!- olsner has quit (*.net *.split).
20:05:32 -!- ^v has joined.
20:06:19 <elliott> vanila: that's just metanotation
20:06:52 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/pattern.unl
20:06:55 <vanila> i cant run this either :/
20:06:59 <vanila> well i run it but nithing happens
20:07:07 -!- drdanmaku has joined.
20:07:12 -!- tromp__ has joined.
20:07:29 <elliott> are you stripping comments?
20:07:53 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/prime_numbers.unl I have to support c if i want to run this.. but i dont know how to :(
20:07:57 <elliott> it doesn't use c or d at least
20:08:10 -!- viznut has joined.
20:08:10 -!- olsner has joined.
20:09:19 -!- fizzie` has changed nick to fizzie.
20:09:28 -!- AnotherTest has quit (Ping timeout: 258 seconds).
20:09:43 -!- AnotherTest has joined.
20:09:43 <vanila> maybe if i emit CPS terms i can
20:09:53 -!- tromp_ has quit (Ping timeout: 258 seconds).
20:10:00 -!- viznut has quit (Ping timeout: 244 seconds).
20:10:00 -!- olsner has quit (Ping timeout: 244 seconds).
20:10:04 <vanila> http://lpaste.net/114354 so far
20:11:01 -!- tromp has quit (Ping timeout: 258 seconds).
20:11:06 -!- tromp_ has joined.
20:11:48 -!- erdic has quit (Ping timeout: 258 seconds).
20:12:14 -!- newsham has quit (Ping timeout: 258 seconds).
20:12:23 -!- erdic has joined.
20:14:50 -!- shikhin has quit (Ping timeout: 258 seconds).
20:15:08 <Bike> can you rewrite this in cps
20:15:15 <Bike> the interpreter itself, i mean
20:16:02 -!- AndoDaan_ has joined.
20:16:32 -!- shikhin has joined.
20:17:26 -!- AndoDaan has quit (Ping timeout: 244 seconds).
20:17:32 -!- AndoDaan_ has changed nick to AndoDaan.
20:27:20 <vanila> http://lpaste.net/114354
20:27:31 <vanila> i changed it to CPS but not sure how to fix c case still
20:29:00 <vanila> i mixed up parameter order in definition of c but even corrected it s not right
20:29:35 <vanila> no i fixd it fully now
20:29:37 <Bike> uh, this is the same paste as before
20:29:41 <Bike> ok, good! i guess!
20:29:58 <vanila> http://lpaste.net/114355
20:32:02 <vanila> The `dF function takes an argument Y and evaluates F, giving a function X, and returns the evaluation of `XY.
20:32:10 <vanila> now triangles works but I still can't run primes
20:32:17 <vanila> because i don't implement d
20:32:31 <vanila> i don't really understand it
20:32:53 <vanila> what would it look like in lambda calculus?
20:33:11 <elliott> vanila: `dX doesn't evaluate X
20:33:15 <elliott> despite unlambda being otherwise strict
20:33:29 <elliott> er, `dF doesn't evaluate F rather
20:33:33 <vanila> `dF = (lambda (y) (let ((x f)) (x y)) ?
20:33:34 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: dF: not found
20:33:58 <elliott> I know there are some subtleties...
20:34:22 <elliott> vanila: note that you have to be able to do, like
20:34:25 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `idF: not found
20:34:33 <elliott> so you can't just do d syntactically
20:34:38 <elliott> it can also be passed as a parameter or whatever
20:35:01 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/prime_numbers.unl
20:35:05 <vanila> holy *** thos uses a LOT of d
20:35:38 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/quine/
20:35:45 <vanila> there's more quines in unlambda than there are any other programs
20:37:10 <elliott> have you seen oerjan's self-interpreter?
20:37:44 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/CUAN/unlambda_interpreter.unl
20:38:20 <elliott> http://oerjan.nvg.org/esoteric/interpreter.unl
20:38:29 <elliott> maybe yours is the same thing but with fewer comments, I don't know
20:38:41 <vanila> wow his code looks really nice
20:38:55 <lambdabot> 2^(n(n-1)/2).[1,1,2,8,64,1024,32768,2097152,268435456,68719476736,3518437208...
20:39:04 <elliott> it has a nice character table
20:39:08 <Taneb> Hmm, that is not the sequence I have
20:39:16 <elliott> I guess that one you linked can't be complete because it doesn't
20:39:21 <Taneb> Next element is > 2E24
20:40:19 <Taneb> I guess what I'm doing is stupid, though
20:40:32 <elliott> vanila: http://oerjan.nvg.org/esoteric/ has an unlambda compiler
20:40:37 <elliott> I think it's hard to properly compile because of d though
20:41:25 <elliott> well, I guess it's essentially just call-by-name (or -need?), but...
20:46:45 -!- skarn has joined.
20:50:26 -!- olls has quit (Quit: Lost terminal).
20:55:32 <Vorpal> Well fuck sheepshaver, I was trying to use a browser in it. That crashes sheepshaver
20:55:46 <Vorpal> Both Netscape Navigator and Internet Explorer 5
21:03:27 -!- MoALTz has joined.
21:04:46 -!- MoALTz_ has quit (Ping timeout: 250 seconds).
21:04:55 <vanila> sheepshaver is so weird howitwants you to identity map low memory area
21:05:05 <vanila> you explicitly cant do that for security reasons...
21:05:09 <vanila> so its dodgy that they want it
21:05:23 <vanila> of course its something weird to do with how the emulatorworks butstill
21:05:28 -!- MoALTz_ has joined.
21:05:33 <vanila> i wishthere was good info about how to emulate powermac
21:05:43 <vanila> at least without being a hardware RE exper
21:05:51 <Vorpal> vanila, your spacebar is partially broken
21:07:15 <fizzie> I've used SheepShaver "succesfully".
21:07:32 <Vorpal> fizzie, oh yes, for a short while
21:08:12 -!- MoALTz has quit (Ping timeout: 272 seconds).
21:08:33 <elliott> it's probably easiest to just buy an old mac off ebay
21:08:40 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
21:09:08 * pikhq_ has a working Famicom now. Wheee.
21:09:11 <elliott> vanila: is it for security? I thought it was to just make sure *NULL segfaults
21:09:29 <Vorpal> elliott, or repair the power connector of my old first model ibook
21:10:00 <Vorpal> elliott, seen ais recently?
21:10:23 <fizzie> There's always qemu-system-ppc too.
21:10:25 -!- MoALTz has joined.
21:10:28 <vanila> I think that kernel data must live there
21:11:26 <fizzie> I bought an old ppc mac off the-Finnish-version-of-eBay (and then sold it again).
21:11:41 -!- AnotherTest has quit (Ping timeout: 240 seconds).
21:12:05 <vanila> 'Allowing processes to map low values increases the security implications of a class of defects known as "kernel NULL pointer dereference" defects'
21:12:20 <elliott> Vorpal: less than two months ago
21:12:26 <vanila> I thought there was more to it than that, but I guess it's just what you said
21:12:39 -!- MoALTz_ has quit (Ping timeout: 255 seconds).
21:12:39 <vanila> ais was here yesterday
21:12:48 <vanila> and I want to talk to zzo
21:13:01 <elliott> okay yeah he's just been using different nicks
21:13:17 <elliott> vanila: I guess that's getting the kernel to dereference a NULL pointer unwittingly?
21:13:22 <elliott> and then it panics or something?
21:13:53 <Vorpal> elliott, that is the gist about the 0-page protection yes
21:13:56 -!- MoALTz_ has joined.
21:15:53 -!- AndoDaan has quit (Quit: Leaving).
21:16:26 -!- MoALTz has quit (Ping timeout: 272 seconds).
21:30:33 <vanila> I want to design a simple lambda language to practice writing a compiler
21:31:07 <vanila> not sure how to design it, I thought about giving it simple types and data type definitions, but work.. :/
21:31:09 -!- Patashu has joined.
21:35:06 <b_jonas> vanila: do you want a compiler specifically, not an interpreter or something?
21:39:43 -!- AnotherTest has joined.
21:44:09 -!- AnotherTest has quit (Ping timeout: 255 seconds).
21:48:24 -!- AndoDaan has joined.
21:49:32 <paul2520> vanila: I'd recommend checking out Build Your own LISP: http://buildyourownlisp.com/
21:50:08 -!- ZombieAlive has joined.
22:19:38 -!- newsham has joined.
22:21:32 <Taneb> I feel like I ought to learn OpenCL or something
22:22:37 <nys> lisp in small pieces
22:22:41 <nys> is a good book
22:25:31 <int-e> Chapter 1. The opening parenthesis.
22:28:42 <nys> no no i was talking in reference to paul2520's earlier recommendation
22:28:43 <elliott> there... isn't a lisp called OpenCL, as far as I know
22:28:49 <elliott> nys was replying to vanila
22:28:54 <lambdabot> LOWI 152220Z AUTO 06007KT 020V100 9999 -SHRA FEW050 BKN060 12/07 Q0998
22:29:19 <elliott> ideally someone would write an open-source common lisp implementation that runs on GPUs called OpenCL for maximum confusion
22:31:33 <vanila> I find lisp in small pieces hard
22:31:44 <nys> i suppose it is
22:31:45 <Bike> it's all the denotational semantics.
22:31:48 <nys> it's nice and deep though
22:32:08 <Bike> anyone here have experience with weird japanese text encodings
22:37:40 <vanila> what should i call my lambda calculus language
22:38:59 <nys> Fat Calculus
22:40:29 <fizzie> While I was fiddling with things, enabled https:// for esolangs.org (at least experimentally).
22:40:33 -!- Primal has joined.
22:41:50 <fizzie> elliott: Next, a Gopher interface.
22:42:08 <elliott> btw we really need a new featured language
22:42:22 <Bike> i vote whatever vanila's doing
22:43:11 <vanila> I would help to make a gopher version of esolangs
22:43:29 <elliott> fizzie: nice overkill RSA key
22:43:34 <Primal> Someone make an app or something
22:44:07 <elliott> does startcom not have an SHA-2 intermediate cert?
22:44:31 <elliott> also, you have SSL3 enabled
22:45:00 <elliott> do you know about https://wiki.mozilla.org/Security/Server_Side_TLS
22:45:22 <elliott> it's offering like 3DES and stuff right now :p
22:45:22 <fizzie> Yes, I copied the zem.fi SSL/TLS settings from there.
22:45:25 <vanila> $ zsync http://esolangs.org/dump/esolang.xml.zsync
22:45:45 <fizzie> I'll see about fixing the esolangs nginx config too.
22:45:50 <elliott> fizzie: it's updated recently though, since poodle
22:45:54 <vanila> ok if i managed to get this as a gopher will it be hosted?
22:45:56 <elliott> well I guess 3DES is actually only disabled on the "modern" one there, sigh
22:46:27 <elliott> fizzie: also it looks like you're on an old openssl
22:46:51 <FireFly> TIL about zsync. seems useful
22:47:07 <elliott> or at least SSL labs claims you have exploitable CVE-2014-0224 (?!) and no TLS_FALLBACK_SCSV (but just disabling SSLv3 is better)
22:47:40 <fizzie> elliott: I haven't really been keeping the rest of the server updated (it's kind of outside the scope of my mandate), but I guess I could install security updates from the repository, at least.
22:47:59 <elliott> I don't think Gregor cares about that server :p
22:48:39 <vanila> any thoughts about gopher
22:48:52 <elliott> can you do gopher over TLS
22:48:59 <FireFly> I'm sure zzo38 would approve of gopher access
22:49:10 <elliott> also all of this is kind of irrelevant without HSTS of course, but presumably that comes after
22:49:59 <fizzie> I was thinking more like a MediaWiki extension that'd host a live Gopher (read) view, not a snapshot.
22:50:02 <fizzie> Not sure if there is one.
22:50:06 <vanila> I like zzo's gopher page
22:50:12 <fizzie> It sounds like the kind of thing someone would have written, but perhaps not.
22:50:25 <fizzie> (If there is, it's probably horrible.)
22:50:36 <vanila> fizzie, I was thinking of writing such a converter so that it could be hosted with a normal gopher server
22:51:48 <Sgeo> Uh. Why is Google telling me that AIM may harm my browsing experience?
22:52:13 <fizzie> I don't know anything about how Gopher servers deal with dynamic content, but if they do, it could query the live pages via the MediaWiki API, of course.
22:53:12 <vanila> that sounds better because it's up to date
22:54:06 <Primal> I need a new Python compiler that can still loop in JavaScript++
22:55:52 <elliott> thankfully the wiki has been replaced by a 502 Bad Gateway page so it's really easy to make a gopher version
22:56:50 <fizzie> aptitude had stalled in the middle of a PHP update, because it wanted to ask me a question.
22:57:04 -!- AnotherTest has joined.
22:57:23 <elliott> I wonder if the wiki was vulnerable to shellshock because of these upgrade practices :p
22:57:43 -!- AnotherTest has quit (Remote host closed the connection).
22:57:54 <fizzie> It's still 502 Bad Gateway even after finishing. Curious.
22:58:10 <elliott> maybe php-fpm didn't restart properly or something
22:58:46 <Primal> Yeah it's still a bad gateway
22:59:20 <fizzie> "connect() to unix:/var/run/php5-fpm.sock failed (13: Permission denied)"
23:00:03 <int-e> hehe. "*tl;dr* It's complicated."
23:00:50 <FireFly> Huh, gopher seems pretty simple
23:01:16 <fizzie> Oh, the default listen.mode for the socket has been changed from 0666 to 0660.
23:01:39 -!- Ethereal_ has joined.
23:01:50 <fizzie> Should be back in business.
23:02:26 <fizzie> (If not, then that's tough luck, since I'll be away for a few minutes.)
23:04:45 <Primal> My Unreliable past is a weird name for a language
23:04:47 <vanila> so i have to parse XML and then translate mediawiki syntax to gopher...
23:05:55 <FireFly> "translate mediawiki syntax to gopher"?
23:06:32 <elliott> fizzie: also, you don't seem to have forward secrecy(? maybe? SSL Labs says something about "with some browsers" but also that it doesn't work with their "reference browsers".)
23:09:20 <elliott> I really don't know why it would be saying that...
23:09:56 <Primal> I need more money for a new VPN but .. I need this money for the fobs
23:11:13 -!- Ethereal_ has quit (Quit: I Burnt my food).
23:12:44 <Sgeo> Installing new Pidgin even though Pidgin keeps dying. Maybe someone's attacking me :/. Even if not and it's just Pidgin sucking majorly, why keep running insecure stuff
23:13:47 <vanila> im sory i dont think I will do this
23:18:05 <int-e> elliott: is it saying that because some non-DH configurations are accepted? Like AES256-SHA...
23:18:48 <elliott> int-e: I guess. it would be weird to say that there's no PFS with "reference browsers" if those reference browsers can't do DH, but I guess maybe they can and just don't negotiate it with the current settings?
23:18:58 <int-e> ( http://sprunge.us/PMYV )
23:19:01 <idris-bot> (input):1:5: error: expected: "!!",
23:19:34 <elliott> yes, the cipher configuration is a mess.
23:20:01 <int-e> surely 90% of those combinations have no right to exist?
23:20:02 <Bike> broken debuggers: the best or the bestest
23:20:22 <elliott> fizzie: https://forum.startcom.org/viewtopic.php?f=15&t=15742 SHA-2 intermediate certificates exist, happily
23:21:01 <Primal> U.S. xabber or jappix if you are looking for an xmpp client
23:29:41 -!- Primal has quit (Quit: Page closed).
23:29:59 <fizzie> elliott: Crafty. All the links in their instructions pointed at the SHA-1 hashed versions.
23:30:40 <elliott> fizzie: I don't think you understand. TLS is meant to be painful.
23:33:08 <elliott> incidentally you're welcome to give me root if that would be less annoying than me bothering you about this :p
23:34:01 <fizzie> "The size of the prime number p constrains the size of the pre-master key PMS, because of the modulo operation. A smaller prime almost means weaker values of A and B, which could leak the secret values X and Y. Thus, the prime p should not be smaller than the size of the RSA private key."
23:35:11 <fizzie> (For the DH parameter thing.)
23:35:42 <elliott> oh, the problem is you have a 4096-bit RSA key?
23:35:58 <fizzie> openssl dhparam 4096 actually said, and I quote, "This is going to take a long time".
23:36:11 <elliott> 4096 bits probably isn't buying you anything but a very slight slowdown for a year-long key if you have PFS anyway
23:36:42 <fizzie> Yes, but I can't switch it to anything shorter until the certificate expires.
23:37:03 <elliott> certificates are such a mess
23:38:09 <elliott> so wait, what is it doing right now then?
23:38:23 -!- ^v has joined.
23:40:08 <fizzie> I don't know. I didn't configure a DH parameter file. Maybe it didn't advertise any EDH ciphers?
23:40:34 <fizzie> "openssl dhparam" has now filled one screen with .s and +s.
23:40:45 <elliott> I get "The connection is encrypted and authenticated using AES_128_GCM and uses ECDHE_RSA as the key exchange mechanism.", fwiw.
23:41:21 <fizzie> Well, it finished, anyway, so I'll give it the generated parameters.
23:41:30 <elliott> I hope these aren't as slow to use as they are to generate.
23:42:43 -!- Dulnes has joined.
23:43:36 <Dulnes> The cookies I've burned them
23:48:36 <elliott> fizzie: I believe you can fix the SHA-2 thing without getting a new certificate, since that part isn't signed, by the way
23:49:27 <fizzie> elliott: Yes, that should be fixed now.
23:49:50 <fizzie> elliott: ssllabs test says overall A (subscores 100, 95, 100, 90).
23:50:02 <elliott> ah, cache was getting in the way
23:50:50 <fizzie> "Forward Secrecy: Yes (with most browsers) ROBUST" now too.
23:51:03 <fizzie> I didn't enable OCSP stapling, because the nginx version was too old for that.
23:51:34 <fizzie> And didn't toggle on HSTS yet either, since, well. The canonical address is still the http:// one, anyway.
23:51:40 <elliott> I think probably nobody cares about OCSP stapling
23:51:47 <elliott> since I don't think anyone does revocation checking right now?
23:51:58 <elliott> fizzie: heh, and I was just typing: thanks for the great work! ok, now how long until I can bug you to make it official and add preloaded HSTS? :p
23:52:18 <Dulnes> Well.. I know a guy who still does
23:52:23 <elliott> I wonder why mozilla's cipher configuration includes CAMELLIA suites.
23:52:36 <elliott> weird japanese clients, maybe?
23:52:37 <InvalidCo> I didn't realize that dwarf had turned into my pet
23:53:11 <Dulnes> palemoon and waterfox are nice to play with
23:53:40 <elliott> I wonder what you need to do to get A+
23:54:30 <InvalidCo> "the book was coated with contact poison!"
23:54:57 <b_jonas> InvalidCo: that's one of the failure to read effects
23:55:05 <fizzie> Also only got 90 in the "cipher strength" category, possibly because I went with the "intermediate" list.
23:55:21 <InvalidCo> apparently was trying to read the spellbook of cancellation
23:56:12 <myname> this seems to happen regularly
23:57:27 <quintopia> apparently the intro comp media class as georgia tech involves the entire class writing programs in Chef
23:57:38 <elliott> fizzie: yeah, going with the modern one would be nice but would rule out firefoxes older than feb 2014, chromes older than sep 2012, IEs older than oct 2013, opera older than july 2013, safaris older than june 2013, etc.
23:57:44 <quintopia> i'm sitting across from the poor sap who has to grade them
23:57:44 <elliott> which isn't a great combination with https-only
23:58:11 -!- Patashu has quit (Ping timeout: 240 seconds).
23:58:19 <elliott> I should figure out why they have that in there.
23:59:19 <fizzie> elliott: Let's see if the 'pert adds DNSSEC glue too. (I asked them to update the nameserver list -- switching VPSes -- and added a postscript about optionally doing that. For the one person with a DNSSEC resolver. And of course those whose DNS it will break as a collateral damage due to overly long DNS replies or whatnot.)
23:59:42 <elliott> fizzie: will you support DANE???
23:59:50 <elliott> a whole half a person would benefit from that
00:00:51 <b_jonas> why ever are they doing that?
00:00:51 <elliott> DNSSEC is nice because instead of relying on four billion master keys, any of which could be compromised by a government, it relies on one master key, which ... well, you can complete the joke
00:01:01 <elliott> (okay, plus one master key per tld)
00:01:07 <b_jonas> I mean, I like chef, it's a good esolang, but still
00:01:30 <quintopia> because it's simple enough for a beginner to pick up
00:01:45 <quintopia> and it gives them a chance to show some creativity
00:02:44 <elliott> fizzie: you should maybe advertise this somewhere so people can test that it works fine for them
00:03:13 <elliott> I suppose I should change my wiki password
00:03:32 <fizzie> elliott: I might do DANE, since AIUI it doesn't need any changes to the certificate. And it'd theoretically stop $SHADY_GOVERNMENT_SUBORNED_CA from issuing fraudulent esolangs.org certificates.
00:03:43 <fizzie> Huh, irssi has DANE support? Bizarre.
00:03:55 <elliott> fizzie: pretty sure the org. and . keys can still own you?
00:05:08 <int-e> What's the root of trust for DNSSEC?
00:06:31 <elliott> int-e: a key to sign the root zone
00:06:33 <fizzie> elliott: Sure, but maybe it could hypothetically stop someone who just has one single CA browser-trusted CA in their pocket, but no feasible way of faking DNS.
00:06:43 <elliott> int-e: haven't you seen the articles about their fancy international key-signing rituals
00:06:58 <elliott> http://www.theguardian.com/technology/2014/feb/28/seven-people-keys-worldwide-internet-security-web
00:07:18 <elliott> fizzie: okay, that's not a state actor, though :p
00:08:53 <int-e> arguably if org. does it, they'd be issuing *real* esolang.org certificates, not fake ones.
00:12:44 -!- oerjan has joined.
00:14:24 -!- qwertyo has joined.
00:24:43 -!- myndzi has quit (Ping timeout: 255 seconds).
00:27:02 <elliott> fizzie: so how long until esolangscorewwwi.onion
00:28:06 -!- NotJoel has left.
00:29:11 -!- not^v has joined.
00:29:19 -!- not^v has quit (Read error: Connection reset by peer).
00:29:33 <int-e> elliott: that's a nice article indeed. funny how old-fashioned some of the measures are
00:29:52 <int-e> "a photograph of themselves with that day's newspaper and their key, to verify that all is well." -- haven't those people heard of Photoshop?
00:30:08 -!- ^v has quit (Ping timeout: 258 seconds).
00:30:09 <elliott> I think it's just 90% theatre.
00:30:20 <elliott> people want ICANN to look like they're taking it very seriously and being impartial
00:30:56 <int-e> at least this show doesn't hurt anybody
00:30:57 <elliott> especially with the general dislike of them being a US-based organisation
00:31:51 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:32:14 <int-e> So where are those safety deposit boxes located?
00:32:27 <int-e> (I'm not quite through yet)
00:32:51 <elliott> the international space station
00:33:22 <elliott> ("In a nondescript industrial estate in El Segundo, a boxy suburb in south-west Los Angeles just a mile or two from LAX international airport, 20 people wait in a windowless canteen for a ceremony to begin.")
00:39:27 <int-e> So the smartcards are all on site. Is that enough to sign a key? :)
00:40:11 <elliott> I think if you can break in and steal the smartcards you win, yeah.
00:40:34 <elliott> why not just rob fort knox, though?
00:40:57 <elliott> I like http://static.guim.co.uk/sys-images/Guardian/Pix/pictures/2014/2/26/1393417295297/The-Icann-office-with-a-l-009.jpg. very high tech.
00:51:14 -!- boily has joined.
00:56:06 <oerjan> is it shinh.org or my web which is stupidly slow now
00:56:46 <oerjan> something intermittent
00:57:20 <vanila> do you think delay is essential in unlambda?
00:57:35 <oerjan> int-e: at least i'm not the only one who cannot see htf you get 53 bytes on that A057755
00:57:52 <oerjan> vanila: you don't need it to program, no
00:57:57 <oerjan> but it's often convenient.
00:58:10 <vanila> its too hard to implement
00:58:21 <int-e> phew. lucky I had that spare ssh connection ... after an upgrade new logins failed thanks to the loginuid PAM module.
00:58:52 <oerjan> vanila: c is much harder, and is also harder to avoid (although you _can_ do that too, i believe)
00:59:22 <int-e> oerjan: I didn't need to do anything special, all effort went into producing a faster-than-0.3-seconds solution.
00:59:44 <oerjan> vanila: also i don't think d is that hard, but the simplest way of implementing it does require you to be able to compare functions to it
01:00:17 <vanila> oerjan, I implemnted c using CPS tranform
01:00:40 <vanila> http://lpaste.net/114355
01:00:48 <oerjan> int-e: well i have 2 alternative methods that are obviously faster, but i cannot get them to be as short as 53 bytes. i have one that is 53 bytes and prints in reverse :P
01:01:20 <oerjan> vanila: if you want to see how to implement d as a pure function, see my ocaml "compiler"
01:01:55 <int-e> "fanzy" is the fanzy way of spelling "fancy".
01:04:44 <oerjan> the variations that use floating point get ruined by the required ceiling :8
01:05:13 <int-e> the best lose 2 characters
01:05:18 <vanila> oerjan, your unlambda code is really nice looking
01:05:26 <vanila> did you write it by hand?
01:05:35 <oerjan> vanila: thanks i invented the indentation style myself, and yes
01:05:59 * int-e wonders what unlambda code vanila is referring to
01:06:16 <vanila> http://oerjan.nvg.org/esoteric/interpreter.unl
01:06:24 <oerjan> i believe the lambda expressions i expanded it from were given in the comments
01:07:10 <oerjan> lucky my website is working again, i have been seeing motd's from the server people that the user page server was down
01:08:30 <oerjan> vanila: i think if you strip my interpreter of whitespace and comments, it's the shortest unlambda self interpreter out there, i don't think it would have been that if i used a generator
01:08:35 -!- qwertyo has quit (Ping timeout: 240 seconds).
01:08:55 <int-e> it's pretty much the obvious indentation style
01:09:01 -!- qwertyo has joined.
01:10:03 * int-e used to use a lambda elimination tool for snippets (like ^v `^v `$F `$G $v `$H $v)
01:10:22 <int-e> but not for complete programs
01:10:49 <int-e> however I never wrote anything more exciting than quines in Unlambda.
01:10:53 <vanila> unlambda seems too long
01:10:56 <vanila> i prefer a minimal language
01:11:13 <vanila> too many weird operators
01:11:25 <Bike> what's it's minimize
01:11:55 <int-e> vanila: its existence is justified by d(elay) and c(all/cc), which are mindbending to use in practice.
01:12:20 <int-e> OTOH, its I/O is quite awful.
01:12:29 <vanila> I suppose unlambda can't be lazy or you'd have to use monad for IO
01:12:35 <vanila> and that would get really stupid
01:12:44 <vanila> so d is kind of acceptable... but i don't like it...
01:12:58 <int-e> vanila: it's there to break you, not to be liked!
01:13:16 <int-e> v is amazing in conjunction with call/cc
01:13:33 <int-e> it can consume a continuation before it can be applied to anything else
01:13:37 <elliott> (I mean, lazy k is a language. but you probably know that)
01:13:56 <int-e> (yes, you can express it using s and k, but the same holds for i)
01:14:23 -!- AndoDaan_ has joined.
01:15:15 -!- AndoDaan has quit (Ping timeout: 240 seconds).
01:16:46 <oerjan> int-e: i used a lambda elimination tool for snippets too, but iirc it was mainly to check my hand elimination
01:17:06 <oerjan> (the ulify2.scm in the same directory)
01:17:10 <vanila> when I read about unlambda i learned that refcounting is effective for it
01:17:24 <vanila> because there is no cycles
01:17:46 <int-e> vanila: yay for strict languages
01:18:16 <vanila> I want to write a compiler for lambda + some?? things for practice at writing compilres which can use ref counting for GC
01:22:54 <oerjan> int-e: the unlambda input system is obviously an attempt to force people to actually _use_ c when programming it. as i've mentioned before, i _think_ you can avoid it, but you'll essentially be CPS transforming instead.
01:23:58 <int-e> oerjan: that part (using i/v for booleans) is ok; what I dislike is the proliferation of ? and . operators, rather than splitting things up into bits.
01:24:32 <oerjan> that meant i had to use an entire character table in the self interpreter
01:27:15 -!- qwertyo has quit (Ping timeout: 240 seconds).
01:28:00 -!- qwertyo has joined.
01:34:05 -!- Patashu has joined.
01:50:38 -!- qwertyo has quit (Ping timeout: 258 seconds).
01:51:28 -!- qwertyo has joined.
01:55:57 <oerjan> int-e: gah now i have a 53 byte solution that is slightly wrong on the last two numbers :(
02:01:47 <oerjan> slightly means that they're close to the right numbers.
02:02:07 <int-e> that doesn't help you in any way.
02:02:19 <Bike> doesn't it, int-e? doesn't it
02:03:39 * int-e wonders what Bike is getting at.
02:08:01 -!- qwertyo has quit (Ping timeout: 264 seconds).
02:08:20 -!- qwertyo has joined.
02:09:18 <Taneb> Help, my wikipedia user page redirects to the High Middle Ages
02:09:32 <Taneb> And has done so since 2008
02:09:52 <oerjan> Taneb: you might check it out occasionally, you know.
02:10:59 <HackEgo> 363) <oerjan> as i was filled with zzo38 mystery at the moment i saw <zzo38> quintopia: I am at Canada.
02:11:15 <elliott> he was last here on the 14th
02:12:45 <Sgeo> In an article about cocoa bean shortages: "R-6 was celebrated for its nutty and woody notes, with undertones of brown fruit and chocolate."
02:12:54 -!- olsner_ has changed nick to olsner.
02:13:08 <Sgeo> Chocolate (which apparently has different flavors?) can have undertones of chocolate?
02:13:10 <Sgeo> I am very confused
02:13:17 <Sgeo> http://www.bloomberg.com/news/2014-11-14/to-save-chocolate-scientists-develop-new-breeds-of-cacao.html
02:13:29 <vanila> scientist have saved choclate!
02:15:12 -!- shikhout has joined.
02:17:56 -!- adu has joined.
02:18:48 -!- shikhin has quit (Ping timeout: 264 seconds).
02:21:14 <oerjan> <elliott> I think it's memoised <-- no, absolutely not.
02:21:34 <oerjan> it would have been weirder if it did, i guess. but also less useful.
02:21:40 -!- adu has quit (Client Quit).
02:22:27 -!- qwertyo has quit (Ping timeout: 258 seconds).
02:23:14 -!- qwertyo has joined.
02:23:57 <oerjan> <vanila> there's more quines in unlambda than there are any other programs <-- that's because they held a competition.
02:27:10 <oerjan> incidentally the shortest one isn't optimal, i discovered.
02:27:19 <int-e> http://www.madore.org/~david/programs/unlambda/#quine
02:28:25 <vanila> he gave away SICP for it
02:30:16 <oerjan> (it contains `kv which can be shortened to just v, also removing the corresponding part in the "string representation")
02:31:12 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: unlambda: not found
02:31:52 <HackEgo> #!/bin/sh \ CMD=`echo "$1" | cut -d' ' -f1` \ ARG=`echo "$1" | cut -d' ' -f2-` \ exec ibin/$CMD "$ARG"
02:32:13 <oerjan> int-e: it's the interface to all the stuff transplanted from EgoBot
02:32:24 <int-e> ah, ibin rather than bin
02:32:43 <int-e> `! unlambda `.i````ss``s`k`s.i``s`k`ki|``s``s|.```s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.```s``s|.```s``s|.s``s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.s``s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.k``s``s|.i``s``s|.|i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.|``s``s|..
02:32:43 <HackEgo> ./interps/unlambda/unlambda.bin: file /tmp/input.290: parse error
02:32:57 <HackEgo> ls: cannot access bini: No such file or directory
02:33:03 <HackEgo> 1l \ 2l \ adjust \ asm \ axo \ bch \ befunge \ befunge98 \ bf \ bf16 \ bf32 \ bf8 \ bf_txtgen \ boolfuck \ c \ cintercal \ clcintercal \ cxx \ dimensifuck \ forth \ glass \ glypho \ haskell \ help \ java \ k \ kipple \ lambda \ lazyk \ linguine \ malbolge \ pbrain \ perl \ qbf \ rail \ rhotor \ sadol \ sceql \ sh \ trigger \ udage01 \ underload \ u
02:33:09 <HackEgo> ls: cannot access ibin/u*: No such file or directory
02:33:15 <HackEgo> ibin/udage01 \ ibin/underload \ ibin/unlambda
02:33:36 <int-e> I guess it's just plain Unlambda, no Unlambda 2.
02:33:43 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: udage01: not found
02:34:01 <oerjan> my guess is your program got cut off
02:34:20 <int-e> `! unlambda `.i````ss``s`k`s.i``s`k`ki|``s``s|.```s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.```s``s|.```s``s|.s``s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.s``s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.k``s``s|.i``s``s|.|i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.|``s``s|..i
02:34:21 <HackEgo> `.i````ss``s`k`s.i``s`k`ki|``s``s|.```s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.```s``s|.```s``s|.s``s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.s``s``s|..``s``s|.i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.k``s``s|.```s``s|.k``s``s|.i``s``s|.|i``s``s|.```s``s|.```s``s|.s``s``s|.```s``s|.```s``s|.s``s``s|.|``s``s|..i
02:34:32 <int-e> oerjan: I selected too little in my terminal
02:36:30 <oerjan> so is this another quine not in the distribution
02:37:01 <int-e> I recall sending David Madore a mail once, but never received a reply.
02:37:29 <oerjan> i recall doing that twice, once for my self interpreter and once for my intercal interpreter
02:38:33 <FireFly> for a moment I interpreted that as "Self interpreter"
02:38:38 <FireFly> As in the Smalltalk dialect
02:39:08 <oerjan> anyway, it's his loss.
02:40:23 <oerjan> presumably he completely lost interest, seeing as that unlambda 3 message has been there for over a decade.
02:44:27 -!- kcm1700_ has joined.
02:47:37 -!- kcm1700 has quit (Ping timeout: 264 seconds).
02:48:56 -!- kcm1700 has joined.
02:49:42 -!- kcm1700_ has quit (Ping timeout: 255 seconds).
02:50:35 -!- qwertyo has quit (Ping timeout: 240 seconds).
02:51:51 -!- qwertyo has joined.
02:56:20 <Dulnes> This is how I feel when I play with lisp https://i.imgur.com/RqI9ncI.jpg
02:59:49 <elliott> this is how I feel when I play with intercal https://upload.wikimedia.org/wikipedia/commons/9/9a/Avenger_-_Westphalian_horse.jpg
03:00:51 <nys> dulnes what the
03:01:10 <nys> could you elaborate on that picture?!
03:01:17 <vanila> http://www.gnu.org/software/emacs/its-cover.png me when lisp
03:01:48 <Dulnes> Sure it's from a video
03:02:17 <Dulnes> https://m.youtube.com/watch?v=iQ61q4oN7x0
03:02:44 <nys> well that's cool but also how does it connect with your feelings about lisp
03:02:49 <elliott> this is how I feel when I play with noit o' mnain worb https://i.imgur.com/C0BUG.jpg
03:03:47 <Dulnes> It just whenever I use it, I just go crazy with it just like that video
03:04:34 <elliott> this video does not seem to contain the image you linked at all
03:05:20 <nys> it sure doesn't i watched the whole thing to make sure
03:05:46 <Dulnes> Nah it's part of a post
03:06:16 <Dulnes> Anyways I have to go my friend is calling me to LE kitchen
03:06:22 <int-e> vanila: so how many cars have you wrecked by programming lisp when you should've paid attention to the road? :P
03:06:44 <elliott> int-e: not as many as cdrs
03:07:58 <FireFly> So I stumbled upon A000012
03:08:03 <lambdabot> The simplest sequence of positive numbers: the all 1's sequence.[1,1,1,1,1,1...
03:08:12 <FireFly> That has to be the silliest sequence on OEIS.
03:09:04 <int-e> Lisp, hmm. I once made the mistake of assuming that Common Lisp is Lisp, rather than an least common denominator of Lisp implementation. Common Lisp fails to acknowledge that there's a large body of Fortran (well, I wanted C) libraries out there that people might want to use; there's no inkling of FFI. So I discounted Lisp at the time. Now I've discovered Haskell, and frankly, to me that means it's too late for Lisp to make...
03:09:10 <int-e> ...much of an impression at all.
03:10:12 <FireFly> "The partial sums give the natural numbers" shocking
03:10:13 <boily> Lisp is a procedural language with an horrible syntax, nasty scopes and horrible macroes.
03:10:27 <lambdabot> Plugin `oeis' failed with: <<timeout>>
03:10:28 <lambdabot> Expansion of Jacobi theta function theta_3(x) = Sum_{m = -infinity..infinity...
03:11:10 <int-e> FireFly: the iterated partial sums give the binomial coefficients
03:11:21 <int-e> FireFly: including the triangle numbers!
03:11:43 <int-e> (I find this useful, actually)
03:12:07 <int-e> > map (take 4) (iterate (scanl1 (+)) (repeat 1))
03:12:09 <lambdabot> [[1,1,1,1],[1,2,3,4],[1,3,6,10],[1,4,10,20],[1,5,15,35],[1,6,21,56],[1,7,28,...
03:12:36 <FireFly> "a(n) is also the number of complete graphs on n nodes." heh
03:12:43 -!- NATT_SiM has joined.
03:13:30 <int-e> guess what, it's also the number of permutations of the numbers 1..n that are sorted in increasing order.
03:14:14 <int-e> I hope that sequence was added on some April 1st.
03:14:43 -!- boily has quit (Quit: AGILE CHICKEN).
03:14:46 <FireFly> I found the sequence while searching for square-free composites, because both of those keywords are mentioned in the list of silly properties of a(n)
03:20:58 -!- zzo38 has joined.
03:21:08 -!- qwertyo has quit (Ping timeout: 255 seconds).
03:21:42 -!- qwertyo has joined.
03:23:42 <HackEgo> [wiki] [[Unlambda]] http://esolangs.org/w/index.php?diff=41014&oldid=33851 * 212.95.7.185 * (-4) Fix link
03:25:58 <int-e> Oh time passes. That 344 character Unlambda 2 quine is 10 years old.
03:28:38 <HackEgo> [wiki] [[Unlambda]] http://esolangs.org/w/index.php?diff=41015&oldid=41014 * 212.95.7.185 * (-13) Update link: follow redirect
03:43:21 <Bike> wanna feel old? this unlambda 2 quine just voted for rick santorum
03:46:32 <nys> i remember when unlambda was big
03:46:37 <nys> as i recall dukakis was running
03:46:43 <nys> for governor
03:49:06 <int-e> Ah, from 100% disk usage to 95% in 23 simple key presses: 'tune2fs /dev/sdc1 -m 0'.
03:49:38 <int-e> (This is an external drive. No system critical log files are stored there.)
03:51:04 -!- qwertyo has quit (Ping timeout: 244 seconds).
03:51:18 -!- qwertyo has joined.
03:58:38 <int-e> Bike: FWIW, I believe the Republicans are generally against lowering the minimum voting age.
04:04:56 <int-e> why ... does systemd have the audacity to use the kernel message buffer for its useless information? sigh...
04:21:01 -!- oerjan has quit (Quit: Zzzz).
04:21:03 -!- qwertyo has quit (Ping timeout: 255 seconds).
04:21:45 -!- qwertyo has joined.
04:25:07 -!- qwertyo has quit (Client Quit).
05:04:54 -!- vanila has quit (Quit: Leaving).
05:18:18 -!- bb010g has joined.
05:26:29 -!- MDude has joined.
05:30:40 -!- AndoDaan_ has quit (Quit: What year is it!?).
05:38:29 -!- adu has joined.
05:47:22 <Bike> http://perlhacks.com/2014/01/dots-perl/ god, what the hell
06:08:21 -!- adu has quit (Quit: adu).
06:18:38 <Dulnes> Bike: oh god what the fuck
06:22:41 -!- NATT_SiM has quit (Remote host closed the connection).
06:27:57 -!- nys has quit (Quit: quit).
06:29:18 <zzo38> I have played a Dungeons&Dragons game today, and I am now working on write recording of it.
06:40:02 -!- mihow has quit (Read error: Connection reset by peer).
06:40:15 -!- mihow has joined.
06:40:17 -!- mihow has quit (Read error: Connection reset by peer).
06:41:21 <J_Arcane> Yikes. http://www.clickykeyboards.com/index.cfm/fa/items.main/parentcat/9244/subcatid/0/id/585221
06:41:29 -!- mihow has joined.
06:41:51 -!- adu has joined.
06:41:57 <zzo38> Do you think a bat can steal a magic wand in complete darkness while someone is in the middle of casting a spell with it?
06:43:47 <HackEgo> danddreclist 589: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
06:43:48 <HackEgo> danddreclist 58: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
06:44:56 <J_Arcane> elliott: experienced sticker shock.
06:45:22 <J_Arcane> I'd kinda like a keyboard with a built in pointing device, but didn't expect that particular price ...
06:45:37 <elliott> they manufacture new Model Ms etc.
06:45:51 <elliott> buying rarities is always gonna be expensive
06:46:11 <elliott> I don't know if you have experience with buckling spring but IME it's kind of awful compared to lighter mechanical switches
06:46:39 <J_Arcane> I grew up with a buckling spring AT. :)
06:46:57 <J_Arcane> I don't like a lot of the Cherry switches I've tried so far because they're too shallow.
06:46:59 <elliott> J_Arcane: http://pckeyboard.com/page/category/EnduraPro $99
06:47:14 <elliott> the Model F has really cool switches I think
06:47:16 <elliott> they're not the same as Model M
06:47:39 <elliott> I believe the unicomps are pretty much identical to what IBM used to sell, FWIW
06:48:09 -!- ZombieAlive has quit (Remote host closed the connection).
06:48:15 <elliott> personally I couldn't bring myself to buy a keyboard with a numpad ever again
06:48:15 <J_Arcane> That's what I've been told. Probably if I'm not getting anything 'special' it's the smarter play.
06:48:51 <J_Arcane> I used to swear by them until I moved to Finland and started using Finnish keyboards.
06:49:23 <elliott> scissor switches are a lot better than rubber domes, at least.
06:49:33 <J_Arcane> They all use the , for the decimal, but that just gets in the way whenever I have to type in English.
06:50:02 <J_Arcane> Yeah. I am trialling the Curve Comfort and the rubbery keys are just gross.
06:50:24 <elliott> https://upload.wikimedia.org/wikipedia/commons/2/2c/Foldable_keyboard.jpg have you ever wanted to live in that one dali painting
06:50:45 <J_Arcane> Heh, yeah, I've used one of those.
06:51:38 <J_Arcane> If only they'd made more of the split one.
06:51:50 <Sgeo> Are the functions for adjusting floating point behavior different on Windows and Linux?
06:53:19 <elliott> J_Arcane: clearly get a datahand
06:53:23 <elliott> that has a pointing device
06:53:35 <Sgeo> I think it's a libc thing
06:53:37 <elliott> bonus: costs way more than that IBM model
06:53:39 <Sgeo> I just want to do stuff from Rust
06:54:24 <J_Arcane> elliott: About on par with the split model-M, looks like. :/
06:54:42 <J_Arcane> http://www.ebay.com/itm/DataHand-Professional-II-Ergonomic-keyboard-/281497842360?pt=PCA_Mice_Trackballs&hash=item418a9432b8
06:55:46 <J_Arcane> Very rare, only 1,000 made. http://www.clickykeyboards.com/index.cfm/fa/categories.main/parentcat/12675
06:55:56 <J_Arcane> Last one to come up on eBay went for $1600.
06:56:20 <elliott> it looks like they literally just sawed a keyboard in two
06:56:44 <elliott> looks like you can't separate the two halves very much? meh
06:57:23 <Dulnes> How do i get stuff to out
06:58:10 <Dulnes> I am thoroughly confuzzled
06:58:56 -!- shikhout has changed nick to shikhin.
06:59:27 <J_Arcane> Oooh. This looks nice: https://elitekeyboards.com/products.php?sub=pfu_keyboards,hhkbpro2&pid=pdkb400b
07:01:49 <elliott> they're even further away from buckling springs than cherry switches are
07:02:07 <elliott> https://elitekeyboards.com/proddata/images/topreswitch405.png
07:02:23 <J_Arcane> And also expensive, and not likely to show up in a shop any time soon for my to try one ...
07:02:36 <elliott> well, the HHKBs are pretty popular
07:03:08 <Dulnes> Do u need a fancy keyboard?
07:03:35 <Dulnes> I just get a keyboard like if it works ill buy it
07:03:57 <elliott> Dulnes: are you a markov chain bot or something
07:04:36 <Dulnes> What do you mean Elliot
07:05:30 <elliott> no, it was too rude to explain :p
07:05:37 <Dulnes> Did you think u was a bot
07:05:54 <J_Arcane> Dulnes: I get cramping and pain in my fingers from the impact on cheaper keyboards; and it's been getting worse lately. I tend to do better with something with a deep keystroke (or a really shallow one once I get used to it).
07:06:07 <J_Arcane> Ergo is a plus too because wrist pain.
07:06:37 <J_Arcane> A bit, and I'm working on that.
07:07:18 <Dulnes> Like sit up straight and angle your hands down
07:07:23 <J_Arcane> elliott: OH wow, the IBM split thing isn't just a simple hinge. It's like a knobby thing, adjusts vertically and horizontally.
07:07:28 <J_Arcane> http://www.dansdata.com/clicky2.htm
07:07:40 <elliott> J_Arcane: you could get a kinesis advantage or something
07:07:42 <Dulnes> Slouching encourages a hunch
07:07:54 <J_Arcane> elliott: Yeah, I'm considering one of those as well.
07:08:30 <J_Arcane> A friend just bought the big weird one, with the two bowls, because he's been hacking for years and it's really starting to get to him
07:08:41 <elliott> can't wait until I'm old and have to worry about ergonomics from all my years of slouching and bad typing
07:09:29 <coppro> if I get a job at google again I'm going to actually set up my desk ergonomics properly
07:09:40 <J_Arcane> I'm only 32. :/ But weak wrists run in my family. Both my parents developed wrist problems relatively young too.
07:09:43 <coppro> right now I'm kind of boned because the university doesn't care
07:09:56 <elliott> J_Arcane: you're over 1.5x my age :p
07:10:04 <coppro> and at home I have non-adjustable furniture that I don't use anyway because I'm terrible and mostly compute from my bed
07:10:25 <J_Arcane> Oooh, and the IBM split is seperatable.
07:10:26 <elliott> same. I'm the laziest person
07:10:29 <Dulnes> J_Arcane: i usually use a touch screen tablet keyboard for my comouter but if i ever want to type fast i use a keyboard that has uplifted key borders so you dont accidently hit the wrong key when you type
07:12:02 <Dulnes> Also computer chairs are on my list i have one that is just like asking you to slouch
07:13:34 <J_Arcane> Oh wow. Speaking of keyboards being 'sawn in half': https://www.kinesis-ergo.com/shop/maxim-for-pc/
07:14:50 <int-e> Sigh. Magic is BAD.
07:15:10 <Dulnes> Where do i go with this keyboard
07:17:12 <int-e> (I'm preparing a LaTeX document. When I added an appendix, all labels of figures and chapter numbers obtained an extra . at the end. Turns out this is supposed to implement a former rule in the german orthography.)
07:18:00 <int-e> Crazy. (This is the scrbook style, from KOMA-script. There's an option to switch this behavior off, fortunately.)
07:18:21 <int-e> But it took quite some time to figure it out.
07:19:59 -!- adu has quit (Quit: adu).
07:23:06 <J_Arcane> Well, KOMA-Script is a German standard, as I understand it.
07:23:32 <J_Arcane> It just has so many cool features that it's useful for a lot of other stuff as well. ;)
07:25:15 <int-e> So the rule implemented is, if there's any section label containing a letter (like A.1) then *all* section labels obtain a trailing dot, throughout the document. This isn't too bad for sections (I didn't even notice it there), but Figure 1.1.: Caption looks just awful.
07:27:04 <int-e> And I'm using a style that's built on top of KOMA-script, so at the point where I should've looked for the documentation I was already digging in style files...
07:32:02 <J_Arcane> I think my last book was gonna be in KOMA-Script before I cancelled it.
07:32:02 -!- b_jonas has quit (Ping timeout: 264 seconds).
07:32:38 <J_Arcane> Maybe I should order one of those Cherry samplers, see if there's one of the switch types I do like.
07:33:01 <J_Arcane> Mostly I've only tried the 'gaming keyboards' and they tend to use the linear switches instead of clicky/bumpy ones.
07:33:06 -!- m724 has joined.
07:34:29 -!- m724 has quit (Client Quit).
08:00:21 -!- b_jonas has joined.
08:07:22 <J_Arcane> Hah, neat. Unicomp still makes APL keyboards.
08:13:33 -!- MDude has changed nick to MDream.
08:15:56 -!- shikhout has joined.
08:18:57 -!- shikhin has quit (Ping timeout: 258 seconds).
08:30:11 -!- shikhout has changed nick to shikhin.
08:54:02 <Jafet> You know what that means, right
09:12:08 -!- b_jonas has quit (Ping timeout: 255 seconds).
09:17:44 -!- b_jonas has joined.
09:28:52 <mroman> blsq ) {5 4 3 2 1 9 8}6{?d?d==}LO
09:51:13 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:20:35 <J_Arcane> ahahahaha. The Wikipedia page for the Shakespeare esolang has Inform-7 in the 'see also' section. :D https://en.wikipedia.org/wiki/Shakespeare_(programming_language)
10:26:07 -!- Phantom_Hoover has joined.
10:26:08 -!- Phantom_Hoover has quit (Changing host).
10:26:08 -!- Phantom_Hoover has joined.
10:28:33 -!- S1 has joined.
10:40:14 <HackEgo> [wiki] [[Talk:Main Page]] http://esolangs.org/w/index.php?diff=41016&oldid=40927 * Rdebath * (+267) /* Tom's idea */ new section
10:40:49 <Sgeo> I don't understand frac()
10:41:13 <Sgeo> Trying to find valid small values of p here: frac(250 / (p*fps)) > 0.5 where 40 <= fps <= 45
10:41:31 <Sgeo> That where is a forall
10:41:49 <Sgeo> fps is a variable, not f*p*s
10:42:53 <Sgeo> I mean, I know p=8 works, and there's a bunch of other easy to find large values for p
10:45:04 <Sgeo> In order for frac(250/a) and frac(250/b) not to something between a and b, the difference between a and b must... not... something?
10:45:21 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41017&oldid=41005 * Rdebath * (+112) Appears to be the Author's intention.
10:46:16 <HackEgo> [wiki] [[Talk:Dimensions]] http://esolangs.org/w/index.php?diff=41018&oldid=41011 * Rdebath * (+98) /* Proof of Turing-completeness */
10:51:43 <Sgeo> I'm actually only interested in values of p of the form 2^n where n is an integer in [-23, 3], so I could just test all of those with code, I ... no I can't, can't easily check that there are no values in between 40 and 45 that don't make it flip over
10:59:09 <Sgeo> I think I could just check both values and see if the whole portion is the same and frac of both is > 0.5
11:31:30 -!- AnotherTest has joined.
11:34:27 <Jafet> |250/40p - 250/45p| < 1/2 gives the trivial lower bound p > 25/18
11:37:51 <Jafet> (The actual solution is when 250/40p < 4, so p > 25/16)
11:43:53 <J_Arcane> Yay. Well, I finished the basic definitions for my BASIC-inspired Racket/Lisp dialect, but it's unusable because I can't figure out the module system at all.
11:46:51 <b_jonas> J_Arcane: um, how about scheme r7rs module system?
11:48:04 <J_Arcane> My macros aren't being provided properly, and I can't figure out why, and without that it's useless for anything but playing around in the REPL.
11:50:23 <J_Arcane> Also tried two different methods for the #lang s-expr (which is what I want to do) and they don't work either. :P
11:54:49 -!- Patashu has quit (Ping timeout: 264 seconds).
12:10:08 -!- AndoDaan has joined.
12:21:26 <mroman> AndoDaan: ww. you did leapfrogging in Burlesque?
12:23:26 <AndoDaan> Yeah, It was easier than I thought (didn't look to golf my code at all though.)
12:24:57 <AndoDaan> And yeah, MNNBFSL might be pretty well suited to implement in Burlesque.
12:27:00 <AndoDaan> mroman, you mentioned that burlesque was going to be Object Oriented (if ircc)?
12:30:27 <AndoDaan> !blsqbot "214365879"ln{JPpL[ro{48.+L[pPjFi}m[0-.+]2CO{<-{.-}r[}m[J{{{0.>}'>{0<.}'<}cn[-}m[jJ2CO{{.*}r[1.<}m[0+]j)abz[{q.+r[}m[z[{{_+}r[}m[++Q}m[p^
12:33:32 -!- AndoDaan_ has joined.
12:36:03 -!- AndoDaan has quit (Ping timeout: 272 seconds).
12:37:48 -!- AndoDaan_ has changed nick to AndoDaan.
12:38:33 <mroman> AndoDaan: I'm not sure yet @oop
12:38:49 <mroman> You can define functions though
12:39:00 <mroman> !blsq %square={^^.*} 9 %square!
12:42:16 -!- S1 has quit (Quit: S1).
12:44:10 <AndoDaan> cool. wow, that will probably ease a lot.
12:46:42 <AndoDaan> ha, just tried using a function as a variable.
12:47:02 <AndoDaan> but your way is probably better...
12:48:51 <blsqbot> | ERROR: Burlesque: (e!) Invalid arguments!
12:49:17 <blsqbot> | That line gave me an error
12:56:52 <fizzie> Re recent submission, didn't much golf that either.
12:58:30 <J_Arcane> I have at last got Heresy working.
12:58:37 <J_Arcane> Next will have to come actually documenting it.
12:58:54 <AndoDaan> Bah, and still a full 50char less than mine.
12:59:36 <AndoDaan> Or... you guys are at the top of your game.
13:05:03 <AndoDaan> But hey, I wrote a deadfish interpreter in python yesterday, soo...
13:05:48 <AndoDaan> nope, don't know how to make that impressive.
13:09:35 <Melvar> < J_Arcane> Oooh. This looks nice: https://elitekeyboards.com/products.php?sub=pfu_keyboards,hhkbpro2&pid=pdkb400b – That looks kinda useless because it has control where the left third-level shift has to be.
13:20:22 <elliott> it's a bit hyperbolic to call a keyboard useless for one design choice
13:20:33 -!- oerjan has joined.
13:22:25 <Taneb> elliott, unless the design choice is something like it not having keys
13:30:29 <HackEgo> \ This is perl 5, version 14, subversion 2 (v5.14.2) built for x86_64-linux-gnu-thread-multi \ (with 88 registered patches, see perl -V for more detail) \ \ Copyright 1987-2011, Larry Wall \ \ Perl may be copied only under the terms of either the Artistic License or the \ GNU General Public License, which may be found in the Perl 5 source kit
13:30:39 <HackEgo> Unimplemented at -e line 1.
13:34:12 <Melvar> Oh huh, it doesn’t have the key to the right of left shift anyway, which is also necessary … and a few other important keys have moved to hard-to-reach locations.
13:35:48 <Melvar> I should have looked more closely before complaining about the most obvious thing.
13:42:26 -!- MoALTz_ has quit (Read error: Connection reset by peer).
13:44:34 -!- MoALTz has joined.
13:44:57 <elliott> true. I'm sure J_Arcane would find it literally impossible to use because it doesn't have keys you personally care about.
13:45:05 <elliott> (p.s., in a US layout, the key to the right of left shift is "z")
13:45:26 <J_Arcane> On a Finnish keyboard, it's <.
13:45:29 <elliott> it also doesn't have a numpad or f keys!!11
13:45:36 <elliott> or a PS/2 cable (probably?)
13:47:03 <elliott> I use US keyboards because I dislike the weird large enter keys.
13:47:28 <elliott> and have gotten used to the placement of @ and ". and want a $ key more than a pound sign
13:47:47 <elliott> by which I mean a pound sterling sign, and not what americans call a pound sign, which is #...
13:53:15 <fizzie> mroman: Minor Burlesque documentation issue: [~ is documented to work only on blocks or ints, even though it seems to work also on strings, like ~] and [- and -].
13:55:53 -!- S1 has joined.
13:56:44 -!- MoALTz_ has joined.
13:58:23 -!- MoALTz has quit (Read error: Connection reset by peer).
14:13:46 -!- vanila has joined.
14:15:50 -!- shikhout has joined.
14:18:42 -!- shikhin has quit (Ping timeout: 240 seconds).
14:22:25 <oerjan> it seems that dmm has gone a bit fruitcake
14:23:25 <vanila> oerjan, I was wondering how come you're so good at esolang stuff
14:23:51 <vanila> obviously you work very hard but maybe you also discovered the crystal orb or something?
14:26:19 <J_Arcane> in other fun programming news, Github arbitrarily switched lexers for syntax highlighting, and now half the languages on there are broken ...
14:26:40 <oerjan> vanila: i've always been good at math stuff.
14:28:14 -!- drdanmaku has joined.
14:32:14 <oerjan> esolanging is basically about building a device with building blocks out of pure logic.
14:32:52 <oerjan> more abstract than ordinary programming, but less abstract than heavy math.
14:35:32 <oerjan> but with no essential sharp border to either side.
14:37:06 * oerjan did not know fruitcake had slided to that meaning in the us.
14:40:40 -!- shikhout has changed nick to shikhin.
14:50:16 -!- AndoDaan has quit (Ping timeout: 265 seconds).
14:57:14 <J_Arcane> I really hate Markdown right now.
14:58:17 <b_jonas> J_Arcane: I always hate it
14:58:32 <b_jonas> and mostly, it's not even markdown's fault, but the fault of those who misuse it
15:00:00 -!- AndoDaan has joined.
15:00:08 -!- AndoDaan has left.
15:00:15 -!- q3k has joined.
15:00:46 <J_Arcane> FFS, GH Markdown can't even handle fucking newlines sanely.
15:01:37 -!- AndoDaan has joined.
15:06:43 <J_Arcane> Anyway, this is what I did this week. https://github.com/jarcane/heresy
15:10:48 <vanila> J_Arcane, http://lpaste.net/114398
15:14:19 -!- S1 has changed nick to S0.
15:16:18 <J_Arcane> Ahaha! My package does work. :D
15:16:59 <vanila> the whole thing is just macros
15:17:10 <vanila> that makes the implementation so short and to the point
15:17:25 <J_Arcane> It was just an excuse to practice macro writing more than anything.
15:17:42 <vanila> you know a really cool macro system is called CK macros
15:17:45 <vanila> you might be interested in it
15:18:08 <vanila> http://okmij.org/ftp/Scheme/macros.html
15:19:38 <J_Arcane> Interesting. Think my brain's a little fried to make much sense out of that right now.
15:26:01 <vanila> it uses syntax-rules to make a new macro system based on interpreting code
15:26:41 -!- MDream has changed nick to MDude.
15:27:25 -!- bb010g has quit (Quit: Connection closed for inactivity).
15:29:37 <J_Arcane> I do kinda like Racket's macro system, now that I've had some time with it. The pattern matching is v. powerful and made something like this mostly easy, right up until it didn't go easy, and then figuring out why can be a nightmare for a noob.
15:30:07 <J_Arcane> In particular, the workarounds needed to do BREAK and CARRY with a hygienic macro system were a pain in the arse.
15:50:32 -!- shikhin has quit (Ping timeout: 258 seconds).
15:56:15 -!- boily has joined.
15:57:20 -!- shikhin has joined.
15:58:36 <HackEgo> [wiki] [[User talk:Bataais]] http://esolangs.org/w/index.php?diff=41019&oldid=40853 * Bataais * (-100) Blanked the page
16:17:17 <Taneb> How does a reduced set of residues differ from a set of units?
16:26:36 -!- S0 has quit (Quit: S0).
16:28:18 <oerjan> Taneb: just independently evolved terminology?
16:32:28 <J_Arcane> I wonder if Heresy really qualifies as an esolang. Other than the insane inspiration, it's pretty useable and normal.
16:36:55 -!- nys has joined.
16:38:19 <J_Arcane> https://github.com/jarcane/heresy
16:41:21 <b_jonas> I didn't know that's what it was called
16:42:09 <b_jonas> if it's basic-inspired, it has to have that
16:42:19 <Bike> yeah this doesn't seem very eso
16:42:25 <Bike> well it also says functional
16:42:42 <Bike> haha rem as a form
16:43:04 <J_Arcane> b_jonas: IT doesn't have one. :D
16:43:52 <b_jonas> why does it have a basic-like do-while loop then? how do you even use that without mutable storage?
16:45:02 <Bike> you call the body repeatedly with a new parameter.
16:45:15 <b_jonas> Bike: that's how a scheme-like do loop works
16:45:28 <J_Arcane> Mainly just to be able to run a REPL, but it's lack of carry support is an oversight.
16:45:29 <b_jonas> Bike: but this one doesn't appear to work like that
16:45:48 <b_jonas> maybe... but then the description is confusing
16:45:50 <J_Arcane> Under the hood, it *is* a scheme do loop.
16:46:21 <elliott> J_Arcane: it is impure because of input despite having no mutable storage, right?
16:46:34 <elliott> can it access files? you can use them for mutable state if you really have to
16:46:35 <J_Arcane> OR rather, a (let loop ... (loop)) construction with a break function (yay exit continuations!)
16:47:20 <J_Arcane> elliott: I think that would be technically true; there's no file I/O yet though, just basic print and input; haven't gotten to external IO. That is one reason why I backed off from using the word 'pure' anywhere in the docs. :D
16:48:30 <b_jonas> J_Arcane: but then its description is strange
16:48:54 <J_Arcane> Heh, well, it's cut and pasted from the code comments (which are a little out of date.
16:49:20 <Bike> also isn't "lisp but basic" logo
16:49:27 <Bike> not that this is much like logo at all, ofc
16:49:28 <b_jonas> J_Arcane: maybe also add some examples if you can make it work
16:49:47 <J_Arcane> Yeah, I have a 99 bottles and a Fact example, but some better ones would be nice.
16:52:16 <J_Arcane> Fixed the docs and the fact example. Thanks for the pointers!
16:52:32 <J_Arcane> Also, my mouse just broke. So that's fun.
16:54:17 -!- NATT_SiM has joined.
16:54:48 <elliott> J_Arcane: good excuse to buy one of those keyboards
16:59:23 -!- shikhin has quit (Remote host closed the connection).
16:59:41 -!- shikhin has joined.
17:10:40 -!- serika has joined.
17:17:45 -!- oerjan has quit (Quit: Bye!).
17:19:53 -!- ZombieAlive has joined.
17:23:08 -!- idris-bot has quit (Quit: Terminated).
17:25:09 -!- Melvar has quit (Quit: rebooting).
17:32:59 -!- Melvar has joined.
17:35:20 <J_Arcane> I made the front page on Hacker News. XD
17:37:02 <elliott> J_Arcane: "CL already does this." -- I don't think CL has continuations
17:42:35 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds).
17:45:39 <J_Arcane> elliott: https://twitter.com/J_Arcane/status/533547756150095872
17:46:11 <elliott> you can do loops and stuff with it
17:46:39 <J_Arcane> There's 99bottles implementation entirely in format, in the shape of a bottle.
17:48:26 <J_Arcane> http://www.99-bottles-of-beer.net/language-common-lisp-114.html
17:56:19 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
17:59:19 <FireFly> What's the computational class of format?
18:03:34 <vanila> i guess its turing complete
18:07:37 <Bike> i don't think it can do unbounded loops.
18:07:45 <Bike> not counting the "call arbitrary lisp functions" part, obviously.
18:09:22 <vanila> http://www.lispworks.com/documentation/HyperSpec/Body/22_cgf.htm maybe this?
18:10:00 <Bike> are you allowing nested calls? like (format nil "...~?..." (format nil ...))
18:10:02 <vanila> and http://www.lispworks.com/documentation/HyperSpec/Body/22_cga.htm might allow goto
18:10:19 <Bike> ~? doesn't do you much good then
18:11:22 -!- idris-bot has joined.
18:12:07 -!- Sprocklem has joined.
18:22:37 <Taneb> shikhin, that is where we are
18:22:40 <Dulnes> having a fullscale argument with a lisp bot is fun
18:23:20 <HackEgo> shikhin: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
18:23:46 <Dulnes> its even more colourful on mobile
18:24:07 <boily> shikhin was never `relcomed?
18:24:23 -!- oonbotti2 has joined.
18:24:25 <shikhin> I'm sorry, I was testing a bot.
18:24:57 <boily> wasn't oonbotti one of fizzie's bot?
18:24:57 <nortti> you could've checked it from the sources
18:25:08 <int-e> `` echo ... ___ ... f | dc
18:25:11 <HackEgo> 0 \ 0 \ 0 \ 0 \ 0 \ 0 \ 0 \ 0
18:25:33 <nortti> (I originally intended for that command to print ascii-art goatse but decided against it)
18:25:48 <boily> btw, how does one pronounce “oonbotti”?
18:25:49 <shikhin> nortti: Clearly no sane person would do that on a public channel!
18:27:17 -!- hjulle has quit (Remote host closed the connection).
18:27:47 <nortti> int-e: different way to mark a double-consonant
18:28:39 -!- Dulnes has quit (Quit: conception buildup in my compiler have to restart).
18:28:58 <boily> @ask Dulnes what is a conception buildup?
18:29:08 <boily> nortti: makes sense.
18:30:22 -!- Dulnes has joined.
18:31:10 <FireFly> isn't the point of irccloud to not disconnect for computer maintenance?
18:31:45 <Dulnes> phone is connected to computer
18:32:02 -!- Sprocklem has quit (Quit: [).
18:32:12 <Dulnes> its charging >_> i dont have a adapter
18:32:16 <fizzie> I think that should be ː, not :.
18:33:39 <Dulnes> my phone just got murdered with lag because its connected ;-;
18:34:36 <fizzie> (And I was under the impression too that you don't have to stay connected to IRCCloud to stay on a channel.)
18:34:37 <boily> fizzie: yes, but I suspect a case of malignant asciiite.
18:36:08 <fizzie> For the record, "oonbotti" is pretty close to a Finnish equivalent of "iamabot" in English. (Or maybe "imabot" to match the colloquiality levels too.)
18:36:09 <int-e> so apparently their pricing page does not work without javascript; the prices are listed as "..." ...
18:38:49 <Dulnes> fizzie: i just had to turn my phone off for the time i didnt want to corrupt my folders
18:40:14 <Dulnes> i dont rlly have it set up to where it still stays connected even if i turn my.phone off
18:42:17 -!- nys has quit (Quit: quit).
18:42:29 <fizzie> And /tː/ is produced almost if not entirely equivalently to /t/ except a longer hold duration.
18:47:18 <fizzie> Heh, Google Translate's (Finnish) synthesis voice apparently has some sort of a fallback when it for some reason or another can't do the normal one. At least for me "hyvä puhesynteesiääni" is done with a relatively high-quality voice (okay, the prosody's pretty off) but "aika hyvä puhesynteesiääni" falls back to something eSpeak-style.
18:48:08 <Dulnes> Google translate is awful
18:49:55 <fizzie> To a human, presumably.
18:50:06 <fizzie> At least that'd be a fair statement.
18:50:43 <fizzie> There's been a couple papers with "superhuman" in the title in recent speech recognition conferences.
18:50:46 <J_Arcane> Humans are pretty awful at Finnish too. ;)
18:51:30 <fizzie> (They tend to restrict the scenario quite a lot to get actual superhuman results.)
18:51:31 <Dulnes> but what about the Finnish who speak it
18:51:50 <Bike> gets superhuman results at recognizing audio files consisting solely of the word "bupkis"
18:53:53 <fizzie> Not quite that bad. But I seem to recall some superhuman numbers for speech so noisy humans can't understand it either.
19:08:53 -!- hjulle has joined.
19:18:19 <boily> we are who we are, except Taneb who isn't elliott.
19:18:29 <Taneb> boily, I am however Taneb
19:22:08 <HackEgo> Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards with dodgy SHIFT KEys, and five genders. (See also: tanebventions)
19:22:17 <HackEgo> A.+6غM8f>6hJLnj0/yvr]Ϡ٫^ÿ \ xa
19:22:26 <Taneb> I am also Ngevd, and atriq
19:22:32 <HackEgo> Tanebventions include D-modules, Chu spaces, automatic squirrel feeders, the torus, Stephen Wolfram, Go, weetoflakes, and this sentence.
19:23:08 <HackEgo> This sentence was invented by Taneb. Taneb invented it.
19:25:34 <shachaf> Taneb: do you want to tell me about d-modules
19:25:43 <HackEgo> D-modules are just modules over the ring of differential operators. Taneb invented them.
19:26:33 <HackEgo> differential operator? ¯\(°_o)/¯
19:27:43 <HackEgo> A Chu space is just a matrix. Taneb invented them, then Chu stole his invention.
19:28:47 <HackEgo> Go is a common verbal game programming language invented by the Germanic Taneb tribes in the strategic territories of East Asia.
19:30:46 -!- serika has left.
19:31:06 <Dulnes> also should i use out of interest these symbols »»» to direct input and output
19:31:53 <shachaf> `` sed 's/rs,/rs, tanebventions,/; s/$/ Taneb invented them./' wisdom/tanebvention # does this go too far?
19:31:54 <HackEgo> Tanebventions include D-modules, Chu spaces, automatic squirrel feeders, tanebventions, the torus, Stephen Wolfram, Go, weetoflakes, and this sentence. Taneb invented them.
19:34:21 <FireFly> Goes too far? Did Taneb invent the concept of limits towards infinity?
19:34:24 <HackEgo> Stephen Wolfram is an esolanger with too much money and power. Taneb invented him.
19:37:11 <HackEgo> Topologically, a torus is just a torus. Taneb invented them.
19:37:48 <fizzie> `? automatic squirrel feeder
19:37:49 <HackEgo> Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them.
19:38:58 <Taneb> Gregor, originally
19:39:12 <Taneb> I did not invent HackEgo
19:39:39 <Dulnes> Taneb: you are quite silly
19:40:24 <fizzie> `run find wisdom -type f -print0 | xargs -0 grep -El '(is|are) just' | wc -l
19:40:29 <fizzie> So many things are just things.
19:40:37 <Gregor> In the category of other things.
19:41:06 <fizzie> `run find wisdom -type f -print0 | xargs -0 grep -El '(is|are) just.*category' | wc -l
19:41:37 <fizzie> `run find wisdom -type f -print0 | xargs -0 grep -El '(is|are) just.*category' | sed -e 's|wisdom/||'
19:41:38 <HackEgo> object \ partial order \ natural transformation \ endofunctor \ functor \ indexed monad \ automatic squirrel feeder \ arrow \ monad \ doodad \ comonad \ preorder
19:41:49 <HackEgo> Doodads are just duoids in the category of endofunctors.
19:41:51 <elliott> `run find wisdom -type f -print0 | xargs -0 grep -El '(is|are) just' | xargs rm
19:41:55 <HackEgo> rm: cannot remove `wisdom/monoidal': No such file or directory \ rm: cannot remove `category': No such file or directory \ rm: cannot remove `wisdom/chu': No such file or directory \ rm: cannot remove `space': No such file or directory \ rm: cannot remove `wisdom/partial': No such file or directory \ rm: cannot remove `order': No such file or direc
19:42:23 <elliott> `run find wisdom -type f -print0 | xargs -0 grep -El '(is|are) just' | xargs -I'{}' rm '{}'
19:43:31 <fizzie> For the record, that just reverted the last 7 things with spaces in their names.
19:45:41 <HackEgo> Justice is just behavior or treatment.
19:49:09 <shachaf> There are several of those that can quite reasonably be deleted.
19:49:40 <HackEgo> wc: wisdom: Is a directory \ 0 wisdom
19:49:46 <J_Arcane> Woot. Finally added a useful numeric range generator to Heresy.
19:52:29 <HackEgo> wisdom/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d/d \ wisdom/d/da
19:54:40 <Dulnes> gonna go play some vidya ghames
19:56:06 <elliott> fizzie: I wonder why IE 8 / WinXP ends up using TLS_RSA_WITH_3DES_EDE_CBC_SHA for esolangs.org. not that XP matters, but... can't it even do TLS_RSA_WITH_AES_128_CBC_SHA?
20:03:55 <HackEgo> #!/bin/sh \ CMD=`echo "$1" | cut -d' ' -f1` \ ARG=`echo "$1" | cut -d' ' -f2-` \ exec ibin/$CMD "$ARG"
20:04:40 <HackEgo> 1l \ 2l \ adjust \ asm \ axo \ bch \ befunge \ befunge98 \ bf \ bf16 \ bf32 \ bf8 \ bf_txtgen \ boolfuck \ c \ cintercal \ clcintercal \ cxx \ dimensifuck \ forth \ glass \ glypho \ haskell \ help \ java \ k \ kipple \ lambda \ lazyk \ linguine \ malbolge \ pbrain \ perl \ qbf \ rail \ rhotor \ sadol \ sceql \ sh \ trigger \ udage01 \ underload \ u
20:05:12 <HackEgo> ls: cannot access ibin | tail -n 40: No such file or directory
20:05:18 <HackEgo> axo \ bch \ befunge \ befunge98 \ bf \ bf16 \ bf32 \ bf8 \ bf_txtgen \ boolfuck \ c \ cintercal \ clcintercal \ cxx \ dimensifuck \ forth \ glass \ glypho \ haskell \ help \ java \ k \ kipple \ lambda \ lazyk \ linguine \ malbolge \ pbrain \ perl \ qbf \ rail \ rhotor \ sadol \ sceql \ sh \ trigger \ udage01 \ underload \ unlambda \ whirl
20:05:41 <HackEgo> The ! or interp command calls various language interpreters transfered from old EgoBot. Try `url ibin/ for a list.
20:06:30 -!- Patashu has joined.
20:06:57 <Dulnes> so what does the bin thing do and where does hackego get the recource from
20:07:46 <HackEgo> Runs arbitrary code in GNU/Linux. Type "`<command>", or "`run <command>" for full shell commands. "`fetch <URL>" downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert <rev>" can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
20:08:03 <Sgeo> http://tvtropes.org/pmwiki/pmwiki.php/VideoGame/BillNyeTheScienceGuyStopTheRock
20:11:23 <zzo38> Do you not like All The Tropes instead?
20:12:26 <b_jonas> that's what I thought, thanks
20:14:17 -!- nys has joined.
20:16:15 -!- shikhout has joined.
20:16:38 -!- shikhout has changed nick to Guest17485.
20:19:03 -!- shikhin has quit (Ping timeout: 255 seconds).
20:19:57 -!- NATT_SiM has quit (Remote host closed the connection).
20:20:30 <b_jonas> Dulnes: roman numerals go up to 3999 inclusive
20:20:52 <zzo38> Unless you put bars on top, the Romans only go up to 3999.
20:21:16 <zzo38> Does such program include fractions? There is fractions too in Roman numbers.
20:21:29 <zzo38> One half is "S" and one twelvth is a dot
20:21:32 <b_jonas> no, this program definitely doesn't include fractions,
20:21:54 <vanila> i commented on your phlog
20:21:56 <b_jonas> but feel free to replace it with a better program (with hopefully better handling of unexpected input)
20:25:01 <zzo38> vanila: Was that on the 13th?
20:25:21 -!- Patashu has quit (Ping timeout: 272 seconds).
20:25:46 <zzo38> It says (947b/1com) the "1com" part means "1 comment"
20:26:12 <zzo38> That submenu lists the comments and the "send comment" menu, if you reload that menu then you can see a comment.
20:26:23 <zzo38> That's how you see it.
20:28:17 <vanila> zzo38, I like your gopher site
20:28:26 <vanila> its cool I wabt to set up one too
20:28:35 <vanila> i thought about converting esolang wiki to gopher
20:28:45 <vanila> but id have to handle a very large XML file so i iddnt do it
20:29:52 -!- NATT_SiM has joined.
20:40:15 <zzo38> The XML could also be converted into a SQLite database; do you know about SQLite?
20:42:09 -!- kcm1700 has quit (Ping timeout: 265 seconds).
20:45:01 -!- kcm1700 has joined.
20:45:13 <FireFly> Does a gopher client have to request the directory above a thing to know what type to treat the thing as?
20:45:54 <zzo38> The type is part of the URL. (If it doesn't use URLs, there will be some other variable to keep track of the type.)
20:47:13 <zzo38> For example the URL gopher://zzo38computer.org/0sqlarge.doc indicates the type is "0".
20:48:11 <Dulnes> (hh)++["^§"].g[ss.h]+++-[ " ok " ." irc.web_host " ]+++( " * " )-[ "»»»" ] = <.irc.app_module> [ "«««" ] this should give me an output of 0 but its giving an output of 2 ;-; what am i to do
20:48:39 <FireFly> When I request gopher://zzo38computer.org I see 'images' with type 1 (i.e. dir) and 'fortune' with type 0 (text). Wouldn't those be requested as 'images' and 'fortune'?
20:49:27 <zzo38> FireFly: Yes, they would be requested as such.
20:49:45 <FireFly> So how would I know which has which type, without a request to ''?
20:50:31 <zzo38> FireFly: You need to provide a way for the user to specify what type to use for the initial request. If no request is specified at all, the request is an enpty string and uses type 1.
20:51:03 <FireFly> Ah, so the type needs to be stored "externally" somehow, so to speak
20:51:03 <zzo38> If URLs are used, the character after the slash that comes after the host/port is the type.
20:52:07 <zzo38> (A gopher client is not required to use URLs; you may use a different method. However, if it is part of a web browser, you should use URLs.)
20:52:14 -!- nys has quit (Quit: quit).
20:54:42 <Dulnes> oh nvm it was the second output bracket
20:55:44 <FireFly> I looked a bit at the RFC and interacted with zzo38computer.org using netcat
20:57:39 -!- Guest17485 has quit (Ping timeout: 272 seconds).
20:57:55 -!- shikhin has joined.
20:58:01 -!- NATT_SiM has quit (Remote host closed the connection).
20:58:10 <zzo38> Also, gopher servers aren't guaranteed to even use a hierarchical directory structure, so you might not even know what is the above directory. All that is known is each file/program has a selector string for accessing it.
20:58:53 <zzo38> If the selector string contains "x/../y" then that is the string that should be sent exactly as is; it is up to the server to interpret it if necessary.
20:59:03 <Sgeo> Jafet: thank you. Now I just need to understand what you did, like where that 4 came from
20:59:42 <vanila> sqlite is nicer tow ork with I think
21:01:30 <zzo38> vanila: And in case you need additional functions, I have written an extension that provides many additional functions (and a few collations and virtual table modules too)
21:04:23 <Dulnes> slowly eats noodles and watches conversation
21:05:19 <zzo38> (For example, if you want to calculate statistics, trigonometry, and other stuff)
21:12:29 -!- NATT_SiM has joined.
21:15:29 -!- idris-bot has quit (Quit: Terminated).
21:16:14 -!- Melvar has quit (Quit: rebooting).
21:16:39 -!- Vorpal_ has joined.
21:18:00 -!- Vorpal has quit (Ping timeout: 255 seconds).
21:19:12 -!- Melvar has joined.
21:20:42 -!- AndoDaan has quit (Ping timeout: 255 seconds).
21:21:46 -!- Bicyclidine has joined.
21:26:44 -!- AndoDaan has joined.
21:45:36 -!- NATT_SiM has quit (Remote host closed the connection).
21:48:26 -!- MDream has joined.
21:51:37 -!- MDude has quit (Ping timeout: 240 seconds).
21:51:49 -!- MDude has joined.
21:51:52 -!- NATT_SiM has joined.
21:53:10 -!- MDream has quit (Ping timeout: 258 seconds).
21:54:12 -!- MDream has joined.
21:58:04 -!- MDude has quit (Ping timeout: 250 seconds).
22:01:58 -!- AnotherTest has quit (Ping timeout: 250 seconds).
22:06:28 -!- Phantom_Hoover has joined.
22:18:00 -!- oerjan has joined.
22:21:54 -!- bb010g has joined.
22:27:34 -!- MDream has changed nick to MDude.
22:32:45 <zzo38> How to reduce a truecolor picture to a palette of a specified number of colors?
22:33:20 <Bicyclidine> sounds like something you'd have several ways to do, like shrinking an image
22:35:59 <zzo38> I believe that, but still I don't know what way is a best way if the palette is pretty small. I could also implement more than one way.
22:37:12 <zzo38> I mean both ways; it can use a supplied palette, if not then it should try to make up a palette.
22:39:05 <zzo38> Probably the simplest way is just to check how many unique colors it is, and if it is too much it will display an error message.
22:47:35 -!- bb010g has quit.
22:48:15 <Phantom_Hoover> <zzo38> I believe that, but still I don't know what way is a best way if the palette is pretty small. I could also implement more than one way.
22:48:30 <Phantom_Hoover> i mean your question hinges on how you actually define 'best'
22:49:06 <Phantom_Hoover> you'll get different algorithms depending on what you're trying to preserve through the palette reduction
22:51:00 <boily> one defining factor when doing a simple k-means could be the colour space where your pixels lie in.
22:51:10 <zzo38> I have a program that claims to be written by Magnetic Scrolls, which implements three algorithms to select the best color to convert into, if already given the palette; they are (if R,G,B are this pixel and r,g,b in the palette): [0] abs(R-r)+abs(G-g)+abs(B-b) [1] R*abs(R-r)+G*abs(G-g)+B*abs(B-b) [2] R*(R-r)*(R-r)+G*(G-g)*(G-g)+B*(B-b)*(B-b); and then whichever index this value is the lowest "distance".
22:51:12 <Gregor> zzo38: Floyd-Steinberg dithering. I find that with a VERY small palette though it looks better if you reduce to about double the number of colors with no dithering (i.e., just choose the closest color), then reduce again with dithering. Maybe that's my own preference though. Anyway, that's not "best", just "what Gregor apparently likes"
22:52:03 <zzo38> Gregor: How does Floyd-Steinberg work?
22:52:13 <boily> zzo38: matrix convolution :D
22:52:14 -!- Vorpal_ has changed nick to Vorpal.
22:53:06 -!- NATT_SiM has quit (Remote host closed the connection).
22:53:07 <ion> Add the quantization error of a pixel onto the neighboring pixels on the bottom right diagonal of a window.
23:06:39 <fizzie> I did some sort of octree thing when I was last generating a palette.
23:07:33 -!- TodPunk has quit (Read error: Connection reset by peer).
23:08:00 -!- TodPunk has joined.
23:11:31 <fizzie> Also I seem to have here references to a 1994 paper by Anthony H. Dekker titled "Kohonen neural networks for optimal colour quantization", in Network: Computation in Neural Systems, vol. 5, no. 3, pp. 351-367.
23:14:10 <fizzie> And there's a link to http://www.cubic.org/docs/octree.htm here.
23:14:52 -!- bb010g has joined.
23:15:26 <fizzie> The NeuQuant link on that page seems to have died, but was related to that paper.
23:15:44 <fizzie> And can still be found at http://members.ozemail.com.au/~dekker/NEUQUANT.HTML
23:18:11 <fizzie> Full disclosure disclaimer: Kohonen maps are from our university, I used to have an office maybe three doors left from that of prof. Kohonen, so I might not quite be an unbiased estimator of quality here.
23:19:44 <Bicyclidine> sigh, yet anothe rprogram ruined by the kohonen lobby
23:22:36 <fizzie> I think the median cut algorithm it mentions is kind of the "de-facto standard" for color quantization, if you don't want to go all SOM.
23:24:13 <fizzie> Gah, this is the ugliest C. I think I wrote this.
23:30:28 <fizzie> If I'm reading it right, it does three palette optimization methods (the popularity one, the octree one and the median cut one), some sort of weirdly optimized palette conversion (based on that [0] distance and a palette sorted by G) and Floyd-Steinberg dithering.
23:36:20 -!- S1 has joined.
23:36:30 -!- S1 has changed nick to |S}.
23:39:18 -!- myndzi has joined.
23:40:56 -!- MoALTz__ has joined.
23:41:37 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
23:59:07 -!- boily has quit (Quit: EMERGENCY CHICKEN).
00:02:42 -!- MoALTz__ has quit (Ping timeout: 245 seconds).
00:16:25 -!- idris-bot has joined.
00:16:31 -!- Bicyclidine has quit (Ping timeout: 272 seconds).
00:18:36 -!- |S} has changed nick to S1.
00:35:40 -!- copumpkin has joined.
00:40:08 -!- NATT_SiM has joined.
00:49:29 -!- S1 has quit (Quit: S1).
00:50:43 -!- zzo38 has quit (Ping timeout: 272 seconds).
00:51:03 -!- zzo38 has joined.
00:51:22 -!- contrapumpkin has joined.
00:54:12 -!- copumpkin has quit (Ping timeout: 240 seconds).
00:55:48 -!- contrapumpkin has changed nick to copumpkin.
01:00:43 -!- AndoDaan has quit (Read error: Connection reset by peer).
01:01:09 <zzo38> I made up a file on my computer with some new pokemon cards I have made up now.
01:06:55 <zzo38> HEAVY GRAVITY STADIUM = All resistance to { # } is ignored.
01:07:11 <zzo38> SUPER IMPOSTER PROFESSOR OAK = Discard an energy card attached to one of your pokemons in order to cause opponent to shuffle his hand into his draw pile and draw ten cards.
01:07:31 <zzo38> COMPACT GARBAGE = Select you or opponent; all cards in his trash will get lost.
01:12:09 -!- vanila has quit (Quit: Leaving).
01:30:37 <fizzie> http://sprunge.us/iRcT wonder what exactly it generated there
01:30:59 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
01:41:17 <Sgeo> Rustaceans seem very good at bikeshedding the word 'unsafe'
01:42:55 <Sgeo> https://www.reddit.com/r/rust/comments/2ly7q8/two_hours_after_rust/clzmbpc
01:43:02 <Sgeo> Not the first time a similar conversation has occurred
01:44:16 -!- copumpkin has quit (Ping timeout: 250 seconds).
01:45:19 <Taneb> I was actually about to try and do some Rust again
01:46:12 <Sgeo> I'm half considering just waiting for 1.0 before doing anything
01:46:22 <Sgeo> But I do have a use case... kind of...
01:46:38 <Sgeo> Want to do some loops regarding 32 bit floats
01:47:00 <Sgeo> Figure that performance probably helps. Probably not -that- significantly though
01:47:33 <Sgeo> Also wrapping C libraries... maybe. For that though it might be better to wait for unboxed closures to land, the library in question is callback intensive
01:47:48 <Sgeo> Would be nice if Rust had a real REPL
01:48:14 <Sgeo> Also there's already a C# wrapper for that library so why am I bothering
01:48:31 -!- copumpkin has joined.
01:49:35 <coppro> Sgeo: what does "unsafe" do?
01:50:22 <Sgeo> unsafe blocks allow using 'unsafe' functions, and a few other things that the Rust compiler cannot verify is safe in particular ways. unsafe functions can also do those things but can only be used from unsafe blocks.
01:50:50 <Sgeo> (incl. dereferencing raw pointers and bypassing the type system ala unsafeCoerce)
01:51:01 <Sgeo> Well, the latter is a specific unsafe function
01:52:31 <int-e> oerjan: Is the domino thing your golf problem? the last one is quite hard...
01:54:03 <oerjan> although i have played the puzzle
01:54:20 <oerjan> (you could say it's in my tatham puzzle rotation)
01:57:55 <Dulnes> what was the first thing you ever did in code
01:58:46 <oerjan> the first thing i remember is writing complex arithmetic in BASIC. without a computer.
01:59:30 <oerjan> (my dad had a textbook, but no computer at home to go with it. this was approximately 1981 or so.)
02:00:08 <int-e> oerjan: (I had to verify that the solutions are unique. They are. So there's a slight chance that one can outperform the data compression approach by an honest search.)
02:00:08 <fizzie> Re earlier paste, heh; what it does is it completely omits the function epilogue from main: http://sprunge.us/Jcib
02:00:12 -!- ^v has joined.
02:00:45 <oerjan> int-e: i was thinking of a search yeah
02:01:03 <oerjan> although you're probably right that it's hard to beat compression.
02:01:40 <fizzie> Leapfrogging has had relatively little attention.
02:02:15 <oerjan> it has? i thought all the haskellers except me were improving it constantly.
02:02:27 <oerjan> (i have no idea how they're doing it :P)
02:02:28 <fizzie> Well, I mean, language-wise.
02:02:37 <fizzie> Only 8 languages in there.
02:02:42 -!- shikhin has quit (Ping timeout: 240 seconds).
02:02:58 <int-e> ah, well the dc folks cannot compete, for example
02:03:17 <fizzie> I was thinking of doing it in dc, actually.
02:03:27 <int-e> how are you hoping to do the parsing?
02:03:44 <int-e> sorry, I was looking at the output, not thinking
02:04:05 <fizzie> It would end up pretty long, I think.
02:04:16 -!- contrapumpkin has joined.
02:04:16 <fizzie> And probably not very interesting.
02:04:46 <Dulnes> What was the most complex thing you've ever created in code
02:04:50 <int-e> I won't try, I've had a hard enough time with Wow
02:05:18 <fizzie> I'm pretty surprised at how short the dc Wow is.
02:05:55 <int-e> (And I'm a bit afraid that tails is just missing an easy trick for saving two characters.)
02:07:23 <Dulnes> sonic boom is probably the worst game ive ever seen
02:07:26 -!- copumpkin has quit (Ping timeout: 265 seconds).
02:08:44 <Dulnes> collision detection doesnt activate for 6.23 seconds and when it does it makes the most ungodly noise
02:09:29 -!- copumpkin has joined.
02:09:53 -!- contrapumpkin has quit (Ping timeout: 272 seconds).
02:14:07 <oerjan> int-e: that last dominosa problem was no problem for my usual methods. but then the real puzzles are larger.
02:18:02 <oerjan> the initial stage of the method is mostly "search for dominoes that only exist in one place", though, so may take a while if unlucky.
02:18:25 <oerjan> (if that really fails, _then_ i have to get clever, but it didn't for this one.)
02:19:49 <oerjan> oh and also "exist in two places but those share part of their border", that got me the first hit here.
02:20:07 <int-e> ok, I have no practice at all...
02:20:39 <oerjan> i think i played dominosa several time before i had the epiphany of how to do it more efficiently.
02:21:51 <oerjan> and also once you've found something, it's important to mark what else that excludes.
02:22:24 <oerjan> tatham's puzzle allows you to insert marks where you know there is a border.
02:22:27 <int-e> yeah, I got that. I missed that the 11 are right next to a corner.
02:23:35 <int-e> so I started with 21 22 in opposite corners
02:24:07 <oerjan> and after that i found 1-4 by brute searching, and that started closing off options.
02:24:28 <int-e> I had to backtrack twice, I think.
02:24:37 <int-e> (well, branch twice)
02:24:46 <oerjan> ah and that wouldn't have worked unless you found the 0-4 corner first, i guess.
02:25:57 <oerjan> that 21 22 thing would have been important if nothing simpler had worked, i guess.
02:26:49 <oerjan> it would have allowed finding the 2-4 next
02:27:15 <int-e> I'm no longer trying to follow btw
02:28:42 <oerjan> well i mean, since you had 21 22 in opposite corners, that means 21 and 22 are both spoken for there. and it so happens that that excludes a couple of 1-2's elsewhere, giving you enough of the border of the 2-4 to place it.
02:28:49 <MDude> Who is it here that has a gopher page?
02:29:38 -!- adu has joined.
02:31:42 <oerjan> one thing i've found is that it's best to start searching for the double ones first: 00 11 etc.
02:33:15 -!- contrapumpkin has joined.
02:33:51 <oerjan> because if you find 00, it gives a better chance of finding unique things involving 0's later.
02:36:26 -!- copumpkin has quit (Ping timeout: 265 seconds).
02:36:31 -!- contrapumpkin has changed nick to copumpkin.
02:40:46 <Dulnes> what is the percentage of tripping over a rope and exploding into flame
02:41:42 <oerjan> depends whether the rope is next to a lava pit.
02:42:31 <oerjan> pretty close to 0, i assume.
02:43:28 <Dulnes> all my code is very messy
02:43:36 <Dulnes> but it gets its job done
02:43:38 <Taneb> I don't often see ropes in my day to day life
02:43:41 <oerjan> i think that is a very high estimate.
02:43:54 <Taneb> And I have never to my knowledge exploded into flame
02:44:00 <Dulnes> 0.0000000000000000003.33%
02:44:11 <oerjan> Taneb: not you either? and here i thought i was the only one!
02:44:22 <Taneb> oerjan, we should start a support group
02:44:26 <oerjan> Dulnes: more plausible.
02:45:18 <oerjan> in fact i'd be willing to think it's higher than that. world population and all.
02:45:39 <Taneb> There aren't that many ropes lying about
02:45:51 <Taneb> Maybe if you lived in a port city or something
02:45:58 <oerjan> you still need some way to spontaneously combust without a fire to ignite you.
02:46:05 -!- adu has quit (Quit: adu).
02:48:00 <oerjan> Taneb: i am thinking some kind of cordon.
02:49:25 <Dulnes> if you were to be accelerated in someway
02:49:38 <Dulnes> bypassing your terninal velocity
02:49:58 <Dulnes> and just ignite your blood
02:50:23 <oerjan> i doubt blood is the first thing to ignite in your body.
02:50:58 <Dulnes> if you hadnt any clothing?
02:52:42 <Dulnes> well you know how your blood vaporises when you are electricity
02:53:21 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
02:53:26 <Dulnes> mmm a rope near an electrical plant
02:55:58 <oerjan> "If SHC is a real phenomenon (and not the result of an elderly or infirm person being too close to a flame source), why doesn’t it happen more often? There are 5 billion (editor's note: as of 2011) people in the world, and yet we don’t see reports of people bursting into flame while walking down the street, attending football games, or sipping a coffee at a local Starbucks."
02:56:06 -!- AndoDaan has joined.
02:57:12 <Dulnes> mmm yes but this rope scenario is in of course theory oerjan
02:57:22 <oerjan> Dulnes: [citation needed] on that blood vaporising
02:58:56 <Bike> i'm glad i'm a biologist, so i can say things like what the fuck are you even talking about
02:59:38 <Bike> plenty of weird random things happen to bodies, like heart attacks! be satisfied with these deaths, you monsters
02:59:38 <Dulnes> well i was having very imaginative brain farts yesterday
02:59:51 <oerjan> Bike: are you a mad biologist who can do the necessary experiments to get to the bottom of this twh
03:00:05 <Dulnes> like what would liquid entropy taste like
03:00:49 * oerjan is reminded of delirium from sandman
03:01:00 <FireFly> but would they sleep furiously?
03:01:03 <Dulnes> oh my friends name us deliriun
03:01:06 <Bike> this experiment doesn't even seem very mad. bleed a cow for a while, then get a bunsen burner. easy. i could probably even get iacuc approval, except it's probably been done already
03:01:12 <AndoDaan> wouldn't 'tasting like something' be doing work?
03:01:40 <Dulnes> imaginative brain farts
03:02:00 <Bike> stringing words together isn't that imaginative, yo
03:02:48 <oerjan> AndoDaan: only if irreversible hth
03:02:54 <Dulnes> unless you go indetail
03:03:52 <AndoDaan> And maybe it's my tongue doing the work.
03:03:55 <Dulnes> like what happens if you touch photons that are super condensed to the point where the laws of the universe are like fuck it why not have liquidized light
03:04:47 -!- hjulle has quit (Ping timeout: 245 seconds).
03:05:51 <oerjan> if you condense light enough you get a "normal" black hole afaiu
03:05:56 <AndoDaan> that can bump into other light and make matter, if dense enough
03:05:59 <oerjan> you need a lot, though.
03:07:44 -!- copumpkin has joined.
03:08:06 <oerjan> https://en.wikipedia.org/wiki/Kugelblitz_(astrophysics)
03:10:14 -!- copumpkin has quit (Read error: Connection reset by peer).
03:11:19 <AndoDaan> could one collapse the space around a blackhole?
03:12:09 <Dulnes> is in a skype with friends
03:12:19 <AndoDaan> like if i had a wee little black hole in my room, and i managed to direct light (a lot of light) around it, could could i create an outher shell black hole?
03:12:24 <Dulnes> please help me discuss this with them
03:13:49 -!- copumpkin has joined.
03:13:51 <Dulnes> apparently no you cant according to my friend
03:16:14 <Dulnes> did you guys hear about the hard light thing
03:17:01 <Dulnes> ok so they condensed the light or something
03:17:08 <oerjan> if it's recently, well i haven't been keeping up with r/physics
03:17:25 <Dulnes> but it wasnt really solid
03:17:44 <oerjan> hm it vaguely rings a bell, this was probably inside some material
03:17:49 <Dulnes> it was just alot of light moving around a set point
03:18:03 -!- contrapumpkin has joined.
03:21:22 -!- copumpkin has quit (Ping timeout: 256 seconds).
03:40:55 <zzo38> Now I have 34 chapters, 58 sessions, and 57 footnotes.
03:45:05 <MDude> How does anything go in a black hole if it can't get out?
03:45:34 <MDude> Can antimatter get out of a black hole, if it bahaves like regular matter going in reverse time?
03:45:57 <oerjan> MDude: no. because gravitation is symmetric under time reversal.
03:46:34 <AndoDaan> But black holes can evaportat with a little trick.
03:46:45 <MDude> That only answers the second question, unless you're saying things can't go in lack holes.
03:47:19 <oerjan> what you could have in theory is a _white_ hole, from which things can _only_ get out. but we don't know of a way to produce them, and haven't found any.
03:47:41 <MDude> I imagine they would empty fairly quickly.
03:48:06 <Dulnes> it would never go in if it has reverse time properties
03:48:09 <Bike> how are white holes even supposed to work?
03:48:10 <oerjan> well they would essentially be black holes time reversed
03:48:17 <Bike> learning physics has really ruined my sci-fi abilities.
03:49:07 <Dulnes> because if the antimatter goes in
03:49:07 <MDude> I guess it doesn't tend to happen due to being very un-entropic.
03:49:28 <Dulnes> it goes back out because of reverse time
03:49:43 <oerjan> Bike: well they are a mathematical solution, but probably thermodynamics doesn't allow them to be formed in the first place.
03:50:03 <oerjan> you'd essentially have to drop hawking radiation into a spot...
03:50:05 <Dulnes> but since nothing can escape it
03:50:19 <Dulnes> then antimatter would never enter
03:50:50 <Dulnes> and not forward which goes infinite
03:51:01 <Taneb> Most actual science scares me
03:51:09 <oerjan> MDude: i assume if a white hole existed, it wouldn't _always_ be spewing out matter, in the same way a _black_ hole isn't _always_ swallowing something.
03:51:19 <Taneb> I like to stay firmly in the region of things that are definitely true and hence useless
03:51:33 <Bike> physics only makes sense locally. here, let me tell you about all the dude ants dudeing about on this apple
03:52:33 <Dulnes> if there are white holes
03:52:36 <Taneb> > (.) flip const join (+) () 12
03:52:58 <Dulnes> it woukd have to swallow stuff to spew it out
03:53:20 <Dulnes> or the second way its just reverse gravitational force
03:53:32 <Taneb> > (<*>) pure (+) 12
03:53:34 <Bike> the Kinda Mediocre Nuclear Force
03:53:37 <Dulnes> that would leave large holes in the universe
03:53:41 <AndoDaan> if it had stuff within region before it was form it would have fuel to spue out.
03:53:53 <Bike> as you can see, i'm an efficient programmer.
03:54:07 <Dulnes> the begining of the universe was a white hole in theory
03:54:17 <Dulnes> and it pushed it outwards at highspeed
03:54:25 -!- ZombieAlive has quit (Remote host closed the connection).
03:54:57 <AndoDaan> Dark energy... what's that all about, aye.
03:55:04 <oerjan> Dulnes: really you are not thinking precisely enough for this, but one hint: if you play a ball thrown through the air backwards, it still looks like a ball thrown through the air. reversing time does not change what gravitation does.
03:55:17 <oerjan> *play a video of a ball
03:55:30 <Dulnes> sorry i wasnt thinking
03:55:44 <MDude> Dark energy is for super villains to charge purple crystals.
03:56:00 <Dulnes> didnt this start with liquid light creating black holes
03:56:07 <Taneb> MDude, I'm a beginner supervillain, where can I found out more about these purple crystals?
03:57:53 <Bike> i'll sell you purple crystals for $1000/pound, dawg.
03:58:01 <MDude> A minute of using a search engine got me nothing.
03:58:23 <MDude> Half Life Wiki has uses of dark energy by a villain, though.
03:58:56 <MDude> They use it for bouncy balls that tend to explode.
03:59:04 <Taneb> Bike, I'm a low-budget beginning supervillain
03:59:15 <Bike> half life wiki is my favorite anime
03:59:24 <Bike> Taneb: i also offer loans with quite reasonable deferral times
03:59:53 -!- not^v has joined.
04:00:07 <MDude> my favorite anime.gif is a set of ink blots I made out of random data from random.org
04:00:42 * oerjan used to collect purple stones when he was tiny
04:01:02 -!- contrapumpkin has changed nick to copumpkin.
04:02:16 <Taneb> oerjan, I'm imagining a tiny adult hauling purple rocks as big as himself around
04:02:19 -!- ^v has quit (Ping timeout: 258 seconds).
04:02:37 <oerjan> Taneb: don't listen to Bike btw, his deferral times involve time dilation
04:02:49 <oerjan> and possibly travelling into black holes
04:03:28 <coppro> ooh I have a great idea
04:03:34 <coppro> we should add a black hole to dbefunge
04:03:40 <Bike> I don't have to sit here and just take what is hypothetically slander, oerjan.
04:03:46 <oerjan> Taneb: also, not very accurate imagination
04:04:01 <lambdabot> <hint>:1:1: parse error on input ‘<’
04:04:14 <Dulnes> a black hole in a data sequence
04:04:17 <coppro> I mean it exerts gravity on the IP
04:04:29 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
04:04:34 <oerjan> > let x = x in x -- haskell black hole
04:04:35 <Bike> several things that aren't black holes exert gravitational force, such as your mother
04:04:43 <coppro> and executing the black hole randomly transports the IP to some random point in the time and space of the fungespace
04:06:10 <Bike> http://esolangs.org/wiki/Gravity i'm not sure if EFE are uncomputable in the same way, hrm
04:08:24 <Dulnes> Bike: omg that mom joke
04:11:31 <Bike> it was uninspired.
04:22:19 -!- oerjan has set topic: The black hole of programming madness | BF Joust scoring poll: http://goo.gl/02KE0Y | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
04:23:03 -!- oerjan has set topic: The black hole of programming madness, or was it the other way around | BF Joust scoring poll: http://goo.gl/02KE0Y | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
04:35:14 -!- adu has joined.
04:36:37 -!- AndoDaan has quit (Ping timeout: 240 seconds).
04:48:23 <Dulnes> guys i just made a thing that reads webbrowser cookies on a phone through the IP address and lets me find out peoples accounts still working on the thing that auto connects to said servers port
04:48:39 <Dulnes> im so proud of myself :0
04:49:33 <Dulnes> until i have to type un manually the name of the port
04:49:49 <Dulnes> until i get a auto snooper
04:50:06 <Dulnes> im doin things manually
04:50:33 <Sgeo> I assume snooper means something other than -chat client that connects to WormNET-
04:51:31 -!- NATT_SiM has quit (Remote host closed the connection).
04:51:34 <Dulnes> kinda like a password sniffer
04:51:56 <Dulnes> which im purposely leaving out of g
04:56:48 <Dulnes> its actually very short
05:05:33 <Taneb> I should go to bed at some point
05:06:56 <Bike> isn't it five am
05:08:22 <Taneb> I'm in a more sensible time zone
05:08:24 <Bike> and do you sleep? no. exactly
05:08:32 <shachaf> sounds like our time zones are seven minutes apart
05:08:56 <shachaf> oh, now they're eight minutes apart
05:09:13 <Taneb> Yeah, I'm in UTC+7minutes
05:09:19 <Dulnes> do u live in Washington
05:09:44 <Taneb> I used to live 30 miles from a Washington
05:11:36 <Taneb> Not that Washington
05:12:41 <Taneb> Not that Washington
05:13:24 <quintopia> do we really need the scoring poll still?
05:13:28 <Taneb> Washington, Tyne and Wear
05:13:28 -!- ^v has joined.
05:13:38 -!- not^v has quit (Ping timeout: 258 seconds).
05:13:40 <quintopia> i mean, fizzie just went ahead and implemented all of them :P
05:14:47 -!- ^v has quit (Client Quit).
05:15:53 -!- quintopia has set topic: The black hole of programming madness, or was it the other way around | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:17:39 <oerjan> it stands to reason that that washington guy had to get his name from somewhere other than the places that were named for him.
05:18:32 <Bike> maybe he was just descended from a washing machine.
05:28:26 <Dulnes> its probably the most intrusive app ive come acrosd
05:29:05 <Dulnes> so much.power over the ppl on my contact list
05:34:00 -!- oerjan has quit (Quit: Et cetera).
05:45:12 -!- copumpkin has joined.
05:50:30 <int-e> "skypr" sounds like a skype usr.
05:52:33 <Dulnes> http://animestuckneko.tumblr.com/image/102852169768 finally got around to mowing the lawn
05:58:41 -!- AndoDaan has joined.
06:01:36 <HackEgo> slist: Taneb atriq Ngevd Fiora Sgeo ThatOtherPerson alot
06:08:42 -!- MDude has changed nick to MDream.
06:18:53 <zzo38> I play this Dungeons&Dragons game, and if I find any beholders in this town, then I have two things that I can use to help in such a case: [1] Box of anti-magic fields [2] Holy symbol of Gxxyuxihuvxi
06:25:53 <zzo38> One of the kind of monsters in the game
06:26:17 <zzo38> It is involving ten small eyes can cast various spells, one big eye to make anti-magic field
06:26:37 <zzo38> AndoDaan: Did you read this level20.tex texts?
06:27:25 <zzo38> Such thing will explain various stuff
06:28:41 <AndoDaan> I've only played DandD once years ago. One of the best gaming experience of my life
06:29:34 <zzo38> You can read it, then. And then learn how I am playing such Dungeons&Dragons game.
06:31:13 <zzo38> Read http://zzo38computer.org/dnd/recording/level20.tex there I typed a story by recording all of the Dungeons&Dragons game.
06:31:25 <AndoDaan> is level20.tex suppose to be a weblink?
06:31:50 <Dulnes> but first before i read
06:32:00 <Dulnes> what is Dungeon and dragons
06:32:02 <zzo38> AndoDaan: It is supposed to be a Plain TeX document.
06:32:28 <zzo38> If you want to compile it by yourself, you will also need a file dungeonsrecording.tex which is in the same directory.
06:33:16 <Dulnes> ignore that hit enter instead of Back space
06:33:29 -!- adu has quit (Quit: adu).
06:34:29 <zzo38> Anything with a percentage sign is a source comment; it won't render it or anything afterward. The command \note will become a footnote when rendered. Just to explain its working a bit.
06:36:52 <Dulnes> so what are you up to zzo38
06:38:27 <zzo38> Now I work on a program to convert Z-machine picture formats.
06:51:51 <zzo38> Do you know Pokemon Card playing?
06:54:14 <Dulnes> but before that i have to tell u something
06:54:33 <zzo38> OK, what do you like to tell me?
06:54:37 <Dulnes> Betty white is older than sliced bread
06:54:56 <zzo38> I do not understand.
06:55:40 <Dulnes> betty white was born in 1922 sliced bread was invented in 1928
06:55:58 <zzo38> O, OK. I don't know who is Betty White, but OK
06:56:42 <Dulnes> anyways, As you were saying?
06:56:58 <zzo38> I made up many puzzles involving Pokemon Card, as well as some new cards, and a few other things
06:58:00 <zzo38> It can be found in directory http://zzo38computer.org/textfile/miscellaneous/pokemon_card/ where puzzle.1 up to puzzle.5 are puzzle games, terminology.txt explains some terminology, newcards.txt is new cards I have made up (the ($1) and so on don't have a name yet), 59eye1mewtwo.txt is a document about the "59 eye + 1 Mewtwo" deck.
06:58:33 <zzo38> Did you make up any new pokemon cards too?
06:59:44 <Dulnes> ill get on that tommorow
07:01:18 <zzo38> I have invented a deck which is much more terrible than a "59 eye + 1 Mewtwo" deck, but nevertheless is 100% guaranteed to beat a "59 eye + 1 Mewtwo" deck.
07:01:35 <Dulnes> This is very well made
07:02:21 <Dulnes> Ill save this to my todo module
07:03:45 <zzo38> What is your opinion of some of these new card, puzzles, etc? Can you figure out any of them, or is it difficult?
07:04:59 <zzo38> Maybe some of the names isn't very good I don't quite know
07:05:41 <Dulnes> mmm I dont know what to.make of proffesor black
07:10:31 <AndoDaan> Back. Don't think I've ever compiled Tex before. Another learning oppertunity.
07:12:23 <zzo38> AndoDaan: Simply run the program "tex" on your computer; at the "**" prompt you type in the filename. Most implementations also allow specifying the filename as a command-line parameter.
07:13:26 <zzo38> The result will be a "dvi" file. (You can also download a precompiled DVI; it is called level20.dvi and is in the same directory.) DVI is a device-independent format for printing; it can be previewed directly, or converted into other formats such as PCL, PDF, PNG, DjVu, or whatever format your printer uses.
07:13:30 <AndoDaan> I think I first have to install an implementation.
07:13:56 <zzo38> Yes, you would need to. Even to use the DVI, you need fonts; a TeX installation will include the necessary fonts.
07:14:10 <zzo38> Yes, MiKTeX will do and is what I have.
07:15:35 <zzo38> The previewer in MiKTeX is called "yap", so you can use that to open the DVI.
07:16:22 <AndoDaan> Okay. (dl and installing usually takes a while for this old laptop)
07:17:00 <AndoDaan> Does your D&D group play in person or online?
07:18:28 <AndoDaan> Must be a good group, seems like a big campaigne to take on.
07:20:46 <AndoDaan> Why aren't slaves ever named Thomas... or Bob. It's always something like "Kjugobe"
07:21:39 <zzo38> Well, Kjugobe is my character, and the name is made up by random
07:22:04 <zzo38> Slaves probably can be named Thomas or Bob, but there is nobody of these names in this story (yet).
07:23:38 <zzo38> My brother's character is named Also (this causes grammatical confusion sometimes).
07:23:55 <zzo38> I have a page about it in All The Tropes wiki.
07:26:38 <AndoDaan> Oh, sorry. "Also" just reminded me of Annyong means hello running gag in Arrested Development.
07:32:21 -!- Patashu has joined.
07:35:36 -!- Patashu has quit (Remote host closed the connection).
07:36:06 -!- Patashu has joined.
07:36:52 -!- AndoDaan has quit (Ping timeout: 245 seconds).
07:40:18 <zzo38> http://allthetropes.orain.org/wiki/User:Zzo38/level20.tex
08:17:16 <Jafet> > floor (250 / (40 * (25 % 18))) `const` "Sgeo"
08:18:01 <Sgeo> I should sleep
08:18:30 <Bike> > "a" `const` "b"
08:24:04 <mroman> fizzie: K. I'll fix it.
08:25:19 <int-e> > "a" `const` "b" `const` "c"
08:26:12 <mroman> @tell AndoDaan s<digit> is "set var" and g<digit> is "get var"
08:26:25 <int-e> > "a" `const` ("b" `const` "c") == ("a" `const` "b") `const` "c"
08:27:00 <mroman> @tell AndoDaan also {g1} doesn't work because Blocks aren't evaluated UNTIL you call eval. You can use |[g1]| though. |[ and ]| are like { } except stuff in between is evaled.
08:27:37 <int-e> Const is associative. It lacks a left unit to make monoid.
08:28:16 <int-e> hmm, I should s/Const/const/
08:28:23 <Jafet> It is a monoid on ()!
08:28:25 <mroman> !blsq 9s0|[g0g0?*|["hi"]|]|
08:28:34 <int-e> Because Now It Looks Like A Data Or Type Constructor.
08:28:58 <int-e> Jafet: But only if you take a relaxed view about bottoms.
08:29:38 <int-e> `seq` is a proper monoid on ().
08:30:18 -!- HackEgo has quit (Ping timeout: 250 seconds).
08:36:31 <elliott> int-e: well, if you believe Reader is a monad...
08:44:19 -!- MoALTz has joined.
09:16:28 -!- Phantom_Hoover has joined.
09:19:20 <elliott> http://www.newyorker.com/magazine/2014/11/24/programmers-price *cries*
09:22:43 <elliott> "Scopely, a mobile-game publishing company, rewards a new hire—or anyone who can deliver one—with eleven thousand dollars wrapped in bacon, an oil portrait of himself, and a harpoon gun." we're doomed
09:39:23 -!- weissschloss has quit (Max SendQ exceeded).
09:41:42 -!- weissschloss has joined.
09:42:06 -!- b_jonas has quit (Ping timeout: 272 seconds).
10:02:27 -!- mihow has quit (Read error: Connection reset by peer).
10:03:30 <fizzie> "The mainly products of the factory are optical quartz glass, opaque quartz blanks,quartz substrate, quartz apparatus, quartz crystal singing bowls, quartz tuning forks, quartz rod, twin born quartz tube, quartz lamp, quartz heating elements, quartz tube and so on."
10:03:34 <fizzie> They're all about the quartz.
10:04:01 <mroman> Since this is the day of targeted advertisement I conclude you like quartz.
10:04:10 <Jafet> It looks like everything I knew about the quartz reproductive cycle has been wrong
10:04:21 -!- mihow has joined.
10:04:39 <fizzie> Technically, it was sent to the TI-86 robotfindskitten role address.
10:04:53 <fizzie> Don't know how they've associated that with quartz exactly.
10:07:29 <mroman> Through a new machine-learning algorithm.
10:15:06 -!- b_jonas has joined.
10:15:54 -!- FreeFull has quit (Quit: BBL).
10:29:27 <mroman> fizzie: Nice @Leapfrogging
10:34:54 <mroman> I kinda whish Java had destructors
10:36:24 <mroman> (not that silly finalize thing)
10:38:52 <fizzie> Perhaps you could emulate them with 'finally' blocks generated by processing your source with m4 and suitable macros, in what would be the pinnacle of elegance.
10:40:21 -!- weissschloss has quit (Max SendQ exceeded).
10:40:48 <fizzie> They do have the try-with thing these days, isn't that kind of.
10:42:39 -!- weissschloss has joined.
10:44:12 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
10:51:15 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:52:16 <mroman> elliott: try-with statements
10:52:38 <mroman> try(conn = jdbc.getConnection();) { //blabla } catch(Exception e) { //blabla }
10:52:51 <mroman> which will close connection afterwards
10:53:17 <mroman> fizzie: it's kinda that.
10:53:33 <mroman> although I'd prefer something like...hm...
10:53:33 <fizzie> It works when the type in question implements java.lang.AutoCloseable.
10:53:45 <mroman> autoclose Connection conn = jdbc.getConnection();
10:53:58 <b_jonas> elliott: maybe you want python-like with blocks?
10:54:01 <mroman> where autoclose instructs the compiler to call close on connection when the method returns or throws
10:54:05 <elliott> so it's like Python's with
10:54:20 <elliott> b_jonas: I don't wan tanything, I was just asking what the try-with fizzie mentioned was :)
10:54:38 <fizzie> elliott: There's no "enter" method, just the "exit" (close), but quite like.
10:55:28 <elliott> what's the use of the enter method anyway?
10:56:40 <b_jonas> elliott: a possible use is that a mutex could have an enter method that locks that mutex, so the enter method can have different semantics than just creating that object
10:57:10 <b_jonas> the mutex object and the lock object aren't the same
10:57:49 <b_jonas> python also has proper c++-like destructors with reference counting too, but this is more explicit
10:58:44 <b_jonas> and more compatible with a possible non-refcounting implementation
10:58:51 <fizzie> In the Java-7+ land, you could write explicitly try(Lock uselessNameHere = new Lock(mutex)) { ... } in which case the constructor of the Lock would be the enter method, though.
10:59:25 <fizzie> Or perhaps mutex.lock().
10:59:31 <b_jonas> fizzie: sure, that's the C++ way
10:59:41 <b_jonas> creating a separate lock object
10:59:54 <b_jonas> like { std::unique_lock mylock(somemutex); ... }
11:00:21 <elliott> b_jonas: there's a perversity about how Python deals with the disadvantages of reference counting, but refuses to exploit its advantages because hey what about Jython
11:01:30 <b_jonas> elliott: I don't think that's really the reason. it's just that they insist on extra-readable code, which is why they provide "with" because it's easier to see a "with" than to see which objects have a semantically significant destructor
11:01:57 <elliott> so are they going to use "with" to allocate memory too? :p
11:07:10 <b_jonas> elliott: memory can be garbage-collected, which doesn't count as observable behaviour
11:07:17 <b_jonas> the garbage-collection can be delayed
11:07:35 <elliott> b_jonas: sure but you can view closing files the samew ay
11:07:38 <b_jonas> whereas closing a file or unlocking a mutex can be an observable and important side effect that you have to do immediately
11:07:50 <elliott> it's just a question of what level you view things at
11:07:53 <b_jonas> sure, sometimes closing files can be delayed, and sometimes even freeing a mutex can be delayed
11:07:59 <elliott> certainly not freeing memory can hold up resources
11:08:06 <elliott> just like not closing a file
11:08:21 <b_jonas> yeah, I guess if you allocate so much memory that you _need_ it to be freed at a particular point in the code, you could with(mmap(...)) or something
11:08:33 <elliott> or just put a strategically-placed "del"
11:09:04 <elliott> point is, it can have effects anywhere between worse performance and your code not working; same for files. mutexes are much easier to argue as an application logic thing, admittedly
11:09:19 <elliott> in the end it's just a sliding scale where we make the trade-off of manual but precise vs. automatic but imperfect resource management
11:26:42 -!- boily has joined.
12:00:13 -!- Patashu has quit (Ping timeout: 240 seconds).
12:26:14 -!- boily has quit (Quit: ICONIC CHICKEN).
12:42:51 <blsqbot> | ERROR: Unknown command: (r0)!
12:42:58 <blsqbot> | "I have 358 non-special builtins!"
12:43:16 <mroman> 1.7.4dev as of now has 380
13:04:59 -!- HackEgo has joined.
13:11:18 -!- MoALTz has quit (Quit: Leaving).
13:24:26 <Taneb> Last night, before I went to bed, I had an idea, so I wrote it down on a piece of paper so I wouldn't forget it
13:24:53 <Taneb> "Data.Group.Homomorphism?" was what I wrote
13:25:00 <Taneb> And I left it on the living room table
13:25:12 <Taneb> One of my housemates has written "No." underneath
13:25:35 <mroman> I would have added "and a glas of milk please"
13:27:19 <Taneb> I drank so many glasses of milk last night...
13:29:09 <mroman> That sounds like an odd thing to brag about but ok...
13:29:53 <mroman> I actually rarely drink milk
13:30:13 <Taneb> It's less bragging, closer to regret
13:30:25 <Taneb> I drink too much milk :(
13:31:18 <Taneb> Went to bed after 5 AM
13:31:20 <mroman> I think at certain times I lay hours in bed thinking I'm sleeping and dreaming but I'm actually awake
13:31:28 <HackEgo> [wiki] [[Talk:Malbolge]] http://esolangs.org/w/index.php?diff=41020&oldid=39476 * TomPN * (+192)
13:31:50 <Taneb> I also had a weird dream...
13:31:59 <Taneb> It had Muse and George R. R. Martin in it
13:34:30 <Taneb> But waking up at 20 past 1 is great when you have lectures at half 10 and half 11
13:39:31 <mroman> you went to bed at 5 AM o_O
13:40:08 <elliott> please, Taneb has nothing on my sleep
13:41:18 <mroman> "The programming hole of black madness"?
13:41:26 <mroman> "The black programming of hole madness"?
13:55:14 -!- Phantom_Hoover has joined.
13:57:18 -!- oerjan has joined.
14:03:55 <int-e> The black hole mattress of sound sleep.
14:10:17 <mroman> `learn_append mroman He also likes black madness.
14:10:20 <HackEgo> Learned 'mroman': mroman is a leading artist in password security (SFW) He also likes black madness.
14:11:49 <oerjan> `run sed -i 's/ He/. He/' wisdom/mroman
14:13:15 <HackEgo> mroman is a leading artist in password security (SFW). He also likes black madness.
14:16:24 -!- drdanmaku has joined.
14:22:23 <mroman> Today I recommended just doubling the password instead of using salts.
14:22:49 <mroman> i.e. h'(p) = h(p+p) instead of h'(p) = h(salt+p)
14:23:05 <mroman> It doubles your password security.
14:24:19 <mroman> Because the attacker doesn't know the salt this way!
14:24:32 <mroman> storing the salt in plaintext is giving it to the attacker for free
14:24:47 <elliott> this is some weak trolling :p
14:25:04 <mroman> elliott: But the idea is somewhat decent.
14:25:35 <mroman> non-disclosed salts make it harder to crack the password.
14:26:07 <elliott> I think I've had enough password security discussions with you for a lifetime :p
14:26:29 <mroman> My more advanced password system uses h'(p) = h(h(p)+p) of course.
14:26:53 <mroman> p+p isn't very strong for two character passwords .
14:27:44 <elliott> here's my favourite passwod system hash(p) = md1(md2(md3(md4(md5(p)))))
14:27:58 <elliott> as you can see it's 1*2*3*4*5 = 120 times more secure than just MD5
14:28:15 <elliott> I also put the result in a jpeg
14:28:17 <mroman> Shouldn't it be as secure as the least secure hash mechanism?
14:28:24 <elliott> no, it's 120 times as secure.
14:29:23 <elliott> for instance you wouldn't expect good_password_function(MD5(p)) to be as weak as MD5, because good_password_function(p) isn't as weak as the identity function
14:29:24 <mroman> No, but I'd be actually interested to know the weaknesses of h'(p) = h(h(p)+p)
14:29:36 -!- nicole has joined.
14:29:56 <HackEgo> nicole: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
14:30:30 <oerjan> `learn_append mroman He can design password hashes that are worse than the identity function.
14:30:32 <HackEgo> Learned 'mroman': mroman is a leading artist in password security (SFW). He also likes black madness. He can design password hashes that are worse than the identity function.
14:30:50 <oerjan> i think this about sums up this discussion.
14:31:12 <mroman> You can always add more stuff!
14:31:20 <mroman> deducing the number of rounds from the password.
14:31:31 <mroman> h'(p) = h(h(p)+p, rounds=f(p))
14:32:02 <elliott> here's my updated password hash: hash2(p) = sha1(sha2(sha3(...sha512(p)...))). as you can see it is at least 512 factorial times stronger than my previous one
14:32:58 <mroman> The solution is btw that h(h(p)+p) doesn't help if two people have the same password
14:33:04 <mroman> so it's a stupid thing to do.
14:33:08 <oerjan> elliott: i sense that hash{n} may be an ackermannlike function.
14:33:43 <elliott> I'm sure we're giving nicole a fantastic impression of this channel's quality
14:34:11 <blsqbot> | {144 89 55 34 21 13 8 5 3 2 1 1}
14:34:13 <oerjan> well for this time of day, the usual channel activity would be *chirp*
14:34:16 <mroman> there. Better impression.
14:34:27 <elliott> oerjan: just wait for hashomega(p) = hash(hash2(hash3(...p...)))
14:35:27 <nicole> I mean you can only hash so many things ...
14:35:50 <mroman> and h(p)+h(p) is obviously better than h(p) because h(p)+h(p) must contain more bits.
14:36:38 <elliott> thankfully thanks to quantum computing we can stack an infinite number of hash functions
14:36:47 <elliott> okay, I should stop. I'm almost as bad as mroman
14:37:03 <nicole> yea I mean if you take the output of one hash and put that directly into another one you are taking a cross-section of the posibilites because fixed langth input on the second one
14:37:44 <mroman> Luckily nobody knows I'm designig a hash function called Burlesque .
14:38:17 <elliott> nicole: in H1(H2(p)), if H2's output is larger than H1's then you can cover all possible outputs of H1... you're not necessarily guaranteed to though, I forget what this property of H1 is called
14:38:32 <elliott> well, larger or even the same
14:38:49 -!- NATT_SiM has joined.
14:40:24 <elliott> hi though, did you come here from the wiki? (in before you've already had the welcoming committee treatment and I look like a fool...)
14:40:53 <oerjan> it's ok boily isn't around to ask about body weigh
14:40:59 <nicole> I guess if you are using hash functions that are significantly different from eachother then it would be worth the extra stuff
14:41:32 <nicole> elliott: nah I just thought it would be fun in here and stuff.
14:41:53 <elliott> nicole: you're going to be so disappointed...
14:42:24 <nicole> elliott: well I have not been let down yet...
14:43:51 <elliott> I'll make sure to keep making up nonsense hash functions, then
14:44:43 <oerjan> well nicole hasn't left yet despite our best attempts at making a hash of it.
14:48:50 <elliott> I think we've scrambled nicole quite enough already
14:49:09 <blsqbot> | ERROR: Burlesque: (!!) Invalid arguments!
14:49:09 <blsqbot> | ERROR: Unknown command: (s@)!
14:49:28 <mroman> that's my hash function I guess!
14:50:39 <blsqbot> | "1011111001001011010110111"
14:50:55 <mroman> not sure how to reverse that
14:51:04 <mroman> nicole: it's r@, not s@
14:51:13 <blsqbot> | {"abcd" "bacd" "cbad" "bcad" "cabd" "acbd" "dcba" "cdba" "cbda" "dbca" "bdca" "bcda" "dabc" "adbc" "abdc" "dbac" "bdac" "badc" "dacb" "adcb" "acdb" "dcab" "cdab" "cadb"}
14:51:50 <blsqbot> | {"" "a" "b" "ab" "c" "ac" "bc" "abc"}
14:52:34 -!- ais523 has joined.
14:53:55 <ais523> is that some sort of hash function?
14:54:38 <blsqbot> | ERROR: Burlesque: (**) Invalid arguments!
14:55:10 <elliott> I still can't understand a line of burlesque
14:55:33 <ais523> elliott: think of it as a normal stack language where all the commands have been replaced by arbitrary two-character sequences
14:55:34 <oerjan> there, now you understand one line
14:55:46 <elliott> nicole: the language the bot use
14:56:01 <mroman> ais523: that's actually a pretty good summary, yes.
14:57:13 <nicole> I know I am reading its github source right now and I cant make head or tails of this maybe ctags will help me tomorow
14:57:59 <mroman> There are two tutorials
14:58:16 <mroman> http://mroman.ch/burlesque/tutorial.html <- this one
14:58:28 <mroman> http://fmnssun.github.io/Burlesque/ <- and that one
14:59:54 <mroman> ais523: it's got variables and functions now though
15:00:17 <mroman> !blsq %foo={)++} {{1 2}{3 4}} %foo!
15:00:50 <J_Arcane> I really should make a proper esolang again sometime, I always seem to wuss out and make something almost useful instead.
15:01:09 <mroman> I usually wuss out of making something useful and make something useless instead
15:02:24 <ais523> J_Arcane: if the language is both esoteric /and/ useful, so much the better
15:02:43 -!- S1 has joined.
15:02:44 <ais523> although My Unreliable Past is basically only useful for philosophical reasons, and/or implementing it on systems limited in a very weird way
15:02:57 <J_Arcane> VIOLET I guess is 'lesser evil
15:03:43 <J_Arcane> Though I do kinda dig the pseudohistoric languages more than just out-right crypticism.
15:07:04 <mroman> Did you take the Certified Burlesque Programmer (CBP) Test?
15:07:06 <ais523> juts got spam with the subject "my subject"
15:07:08 <nicole> !blsq "asdfqwer" "sgdfgfhj" IN
15:07:23 <ais523> I suspect someone was filling out an automated spambot configuration thing from a tutorial and took it a little too literally
15:07:52 <fizzie> (For no particular reason.)
15:09:40 <mroman> elliott: To become a CBP you must solve http://golf.shinh.org/p.rb?number+lines+reverse in 11B in Burlesque
15:10:14 <elliott> can I just solve it in haskell and J and then smudge the two solutions together?
15:10:18 <elliott> pretty sure that's how burlesque works
15:12:36 <mroman> elliott: but you have to reverse it
15:12:46 <mroman> since J is right->left and blsq is left->right
15:12:50 -!- kline has changed nick to im1ach.
15:13:37 <mroman> Can't compete with that. Only have prefixes.
15:14:10 <blsqbot> | ERROR: (line 1, column 4):
15:14:18 <mroman> that's actually a command prefix
15:14:37 <elliott> I mean, J is a f b, not f a b
15:17:51 <mroman> I'm sure you can write a Burlesque parser with infix .
15:17:57 -!- shikhin has joined.
15:18:43 <blsqbot> | ERROR: Burlesque: (z[) Invalid arguments!
15:19:08 <blsqbot> | ERROR: Burlesque: (z[) Invalid arguments!
15:19:25 <mroman> that's not how zip works
15:19:29 <mroman> !blsq "mroman" "nicole" z0
15:19:29 <blsqbot> | ERROR: Unknown command: (z0)!
15:19:31 <mroman> !blsq "mroman" "nicole" z[
15:19:31 <blsqbot> | {{'m 'n} {'r 'i} {'o 'c} {'m 'o} {'a 'l} {'n 'e}}
15:19:39 <mroman> !blsq "mroman" "nicole"**
15:19:57 <nicole> didnt think that it did tha
15:21:00 <nicole> !blsq "mroman" "nicole" z[ u[
15:21:43 <nicole> some complex statitics stuff in here like variance
15:22:24 <mroman> and some distributions
15:22:28 <mroman> and a chi squared test
15:24:17 <nicole> that was a dissapointing output for coolmap
15:24:35 <mroman> !blsq "hi"{{zz}{ZZ}{<-}}M-
15:25:20 <mroman> !blsq "hi"{qzzqZZq<-}}M-
15:25:53 <mroman> !blsq "hi"{qzzqZZq<-}M-
15:26:58 <blsqbot> | ERROR: You should not transpose what you can't transpose. Yes this is an easteregg!
15:27:41 <nicole> !blsq {{h' i'}{b' g'}} tp
15:27:44 <lambdabot> Couldn't match type ‘GHC.Types.Char’ with ‘[a]’
15:27:46 <mroman> !blsq {{1 2}{3 4}}tpBS
15:27:51 <mroman> !blsq {{1 2}{3 4}}tpSP
15:27:54 <mroman> !blsq {{1 2}{3 4}}tpsp
15:28:05 <blsqbot> | ERROR: Burlesque: (SP) Invalid arguments!
15:28:05 <blsqbot> | ERROR: Unknown command: (tb)!
15:28:09 <elliott> burlesque is useless for cooking
15:29:26 <nicole> !blsq {{h' i'}{b' ee}} cp
15:29:26 <blsqbot> | ERROR: Burlesque: (cp) Invalid arguments!
15:29:34 <elliott> come on, that was funny :(
15:29:51 <mroman> !blsq {'h 'i}{'b ee}cp
15:29:52 <blsqbot> | {{'h 'b} {'h ee} {'i 'b} {'i ee}}
15:30:05 <mroman> !blsq {'h 'i}{'b ee}cpsp
15:30:31 <mroman> (sp is used to pretty print 2d arrays)
15:30:37 <nicole> !blsq {{3.4 5}{4 ee}} cp
15:30:37 <blsqbot> | ERROR: Burlesque: (cp) Invalid arguments!
15:30:49 <mroman> nicole: cp wants two lists
15:30:54 <mroman> but you give it a list containing two lists
15:31:07 <nicole> !blsq {3.4 5}{4 ee} cpsp
15:32:13 <nicole> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1} cp
15:32:14 <blsqbot> | ERROR: (line 1, column 34):
15:32:14 <blsqbot> | expecting "%", "g", "s", "S", "m{", "q", "{", "\"", "-", digit, "'", "(", "y" or "}"
15:32:25 <nicole> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}} cpsp
15:32:47 <nicole> I was kinda wanting the crossproduct
15:33:16 <mroman> that is the crossproduct
15:33:27 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}} )cpsp
15:33:27 <blsqbot> | [Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", "7 8", "\n", Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", "pi 6.1"]
15:33:47 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}} {p^cp}m[sp
15:33:47 <blsqbot> | [Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", Sh, "\n", 7, "\n", Sh, "\n", 8, "\n", Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", Sh, "\n", pi, "\n", Sh, "\n", 6.1]
15:33:58 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}}cp)cpsp
15:33:59 <blsqbot> | [Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", "[3.4, 5] [7, 8]", "\n", Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", "[3.4, 5] [pi, 6.1]", "\n", Sh, "\n", ERROR: Burlesque: (cp) Invalid arguments!, "\n", "[9, ee] [7, 8]", "\n", S
15:34:01 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}}cp)cp
15:34:01 <blsqbot> | {ERROR: Burlesque: (cp) Invalid arguments! {{3.4 5} {7 8}} ERROR: Burlesque: (cp) Invalid arguments! {{3.4 5} {pi 6.1}} ERROR: Burlesque: (cp) Invalid arguments! {{9 ee} {7 8}} ERROR: Burlesque: (cp) Invalid arguments! {{9 ee} {pi 6.1}}}
15:34:03 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}}cp
15:34:04 <blsqbot> | {{{3.4 5} {7 8}} {{3.4 5} {pi 6.1}} {{9 ee} {7 8}} {{9 ee} {pi 6.1}}}
15:34:11 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}}cp{p^cp}m[
15:34:11 <blsqbot> | {{{7 3.4} {7 5} {8 3.4} {8 5}} {{pi 3.4} {pi 5} {6.1 3.4} {6.1 5}} {{7 9} {7 ee} {8 9} {8 ee}} {{pi 9} {pi ee} {6.1 9} {6.1 ee}}}
15:34:13 <mroman> !blsq {{3.4 5}{9 ee}} {{7 8}{pi 6.1}}cp{p^cp}m[sp
15:34:14 <blsqbot> | [7, 3.4] [7, 5] [8, 3.4] [8, 5]
15:34:14 <blsqbot> | [pi, 3.4] [pi, 5] [6.1, 3.4] [6.1, 5]
15:34:14 <blsqbot> | [7, 9] [7, ee] [8, 9] [8, ee]
15:35:13 <mroman> also ee and pi aren't parse level constants
15:35:31 <mroman> but that's a new feature of 1.7.4
15:35:38 <mroman> so it's not documented yet.
15:36:38 <nicole> !blsq {3 -3 1} {-12 12 -4} cpsp
15:36:57 <nicole> nope that is suppoed to equal 0
15:37:01 <nicole> !blsq {3 -3 1} {-12 12 -4} cp
15:37:02 <blsqbot> | {{3 -12} {3 12} {3 -4} {-3 -12} {-3 12} {-3 -4} {1 -12} {1 12} {1 -4}}
15:37:26 -!- im1ach has changed nick to kline.
15:45:44 -!- ais523 has quit (Ping timeout: 265 seconds).
15:46:11 <nicole> I mean I am doing the math right in front of me... (-3x(-4))-(1x12) = 0
15:49:12 -!- vanila has joined.
15:51:26 -!- nicole has left ("Leaving").
15:53:50 <Dulnes> One of my cores overheated and broke sooo I need a new one, Any ideas?
15:55:40 <Dulnes> On where to buy one the ones i had were already came with the computer So ive just been using those. Ive looked for some but.all are 1/3 the size in how much space it has
15:56:59 <elliott> do you mean one of your CPUs
15:57:41 <Dulnes> so effectively i have no computer
15:58:14 <Dulnes> ill just buy a new one nvm
15:58:28 <elliott> ...can't you just use the remaining CPUs?
15:59:09 <Dulnes> nope :T they are broken also
15:59:40 <Dulnes> i really only need two CPUs
16:07:18 -!- hjulle has joined.
16:13:26 -!- MDream has changed nick to MDude.
16:22:05 <Dulnes> mmm anyways thats.just my Dr
16:24:26 -!- NATT_SiM has quit (Remote host closed the connection).
16:28:55 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ?toroman: not found
16:29:26 <Dulnes> i forgot the cmd again well whatever
16:36:19 * oerjan kills a tab for the heresy of making unrequested sound
16:47:20 -!- Sprocklem has joined.
16:47:44 <int-e> oerjan: first adblock, then close
16:48:03 <oerjan> *first install adblock
16:48:17 <oerjan> it doesn't happen often enough to make me bother?
16:49:05 <Dulnes> regular adblock gets paid to not block ads
16:50:39 <int-e> yes, but an adblock author cooperating with ad providers, well it just smells fishy
16:51:03 <elliott> I remember there being fishier things about adblock edge
16:51:27 <elliott> but I use µBlock because it's the only one that doesn't use a trillion gigabytes of RAM injecting tons of CSS into every single page
16:52:38 <FireFly> I don't mind non-intrusive ads
16:52:54 <vanila> non intrusive ads don't exist!
16:53:51 <quintopia> "i hope you happen to click up here!"
16:54:04 <FireFly> Like, say, small webcomics making use of project wonderful to advertise other small webcomics
16:55:09 <int-e> I wish we had a viable business model for the web that is not based on surveillance.
16:55:36 <int-e> I don't mind the non-flashy ads, but I do mind the tracking.
16:56:03 <int-e> (much to my dismay, animated gifs still haven't quite died out.)
16:56:22 -!- ais523 has joined.
16:56:42 <int-e> I do wonder though, whether tracking has already moved on to the next obvious step: just buy webserver logs. Or take them for free (google analytics...)
16:57:17 -!- FreeFull has joined.
16:57:19 <Dulnes> and the phisher ads are a annoying
16:57:36 <FireFly> Sure, that doesn't count as non-intrusive :P
16:57:55 -!- `^_^v has joined.
16:58:16 <elliott> int-e: have you seen panopticlick?
16:58:45 <Jafet> Just get the ISP to do tracking for you (Verizon)
17:00:35 -!- oerjan has quit (Quit: AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADS).
17:00:41 <int-e> "Currently, we estimate that your browser has a fingerprint that conveys at least 22.17 bits of identifying information." ... removing de_DE from the accepted languages, "Within our dataset of several million visitors, only one in 213,892 browsers have the same fingerprint as yours."
17:01:04 <int-e> I do have javascript disabled, otherwise this would be much much worse.
17:01:09 <elliott> then you stick out like a sore thumb but nobody can tell which sore thumb you are
17:01:18 <elliott> disabling javascript can actually help panopticlick :/
17:01:26 <Jafet> I'm pretty easy to track since I use elliott's useragent string
17:01:35 <elliott> IIRC tor browser without javascript gets more bits than tor browser with javascript
17:02:12 <int-e> elliott: That's not a good reason for enabling javascript.
17:02:34 <elliott> it's not, no. but it does mean it's not an unqualified win for pure tracking
17:03:33 -!- ais523 has quit (Ping timeout: 265 seconds).
17:05:13 <int-e> You can play other fun games. For example, Panopticlick currently has about 4.51 million samples.
17:06:27 -!- Sprocklem has quit (Ping timeout: 265 seconds).
17:09:29 <fizzie> "Your browser fingerprint appears to be unique among the 4,705,644 tested so far."
17:09:34 <fizzie> Yay, I'm a special snowflake.
17:09:50 <fizzie> (This was with scripts on.)
17:09:57 <elliott> q: how many bits does the exact "N bits"/"one in X" figure leak?
17:10:10 <elliott> wait, I guess that's kind of obvious
17:10:50 <fizzie> Heh, I had a unique HTTP_ACCEPT.
17:11:24 <mroman> I think nicole confuses cross product with the other kind of cross product
17:11:37 <int-e> elliott: the nice thing is that if you visit the page twice, the number gets smaller. so some simple linear algebra lets you estimate the number of total samples
17:11:44 <fizzie> (Thanks to manually putting 'el' there because I wanted β.zem.fi to show up in Chromium properly.)
17:12:18 -!- adu has joined.
17:12:52 <elliott> int-e: that sounds harder than just setting some header to something ridiculous to get a unique result like fizzie
17:13:11 <int-e> elliott: then it doesn't display a number
17:13:22 <elliott> 17:09:08 <fizzie> "Your browser fingerprint appears to be unique among the 4,705,644 tested so far."
17:13:22 <fizzie> Doesn't it say the "among the N tested so far" message for non-unique results?
17:13:22 <int-e> so you still have to reload, and then multiply by 2
17:13:39 <elliott> it is less mathematically elegant I admit
17:13:44 <int-e> I thought I tested that ... it has been a while though, admittedly.
17:15:28 <int-e> fizzie: no, it says "one in <N> visitors have the same fingerprint as you"
17:15:36 <int-e> (modulo precise wording)
17:15:56 <int-e> and "among our millions of samples"
17:17:22 <fizzie> I guess the exact count is just a prize for being unique, then.
17:20:20 <fizzie> Or if you're still doing a no-scripts version, at least for me the content (including the "among the N tested" message) comes directly from https://panopticlick.eff.org/index.php?action=ajax_log_clientvars over AJAX.
17:20:36 -!- NATT_SiM has joined.
17:22:33 <fizzie> No, you're right; you need to be unique to get the exact number. That's funny.
17:22:46 -!- ais523 has joined.
17:27:13 <newsham> http://www.i-programmer.info/news/105-artificial-intelligence/7985-a-worms-mind-in-a-lego-body.html
17:27:19 <mroman> only one in 34,601 browsers have the same fingerprint as yours.
17:28:02 <mroman> that's with JS disabled though
17:28:43 <mroman> my browser plugin details are unique
17:32:15 <J_Arcane> http://danluu.com/empirical-pl/
17:37:59 -!- NATT_SiM has quit (Remote host closed the connection).
17:39:37 -!- NATT_SiM has joined.
17:41:58 * Melvar appears to have a unique HTTP_ACCEPT header.
17:49:23 -!- MoALTz has joined.
17:54:59 -!- NATT_SiM_ has joined.
17:55:04 -!- NATT_SiM has quit (Read error: Connection reset by peer).
17:56:33 -!- S1 has quit (Quit: S1).
17:56:58 <Taneb> Without quite realizing, I made GHC compute 10!, in unary, at compile time
17:57:22 <tromp_> how many days is 10! seconds?
17:57:47 <ais523> Taneb: has it finished yet?
17:57:49 <Taneb> > product [1..10] `div` (24*60*60)
17:57:53 <Taneb> ais523, I killed it
17:58:06 <ais523> 10 factorial's only a few million, IIRC
17:58:15 <ais523> the "unary" probably causes problems, though
17:58:51 <tromp_> a friend of mine just won the IOCCC with that computation
17:59:04 <ais523> oh, are the results out already?
17:59:14 <tromp_> only winners, no source yet
17:59:21 <ais523> I have a theory that the number of submissions is actually reasonably small
17:59:42 <Bike> > product [1, 7, 2, 3] `div` (1)
18:00:34 <J_Arcane> Dammit, I'm supposed to be doing homework but now I want to write a for w/carry version of !.
18:01:21 <ais523> where ! means factorial?
18:01:32 <ais523> for some reason, the first association that came into my head was Prolog's cut
18:01:44 <Taneb> Right, ran it with a sufficiently small value of 10 (ie., 7), and it doesn't compile
18:01:51 <Taneb> Context reduction stack overflow
18:02:29 <Taneb> http://lpaste.net/114452
18:05:12 <Bike> gonna need a compiler that rewrites product[...]/product[...] based on factorization
18:05:36 <Bike> actually let's say general rational functions
18:05:37 <Taneb> Just realised that only had 7 as a sufficiently small value of 10 if 6 is a sufficiently small value of 7
18:06:18 <Bike> hey taneb maybe you should implement a more efficient multiplication algorithm and that would fix it
18:06:35 <Bike> i'm thinking schönhage
18:06:52 <Bike> or fürer but taht seems overcomplicated
18:07:23 <Taneb> Bike, it's doing it in unary
18:07:34 <Taneb> Any binary multiplication'd be much much faster
18:07:42 <Bike> exactly. i think you need fourier transforms
18:08:47 <ais523> fourier-based multiplication doesn't work in unary
18:08:57 <ais523> needs a hyperpositive base to work
18:09:00 <ais523> (i.e. more positive than 1)
18:10:14 <b_jonas> this conversation is surreal
18:11:15 <ais523> b_jonas: half the reason I even stay here is to have surreal conversations
18:14:32 <Bike> data N; data O n; data Z n; type family x + y; type instance N + n = n; type instance Z m + Z n = Z (m + n); type instance Z m + O n = O (m + n); type instance O m + O n = Z (m + (n + O N))
18:14:42 <Bike> i'm sure this is totally reasonable and also that i know the haskells.
18:15:27 <elliott> pretty sure that would work as-is
18:15:47 <Bike> fuck you if you want to add an odd number and an evne number in that order, though. you're what's wrong with america.
18:16:50 <Bike> the order is inside out from what i originally thought of, though. life is suffering tbh.
18:19:20 <Bike> type instance Z m * Z n = Z (Z (m * n)); type instance Z m * O n = (Z m + Z (Z (m * n))); type instance O m * O n = (O m + O n + Z (Z (m * n)) + O N)
18:20:01 <Bike> glad i can contribute to taneb doing completely reasonable things.
18:23:29 <Bike> oh and N * n = N i /guess/
18:24:17 <int-e> nice, binary arithmetic
18:25:05 <Bike> for my next trick, a carry lookahead adder
18:25:51 <Jafet> Circuit parallelism in the type system
18:26:04 -!- NATT_SiM_ has quit (Remote host closed the connection).
18:26:16 <Jafet> Never before seen in the civilised world, ladies and gentlemen
18:26:31 <J_Arcane> Hmmm. I think carry is doing crazy things ...
18:26:51 <ais523> Bike: now I'm trying to figure out if that violin-based adder is carry lookahead
18:27:00 <int-e> Bike: I'd try and optimize that a bit: type instance Z m * Z n = Z (Z (m * n)); type instance Z m * O n = Z (m + Z (m * n)); type instance O m * Z n = Z (n + Z (m * n)); type instance O m * O n = O (n + m + Z (m * n))
18:27:22 <Bike> even reasonabler.
18:28:34 <int-e> But I'll punt on the carry look-ahead.
18:28:40 -!- adu has quit (Quit: adu).
18:29:26 <ais523> We can define the sum in terms of the carry, and the carry in terms of itself:
18:29:28 <ais523> * `sum` = `x` bitwise-XOR `carry`
18:29:29 <ais523> * `carry` = (`a` bitwise-OR (`x` bitwise-AND `carry`)) leftshifted 1
18:29:32 <ais523> there's the basic algorithm
18:29:50 <ais523> (`x` and `a` are the bitwise-xor and bitwise-and of the numbers you're adding
18:30:26 <Bike> i'm not sure how you'd do bitwise operations on types.
18:30:30 <J_Arcane> Sigh. I am an idiot. Carry works fin, I was using my function variable instead of my loop variable to accumulate the value ...
18:30:49 -!- NATT_SiM has joined.
18:30:55 <Bike> i've got it. what if we just used some kind of sub-type programming. we could have "number" objects and "functions" operating on them. maybe we could evne make "numbers" a type
18:33:29 <Bike> "the HT80C51 processor (2007???) from Handshake Solutions" so the wikipedia article on async cpus is pretty shitty
18:34:11 <Bike> «During demonstrations, the researchers amazed viewers by loading a simple program which ran in a tight loop, pulsing one of the output lines after each instruction. This output line was connected to an oscilloscope. When a cup of hot coffee was placed on the chip, the pulse rate (the effective "clock rate") naturally slowed down to adapt to the worsening performance of the heated transistors. When liquid
18:34:17 <Bike> nitrogen was poured on the chip, the instruction rate shot up with no additional intervention. Additionally, at lower temperatures, the voltage supplied to the chip could be safely increased, which also improved the instruction rate—again, with no additional configuration.»
18:34:26 <Bike> this, however, seems totally useful and practical. maybe if those resistors are busy computing 10! in unary
18:35:01 <Jafet> I would be amazed to see 10! being computed by resistors
18:35:06 <ais523> Bike: ooh, async CPUs is pretty close to what I was doing on my thesis, before I discovered the underlying theory sucked
18:35:10 <J_Arcane> (fact n) in Heresy: https://twitter.com/J_Arcane/status/534414254510997504
18:35:20 <Bike> ais523: yeah i remember you mentioned that
18:35:23 <Bike> ais523: sucks how
18:35:51 <Bike> J_Arcane: well /now/ it looks eso, good job
18:36:19 <J_Arcane> I plan to add carry support to do loop as well. It's a filed issue.
18:37:13 <Bike> ais523: like, does it inherently suck, or is it just like wikipedia says and nobody's worked on it.
18:37:20 <ais523> you should see how many ridiculous recursive fibonaccis we've written in Verity
18:37:23 <ais523> the lastest one makes the compiler crash
18:40:23 <J_Arcane> Bike: Shit like that is why I called it Heresy. :D
18:40:48 <Bike> what can i say, anaphoric macros leave a bad taste in m mouth
18:40:51 <ais523> Bike: basically, the state is that there was a bunch of work done in Holland like 20 years ago that had some promising results
18:40:57 <ais523> but fell a little short of the result everyone ants
18:41:11 <ais523> and mentioned that that would be a sensible result to aim for
18:41:13 <ais523> then nothing else happened
18:41:28 <Bike> i'm just curious about async cpus since it seems a bit like biological clocks
18:42:16 <Bike> has there been any research on karman streets appearing in multicore async cpus? i'm sure this is a major research area
18:42:27 <J_Arcane> Bike: Also fun, underneath it's still technically entirely functional code. Heresy's for is a recursive list eater, even carry is just passing one of the optional arguments to the next recursion.
18:50:27 -!- S1 has joined.
18:57:22 <J_Arcane> Oh maaan. http://www.ebay.ca/itm/Rare-Vintage-Gimix-Ghost-6809-computer-OS-9-GMX-I-complete-original-box-extras-/231387896256?pt=US_Vintage_Computers_Mainframes&hash=item35dfcb19c0
18:57:49 <Taneb> Right, I've got it to use bnary addition
18:57:56 <Taneb> Which makes it so much faster
19:04:31 <Taneb> Now I've got a less naive implementation of multiplication too :)
19:06:35 <Taneb> http://lpaste.net/114454
19:11:37 -!- Sprocklem has joined.
19:12:10 -!- Sprocklem has changed nick to Guest76372.
19:24:35 -!- NATT_SiM has quit (Remote host closed the connection).
19:26:02 -!- NATT_SiM has joined.
19:27:26 <Dulnes> omfg my power went out
19:32:59 -!- callforjudgement has joined.
19:33:02 -!- ais523 has quit (Disconnected by services).
19:33:04 -!- callforjudgement has changed nick to ais523.
19:33:30 <Vorpal> ais523, did you ever do anything with my patches to build ick on classic Mac OS?
19:33:43 <Vorpal> I happened to find them the other day, and I was wondering whatever happened to that
19:33:47 <ais523> Vorpal: no, other than admire them
19:33:50 <ais523> I don't have a Mac Classic
19:33:56 <ais523> I can put them as a branch in the repository if you like?
19:34:19 <Vorpal> ais523, thanks I guess. But eh I don't have time to maintain them or such
19:34:40 <ais523> just as a "historical interest" thing, like the DOS port
19:34:49 <Vorpal> Still using darcs btw?
19:35:06 <Vorpal> ais523, also remember the mac Makefile *has* to be encoded as MacRoman not ASCII in order to work
19:35:28 <ais523> Vorpal: ESR ported like five different repos into git
19:35:49 <ais523> Vorpal: you should probably read this: http://nethack4.org/blog/save-optimization.html
19:35:53 <ais523> http://esr.ibiblio.org/?p=2491
19:36:07 <ais523> (you can read my post about optimizing save files in NH4 too if you like but it's not what I was trying to link you to)
19:36:23 <ais523> both because it describes the history of the repo, and because it offers an insight into what it's like trying to work with ESR
19:37:50 <Dulnes> guys is noscript something i should get
19:38:07 <Vorpal> ais523, oh okay, I already clicked before I saw your link. I was just going to write: "interesting, but what has this got to do with anything?"
19:38:44 <ais523> Dulnes: if you have a personality like me, it's really useful
19:38:48 <ais523> I don't know how much like me you are, though
19:38:58 <ais523> I see it as a way of generally removing annoyances, many of which people believe to be useful functionality
19:38:59 <elliott> Dulnes: don't you need to fix your broken CPUs first?
19:39:01 <Vorpal> ais523, "trying to work"?
19:39:45 <Dulnes> which ive been trying to do while i was gone
19:40:03 <elliott> did you clean them with soap
19:40:24 <Dulnes> im transplanting my desktops CPUs out
19:40:33 <ais523> elliott: is Dulnes Sgeo, or have you changed who you give humorous bad advice to?
19:41:09 <elliott> ais523: I'm happy to give bad advice to people who I think are trying to troll me badly <_<
19:41:18 <Dulnes> And no im not cleaning it with soap
19:41:50 <Dulnes> elliott: why would i have a reason to troll you? i dont even know you
19:42:13 <elliott> Dulnes: what language is (hh)++["^§"].g[ss.h]+++-[ " ok " ." irc.web_host " ]+++( " * " )-[ "»»»" ] = <.irc.app_module> [ "«««" ] in anyway?
19:42:45 <Vorpal> ais523, well, esr has a /significant/ ego I can tell at this point.
19:42:55 <Dulnes> also its my friends bots code
19:43:10 <Dulnes> im just borrowing it >_>
19:43:39 <elliott> ok. you need to fix your broken CPU core so you can code in your skypes again
19:44:14 <Dulnes> or i can just throw my entire desktop out the window
19:44:29 <Dulnes> and use my phone forever
19:44:37 <elliott> in summary, I have no idea what could have possibly given me the impression that you're not saying true things
19:44:57 <Dulnes> i dont need you to believe me
19:45:13 <Dulnes> i just need to know where to buy a good one
19:45:15 <ais523> !bfjoust dulnes_example (hh)++["^§"].g[ss.h]+++-[ " ok " ." irc.web_host " ]+++( " * " )-[ "»»»" ] = <.irc.app_module> [ "«««" ]
19:45:17 <zemhill> ais523.dulnes_example: points -30.67, score 3.72, rank 47/47
19:45:25 <EgoBot> Score for ais523_dulnes_example: 6.1
19:45:27 <ais523> I guess it probably isn't BF Josut?
19:45:42 <elliott> ais523: I don't think it's anything seeing as the last snippet of bot code before that had unmatched barckets
19:45:49 <elliott> and random embedded brainfuck code
19:46:04 <elliott> and also the "bot" connected via webchat :p
19:46:12 <ais523> it was me who pointed that out
19:46:23 <ais523> thing is, that might actually be a sane impl on Windows 95
19:46:52 <ais523> hmm, are we talking about the same person?
19:47:12 <elliott> ais523: yes, I just didn't pay as much attention yesterday
19:47:28 <elliott> I think you can get a browser that will run webchat on Windows 95, but only just
19:47:36 <Dulnes> werent we talking about black holes
19:47:41 <elliott> thankfully none of this is a true thing
19:48:17 <Vorpal> ais523, also consider model based checking for ick? Like QuickCheck.
19:48:52 <Vorpal> Might be fun, writing a haskell FFI for intercal so you can use quickcheck on it. Maybe?
19:49:40 <ais523> Vorpal: actually I wrote something for fuzzing the optimizer which is vaguely similar to that
19:49:42 <ais523> it generates random INTERCAL expressions, then feeds a bunch of random numbers through them (many of which have significant values like powers of 2)
19:50:00 <elliott> there's quickcheck ports to other languages
19:50:09 <ais523> and sees if they produce the same result on an optimized and unoptimized program
19:50:17 <ais523> we found several optimizer bugs that way
19:50:29 <Vorpal> elliott, I know a guy who ported it/is porting it to C++11. :/
19:50:57 <Vorpal> Well, apart from C++ not being reasonable, sure
19:50:57 <ais523> incidentally, I'm /still/ not sure if ESR has figured out that I'm a different person from Claudio Calvelli yet
19:51:08 <Vorpal> ais523, have you told him?
19:51:27 <ais523> I think I did once, but there's not much point really
19:51:44 <ais523> I'll mention it again if it ever becomes important
19:52:16 <elliott> why would you go out of your way to talk to esr :p
19:52:25 <Vorpal> ais523, cfunge has an even simpler fuzz test btw, where it feeds a random program into cfunge (which is set to run in "safe mode", which disables instructions that could affect system state, like writing a file). It then checks if it crashes within x seconds, if not it runs it again under valgrind for another x seconds and checks for errors being reported.
19:53:16 <ais523> strangely enough, I'd made my own attempt to collect old INTERCAL versions independently from ESR
19:53:21 <ais523> but he has better connections than I do, so was better at it
19:54:33 <Vorpal> ais523, anyway, feel free to put up that patch if you still have it around. I don't currently know where I have it as a patch. I just found the source and build directory on the old mac.
19:54:44 <Vorpal> Where there is no version control.
19:55:31 <Vorpal> Oh and if I didn't credit myself already, note down it was me who did it somewhere. And remember the Mac MPW Makefile must be encoded as MacRoman.
19:55:36 -!- Guest76372 has quit (Changing host).
19:55:37 -!- Guest76372 has joined.
19:55:59 <ais523> Vorpal: do you know which version it was a patch /against/?
19:56:00 -!- Guest76372 has changed nick to Sprocklem.
19:56:30 <Vorpal> ais523, no, but I guess I could check if you know a reasonble way to detect it?
19:57:06 <Vorpal> ais523, I'm starting sheepshaver right now
19:57:09 <ais523> Vorpal: if you have the complete source directory as well as the patch, you could reverse the patch and apply it to the source dir
19:57:29 <Vorpal> I do not have the patch, just the complete source & build directory
19:57:51 <ais523> let's see if I have the patch
19:58:00 <ais523> please tarball up at least the source directory
19:58:17 <ais523> tarballing up the build directory is not "technically" necessary as it should be in theory reproducible, but I'm not sure that most peopel actually can
19:58:40 <Vorpal> ais523, tarball doesn't do resource forks do it?
19:58:49 <Vorpal> So the build directory will be corrupted
19:58:54 <Vorpal> Source should be fine though
19:58:55 <ais523> Vorpal: OS X can tarball resource forks
19:59:02 <ais523> no idea if that was backported to Classic though
19:59:21 <Vorpal> I will have to copy it as-is to a different computer and then tar it there
19:59:23 <ais523> do you have any proprietary Mac-specific archiver?
19:59:31 <ais523> someone's probably reverse-engineered it by now
19:59:48 <Vorpal> ais523, hm there is the directory "ick mac" and "ick mac - new" directories.
19:59:56 <Vorpal> I will copy both and diff them
20:00:03 -!- NATT_SiM has quit (Remote host closed the connection).
20:00:09 <Vorpal> Oh great there is ick-mac.prev too
20:00:41 <Vorpal> Oh and a locked disk image marked "ick"
20:01:07 <elliott> sounds like you have a bit of an
20:02:18 <Vorpal> Well I copied all the ones I found. I will do some directory diffing now
20:02:47 -!- Patashu has joined.
20:05:14 <vanila> There was a follow-up study that illustrated the issue by inviting Lispers to come up with their own solutions to the problem, which involved comparing folks like Darius Bacon to random undergrads. A follow-up to the follow-up literally involves comparing code from Peter Norvig to code from random college students.
20:05:22 <vanila> could you help me find that follow-up please?
20:05:31 <vanila> http://danluu.com/empirical-pl/#wat_summary
20:05:35 <vanila> regarding this linked earlier
20:07:50 <Vorpal> ais523, one of the versions involve resource fork :/
20:08:07 <Vorpal> No, there is a resource script I think
20:08:38 <Vorpal> ais523, Are you sure you don't have the patch around any more?
20:10:27 <Vorpal> ais523, oh I think this will show a dialog box with the options to the ick command in MPW
20:10:44 <ais523> Vorpal: haven't looked for it yet, got confused
20:11:14 <ais523> Vorpal: I have a "macppc_beginning.patch" but it's just 637 lines long
20:11:38 <Vorpal> can you upload that somewhere?
20:12:15 <ais523> Vorpal: nethack4.org/esolangs/macppc_beginning.patch
20:13:05 <Vorpal> That mime type, I guess I'll download it
20:13:28 <ais523> what mime type does my server give it?
20:13:55 <Vorpal> Something that makes firefox want to save it rather than view it
20:14:30 <Vorpal> Anyway, it appears that I have a newer version here, since ick.r is missing in your patch
20:14:32 <ais523> ah right, I think my server just doesn't know what type it is
20:15:08 <Vorpal> ais523, The big problem is that 1) I don't know which files are generated any more 2) I have no idea if the resource fork or file type matter on any of these files
20:15:22 <Vorpal> As in the mac creator flag and file type (4 letters each)
20:16:02 <Vorpal> Heh, sublime does macroman, nice
20:16:21 <Vorpal> elliott, What is the command to search the logs?
20:16:35 <ais523> Vorpal: there isn't one any more because HackEgo doesn't have access to them
20:16:42 <HackEgo> [wiki] [[User talk:Zzo38]] http://esolangs.org/w/index.php?diff=41021&oldid=39850 * Nthern * (+222) /* Capuirequiem reference interpreter */ new section
20:16:49 -!- shikhout has joined.
20:17:20 <Vorpal> ais523, I do have a backup disk that might contain the Linux side repo of this, let me look at it (I have reinstalled this computer since I did that)
20:19:27 <Vorpal> ais523, this might be of interest: http://sprunge.us/OOGg
20:19:41 -!- shikhin has quit (Ping timeout: 250 seconds).
20:23:14 -!- Bicyclidine has joined.
20:26:02 -!- Patashu has quit (Ping timeout: 264 seconds).
20:27:57 <Vorpal> ais523, okay so I know which version to use now. However, this is with resource forks stored as the sheepshaver emulator does it when you copy file to the shared-with-host virtual disk thing.
20:28:10 <Vorpal> I have no idea if this is useful for anyone using a real mac
20:28:24 <ais523> I have no idea if all this is useful even for someone running Linux
20:28:54 <Vorpal> And on my real mac I only have stuffit for compressing it. Also there are no build instructions anywhere, except for esolang logs I guess. I certainly have no idea how to build it any more.
20:30:38 <Vorpal> ais523, I'm writing a short read me with the stuff I know about (not much at this point) then sending it to you
20:45:08 <Vorpal> ais523: https://www.dropbox.com/s/65xc2m46wu3itih/ick-mac_final.tar.xz?dl=0
20:46:11 <ais523> hmm, another website that claims to require JavaScript, but actually doesn't
20:46:18 <Vorpal> ais523, Hope you can figure out which version it is based on (probably a darcs revision, not a specific release)
20:46:29 <ais523> Vorpal: ooh, I have an ick-mack-patches directory too
20:46:38 <ais523> that I didn't notice last time I looked
20:46:46 <Vorpal> ais523, okay? I have no idea about that
20:47:06 <Vorpal> ais523, I do think some of the source is patched to fix issues with path generation
20:47:18 <ais523> Vorpal: what's the README actually named?
20:47:24 <int-e> ais523: is it one of those that include a CSS file that hides most contents?
20:47:48 <Vorpal> ais523, macppc/Makefile *must be MacRoman*
20:48:00 <Vorpal> ais523, it looks like it contains weird letters, because it does
20:48:10 <ais523> that ick_createdata thing looks like a bug that should be fixed
20:48:16 <ais523> also, you've gone on about this encoding thing like 10 times now
20:48:20 <ais523> it's not like iconv doesn't exist
20:48:39 <Vorpal> ais523, well, just treat it as a binary file is probably best.
20:49:20 <ais523> except, hmm, iconv doesn't know the name "macroman"
20:49:49 <ais523> oh, it's just called "macintosh"
20:49:55 <ais523> SysLibs = {ShareDir}syslib.i ∂
20:50:02 <ais523> is that the correct transcode to UTF-8?
20:50:10 <Vorpal> ais523, ∂ is line continuation \
20:50:14 <Vorpal> There is another character too
20:50:31 <ais523> {ObjDir} ƒ {SrcDir} {PreBDir} {GenSrcDir}
20:50:33 <ais523> who designed this syntax
20:50:40 <Vorpal> ais523, I have no idea
20:50:54 <ais523> this is like British people using ¬ and £ in language definitions because they don't know better
20:51:04 <ais523> (and I think ¬ is on UK keyboards because it's in EBCDIC?)
20:51:13 <Vorpal> ais523, also there is ƒƒ but I don't remember how it differs. ƒƒƒ even i think?
20:51:48 <Vorpal> ais523, anyway if you can commit it as a binary file it is probably best to do so, saves people from having to re-encode it if they want to use it.
20:52:19 <ais523> huh, according to Wikipedia, there is actually also a capital Ƒ
20:53:17 <Vorpal> Bicyclidine, yes the make file is louder :P
20:53:25 <Vorpal> ais523, in MPW make files!?
20:53:30 <ais523> Wikipedia also has dire warnings about confusing the character in the Makefile with ʄ
20:53:32 <ais523> Vorpal: no, just in general
20:53:49 <Vorpal> ais523, wikipedia has a page on MPW make files?
20:53:58 <ais523> it has a page on ƒ though
20:54:28 <Vorpal> ais523, you should look at the comment near the top of uncommon.c where it deals with path separators
20:54:40 <ais523> oh, Wikipedia actually has two paragraphs on MPW make files
20:54:43 <ais523> https://en.wikipedia.org/wiki/Macintosh_Programmer%27s_Workshop#Writing_MPW_tools
20:55:17 <Vorpal> ais523, yep I basically build ick as an MPW tool
20:55:29 <Vorpal> Otherwise there would be no command line argument support
20:55:52 <Vorpal> ais523, after reading uncommon.c you will ask again "who designed this syntax"
20:56:57 <ais523> huh, this is pretty similar to Wikipedia escaping syntax
20:57:27 <Vorpal> How are mac paths similar? Or the make file?
20:57:31 <ais523> [[page]] is [[:page]] is named "page" (and are the same page), [[::page]] would be a page named ":page" but that's disallowed because the software gets confused handling its own escaping syntax
20:58:28 <Vorpal> ais523, that makes no sense, what does the single : actually do there?
20:58:44 <ais523> forces the link to be an actual link
20:58:56 <ais523> rather than something else that might have similar syntax
20:59:07 <ais523> e.g. [[:Category:2014]] compared to [[Category:2014]] on Esolang
20:59:38 <Vorpal> ais523, anyway I patched ick to not generate foo//bar in compile commands I remember, since that breaks with foo::bar on mac
21:00:13 <Vorpal> ais523, also classic mac supports / in file and directory names (it was forbidden in 9.1 or so I think, in preparation for OS X)
21:00:38 -!- NATT_SiM has joined.
21:00:42 <Vorpal> Forbidden as in "you can't create new ones"
21:02:09 <Vorpal> ais523, oh another thing I remember now that I forgot in the readme. ick will output the compiler commands to run. Since MPW tools can't execute other tools
21:02:21 <Vorpal> Because reasons and fucked up memory management
21:02:40 <Vorpal> IIRC they are basically loaded as libraries into the MPW workbench
21:03:05 <Vorpal> And it would cause freezes if it tried to run another tool
21:03:36 <ais523> so basically a permanent -c
21:05:30 <Vorpal> there are some patches in perpet.c it appears (I find this file naming confusing btw)
21:05:50 -!- NATT_SiM has quit (Ping timeout: 258 seconds).
21:06:05 <ais523> Vorpal: basically, the file names are tangentially related to the purpose of the file
21:06:13 <ais523> that's it, that's the only principle behind the names
21:06:20 <ais523> so there's normally some connection, but a very remote one
21:06:41 <ais523> that said, I have no idea what's behind the name "feh.c" (which eventually became "feh2.c")
21:07:52 <int-e> @google fiddle lose ick feh
21:07:53 <lambdabot> https://gitorious.org/intercal/intercal/source/9745c958c4bc00939fd244d78530ad232be61b72:Makefile
21:08:17 <Vorpal> ais523, searching for #ifdef MPW_C and variants of that should probably help you find most patches
21:08:20 <int-e> (those are some good search terms)
21:09:58 <Vorpal> ais523, perpet.c line 807-826 might be interesting too
21:20:28 <fizzie> Just bought: one-way tickets to London.
21:20:30 <fizzie> And § is another only-in-some-keyboards key.
21:26:33 -!- Phantom_Hoover has quit (Ping timeout: 258 seconds).
21:30:54 -!- yukko has quit (Ping timeout: 265 seconds).
21:31:03 -!- zemhill has quit (Ping timeout: 245 seconds).
21:31:24 -!- NATT_SiM has joined.
21:34:10 <Vorpal> I have §. Unshifted even
21:34:30 <Vorpal> It is the key to the left of 1
21:34:45 <Vorpal> What is that on US keyboards I wonder
21:34:57 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ~: not found
21:36:33 <fizzie> Vorpal: We do, too, because the Finnish layout is practically identical to the Swedish one.
21:37:07 <Vorpal> It is a fairly useless symbol
21:37:39 <fizzie> The British layout has ` and ¬ there. (So same as US in that regard, except with ¬ replacing ~.)
21:38:09 <fizzie> (They've got # and ~ in the key where we have ' and *.)
21:38:37 <fizzie> (Also I just used § in an email today.)
21:39:51 <ais523> the British keyboard also has a second | on altgr-`
21:39:56 -!- Phantom_Hoover has joined.
21:40:22 <ais523> it produces the same character as shift-\ on Linux, but typically a different character from | on Windows (often a "broken" pipe)
21:40:25 -!- ZombieAlive has joined.
21:41:19 -!- NATT_SiM has quit (Remote host closed the connection).
21:41:57 -!- zemhill has joined.
21:44:10 -!- ais523 has quit (Read error: No route to host).
21:44:27 -!- ais523 has joined.
21:45:49 -!- `^_^v has quit (Ping timeout: 256 seconds).
21:46:28 -!- NATT_SiM has joined.
21:48:04 <fizzie> The broken bar can be confusing.
21:48:08 -!- zemhill has quit (Ping timeout: 245 seconds).
21:49:06 <fizzie> A relatively common Finnish keymap has the key-between-z-and-shift as < unshifted, > with shift, | (solid bar) with altgr and ¦ (broken bar) with shift-altgr.
21:49:41 -!- perrier has quit (Remote host closed the connection).
21:51:18 -!- perrier has joined.
21:51:33 <fizzie> Though that's not an official part of the modern SFS (Finnish national standards body) 2008 fi keymap -- it doesn't define any level4 meaning for the key.
21:52:10 -!- yukko has joined.
21:52:51 <fizzie> It's the most mortal of layouts: there's a total of 19 dead keys (if you count all shift levels separately).
21:53:44 -!- zemhill has joined.
21:55:55 <b_jonas> yeah, the latin1 broken bar
21:56:17 <b_jonas> I have a mark next to it in my font because my normal bar | is broken too
21:56:25 <fizzie> And the SFS layout also has the worst thing, which is putting a non-breaking space as altgr-space. Combine with the fact that | comes from altgr-< and every third pipeline fails due to an unintentional nbsp between | and the command.
21:57:06 <b_jonas> fizzie: yes, that's a bad idea. there's a good reason why shift-space and altgr-space still has to give space
21:57:25 <olsner> mac seems to generically have alt-space as nbsp, regardless of layout
21:57:30 <b_jonas> in fact, in my weird layout I use capslock to write hungarian letters,
21:57:44 <b_jonas> but I don't have to press it exactly, because all the a-z letters still produce the same thing with caps lock as without
21:57:54 <olsner> (at least I've never seen swedish layout produce nbsp except on mac)
21:58:00 <b_jonas> and produce the same letter with capslock-shift as with shift
21:58:11 <b_jonas> so I can hold the capslock for longer than needed
21:58:33 <b_jonas> I only have some extra symbols on capslock-digits and capslock-shift-digits
22:02:15 -!- Bicyclidine has quit (Ping timeout: 265 seconds).
22:03:07 -!- NATT_SiM has quit (Remote host closed the connection).
22:07:08 <int-e> Oh well, Unicode is just weird. ⌨
22:08:10 <int-e> but now I can type ⦇⟦⦃«⟪⟫»⦄⟧⦈
22:08:41 <Vorpal> <ais523> it produces the same character as shift-\ on Linux, but typically a different character from | on Windows (often a "broken" pipe) <-- \ is altgr-+ for me, | is altgr + key left of z
22:08:45 <Vorpal> ais523, so that didn't help
22:09:07 <ais523> key left of z on a UK keyboard is \ unshifted, | shifted
22:09:10 <Vorpal> <fizzie> A relatively common Finnish keymap has the key-between-z-and-shift as < unshifted, > with shift, | (solid bar) with altgr and ¦ (broken bar) with shift-altgr. <-- same for my Swedish keymap
22:09:16 <int-e> . u ⟅ I wonder whether anybody uses these... ⟆
22:09:35 <Vorpal> <fizzie> It's the most mortal of layouts: there's a total of 19 dead keys (if you count all shift levels separately). <-- Does Swedish have that much?!?
22:10:16 <olsner> of course not, we're not finns are we?
22:10:29 <int-e> (Actually I have seen ⟅ ⟆ on somebody's slides recently.)
22:10:38 <fizzie> The "traditional" Finnish layout doesn't have that much, at least.
22:11:48 <Vorpal> <b_jonas> fizzie: yes, that's a bad idea. there's a good reason why shift-space and altgr-space still has to give space <-- I had issues in some terminal, I think it was either the cygwin one or putty with altgr-<key right of å> (which yields ~ as a dead key, so you have to type altgr+key-left-of-å <space>) opening the menu on altgr-space
22:12:04 <Vorpal> When I didn't release altgr quickly enough
22:12:34 <fizzie> ▕block drawing for absolute value▏
22:12:45 <Vorpal> That renders poorly for me
22:12:51 <olsner> tilde on a dead key is not great for coding
22:12:53 <Vorpal> the | and the b merge together
22:13:16 -!- Bicyclidine has joined.
22:13:46 <int-e> olsner: I learned to hate dead keys in Pascal. ~ wasn't an issue. ^ was.
22:13:52 <olsner> especially bad in editors that don't handle dead keys
22:14:08 <Vorpal> int-e, oh yes, ^ is shift-<key left of å> for me
22:14:11 <olsner> I guess I just wrote c++ without destructors
22:15:11 <Vorpal> ais523, anyway, hopefully you can do something with that tarball. Figure out what it was based on and then put it up there for historical interest
22:15:24 <fizzie> I hit some issue recently where ~ was a dead key, but also pressing ~ + space did not insert ~ but ̃, which is not really good for anything.
22:15:31 <fizzie> (That's a space with COMBINING TILDE.)
22:15:46 <fizzie> And pressing ~ + ~ didn't insert anything.
22:15:52 <fizzie> I couldn't figure out any way to get a regular ~ out of it.
22:16:10 <int-e> that sounds utterly broken.
22:16:28 <fizzie> I think it was some virtual on-screen thing, I forget which device.
22:16:47 <ais523> Vorpal: I'll have a look when I'm more awake and working on INTERCAL
22:17:11 <ais523> thanks for the files, anyway, we can probably make something of this
22:17:38 <Vorpal> ais523, I'm not around much, dropping me an email might be better if you need to get in contact with me.
22:19:22 -!- NATT_SiM has joined.
22:20:52 <fizzie> Aw, we didn't get DNSSEC for esolangs.org. :/
22:21:01 <fizzie> Oh well, it's not like anyone actually uses it.
22:24:29 -!- Sprocklem has quit (Ping timeout: 265 seconds).
22:25:16 -!- AndoDaan has joined.
22:26:28 <Melvar> < fizzie> It's the most mortal of layouts: there's a total of 19 dead keys (if you count all shift levels separately). – Now I want to know wha they are, ’cause even Neo2 only has eighteen.
22:33:25 -!- S1 has quit (Quit: S1).
22:33:58 <fizzie> Melvar: Based on the layout image, some sort of horizontal-line-in-the-middle (1), grave accent (2), acute accent (3), cedilla (4), something that looks like flipped cedilla (5), a hook above (6), something cedilla-like on the right side (7), ring above (8), the Hungarian double acute accent (9), diaeresis (10), ^ above (11), ~ above (12), - above (13), two variants of reversed ^ that look ...
22:34:04 <fizzie> ... pretty similar (14, 15), dot above and below (16, 17)... and, hm. There's two more, but they look suspiciously similar to dot-above and horizontal-line-in-the-middle, so maybe they're redundant. I'll try and find the official list.
22:35:05 <fizzie> Here's the official list.
22:36:00 -!- oerjan has joined.
22:37:41 <fizzie> Yes, they're redundant. Sorry, so there are 19 dead keys but only 17 unique ones.
22:41:55 <fizzie> And the characters are 0301 0300 0327 0328 031B 0309 030B 030A 0308 0302 0303 0304 030C 0306 0323 0307 and there's no code point listed for the combining horizontal line, if I'm interpreting this right it's not actually a single combining Unicode character but more a general "add a stroke" character that can produce d, g, t, l, h, o with an extra stroke.
22:42:42 <fizzie> (That's 0111, 01E5, 0167, 0142, 0127 and 00F8, respectively.)
22:43:38 <Melvar> The ones Neo2 doesn’t have are hook and horn (Vietnamese), and it overloads cedilla and ogonek, because they mostly only go on different letters. The additional ones Neo2 has are: turn, rhotic hook (which may actually serve as Vietnamese horn as well), and greek dasia and psili.
22:45:08 <fizzie> Also the Finnish names for the combining characters are (a) ridiculous and (b) something I've never heard of. (akuutti-korkomerkki, gravis-korkomerkki, sedilji, ogonek, sarvi, yläpuolinen koukku, kaksois-akuutti-korkomerkki, yläpuolinen ympyrä, treema, sirkumfleksi, tilde, pituusmerkki, hattu, lyhyysmerkki, alapuolinen piste, yläpuolinen piste)
22:45:41 -!- NATT_SiM has quit (Remote host closed the connection).
22:46:19 <oerjan> sedilji and ogonek are presumably borrowed from french and russian
22:46:46 <Melvar> Polish actually I believe, that’s where the ogonek is used.
22:47:13 <oerjan> oh right it wouldn't make sense for cyrillic
22:47:45 <oerjan> fizzie: does hattu mean "hat"
22:50:30 <Melvar> Looks like it does, and also háček, which is not what one usually means by a hat on a letter in English.
23:00:27 <Melvar> Having looked at them in Wiktionary, all of those names seem not particularly ridiculous.
23:01:36 -!- Bicyclidine has quit (Ping timeout: 255 seconds).
23:08:47 -!- Bicyclidine has joined.
23:11:55 -!- NATT_SiM has joined.
23:13:32 <HackEgo> [wiki] [[User talk:Zzo38]] http://esolangs.org/w/index.php?diff=41022&oldid=41021 * Zzo38 * (+305)
23:22:03 -!- Sprocklem has joined.
23:26:27 -!- digitalc1ld has changed nick to digitalcold.
23:27:18 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
23:29:18 -!- Bicyclidine has joined.
23:31:21 -!- NATT_SiM has quit (Remote host closed the connection).
23:35:22 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41023&oldid=41002 * BCompton * (+473)
23:35:53 <HackEgo> [wiki] [[Talk:My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41024&oldid=41023 * BCompton * (+57) /* Transactions */
23:36:52 -!- NATT_SiM has joined.
23:37:21 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41025&oldid=41024 * Ais523 * (+79) /* Transactions */ good catch
23:37:53 <HackEgo> [wiki] [[My Unreliable Past]] http://esolangs.org/w/index.php?diff=41026&oldid=40999 * Ais523 * (+4) /* Semantics */ fix thinko
23:38:30 <HackEgo> [wiki] [[My Unreliable Past]] http://esolangs.org/w/index.php?diff=41027&oldid=41026 * Ais523 * (+56) /* Semantics */ clarify
23:40:54 <fizzie> oerjan: Yes. Oh, someone already said that.
23:41:49 <fizzie> And I'm sorry but "gravis-korkomerkki" is unarguably ridiculous, no matter how you spin it.
23:44:48 -!- ais523 has quit.
23:45:23 -!- heroux has quit (Ping timeout: 256 seconds).
23:46:48 <fizzie> Nobody uses (or even knows) the phonetics-specific meaning of "korko", especially since it has a perfectly normal and well-known word ("paino") already.
23:47:58 <fizzie> (And "gravis" is just a gratuitous loanwordery. And a family of sound cards.)
23:49:22 <Melvar> I don’t think any language hasn’t loaned that in in one form or other …
00:05:42 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
00:08:48 -!- heroux has joined.
00:18:00 -!- Bicyclidine has joined.
00:34:17 -!- adu has joined.
00:35:14 -!- NATT_SiM has quit (Remote host closed the connection).
00:35:20 <FreeFull> Melvar: Ogonek is used in other languages
00:35:38 <FreeFull> The name came from Polish though
00:37:46 -!- NATT_SiM has joined.
00:44:47 <Melvar> FreeFull: Yes, I know, I realize I kinda swallowed that.
00:51:18 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
00:53:54 <FreeFull> Romanian has a weird comma thing
00:55:04 -!- shikhout has changed nick to shikhself.
00:55:33 -!- shikhself has changed nick to shikhin.
00:57:18 <HackEgo> [U+0218 LATIN CAPITAL LETTER S WITH COMMA BELOW] [U+021A LATIN CAPITAL LETTER T WITH COMMA BELOW]
00:57:19 -!- NATT_SiM has quit (Remote host closed the connection).
00:58:12 <Melvar> ĢĶĻŅ also have commas, but
00:58:21 <HackEgo> [U+0122 LATIN CAPITAL LETTER G WITH CEDILLA] [U+0136 LATIN CAPITAL LETTER K WITH CEDILLA] [U+013B LATIN CAPITAL LETTER L WITH CEDILLA] [U+0145 LATIN CAPITAL LETTER N WITH CEDILLA]
00:58:49 <Melvar> The unicode names are “wrong” on this.
00:59:00 <HackEgo> [U+0156 LATIN CAPITAL LETTER R WITH CEDILLA]
00:59:37 -!- NATT_SiM has joined.
01:00:23 <oerjan> `unicode LATIN CAPITAL LETTER C WITH CEDILLA
01:01:02 <HackEgo> U+000F <control> \ UTF-8: 0f UTF-16BE: 000f Decimal:  \ \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral)
01:01:09 <oerjan> `unicode LATIN CAPITAL LETTER C WITH COMMA BELOW
01:01:42 <oerjan> lifthrasiir: it seems to me that you have color codes in that?
01:01:54 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
01:03:50 <HackEgo> [U+010F LATIN SMALL LETTER D WITH CARON] [U+0064 LATIN SMALL LETTER D] [U+030C COMBINING CARON]
01:03:54 <lifthrasiir> there are no official names for controls ("<control>", if you prefer that)
01:05:24 <HackEgo> U+0002 <control> \ UTF-8: 02 UTF-16BE: 0002 Decimal:  \ \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral)
01:05:53 <FireFly> It probably just uses UnicodeData.txt?
01:06:35 <HackEgo> #!/usr/bin/env python \ import os, sys \ import unicodedata \ s = u" ".join("[U+{0:04X} {1}]".format(ord(c), unicodedata.name(c, "DUNNO")) for c in " ".join(sys.argv[1:]).decode("utf-8")).encode("utf-8") \ if u"DUNNO" in s: \ os.execvp("multicode", ["multicode"] + sys.argv[1:]) \ else: \ print s
01:07:07 <oerjan> it has a fallback mechanism
01:08:19 <oerjan> the ďď above gets the default treatment, while FireFly's 0002 goes via the fallback
01:09:14 <HackEgo> #!/usr/bin/python \ \ \ import os, glob, sys, unicodedata, locale, gzip, re, traceback, encodings \ import urllib, webbrowser, textwrap \ \ # bz2 was introduced in 2.3, we want this to work also with earlier versions \ try: \ import bz2 \ except ImportError: \ bz2 = None \ \ # for python3 \ try: \ unicode \ except NameError: \
01:09:40 <FireFly> I thought it was just a matter of whether you supply only one or multiple characters
01:09:55 <HackEgo> [U+0061 LATIN SMALL LETTER A]
01:10:15 <HackEgo> U+0061 LATIN SMALL LETTER A \ UTF-8: 61 UTF-16BE: 0061 Decimal: a \ a (A) \ Uppercase: U+0041 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right)
01:11:18 -!- olsner has quit (Ping timeout: 240 seconds).
01:13:35 <HackEgo> U+0061 LATIN SMALL LETTER A \ UTF-8: 61 UTF-16BE: 0061 Decimal: a \ a (A) \ Uppercase: U+0041 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right) \ \ U+0002 <control> \ UTF-8: 02 UTF-16BE: 0002 Decimal:  \ \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral) \ \ U+0063 LATIN SMALL LETTER C \ UTF-8: 63 UTF-16BE: 00
01:22:13 <Dulnes> How does one go about hardening light?
01:27:52 <Taneb> Limestone impurities
01:28:45 <Dulnes> Hm? What about limestone
01:34:08 <Bike> i hear light is a wave
01:36:46 <Dulnes> www.princeton.edu/main/news/archive/S41/10/73O28/index.xml?section=topstories
01:37:08 <Dulnes> Idk if it's true or not but you decide
01:37:55 -!- madbr has joined.
01:39:15 -!- Sprocklem has quit (Ping timeout: 264 seconds).
01:40:52 <Bike> http://journals.aps.org/prx/abstract/10.1103/PhysRevX.4.031043 gee
02:03:31 -!- NATT_SiM has quit (Read error: Connection reset by peer).
02:03:53 -!- NATT_SiM has joined.
02:06:17 <Taneb> Dulnes, limestone is how you make water hard
02:06:40 -!- NATT_SiM has quit (Remote host closed the connection).
02:10:38 -!- NATT_SiM has joined.
02:11:52 -!- Sprocklem has joined.
02:12:20 -!- Sprocklem has changed nick to Guest97875.
02:14:07 -!- Guest97875 has quit (Changing host).
02:14:07 -!- Guest97875 has joined.
02:14:26 -!- Guest97875 has changed nick to Sprocklem.
02:16:35 -!- shikhout has joined.
02:19:34 -!- shikhin has quit (Ping timeout: 244 seconds).
02:25:17 -!- NATT_SiM has quit (Remote host closed the connection).
02:25:18 <adu> `unidecode 💩
02:25:19 <HackEgo> U+1F4A9 PILE OF POO \ UTF-8: f0 9f 92 a9 UTF-16BE: d83ddca9 Decimal: 💩 \ 💩 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
02:39:20 -!- olsner has joined.
02:44:20 -!- AndoDaan has quit (Ping timeout: 258 seconds).
03:14:53 -!- NATT_SiM has joined.
03:42:16 -!- hjulle has quit (Ping timeout: 256 seconds).
03:59:38 -!- Sprocklem has quit (Ping timeout: 240 seconds).
03:59:54 -!- MoALTz_ has joined.
04:02:55 -!- MoALTz has quit (Ping timeout: 258 seconds).
04:42:47 -!- aloril has quit (Remote host closed the connection).
04:55:30 -!- vanila has quit (Quit: Leaving).
04:59:25 -!- oerjan has quit (Quit: leaving).
05:33:00 -!- aloril has joined.
06:02:18 -!- adu has quit (Quit: adu).
06:08:21 -!- aloril has quit (Remote host closed the connection).
06:11:51 -!- ZombieAlive has quit (Remote host closed the connection).
06:13:25 -!- aloril has joined.
06:14:03 <zzo38> Again, he lost before he could pick his last remaining side card. How common is such a thing?
06:21:13 <zzo38> (I mean he ran out of cards.)
06:22:49 <int-e> Argh. "only". "Mark Zuckerberg estimated earlier this year that the company’s U.S. users spend a total of nine hours a day on digital media, but only 40 minutes of that on Facebook."
06:26:05 <zzo38> int-e: What company is that? How was the data estimated?
06:26:57 <int-e> I'm reading about "Facebook at Work", and I'm appalled at the idea.
06:27:43 <int-e> (The initial article I read about it said it would use "the familiar Facebook interface" and to me there is no such thing.)
06:27:52 -!- NATT_SiM has quit (Remote host closed the connection).
06:28:32 -!- MDude has quit (Ping timeout: 250 seconds).
06:32:21 <int-e> zzo38: Actually Facebook will have hard numbers on that (the statement is about their users), with some errors because just because a browser tab is visible doesn't mean anybody is using it, and because some of the people with US IPs are not actually in the US.
06:35:46 -!- MoALTz has joined.
06:36:25 <int-e> One of the biggest issue I have with Facebook is that they make Google look like the good guys.
06:36:55 -!- MoALTz_ has quit (Ping timeout: 264 seconds).
06:54:55 <int-e> I guess fungot would know...
07:15:10 -!- madbr has quit (Quit: Pics or it didn't happen).
07:24:39 -!- Patashu has joined.
07:29:18 -!- Patashu has quit (Remote host closed the connection).
07:29:29 -!- Patashu has joined.
07:31:16 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:20:30 -!- shikhout has quit (Ping timeout: 255 seconds).
08:29:56 <fizzie> The MD for 4000 was quite suspicious too.
08:39:01 <zzo38> How to make error diffusion without "ghost images" appearing?
08:43:06 <int-e> I suppose one should not distribute errors across edges in the image, but how to implement that, I don't know.
08:43:33 <fizzie> Gimp has a "reduced color bleeding" Floyd-Steinberg mode, but I'm not entirely sure what it does.
08:43:58 <fizzie> And I vaguely remember something about scanning every other line left-to-right and every other right-to-left, but I'm not sure what sort of artefacts that is supposed to reduce.
08:47:26 <fizzie> You could apply some general image segmentation algorithm (to the original or the quantized form), and then do color conversion and dithering within each segment, but I wouldn't be surprised if all that accomplishes would be to just make segmentation errors be visible as artefacts.
08:49:42 <zzo38> I thought of something else to try let's see how well it works.
08:51:12 <zzo38> No, what I tried doesn't work.
09:01:51 <zzo38> I am getting "ghost images" which are pretty far away from the original and have a similar shape.
09:04:18 -!- Phantom_Hoover has joined.
09:06:35 -!- AndoDaan has joined.
09:06:52 <zzo38> I think I found the mistake now.
09:07:10 <int-e> how do you distribute the error among neighbouring pixels? I don't see this happening...
09:08:06 <zzo38> I fixed it; the mistake was in a different calculation.
09:54:20 -!- AndoDaan_ has joined.
09:56:58 -!- AndoDaan has quit (Ping timeout: 250 seconds).
10:12:39 -!- mihow has quit (Read error: Connection reset by peer).
10:14:07 -!- mihow has joined.
11:00:32 -!- shikhin has joined.
11:13:33 -!- boily has joined.
11:32:11 -!- Phantom_Hoover has quit (Ping timeout: 258 seconds).
11:35:43 -!- Patashu has quit (Ping timeout: 264 seconds).
11:40:33 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: tomroman: not found
12:18:52 <boily> I can't segment “tomroman”. Is it “Thomas Roman”, or “to mroman”?
12:25:08 -!- drdanmaku has joined.
12:25:19 <AndoDaan_> mroman, nearly done with the MNNBFSL interpreter in Burlesque
12:25:34 -!- boily has quit (Quit: EMULSIFIED CHICKEN).
12:27:17 <AndoDaan_> Finally when i'm figuring out how to simulate variables and functions in burlesque, you add them.
12:30:23 -!- AndoDaan_ has changed nick to AndoDaan.
12:30:52 <mroman> AndoDaan: usually you just keep a list somewhere laying around and use DimAccess or DimSet
12:31:05 <mroman> or BlockAccess and setat
12:31:31 <mroman> the other approach is to translate the input program to Burlesque and then eval it
12:31:35 <mroman> possibly a combination of both.
12:33:35 <AndoDaan> i'm figuring if you have an array with something like {{"a"vv 3} {"add2"vv 2+.}} you can search for "add2" and evauate the block it's in.
12:37:30 <mroman> there's cn which does exactly that btw.
12:37:39 <mroman> well... not exactly that but similar
12:37:58 <AndoDaan> You think Anarchy Golf will update when you're done upgrading?
12:38:13 <mroman> !blsq 9"a"{{"a"==} {vv?*}}cn
12:38:16 <mroman> !blsq 9"a"{{"a"==} {vv?*}}cne!
12:38:16 <blsqbot> | ERROR: Burlesque: (.*) Invalid arguments!
12:38:25 <mroman> !blsq 9"a"{{"a"==} {vvS[}}cne!
12:38:25 <blsqbot> | ERROR: Burlesque: (S[) Invalid arguments!
12:38:31 <mroman> !blsq 9"a"{{"a"==} {vv^^?*}}cne!
12:38:31 <blsqbot> | ERROR: Burlesque: (.*) Invalid arguments!
12:38:31 <blsqbot> | ERROR: Burlesque: (^^) Stack size error!
12:38:34 <mroman> !blsq 9"a"{{"a"==} {vv^^?*}}cne!
12:38:35 <blsqbot> | ERROR: Burlesque: (.*) Invalid arguments!
12:38:35 <blsqbot> | ERROR: Burlesque: (^^) Stack size error!
12:38:38 <mroman> !blsq 9"a"{{"a"==} {vv^^?*}}cn
12:38:49 <mroman> !blsq 9"a"{{"a"==} {^^?*}}cne!
12:38:53 <AndoDaan> I'm using cn for the MNNBFSL instructions
12:39:06 <mroman> !blsq 9"b"{{"a"==} {^^?*} {"b"==} {^^?*^^?*}cne!
12:39:07 <blsqbot> | ERROR: (line 1, column 43):
12:39:07 <blsqbot> | expecting "%", "g", "s", "S", "m{", "q", "{", "\"", "-", digit, "'", "(", "y" or "}"
12:39:13 <mroman> !blsq 9"b"{{"a"==} {^^?*} {"b"==} {^^?*^^?*}}cne!
12:41:46 <AndoDaan> still missing the while condition, and will be reduced some what, but that's what it's shaping up to be.
12:43:52 <mroman> line 13 looks like a syntax error
12:45:33 <AndoDaan> fat pinky. fixed http://codepad.org/Y1WCJjFj
12:50:04 <AndoDaan> p is close to { on my keyboard.
12:51:27 <AndoDaan> and the constant {PP ... Pp}e! doesn't help with the muscle memory.
12:53:48 <AndoDaan> Gonna finish it up later todayor tomorrow. I just wanted to say it was fun. Thanks for suggesting it.
12:54:04 -!- AndoDaan has quit (Quit: Sleep? What is sleep?).
12:56:03 <mroman> What a weird keyboard.
12:56:23 <mroman> Everybody knows P is not even close to {
13:01:11 <fizzie> p is right below } (altgr-0) here.
13:03:18 -!- Frooxius has quit (Quit: *bubbles away*).
13:04:08 <elliott> 12.5 gigabytes of swap used is not a good statistic...
13:07:37 -!- Frooxius has joined.
13:12:56 <FireFly> P would be close to { if I didn't use dvorak
13:33:29 <mroman> FireFly: Exactly. But who the hell doesn't use Dvorak.
14:02:52 <fizzie> I can't find any reasonable statistics quickly, but I'd wager a guess that several people.
14:03:40 -!- S1 has joined.
14:05:21 <fizzie> While looking for said statistics, though, I did find incontrovertible proof that learning Dvorak makes you smart: "-- I could almost feel my synapses firing faster and new neuron connections being made. I felt like I got a turbo boost to my IQ during that period where I thought fast, was more creative and just generally sharper."
14:07:11 <elliott> sounds like the results people report for trepanning
14:08:09 <elliott> I read a great webpage once that was like [pages of description of how he got a buddy to drill into his skull] [hyperbolic praise over how amazing he feels in the immediate aftermath and how great an idea it was] [pause] [entry admitting that the gains didn't last and probably never existed that much and that he regrets doing it]
14:08:27 <elliott> sorry about the hole in your head, dude
14:09:46 <fizzie> That sounds vaguely familiar. (And also a bit more extreme than typing with a different layout.)
14:11:08 <elliott> look, the Keyboard Fascists will never get me to trepannify myself
14:18:34 -!- NATT_SiM has joined.
14:25:18 -!- hjulle has joined.
14:36:43 -!- NATT_SiM has quit (Remote host closed the connection).
14:51:03 -!- NATT_SiM has joined.
14:51:49 -!- NATT_SiM has quit (Remote host closed the connection).
15:08:57 -!- `^_^v has joined.
15:41:51 <Bike> that sounds like a good webpage
15:46:21 <J_Arcane> Scheme in Arabic. https://github.com/nasser/---
15:58:40 -!- hubs has joined.
15:58:53 -!- S1 has changed nick to S0.
16:01:16 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
16:01:43 -!- hubs has quit (Quit: hubs).
16:04:13 -!- S0 has changed nick to S1.
16:13:17 -!- drdanmaku has joined.
16:30:18 <HackEgo> [U+002D HYPHEN-MINUS] [U+002D HYPHEN-MINUS] [U+002D HYPHEN-MINUS]
16:30:47 <Melvar> Does github not allow arabic repositories or something?
16:34:24 <J_Arcane> maybe because the reponames are used as default directory names?
16:35:03 <Bike> i'm pretty sure i have a couple folders named in cyrillic
16:35:24 <Melvar> J_Arcane: I’m not sure how you mean that would affect it.
16:36:13 <J_Arcane> I don't know the state of support for unicode filenames in various OSes.
16:36:28 <J_Arcane> Perhaps they default to 'ascii safe' names for them.
16:37:30 <HackEgo> [U+061F ARABIC QUESTION MARK]
16:39:58 -!- MDude has joined.
16:41:50 <Melvar> “first:hrf rest:(hrf / [٠١٢٣٤٥٦٧٨٩] / '-' / '؟' / 'ـ' )* space?” ← This line looks very funny with proper bidi layout.
16:42:07 <Bike> is that phoenician
16:42:47 <Bike> oh. numerals. not used to those.
16:43:00 -!- S1 has quit (Quit: S1).
16:44:47 <Melvar> So, of that line, “٠١٢٣٤٥٦٧٨٩] / '-' / '؟' / 'ـ” is right-to-left (including mirroring the ‘]’), and then “٠١٢٣٤٥٦٧٨٩” is a left-to-right subchunk because that’s what arabic does with numerals.
16:46:36 <elliott> Melvar: do you have an, uh, reference rendering of that line
16:47:34 <Melvar> I could screenshot it from my browser … it’s at https://github.com/nasser/---/blob/master/peg/qlb.peg under “symbol =”.
16:47:57 <Bike> hm. the [ ends up next to the underscore for me.
16:48:12 <Bike> thaaaaat's probably not right
16:48:33 <Melvar> It’s not an underscore.
16:49:10 <Melvar> It’s next to the opening [ because it’s the last thing in the right-to-left chunk.
16:50:41 <elliott> Melvar: I was just curious as to whether my terminal is doing it correctly.
16:52:18 -!- hjulle has quit (Ping timeout: 265 seconds).
16:56:08 -!- shikhout has joined.
16:56:50 <Melvar> elliott: http://i.imgur.com/Hz2WcBD.png
16:57:17 <elliott> Melvar: cool, it survives irssi + mosh + terminal for me and displays the bidi correctly
16:57:29 <elliott> (in layout order, not logical order)
16:57:53 <Melvar> Well, that should only be a matter of your terminal, since it’s about character properties.
16:58:12 <elliott> you trust programs that layout unicode characters on screen to not mess it up?
16:58:21 <elliott> er, programs that run in a terminal I mean
16:58:42 <Bike> my ignorant question is now preserved forever
16:59:01 <Melvar> I mean, mosh possibly could confuse the terminal about – ohgodIhavetobeelsewhere
16:59:16 <elliott> https://mosh.mit.edu/#techinfo I think it's more likely to be right with mosh than without
16:59:22 -!- shikhin has quit (Ping timeout: 255 seconds).
16:59:22 <elliott> since it does things with unicode
17:05:50 <Melvar> elliott: If you select the line, it should select according to logical order, so if you get discontinuous-looking selections, your terminal is doing it right and I would like to know which it is.
17:06:22 <elliott> my selection are continuous but weird
17:06:39 <elliott> if I select from the third character after the second displayed [ to the ' then I get '؟' / 'ـ'
17:07:06 <elliott> it generally handles unicode way better than the usual X11 terminals
17:07:21 -!- NATT_SiM has joined.
17:07:31 <elliott> by "then I get", I mean it looks like I've selected what I said, but it copies as what I pasted.
17:08:48 <Melvar> Huh, maybe it applies the selection to the logical order but shows it superimposed on the layout order?
17:09:17 <elliott> https://letsencrypt.org/ huh.
17:09:23 <elliott> Melvar: right, that's what I think
17:09:35 <Melvar> Anyway, really need to leave now.
17:09:35 <elliott> it visually selects like any other line but copies weirdly
17:11:58 -!- NATT_SiM has quit (Ping timeout: 255 seconds).
17:19:12 -!- NATT_SiM has joined.
17:19:38 -!- NATT_SiM has quit (Remote host closed the connection).
17:20:18 -!- NATT_SiM has joined.
17:41:18 -!- S1 has joined.
17:51:46 -!- S1 has changed nick to |S}.
17:57:07 -!- NATT_SiM has quit (Remote host closed the connection).
17:58:45 <fizzie> elliott: But will it work in IE?
17:59:00 <elliott> fizzie: they have an existing root CA co-signing for them, it seems
17:59:13 -!- augur has quit (Remote host closed the connection).
17:59:57 <fizzie> Oh, IdenTrust is a CA? Okay, with that sort of name, shouldn't have been surprised.
18:00:07 <elliott> well, they sign the letsencrypt.org key.
18:01:37 -!- NATT_SiM has joined.
18:02:58 -!- MoALTz has quit (Quit: Leaving).
18:17:34 -!- NATT_SiM has quit (Remote host closed the connection).
18:18:57 -!- NATT_SiM has joined.
18:19:53 -!- |S} has changed nick to S1.
18:29:26 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41028&oldid=41025 * BCompton * (+712) IO Questions
18:36:04 -!- NATT_SiM has quit (Remote host closed the connection).
18:37:15 -!- NATT_SiM has joined.
18:54:30 -!- NATT_SiM has quit (Remote host closed the connection).
19:00:03 -!- Sprocklem has joined.
19:01:20 -!- NATT_SiM has joined.
19:05:34 -!- NATT_SiM has quit (Remote host closed the connection).
19:05:47 -!- NATT_SiM has joined.
19:14:14 -!- shikhout has changed nick to shikhin.
19:19:39 -!- shikhin has quit (Ping timeout: 240 seconds).
19:20:48 -!- shikhin has joined.
19:29:31 -!- NATT_SiM has quit (Remote host closed the connection).
19:29:50 -!- Sprocklem has quit (Ping timeout: 245 seconds).
19:32:16 -!- NATT_SiM has joined.
19:39:41 -!- Patashu has joined.
19:49:46 -!- augur has joined.
19:51:19 -!- augur has quit (Remote host closed the connection).
19:57:48 -!- NATT_SiM has quit (Remote host closed the connection).
20:01:24 -!- S1 has left.
20:05:19 -!- NATT_SiM has joined.
20:07:43 -!- zzo38 has quit (Remote host closed the connection).
20:10:28 -!- augur has joined.
20:16:26 -!- augur has quit (Remote host closed the connection).
20:16:40 -!- augur has joined.
20:25:25 -!- Patashu has quit (Ping timeout: 258 seconds).
20:31:58 -!- NATT_SiM has quit (Remote host closed the connection).
20:37:34 -!- NATT_SiM has joined.
20:38:29 -!- augur has quit (Remote host closed the connection).
20:39:53 <newsham> static type checker for javascript http://flowtype.org/
20:55:54 -!- NATT_SiM has quit (Remote host closed the connection).
20:57:31 -!- NATT_SiM has joined.
21:03:33 -!- vanila has joined.
21:04:38 -!- NATT_SiM has quit (Remote host closed the connection).
21:08:44 -!- NATT_SiM has joined.
21:12:59 -!- b_jonas has quit (Ping timeout: 240 seconds).
21:15:49 <int-e> Is CSS property inheritance esoteric? http://int-e.eu/~bf3/tmp/test.html
21:16:17 -!- copumpkin has quit (Ping timeout: 256 seconds).
21:17:01 <Dulnes> i dont use firefox? and why do you need to know
21:17:16 <int-e> I'm honestly wondering whether it's supposed to look like that, according to the CSS specification.
21:17:42 <Dulnes> it does it on some chrome sites
21:18:05 <Dulnes> Firefox just overlaps based on Font style
21:18:22 <Dulnes> and kinda pushes it together
21:18:47 <Dulnes> So i guess? idk ask someone else i use noscript
21:19:04 <int-e> Ah but did you look at the source? The question is about the meaning of the relative line-height, 100%.
21:20:24 <Dulnes> Also newsham that will be very useful
21:20:28 -!- b_jonas has joined.
21:22:00 <Dulnes> Ask taneb or someone im going to bed
21:22:45 <int-e> Good night, Dulnes
21:22:51 <elliott> int-e: fwiw they overlap in my browser (chrome) too, but I suspect you know that
21:22:58 <vanila> it looks the same on chromium
21:23:46 <int-e> elliott: no, I only have this one browser on this computer. (and links, which won't exhibit this particular effect)
21:25:20 <int-e> I also haven't looked at the specification yet. It's quite possible that this is correct (though I have my doubts that it was intended.)
21:29:41 <int-e> uh, brx' solution will take a while to decipher...
21:29:48 <Dulnes> actually i might stay to help int-e
21:30:05 <Dulnes> waits for phone to die
21:30:24 <int-e> Dulnes: it's not important
21:30:32 <Dulnes> Use palemoon and see if it doesnt overlap
21:31:35 <elliott> compiler flags are not going to change firefox's layouting engine
21:33:17 <int-e> I can explain why the lines overlap easily -- the browser is inheriting the line-height as an absolute length, so we're rendering a 30pt font with a line height derived from a 10pt one.
21:33:38 <int-e> Dulnes: sleep seems more important to me
21:42:37 <int-e> okay... I got the gist of it. grep/1/&/2/&/3/&/4/,9..$$ computes permutations of 1..4. Then it's actually using 'eval' to evaluate expressions. And it has 14 expression shapes that it tries in a specified order ... fun.
21:43:06 <int-e> (This is brx' solution to Make 24 on anagol)
21:47:14 <int-e> and it doesn't work in my perl...
21:47:36 <int-e> (needs one more space)
21:50:20 <int-e> oh and I guess it needs $$ to be between 4321 and 9999.
21:55:50 -!- NATT_SiM has quit (Remote host closed the connection).
21:59:19 -!- NATT_SiM has joined.
22:10:51 <fizzie> Oh, Make 24 timed out?
22:16:38 -!- reynir has changed nick to reynur.
22:23:39 -!- augur has joined.
22:24:35 -!- augur has quit (Read error: Connection reset by peer).
22:24:44 -!- augur has joined.
22:28:54 <vanila> The shorted lambda term that no one knows if halts or not is probably collatz conjecture
22:29:09 <vanila> at least labmda function from church nat to church nat
22:29:27 <vanila> I do not know of closed lambda term whose halting is hard to decide
22:31:51 <vanila> I was just thinking 3x+1 and halving is quite easy and short with church numerals
22:31:54 <tromp_> i dont see how collatz translates to a (non)halting term
22:31:57 <vanila> and then you just have to loop it
22:32:11 <vanila> well w ecan't be sure yet that the lambda term halts on all church nat inputs
22:32:20 <vanila> when considered as a function N -> N
22:32:40 <tromp_> collatz conjecture is a forall exists statement
22:32:49 -!- NATT_SiM has quit (Remote host closed the connection).
22:33:08 <vanila> you just run the collatz 'step' function in a loop until you hit 1
22:33:27 <tromp_> goldbach is a single lambda term
22:33:31 <Jafet> The term that halts if and only if it can find an even integer > 2 not the sum of two primes
22:33:45 <vanila> you need primality checking for that so I think it would be longer
22:33:47 <elliott> you can write a program to search for collatz counterexamples
22:33:56 <elliott> it'll be shorter than goldbach
22:34:22 <Jafet> They would need to be periodic counterexamples
22:34:50 <vanila> goldbach will probbably be resolved before collatz
22:34:53 -!- NATT_SiM has joined.
22:35:01 <vanila> people are getting really good results on prime gaps
22:35:10 <Jafet> itt: an integer for which collatz termination is unprovable
22:35:21 <tromp_> no, elliot, collatz doesnt have finite refutation
22:35:41 <Jafet> Nonexistence of periodic collatz is refutable
22:35:45 <elliott> I was proposing a special case
22:35:50 <tromp_> and goldbach is quite small
22:36:23 -!- NATT_SiM_ has joined.
22:36:32 -!- NATT_SiM has quit (Read error: Connection reset by peer).
22:36:38 -!- NATT_SiM_ has quit (Remote host closed the connection).
22:37:24 <tromp_> existence of nontrivial collatz periods is certainly less interesting than goldbach
22:40:30 <tromp_> elliot, can you code a collatz period finder in 284 bits?
22:41:12 <elliott> it's a pretty simple recursive algorithm
22:42:03 -!- oerjan has joined.
22:42:30 <tromp_> 284 bits is not much. you have to divide by on church numerals, and search over list... it asdds up quickly
22:42:41 <elliott> https://en.wikipedia.org/wiki/Collatz_conjecture#As_an_abstract_machine_that_computes_in_base_two I like collatz-conjecture-as-halting-problem
22:42:45 <elliott> tromp_: you could do it on bit strings instead.
22:42:48 -!- reynur has changed nick to reynir.
22:43:16 <vanila> we don't need to find period??
22:43:21 <vanila> are there loops which never reach 0
22:43:28 <FreeFull> elliott: It's really easy to solve the Collatz conjecture if you've solved the halting problem
22:43:46 <FreeFull> elliott: It's easy to construct a program that halts if there is a counterexample
22:43:52 <FreeFull> Then you just feed it to your oracle :)
22:43:52 <vanila> i dont thinnk we care about cycles
22:44:30 <FreeFull> Actually, it's somewhat tricky
22:44:50 <tromp_> elliot: ok, that looks doable in 284 bits
22:44:51 <FreeFull> You actually want to use the oracle inside your program
22:45:12 <FreeFull> For each number, check if the program that computes the sequence halts
22:45:18 <vanila> what are you counting the bits of?
22:45:24 <vanila> is that that weird lambda language
22:45:28 <FreeFull> If so, continue with the next number
22:45:36 <FreeFull> Then, use the oracle on that program, to check if it halts
22:45:50 <FreeFull> If it doesn't, the collatz conjecture is true
22:46:13 <vanila> why not just count characters of a lambda calculus program or so?
22:46:37 <tromp_> because bits is the most neutral measure
22:50:10 -!- ZombieAlive has joined.
22:51:19 -!- Koen__ has joined.
22:54:03 -!- NATT_SiM has joined.
22:55:12 <oerjan> some of us seem to have become a bit addicted to code golfing
22:55:39 <vanila> im too bad at perl to golf
22:55:59 <oerjan> vanila: i golf in haskell
22:56:09 -!- shikhout has joined.
22:56:11 <oerjan> anarchy golf has a bunch of languages
22:56:29 <Bike> i golf on a fairway you sick fuckers
22:56:37 <Koen__> you should make a language where every program is 140 characters
22:56:38 <oerjan> you can even golf in several esolangs
22:56:50 <oerjan> (a number here do burlesque)
22:57:08 <Bike> 140 characters and infinite alphabet. funes the memorious
22:57:27 <Dulnes> my eyes hurt i must change the colour of my client
22:58:51 <oerjan> ah make 24's deadline has expired
22:59:17 <oerjan> i didn't try that one though, looked too arduous to do as anything other than compression, which doesn't interest me.
22:59:40 -!- shikhin has quit (Ping timeout: 264 seconds).
23:00:08 -!- NATT_SiM has quit (Remote host closed the connection).
23:01:45 -!- NATT_SiM has joined.
23:02:48 <int-e> oerjan: you can still look at the solutions. brx' is the closest to a proper one.
23:04:55 <oerjan> oh i did look at that one
23:07:35 <oerjan> i have no real idea how either works, though.
23:07:44 <int-e> Apparently I've been the only one who encoded the solutions as operator pattern and permutations.
23:09:41 <oerjan> Dulnes: http://golf.shinh.org/p.rb?Make+24
23:10:58 <int-e> oerjan: I have a function f that produces a stream of numbers 0..3; the key is this pattern: (-1FGF)>1G(>2F)<1GF)>2 <-- each F is expanded to $F[f] (and perl -a conveniently places the 4 fields of each input line in @F), and each G is replaced by $G[f], and G is the array of operators. Finally, (xx and )xx are replaced by ( if $vxx evaluates to true; $v is another number between 0 and 3. So that results in the various ways...
23:11:04 <int-e> ...of placing () and there are only 4 of those total.
23:11:37 <int-e> s/(\W)(..)/"$v$2?\$1:''"/gee does the (xx and )xx replacement; and s/(\w)/$$1[f]/g takes care of the F and G.
23:11:45 <oerjan> Dulnes: it's in theory about expressing 24 as an expression in given numbers, but it's ruined by the fact you have to get _exactly_ the same answers as listed, with no real rule for which one to choose.
23:12:28 <oerjan> so everyone who solved it has to encode the wanted answers in the program.
23:13:01 <int-e> no. brx hasn't, he's specified a search order.
23:13:23 <oerjan> and it gives the right result?
23:13:33 <int-e> (and the search isn't exhaustive)
23:13:50 <Dulnes> May i share this problem with some people
23:14:11 <oerjan> of course. the deadline is expired though, although you can still submit additional answers.
23:16:28 <oerjan> there are several currently open, see http://golf.shinh.org/
23:18:38 <int-e> oerjan: as far as I can see he's searching for the lexicographically latest permutation such that one of the following pattern (with numbers omitted) works: -*(-) -*(+) -** -*- +*(-) +*(+) +** +*- (++)* (*-)* +++ ++- /++ +-- with later ones taking priority.
23:19:14 <int-e> so it's a very restricted search but you can, for example, permute the inputs and it'll still work.
23:20:07 <oerjan> int-e: ok so he's encoded the wanted _priorities_ in an ad-hoc way rather than the answers
23:21:58 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/toroman
23:22:31 <int-e> oerjan: it's not pretty but far better than I dreamed possible.
23:22:56 <Dulnes> oerjan: btw codegolf ? thats competitive right
23:26:39 <int-e> oooh fizzie exploited the trailing whitespace, too
23:27:36 <int-e> fizzie: the thing is a bash, you could've used $[] for $(())
23:28:10 -!- `^_^v has quit (Ping timeout: 265 seconds).
23:28:35 <Dulnes> 37*6e124 * 556( 56 / 34 ) = ¿?
23:30:40 -!- Phantom_Hoover has joined.
23:31:39 <HackEgo> [wiki] [[My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41029&oldid=41027 * BCompton * (+1) /* Semantics */ Data is plural
23:36:22 <Dulnes> Whats that language that makes everything look like binary
23:37:52 <tromp_> binary lambda calculus?
23:38:05 <oerjan> Dulnes: of course, the goal is to have the shortest program (in your language, or sometimes at all)
23:39:03 <Dulnes> anylanguage? even if its one of the joke ones
23:41:33 <oerjan> sure. some of the esolangy ones are pretty good for golfing, with very short commands. others are hard to golf in, though.
23:41:55 <oerjan> as i said, burlesque is popular here.
23:42:42 <oerjan> i've submitted a few in unlambda. not very good for numbers, that.
23:42:45 <Sgeo> Does an esolang that is easier to implement a REPL for than any other mode including file interpretation sound like a thing that could be made?
23:42:51 <Sgeo> I blame FreeFull for giving me the idea
23:43:53 <oerjan> if you can think of a language where that actually _is_ easier, sure.
23:43:54 <FreeFull> You have to keep in mind, stdin is practically a file
23:44:13 <FreeFull> Maybe if you tied the output to the input
23:44:26 <FreeFull> So the user has to use the output to change their input to be suitable
23:44:33 <Dulnes> Ive had alot of short commands in python and javascript++ and C# idk if i can make "short" commands in an esolang i like to make commands long and stringy for no reason
23:44:43 <FreeFull> And you can use randomisation to make sure the output doesn't stay the same
23:44:54 <FreeFull> So you can't just feed in a file and have it work
23:46:48 <int-e> fizzie: there. 180 :)
23:47:01 * Dulnes jokingly makes it in huh?++
23:47:07 <FreeFull> I was thinking earlier, it'd be neat to have a system where you can feed in stuff like i² = j² = k² = ijk = -1; and have it automatically derive how to work with quaternions
23:48:13 <int-e> fizzie: (2 bytes from the $[]; the remaining bytes came from recompressing the data (1 byte) and then truncating the file (ok, so zcat is now somewhat unhappy, but who cares...))
23:48:45 -!- NATT_SiM has quit (Remote host closed the connection).
23:54:09 -!- NATT_SiM has joined.
23:56:27 <Dulnes> 37*6e124+*+556(+56+%2F+34+)+&cad=h = 2.032998e+129
23:59:30 -!- NATT_SiM has quit (Remote host closed the connection).
23:59:40 <Jafet> You can't make a system that takes arbitrary rewrite rules or group presentations and works out the correct normal forms
00:02:41 <Phantom_Hoover> FreeFull, what Jafet said, it's uncomputable in general
00:02:43 <Jafet> GAP and Pari/GP can work with finite structures
00:02:58 <Jafet> I don't think they accept group presentations as input though
00:03:35 <Phantom_Hoover> i'm sure it's well-behaved on some sufficiently small subset that includes the quaternions, though
00:06:34 -!- NATT_SiM has joined.
00:07:56 <FreeFull> I'm not looking for anything that's more powerful than a human
00:08:56 <Jafet> There are also equational logics that can probably decide equivalence between two given quaternions
00:18:37 <Phantom_Hoover> Jafet, i mean it's not like working out a canonical form for a given quaternion is in any way hard
00:19:04 -!- NATT_SiM has quit (Remote host closed the connection).
00:19:09 <lambdabot> ENVA 182350Z 09005KT 050V110 CAVOK M02/M03 Q1028 RMK WIND 670FT 11007KT
00:19:17 <Jafet> If you know they're quaternions, sure
00:19:26 <Phantom_Hoover> (see also http://en.wikipedia.org/wiki/Word_problem_for_groups#Examples)
00:19:47 <Jafet> If all you have is some smtlib code that happens to implement quaternions
00:19:54 <Jafet> But you don't know that yet
00:20:25 <oerjan> quaternions have the property that the additive basis is a multiplicative subgroup
00:20:37 <Dulnes> oerjan: minter cuz its cold and wtf is a wint, minter sounds better
00:20:51 <oerjan> generates one. that is finite.
00:21:25 <Phantom_Hoover> well i mean we're implicitly talking about the unit quaternion group here
00:21:42 <Dulnes> how much can lambdabot compute/solve btw lets say in the e+ range
00:22:14 <lambdabot> 3.7182818284590452353602874713526624977572
00:23:02 <Jafet> > exp 1000000 :: CReal
00:23:14 <Jafet> > exp 1000 :: CReal
00:23:15 <lambdabot> 1970071114017046993888879352243323125316937985323845789952802991385063850782...
00:24:06 <Dulnes> uh well 1 e = how many zeros come after the last digit i have. eg; 254e+9
00:24:24 <oerjan> > 10 * (exp 1 + 1) :: CReal
00:24:26 <lambdabot> 37.1828182845904523536028747135266249775725
00:24:52 <oerjan> huh CReal show only limits digits after the decimal point
00:25:16 <oerjan> (there's a function to adjust that, though)
00:25:19 <Jafet> show doesn't use scientific notation
00:25:48 <Dulnes> i meant will the bot shorten it to e
00:25:49 <Jafet> > read "1e100" :: CReal
00:25:51 <lambdabot> 1000000000000000000000000000000000000000000000000000000000000000000000000000...
00:26:10 <oerjan> Dulnes: not with any of the standard types, no. (or CReal for that matter).
00:26:42 <oerjan> it's not a computer algebra system, it's a haskell interpreter
00:26:57 <oerjan> you could write a CAS in haskell, presumably
00:27:18 <Jafet> Hmm, mathematica over irc
00:28:05 <Jafet> Mathematica's text I/O is crap though
00:28:27 -!- b_jonas has quit (Ping timeout: 258 seconds).
00:29:13 <Jafet> Well, compared to the notebook interface
00:31:27 <Dulnes> > read "3e20" :: CReal
00:32:42 <Dulnes> Also is this the original lambdabot?, ive come across alot of copies on my irc adventure
00:34:55 -!- b_jonas has joined.
00:35:04 <FireFly> Otherwise it wouldn't be named 'lambdabot' (on Freenode)
00:35:19 <int-e> What identifies a bot?
00:35:51 <int-e> Has lambdabot stopped being the original lambdabot when Cale (I think) took over from dons?
00:37:44 <Dulnes> Unless Cale changed lambdabot's code then no
00:38:07 <lambdabot> git clone git://github.com/int-e/lambdabot.git
00:38:32 <Dulnes> Also this one seems more Helpful/responsive than others
00:39:56 <oerjan> Registered : Aug 31 10:04:41 2005 (9 years, 11 weeks, 4 days, 14:34:36 ago)
00:40:17 <oerjan> that's the freenode account it's using
00:40:23 <oerjan> which is older than mine
00:40:52 <int-e> Anyway, I would agree that it's fair to call this one the original. There's a straight line from the original lambdabot on #haskell to this one.
00:41:46 <lambdabot> LOWI 190020Z AUTO 00000KT 9999 FEW005 SCT010 BKN080 04/04 Q1011
00:42:03 <lambdabot> ESSA 190020Z 06008KT CAVOK 04/03 Q1029 R01L/19//95 R01R/19//95 R08/19//95 NOSIG
00:42:07 <int-e> There's the one unofficial command.
00:42:25 <int-e> (Meaning the hackage version of lambdabot doesn't know it.)
00:42:52 <int-e> lambdabot is... undermaintained (is that a word? let's pretend it is.)
00:42:57 <Dulnes> that means its original
00:43:04 <FireFly> And it's used in approximately one channel (the command, that is)
00:43:42 <Dulnes> i could never haskell like this
00:44:03 <oerjan> hey int-e is even older. and here i keep thinking of you as nearly a newbie, which you are on #esoteric i guess.
00:44:28 <int-e> oerjan: I took a leave of absence from #esoteric
00:44:36 <oerjan> Registered : Apr 24 14:51:11 2004 (10 years, 30 weeks, 0 days, 09:51:43 ago)
00:45:02 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:45:31 -!- Koen__ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
00:46:07 <oerjan> int-e: if it were german or norwegian, asking whether the equivalent of "undermaintained" is a word would be nonsense, no? :P
00:46:31 <int-e> 2004-04-24-raw.txt:< 1082848258 ? :int-e!~noone@td9091b33.adsl.terralink.de JOIN #esoteric
00:47:38 <Dulnes> Im amazed at how long you've stayed on irc int-e
00:47:43 <oerjan> Dulnes: it's a horrible pun in the shape of romantic math hth
00:47:50 <int-e> Dulnes: screen is amazing
00:48:58 <FireFly> I've been on IRC for ten years, then, but not on Freenode (was it even Freenode back then?)
00:48:59 <int-e> It's just simple arithmetic.
00:49:43 <Dulnes> Im only 27 and havent used irc in this entire time
00:50:13 <oerjan> int-e: you never know with date and time.
00:50:31 <oerjan> suddenly they skip a couple weeks for silly reasons
00:51:01 <int-e> But! Easter celebration is a serious matter.
00:51:22 <FireFly> That reminds me of the Swedish calendar, which I learned about the other day
00:51:55 <FireFly> Apparently we had the silliest idea for transitioning to the Gregorian calendar of all countries
00:52:04 <oerjan> talk about backpedalling
00:53:49 <Dulnes> i was 17 when int-e started irc
00:55:28 -!- b_jonas has quit (Ping timeout: 264 seconds).
00:55:42 <int-e> oerjan: Ok, so basically I was on #esoteric for some time in 2005 and 2006, then disappeared for almost 7 years.
00:56:25 <FireFly> HackEgo doesn't have access to logs anymore, does it?
00:56:37 <FireFly> Though those probably didn't go that far back anyway
00:57:55 <Dulnes> send me a.link to the logs
00:57:59 <oerjan> i thought HackEgo had downloaded some older ones from tunes or the like
00:58:07 <oerjan> Dulnes: it's in the topic
00:58:10 <HackEgo> :-( \ 113500 \ a.out \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dc \ dir \ dog \ etc \ factor \ faith \ head \ hej \ hello \ hello.c \ ibin \ index.html?dl=1812 \ interps \ lib \ paste \ pref \ prefs \ py.py \ quines \ quotes \ script.py \ share \ src \ test.c \ Wierd \ wisdom \ wisdom.pdf \ you
00:58:28 <oerjan> FireFly: i think the logs show up better on google now than they used to, though.
00:58:55 <int-e> `` ls -la complaints
00:58:55 <HackEgo> lrwxrwxrwx 1 5000 0 9 Sep 12 13:29 complaints -> /dev/null
00:59:08 <int-e> `` cat bin/complain
00:59:09 <HackEgo> print_args_or_input "$@" >> complaints; echo Complaint filed. Thank you.
00:59:47 <int-e> I love this one. It must've been inspired by the BOFH.
01:00:13 <HackEgo> rm: cannot remove `hej you': No such file or directory
01:01:07 <HackEgo> <!DOCTYPE html> \ <html lang="en" dir="ltr" class="client-nojs"> \ <head> \ <title>Wierd - Esolang</title> \ <meta charset="UTF-8" /> \ <meta name="generator" content="MediaWiki 1.20.4" /> \ <link rel="alternate" type="application/x-wiki" title="Edit" href="/w/index.php?title=Wierd&action=edit" /> \ <link rel="edit" title="Edit" href="/w/ind
01:01:18 <FireFly> https://www.google.com/search?q=site:codu.org+inurl:2008+FireFly I suppose I never joined in the 2008 then
01:01:27 <FireFly> (which was when I first found the wiki)
01:01:39 <oerjan> i've noticed a nick i don't really know doing HackEgo tests in private, i think those two files are from there
01:02:08 -!- b_jonas has joined.
01:02:42 <HackEgo> >++++++++++++++++++++++++++++++++++++++[--------------------------------------<[->>+<<]>[-<+>]>[-<+>]<>++++++++++<[->>>+<<<]>>>[<<[<+>>+<-]>[<+>-]>-]<<[-]<[-<+>]<>,----------]<>>+<<[->><[->>+<<]>[-<+>]>[-<+>]<<[->>+>+<<<]>>>[-<<<+>>>]<[-<+>]<<<]>>>>++++++++++<<[->+>-[>+>>]>[+[-<+>]>+>>]<<<<<<]>>[-]>>>++++++++++<[->-[>+>>]>[+[-<+>]>+>>]<<<<<]>[-]
01:02:58 <FireFly> `` ibin/brainfuck <index.html*
01:02:59 <HackEgo> bash: ibin/brainfuck: No such file or directory
01:03:18 <HackEgo> #!/bin/sh \ . lib/interp \ \ # Get the bitwidth from the command \ BW=`echo "$CMD" | sed 's/bf//'` \ if [ "$BW" = "" ] ; then BW=8 ; fi \ \ interp_file ./interps/egobf/src/egobfi$BW
01:03:46 <oerjan> `` \! bf <<<index.html
01:04:00 <oerjan> hm i guess maybe it doesn't do anything
01:04:13 <oerjan> well there's a , and no . in what's showing
01:04:20 <FireFly> the file is called.. somtehing weird
01:04:51 <FireFly> `` grep -o \\\. index.html*
01:05:42 <int-e> `` echo abcde | ./interps/egobf/src/egobfi8 index.html*
01:05:46 <Dulnes> im looking through these logs
01:05:55 <int-e> `` echo abcdf | ./interps/egobf/src/egobfi8 index.html*
01:06:07 <Dulnes> you guys had alot of fun
01:06:56 <int-e> oerjan: it does something :)
01:07:51 -!- adu has joined.
01:08:41 <int-e> "alot" indicates too small an allottment of space
01:10:24 <int-e> s/ott/ot/ Spelling is hard.
01:12:09 -!- NATT_SiM has joined.
01:13:20 -!- NATT_SiM has quit (Remote host closed the connection).
01:14:21 <FireFly> `` echo a | ./interps/egobf/src/egobfi8 index.html*
01:14:25 <FireFly> `` echo aa | ./interps/egobf/src/egobfi8 index.html*
01:15:22 <FireFly> Looks like the char-code plus the index of the character?
01:15:56 <int-e> `` echo aaa | ./interps/egobf/src/egobfi8 index.html*
01:16:03 <int-e> `` echo aaaa | ./interps/egobf/src/egobfi8 index.html*
01:17:34 <FireFly> `` echo -e '\0\0' | ./interps/egobf/src/egobfi8 index.html*
01:18:28 <int-e> `` echo 1 | ./interps/egobf/src/egobfi8 index.html*
01:18:32 <int-e> `` echo 01 | ./interps/egobf/src/egobfi8 index.html*
01:18:36 <int-e> `` echo 2 | ./interps/egobf/src/egobfi8 index.html*
01:18:39 <int-e> `` echo 3 | ./interps/egobf/src/egobfi8 index.html*
01:18:42 <int-e> `` echo 4 | ./interps/egobf/src/egobfi8 index.html*
01:18:46 <int-e> `` echo 5 | ./interps/egobf/src/egobfi8 index.html*
01:18:51 <int-e> I see a pattern there.
01:19:13 <FireFly> `` echo -e '20' | ./interps/egobf/src/egobfi8 index.html*
01:19:51 <int-e> > let f = 0 : scanl (+) 1 f in f!!20 `mod` 256
01:20:22 <int-e> > let f = 0 : scanl (+) 1 f in f!!5 `mod` 256
01:20:27 <int-e> > let f = 0 : scanl (+) 1 f in f!!21 `mod` 256
01:20:36 <FireFly> `` for i in $(seq 15); do ./interps/egobf/src/egobfi8 index.html* <<<$i; done
01:20:36 <HackEgo> 12358132134558914423312198219
01:20:53 <FireFly> `` for i in $(seq 15); do ./interps/egobf/src/egobfi8 index.html* <<<$i; echo; done
01:20:53 <HackEgo> 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 121 \ 98 \ 219
01:21:36 <int-e> `` echo 257 | ./interps/egobf/src/egobfi8 index.html*
01:22:01 <HackEgo> :-( \ 113500 \ a.out \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dc \ dir \ dog \ etc \ factor \ faith \ head \ hello \ hello.c \ ibin \ index.html?dl=1812 \ interps \ lib \ paste \ pref \ prefs \ py.py \ quines \ quotes \ script.py \ share \ src \ test.c \ Wierd \ wisdom \ wisdom.pdf
01:22:34 <HackEgo> --[------->++<]>-.[->+++<]>.+++++.-----------.+++++++++.+++++++++.+[->+++<]>++.+.--[--->+<]>-.--[->++<]>.--[->++<]>-.+.++[->+++<]>++.+++++.++++++.[->+++++<]>+++.+[--->+<]>+++.++[->+++<]>.>++++++++++.-[->++++<]>-.[->+++<]>.+++++.-----------.+++++++++.+++++++++.+[->+++<]>++.+.--[--->+<]>-.--[->++<]>.--[->++<]>-.+.++[->+++<]>++.+++++.+++++.++++++.[
01:22:48 <HackEgo> ls: invalid option -- ' ' \ Try `ls --help' for more information.
01:22:51 <HackEgo> -rw-r--r-- 1 5000 0 2316 Oct 31 00:50 113500
01:23:18 <FireFly> `` grep -r '[+-><.]{10}' .
01:23:44 <oerjan> int-e: that was an lpaste i fetched 2 weeks ago
01:23:47 <FireFly> Hm, should've used --only-filename
01:25:18 <FireFly> `` grep -EHo -r '[-+><.]{10}' .
01:25:38 <oerjan> and i also fetched the index.html* thing 4 weeks ago
01:25:49 <HackEgo> ./prefs:++++++++++ \ ./prefs:>+++++>++> \ ./prefs:++++++++>+ \ ./prefs:+++++++<<< \ ./prefs:>----.>>>- \ ./prefs:.<++++.<++ \ ./prefs:++.>>+.++. \ ./prefs:<<<+++++++ \ ./prefs:++++++++++ \ ./prefs:++++++++++ \ ./prefs:++++++++.+ \ ./prefs:.>>>------ \ ./prefs:---.<++++. \ ./prefs:>----.<--- \ ./prefs:--.<++++++ \ ./prefs:++++++++++ \ ./prefs:+++
01:26:12 <FireFly> `` grep -EHo -r '[-+><.]{10}' . | cut -d: -f1 | uniq
01:26:35 <oerjan> basically the weird filenames is because they're generated from urls.
01:28:29 -!- vanila has quit (Quit: Leaving).
01:28:49 <oerjan> `` grep -EHo -r '[-+><.]{10}' . | cut -d: -f1
01:29:20 <HackEgo> ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs \ ./prefs
01:29:45 <oerjan> `` grep -EHo -r '[-+><.]{10}' . | cut -d: -f1 | uniq
01:29:54 <int-e> oh come on, use grep -l
01:30:20 <FireFly> Oh, *that* is what it's called
01:30:31 <oerjan> is it just timing out?
01:30:34 <FireFly> I searched the manpages but couldn't find it
01:31:02 <int-e> FireFly: searching for -l works just fine ;-)
01:31:25 <FireFly> Right, but searching for "only" (as in --only-matching") doesn't
01:31:35 <FireFly> I expected --only-filename or some such
01:32:00 <FireFly> ``grep -Elr '[-+><.]{10}' . | uniq
01:32:01 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `grep: not found
01:32:05 <FireFly> `` grep -Elr '[-+><.]{10}' . | uniq
01:32:14 <int-e> hmm, it's --files-with-matches ... I don't think I'll try and remember that.
01:32:15 <HackEgo> ./prefs \ ./bin/emmental \ ./bin/macro \ ./bin/searchlog \ ./share/lua/5.2/luarocks/fs/lua.lua \ ./pref \ ./index.html?dl=1812 \ ./src/ploki/try/poly.poly \ ./src/emmental.hs \ ./113500 \ ./paste/paste.10124 \ ./paste/paste.31138 \ ./paste/paste.27038 \ ./paste/paste.30032 \ ./paste/paste.29969 \ ./paste/paste.24049 \ ./paste/paste.30902 \ ./pas
01:32:34 <int-e> but you don't need the -uniq either
01:32:55 -!- NATT_SiM has joined.
01:33:03 <FireFly> That makes sense, I didn't think that through
01:33:39 <FireFly> oh, right, some of those are probably --------- comments
01:39:22 -!- copumpkin has joined.
01:41:22 * int-e found the answer to http://int-e.eu/~bf3/tmp/test.html ; it was rendered correctly. (I've added a link to the CSS specification there.)
01:45:57 <HackEgo> [wiki] [[Talk:Malbolge]] M http://esolangs.org/w/index.php?diff=41030&oldid=41020 * Oerjan * (+46) It doesn't count as signed without timestamp hth
01:46:14 -!- NATT_SiM has quit (Remote host closed the connection).
01:51:34 -!- NATT_SiM has joined.
01:52:46 <HackEgo> [wiki] [[Talk:My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41031&oldid=41028 * Oerjan * (+145) ...or a nick. Or either. Or both.
01:56:14 <HackEgo> [wiki] [[User talk:Oerjan]] http://esolangs.org/w/index.php?diff=41032&oldid=39074 * 213.162.68.152 * (+87) What about signatures without comments, I wonder?
01:57:00 -!- NATT_SiM has quit (Ping timeout: 258 seconds).
02:00:22 <HackEgo> [wiki] [[User talk:Oerjan]] http://esolangs.org/w/index.php?diff=41033&oldid=41032 * Oerjan * (+107) AAAAAAAAAAAAAA!!!!
02:01:06 <HackEgo> [wiki] [[AAAAAAAAAAAAAA!!!!]] M http://esolangs.org/w/index.php?diff=41034&oldid=40307 * Oerjan * (+6) AAAAAAAAAAAAAA!!!!
02:02:32 -!- NATT_SiM has joined.
02:09:16 <oerjan> hmph haskell.org is giving me a cloudflare error page
02:11:32 <int-e> hmm. "You can follow the progress on #haskell-infrastructure on Freenode"
02:19:32 -!- NATT_SiM has quit (Remote host closed the connection).
02:20:11 -!- adu has quit (Quit: adu).
02:27:40 -!- adu has joined.
02:27:41 -!- adu has quit (Client Quit).
02:28:06 <Dulnes> hmm whats wrong with haskell.org
02:28:18 <oerjan> Dulnes: maintenance apparently
02:28:25 -!- adu has joined.
02:30:46 <int-e> unscheduled RAID disk failure
02:34:29 <int-e> http://www.mail-archive.com/haskell@haskell.org/msg25054.html
02:34:49 <int-e> (of course the mailman archive is down, too...)
02:36:20 <Dulnes> how the fuck did it lose its raid disk
02:36:21 <int-e> because of tuesday
02:37:14 <int-e> ok, that was weak, let me check with BOfH
02:38:13 <int-e> "MAGNETS! Wrap your disks up in a pillow case with lots of magnets - Solar Flares hate that."
02:38:18 <int-e> That would explain it.
02:39:56 <Dulnes> there was a solar flare?
02:40:31 <int-e> http://bofh.ntk.net/BOFH/0000/bastard06.php
02:49:54 <Dulnes> doesnt answer that question
02:56:26 <int-e> oh perhaps you wanted http://www.tesis.lebedev.ru/en/sun_flares.html?m=11&d=17&y=2014
03:53:42 -!- adu has quit (Quit: adu).
04:03:59 * Dulnes stabs chat to see if it died
04:04:33 -!- variable has quit (Remote host closed the connection).
04:11:56 -!- digitalcold has quit (Ping timeout: 272 seconds).
04:12:41 -!- digitalcold has joined.
04:19:18 -!- NATT_SiM has joined.
04:20:25 <MDude> I should work on making things, but what?
04:27:25 <HackEgo> [wiki] [[Karma]] http://esolangs.org/w/index.php?diff=41035&oldid=38299 * 128.62.56.69 * (+5) /* Examples */
04:46:47 -!- variable has joined.
04:56:54 -!- shikhin has joined.
05:00:17 -!- shikhout has quit (Ping timeout: 255 seconds).
05:19:16 -!- aloril has quit (Quit: Leaving).
05:24:26 -!- oerjan has quit (Quit: Nite).
05:24:28 -!- MDream has joined.
05:27:51 -!- MDude has quit (Ping timeout: 250 seconds).
05:33:17 -!- MDream has changed nick to MDude.
05:37:51 <Dulnes> haskell.org/ghc/ is working but still slow as shit
05:38:10 <Dulnes> also wiki is "working" barely
06:21:01 -!- Igrab has joined.
06:21:14 <HackEgo> slist: Taneb atriq Ngevd Fiora Sgeo ThatOtherPerson alot
06:22:25 <int-e> Dulnes: did you ever get that sleep you wanted?
06:27:08 -!- aloril has joined.
06:32:47 -!- Igrab has left.
06:34:56 -!- NATT_SiM has quit (Remote host closed the connection).
06:53:19 <Dulnes> https://system76.com/laptops/gazelle i must buy this
07:29:11 <Sgeo> Hey Google? This is not English, believe it or not: https://twitter.com/mothy_akuno
07:32:19 -!- Patashu has joined.
07:36:21 -!- Patashu has quit (Remote host closed the connection).
07:36:32 -!- Patashu has joined.
07:43:31 <Sgeo> Maybe there shouls be an Evillious List
07:43:36 <Sgeo> Or I should get an RSS reader
07:46:04 -!- MDude has changed nick to MDream.
07:49:11 <Sgeo> OOh Factor 0.97 is out
07:50:47 <Sgeo> Factor can talk to Python now
08:34:47 <mroman> !blsq ,#Q2 SH ~- ",#Q" \/ .+ sh
08:34:47 <blsqbot> | ,#Q2 SH ~- ",#Q" \/ .+ sh
08:35:19 <mroman> (a *real* quine in Burlesque)
08:46:08 <blsqbot> | 9999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999
08:47:15 <blsqbot> | Ain't nobody got time fo' dat!
08:48:22 <mroman> I just rediscovered @ can do that
08:48:38 <blsqbot> | ERROR: Unknown command: (.5)!
08:49:43 <blsqbot> | ERROR: (line 1, column 1):
08:49:43 <blsqbot> | expecting "\"", "-", digit, "'" or "["
08:51:34 <HackEgo> mroman is a leading artist in password security (SFW). He also likes black madness. He can design password hashes that are worse than the identity function.
08:52:09 <mroman> `learn_append mroman He invented the identity function.
08:52:11 <HackEgo> Learned 'mroman': mroman is a leading artist in password security (SFW). He also likes black madness. He can design password hashes that are worse than the identity function. He invented the identity function.
08:54:03 <HackEgo> identity function? ¯\(°_o)/¯
08:54:34 <mroman> shachaf: Perhaps you meant indentity function
08:58:24 <mroman> `ls wisdom just screwed up my terminal
08:58:31 <mroman> with some formating codes and what not
09:01:31 <HackEgo> indentity function is the function that measures how indented source code is.
09:02:07 <shachaf> That's not the thing HackEgo says you invented, though.
09:05:33 <mroman> I didn't invent the indentity function
09:34:57 -!- Phantom_Hoover has joined.
09:41:36 -!- MoALTz has joined.
10:11:59 <HackEgo> The identity function is a mockingbird.
10:13:05 <mroman> @tell oerjan learn should probably warn if you are about to overwrite an existing entry.
10:20:55 <shachaf> oerjan: Would you be happier if slashlearn was //-separated?
10:32:18 <shachaf> `` sed -i -e '3a [ -e wisdom/"$topic" ] && op='\''Overwrote'\'' || op='\''Wrote'\''' -e 's/Learned/$op/' bin/slashlearn
10:34:32 <shachaf> `slashlearn identity function/The identity function is an identity bird.
10:34:34 <HackEgo> Overwrote «identity function»
10:34:40 <shachaf> `rm wisdom/identity\ function
10:34:41 <HackEgo> rm: cannot remove `wisdom/identity\\ function': No such file or directory
10:34:48 <shachaf> `rm wisdom/identity function
10:35:03 <shachaf> `slashlearn identity function/The identity function is a mockingbird.
10:35:05 <HackEgo> Overwrote «identity function»
10:37:34 <HackEgo> #!/bin/bash \ topic=$(echo "$1" | lowercase | cut -d / -f 1) \ [ -z "$topic" ] && exit 1 \ [ -e wisdom/"$topic" ] && op='Overwrote' || op='Wrote' \ value=$(echo "$1" | cut -d / -f 2-) \ echo "$value" > wisdom/"$topic" && echo "$op «$topic»"
10:39:02 <shachaf> `rm wisdom/identity function
10:39:14 <shachaf> `` [ -e wisdom/'identity function' ] && echo a || echo b
10:39:30 <shachaf> `slashlearn identity function/The identity function is a mockingbird.
10:39:31 <HackEgo> Overwrote «identity function»
10:39:38 <shachaf> I must be missing something obvious.
10:40:36 <shachaf> `rm wisdom/identity function
10:41:43 <shachaf> `` topic=$(echo "identity function/The identity function is a mockingbird." | lowercase | cut -d / -f 1); echo "$topic"; [ -e wisdom/"$topic" ] && echo a || echo b
10:44:11 <fizzie> I couldn't think of anything else than «op='Overwrote'» being a non-success, but that should not (and does not seem to) be the case.
10:44:43 <shachaf> I was thinking maybe $topic is somehow an empty string there and it's checking the existence of wisdom/
10:44:50 <shachaf> But it looks like that's not it?
10:45:24 <fizzie> It's not an empty string when echoed at the end. I don't know.
10:46:11 <shachaf> `` (cat bin/slashlearn | head -n-1; echo 'echo $op') > /tmp/foo; chmod +x /tmp/foo; /tmp/foo 'identity function/blah'
10:46:41 <shachaf> `` slashlearn 'identity function/blah'
10:46:43 <HackEgo> Overwrote «identity function»
10:46:57 <shachaf> `rm wisdom/identity function
10:47:05 <shachaf> I should do it in one go so it doesn't change hg history.
10:48:05 <fizzie> `` (cat bin/slashlearn | head -n-1; echo 'echo $op') > /tmp/foo; chmod +x /tmp/foo; /tmp/foo 'identity function/blah'; rm /wisdom/'identity function'; slashlearn 'identity function/blah'; rm /wisdom/'identity function'
10:48:07 <HackEgo> Overwrote \ rm: cannot remove `/wisdom/identity function': No such file or directory \ Overwrote «identity function» \ rm: cannot remove `/wisdom/identity function': No such file or directory
10:48:32 <shachaf> `` (cat bin/slashlearn | head -n-1; echo 'echo $op'; tail -n1 bin/slashlearn) > /tmp/foo; chmod +x /tmp/foo; /tmp/foo 'identity function/blah'; rm -f wisdom/'identity function'
10:48:32 <HackEgo> Wrote \ Wrote «identity function»
10:48:50 <shachaf> Er, wait, I think I interfered with your thing.
10:49:35 <fizzie> Oh, I kept writing /wisdom.
10:50:14 <shachaf> `` rm -f wisdom/'identity function'; (cat bin/slashlearn | head -n-1; echo 'echo $op'; tail -n1 bin/slashlearn) > /tmp/foo; chmod +x /tmp/foo; /tmp/foo 'identity function/blah'; rm -f wisdom/'identity function'
10:50:15 <HackEgo> Wrote \ Wrote «identity function»
10:50:32 <shachaf> `` rm -f wisdom/'identity function'; slashlearn 'identity function/blah'; rm -f wisdom/'identity function'
10:50:52 <shachaf> `` slashlearn 'identity function/blah'; rm -f wisdom/'identity function'
10:51:00 <fizzie> Well, that's all quite correct.
10:51:44 <fizzie> `slashlearn identity function/just verifying
10:51:45 <HackEgo> Overwrote «identity function»
10:51:54 <fizzie> Yeah, you hit a snag that's very cleverly hidden.
10:52:14 <fizzie> Or at least I believe it's that.
10:52:32 <shachaf> Oh, it's nondeterministic.
10:52:55 <fizzie> It's executed twice, is the thing.
10:53:09 <fizzie> When the script makes modifications to the repository, it involves rerunning the command.
10:54:17 <fizzie> I wrote a concise explanation about this (and a convoluted example), but I've partially forgotten the details.
10:54:27 <fizzie> I'll see if I can find it and/or remind myself.
10:56:36 -!- shikhout has joined.
10:56:43 <fizzie> Right. So it runs things in general with no locking, but when it detects a modification, it obtains an exclusive lock, and reruns the command.
10:57:04 <shachaf> Not on a pristine repository?
10:57:17 <fizzie> No. It updates the checked-out copy, but doesn't "reset" it.
10:57:25 <fizzie> Arguably, it perhaps should do that.
10:57:37 <shachaf> Not a difficult argument to make.
10:57:59 <shachaf> I guess one thing to do would be to write a status file the first time the command runs and then delete it the second time.
10:58:16 <fizzie> Or, well, to be more exact, it cleans up the repository part.
10:58:19 <shachaf> Of course you could run into locking issues that way.
10:58:27 <shachaf> Right, but it should start fresh.
10:59:11 <fizzie> It does a hg status -umad and tries to remove all those files.
10:59:49 <fizzie> In fact, I'm not sure why that's not sufficient to make slashlearn work, since it should report the new "wisdom/identity function" as modified, and remove that.
10:59:49 -!- shikhin has quit (Ping timeout: 265 seconds).
11:00:05 <fizzie> At any rate, I would hesitate a guess that it's related to this double-execution somehow.
11:01:03 <fizzie> If I read that right, it will have problems with file names with spaces in them when cleaning up.
11:01:25 <fizzie> f = sline.split(" ")[1] where sline is the hg status output.
11:01:57 <elliott> fizzie: I think that is maybe my code :/
11:02:07 <elliott> hopefully gregor actually rewrote it so it's not my fault
11:02:42 <elliott> I do remember writing hg status -umad.
11:02:49 <elliott> it was too perfect that those were exactly the options I needed.
11:03:11 <fizzie> elliott: I can't ever remember the URL for the web-browsable repository for the bot sources itself, so I was just reading it directly.
11:03:14 <fizzie> It's somewhere, though.
11:04:22 <fizzie> http://codu.org/projects/hackbot/hg/index.cgi/file/tip/multibot_cmds/PRIVMSG/tr_60.cmd
11:04:40 <fizzie> Wait, that's different.
11:05:42 <fizzie> Must be an old version.
11:06:22 <fizzie> http://sprunge.us/UjDb?py is anyway the current code.
11:07:00 <elliott> okay this looks like maybe gregor rewrote it based on what I wrote
11:07:07 <fizzie> I'm thinking a least-amount-of-changes fix would be s/sline.split(" ")/sline.split(" ", 1)/
11:09:54 <HackEgo> #!/bin/bash \ topic=$(echo "$1" | lowercase | cut -d / -f 1) \ [ -z "$topic" ] && exit 1 \ value=$(echo "$1" | cut -d / -f 2-) \ echo "$value" > wisdom/"$topic" && echo "Learned «$topic»"
11:11:18 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
11:11:19 <shachaf> Bah, cut with a multi-character delimiter doesn't work.
11:11:33 <fizzie> shachaf: Aw, you missed a great chance to work around the issue by having the first iteration communicate with the second one via /tmp (also not cleaned).
11:12:02 <shachaf> fizzie: Yes, I suggested that earlier.
11:12:12 <shachaf> But you run into locking issues that way.
11:12:13 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41036&oldid=41017 * TomPN * (-58)
11:12:32 <HackEgo> [wiki] [[Talk:Dimensions]] http://esolangs.org/w/index.php?diff=41037&oldid=41018 * TomPN * (-398)
11:13:43 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41038&oldid=41036 * TomPN * (+142) /* Example programs */
11:15:28 <fizzie> Scratch that, /tmp is in fact cleared, I was just reading it wrong. The only way you can pass information from the first run to the second is via /hackenv/. Though you could still write a status file with a space in the file name.
11:15:38 <fizzie> On the other hand, I could just go ahead and fix that part.
11:15:59 <elliott> fizzie: y'know, the hg repo for hackego is on bitbucket
11:16:26 <fizzie> And it was in fact my browser history.
11:17:01 <fizzie> https://bitbucket.org/GregorR/hackbot/src/tip/multibot_cmds/PRIVMSG/tr_60.cmd?at=default seems current.
11:17:26 <fizzie> I could make a bull request or suggest a patch or whatever one does on bitbucket.
11:17:44 <shachaf> make a bull request to the stock market
11:18:13 <elliott> is Lymia really still on HackEgo's ignore list -_-
11:18:32 <elliott> anyway, this actually is based on my horrible code, woo
11:19:52 <fizzie> I'm pretty sure I had a bitbucket account, but I don't know what it is.
11:21:30 -!- boily has joined.
11:22:08 <fizzie> Oh, "fizzie". How inventive.
11:25:34 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41039&oldid=41008 * TomPN * (+777) /* Syntax */
11:27:58 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41040&oldid=41039 * TomPN * (+54)
11:29:19 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41041&oldid=41040 * TomPN * (+0) /* 1 qubit transformations */
11:29:31 <fizzie> And 'hg status' will indeed output it verbatim with no escaping.
11:29:34 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41042&oldid=41041 * TomPN * (+0) /* 2 qubit transformations */
11:29:45 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41043&oldid=41042 * TomPN * (+0) /* 3 qubit transformations */
11:30:01 <elliott> -0 --print0 end filenames with NUL, for use with xargs
11:32:02 <shachaf> If you're fixing it you might as well do that.
11:32:07 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41044&oldid=41043 * TomPN * (+262) /* Output */
11:32:21 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41045&oldid=41044 * TomPN * (+1) /* Loops */
11:32:59 <shachaf> `` touch hmm; touch $'hmm\n? hello'
11:33:03 <fizzie> I added a comment about it at https://bitbucket.org/GregorR/hackbot/pull-request/3/fix-repository-cleanup-wrt-spaces-in-paths/diff -- that's as far as I'll go for the moment.
11:34:29 <fizzie> There's also -n --no-status hide status prefix which might simplify things.
11:35:19 <fizzie> I'm not sure which one is better, "U no mad" or "U mad now?"
11:35:27 <shachaf> Something can be worked out. -b isn't an option to hg status, anyway.
11:35:33 <shachaf> I was thinking of "nomad".
11:36:41 <elliott> -n0umad is the most obnoxious one.
11:37:18 <shachaf> I think the correct solution is to run it in an entirely clean environment.
11:39:07 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41046&oldid=41045 * TomPN * (+295) /* Syntax */
11:49:38 <fizzie> I think the reason it doesn't do that is due to EgoBot architecture -- multibot_cmds/PRIVMSG/tr_60.cmd (the handler for `) isn't supposed to be so tightly coupled to the repository checkout/removal process, which happens in some place I can't even locate. (Granted, the whole hg status + cleanup + up dance inside is already there, so.)
11:54:00 <fizzie> In fact, as far as I can tell, there's actually just the one shared checked-out copy, and not separate ones like I assumed.
12:00:20 <HackEgo> The identity function is a mockingbird.
12:04:43 <elliott> fizzie: yes, checkout would probably add a lot of overhead
12:06:53 <shachaf> What is the simplest way to make slashlearn split on // rather than on /?
12:10:03 <fizzie> awk comes to mind, though I don't remember if it has a nice shorthand for cut "2-" equivalent.
12:11:42 <fizzie> Seems not to be the case.
12:14:32 -!- Patashu has quit (Ping timeout: 255 seconds).
12:15:13 <fizzie> `run echo 'foo bar//baz quux//zuul' | perl -naF"'//'" -e 'print join("//", @F[1..$#F]);' # and there's this but I hesitate to call it simple, let alone "simplest"
12:18:12 <shachaf> Probably simplest to give up on bash and just use some other language.
12:18:32 <fizzie> Oh, you could also use bash itself for the splitting.
12:19:23 <fizzie> ${foo%%//*} and ${foo#*//}.
12:19:56 -!- heroux has quit (Ping timeout: 255 seconds).
12:20:11 <fizzie> `run topic="foo bar//baz quux//zuul"; echo "[${topic%%//*}] [${topic#*//}]" # that's quite simple
12:20:13 <HackEgo> [foo bar] [baz quux//zuul]
12:20:45 -!- heroux has joined.
12:20:52 <shachaf> maybe one day i'll know all these bash things
12:20:55 <shachaf> or at least know that they exist
12:23:17 <Taneb> Hey, remember a few months/years back someone was gonna write an article on esolangs for Washington Post or something?
12:23:23 <fizzie> I can only remember that they exist, but never (a) which one of #/% removes a prefix/suffix and (b) which one of #/## (resp. %/%%) is the shortest-matching/longest-matching. Though I guess for (b) a reasonable mnemonic would be that ## is longer than #.
12:23:35 <fizzie> I think it was some other newspaper.
12:23:49 <Taneb> Did anything ever come of that?
12:23:52 <elliott> the dude basically said he couldn't make a good article out of it :p
12:24:03 <Taneb> Ahahahaha, makes sense
12:24:12 <elliott> which is understandable since cpressey was pretty close to trolling him the entire time and the rest of us are boring weirdos
12:25:10 <Taneb> I can agree with that
12:25:43 <Taneb> The other day I spent a lecture writing a factorial function in GHC's type system.
12:25:44 -!- boily has quit (Quit: UNCOMMON CHICKEN).
12:25:55 <Taneb> And then when I got home I vastly improved it
12:26:13 <int-e> I trust you were not the lecturer?
12:26:27 <int-e> Or should I say, hope...
12:27:37 <Taneb> Still got a few years yet at least before that could be the case
12:27:58 <Taneb> As in, I'm a lowly undergrad right now
12:30:20 <int-e> oh just over 3 hours until I find out how the Python people saved that one last character...
12:30:40 <int-e> (I have a 68 character version of "Wow" on anagol)
12:33:53 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
12:40:58 -!- shikhout has changed nick to shikhin.
12:48:52 <fizzie> I wondered about that, too. Didn't have any intermediate 68B stage, personally. Have you compared symbol/alnum statistics?
12:52:35 <mroman> no List of Pink Floyd Songs by release date
12:53:00 <shachaf> Just sort https://en.wikipedia.org/wiki/List_of_songs_recorded_by_Pink_Floyd by year.
12:59:37 <mroman> maybe it wasn't pink floyd
13:08:04 <elliott> that's, uh... a difficult mixup to make
13:09:42 <Taneb> mroman, was it the one that goes na na na na na naaaa na nana na na na na?
13:16:11 <J_Arcane> #5, #4, and #2 here are quite programming relevant. http://www.cracked.com/blog/5-trivial-things-with-armies-crazy-advocates/
13:22:21 -!- ais523_ has joined.
13:25:01 <mroman> That would be easy to find
13:25:17 <mroman> it either ends in batman or "hey hey goodbye"
13:26:16 <Taneb> mroman, I was going for So What, by Pink
13:26:26 <mroman> it's are we all we are
13:32:28 -!- MoALTz has quit (Quit: Leaving).
13:35:00 <J_Arcane> https://github.com/rails/rails/issues/17671
13:35:14 -!- nortti has changed nick to lawspeaker.
13:36:45 -!- lawspeaker has changed nick to nortti.
13:54:45 <elliott> does that mean if you have a Human model rails will automatically map it to a table called humen
13:55:54 <ais523_> elliott: NetHack's pluralizer has a special case for that
14:17:31 -!- S1 has joined.
14:18:13 <elliott> nice, almost half of the debian technical committee have resigned in less than two weeks...
14:18:39 <ais523_> how does that split between the people who supported systemd, and the people who opposed it
14:19:20 <elliott> I think 1 anti-systemd (the latest, ian jackson, who raised the GR) and the other 2 nominally pro (but maybe one or both were neutral to some extent? I forget)
14:19:30 <ais523_> (incidentally, my current opinion on systemd is "it's actually a sensible and reasonable idea, but given its provenance, I don't trust it to be remotely bug-free, and it'd be nice if it were more loosely coupled to the rest of userland"
14:19:36 <elliott> there's also been one or two more non-committee devs resigning in that timespan
14:19:54 <ais523_> the TC was only 7 or 8 devs?
14:20:30 -!- S1 has quit (Client Quit).
14:20:34 <elliott> they're meant to be a last resort, AIUI
14:40:21 -!- oerjan has joined.
14:41:28 <lambdabot> mroman said 4h 28m 22s ago: learn should probably warn if you are about to overwrite an existing entry.
14:45:55 <oerjan> hasn't been barking for over a week
14:51:29 <fizzie> (Source: apartment description, "-- the one bedroom apartment comprises of Two double bedrooms, --")
14:54:10 <fizzie> No, it was an email from an accommodation provider company.
14:54:41 -!- fungot has joined.
14:54:58 <oerjan> fungot: don't run away like that :(
14:54:58 <fungot> oerjan: i just tried to get in the helpdesk.... anyone have that available? i'll take that as no
14:55:11 <fizzie> I don't know where fungot was, it hadn't "read failed"ed, but it was just stuck.
14:55:12 <fungot> fizzie: will need to have a little more facile with scheme, though. but i just found the fnord, the fnord brewing. :) archive.org is sometimes a very lonely place......
14:55:54 <oerjan> fungot: i don't think looking for fnords in archive.org is a healthy thing to do.
14:55:54 <fungot> oerjan: i'll keep that in mind. :d): http://koti.mbnet.fi/ yiap/ fnord/ fnord
14:59:14 <elliott> fizzie: is fungot going to develop a british accent?
14:59:15 <fungot> elliott: this is java 1.4, who knows. monads and stuff, instead of the force i-have)
14:59:22 <elliott> oh no, worse, ported to java
15:00:02 <oerjan> we all know that won't actually help.
15:00:57 <fizzie> Currently it has a force, I see.
15:01:18 <oerjan> fungot: are you a jedi
15:01:18 <fungot> oerjan: am i now? :d did i leave? except to wish me good night, sarahbot. foxfire would have been
15:01:30 <fizzie> "Renteln and Dundes (2005) give the following (bad) mathematical jokes about poles: -- Q: Why did the mathematician name his dog "Cauchy?" A: Because he left a residue at every pole. --" thank you, MathWorld, for reproducing these bad jokes about poles.
15:02:19 <fizzie> (Renteln, P. and Dundes, A. "Foolproof: A Sampling of Mathematical Folk Humor." Notices Amer. Math. Soc. 52, 24-34, 2005 seems to be worth a closer look, though.)
15:02:34 <oerjan> just keep the poles out of planes
15:02:39 <oerjan> or you know what happens
15:03:14 -!- Phantom_Hoover has joined.
15:07:47 <oerjan> someone is golfing in CLC-INTERCAL
15:08:30 <ais523_> it's probably a better golf language than C-INTERCAL
15:09:14 <oerjan> is %20 a regular competitor, or what you get if you don't fill in the name field
15:09:38 <elliott> %20 is a whitespace programmer
15:10:11 -!- Lorenzo64 has joined.
15:11:03 <oerjan> Wow expires in under an hour
15:20:40 -!- adu has joined.
15:56:18 -!- adu has quit (Quit: adu).
15:59:59 <int-e> oh, nasty; if you bother with ffi you can just use ffi for output as well (Python)
16:01:24 <fizzie> int-e: I had a hypothesis that that might've been the difference, but couldn't construct a 68B solution with native output, thanks to the print statement newline/whitespace adding.
16:02:05 <fizzie> int-e: What was yours like, if you don't mind sharing it?
16:03:35 <int-e> from ctypes import*;print"%c"*765%eval("CDLL('').rand()%95+32,"*765)
16:08:00 <int-e> tails' and my dc solutions are actually quite different... tails has a ring buffer and exploits that to terminate the initialisation vector without any conditional, but pays for it by a couple of O% operations.
16:08:12 -!- NATT_SiM has joined.
16:08:16 <int-e> I have a linear buffer for the hole sequence
16:08:31 <int-e> but cannot inline the printing, as far as I can see.
16:09:15 -!- vanila has joined.
16:10:08 -!- Lorenzo64 has quit (Quit: Leaving).
16:10:35 <int-e> oerjan: I hope you can derive some pleasure from the alternative Haskell solution. :)
16:12:40 <Dulnes> So imagine windows 7 set up.like windows XP with a vista theme
16:13:07 <Dulnes> but like filled to the brim with virus's and malware
16:13:20 <int-e> Dulnes: sounds ... normal?
16:14:46 <Dulnes> It auto installs malware when ever you go into the browser its probably the most attrocious thing ive ever seen
16:15:50 <int-e> well, do the right thing, throw it into the closest blast furnace
16:15:54 <elliott> is this what you have installed on your computer with one broken core
16:18:02 <ais523_> <Dulnes> It auto installs malware when ever you go into the browser its probably the most attrocious thing ive ever seen <- I'm not quite sure you understand how malware works
16:18:50 <Dulnes> Its the morning im tired
16:18:50 <ais523_> that's even /more/ unlikely
16:20:01 <Dulnes> whatever ill just fall back asleep to tired
16:27:17 -!- NATT_SiM has quit (Remote host closed the connection).
16:30:58 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
16:35:19 <fizzie> "-- in the interest of fairness and to ensure the best service for all guests limits the data download to a maximum limit of 1GB (1024MB) per day -- Broadband charges including data download exceeding 1GB (1024MB) per day - £250 per week or part of week --" wow, that's a lotta money for bytes.
16:35:44 <ais523_> this is the AWS pricing model, I think
16:35:58 <ais523_> offer a free service with low caps, and hope that people go over so that you can charge them a huge amount in overage fees
16:36:08 -!- `^_^v has joined.
16:36:37 <ais523_> one of my top priority when looking for a VPS provider was to find one that wouldn't charge for overage (but rather, would just put physical caps on the use)
16:40:13 -!- MDream has changed nick to MDude.
16:40:43 -!- drdanmaku has joined.
16:42:34 -!- NATT_SiM has joined.
16:46:34 <oerjan> what, you can do foreign imports without a pragma in haskell?
16:46:47 -!- NATT_SiM has quit (Ping timeout: 255 seconds).
16:50:24 <int-e> oerjan: part of Haskell 2010
16:50:29 <int-e> I was surprised, too.
16:51:58 <int-e> there, improved the dc solution a bit more. it's now producing trailing whitespace...
16:52:43 <int-e> which was the real trick for inlining the printing in tails' code.
16:53:05 <int-e> sadly the cute B0A is gone.
16:54:36 <int-e> anyway, I guess somebody wrote that stupid test of glibc's random number generator and felt amazed when they spotted the "Wow" substring fairly early on.
16:56:22 <ais523_> now I have an idea for an anagolf problem
16:56:31 <ais523_> compression challenge, where the output is a long hex string
16:56:35 -!- shikhout has joined.
16:56:44 <int-e> oh my ... http://golf.shinh.org/reveal.rb?Wow/PatchiKnowsWhatsUp_1415208522&py even includes a space between print and ".
16:56:49 <ais523_> that's obtained by hashing some relatively short terms (but long enough to bruteforce)
16:57:16 <ais523_> err, long enough that you can't bruteforce
16:57:22 <ais523_> then I'd win that challenge by knowing what they are
16:57:49 <int-e> yeah, no fun in that
16:58:13 <int-e> Wow was barely ok because there really isn't much you can do inside 45 characters of C code.
16:58:35 <ais523_> glibc's RNG uses an algorithm known to be easy to reverse-engineer
16:59:04 <ais523_> the GolfScript solution actually just implements the algo in question
16:59:09 <int-e> especially after guessing main(){for(;;){putchar(...%95+32);}}
16:59:26 -!- shikhin has quit (Ping timeout: 245 seconds).
16:59:38 <int-e> ais523_: I'd suppose that tails followed the same approach as I did: write the C solution, then look at glibc's source code.
17:00:07 <ais523_> I actually have glibc's algo memorized apart from the constants
17:00:28 <ais523_> new seed = old seed * something + something, output value = seed >> something
17:00:44 <ais523_> it's pretty simple as algos go
17:01:29 -!- ais523 has joined.
17:02:02 <int-e> let r = zipWith (+) (0:0:0:r) $ [16807^i `mod` (2^31 - 1) | i<-[0..30]] ++ r in map (\n -> n `mod` 2^32 `div` 2) r
17:02:06 <int-e> > let r = zipWith (+) (0:0:0:r) $ [16807^i `mod` (2^31 - 1) | i<-[0..30]] ++ r in map (\n -> n `mod` 2^32 `div` 2) r
17:02:07 <lambdabot> [0,8403,141237624,811325037,492480232,713292089,1046430673,542994004,1442217...
17:02:31 <int-e> > let r = zipWith (+) (0:0:0:r) $ [16807^i `mod` (2^31 - 1) | i<-[0..30]] ++ r in map (\n -> n `mod` 2^32 `div` 2) (drop 313 r)
17:02:33 <lambdabot> [1804289383,846930886,1681692777,1714636915,1957747793,424238335,719885386,1...
17:03:11 <int-e> `c main(){for(;;)printf("%d,",rand());}
17:03:12 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: c: not found
17:03:44 <int-e> `ibin/c main(){for(;;)printf("%d,",rand());}
17:03:50 <HackEgo> 1804289383,846930886,1681692777,1714636915,1957747793,424238335,719885386,1649760492,596516649,1189641421,1025202362,1350490027,783368690,1102520059,2044897763,1967513926,1365180540,1540383426,304089172,1303455736,35005211,521595368,294702567,1726956429,336465782,861021530,278722862,233665123,2145174067,468703135,1101513929,1801979802,1315634022,63
17:04:44 <int-e> `ibin/haskell main = let r = zipWith (+) (0:0:0:r) $ [16807^i `mod` (2^31 - 1) | i<-[0..30]] ++ r in print $ map (\n -> n `mod` 2^32 `div` 2) r
17:04:45 <HackEgo> ./interps/ghc/runghc: line 5: /opt/ghc/bin/runhaskell: No such file or directory
17:05:34 <int-e> 16807 is easy to remember because it's 7^5
17:06:08 <FireFly> > let r = zipWith (+) (0:0:0:r) $ [16807^i `mod` (2^31 - 1) | i<-[0..30]] ++ r in map (\n -> n `mod` 2^32 `div` 2) r
17:06:09 <lambdabot> [0,8403,141237624,811325037,492480232,713292089,1046430673,542994004,1442217...
17:10:37 <int-e> the first 313 values are dropped. (in the C code it's 310, but it turned out to be convenient to shift the sequence a bit)
17:10:44 <HackEgo> [wiki] [[DNA-Sharp]] http://esolangs.org/w/index.php?diff=41047&oldid=40137 * 149.69.108.53 * (-80) I unfortunately don't know where the interpreter is, but it's not at the listed link...
17:11:22 <int-e> FireFly: I had already run them in lambdabot, but I see I had also copied the wrong command in the HackEgo attempt.
17:15:13 -!- oerjan has quit (Quit: leaving).
17:15:43 -!- NATT_SiM has joined.
17:15:45 -!- NATT_SiM has quit (Remote host closed the connection).
17:16:07 -!- NATT_SiM has joined.
17:16:40 -!- NATT_SiM has quit (Remote host closed the connection).
17:17:06 -!- NATT_SiM has joined.
17:20:11 -!- NATT_SiM has quit (Read error: Connection reset by peer).
17:20:18 -!- tlewkow has joined.
17:22:27 -!- tlewkow_ has joined.
17:23:36 -!- augur has quit (Remote host closed the connection).
17:25:27 -!- tlewkow has quit (Ping timeout: 258 seconds).
17:26:15 -!- shikhout has changed nick to shikhin.
17:27:24 -!- tlewkow_ has quit (Remote host closed the connection).
17:36:47 -!- tlewkow has joined.
17:39:34 <ais523> wow, I could block like 90% of my spam by simply dropping any message that doesn't have my address in the To: line
17:40:57 <ais523> not counting mailing lists, is it possible for someone who isn't a spambot to send email with an incorrect To: address even by accident
17:41:26 <fizzie> If someone Bcc's you, perhaps.
17:42:16 <ais523> fizzie: oh right, obviously
17:42:28 <J_Arcane> Oh sweet heavenly angels I finally have bourbon.
17:42:47 <fizzie> I don't recall what the copy you get looks in that case.
17:43:01 <ais523> it doesn't have your name anywhere in To: or Cc:
17:43:08 -!- Koen__ has joined.
17:43:38 <fizzie> I get something like 90% of the spam my zem.fi addresses get filtered by a simple dnsbl blacklist (Spamhaus' zen and SpamCop) check.
17:44:19 <ais523> most of these spambots are pretty transparent
17:44:33 <ais523> some even send the entire list of emails they're spamming in the To: line
17:46:29 <fizzie> Sometimes the To: address is f<somethingelse> in the same domain, which makes me think it's the first address in a batch of messages or something.
18:05:54 <Gregor> I reduced my spam intake by very nearly 100% by using e4ward.com and deleting email addresses that get spam :3
18:10:30 <Taneb> I've got a friend who uses a different email for each service
18:12:03 <Taneb> (He has one for every valid uuid or something)
18:12:48 <Gregor> Taneb: That's what I do w/ e4ward.
18:12:51 <fizzie> Gregor: Did you notice the comment about newlines?
18:13:14 <Gregor> Yes, but I think your patch should do fine. I'm not sure how much I care about newlines in filenames X-D
18:13:18 <Taneb> I'm too lazy and sometimes like to look at spam and laugh at it
18:13:34 <fizzie> I've used suffixes (user+servicename@) for some places, and a spamtrap hotmail address for random websites that I wouldn't really want make an account for but who insist.
18:13:34 <Gregor> fizzie: I know it's still wrong... lemme put it this way: If you want to fix it, I'll happily merge another patch. Otherwise, meh.
18:13:46 <fizzie> Gregor: "I'll think about it."
18:24:01 -!- shikhin has quit (Ping timeout: 240 seconds).
18:27:23 <elliott> fizzie: I've had things strip off the +foo, I think.
18:28:05 -!- shikhin has joined.
18:42:28 -!- tlewkow has quit (Remote host closed the connection).
18:47:29 -!- ais523 has quit.
18:47:41 -!- tlewkow_ has joined.
18:47:49 -!- ais523 has joined.
18:57:21 <HackEgo> [wiki] [[My Unreliable Past]] http://esolangs.org/w/index.php?diff=41048&oldid=41029 * BCompton * (+2278)
19:03:51 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41049&oldid=41031 * Ais523 * (+396) /* IO */ any nondeterministic method's OK
19:06:19 <Dulnes> Some one made a bootleg version of windows 2003 for the nintendo
19:06:58 <Melvar> Oh, I thought it was in response to the NaN. Should’ve looked at the timestamps first.
19:06:59 <lambdabot> parse error (possibly incorrect indentation or mismatched brackets)
19:08:05 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
19:08:13 -!- idris-bot has quit (Quit: Terminated).
19:08:19 <ais523> Melvar: sorry about your bot
19:08:23 <ais523> I didn't expect that to happen
19:08:37 -!- idris-bot has joined.
19:09:22 <Melvar> Nobody does, but idris happens to crash when asked that. The best thing I can really do is teach my bot to start a new idris when this happens.
19:10:11 <Dulnes> Idris crashed when he divided by zero
19:11:54 <Melvar> Specifically, if you do it in the repl, some top-level handler catches it and goes back to the prompt, but when idris runs in ideslave mode, that handler isn’t present. I’m not sure where to look for the problem or how to fix it.
19:12:55 <Dulnes> just review every part of your code
19:14:44 <Dulnes> How many lines is Idris?
19:15:32 -!- S1 has joined.
19:17:04 <Melvar> How should I count them?
19:19:53 <Dulnes> There should be an end variable depending on what you use? that tells you how many lines are in it
19:20:08 <Dulnes> idk what you use so its differdent for me
19:20:55 <ais523> Dulnes: a large project like Idris is spread across a ton of different files, many of which are in different languages, some of which are build system or the like, some of which are documentation
19:21:18 -!- MDude has quit (Read error: Connection reset by peer).
19:21:47 <Dulnes> if theres an error its going to be hell finding it
19:22:08 <Melvar> I meant whether to include empty lines, comment lines, doc lines, etc. and if there’s a convenient utility implementing your choice.
19:22:25 <ais523> well, a crash upon dividing by zero is unlikely to be in the documentation…
19:22:51 <Melvar> wc on src/ reports 38515 lines total.
19:23:35 <ais523> huh, that's smaller than I was expecting
19:24:29 <Dulnes> yeah the way ais523 worded it i thought it would be larger
19:24:31 <ais523> NetHack 4 is 167762 by the same counting method
19:25:21 <Dulnes> Melvar it would be best to find whats causing that thats a very simple crash bug
19:26:14 <Dulnes> Cant you just black list the area that trys to divide by zero?
19:26:15 <ais523> Dulnes: not really; in this case, we told it to divide by zero and it divided by zero
19:26:40 <Dulnes> So it doesnt divide by zero but anything else
19:26:47 <ais523> so the problem's to find the situation in which it should actively not do what it's told
19:26:52 <ais523> and substitute an appropriate outcome
19:27:01 <Jafet> So what, the repl has a signal handler?
19:27:09 <ais523> if you defined, say, 0 `div` 0 as 0, then that would avoid the crash, but it would be wrong
19:27:31 <ais523> and `div` is probably a compiler primitie
19:27:36 <idris-bot> Can't resolve type class Integral a
19:27:45 <idris-bot> \{meth1} => prim__sdivBigInt 4 meth : Integer -> Integer
19:28:06 <ais523> so it's being compile down to other languages' divisions
19:28:46 <idris-bot> \{meth1} => prim__sdivBigInt 5 meth : Integer -> Integer
19:29:05 <Dulnes> so if its not by zero it can do it
19:29:13 <Jafet> You could try to install your own signal handler
19:29:31 <idris-bot> \{meth1} => prim__sdivBigInt 0 meth : Integer -> Integer
19:30:16 <ais523> it didn't run, I only gave it one argument
19:30:30 <ais523> so I asked it for the concept of dividing 0 by something
19:30:37 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 0 : Integer -> Integer
19:30:45 <ais523> whereas that's the concept of dividing something by zero
19:30:53 <Melvar> The thing is, idris is written in Haskell. The repl uses a haskell implementation, which for that primitive throws an exception. The repl runs under an appropriate catch, ideslave does not. The question is how and where to insert the catch into ideslave and produce a proper response in the protocol.
19:31:17 -!- tlewkow_ has quit (Remote host closed the connection).
19:36:12 <Dulnes> so when the math/compilation section/file made
19:36:27 <J_Arcane> ... https://github.com/naetech/nightrain
19:37:31 <Dulnes> i already know of this
19:40:28 <Dulnes> > 551672727178263718277272/8766
19:41:54 -!- adu has joined.
19:51:18 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
19:54:00 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 65 : Integer -> Integer
19:56:18 -!- adu has quit (Quit: adu).
20:01:21 -!- Patashu has joined.
20:01:43 <HackEgo> [wiki] [[Rasen]] http://esolangs.org/w/index.php?diff=41050&oldid=40985 * 192.52.109.131 * (-10) /* Cat Program */
20:01:51 -!- ais523 has quit (Ping timeout: 258 seconds).
20:01:56 <J_Arcane> Unicomp wants $68 to ship one of their Keyboards to Finland ...
20:06:19 -!- ais523 has joined.
20:07:41 <ais523_> so this is why my laptop is running out of power while suspended
20:07:42 <J_Arcane> Dulnes: PRobably because they only ship internationall through FedEx (which is grossly overpriced) and because the keyboard weighs 5.5 lbs...
20:07:48 <ais523_> something's making it spontaneously turn itself on
20:07:58 <ais523_> just this time, it was close enough to a wi-fi access point that I caught it on IRC
20:11:57 <ais523_> hmm, now I'm wondering why no pingout
20:12:17 -!- ais523 has quit (Ping timeout: 265 seconds).
20:13:42 -!- kcm1700_ has joined.
20:15:58 -!- kcm1700 has quit (Ping timeout: 255 seconds).
20:18:13 -!- kcm1700_ has quit (Ping timeout: 255 seconds).
20:18:42 -!- kcm1700 has joined.
20:22:16 -!- tlewkow_ has joined.
20:22:19 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41051&oldid=41049 * BCompton * (+209) /* IO */
20:26:24 -!- Patashu has quit (Ping timeout: 255 seconds).
20:31:15 -!- adu has joined.
20:33:11 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41052&oldid=41051 * Ais523 * (+517) /* IO */ fail chance of Hello World
20:34:41 -!- heroux has quit (Ping timeout: 240 seconds).
20:35:20 -!- augur has joined.
20:36:31 -!- heroux has joined.
20:46:30 <ais523_> is it just me, or is the proportion of the wiki made of bad BF derivatives going down?
20:46:36 <ais523_> or did someone just rig up Special:Random to disfavour them?
20:47:58 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41053&oldid=41052 * BCompton * (+139) /* IO */
20:48:21 <HackEgo> [wiki] [[My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41054&oldid=41048 * BCompton * (-11) /* Hello, world! */
20:48:49 <HackEgo> [wiki] [[Talk:My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41055&oldid=41053 * BCompton * (+86) /* IO */ Forgot my sig
20:51:36 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41056&oldid=41055 * BCompton * (+4) /* IO */
20:52:00 <HackEgo> [wiki] [[My Unreliable Past]] http://esolangs.org/w/index.php?diff=41057&oldid=41054 * BCompton * (+7) /* Hello, world! */
20:53:43 <ais523_> bleh, 11, if I count C-INTERCAL as a language I created
20:53:58 <ais523_> which I guess I do because I put in so many of the features that make it different from other impls
21:16:57 -!- AnotherTest has joined.
21:22:53 -!- augur has quit (Remote host closed the connection).
21:33:06 -!- Phantom_Hoover has joined.
21:39:57 -!- hjulle has joined.
21:43:04 -!- adu has quit (Quit: adu).
21:45:54 <newsham> http://studio.code.org/s/frozen/stage/1/puzzle/1
21:48:36 <int-e> http://studio.code.org/assets/spinner-big-c3078e9dccaffcd3763893a183dde788.gif
21:49:03 <int-e> Why does nothing ever work without Javascript anymore. Oh well I guess that saves me a ton of time.
21:49:22 <ais523_> int-e: I was looking at some web pages in w3m earlier
21:49:46 <ais523_> and complaining "why does this page need frames" and "why does that page need the ability to show the 'title' of an element"
21:52:01 <vanila> its good that this uses javascript
21:52:11 <vanila> something like this would normally be using flash
22:02:00 <HackEgo> [wiki] [[Talk:My Unreliable Past]] http://esolangs.org/w/index.php?diff=41058&oldid=41056 * Ais523 * (+322) /* IO */ that looks about right
22:03:25 -!- tlewkow_ has quit (Remote host closed the connection).
22:04:59 -!- tlewkow has joined.
22:06:19 <ais523_> wow, has TDWTF screwed up their website
22:06:34 <ais523_> it has horizontally scrolling portions that you can't actually scroll because they're covered by transparent clickable areas
22:09:03 <Taneb> How oddly appropriate
22:20:45 -!- tlewkow has quit (Remote host closed the connection).
22:23:34 -!- L8D has joined.
22:23:48 <L8D> what's that one esoteric LC with just s, k and ` ?
22:24:19 <ais523_> L8D: are you thinking of Unlambda?
22:24:25 <ais523_> that's a Turing-complete subset of Unlambda
22:24:28 <ais523_> although it has other commands
22:24:35 <ais523_> you might also be thinking of Lazy K
22:24:46 <L8D> someone from this channel authored it
22:24:50 <ais523_> or "SK combinator calculus" which is the mathematical name for that subset
22:25:16 <L8D> yes I'm familiar with sk combinator calculus
22:25:30 <L8D> someone figured out a way to denote precedence using only a single character
22:25:40 <ais523_> that's copied from Unlambda
22:25:43 -!- tlewkow_ has joined.
22:26:04 <L8D> that was the other language they mentioned
22:26:04 <elliott> there's that bird one slereah did
22:26:09 <ais523_> you can compile SK into Underload
22:26:15 <elliott> it sounds like unlambda to me though
22:26:24 <elliott> except unlambda has extra stuff
22:26:26 <L8D> they had some sort of name for it though
22:26:26 <ais523_> (that's how Underload was originally proved TC)
22:26:31 <ais523_> but it has a bunch of extra stuff
22:26:40 <ais523_> L8D: perhaps you're thinking of Iota? only that has just the one combinator
22:27:27 <L8D> the name has something to do with binary or byte
22:28:18 -!- augur has joined.
22:28:21 <tromp_> why do you need to denote precedence with s&k ?
22:28:44 <L8D> because: s (k s)
22:28:55 <L8D> is different than: s k s
22:29:10 <tromp_> but these esolangs use prefix apply, where it's not an issue
22:29:19 <ais523_> those examples are `s`ks and ``sks in Unlambda syntax
22:29:33 <ais523_> tromp_: well, you can think of prefix apply as being a precedence marker
22:29:41 <ais523_> just like $ exists mostly for precedence in Haskell
22:30:27 <tromp_> so L8D, how does what you have in mind differ from Lazy K?
22:30:48 <tromp_> using a binary notation?
22:31:01 <L8D> because the interpreter was an entry to some competition on obfuscated C
22:31:08 <L8D> and it didn't have i
22:31:17 <tromp_> my precursor to BLC was a binary combinatory logic
22:31:22 <ais523_> L8D: if you want binary notation, Jot?
22:31:33 <L8D> I remember jot being mentioned
22:32:04 <L8D> http://esolangs.org/wiki/Binary_lambda_calculus
22:32:09 <L8D> ^ it was an interpreter for that
22:32:30 <tromp_> http://www.ioccc.org/2012/tromp/hint.html
22:32:42 <tromp_> http://www.ioccc.org/2012/tromp/tromp.c
22:33:13 <tromp_> so that's not s and k :)
22:35:38 <L8D> I wish I had an awesome last name like "tromp"
22:35:49 <tromp_> just a regular Dutch name
22:36:36 <L8D> I wish I had an awesome Dutch name
22:36:51 <L8D> tromp_: is 'biel' a ditch last name?
22:36:57 <L8D> I thought it was french
22:36:57 <vanila> http://homepages.cwi.nl/~tromp/
22:37:14 <vanila> your sokoban link is deda http://www.gamegate.com/othergames.jsp?NAVID=1&GAMEID=12
22:37:47 <tromp_> i don't know any Dutch called biel
22:38:32 <L8D> why are there so many programmers in the netherlands?
22:38:54 <L8D> I've met like 50
22:40:56 <Taneb> I inherited an awesome dutch surname
22:41:01 <tromp_> http://www.gamegate.com/games.jsp was still working on jun 28 2014; maybe they'll come back
22:41:34 <ais523_> tromp_: now I'm trying to remember exactly what it is
22:43:17 <Taneb> ais523_, do you want me to tell you?
22:43:22 <Taneb> (it's pretty easy to find)
22:43:25 <tromp_> google Taneb and you'll see :)
22:43:48 <ais523_> it's been mentioned on here before, you may as well mention it again
22:44:04 <ais523_> I thought it might be that, but I wasn't sure
22:44:15 <ais523_> hmm, that name arguably becomes even more awesome if overkerned
22:44:25 <Taneb> ais523_, see my article on the wiki
22:44:34 <Taneb> In a graphical browser
22:45:18 <ais523_> is that /intentionally/ overkerned?
22:45:24 <ais523_> or is the font just broken?
22:45:50 <ais523_> haha, I didn't even know it was possible to put styling in DISPLAYTITLE
22:46:00 -!- oerjan has joined.
22:46:11 <ais523_> it is very slightly too wide to work correctly on this browser, though
22:46:23 <Taneb> It looks overoverkerned to me
22:46:31 -!- AnotherTest has quit (Ping timeout: 245 seconds).
22:48:06 <ais523_> it's underoverkerned if you want it to actually look exactly like an 'm'
22:48:10 <vanila> i want to work on an esolang thing, any ideas
22:48:46 <Dulnes> So windows 9 cant be a thing because of the legacy source
22:49:32 <Dulnes> Also someone jailbroke and bootlegged a windows 2003 server onto The NES
22:49:58 <Dulnes> i know just wondering why ita terrible
22:50:09 <vanila> the NES has a 6502 CPU
22:50:14 <vanila> how do you run windows 2003 on that
22:50:23 <Dulnes> yeah my friends me a.link
22:50:30 <Dulnes> i just wanna see if its true
22:50:31 <ais523_> vanila: Dulnes apparently runs IRC bots on Windows 95, that connect via the web interface
22:50:43 <vanila> I use internet explorer on Windows 95
22:51:19 <elliott> I used windows 95 in a VM as my main OS for a short while
22:51:23 <elliott> the aesthetic is definitely good
22:51:37 <vanila> I just need a hard drive and thn I can use windows 95 for real
22:51:49 <ais523_> elliott: I used Windows 95 back when it was the world's most widely used consumer OS
22:51:58 <ais523_> it was a step forwards from many things
22:51:58 <Taneb> I have a Windows 98 computer somewhere
22:52:06 <Taneb> It hasn't been turned on in a while but it still probably works
22:52:10 <vanila> I don't know how to get a cheap hard drive
22:54:00 <ais523_> I saw lots of posts recommending Newegg on Slashdot, but I'm suspicious because they have the same owner
22:54:17 <ais523_> and Slashdot's owners have infinite mod points
22:54:23 <vanila> what is the cutting edge in esolang research?
22:54:33 <ais523_> I posted My Unreliable Past recently
22:55:49 <ais523_> http://esolangs.org/wiki/My_Unreliable_Past
22:56:02 <ais523_> Esolang URLs are predictable enough that you can just type them, rather than using Google
22:56:08 <ais523_> @google my unreliable past
22:56:09 <lambdabot> http://productforums.google.com/d/msg/youtube/ZIP2LmHL1Ro/_8uLjgZEJYoJ
22:56:19 <ais523_> I don't know if I want to follow that link
22:56:37 -!- hjulle has quit (Ping timeout: 255 seconds).
22:57:21 -!- shikhout has joined.
22:58:18 <Taneb> ais523_, some I wouldn't want to type
22:58:25 <oerjan> ^wiki My Unreliable Past
22:58:25 <fungot> http://esolangs.org/wiki/My Unreliable Past
22:58:28 <Taneb> Like Real Fast Nora's Hair Salon 3: Shear Disaster Download
22:58:35 <ais523_> ^^wiki needs to URL escape
22:58:43 <oerjan> fungot: you need better escaping hth
22:58:43 <fungot> oerjan: once you know how hard it would be great if we actually had a thought lately. i feel fnord
22:58:46 <Taneb> Or Eodermdrome (because I can never remember how to spell it)
22:58:58 <ais523_> Taneb: you spelt it correctly
22:59:14 <ais523_> but even if you can't remember, just keep moving the letters around until they don't form a planar graph
22:59:57 <Taneb> Oh, heh, I didn't realise it was a non-planar graph
23:00:28 <oerjan> Taneb: eodermdrome is a word constructed to be the shortest possible representation of a complete graph of 5 letters
23:00:29 -!- shikhin has quit (Ping timeout: 258 seconds).
23:00:43 <oerjan> and it's older than the language
23:00:59 <Taneb> Much like Real Fast Nora's Hair Salon 3: Shear Disaster Download
23:01:35 <Taneb> Which is also designed to be a complete graph, or something
23:01:56 <ais523_> the word inspired the language
23:02:10 <fungot> +15[>+4>+7>+7>+8<4-]>3-.>-4..<2+7.<-2.-11..>2-3.<+3.>2-5.-3.<-4.>+2.<+6.<.<-.>3+.+3.<.<2+.>+4.>+2.+2.-2.<2.,[.,]
23:02:28 <Taneb> I think with Real Fast Nora's Hair Salon 3: Shear Disaster Download, the language was created to fill the name
23:02:31 <ais523_> that looks suspiciously bf_txtgenned
23:02:40 -!- augur has quit (Remote host closed the connection).
23:02:43 <Taneb> But I kind of wanted to make a language like that already
23:02:46 <oerjan> ais523_: it's basically just printing http://esolangs.org/wiki/ and then an ordinary cat
23:02:54 <ais523_> Taneb: was that a spambot name? or did you just want something that looked like a spambot name
23:03:02 <ais523_> and the constant string is bf_txtgenned
23:03:05 <Taneb> ais523_, it was a spambot name
23:03:14 <Taneb> I believe elliott suggested it should be made a language
23:03:17 <oerjan> so making it escape will take some major expansion
23:03:23 <ais523_> you can tell because it uses two working cells of size 7*15
23:03:45 <olsner> I guess it should be possible to find the IRC logs of when that happened
23:04:04 <vanila> (Set A to 100 with high probability... around 1/589 chance of failure)
23:04:26 <oerjan> hm i recall there was this spam page name everyone agreed needed to be made a language but no one has iirc
23:05:07 <Taneb> codu.org doesn't seeeeeem to be loading
23:05:08 <oerjan> vanila: on the wiki. i don't remember the name, also the page may have been deleted (it was spam, after all)
23:05:15 <oerjan> Taneb: i noticed, switched to tunes
23:05:43 <oerjan> i thought my connection was flaky again, but downforeveryoneorjustme agreed
23:05:50 <Taneb> Awww, I have to download a .zip of pre-2013 logs
23:06:11 <oerjan> Gregor: codu.org seems to be down hth
23:06:39 <vanila> this is very interesting ais523_
23:07:04 <ais523_> I try to make my languages interesting
23:07:07 -!- augur has joined.
23:07:14 <ais523_> the life of creating 100 awful BF derivatives is not for me
23:07:18 <oerjan> Gregor: google doesn't know that acronym tdnh
23:07:20 <vanila> i wouldnt' want to program in it though
23:07:46 <ais523_> since when was "people want to program in it" a requirement for an esolang? :-)
23:07:53 <ais523_> although apparently at least one person does want to prorgam in it
23:07:54 <Gregor> The nameserver is down >_O
23:08:15 <Taneb> I try to have an idea then make a language out of it
23:08:34 <Taneb> Like, Fueue was mostly "Underload with a queue instead of two stacks"
23:08:46 <Gregor> Yeah, codu isn't down, its nameservers are down and everybody's abandoned it because of that.
23:08:57 <vanila> maybe i coul contribute to esolangs some way other than inventing one
23:09:02 <vanila> any suggestions for that?
23:09:09 <Gregor> oerjan: It seemed unlikely that codu was down since I'm connected thru it :3
23:09:20 <Taneb> vanila, try implementing Eodermdrome!
23:09:33 <ais523_> vanila: writing interpreters; computational class analyses; writing programs; cross-implementation (i.e. implementing one esolang in another)
23:10:02 <oerjan> Gregor: well i meant the web page, naturally
23:10:15 <oerjan> `echo other things not included
23:10:26 <vanila> are there any markers on the wiki for things that need done?
23:10:51 <oerjan> vanila: Category:Stubs is the closest thing
23:10:52 <vanila> reading about Eodermdrome
23:10:53 <Gregor> oerjan: The web page is up... by some definition ;)
23:11:11 <fizzie> Category:Unimplemented exists, too, but it's not quite that.
23:12:18 <ais523_> Eodermdrome is NP-hard to implement efficiently, isn't it?
23:12:40 <olsner> something graph isomorphism something?
23:12:40 <oerjan> ais523_: well except for the bounded number of letters
23:12:52 <oerjan> which means it's _technically_ in P, i think.
23:13:16 <oerjan> although probably with quite a high exponent
23:14:10 <oerjan> also some people have suggested the spec does not exclude unicode letters (which won't change it from P since unicode is also finite, but may make it easier to program)
23:15:00 <Taneb> Found the logs about how Real Fast Nora's Hair Salon 3: Shear Disaster Download gained its name
23:15:34 <vanila> I thought of anew keyboard layout but i made a mistake
23:15:40 <Taneb> And huh, I made the language before the name?
23:16:26 <ais523_> oerjan: it was meant to, but I sort-of believe that esolangs can outgrow their authors
23:16:31 <oerjan> vanila: make it one that doesn't leave out alot of spaces after as hth
23:16:36 <ais523_> unless the spec is obviously nonsensical or self-contradictory
23:17:07 <vanila> http://i.imgur.com/NoylOuA.png
23:17:54 <oerjan> vanila: it's jumps not jumped, otherwise you miss s
23:18:17 <vanila> I need a list of all valid sentences which use every letter once
23:18:25 <vanila> then I can choose the best keybaord layout from it
23:18:38 <ais523_> vanila: there are a lot of such sentences
23:18:39 <vanila> idea: the keys chance every time you press one in some permutation
23:18:44 <ais523_> infinitely many, most likely
23:18:55 <vanila> there is less than 26!
23:18:55 <oerjan> you probably want to drop the duplicate letters
23:19:09 <vanila> when I said once I meant not more than once and not less
23:19:13 <oerjan> vanila: um there are probably no valid sentences that do that
23:20:02 <oerjan> for one thing, vowels are too much rarer than consonants
23:20:10 <ais523_> oerjan: there are some very contrived sentences
23:20:27 <ais523_> or, well, the one that was the solution to the Enigma metapuzzle at Agora is two sentences
23:20:33 <ais523_> "Zing! Vext cwm fly jabs Kurd qoph"
23:21:14 <fizzie> I think I've seen the "Mr. Jock, TV quiz PhD, bags few lynx" one (one of the first google-hits) somewhere.
23:21:25 <fizzie> http://www.fun-with-words.com/pang_example.html lists six examples.
23:21:31 <oerjan> i suppose welsh helps with the vowels :P
23:21:47 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:22:01 <vanila> Waltz, nymph, for quick jigs vex bud.
23:22:01 <Sgeo> Was at JSSummit today
23:22:14 <oerjan> vanila: i spot two i's
23:22:18 <Sgeo> One of the presenters apparently didn't try out their examples and didn't understand people's confusion
23:22:59 <oerjan> and assuming all letters are there, that's all
23:23:19 <oerjan> > sort "Waltz, nymph, for quick jigs vex bud"
23:23:38 <ais523_> oerjan: it has all letters
23:23:41 -!- `^_^v has quit (Ping timeout: 240 seconds).
23:25:20 <vanila> howdo i find all graph based esolangs?
23:25:58 <ais523_> not sure we have a category for that
23:26:02 <oerjan> you can search for "graph" if not
23:26:13 <vanila> TURKEY BOMB, the first known programming-language-cum-drinking-game, evolved independently on four seperate continents and was widely used as an implementation base for computer operating systems for several centuries.
23:26:14 <fizzie> Category:Non-textual is not large.
23:26:24 <fizzie> Assuming all of them have been correctly categorized.
23:26:34 <oerjan> fizzie: um eodermdrome isn't non-textual, but still graph-based
23:27:19 <fizzie> Well, Eodermdrome's not in any useful category, so clearly there are none.
23:27:37 <fizzie> http://www.rinkworks.com/words/pangrams.shtml "Glum Schwartzkopf vex'd by NJ IQ."
23:27:55 <oerjan> there might not be that many. i recall kolmogorov machine and andrei machine, or something.
23:28:24 <oerjan> hm Graph mentions Cvlemar
23:29:07 <fizzie> On the Rinkworks page, the 29-letter "Sphinx of black quartz, judge my vow" is very non-contrived.
23:29:18 <vanila> so I like the idea of graph based languages
23:29:25 -!- tlewkow_ has quit (Remote host closed the connection).
23:29:28 <vanila> but it should be efficient to implement
23:29:44 <oerjan> anyway, searching for "graph" throws up several relevant pages.
23:29:50 <fizzie> There's Grasp, but it's sadly incomplete.
23:29:59 * Sgeo decides to repeat himself here
23:30:06 <Sgeo> FnOnce occurs in nature, outside of Rust: Languages like Python that support generators can use an easy syntax for some monads. Which monads? Exactly those monads whose >>= takes an FnOnce as a continuation. Option, but not List
23:30:12 <vanila> or are you using google?
23:30:13 <oerjan> http://esolangs.org/w/index.php?search=graph&title=Special%3ASearch&fulltext=1
23:30:31 <vanila> when I used search ti took me straight to graph page, i gues theres another search box
23:30:47 <elliott> we have seriously differing definitions of the word "nature"
23:31:01 -!- augur has quit (Remote host closed the connection).
23:31:12 <oerjan> vanila: no, but you need to use the "containing" option in the menu if there is a page by the same name
23:31:13 <vanila> http://esolangs.org/wiki/Wire-crossing_problem
23:31:19 <vanila> I should make a language based on planar graphs
23:31:24 -!- tlewkow has joined.
23:35:32 <oerjan> Sgeo: i think that may be the same monads as https://hackage.haskell.org/package/STMonadTrans works for
23:36:10 <Sgeo> Ooh so Rust is more type safe than Haskell?
23:36:25 <oerjan> in that case, presumably
23:36:42 <oerjan> haskell lacks those pesky uniqueness types
23:37:14 <Sgeo> If I see a mistake in a Stackoverflow answer, should I just fix it?
23:37:22 <Sgeo> It's a trivial mistake but a compilation error nontheless
23:38:05 <oerjan> Sgeo: no. make a comment instead. i've been burned on that myself.
23:38:20 <Sgeo> "Edits must be at least 6 characters; is there something else to improve in this post?"
23:38:26 <Sgeo> But... it's a 5 character mistake.
23:38:51 <oerjan> unless you've got enough rep _not_ to need it confirmed by random strangers who may not even know the language you're fixing, don't even try
23:39:42 <oerjan> i got so annoyed at SO's policy on code edits that i pledged not to do them again.
23:39:59 <oerjan> (even though i now _do_ have enough rep)
23:41:22 <Sgeo> http://stackoverflow.com/questions/27022848/how-to-mutate-struct-field-in-method#comment42580981_27023282
23:43:20 <oerjan> i think that went well
23:44:04 <Sgeo> The original author can make smaller edits apparently
23:44:17 <vanila> I couldn't figure out how to use ST with ListT
23:44:34 <vanila> someone said it could be done with MonadPrompt but it is hard
23:44:42 -!- L8D has left.
23:45:06 <vanila> http://esolangs.org/wiki/Esoteric_Awards
23:45:33 <Sgeo> Am I expected to upvote that reply?
23:45:43 <oerjan> Sgeo: i don't think so
23:46:43 <oerjan> upvotes are for useful information, afaict
23:47:16 <vanila> http://www.vb-helper.com/FourColorMap1Solved.gif
23:47:36 <vanila> i dont know what the language is yet though
23:48:21 <vanila> you would draw the graph and color it in i guess
23:48:35 <vanila> with 4 cours other wise the program is invalid
23:48:52 <oerjan> vanila: have you seen piet? that's not graph-based though, only color
23:49:40 <Sgeo> "Hmmm... I think it would classify as days+1 days"
23:49:53 <vanila> I wonder how to make ti into something programmable
23:49:55 <tromp_> http://esolangs.org/wiki/Kolmogorov_machine
23:50:21 <oerjan> tromp_: was mentioned, also in the search link
23:50:52 <vanila> something like game of life is turing complete
23:50:57 <vanila> so it should be easy to make this turing complete
23:51:02 <vanila> but it willb e hard to make it human programmable
23:53:16 <vanila> if you input a picture for your pogram its not turing complete
23:53:22 <vanila> at least not just by recoloring the graph
23:53:29 <vanila> yu'd need a way to store unbounded amounts of data
23:53:35 <vanila> i dont know how that is possible
23:58:29 <vanila> http://esolangs.org/wiki/%E2%84%92
00:02:20 <FireFly> <vanila> I need a list of all valid sentences which use every letter once ← Wikipedia used to have a list of pangrams, but apparently it was deleted a while ago: http://en.wikipedia.org/wiki/List_of_pangrams
00:02:34 <FireFly> It included a bunch of perfect pangrams in english, though
00:04:10 <ais523_> "What service does it provide our readers to show them a pangram in Cherokee, or Malay, or for the love of God, Klingon or in country codes?"
00:04:21 <ais523_> I can see why this was inappropriate for Wikipedia, but I hope it got archived somewhere
00:04:40 -!- S1 has quit (Quit: S1).
00:06:10 <FireFly> Luckily archive.org has it covered: http://web.archive.org/web/20141012231620/http://en.wikipedia.org/wiki/List_of_pangrams
00:06:34 <FireFly> The perfect pangrams in English all look very forced
00:06:49 <HackEgo> [wiki] [[Linguistic Calculus]] http://esolangs.org/w/index.php?diff=41059&oldid=36506 * BCompton * (+0) /* Syntax */ Fixed spelling
00:07:15 <FireFly> By which I mean, those words look more welsh than english
00:08:38 <ais523_> you normally need to use Welsh loanwords to English to get the really short pangrams
00:08:42 <FireFly> "Yxskaftbud, ge vår WC-zonmö IQ-hjälp."
00:08:46 <ais523_> Arabic, too, because it's the easiest way to get Q without U
00:13:17 <ais523_> the phonetic pangrams are fun
00:13:22 <ais523_> there are perfect ones for some accents
00:13:59 <oerjan> <ais523_> it's underoverkerned if you want it to actually look exactly like an 'm' <-- i made that, it won't work perfectly in all browsers regardless so we converged on a compromise that doesn't look too bad in the ones we tested
00:14:49 <olsner> hm, "WC-zonmö" is quite forced
00:16:18 -!- Bicyclidine has joined.
00:16:51 <oerjan> that's the maid that takes care of your toilet zone, i take. and she isn't too bright.
00:17:31 <olsner> the axe handle courier is sorting it out though
00:19:07 <oerjan> norwegian wikipedia's pangram article has only the english quick brown fox example
00:19:52 <olsner> Vår sære Zulu fra badeøya spilte jo whist og quickstep i min taxi?
00:20:12 <olsner> IQ-løs WC-boms uten hørsel skjærer god pizza på xylofon.
00:20:23 <olsner> (the archived wikipedia page had a few)
00:20:37 <oerjan> not 29-letter ones, though :(
00:21:45 <oerjan> or well, not the ones you listed... checking
00:23:41 <Taneb> lipogramming is fun in my opinion, I am happy with it, not as much with pangramming
00:23:48 <oerjan> swedish is probably easier since it actually uses x and i think c natively
00:24:00 <oerjan> (not sure about the c)
00:26:27 <ais523_> I'm reading http://www.leesallows.com/files/In%20Quest%20of%20a%20Pangram1.pdf
00:27:13 <olsner> kk in swedish is always ck except when it's ch
00:27:14 <oerjan> Taneb: nah, pangrams are always better, that's clear.
00:27:50 <oerjan> olsner: right, i wasn't misremembering then
00:33:45 -!- ais523_ has quit (Quit: Page closed).
00:34:36 -!- adu has joined.
00:39:33 <fizzie> While not very dictionary-compatible, the "Dwarf mobs quiz lynx.jpg, kvetch!" listed on that Wikipedia page is impressively reasonable.
01:00:23 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
01:05:37 <HackEgo> [wiki] [[Portal 2]] http://esolangs.org/w/index.php?diff=41060&oldid=40880 * 152.26.69.32 * (+0) /* Instructions */ fixed a word that didn't make any sense.
01:06:24 <Sgeo> It was clearly deliberate that 0 portals can only be moved to the left
01:06:39 <Dulnes> much coincidence i was just watching a portal speed run
01:07:23 <Sgeo> Probably also the { doesn't make sense with 'last'
01:07:59 <Sgeo> Implementation says different
01:12:09 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 754 : Integer -> Integer
01:12:28 <idris-bot> \{meth1} => prim__sdivBigInt 754 meth : Integer -> Integer
01:12:48 <HackEgo> [wiki] [[Talk:My Unreliable Past]] M http://esolangs.org/w/index.php?diff=41061&oldid=41058 * BCompton * (+251) /* IO */
01:13:05 <Sgeo> Idris can show functions?
01:13:21 <Sgeo> Also that is a lot of meth. So much meth in Idris and Picolisp
01:14:53 -!- adu has quit (Quit: adu).
01:18:00 -!- adu has joined.
01:21:08 -!- idris-bot has quit (Ping timeout: 244 seconds).
01:22:30 -!- Melvar has quit (Ping timeout: 264 seconds).
01:26:25 <vanila> http://en.wikipedia.org/wiki/User:CarnivorousBunny
01:27:56 <vanila> Amazingly few discotheques provide jukeboxes
01:31:39 <vanila> I checked out gopher a bit but it sucks
01:31:49 <vanila> i dont find any good gopher sites
01:32:02 <vanila> except zzo38computer and wikipedia converted to gopher
01:34:06 <Sgeo> Here's an interesting thought: In Rust, if I have a &mut T, and a function to give me a new T (say, a modified copy of the old one), I can mutate in such a way that whatever gave me the &mut T can actually see the mutation, even though it's more of a replacement... unlike other imperative languages where I can't fully replace as a mutation
01:34:33 <Sgeo> I guess this doesn't work for all T though, hmm
01:36:10 <vanila> why is the no formal model of rust type system :/
01:36:30 <vanila> are we supposed to just believe in its soundness
01:36:38 <Sgeo> I think someone made one, or at least a formal model of something, in order to work out how to bring about dynamically sized types
01:36:44 <Bike> faith is a virtue
01:37:02 <vanila> i want to like rust but it's so frustrating
01:37:14 <Sgeo> http://smallcultfollowing.com/babysteps/blog/2014/01/05/dst-take-5/
01:37:35 <Sgeo> https://github.com/nikomatsakis/rust-redex
01:37:48 <Bike> i want to like superfluid helium, but the i'm too big on laminar flow
01:38:12 <vanila> rust-redex is clearly nonsense
01:38:20 <vanila> I get this shown to me whenever I mention this
01:38:46 <Sgeo> I don't actually know anything about either redexes or formal models
01:39:42 <Bike> is this like prenex
01:40:07 <Sgeo> I tried to google prenex and google autocompleted prenex normal form
01:40:16 <Bike> well that's what i meant
01:40:26 <Bike> so... guess that worked out
01:56:23 -!- adu has quit (Quit: adu).
01:57:11 <Taneb> Help I have a very small computer thingy and I do not quite know what to do with it
01:57:51 <Bike> program it to get onto irc and troll elliott
01:58:36 -!- Melvar has joined.
01:59:39 <Taneb> It... that would be impressive
02:00:06 <Taneb> I've managed to make it toggle an LED when you press a button
02:00:28 <Bike> fpga? microcontroller? motorized pants?
02:00:58 <Taneb> An STM32 Discovery, whatever one of them is
02:01:16 <Bike> seems to be a microcontroller.
02:01:38 <shachaf> Bike: any more linear in your algebra yet?
02:01:57 <Bike> 128 KB flash, 8 KB ram. bet it only takes that much memory to troll elliott. think creatively.
02:02:26 <Bike> shachaf: nnnnnope
02:02:33 <shachaf> i got a good Cale lecture about it and all sorts of things make more sense now
02:02:44 <Bike> i'm not a big fan of kale
02:02:48 <Bike> just don't like the taste tbh
02:03:09 <oerjan> it's not even SPELT the same
02:03:17 <Bike> you're not even spelt the same
02:03:27 <shachaf> oerjan: you appear to have a v. high standard for your puns
02:03:31 <Bike> hang on. is spelt a word?
02:03:35 <Taneb> Bike, I've got a fancier model I think it has 512kb flash and 80kb ram
02:03:50 <shachaf> Bike: yes, it's a kind of wheat
02:04:03 <shachaf> Bike: you missed an opportunity
02:04:13 <Bike> Taneb: wow way to wuss out
02:04:26 <Taneb> It's not strictly speaking mine
02:04:29 <shachaf> oerjan: such as being spelt the same, or being funny
02:04:48 <Taneb> Just I'm in a position where if I break it I have to tell me to pay me for it
02:05:25 <oerjan> Bike: sure. three words, even.
02:05:33 -!- adu has joined.
02:06:28 <Bike> anyway i guess you should be careful if you haven't done this sort of thing before
02:06:30 <Taneb> But no-one told me that the rest of the English-speaking world doesn't use it
02:06:38 <Bike> i literally melted part of my microcontroller a few days ago
02:06:43 <Bike> that's the srot of thing you can do
02:06:58 <shachaf> Bike: wait so you know about tensors and things, right?
02:07:05 <lambdabot> "literally literally literally literally literally literally literally liter...
02:08:03 <oerjan> tensor and things and quarks and springs
02:08:37 <Bike> fun fact (0 = 1) tensors are called that because they were developed to describe physical tension.
02:08:42 <Bike> cauchy sucks at names i guess!
02:08:43 <oerjan> i hear tensors can be stressful
02:10:23 -!- MDude has joined.
02:10:43 <shachaf> Bike: i spent a bit of time trying to figure out what (0=1)-tensors were
02:11:08 <shachaf> anyway so what are tensors
02:11:11 <Bike> you mean 0,1 tensors?
02:11:17 <Bike> they're multilinear operators.
02:11:50 <Bike> wow, if you type "multilinear operator" into wikipedia it just straight up redirects you to tensor.
02:12:38 <shachaf> Cale was telling me about what a scam the `h̀essian matrix́´ was
02:13:02 <Bike> writing them out is definitely bullshit
02:13:08 <Bike> they're probably differentials or wahtever
02:13:36 <shachaf> well, they're representing a thing as a matrix just because it happens to -- well, like, whatever, man
02:14:06 <Bike> yeah it's the same with tensors
02:14:33 <Bike> it's like, 2-tensors and matrices are SORTA not the same, but everyone writes 2-tensors as matrices, which now means a syntax thing instead of the other thing
02:14:53 <shachaf> i started h8in' on matrices a bit less
02:15:40 <Bike> it's like i ranted before, matrices are cool, multiplying them by hand and all the other garbage you do in a linalg class suck
02:16:11 <shachaf> what, why would you ever multiply them by hand
02:16:27 <Bike> because you hate children.
02:16:42 <Bike> had to do it in high school. have to do it in college. fuuuuuck iiiiit
02:17:29 <Taneb> This reminds me, I need to learn whatever the hell my vision and graphics module is on about
02:17:56 <Bike> Vision? Like sweaty things looking at things? Rhodopsins?
02:28:30 <oerjan> my problem with wikipedia's Esoteric programming language article: people adding self-created junk languages to it and i cannot delete it because some of the _good_ example languages are just as badly cited.
02:28:43 <shachaf> Bike: so the hessian thing is e.g. f : R⊗R -o R, or : R -o (R -o R)
02:28:58 <Bike> sorry shachaf i don't speak jive
02:29:11 <vanila> does anyone here speak jive?
02:29:17 <shachaf> help which thing is jive here
02:29:47 <Bike> this channel is tragically unhip i'm afraid
02:30:17 <shachaf> Bike: by V -o W i just mean a linear map from V to W
02:30:55 <Bike> is that supposed to be R tensor product R
02:31:16 <Bike> ok so i don't know what that means.
02:31:30 <shachaf> well it's just the second derivative of a function
02:31:56 <shachaf> but it's represented as a matrix because R -o R ~~ R
02:33:46 <shachaf> wait i'm saying nonsense again
02:39:24 <shachaf> ok, so if f : R^n -> R, then Df : R^n -> (R^n -o R), and DDf : R^n -> (R^n -o (R^n -o R)), so DDf(x) is represented as (R^n -o R^n) or a square matrix
02:39:32 <shachaf> i don't know why i'm even talking about this
02:56:36 <shachaf> Bike: also the definition of the tensor product as left adjoint to -o is kind of odd
03:02:20 -!- tlewkow has quit (Remote host closed the connection).
03:14:27 -!- digitalcold has quit (Ping timeout: 245 seconds).
03:15:18 -!- digitalcold has joined.
03:25:23 -!- augur has joined.
03:46:08 <Sgeo> I wonder if there's an IO-like monad for Haskell that corrals mutability into a Rust-like system where one component can't actually observe another component mutate
03:53:51 <vanila> Sgeo, isn't that what ST does?
03:55:18 <Sgeo> I don't know what it means to store an STRef well enough to say
03:55:54 <Sgeo> I guess that makes sense though
03:55:56 <vanila> well i just mean ST lets you do mutation
04:56:22 -!- augur_ has joined.
04:57:06 -!- shikhin has joined.
04:59:41 -!- augur has quit (Ping timeout: 258 seconds).
05:00:18 -!- shikhout has quit (Ping timeout: 264 seconds).
05:00:37 <vanila> http://homepages.cwi.nl/~tromp/pearls.html
05:00:42 <vanila> p(c){putchar( c);}f(x,y,m){
05:00:42 <vanila> (y=m- abs(m -y))- m&&m-
05:00:42 <vanila> x?f(x <m?y:x&m,x<m? x:y,m
05:00:42 <vanila> 1&&y?32:64);} main(z){for(z
05:00:45 <vanila> (z%N?32:10))f (z%N,z/N,N);}
05:03:22 <lifthrasiir> vanila: shorten your program enough, eliminate long identifiers if possible, adjust long identifiers or numbers or string literals so that it can be broken up or at least be relocated, shape and adapt your code.
05:04:43 <lifthrasiir> maybe the most part is the very first step, what you think "enough" might not be enough.
05:07:34 <vanila> icannot understand the code
05:08:54 <lifthrasiir> sure, it makes use of C's quirky precedence rules and recursive functions.
05:11:52 <lifthrasiir> vanila: you also may want to look at the theoretical side, http://en.wikipedia.org/wiki/Hilbert_curve
05:14:30 -!- MDude has changed nick to MDream.
05:43:33 -!- DTSCode has joined.
05:47:05 -!- shikhin has quit (Remote host closed the connection).
05:48:28 -!- oerjan has quit (Quit: Nite).
06:13:30 -!- FireFly has quit (Excess Flood).
06:13:34 -!- shachaf has quit (Ping timeout: 244 seconds).
06:13:42 -!- shachaf has joined.
06:14:35 -!- FireFly has joined.
06:39:25 -!- drdanmaku has joined.
06:44:45 -!- vanila has quit (Quit: Leaving).
07:26:19 -!- Patashu has joined.
07:42:57 <Sgeo> So, at these tech conferences, like JSSummit, if someone has broken examples and doesn't understand people's confusion and corrections, is everyone still expected to claim that it was a good presentation?
07:45:11 <DTSCode> is it teaching theories and just implementing them in js?
07:46:25 <DTSCode> btw, facebook made an implementation of js with static typing
07:51:57 -!- Froox has joined.
07:53:52 <Sgeo> I'm going to go correct the person on Twitter
07:54:33 <DTSCode> i love a good twitter debate
07:54:41 -!- olsner has quit (Ping timeout: 240 seconds).
07:55:02 -!- Frooxius has quit (Ping timeout: 240 seconds).
07:55:04 <DTSCode> and by good twitter debate i mean stupid pointless twitter argument
07:56:02 -!- yiyus has quit (Ping timeout: 240 seconds).
07:56:13 <Sgeo> https://twitter.com/ricardoaandres/status/535187248787259393 slide 51
07:57:23 -!- olsner has joined.
07:57:53 -!- DTSCode has changed nick to dts_Zzzz.
07:59:15 -!- Phantom_Hoover has joined.
07:59:42 -!- FreeFull has quit (Ping timeout: 240 seconds).
08:00:37 <Sgeo> He got the argument-based version right
08:00:41 <Sgeo> Around slide 34
08:01:41 -!- olsner has quit (Ping timeout: 240 seconds).
08:01:50 -!- FreeFull has joined.
08:01:56 -!- olsner has joined.
08:03:01 <fizzie> That looks more reasonable. 51 is rather clearly wrong, given that 'demethodize' doesn't even return a function.
08:04:50 <Sgeo> That was the first thing I noticed, and I commented on it during the presentation. Failed to notice that undefined at the time until I tried it in Firefox
08:05:04 -!- yiyus has joined.
08:12:08 <Sgeo> Yeah I hope I don't get into trouble for correcting someone publically at an expensive conference
08:30:44 -!- MDUd has joined.
08:34:53 -!- MDream has quit (Ping timeout: 255 seconds).
08:40:40 <mroman> Prelude Test.QuickCheck> let prop_Foo xs = xs == reverse xs
08:40:40 <mroman> Prelude Test.QuickCheck> quickCheckWith stdArgs { maxSuccess = 5000 } prop_Foo
08:40:43 <mroman> +++ OK, passed 5000 tests.
08:40:45 <mroman> this doesn't look right.
08:42:57 <mroman> without a specified type
08:43:21 <mroman> [(),()] == reverse [(),()]
08:45:42 -!- adu has quit (Quit: adu).
08:46:00 <int-e> another victory for ghci's extended defaulting rules
08:46:41 <int-e> @check \xs -> reverse xs == xs
08:55:10 <mroman> It's somewhat confusing, yes.
09:25:44 -!- Patashu has quit (Ping timeout: 255 seconds).
09:49:59 <fizzie> this message rustic dictator
09:50:28 <fizzie> (Testing out a dictation thing.)
09:57:42 -!- Patashu has joined.
10:06:50 <fizzie> Poor dc, gets completely left out of half the challenges, thanks to having only ? for input.
10:08:35 <int-e> yeah, not for different letter parity though
10:08:57 <int-e> because as I just realized there is ONLY ONE TEST CASE.
10:09:13 <int-e> stupid, stupid, stupid.
10:12:15 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41062&oldid=41046 * TomPN * (+83) /* Quantum entanglement */
10:13:41 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41063&oldid=41062 * TomPN * (-76) /* Input and output */
10:17:59 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41064&oldid=41063 * TomPN * (+179)
10:19:29 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41065&oldid=41064 * TomPN * (+197) /* Teleportation */
10:26:47 <shachaf> int-e: So it's just a "print this output" exercise?
10:27:06 <int-e> I'm afraid so, for most programming languages
10:27:29 <int-e> golfscript/burlesque are likely to be honest there.
10:28:17 <int-e> (my 57 character Haskell solution is honest)
10:29:13 -!- Patashu has quit (Remote host closed the connection).
10:29:23 -!- Patashu has joined.
10:29:31 <shachaf> I don't like this pid business.
10:30:16 <shachaf> I can save a character with that trick but I don't want to use it if no one else is.
10:31:09 <int-e> You'll not be the only one
10:32:22 <int-e> yes. it's a natural idea.
10:32:24 <shachaf> I'd rather it just insisted on determinism by running a few times.
10:32:33 <int-e> anagol should've used the setpid to start everybody from the same fixed PID.
10:34:11 <int-e> but in this problem, I expect the perl solutions to encode about 15 bits of information in the PID, and that's just stupid.
10:35:44 <shachaf> I have a 32-character Ruby solution and I can save one character using the pid trick. Is that what leonid is doing?
10:36:03 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
10:36:29 <int-e> shachaf: a previous leonid submission: http://golf.shinh.org/reveal.rb?Wow/leonid_1415748522&rb
10:39:21 <shachaf> So I guess they're just doing the obvious thing.
10:41:39 <int-e> I also have a completely honest 32 characters perl solution. So the 30 characters one is actually still plausible.
10:41:50 <fizzie> My Burlesque is at least honest, but that's really the easier thing to do in that case.
10:43:09 <int-e> I suppose burlesque has a really short way of doing (`mod`2).length.nub (or (`mod`2).length.group.sort)
10:43:47 <int-e> The need for import Data.List is killing that approach in Haskell
10:48:41 <shachaf> Oh, I just got it to 31 without using a pid.
10:49:32 <shachaf> Do you know what the range of allowed pids is?
10:49:43 <shachaf> I don't know how this tool works.
10:53:21 -!- Phantom_Hoover has joined.
10:55:13 <shachaf> If I "use form" will it insert a newline after my code?
10:56:29 <fizzie> Not unless you type in one.
10:57:32 <int-e> experimentally 302 works, everything below that I tried failed, and it goes up to 32767.
10:59:00 <fizzie> And I don't know about really short, but the (`mod`2).length.nub is NBL[2.% (and now I spoiled my solution, but maybe it's trivial enough), and (`mod`2).length.group.sort is <>gl2.% (there's a "gl" shortcut for length.group) which is the same length.
10:59:24 <shachaf> If you submit more than once does it only take the smallest solution?
10:59:33 <shachaf> Is that why people have (alt) etc.?
10:59:34 <mroman> > length . group . sort $ "abcabbc"
10:59:47 <mroman> gl is length . group hth
11:00:34 <blsqbot> | {"a" "a" "b" "bb" "c" "c"}
11:00:50 <blsqbot> | ERROR: Unknown command: (g[)!
11:00:52 <blsqbot> | {"a" "b" "c" "a" "bb" "c"}
11:03:24 <mroman> int-e: you could brute force a random seed in blsq
11:04:06 <mroman> but that's already 13B
11:04:09 <int-e> mroman: good luck doing that for 28 bits
11:04:44 <fizzie> The obvious dishonest Burlesque would probably be something like ,162450548b2XX)sh^p and that's already quite a bit longer. I don't know if there are good ways to compact big numbers in Burlesque -- "3m738"84B! is already longer. (Though I kind of like the idea of using bases > 36 and relying on the fact that the number doesn't happen to have any offending digits.)
11:05:22 <shachaf> Clearly the system should let you initialize /dev/random with anything you want.
11:09:37 <fizzie> http://sprunge.us/SXNa <- "illegal" bases that happen to work for that number.
11:13:33 <mroman> toBase bs n = map (\c -> (['0'..'9'] ++ ['a'..'z']) !! (fromIntegral c)) $ digits bs n
11:14:15 <mroman> I guess I could extend that to upper case letters as well
11:15:42 <mroman> gives you 10 more characters :)
11:16:17 <int-e> > (length "$$*5668",length "162450548")
11:16:46 <int-e> > 162450548`divMod`5668
11:17:56 <shachaf> Hmm, I used 324901096 to save some characters.
11:18:11 <shachaf> But maybe that wasn't worth it...
11:18:14 -!- boily has joined.
11:18:38 <int-e> then using $$ that way is still good for one character, potentially
11:19:04 <int-e> (28661 is prime so there's no nicer split)
11:19:53 <shachaf> That's what I did, 11336*28661
11:25:25 <mroman> fizzie: XX)sh^p isn't optimal though
11:25:48 <mroman> that is, if anagol ignores trailing newline
11:26:27 <blsqbot> | ERROR: Burlesque: (<-) Invalid arguments!
11:26:27 <blsqbot> | ERROR: Burlesque: (m[) Invalid arguments!
11:26:39 <mroman> !blsq 162450548b2)';<-Q
11:26:39 <blsqbot> | 0;0;1;0;1;1;1;0;0;0;1;1;0;0;1;1;0;1;1;1;0;1;0;1;1;0;0;1;
11:27:05 <mroman> )';<-Q is 1B shorter than XX)sh^p
11:27:16 <mroman> (you need to replace ; with a newline, of course)
11:27:27 <mroman> but I can't send blsqbot newlines
11:29:00 <shachaf> Wait, you can choose not to print the final newline?
11:29:18 <fizzie> shachaf: You can also print 42 extra final newlines.
11:29:53 <fizzie> And in general any extra whitespace at the end.
11:30:34 <fizzie> It slightly compensates the fact that the testcases are always entirely random about whether they have final newlines or not.
11:31:33 <mroman> (that it ignores trailing whitespaces)
11:31:40 <fizzie> mroman: I didn't even know Q existed.
11:32:01 <fizzie> (It is documented, sure.)
11:32:03 <mroman> you might as well do )Q instead of )sh
11:32:32 <mroman> It's documented and there is even a notice about it :)
11:32:49 <mroman> "Notes for Burlesque 1.7.x -> 1.7.3: Please check out the new Specials and Modifiers (scroll down) and also to some new syntax extensions. I.e. instead of {5} you can now writ q5! Please check out the new commands. .- has received additional functionality. Also Swap, Dup and Pretty now have single-character Commands (j, J and Q (in that order)). "
11:33:05 <mroman> that has some typos in it :D
11:33:18 <mroman> I kinda wanted to reorganize the documentation and rebuild it
11:33:24 <mroman> but it'd be sooo muuuch effort
11:33:26 <fizzie> I don't think I have any "sh"s in any final versions that I've submitted.
11:33:57 <fizzie> There are so many other shortcuts that incorporate something pretty in them.
11:35:59 <mroman> Thanks to the biggest flaw when using burlesque to golf
11:43:42 <mroman> in case you don't know sH either
11:44:39 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
11:47:07 <mroman> useful back in the days when sp,SP,bs and BS didn't exist
11:47:11 <mroman> now probably rarely useful
11:48:33 <mroman> I get the feeling I grew up with Burlesque
11:49:48 -!- Patashu has quit (Ping timeout: 255 seconds).
11:49:49 <fizzie> I knew about sH, but I don't remember the different formats, and haven't really used them.
11:51:19 <shachaf> Wait, does whitespace not count for the length of a program, too?
11:51:29 <shachaf> That would be too easy to abuse.
11:51:51 <fizzie> It doesn't have a column in the statistics, but it does count for the actual length number.
11:52:25 <fizzie> (So you can get the amount of whitespace by subtracting the sum of statistics from size.)
11:53:11 <shachaf> I meant whitespace at the end of the program.
11:53:13 -!- Phantom_Hoover has joined.
12:02:37 <Taneb> What effect does having x permission but not r have? (in Unix)
12:16:29 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
12:20:10 -!- boily has quit (Quit: REPULSIVE CHICKEN).
12:20:53 <fizzie> On a file, http://sprunge.us/UAbF -- but it needs to be a real executable, not a #! script, because otherwise the interpreter would just fail to read it: http://sprunge.us/AOjH
12:22:10 <fizzie> (On a directory, it's just "can access the directory, but not read the list of contents".)
12:47:53 -!- S1 has joined.
12:51:19 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
13:03:50 <mroman> can you stream lazily input from a socket to a function working on strings?
13:04:30 <mroman> unlines . map (reverse) lines
13:05:50 <mroman> I could actually feed the input linewise to the function though
13:11:43 -!- hjulle has joined.
13:12:28 <mroman> but linewise oughta work for IRC
13:18:57 -!- drdanmaku has joined.
13:34:40 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41066&oldid=41065 * TomPN * (+319) /* Example programs */
13:35:08 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41067&oldid=41066 * TomPN * (+50) /* True random number generator */
13:36:53 <mroman> !blsq 12rom{mo12.+m{3' lp}}sp
13:36:53 <blsqbot> | 1 2 3 4 5 6 7 8 9 10 11 12
13:36:53 <blsqbot> | 2 4 6 8 10 12 14 16 18 20 22 24
13:36:53 <blsqbot> | 3 6 9 12 15 18 21 24 27 30 33 36
13:37:08 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41068&oldid=41067 * TomPN * (+48) /* 1 qubit transformations */
13:37:45 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41069&oldid=41068 * TomPN * (+48) /* 2 qubit transformations */
13:38:00 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41070&oldid=41069 * TomPN * (-1) /* 2 qubit transformations */
13:38:26 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41071&oldid=41070 * TomPN * (+48) /* 3 qubit transformations */
13:39:59 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41072&oldid=41071 * TomPN * (+71) /* def function */
13:40:34 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41073&oldid=41072 * TomPN * (+29) /* def function */
13:45:58 <elliott> Under a new five-year strategic partnership announced today, Yahoo Search will become the default search experience for Firefox in the U.S.
13:46:23 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41074&oldid=41073 * TomPN * (+50) /* Hadamard */
13:47:04 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41075&oldid=41074 * TomPN * (+4) /* Hadamard */
13:47:13 <elliott> https://blog.mozilla.org/wp-content/uploads/2014/11/Virgin-flight-27.jpg https://blog.mozilla.org/wp-content/uploads/2014/11/Suppenkuche-restaurant.jpg oh wow, they're trying to make it look pixel-for-pixel like google
13:47:41 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41076&oldid=41075 * TomPN * (+21) /* Hadamard */
13:48:31 <S1> Suppenkuche :3
13:48:33 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41077&oldid=41076 * TomPN * (+3) /* Hadamard */
13:49:52 <mroman> fizzie: isn't there nublength?
13:50:17 <mroman> it was on a todo list at some point
13:50:21 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41078&oldid=41077 * TomPN * (+45) /* Pauli X */
13:50:27 <mroman> but it doesn't look like it made it into 1.7.3
13:51:34 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41079&oldid=41078 * TomPN * (+46) /* Pauli Y */
13:52:21 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41080&oldid=41079 * TomPN * (+46) /* Pauli Z */
13:52:22 <mroman> !blsq {1 2 3 4 5}{2 3 4}ss
13:52:34 <mroman> !blsq {1 0 2 3 4 5}{2 3 4}ss
13:52:37 <mroman> !blsq {1 0 2 3 4 5}{0 2 3 4}ss
13:52:58 <blsqbot> | ERROR: Burlesque: (fi) Invalid arguments!
13:52:58 <blsqbot> | ERROR: Burlesque: (co) Invalid arguments!
13:53:15 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41081&oldid=41080 * TomPN * (+48) /* Phase shift */
13:54:31 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41082&oldid=41081 * TomPN * (+109) /* CNOT */
13:55:39 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41083&oldid=41082 * TomPN * (+106) /* SWAP */
13:56:19 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41084&oldid=41083 * TomPN * (+3) /* SWAP */
13:59:03 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41085&oldid=41084 * TomPN * (+357) /* Fredkin */
14:00:40 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41086&oldid=41085 * TomPN * (+357) /* Toffoli */
14:03:25 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=41087&oldid=40924 * TomPN * (-2) /* See also */
14:03:58 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=41088&oldid=41087 * TomPN * (-83) /* Example program */
14:04:09 <HackEgo> [wiki] [[Musical notes]] http://esolangs.org/w/index.php?diff=41089&oldid=41088 * TomPN * (+1) /* See also */
14:05:31 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41090&oldid=41038 * TomPN * (+25)
14:06:05 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41091&oldid=41090 * TomPN * (-2)
14:06:51 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41092&oldid=41086 * TomPN * (+23) /* See also */
14:07:18 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41093&oldid=41092 * TomPN * (+17) /* See also */
14:07:50 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41094&oldid=41093 * TomPN * (+26) /* See also */
14:08:21 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41095&oldid=41091 * TomPN * (+43) /* See also */
14:09:22 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41096&oldid=41095 * TomPN * (+40) /* See also */
14:09:48 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41097&oldid=41094 * TomPN * (+40) /* See also */
14:11:03 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41098&oldid=41097 * TomPN * (+30) /* See also */
14:11:24 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41099&oldid=41098 * TomPN * (-30) /* See also */
14:12:05 <HackEgo> [wiki] [[Talk:Quantum Dimensions]] N http://esolangs.org/w/index.php?oldid=41100 * TomPN * (+95) Created page with "== Quantum languages category == can somebody create a quantum languages category please? TomPN"
14:12:23 -!- hjulle has quit (Ping timeout: 255 seconds).
14:12:34 -!- Koen__ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
14:26:23 <mroman> not sure if this is short enough for anything
14:27:17 -!- idris-bot has joined.
14:28:34 -!- diginet has quit (Ping timeout: 265 seconds).
14:30:58 <mroman> fizzie: length for ints is btw. ln
14:31:50 -!- diginet has joined.
14:31:50 <fizzie> I know, I saw that in someone's solution.
14:33:02 <fizzie> `run echo '1123Zp' | dc
14:37:35 <mroman> It's lines for strings
14:58:43 -!- Phantom_Hoover has joined.
15:02:41 -!- hjulle has joined.
15:07:00 <blsqbot> | ERROR: Burlesque: (\[) Invalid arguments!
15:07:00 <blsqbot> | ERROR: Burlesque: ([[) Invalid arguments!
15:07:00 <blsqbot> | ERROR: Burlesque: (m[) Invalid arguments!
15:26:59 <blsqbot> | ERROR: Burlesque: (m[) Invalid arguments!
15:27:00 <elliott> maybe it should work on integers too!
15:27:12 <mroman> m[ can't map over integers
15:27:19 <mroman> [[ doesn't work then either
15:28:29 -!- hjulle has quit (Ping timeout: 244 seconds).
15:29:01 -!- tlewkow_ has joined.
15:41:46 -!- MDUd has changed nick to MDude.
15:47:51 <elliott> mroman: I'm sure you could figure out some meaning for them
15:47:55 <quintopia> i am fairly certain that, as a programming language and not something like a human with an advanced frontal lobe, it has no concept of good or evil
15:48:05 <elliott> mroman: maybe map it over every digit and then concatenate the result as an integer
15:49:08 <elliott> so mapping (- 1) on 1234 would give you 123, and on 101 it'd give you (0 * 10^2) + ((-1) * 10^1) + (0 * 10^0) = -10
15:50:23 <elliott> perhaps map (\x -> x*10 + x) 123 -> (11 * 10^2) + (22 * 10^1) + (33 * 10^0) = 1100 + 220 + 33 = 1353
15:51:04 -!- ais523 has joined.
15:53:23 -!- S1 has quit (Quit: S1).
16:01:14 -!- tlewkow_ has quit (Remote host closed the connection).
16:16:22 <Taneb> TONIGHT I WILL BAKE A CAKE MAYBE
16:16:53 -!- Dulnes has quit (Quit: Updating details, brb).
16:18:03 -!- Dulnes has joined.
16:19:37 -!- ais523 has quit (Ping timeout: 264 seconds).
16:21:24 -!- vanila has joined.
16:23:46 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 67 : Integer -> Integer
16:24:12 <Dulnes> is this why its colourful
16:24:14 -!- caps has joined.
16:24:38 -!- caps has left.
16:32:43 -!- ais523 has joined.
16:37:01 <J_Arcane> Hah! https://github.com/microcai/llvm-qbasic
16:38:35 <vanila> if he wants c call why not emit C
16:38:59 <vanila> http://microcai.org/2013/03/08/killubuntu.html lol
16:39:30 <vanila> "For every bug found in the softwre, there is a ugly man behind. For too many days!" - microcai
16:40:11 <elliott> does llvm-qbasic support the important drawing and PC speaker commands
16:45:38 <vanila> lead, load, goad, gold
17:18:44 <ais523> actually, this is the first thing that annoyed me about Windows
17:18:56 <ais523> and made me wonder if there were better options
17:19:02 <ais523> Windows 1 has an API for manipulating the PC speaker
17:19:10 <ais523> by Windows 3.1, it was deprecated but still worked
17:19:25 <ais523> it was removed some time between Windows 98 and Windows XP
17:19:39 <ais523> so I grudgingly had to check what they replaced it with, and the new replacement API didn't work
17:19:55 <ais523> you were meant to throw MIDI through the speakers, but the process would freeze for like 30 seconds when you loaded a MIDI file
17:20:07 <ais523> it worked after that, but that's an unacceptably long freeze
17:20:34 <ais523> (Windows Media Player was also affected by the freeze, but it happened when a file looped back to the start, rather than at the start of playback, for some reason)
17:20:37 -!- AnotherTest has joined.
17:29:31 -!- dts_Zzzz has changed nick to DTSCode.
17:46:15 <idris-bot> (NS (UN "+") ["Classes", "Prelude"])
17:46:15 <idris-bot> (Pi (TType (UVar -1)) (TType (UVar -1)))
17:46:52 <Melvar> (The type annotation is part of the quoting syntax.)
17:49:32 -!- AnotherTest has quit (Ping timeout: 244 seconds).
18:18:48 -!- `^_^v has joined.
19:03:44 -!- bitemyapp has quit (Quit: leaving).
19:26:01 -!- ais523 has quit (Read error: Connection reset by peer).
19:26:10 -!- ais523 has joined.
19:26:39 -!- Froox has changed nick to Frooxius.
19:34:29 -!- ais523 has quit.
20:01:13 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
20:04:04 -!- Patashu has joined.
20:23:15 -!- tlewkow_ has joined.
20:26:52 -!- Patashu has quit (Ping timeout: 255 seconds).
20:41:26 -!- DTSCode has changed nick to rabbitbiscuit.
20:41:59 -!- rabbitbiscuit has changed nick to DTSCode.
20:52:48 -!- tlewkow_ has quit (Remote host closed the connection).
21:00:19 -!- tlewkow has joined.
21:01:23 -!- tlewkow has quit (Remote host closed the connection).
21:23:25 -!- kcm1700 has quit (Remote host closed the connection).
21:23:36 -!- kcm1700 has joined.
21:54:58 -!- tlewkow_ has joined.
22:01:11 -!- scoofy has joined.
22:02:22 -!- supay has joined.
22:06:16 -!- DTSCode has changed nick to dts.
22:08:32 -!- dts has quit (Quit: Leaving).
22:08:51 -!- dts has joined.
22:09:40 -!- dts has quit (Changing host).
22:09:40 -!- dts has joined.
22:11:23 -!- hjulle has joined.
22:14:34 -!- dts has quit (Quit: Leaving).
22:15:16 -!- DTSCode has joined.
22:20:16 -!- DTSCode has quit (Quit: Leaving).
22:20:34 -!- dts has joined.
22:32:52 -!- oerjan has joined.
22:45:25 <oerjan> <mroman> it uses [()] <-- would you know, i answered precisely that as a stackoverflow question a while ago.
22:45:52 <HackEgo> dontaskdonttelllist: quintopia coppro myname mroman(use query)
22:47:13 <oerjan> i think my problem with using query is that it's only _partly_ a personal message, i want to say it in the channel as _well_.
22:50:15 <shachaf> link to the logs in /query
22:50:32 <Bike> maybe you need to chill
22:50:48 <oerjan> i guess that's better than repeating an entire monologue
22:50:57 <oerjan> Bike: no need to chill around here
22:51:03 <lambdabot> ENVA 202220Z 09003KT 9999 SCT029 M00/M01 Q1032 RMK WIND 670FT 14003KT
22:51:54 <oerjan> hm did that command get removed
22:52:00 <lambdabot> Local time for oerjan is Thu Nov 20 23:51:31 2014
22:52:06 <vanila> The only good gopher website I found is zzo38computer
22:52:15 <oerjan> nah your client just doesn't respond
22:52:18 <vanila> gopher seems very much abandoned
22:52:28 <vanila> I disabled CTCP after some trolls tried to get info on me
22:52:48 <oerjan> vanila: i think zzo38 knows of some other sites? don't know if they're good though.
22:53:13 <oerjan> hm do we have another brit
22:53:57 <oerjan> _are_ there more british or finnish in the channel, i think that came up the other day. also will fizzie be recounted when he moves
22:54:19 <nortti> oh, where is he moving to?
22:55:02 <oerjan> and somehow, i seem to remain the only norwegian.
22:57:04 <fizzie> Am I going to have to change my nick to "ukzzie"?
22:57:34 <vanila> yesterday I thought about an esolang but I couldn't make it turing complete
22:57:45 <oerjan> they don't _have_ to be turing complete
22:57:56 <vanila> http://paulino.cee.illinois.edu/Images/education/graph/graph_intro.png
22:58:14 <vanila> i like the idea of inputting a drawing like this and computation being something like a CA or similar on it...
22:58:18 <fizzie> Actually, I got slightly worried about the zem.fi domain, because you can't get a .fi domain if you don't live in Finland (even if you're a citizen) -- but if I read the law correctly, you can *keep* a legally obtained .fi domain indefinitely even if you move out.
22:58:19 <vanila> but there's no way to get infinite memory
22:58:30 <vanila> yeah it doesnt ahve to be but i think this one should be
22:58:40 <vanila> or shoudl i say, when I realized it wasnt that made it seem worse
22:58:47 <oerjan> vanila: i think you need infinite setup, _or_ a rule to grow new cells.
22:59:01 <vanila> both are kind of impossible
22:59:17 <vanila> so this idea fell flat
22:59:49 <oerjan> i see how growing new rules is tricky with that kind of layout, but infinite setup shouldn't be...
23:00:01 <vanila> you could have a infinite image!
23:00:14 <oerjan> although you could let new cells grow out of vertices
23:01:16 <oerjan> might make it hard to get them where you want, though.
23:01:31 <oerjan> vanila: well not as a png, sure
23:01:44 <vanila> I think thisis why there are so few graph language
23:02:08 <oerjan> well graphs are tricky to draw with nice layout
23:02:12 -!- Frooxius has quit (Read error: Connection reset by peer).
23:02:30 -!- Frooxius has joined.
23:03:55 -!- `^_^v has quit (Ping timeout: 264 seconds).
23:04:14 -!- blsqbot has quit (Ping timeout: 250 seconds).
23:05:55 <oerjan> also, http://www.chiark.greenend.org.uk/~sgtatham/puzzles/js/map.html
23:07:00 <oerjan> (you can also download the puzzle collection)
23:15:49 <vanila> it could be a challenge to write solvers for these puzzles
23:16:10 <shachaf> anagol does care about whitespace at the ends of lines, right?
23:18:39 <oerjan> <fizzie> And in general any extra whitespace at the end. <-- wait, not just newlines? this changes EVERYTHING.
23:19:30 <shachaf> unwords is a very long word.
23:22:15 <oerjan> although if what fizzie says is true, it doesn't if there is ONLY ONE LINE
23:22:43 <shachaf> if there's no line terminator at the end, is it truly a line?
23:22:55 <oerjan> as far as anagol is concerned.
23:25:30 <oerjan> unfortunately mapM + ++" " is even longer :(
23:25:45 <oerjan> so maybe it doesn't change that much.
23:28:33 <fizzie> oerjan: I'm pretty sure it's true. I think I've used . in Befunge-98 successfully for one-number-as-answer kind of thing, while it doesn't work for multi-line answers. (It adds a trailing space, like the Forth .)
23:29:17 -!- Phantom_Hoover has joined.
23:31:51 <oerjan> bah i cannot see how to use it for improving my A057755 solution, anyhow
23:32:00 <oerjan> (i have an ugly unwords in that)
23:33:32 <oerjan> bah henkma managed to tie int-e on it
23:33:41 <oerjan> (not surprising, but still...)
23:35:21 <shachaf> another long word is fromIntegral
23:37:59 <oerjan> not golf, that's for sure
23:38:59 <oerjan> fromInteger is 1 char shorter, i notice, in a pinch
23:39:18 -!- S1 has joined.
23:42:20 <Sgeo> Whee https://twitter.com/HeadDZombie/status/535513753178353664
23:42:32 <Sgeo> Wish I used the #jssummit hashtag though, no one's going to see that
23:45:28 <int-e> oerjan: yeah, henkma found the slow solution :)
23:45:53 <int-e> (I like the fact that the statistics come out the same)
23:46:49 <int-e> oerjan: read.show is even shorter
23:46:59 -!- mihow has quit (Read error: Connection reset by peer).
23:47:26 -!- mihow has joined.
23:48:09 <int-e> (ok, it will typically break even with toInteger, and possibly use, but I have not needed that particular conversion so far)
23:48:15 -!- mihow has quit (Read error: Connection reset by peer).
23:48:47 <oerjan> well it was shachaf who thought he needed it
23:48:53 -!- mihow has joined.
23:52:34 <oerjan> int-e: is your 51 solution on the parity one still non-cheating? i'm wondering if there's any point in trying not to cheat.
23:53:01 <oerjan> (well as in, actually reading the input)
23:53:07 <shachaf> I thought int-e said the 51 solution was cheating and the 57 solution wasn't.
23:53:39 <oerjan> yukko: lots of them are
23:53:51 <yukko> I did one at 35 points but it got a bit tedious
23:54:13 <int-e> and I expect henkma's 49 character one to be cheating as well, but who knows.
23:54:18 <shachaf> Is there a way to withdraw my solution?
23:54:28 <oerjan> yeah i think untangle gets quickly tedious because there isn't any _real_ difficulty in it
23:54:44 <oerjan> shachaf: i don't think so.
23:54:58 <oerjan> shachaf: make a better one >:)
23:55:04 <shachaf> oerjan: I want to be out of the system.
23:55:55 <oerjan> shachaf: you should have thought about that before hth
23:55:56 <int-e> If I had realized that there was only one (short) test case I wouldn't have submitted anything at all.
23:56:37 <int-e> But I only figured that out when conja beat me with 52 to 57 characters.
23:57:34 <int-e> (it's a pity too; I like that 57 characters code)
23:57:54 <oerjan> my first attempt was 59
23:58:12 <oerjan> well only attempt so far
23:58:21 <int-e> my first version was 62 because I wanted to use Data.List.
23:58:36 <int-e> as usual, it's not worth it.
00:00:02 <oerjan> oh wait that's obviously buggy
00:03:34 <oerjan> hm the fact that henkma managed to get the slow solution down to 53 chars is intriguing, since i haven't managed to get my fast ones down to 54...
00:03:47 <Taneb> I need to make my computer not-broken :(
00:04:01 <oerjan> Taneb: you need an un-axe hth
00:04:16 <Taneb> oerjan, I ordered one off Amazon
00:04:39 <oerjan> be careful to keep it away from firewood btw
00:04:56 <oerjan> don't want a tree suddenly growing in the living room
00:05:38 <oerjan> shachaf: i suggest testing that far from inhabited areas hth
00:05:46 <oerjan> possibly away from the planet
00:09:05 <Taneb> oerjan, we don't have a fireplace, that's not much of an issue
00:09:09 <Taneb> But I'll bear that in mind
00:18:02 <Taneb> How would you go about making a gold-backed cryptocurrency?
00:18:42 <vanila> Taneb, that doesn't make sense
00:18:51 <Taneb> vanila, that's half the point
00:18:54 <vanila> the point of a cryptocurrency is that its backed by crypto
00:19:00 <lambdabot> ESSA 202350Z 03005KT 6000 BR SCT009 BKN013 04/04 Q1030 R88/29//95 TEMPO 4000 BKN004
00:19:02 <vanila> you can't e.g. speed up encryption with gold
00:19:08 <vanila> unless you count the gold parts in your computer
00:19:20 -!- hjulle has quit (Remote host closed the connection).
00:19:28 <Taneb> (essentially, this is me being silly and wondering if it is actually possible)
00:19:47 <lambdabot> http://en.wikipedia.org/wiki/Dollar_coin_(United_States)
00:19:48 <lambdabot> Title: Dollar coin (United States) - Wikipedia, the free encyclopedia
00:19:50 <elliott> @google dollarcoin proof of dollar
00:19:55 <lambdabot> http://catalog.usmint.gov/presidential-2014-one-dollar-coin-proof-set-PE4.html
00:19:55 <lambdabot> Title: Presidential 2014 One Dollar Coin Proof Set - US Mint
00:20:03 <oerjan> Taneb: i think i've seen the idea somewhere
00:20:08 <oerjan> i suspect so has elliott
00:20:16 <elliott> @google dollarcoin sigbovik
00:20:17 <Taneb> oerjan, I maaaaay have mentioned it in the past, but dollarcoin? HMMM
00:21:36 <oerjan> you know, that could actually be interesting if it was still otherwise anonymous...
00:22:41 -!- dts has changed nick to dtsbot.
00:22:55 -!- dtsbot has changed nick to nasabot.
00:23:42 <vanila> http://alexey.radul.name/ideas/2013/cleverness-of-compilers/
00:24:20 -!- nasabot has changed nick to dts.
00:25:59 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
00:26:49 <oerjan> i don't think IE likes that mandelbrot program :(
00:27:10 <vanila> are you on windows 96?
00:28:11 <oerjan> it just froze for a few seconds, but it wasn't as bad as i feared
00:34:16 * FireFly confiscates oerjan's swatter
00:34:53 <oerjan> it's ok, it always gets back somehow
00:35:19 <shachaf> that's because it's not an actual swatter, it's just you pressing some keys on your keyboard to type some ascii art
00:35:27 <int-e> > cycle "swatter "
00:35:28 <lambdabot> "swatter swatter swatter swatter swatter swatter swatter swatter swatter swa...
00:35:46 -!- Bicyclidine has joined.
00:35:52 <oerjan> i'd swat you but someone stole my swatter.
00:36:16 <int-e> shachaf has a point; next time, we should confiscate oerjan's keys
00:37:23 <int-e> AAnn eexxttrraa sseett ooff kkeeyyss wwoouulldd ssuurreellyy cccoommee iinn hhaannddyy..
00:37:27 <shachaf> oerjan: i was looking for past swattings in logs but i keep finding bf programs hth
00:37:46 <int-e> oh, a triplicate c, how did that happen.
00:38:22 <int-e> ttyyppiinngg lliikkee tthhiiss iiss ssuurrpprriissiinnggllyy hhaarrdd..
00:38:40 <oerjan> hm programming challenge: write "Hello, world!" in your favorite language, but using only doubled characters
00:39:21 <oerjan> (a hello world program, that is)
00:39:29 <vanila> i'd be surprised if thats possible!
00:39:41 <oerjan> there's probably _some_ language_ in which it is.
00:39:44 <int-e> let's see. brainfuck is out; unlambda is out; haskell is out ...
00:40:03 <MDude> The "" always mathcing with itself could be a problem.
00:40:08 <oerjan> are you sure brainfuck is out? hm i guess you can only get even byte values
00:40:56 <shachaf> my favorite language is cut -c1,3,5,7,9,11,13,15,17,19,21,23,25,27,29 hth
00:42:01 <oerjan> is haskell on the ghci command line out
00:42:38 <vanila> invent new language where even second byte is ignored
00:42:57 <oerjan> i think we shall ignore previously undefined languages
00:43:14 <oerjan> you can just start with vv
00:43:35 <oerjan> admittedly every second line must be empty
00:43:42 -!- tlewkow_ has quit (Remote host closed the connection).
00:43:49 <shachaf> newlines have to be doubled too
00:43:51 <oerjan> but this seems not as obviously impossible
00:44:00 <oerjan> shachaf: that's equivalent to what i said
00:44:16 <shachaf> if i had read what you said i wouldn't have said what i said
00:44:44 <int-e> What about BLC, hmm. The text version won't do the trick, but the 8 bit version could have enough degrees of freedom.
00:46:24 <shachaf> oerjan: hmm, in haskell you can write [[qq||bbllaahh||]]
00:46:39 <shachaf> conveniently qq is a doubled letter and all the quasiquoters are called qq
00:47:06 <shachaf> But I don't think you'll manage to import anything to use them.
00:47:41 <oerjan> shachaf: inconveniently, {{--##LLAANNGGUUAAGGEE QQuuaassiiQQuuoottees##--}} isn't what you want
00:47:55 <int-e> -- aatt lleeaasstt yyoouu ccaann hhaavvee ccoommmmeennttss..
00:48:09 <shachaf> oerjan: oh, come on, jjuusstt ppuutt iitt in the cabal file
00:48:13 <shachaf> that doesn't have to be doubled
00:48:17 <int-e> oerjan: you forgot to double the 's' there, hth
00:48:55 <oerjan> ...ok maybe that's a bit too far
00:50:14 -!- dts has changed nick to dts|offtowork.
00:51:32 <int-e> oerjan: yeah, maybe.
00:52:04 <ion> wwee mmiigghhtt nneeeedd ttoo ddiissaabbllee llooccaall eecchhoo..
00:52:25 <shachaf> oerjan: at least you can compile c files
00:53:02 <oerjan> the combinator calculus style can be used somewhat
00:53:41 <oerjan> ((((KK))((KK)))) gives K
00:53:57 <int-e> ``((II))MN works for application
00:53:58 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `((II))MN: not found
00:54:15 <int-e> oh, that's not even necessary
00:54:20 <oerjan> int-e: you can mix styles? although you don't need it
00:54:23 <MDude> Is there a language where two escape characters causes the character after the second escape character to be ignored?
00:54:38 <oerjan> so the question is, can we get S
00:55:09 <elliott> oerjan: you have K, so yes.
00:55:39 <int-e> ((00)) is a shorter K.
00:55:54 <oerjan> int-e: i didn't know you could mix styles, i said
00:57:09 <int-e> ((KK((KK))SS)) looks kind of pretty
01:02:58 -!- tlewkow_ has joined.
01:07:35 -!- tlewkow_ has quit (Ping timeout: 258 seconds).
01:18:57 <ion> http://www.varissuonliikekeskus.fi/staff/12-K-Supermarket_Annika_7757.jpg
01:19:12 -!- S1 has quit (Quit: S1).
01:19:23 -!- vanila has quit (Quit: Leaving).
01:22:39 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
01:22:47 -!- idris-bot has quit (Quit: Terminated).
01:27:43 <FreeFull> I should learn how to work with SKI calculus at some point
01:30:33 <Taneb> It's generally easier to work in lambda calculus and translate
01:37:12 <Taneb> I can't get in my head what a quotient group is :(
01:37:42 <Bicyclidine> it's like, you have a group, but then add an equivalence class based on some other group.
01:37:53 <int-e> why? you just take the congruence classes of a congruence relation on some group.
01:38:18 <Bicyclidine> because when someone asks what it is they say something like that, int-e
01:39:15 -!- idris-bot has joined.
01:40:12 <int-e> If examples work for you, that's how you get from addition on Z to addition in Z/kZ (i.e. modulo k): you take the relation that relates a and b if a-b is divisible by k.
01:47:02 <oerjan> the special thing about groups and things inheriting from groups is that the congruence relations are determined by the set of elements congruent to the identity.
01:47:25 <oerjan> this does not hold e.g. for semigroups and monoids
01:48:58 <Bicyclidine> i guess i think of it with sameness. Z/2Z is the integers except all even integers (2Z) are the same. so 2 = 4 = 6. Since 3 = 2 + 1, 3 = 5 = 7. so you're left with {0,1} and they add in a modulary way.
01:53:54 <int-e> Right, where 0 is a representative for 2Z and 1 represents 2Z+1.
01:57:55 <oerjan> <Taneb> TONIGHT I WILL BAKE A CAKE MAYBE <-- did this happen
01:58:07 <Taneb> Did other things instead
01:58:18 <oerjan> WELL THERE'S YOUR PROBLEM
01:58:19 <Taneb> And tomorrow instead of going to cakenight I will be playing D&D
01:59:18 <int-e> . o O ( drunk & depressed )
02:00:40 <Taneb> I don't think that is why I didn't make cake
02:01:32 <MDude> Fumbled your baking roll?
02:02:53 <oerjan> critical failure, cake eaten by monster
02:03:06 <oerjan> (also ate half of party)
02:03:16 <Taneb> (joining an in-progress game as a barbarian)
02:04:07 <Taneb> Which is a little out of my comfort zone, but it could be fun
02:04:18 <oerjan> timeo barbaros, et placentas ferentes
02:06:07 <Taneb> If my Latin is up to scratch, that summarizes most of my D&D characters
02:06:45 <Taneb> Although my character in an upcoming not-D&D game is definitely neither, being literally Silvio Burlusconi
02:07:30 <oerjan> is the misspelling intentional twh
02:09:10 <Taneb> The game will be about; the year is 2020 and the G8 are having to deal with First Contact
02:09:58 <Taneb> Anyway I should sleep
02:10:16 <oerjan> so literally fictionally literally
02:13:00 <Taneb> (I'm assuming as soon as his bad on holding public office is over Berlusconi will weasel his way back into power)
02:15:55 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
02:24:26 -!- idris-bot has quit (Quit: Terminated).
02:40:19 -!- adu has joined.
02:52:45 <shachaf> How does Anagol scoring work? Do you get 10000 points per language per problem if you're the only person to solve that problem with that language?
02:54:02 <shachaf> It sounds like if you wanted to get lots of points, you would autogenerate inefficient solutions for every available language for every problem, rather than spend time golfing.
03:02:46 <FireFly> I think only the shortest solution overall for a problem gets 10000
03:04:36 <shachaf> What, so people writing in golfscript or what have you always get the points?
03:05:24 <FireFly> If by golfscript you mean burlesque
03:06:25 <FireFly> I don't think the score is accumulated anyhow, so I'm not sure how meaningful it is
03:07:36 <oerjan> pretty sure golfscript sometimes beats burlesque...
03:08:39 <oerjan> also yes it is http://golf.shinh.org/u.rb
03:10:01 <shachaf> oerjan: is there anything i can do at this point to not appear on that page twh
03:10:53 * oerjan doesn't actually know but thinks shachaf should chill
03:13:38 <oerjan> huh i'm already at 28th place in haskell
03:16:02 <oerjan> hm zzo38 is a bit below but he has a better average
03:16:17 <oerjan> there should be some way to sort by average
03:17:08 <int-e> shachaf: I suppose if you were to send the owner a mail asking nicely then he'd remove you from the database.
03:17:38 <shachaf> int-e: i have decided to chill
03:19:12 <oerjan> int-e: i think i essentially found your 57 char solution
03:20:16 <int-e> oh I had not found the per language user lists.
03:21:21 <int-e> ok, that rank is not very meaningful.
03:21:40 <oerjan> when you have >9000 average the rest is basically just stamina
03:26:32 <oerjan> i have a hunch the only non-alpha difference is that you use ; where i use newline
03:27:35 <shachaf> Aren't those both non-alpha?
03:27:45 <oerjan> shachaf: alpha equivalence, i mean
03:27:57 <shachaf> I thought you were counting symbols.
03:28:10 <oerjan> thus concluding int-e uses ;
03:28:21 <oerjan> (which is no surprise since he always does)
03:28:37 <oerjan> http://golf.shinh.org/p.rb?different+letters+parity
03:28:57 <oerjan> i couldn't bring myself to remove the quotes while it's still erroring out at the end
03:29:05 <shachaf> I wonder how leonid did 26 characters in Ruby.
03:34:03 <shachaf> You have 51 characters for a cheating solution?
03:35:03 <oerjan> i haven't started on the cheating yet
03:35:12 <oerjan> just found out how you got the 162450548
03:35:47 <shachaf> Oh, you said you found the 57 solution. Never mind.
03:38:17 <oerjan> first cheat attempt was longer than the proper one :P
03:39:00 <int-e> embedding "0010111000110011011101011001" gives me 52 characters.
03:39:17 <shachaf> int-e: Yes. That one's easy.
03:39:37 <oerjan> so converting from a number doesn't pay, ok
03:39:40 <shachaf> I was wondering whether you could go lower while embedding it as a string, but I don't think so.
03:40:21 <shachaf> int-e: that's a long way of writing True. 1>0 is shorter hth
03:40:45 <int-e> shachaf: thanks for the advice
03:40:49 <oerjan> int-e: i just sort of assumed if you get that close, it's more likely you just adjusted that a bit...
03:41:21 <oerjan> maybe thinking like that is a reason i don't get the golfing :(
03:42:30 <oerjan> i'm not even sure how you get the PID in haskell, but i'm assuming it needs an import.
03:42:47 <int-e> oerjan: well you know it's wrong; but it's really hard to get over one self and start a solution from scratch.
03:43:30 <oerjan> wait, are we talking golfing or life guidance here
03:44:37 <int-e> The easiest is System.Posix.getProcessID I think
03:45:32 <int-e> oerjan: I'm talking about golf, but that doesn't mean what I'm saying is not more widely applicable.
03:45:57 <shachaf> int-e: is it applicable to code golf too?
03:47:19 <int-e> shachaf: ... I'd clarify but you know exactly what I meant. Where'd that mapole bat get to?
03:48:37 <shachaf> all we have left are hungus prods and saucepans
03:48:54 <shachaf> and oerjan's hoarding the saucepan
03:49:12 <oerjan> well boily has the mapole, but he's not around
03:49:33 <int-e> oerjan: can you test the resonant frequency of that pan on shachaf?
03:49:34 <shachaf> he's usually pretty gentle with it, anyway
03:49:57 <int-e> I should think of a weapon of my own.
03:50:12 <oerjan> something more int-elligent
03:51:02 <shachaf> what does your nick mean, anyway
03:51:07 * int-e sprays shachaf with grey goo
03:51:25 <int-e> (I hope that's intelligent enough.)
03:53:36 <HackEgo> olist 968: shachaf oerjan Sgeo FireFly boily nortti
04:01:25 <shachaf> Oh, that's how the 51 solution works.
04:04:07 <oerjan> cojna's statistics seem a bit different
04:05:01 <int-e> oerjan: easy, don't use `` and don't use ;
04:05:36 <int-e> oh you have one more letter... interesting.
04:06:32 -!- ZombieAlive has quit (Remote host closed the connection).
04:08:54 <shachaf> fromEnum is also a v. long name
04:10:01 <oerjan> did you get a hint from my solution ...
04:10:25 <shachaf> Oh, there are several somewhat different 51 solutions.
04:10:33 <oerjan> i now have a second 51
04:10:49 <int-e> no hard hint, but the idea that one could get the same length with different number of alphanums put me on the right track
04:11:52 <int-e> and it's funny, I cannot match henkma's statistics.
04:12:31 <oerjan> which however match cojna's
04:13:44 <shachaf> is comparing solutions of the same length with someone else frowned upon
04:14:59 <int-e> I wouldn't do it. It's quite likely that there are distinct ideas in there.
04:15:16 <int-e> (which can be combined)
04:15:29 <shachaf> but can be combined by both parties
04:15:42 <int-e> putting third parties at a disadvantage
04:16:23 <oerjan> i'm pretty sure anagolf explicitly says you're allowed to release spoilers
04:17:10 <int-e> It does. I still wouldn't do it. :)
04:22:41 <oerjan> this is strangely similar to that A057755 sequence
04:23:17 <oerjan> once again, i have an idea for shortening by 2 that fails because it produces everything in the wrong order
04:23:18 <int-e> I don't know why you're stuck on A057755.
04:23:55 -!- copumpkin has joined.
04:24:00 <oerjan> well or 1 in the other case
04:24:07 <shachaf> That one was length (show (2^2^n))?
04:24:27 <int-e> shachaf: that's 2 spaces and another chracter too long
04:24:51 <int-e> (possibly 2, but that depends on the context)
04:25:33 <shachaf> i'm not golfing i'm communicating hth
04:26:17 <int-e> shachaf: just getting back at you for the "1>0 is shorter" snipe
04:26:32 <oerjan> anyway, the most trivial solution to that i thought of is 54 chars, which is 1 char too long.
04:26:52 <oerjan> and all my other approaches end up longer.
04:27:35 <oerjan> and int-e's solution is much faster than the trivial one.
04:27:52 <oerjan> although henkma's _isn't_, so maybe you can get it that way
04:28:14 <int-e> I still consider submitting the fast one a psychological success so far :P
04:28:45 <oerjan> shachaf: imprecisely, though
04:29:29 <shachaf> i have six slightly different 51 solutions
04:30:08 <oerjan> i just have 3. well i guess i erased some.
04:30:53 <lambdabot> (!!3)<$>transpose[show$foldr(\k a->2*10^2^n+a*k`div`(2*k+1))0[1..2^n]|n<-[0..]]
04:30:56 <lambdabot> [show(sum$scanl div(100^n)[1..[4..]!!n])!!n|n<-[0..]]
04:31:36 <int-e> [4..]!!n <-- ouch, isn't that just n+4.
04:31:43 -!- ZombieAlive has joined.
04:32:17 <shachaf> > [show(sum$scanl div(100^n)[1..[4..]!!n])!!n|n<-[0..]]
04:32:19 <lambdabot> "271828182845904523536028747135266249775724709369995957496696762772407663035...
04:32:35 <int-e> > [show(sum$scanl div(100^n)[1..n+4])!!n|n<-[0..]]
04:32:36 <lambdabot> "2718281828150208757*Exception: Prelude.(!!): index too large
04:33:33 <shachaf> [0..]!! is another way to do fromInt
04:34:34 <J_Arcane> anyone have any thoughts on this? https://github.com/jarcane/heresy/issues/5
04:42:03 <int-e> damn, how did henkma do it...
04:45:54 <shachaf> oerjan: do you want to compare 51s
04:50:50 <shachaf> does anagol only check stdout?
04:51:12 <shachaf> what's the shortest way to write _|_?
04:51:30 <shachaf> well. to write a _|_ that crashes the program
04:51:33 <int-e> usually some kind of pattern match failure
04:51:36 <shachaf> or is terminating with timeout ok?
04:51:49 <shachaf> timing out with the right output
04:53:42 <oerjan> 1/0 looks pretty short
04:54:39 <oerjan> i've also had output get cut off when i tried to error out in pure code
04:54:51 <oerjan> as in, using interact rather than mapM print
04:55:59 <oerjan> if anagolf has blackholes enabled, then x=x should work...
04:56:04 <Sgeo> I wish I understood enough about My Little Pony to understand all of this https://www.youtube.com/playlist?list=PLD873B11F5D796B41
04:58:03 <oerjan> ah indeed blackholes work
04:58:42 <shachaf> Ah, that's one shorter than []!!0
04:58:55 <shachaf> Unless I use it more than once.
04:59:53 <shachaf> Right. Unless you use it more than once.
05:00:36 <int-e> in which case you may be bitten by the dreaded monomorphism restriction
05:01:08 <oerjan> in theory, you shouldn't
05:02:35 <shachaf> This approach is at 57 right now. I doubt it'll work.
05:02:57 <oerjan> well is it a non-cheating one
05:03:48 <oerjan> (where in this problem we define that as "actually solves the general problem rather than just printing the right output")
05:06:09 -!- adu has quit (Quit: adu).
05:12:39 <int-e> shachaf: I don't think I've ever written an explicit bottom while code golfing Haskell. Writing function with undefined cases, otoh, I've done quite a bit.
05:13:48 <shachaf> so that brings me back to 51
05:13:50 <int-e> and then there's this recurring pattern: m@main=getLine>>=f>>m, with termination on end of input because getLine fails.
05:15:42 <shachaf> is there a better way to write a _|_ base case than f n|n>0=...?
05:18:55 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
05:20:10 * oerjan reverse engineer's shachaf's idea
05:23:39 -!- J_Arcane has joined.
05:25:59 <int-e> oh I had one in my Make 24 entry, but indeed that wasn't worth it.
05:29:29 <int-e> > length "c%(x:y)|(a,b)<-divMod c x=b:a%y" - length "c%(x:y)=mod c x:(div c x)%y"
05:29:46 <int-e> err, and that's still 2 characters too long
05:30:16 <int-e> > length "c%(x:y)|(a,b)<-divMod c x=b:a%y" - length "c%(x:y)=mod c x:div c x%y"
05:31:01 <shachaf> I was pleased with this solution but it's too long. :-(
05:34:27 <int-e> > scanl (\x k->2*x+k+1) 0 [0,0,1,0,1,1,1,0,0,0,1,1,0,0,1,1,0,1,1,1,0,1,0,1,1,0,0,1] -- hmm, no.
05:34:29 <lambdabot> [0,1,3,8,17,36,74,150,301,603,1207,2416,4834,9669,19339,38680,77362,154725,3...
05:34:38 <int-e> > foldl (\x k->2*x+k+1) 0 [0,0,1,0,1,1,1,0,0,0,1,1,0,0,1,1,0,1,1,1,0,1,0,1,1,0,0,1]
05:35:08 <int-e> > foldl (\x k->2*x+k+1) 0 $ reverse [0,0,1,0,1,1,1,0,0,0,1,1,0,0,1,1,0,1,1,1,0,1,0,1,1,0,0,1]
05:35:55 <shachaf> > preview binary "0010111000110011011101011001"
05:36:00 <shachaf> > preview binary $ reverse "0010111000110011011101011001"
05:36:46 <Dulnes> hhh what are you talking about now?
05:36:51 <oerjan> i've wanted to use 48445273 but i cannot get things to come out in the right order
05:37:24 <Dulnes> Why do you need binary?
05:37:45 <int-e> Dulnes: in essence, we're compressing this string: 0010111000110011011101011001
05:37:49 <oerjan> Dulnes: trying to solve a golfing problem with compression
05:38:21 <shachaf> Do people object to me posting 51 solutions?
05:39:02 <Dulnes> why would they object to 51?
05:39:27 <int-e> it's fun to discover tricks onself
05:40:27 <int-e> but I guess we've discussed this problem so much now that only getting below 51 is still a bit of a mystery
05:42:12 <shachaf> I used divMod for f(x,y)|x>0=print y>>f(x`divMod`2);main=f(215443002,0)
05:42:27 <shachaf> In theory it could actually help with that approach, maybe.
05:43:34 <Dulnes> Mmm have fun golfing im still trying not to break stuff
05:44:08 <int-e> > let f(x,y)|x>0=show y++f(x`divMod`2) in f(215443002,0)
05:44:09 <lambdabot> "0010111000110011011101011001*Exception: <interactive>:3:5-36: Non-exhaustiv...
05:45:15 <Dulnes> im awful at compressing stuff when it comes to this
05:46:47 <oerjan> wait what's the difference between 215443002 and 162450548 here
05:47:06 <int-e> > (162450548 + 2^28)`div`2
05:47:31 <shachaf> > let f(x,y)|x>0=show y++f(x`divMod`2) in f(162450548,0)
05:47:32 <lambdabot> "0001011100011001101110101100*Exception: <interactive>:3:5-36: Non-exhaustiv...
05:49:07 <oerjan> Dulnes: you can probably check if idris-bot is around in your client somehow
05:50:35 <oerjan> (trying to tab complete works for me)
05:51:04 <Dulnes> yeh /msg works but idk if it still shows functions it didnt last time i tried it didnt respond
05:51:40 <oerjan> um it cannot respond if it's not online
05:51:44 <int-e> shachaf is really close to a 49 character solution.
05:52:33 <shachaf> int-e: too late, i already gave up
05:52:40 <shachaf> but maybe now with your SPOILERS i'll try again
05:52:58 <Dulnes> 50 is more achievable imo
05:53:52 <shachaf> i like how |x<- is the same length as \x->
05:55:03 <Dulnes> oerjan: also you could have said it wasnt online so i didnt have to look for it
05:55:46 <oerjan> Dulnes: i've noticed you giving commands when it isn't here before, so i'd rather you find out how to check that yourself :P
05:56:07 <Dulnes> i never check the online tab tbh
05:56:24 <Dulnes> brb i must take that calc else where
05:57:36 -!- vanila has joined.
06:00:17 <int-e> (Of course, the divMod is not worth it in the end.)
06:00:24 -!- adu has joined.
06:01:07 <Dulnes> whoops i didnt div it crap
06:01:13 <oerjan> um the variations with div and mod split are also 51
06:02:52 <shachaf> Dulnes: what are you doing
06:02:58 <shachaf> i don't understand any of the things you're saying
06:03:02 <shachaf> are you talking to someone here?
06:05:36 <Dulnes> myself idk whatever making notes?
06:06:06 <int-e> oerjan: I don't know how you could end up with 51 :)
06:06:41 <shachaf> Is oerjan just talking about f n|n>0=print(n`mod`2)>>f(n`div`2);main=f 162450548 ?
06:07:23 <oerjan> shachaf: no, i'm talking about main=f 162450548;f n|n>0=print(mod n 2)>>f(div n 2) hth
06:07:48 <int-e> oerjan: okay, but that's not shachaf's version.
06:08:09 <oerjan> int-e: it's what i reversed engineered from his hints before
06:08:44 <int-e> Anyway, I think I've said too much for you, and probably too little for shachaf.
06:09:43 <oerjan> (also, i had exactly those variable names)
06:11:09 <int-e> I had main=f 162450548;f n|n>0=print(n`mod`2)>>f(n`div`2)
06:11:35 <oerjan> i also don't see how the 215443002 thing would work without divMod and be shorter
06:11:56 <shachaf> did you also have main=mapM(\n->print$162450548`div`2^n`mod`2)[0..27]
06:12:00 <shachaf> or main=mapM print[mod(162450548`div`2^n)2|n<-[0..27]]
06:12:48 <oerjan> main=mapM print[mod(div 162450548$2^n)2|n<-[0..27]] hth
06:13:13 <oerjan> i have a point-free variant of the former
06:13:32 <shachaf> main=mapM(\n->print$162450548`div`2^n`mod`2)[0..27]
06:13:32 <shachaf> main=mapM(\n->print$mod(162450548`div`2^n)2)[0..27]
06:13:33 <shachaf> main=mapM(print.(`mod`2).div 162450548.(2^))[0..27]
06:13:33 <shachaf> main=mapM print[162450548`div`2^n`mod`2|n<-[0..27]]
06:13:33 <shachaf> main=mapM print[mod(162450548`div`2^n)2|n<-[0..27]]
06:13:52 <int-e> Now there's a route I didn't try at all.
06:14:07 <oerjan> see what you've done, now int-e will get 48
06:14:17 <int-e> that is ... unlikely.
06:14:18 <Dulnes> ( off topic ) whats the easiesr way to measure the curvature of a circle and a siclicle shape? )
06:14:51 <int-e> siclicle <-- you may want to check the spelling of that.
06:15:06 <oerjan> no, that's obviously a very sharp icicle
06:15:44 <int-e> oerjan: "i also don't see how" <-- that's your problem right there ;-)
06:17:46 <oerjan> shachaf: i think we shall be happy they don't usually have icicles in sicily or we would all be dead
06:18:08 <shachaf> oerjan: not to mention siclicles
06:18:37 <Dulnes> I spelt a word wrong whatever
06:18:53 <oerjan> Dulnes: are you using a compass and ruler
06:19:30 <oerjan> you need to find the center of the circle, the curvature is the inverse of the radius iirc
06:19:59 <int-e> also there are mathworld and wikipedia articles on curvature
06:20:21 <int-e> including formulas in terms of derivatives, ready to plug stuff in
06:20:26 <Dulnes> like the exact x y z cordinates of a curvature
06:20:46 -!- MDude has changed nick to MDream.
06:20:50 <oerjan> ...a curvature is a number, not a point
06:20:57 <Dulnes> wiki is awful mathworld is bleh ill just whatever ive got dis
06:21:32 <shachaf> oerjan: are you sure it's not secretly a linear map hth
06:21:51 <oerjan> shachaf: well there's probably _some_ way to make it that. there always is.
06:27:55 <int-e> oerjan: https://en.wikipedia.org/wiki/Curvature_vector#Normal_or_curvature_vector hth
06:30:36 <Dulnes> welp nvm that was helpful int-e
06:31:10 <Bike> curvature's only a number in 2d, aka worst-d
06:31:31 <shachaf> Bike: p. sure 3d is worst-d
06:31:39 <Bike> 2d doesn't even have chaos
06:31:41 <Bike> imo? fuck that
06:32:14 <shachaf> 3d is full of all sorts of scow
06:32:31 <Dulnes> bike go turn a sphere inside out
06:32:38 <Bike> i used to be a boy scout, you know
06:32:54 <shachaf> Look, Dulnes, what are you doing here?
06:33:00 <shachaf> I really don't understand.
06:33:23 <Dulnes> And? im only asking i do code stuff during the day
06:33:51 <vanila> Have you tried Windows 93
06:34:07 <Bike> anyway, curvature is bilinear in three dee.
06:34:15 <Bike> i hear physicists care about this for some reason.
06:34:15 <vanila> Bike, Do you kno anything about 3d knots?
06:34:54 <oerjan> Bike is a bike, so he has no use for shoelaces
06:35:15 <shachaf> oerjan: in my experience bikes like to eat shoelaces
06:35:39 <Bike> i guess curvature is a tensor (field) in 2d too, but nobody cares since it's pretty boring tensorwise.
06:35:58 <Bike> and i guess saying "bilinear in three dee" is wrong too, in a way.
06:36:03 <Bike> no wonder nobody likes math.
06:36:16 <int-e> Bike: don't jump to conclusions like that
06:36:32 <int-e> Bike: but I'm curious what the variables are when you say that curvature is bilinear.
06:36:51 <Bike> int-e: directional vectors on the 2-manifold
06:36:51 <int-e> "nobody likes math" is definitely untrue.
06:37:00 <Bike> the... 2d manifold? words are also bad
06:37:25 <Bike> int-e: i mean, you know. if you have a sphere and a saddle point, they might have the same curvature in one direction along the manifold but not another.
06:38:38 <Bike> wow i just confused levi-civita symbols with levi-civita connections. again, no wonder nobody likes math
06:39:03 <Bike> wikipedia even says "not to be confused with". but what did I do? i confused with. i'm terrible. no wonder nobody likes Bike.
06:39:11 <Dulnes> vanila 93 isnt existent unless you think of the multiverse theory where there is a universe that has it
06:39:26 <vanila> Dulnes, yes its real I run it web browser http://www.windows93.net/
06:40:04 <Dulnes> i thought you meant something that was sold
06:40:35 <Dulnes> Its your childhood OS on acid
06:41:39 <Dulnes> Ok you hooligans get back to your compression stuff
06:41:52 <Dulnes> Didnt mean to interupt
06:44:21 <oerjan> int-e: THX TDH HTH HAND
06:44:40 <int-e> oerjan: did or didn't?
06:45:00 <oerjan> i don't use D to mean didn't, i think
06:45:32 <int-e> oerjan: glad to help (GTH ... ah, better not abbreviate it like that.)
06:46:46 <oerjan> now if uncurry were shorter, divMod _might_ help
06:49:07 <oerjan> we can only assume that poor cojna has forgot to remove two spaces.
06:49:27 <int-e> shachaf: A very useful trick in golfing is to exploit the special syntax that Haskell offers for two-argument functions.
06:53:25 -!- adu has quit (Quit: adu).
06:54:54 <shachaf> int-e: Yes, I've done that plenty of times.
07:26:39 -!- oerjan has quit (Quit: Nite).
07:27:54 -!- vanila has quit (Quit: Leaving).
07:30:56 -!- Patashu has joined.
07:34:34 -!- Patashu has quit (Remote host closed the connection).
07:34:45 -!- Patashu has joined.
07:43:52 -!- dts|offtowork has changed nick to dts.
08:57:37 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=41101&oldid=41012 * 134.169.181.220 * (+42) /* Normal implementations */
09:05:32 <mroman> @tell oerjan You can remove me from the dontaskdonttelllist
09:05:54 <mroman> or someone in here who knows sed well enough can do it
09:07:33 <int-e> `` sed -i 5d bin/dontaskdonttelllist
09:09:39 <int-e> sed -i /mroman/d bin/dontaskdonttelllist would've been clearer, I guess.
09:11:58 -!- dianne has quit (Ping timeout: 245 seconds).
09:13:56 -!- dianne has joined.
09:18:04 <shachaf> int-e: I spent so much time earlier trying to figure out how to get rid of the parentheses in (x`div`2)#(x`mod`2)
09:18:22 <shachaf> Now I came back to the computer and saw it right away, of course.
09:18:55 <HackEgo> dontaskdonttelllist: quintopia coppro myname
09:19:00 <int-e> shachaf: but that's normal, missing the blatantly obvious because one is preoccupied with looking for clever tricks.
09:19:22 <shachaf> I was trying things out with an operator earlier but I couldn't get the precedence working.
09:19:55 <shachaf> I assume your solution is alpha-equivalent to mine now.
09:20:11 <int-e> why is everybody using # out of the four possibilities (#, %, !, ?)?
09:20:44 <shachaf> But I got odd errors and I thought maybe Data.Ratio was imported by default (it wasn't).
09:20:46 <int-e> shachaf: I have two solutions, one based on your earlier code, one quite a bit different (but also using an infix operator for profit).
09:21:40 <shachaf> ! is taken for BangPatterns. ? is taken for ImplicitParams.
09:21:51 <shachaf> % is taken for Data.Ratio. # is taken for MagicHash.
09:22:26 <shachaf> Not to mention all sorts of Unicode symbols.
09:22:35 <shachaf> I guess length is measured in bytes, though.
09:22:43 <int-e> which don't help in anagol, because ... exactly.
09:24:56 <shachaf> By the way, turns out PatternGuards are in Haskell 2010.
09:25:10 <int-e> yes, they're useful
09:25:14 <int-e> less useful is FFI.
09:25:18 <shachaf> It can be a compact substitute for let if in some cases, if nothing else.
09:25:30 <shachaf> It was pretty useful for that thing that imported C rand.
09:25:47 <int-e> exactly. and that has been the only case so far.
09:26:39 <shachaf> Golfed programs tend to be hard to read, so I keep having this urge to make my programs hard to read so they'll be shorter.
09:27:17 <shachaf> As long as it manifests itself as not writing spaces, it kind of works...
09:27:27 <shachaf> But I need a better heuristic.
09:32:41 <mroman> int-e: by convention you use #
09:35:42 <int-e> no, I use ? by convention ;)
09:36:58 <mroman> That's not how conventions work.
09:40:08 <int-e> I disagree. It is a convention, because I'm consistent about this. Maybe there's another, more generally accepted convention, but that's besides the point.
09:48:36 -!- dts has changed nick to dts_Zzz.
11:11:07 -!- Phantom_Hoover has joined.
11:20:44 -!- boily has joined.
11:22:13 <mroman> I bet you use camelCase when programming in LISP!
11:31:09 <int-e> unlikely; that would make the code look inconsistent if I use any standard functions
11:34:22 <int-e> but for ? vs. # I see no reason whatsoever to prefer # over ?.
11:35:19 <int-e> (as a rule I'm not using implicit parameters; I'm more likely to use MagicHash)
11:35:33 <mroman> because notogawa prefers # over ?
11:35:39 <mroman> and he's like the god of haskell golfing
11:36:09 <int-e> I didn't know notogawa when I made the choice to prefer ?.
11:37:09 <fizzie> I always worry I use the wrong variable/function/whatnot names when doing something involving names.
11:37:12 <int-e> right now I'm wondering about leapfrogging. 121 is nice, but still one character behind henkma.
11:43:36 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
11:49:59 <shachaf> oerjan: whoa, i just found out that Roald Dahl is norwegian??
11:50:09 <shachaf> oerjan: perhaps some jokes have gone over my head here
11:52:32 -!- Patashu has quit (Ping timeout: 264 seconds).
11:57:02 -!- qlkzy has quit (Excess Flood).
11:58:39 -!- qlkzy has joined.
12:27:24 -!- boily has quit (Quit: AFFABLE CHICKEN).
12:34:02 <fizzie> You sure leapfrogged the competition. (Groan.)
12:34:51 -!- sebbu2 has joined.
12:35:28 -!- sebbu2 has quit (Changing host).
12:35:28 -!- sebbu2 has joined.
12:36:19 -!- sebbu has quit (Ping timeout: 250 seconds).
12:59:04 <scoofy> does brainfuck traditionally signed or unsigned char?
12:59:21 -!- sebbu2 has changed nick to sebbu.
12:59:58 <b_jonas> scoofy: either unsigned, or unsigned with overflow and underflow forbidden
13:00:32 <scoofy> either with, or without overflow?
13:00:53 <int-e> of course unsigned is indistinguishable from signed with wrap-around on overflow and underflow.
13:01:06 <b_jonas> range 0..255 is always allowed, if you overflow it depends on the implementation: some implementations have larger ranges, some just wrap around modulo 256
13:01:09 <scoofy> well, question is about interpretation.
13:01:17 <FireFly> int-e: except for I/O I guess
13:01:20 <int-e> 0..255 is the usual interpretation.
13:01:40 <int-e> FireFly: even there, what difference does it make?
13:01:57 <FireFly> I guess it's just a matter of convention even for byte values
13:02:10 <b_jonas> int-e: sure, it's just definitely not signed char, because it's safe to go over 127
13:08:12 -!- qlkzy has quit (Excess Flood).
13:09:29 -!- yorick has quit (Ping timeout: 245 seconds).
13:12:31 -!- qlkzy has joined.
13:12:31 -!- qlkzy has quit (Excess Flood).
13:14:45 -!- qlkzy has joined.
13:14:45 -!- qlkzy has quit (Excess Flood).
13:15:02 -!- qlkzy has joined.
13:20:30 <fizzie> The conventional bfjoust conceptual interpretation is [-127, 128]. :)
13:20:45 -!- yorick has joined.
13:21:07 <fizzie> (Sure, it's a whole different language.)
13:21:16 <b_jonas> fizzie: what? don't you mean [-128..127]?
13:24:52 <fizzie> b_jonas: No, the halfway point is generally considered to be 128, not -128.
13:25:05 <b_jonas> fizzie: is that just to be different? ok
13:25:21 <b_jonas> it doesn't affect semantics anyway
13:26:06 <b_jonas> I guess that's just a shiboleth: if someone gives dumps containing -128, you recognize them as an unexperienced newbie bfjouster.
13:27:53 <fizzie> I was going to say that that's how it's shown by tools like EgoJSout, but that's slightly arguable -- the tape dumps show a hex number. But the graphical tape plotter shows hex values 01..80 as "positive" (above the zero axis) and 81..FF as "negative" (below).
13:28:26 <fizzie> (And that's the way it's described on the wiki.)
13:29:35 <b_jonas> right, so you that tool isn't written by a bfjoust newbie
13:32:51 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
13:47:08 <lambdabot> EFHK 211320Z 04009KT 1400 R04R/P1500D R15/P1500N R22L/P1500N R04L/P1500N SN VV005 M02/M03 Q1027 NOSIG
13:47:34 <lambdabot> ESSA 211320Z 01002KT 8000 -DZ BR BKN005 BKN013 02/02 Q1027 R88/29//95 BECMG SCT006 BKN015
13:48:39 <fizzie> There's it's just negative Drizzt.
14:32:17 <elliott> fizzie: speaking of drizzles, when are you moving?
14:36:34 <mroman> !blsq "+++++++++."".""X"r~"-""\/^^{vvvv}c!!!-.256.%{vvvv}c!sa\/"r~"+""\/^^{vvvv}c!!!+.256.%{vvvv}c!sa\/"r~"[""{"r~"]""}{\/^^{vvvv}c!!!}w!"r~">""+."r~"<""-."r~"X""\/^^{vvvv}c!!!L[+]\/+]\/+]^^3\/.+1RAp^\/+]\/[-1RA^^-]\/[-\/"r~"\'\'1 128r@{vv0}m[0"\/.+pse!vvvv<-sh
14:37:10 -!- blsqbot has joined.
14:37:16 <mroman> !blsq "+++++++++."".""X"r~"-""\/^^{vvvv}c!!!-.256.%{vvvv}c!sa\/"r~"+""\/^^{vvvv}c!!!+.256.%{vvvv}c!sa\/"r~"[""{"r~"]""}{\/^^{vvvv}c!!!}w!"r~">""+."r~"<""-."r~"X""\/^^{vvvv}c!!!L[+]\/+]\/+]^^3\/.+1RAp^\/+]\/[-1RA^^-]\/[-\/"r~"\'\'1 128r@{vv0}m[0"\/.+pse!vvvv<-sh
14:38:08 <mroman> !blsq "-[+>+<[+<]>]>+."".""X"r~"-""\/^^{vvvv}c!!!-.256.%{vvvv}c!sa\/"r~"+""\/^^{vvvv}c!!!+.256.%{vvvv}c!sa\/"r~"[""{"r~"]""}{\/^^{vvvv}c!!!}w!"r~">""+."r~"<""-."r~"X""\/^^{vvvv}c!!!L[+]\/+]\/+]^^3\/.+1RAp^\/+]\/[-1RA^^-]\/[-\/"r~"\'\'1 128r@{vv0}m[0"\/.+pse!vvvv<-sh
14:38:08 <blsqbot> | Ain't nobody got time fo' dat!
14:38:32 <mroman> !blsq "++++++++[>++++++++<-]>+."".""X"r~"-""\/^^{vvvv}c!!!-.256.%{vvvv}c!sa\/"r~"+""\/^^{vvvv}c!!!+.256.%{vvvv}c!sa\/"r~"[""{"r~"]""}{\/^^{vvvv}c!!!}w!"r~">""+."r~"<""-."r~"X""\/^^{vvvv}c!!!L[+]\/+]\/+]^^3\/.+1RAp^\/+]\/[-1RA^^-]\/[-\/"r~"\'\'1 128r@{vv0}m[0"\/.+pse!vvvv<-sh
14:41:40 <fizzie> elliott: Or, depending on definition, somewhen in February, which is hopefully when we'll be moving to some more permanent place and shipping stuff from Finland.
14:42:12 <elliott> in the meantime you will take up residency in a Small, yet Comfortable Hole, in the ground
14:45:11 <fizzie> Actually, I just got booking confirmations from the temporary place.
14:46:10 <fizzie> (Although it was relatively light on the details.)
14:48:24 <fizzie> It's that place with the the £250/week Internet if you use more than 1 gigabyte in a day, except it's relatively possible that's actually not part of the terms for this particular place.
14:49:29 <fizzie> Yes, it was entirely ridiculous.
14:49:35 <fizzie> (The first gigabyte's free.)
14:50:32 <fizzie> "As a guide additional charges include, but is not limited to the following: -- Broadband charges including data download exceeding 1GB (1024MB) per day - £250 per week or part of week."
14:50:43 <elliott> fizzie: that's pretty good internet for a hole
14:51:03 <elliott> fizzie: incidentally I'm pretty sure the 3G dongles you can get at $any_mobile_shop are cheaper than that.
14:52:29 <fizzie> I'm having a slight culture shock what with your "just about everything has a data cap" thing.
14:52:41 <fizzie> They used to be almost unheard-of here, although Finland's been catching up lately.
14:52:52 <mroman> 250 Pounds A WEEK is like uhm
14:53:01 <blsqbot> | ERROR: Unknown command: (/4)!
14:53:01 <blsqbot> | ERROR: Unknown command: (*4)!
14:53:11 <mroman> that many times too much
14:55:08 <fizzie> We're currently paying something (it's negotiated for the whole building and part of the upkeep costs, so this is an estimate) like 5€/month for 10M/10M unlimited broadband, and I used to pay another 5€/month for no-data-cap-but-real-slow-bandwidth-cap (512Kbps, I think) 3G mobile thing.
14:57:48 <fizzie> (Before switching to a prepaid data thing that costs 20€/(10 GB valid for 6 months) aka 3.34€/month, since I use it for about 100MB/month. So I do have *something* with a data cap, now. It's just something I don't use.)
15:00:05 <mroman> instead of fixing javascript
15:00:14 <mroman> you just bork around it
15:01:29 <FireFly> £35/month seems like it should get you 100/100 without caps, at least
15:01:51 <fizzie> Yes, but £35/day even more so.
15:01:57 <FireFly> so £35/*day* seems quite unreasonable :P
15:03:10 <FireFly> mroman: those parens are redundant hth
15:03:13 <fizzie> Take that £250/week figure with a grain of salt -- I mean, it's listed on the website of the company as an example, but when I asked about Internet and any limits regarding our booking, they just said it's included and it's approximately 10-16M/1M, and didn't mention any traffic caps.
15:03:30 <mroman> FireFly: It doesn't help
15:03:57 <FireFly> also return~-x is even shorter
15:03:58 <mroman> I'd rather write func add1(x : int) : int { return x+1; }
15:03:59 <fizzie> Maybe you can push all your JavaScript through the C preprocessor and #define INTIFY 0| return INTIFY x+1;
15:04:09 <FireFly> mroman: you can write return Math.floor(x + 1)
15:04:14 <FireFly> Which is less golfed and easier to read
15:04:15 <mroman> func add1(x) { x=x|0; return (x+1)|0; }
15:04:49 <FireFly> If someone actually uses tricks like |0 in meant-to-be-readable code I want to hit them
15:05:01 <FireFly> Well, not actually hit them, but mentally
15:05:10 <mroman> it's used as type annotations
15:05:14 <mroman> for static checkers and what not
15:06:34 -!- idris-bot has joined.
15:13:05 <elliott> FireFly: that's "idiomatic JS"
15:20:45 <FireFly> elliott: I think asm.js is meant to be a compiler target
15:21:10 <elliott> I don't think Math.floor works, doesn't | also clamp to 32 bits?
15:21:32 -!- kcm1700_ has joined.
15:21:38 -!- kcm1700 has quit (Read error: Connection reset by peer).
15:27:11 -!- MDream has changed nick to MDude.
15:27:18 -!- AnotherTest has joined.
15:28:24 <mroman> !blsq 9999999999999999999999999999999999999999fp
15:28:25 <blsqbot> | -10000000000000000000000000000000000000000
15:28:39 <mroman> !blsq 999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999fp
15:28:39 <blsqbot> | -1000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
15:28:57 <mroman> !blsq 999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999fpb2
15:28:58 <blsqbot> | That line gave me an error
15:34:11 -!- `^_^v has joined.
15:45:25 -!- S1 has joined.
15:56:17 <blsqbot> | ERROR: Unknown command: (+1)!
15:56:18 <blsqbot> | ERROR: Unknown command: (--)!
15:56:18 <blsqbot> | ERROR: Unknown command: (--)!
15:57:00 <blsqbot> | ERROR: (line 1, column 6):
15:58:05 <blsqbot> | ERROR: (line 1, column 1):
15:58:05 <blsqbot> | expecting "\"", "-", digit, "'" or "["
15:58:15 <blsqbot> | ERROR: (line 1, column 2):
15:58:15 <blsqbot> | expecting "\"", "-", digit, "'" or "["
15:58:49 <blsqbot> | ERROR: (line 1, column 4):
15:58:54 <blsqbot> | ERROR: (line 1, column 3):
15:59:06 <mroman> fun fact "ra" expects characters to be 'a' rather than 'a
16:00:50 <mroman> !blsq "['a','b']"ps2sH
16:00:54 <mroman> !blsq "['a','b']"ps0sH
16:00:57 <mroman> !blsq "['a','b']"ps1sH
16:01:02 <mroman> !blsq "['a','b']"ps3sH
16:01:44 <mroman> !blsq "1,2,3,4"ps(,);;
16:01:45 <blsqbot> | ERROR: Burlesque: (;;) Invalid arguments!
16:01:50 <mroman> !blsq "1,2,3,4"ps(,)j;;
16:01:50 <blsqbot> | ERROR: Burlesque: (;;) Invalid arguments!
16:02:05 <blsqbot> | ERROR: Burlesque: (;;) Invalid arguments!
16:03:41 <mroman> !blsq "1,2,3,4"pssg~]\[
16:04:31 <fizzie> elliott: By the way, if I understood correctly, the hole will be somewhere between the 9th and 13th floor, which is also quite high up for a hole. (I suppose it's possible the numbers mean below-the-ground floors, though.)
16:05:14 <elliott> fizzie: that's just how bad the hole is (9th and 13th flaw), and also how floored by how bad it is you'll be
16:06:26 -!- adu has joined.
16:09:52 -!- adu has quit (Client Quit).
16:11:35 <mroman> fizzie: psShra is a nice trick btw
16:11:56 <blsqbot> | ERROR: Burlesque: (ri) Invalid arguments!
16:11:56 <blsqbot> | ERROR: Burlesque: (;;) Invalid arguments!
16:12:08 <mroman> mainly because ;; wants a string
16:12:16 <mroman> (which is fixed in 1.7.4 though)
16:12:42 <mroman> although ri won't work with heterogenous lists of course
16:12:46 <mroman> !blsq "1,2,3,4"",";;ri
16:12:50 <mroman> !blsq "1,2,3.0,4"",";;ri
16:12:51 <blsqbot> | That line gave me an error
16:12:55 <mroman> !blsq "1,2,3.0,4"",";;rd
16:13:01 <mroman> !blsq "1,2,3.0,4"psShra
16:13:23 <mroman> !blsq "1,2,3.0,4,'a'"psShra
16:13:24 <blsqbot> | ERROR: (line 1, column 2):
16:13:24 <blsqbot> | expecting "\"", "-", digit, "'" or "["
16:13:32 <mroman> !blsq "1,2,3.0,4,'a"psShra
16:13:33 <blsqbot> | ERROR: (line 1, column 28):
16:13:33 <blsqbot> | expecting "\"", "-", digit, "'", "[" or "]"
16:13:39 <mroman> !blsq "1,2,3.0,4,a"psShra
16:13:40 <blsqbot> | ERROR: (line 1, column 2):
16:13:40 <blsqbot> | expecting "\"", "-", digit, "'" or "["
16:24:23 -!- adu has joined.
16:33:14 <blsqbot> | ERROR: (line 1, column 1):
16:33:14 <blsqbot> | expecting "\"", "-", digit, "'" or "["
16:36:09 -!- AnotherTest has quit (Ping timeout: 245 seconds).
17:24:29 -!- tlewkow has joined.
17:24:31 -!- tlewkow has quit (Remote host closed the connection).
17:24:54 -!- tlewkow has joined.
17:25:25 -!- tlewkow has quit (Remote host closed the connection).
17:25:38 -!- tlewkow has joined.
17:26:18 <J_Arcane> https://github.com/nomic-io/nomic
17:28:48 <S1> kind of evolution
17:32:38 <S1> Code that randomly changes the @nomic-io Github password, so no human has access to the account
17:32:47 <S1> fascinating
17:35:58 -!- tlewkow has quit (Remote host closed the connection).
17:39:39 -!- tlewkow has joined.
17:50:56 <idris-bot> Can't resolve type class Num (Integer -> Integer)
17:51:12 <Dulnes> get out of there astris
17:51:37 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 73866 : Integer -> Integer
17:59:23 -!- S1 has quit (Quit: S1).
18:04:44 -!- tlewkow has quit (Remote host closed the connection).
18:08:07 -!- tlewkow_ has joined.
18:17:36 -!- Phantom_Hoover has joined.
18:18:16 -!- FreeFull has quit (Quit: BBL).
18:18:27 -!- dts_Zzz has changed nick to dts.
18:25:58 <HackEgo> [wiki] [[Light Pattern]] http://esolangs.org/w/index.php?diff=41102&oldid=40968 * BCompton * (+24) /* Original Hello, World */
18:50:38 <Gregor> J_Arcane: The "ASL" at the bottom is clearly the work of twits.
18:59:07 -!- AnotherTest has joined.
19:09:38 <elliott> Gregor: 12 hours/code/github, u?
19:10:40 <fizzie> Oh, I used up my conversation allowance demoing it to colleagues.
19:13:12 <fungot> FireFly: is ur paper, there are 3 words... ' today its me... because i m quite free these days la
19:13:33 <FireFly> yes, it does indeed stand for three words
19:13:52 <fizzie> fungot: Have you been thinking about trying out internet dating?
19:13:53 <fungot> fizzie: no one might wish us n bring us presents again, but we know that we miss you guys.
19:14:38 <shachaf> fungot: how do you do american sign language over irc
19:14:38 <fungot> shachaf: send to someone else have already liked her sis one last amendmentto make. so i wait for u.:)
19:19:55 <Gregor> I didn't realize that fungot had an "annoying twelve year old" mode.
19:19:55 <fungot> Gregor: thank u. please tell lucy i forgot to tell me what u thinking just now leh. at ard decimal tmr at the coffeeshop near their office
19:20:06 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms* speeches ss wp youtube
19:20:19 <fungot> Selected style: oots (Order Of The Stick)
19:20:25 <shachaf> fungot: whoa, since when do you have that
19:20:25 <fungot> shachaf: my master and answer the charges that rely on the more traditional torture methods. which is to say, " i", thus ruining the spell " haste" if the good. or any room with my prisoners, and i would not be so dismissive of.
19:20:47 <shachaf> fizzie: where are the transcriptions from?
19:22:27 <fizzie> shachaf: http://wing.comp.nus.edu.sg/SMSCorpus/
19:22:37 <fizzie> Oh, I thought it was still in SMS style.
19:23:24 <fizzie> I think I scraped http://oots.wikia.com/ or something.
19:23:40 <fizzie> Yes, this looks familiar. I think that's it.
19:26:16 <fizzie> I tested 4 comments (since that's the limit) of the SMS style when showing off, and managed to get something that pretty well reproduces the tone of short SMS message system messages: http://sprunge.us/NJHQ
19:26:28 <fizzie> Except for the "sword alone can't stop" scenario in the last.
19:27:59 <shachaf> i thought S stood for Simple
19:33:22 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
19:41:22 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
19:42:03 -!- tlewkow_ has quit (Remote host closed the connection).
19:44:02 <olsner> "short SMS message system" is a very redundant acronym redundancy
19:44:30 <olsner> (but it seems to be 'service', not system)
19:44:33 <shachaf> i think that's the idea, olsner
19:44:57 <shachaf> perhaps fizzie types "SMS messages" but then thought that the pedants would swoop in and cry redundancy
19:45:06 <olsner> I thought it was accidental
19:45:29 <shachaf> so he added "short SMS message system messages" so it would be completely obvious that he's being redundant on purpose and people wouldn't be like that
19:45:36 <shachaf> but apparently that's not good enough
19:45:44 <olsner> nope, not nearly enough
19:47:21 <fizzie> shachaf: You will be burned as a witch for such accurate clairvoyance.
19:48:58 <fizzie> (The "system"/"service" part was inexcusable, however. Mea culpa.)
19:52:08 -!- drdanmaku has joined.
20:16:47 -!- nycs has joined.
20:19:24 -!- `^_^v has quit (Ping timeout: 240 seconds).
20:28:31 -!- nycs has quit (Quit: This computer has gone to sleep).
20:28:57 -!- vanila has joined.
20:56:54 <scoofy> did anyone ever do 16 bit arithmetic in 8 bit brainfuck?
20:59:50 -!- Patashu has joined.
21:02:34 <fizzie> To quote the awib design report: "For instance, 8-bit centric developers often implement 16-bit airthmetic by relying on 255 incremented becoming 0, which will fail miserably in any other cell size." Sadly, it doesn't cite examples.
21:03:02 <fizzie> I can only think of some programs with arbitrary-precision stuff implemented with 8-bit cells, not specifically 16-bit arithmetic.
21:03:46 -!- adu has quit (Quit: adu).
21:05:43 <Gregor> fizzie: http://esolangs.org/wiki/Brainfuck_bitwidth_conversions <-- examples
21:06:48 <fizzie> Fancy. And I was right at [[Brainfuck algorithms]] and even looked at "See also", don't know why I missed it.
21:07:19 <Gregor> I should hope I'd remember that page since I wrote it.
21:07:28 <olsner> is it possible to do it cell size agnostically?
21:08:00 <Gregor> olsner: You can CHECK for cell size and then have code specialized to many different cell sizes.
21:37:42 -!- zzo38 has joined.
21:39:12 <elliott> olsner: you can just pretend it's boolfuck
21:43:47 <elliott> is the subset of BF complete given by +<>[] and you can only write to a cell once TC
21:44:35 <zzo38> If arbitrary jumps are allowed then it is TC but other than that I don't know
21:45:49 -!- FreeFull has joined.
21:46:09 <Gregor> I doubt that it's possible to simulate a rewritable tape using a write-once tape.
21:46:21 <vanila> hi zzo38 I enjoyed your gopher:// site
21:46:47 <elliott> Gregor: it feels sort of like reversible computing to me
21:47:01 <elliott> in that maybe you can do it just by accumulating lots and lots of garbage
21:48:13 <zzo38> http://en.wikipedia.org/wiki/Wang_B-machine
21:49:17 <vanila> the cool thing about Janus (reversible language) is that it acn simulate itself withour generating lots of garbage
21:56:35 -!- S1 has joined.
22:04:31 -!- dts has changed nick to dts|gaming.
22:11:08 <vanila> brainfuck gets a lot of popularity
22:11:18 <vanila> shouldn't we program in subleq more
22:11:23 -!- adu has joined.
22:13:28 <S1> I didn't see brainfuck being mentioned here in about.... a looong time :|
22:14:12 <S1> it's just not esoteric enough it seems
22:15:17 <vanila> S1, I think subleq is hard to program in though
22:15:26 <vanila> like you can program BF by yourself, but not subleq
22:15:32 <vanila> so one would require a compiler
22:16:05 <S1> Didn't read the article, sry
22:16:12 <S1> quite busy atm
22:16:15 -!- adu has quit (Ping timeout: 265 seconds).
22:16:36 <vanila> its an assembly instruction set
22:16:48 <S1> yea I did read the first few sentences though
22:16:58 <FireFly> "subtract and branch if less than or equal to"
22:17:18 -!- adu has joined.
22:17:26 <FireFly> The instruction name quite accurately summarizes the whole instruction set
22:18:28 <S1> is it turing complete?
22:19:43 -!- tlewkow_ has joined.
22:19:45 -!- Bicyclidine has joined.
22:20:06 <zzo38> What is it called if you are using base two numbers but the possible digits are 1 and 2 instead of 0 and 1?
22:20:31 <S1> still binary
22:21:00 -!- tlewkow_ has quit (Remote host closed the connection).
22:21:23 <zzo38> No this is a different kind
22:21:29 <fizzie> zzo38: http://en.wikipedia.org/wiki/Bijective_numeration
22:21:42 <fizzie> (That's the general concept for base k with digits 1..k.)
22:22:04 <zzo38> Yes this is what it is
22:22:15 <zzo38> It is what I meant
22:22:19 -!- adu has quit (Ping timeout: 244 seconds).
22:24:04 <zzo38> I have made up a kind of run length coding using bijective binary numbers; 1 and 2 is represented by bit 0 and 1 and then the next bit tell you if there is more bits or not.
22:32:08 <zzo38> I made up a new kind of sokoban compression which I used to compress the original 50 sokoban levels from the original DOS version into less than one eighth of their original size.
22:32:55 <zzo38> First is stored 18-bits to tell the player's starting position and the board size. Next the walls are RLE'd in a horizontal boustrophedon starting at the top-left, skipping the player's starting position.
22:33:35 <zzo38> After that the targets are encoded in a similar way, but vertically and the walls are skipped but the player isn't. Finally the position of boxes is coded.
22:34:28 <zzo38> (It assumes there is the same number of boxes as targets, boxes that do not start on targets are more likely than ones that do start on targets, and that there isn't any box that isn't initially on a target in a position where it is impossible to be moved from.)
22:38:52 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
22:39:03 <zzo38> Are there better ways which aren't too much more complicated?
22:40:48 <S1> I don't know what this actually is, what you're encoding but 1/8 sounds good ^-^
22:41:34 <vanila> I ha vlooked for other gopher:// sites but there aren't many [which aren't very old and bad]d
22:41:55 <vanila> interesting to use boustrophedon
22:44:01 <zzo38> Yes there aren't a lot, although there are some
22:44:38 <zzo38> I used boustrophedon dince it ends up working much better with this kind of encoding numbers for RLE
22:47:45 -!- nooga has joined.
22:47:58 <nooga> this place is full
22:50:12 <quintopia> zzo38: does boustrophedon work better than spiral for grouping walls?
22:50:30 -!- boily has joined.
22:51:26 <zzo38> I didn't try spiral so I don't know
22:55:31 <quintopia> anyway, maybe boustrophedon is best
22:56:48 <nooga> indeed, hi elliott
22:57:42 <nooga> wow, I'm mentioned in the wisdom file
22:59:46 <shachaf> you're either wisdom or you're againsdom
23:00:04 <nooga> I'm sure it's the latter
23:07:13 <HackEgo> [wiki] [[REBEL]] http://esolangs.org/w/index.php?diff=41103&oldid=40976 * BCompton * (+12) /* External resources */
23:08:51 -!- tlewkow has joined.
23:13:46 -!- AnotherTest has quit (Remote host closed the connection).
23:16:27 <boily> quintopia: quinthellopia!
23:16:37 <boily> what does the elliott say?
23:17:00 <boily> speaking of wisdom, I haven't updated it in a looong time...
23:20:45 -!- S1 has quit (Quit: S1).
23:22:02 <nooga> I recently stumbled upon K and Arthur Whitney's stuff
23:22:18 <nooga> seems pretty eso, are you guys familiar with that?
23:23:28 <nooga> http://nsl.com/papers/origins.htm now this is pretty indie
23:24:20 <Taneb> J and K are based on APL right?
23:24:25 <lambdabot> CYUL 212300Z 27011G20KT 15SM SKC M06/M15 A3033 RMK SLP274
23:24:29 <Taneb> I've been playing with APL recently
23:25:57 <Sgeo> http://www.fark.com/comments/8499094/Fark-Two-computer-scientists-respond-to-a-predatory-journal-with-7-words-complete-with-charts-graphs-Total-WTF-The-journal-prints-it-Not-safe-for-work-Language
23:26:34 -!- oerjan has joined.
23:26:59 <oerjan> int-e: wat you're soundly beating henkma on leapfrogging
23:28:11 <nooga> Sgeo: I remember reading about guys who were invited to speak on a conference after submiting papers generated using markov chains
23:28:32 <lambdabot> mroman said 14h 22m 58s ago: You can remove me from the dontaskdonttelllist
23:32:58 -!- tlewkow has quit (Remote host closed the connection).
23:33:43 <oerjan> <int-e> shachaf: but that's normal, missing the blatantly obvious because one is preoccupied with looking for clever tricks. <-- i have to keep wondering what blatantly obvious thing i'm missing on the A[057]* one
23:34:07 -!- zlsa has joined.
23:34:43 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
23:34:47 <boily> zlsa: please yourself!
23:35:05 <oerjan> some of those aren't around these days
23:35:15 <fungot> ^<lang> <code>; ^def <command> <lang> <code>; ^show [command]; lang=bf/ul, code=text/str:N; ^str 0-9 get/set/add [text]; ^style [style]; ^bool
23:35:31 <zlsa> ^python print("hello world")
23:35:49 <zlsa> oh that's right, this is #esoteric
23:35:49 <oerjan> boily seems to have dropped joining metasepia after int-e stole metar
23:36:08 <shachaf> ^bf ++++++++++++++++++++++++++++++++++++++++++++++++.
23:36:08 <oerjan> zlsa: bf = brainfuck, ul=underload, those are your options
23:36:41 <zlsa> brb, learning brainfuck
23:36:44 <oerjan> HackEgo and EgoBot have several languages, though
23:37:00 <boily> oerjan: yes. I'm still jealous about that :P
23:37:16 <boily> (meanwhile, I'm learning rust, and probably will make a new IRC bot.)
23:37:47 <oerjan> (HackEgo includes most of EgoBot's ones in the ! subcommand.)
23:37:54 <int-e> oerjan: It was strange. I did a lot of hard work on leapfrogging and then I found something simple that saved 7 characters.
23:38:40 <oerjan> and iirc i still haven't managed to beat my initial one
23:38:43 <HackEgo> Runs arbitrary code in GNU/Linux. Type "`<command>", or "`run <command>" for full shell commands. "`fetch <URL>" downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert <rev>" can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
23:38:53 <zlsa> it is running in a sandbox, right?...
23:38:55 <oerjan> although i've not tried that much with it
23:39:02 <HackEgo> HackEgo, also known as HackBot, is a bot that runs arbitrary commands on Unix. See `help for info on using it. You should totally try to hax0r it! Make sure you imagine it's running as root with no sandboxing.
23:39:32 <fungot> shachaf: if the power, as duly noted. i've been up on the mountain, with two gates lost, we know that we're going.
23:39:52 <oerjan> zlsa: although i'm less sure about it's unhackability than i used to be. there have been some disturbing bugs showing up lately.
23:40:14 <oerjan> (and of course, a _real_ expert could probably break it, anyway.)
23:40:19 <zlsa> `run echo "foobar"
23:40:29 <HackEgo> bash: emacs: command not found
23:40:37 <HackEgo> Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
23:40:50 <HackEgo> 23:40:15 up 0 min, 0 users, load average: 0.00, 0.00, 0.00 \ USER TTY FROM LOGIN@ IDLE JCPU PCPU WHAT
23:41:07 <HackEgo> bash \ bunzip2 \ bzcat \ bzcmp \ bzdiff \ bzegrep \ bzexe \ bzfgrep \ bzgrep \ bzip2 \ bzip2recover \ bzless \ bzmore \ cat \ chgrp \ chmod \ chown \ cp \ cpio \ dash \ date \ dd \ df \ dir \ dmesg \ dnsdomainname \ domainname \ echo \ ed \ egrep \ false \ fgrep \ findmnt \ fuser \ grep \ gunzip \ gzexe \ gzip \ hostname \ ip \ kill \ kmod \ less \
23:41:24 <fizzie> oerjan: Is there a way to get the usual EgoBot language listing from HackEgo?
23:41:24 <HackEgo> alternatives \ java-6-openjdk
23:41:43 <HackEgo> agpgart \ audio \ audio1 \ audio2 \ audio3 \ audioctl \ console \ core \ dsp \ dsp1 \ dsp2 \ dsp3 \ fd \ full \ kmem \ loop0 \ loop1 \ loop2 \ loop3 \ loop4 \ loop5 \ loop6 \ loop7 \ mem \ midi0 \ midi00 \ midi01 \ midi02 \ midi03 \ midi1 \ midi2 \ midi3 \ mixer \ mixer1 \ mixer2 \ mixer3 \ mpu401data \ mpu401stat \ null \ port \ ptmx \ pts \ ram \
23:41:58 <oerjan> also, it doesn't have the userinterp part
23:42:16 <fizzie> oerjan: That's kind of crude, compared to the version that has the split to eso- and non-teric parts.
23:42:18 <oerjan> it could be reimplemented in HackEgo of course.
23:42:34 <HackEgo> whoami: cannot find name for user ID 5000
23:42:38 <oerjan> fizzie: i haven't seen that in HackEgo, but i may not have looked carefully.
23:42:50 <HackEgo> whoami: invalid option -- 'n' \ Try `whoami --help' for more information.
23:42:55 <zlsa> `run ls /dev/s*
23:42:57 <HackEgo> /dev/sequencer \ /dev/shm \ /dev/smpte0 \ /dev/smpte1 \ /dev/smpte2 \ /dev/smpte3 \ /dev/sndstat \ /dev/stderr \ /dev/stdin \ /dev/stdout
23:43:03 <shachaf> int-e: what are you expecting exactly
23:43:30 <HackEgo> zlsa: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
23:43:37 <int-e> shachaf: numerical output, but it was the wrong command.
23:43:46 <shachaf> int-e: but `whoami gave numerical output
23:44:06 <shachaf> That advice is said to be outdated, by the way.
23:44:13 <nooga> maybe try dd-ing one device to another
23:44:23 <shachaf> oerjan: Did you logread today?
23:44:43 <shachaf> Er, no, #esoteric on irc.dal.net is gone.
23:44:46 <int-e> shachaf: maybe esoterically minded persons can still find a way to contact it
23:44:56 <fizzie> nooga: There aren't any very interesting devices to dd from/to.
23:46:10 <oerjan> shachaf: i'm in the process
23:46:11 <zlsa> i've discovered more languages in the last ten minutes than I have in the last year
23:46:38 <zemhill> zlsa: I do !bfjoust; see http://zem.fi/bfjoust/ for more information.
23:46:38 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
23:46:43 <EgoBot> EgoBot is a bot for running programs in esoteric programming languages. If you'd like to add support for your language to EgoBot, check out the source via mercurial at https://codu.org/projects/egobot/hg/ . Cheers and patches (preferably hg bundles) can be sent to Richards@codu.org , PayPal donations can be sent to AKAQuinn@hotmail.com , complaints can be sent to /dev/null
23:46:51 <zlsa> !help languages
23:46:51 <EgoBot> languages: Esoteric: 1l 2l adjust asm axo bch befunge befunge98 bf bf8 bf16 bf32 boolfuck cintercal clcintercal dimensifuck glass glypho haskell kipple lambda lazyk linguine malbolge pbrain perl qbf rail rhotor sadol sceql trigger udage01 underload unlambda whirl. Competitive: bfjoust fyb. Other: asm c cxx forth sh.
23:46:59 <nooga> I'm fed up with languages lately
23:47:00 <Taneb> `quote Northumberland
23:47:02 <HackEgo> 622) <oerjan> shachaf: wait, _you_ are in northumberland? <shachaf> No. <oerjan> whew <oerjan> we don't have room for more esolangers there. <shachaf> oerjan: Wait, *you* are in Northumberland? <oerjan> no <shachaf> Whew. <shachaf> We don't have room for more esolangers there.
23:47:22 <Taneb> To my knowledge, we are at a record shortage of Northumbrian esolangers
23:47:52 <zlsa> somebody wrote a brainfuck interpreter in haskell
23:47:58 <zlsa> ... talk about the pot calling the kettle black
23:48:10 <fizzie> Several somebodies, I'm sure.
23:48:12 <ion> A Haskell interpreter in brainfuck would be cooler.
23:48:22 <shachaf> Taneb: whoa, newcastle isn't in northumberland?
23:48:51 <shachaf> but #trains was talking about newcastle the other day
23:48:52 <Taneb> Newcastle is in Tyne and Wear
23:48:56 <nooga> I just seen brainfuck implemented using Rust macros
23:49:27 <nooga> it's not even fun anymore
23:49:28 <int-e> . o O ( echo nobody:x:500:515161:Odysseus:/bin/bash >> /etc/passwd )
23:50:57 <int-e> I recall times when 500 was the first assigned user id for normal users.
23:51:19 <shachaf> but there are no more normal users
23:51:36 <fizzie> I have the vaguest feeling Slackware had some smallish (less than 1000) number.
23:52:19 <oerjan> zlsa: http://esolangs.org/wiki/Fueue#Brainfuck_interpreter hth
23:52:45 <oerjan> that's like the pot and the kettle having a mud wrestling match
23:54:04 <zzo38> How do you mean, there are no more normal users?
23:54:54 <oerjan> it would be so fitting if zzo38 was the only one left
23:55:44 <zzo38> What exactly is a "normal user" anyways?
23:56:00 <oerjan> yes, shachaf, exactly what is a normal user
23:56:00 <int-e> I meant a non-system user
23:56:08 <int-e> I'm not sure what shachaf meant.
23:57:33 <fizzie> oerjan: I think it has something to do with an uniform distribution of body parts no matter how you disassemble one.
23:58:02 <oerjan> fizzie: that sounds more like a zombie user to me hth
23:58:27 <int-e> `cat /proc/288/cmdline
23:58:29 <HackEgo> sh.-c.'env' 'PATH=/hackenv/bin:/opt/python27/bin:/opt/ghc/bin:/usr/bin:/bin' 'HACKENV=/hackenv' 'http_proxy=http://127.0.0.1:3128' 'LANG=en_NZ.UTF-8' '/home/hackbot/hackbot.hg/multibot_cmds/lib/limits' 'cat' '/proc/288/cmdline' | cat.
00:01:24 <oerjan> very unusual unobfuscated c?
00:02:20 <int-e> elliott: is it? it prevents evil program doing file operations on the final output file; all they get access to is a pipe.
00:02:32 <elliott> int-e: there is no output file
00:02:52 <elliott> I think Python's subprocess module is adding the | cat
00:02:58 <ion> | cat | cat for two-factor security
00:03:01 <int-e> if it's a pipe already, then indeed...
00:03:08 <elliott> since you *can* point stdout to a file object there
00:03:17 <vanila> rot13 | rot13 | could be used instead of ca
00:03:17 <elliott> so I guess they just do it for everything because it doesn't hurt
00:03:58 <nooga> btw, are there some new, hot esolangs that aren't just some funky syntax sprinkled on top of boring execution model?
00:03:58 <int-e> `` ls -l /proc/self/fd
00:04:01 <HackEgo> total 0 \ lr-x------ 1 5000 878264 64 Nov 22 00:03 0 -> /tty1 \ l-wx------ 1 5000 878264 64 Nov 22 00:03 1 -> pipe:[248] \ l-wx------ 1 5000 878264 64 Nov 22 00:03 2 -> /tty1 \ lr-x------ 1 5000 878264 64 Nov 22 00:03 3 -> /console \ l-wx------ 1 5000 878264 64 Nov 22 00:03 4 -> /console \ lr-x------ 1 5000 878264 64 Nov 22 00:03 5 -> /tty1 \ l-wx-
00:04:23 <vanila> nooga, there is an intereting one
00:05:00 <vanila> http://esolangs.org/wiki/My_Unreliable_Past
00:05:06 <elliott> nooga: probably yeah in the last ten billion years you haven't been here :p
00:05:09 <int-e> `` ls -l /proc/self/fd | sed 's/.*:...//'
00:05:11 <HackEgo> total 0 \ 0 -> /tty1 \ 7] \ 2 -> /tty1 \ 3 -> /console \ 4 -> /console \ 5 -> /tty1 \ 6 -> /tty1 \ 7 -> /tty1 \ 8 -> /proc/293/fd
00:05:29 <vanila> http://esolangs.org/w/index.php?title=Special:RecentChanges&limit=500&days=30
00:06:00 <vanila> Casino viagra program language[edit]
00:06:00 <vanila> Make a casino viagra program language. Sometimes this word is same as spam word, so you have to make sure it really is authentic. --Zzo38 04:38, 16 July 2008 (UTC)
00:08:23 <nooga> elliott: that's why I'm asking. I was hoping that someone would point me to the interesting bits :D
00:08:58 <oerjan> <shachaf> oerjan: perhaps some jokes have gone over my head here <-- not that i recall. as a norwegian, i tend to think of him as mostly british, anyway.
00:11:55 <oerjan> nooga: were you around for Sgeo's braintrust
00:13:45 <vanila> casino viagra should be based on spam keywords and maybe email, an maybe bayesian spam filters
00:14:07 <vanila> you could have an email that tries to filter spam, and only code that gets past it is executed
00:14:19 <oerjan> design feature #1: programs cannot be reliably sent via email
00:14:53 <int-e> so make them newline sensitive
00:15:04 <vanila> OR: Maybe ONNLY Programs whihc get caught by spam filter are executed
00:15:06 -!- tlewkow_ has joined.
00:15:06 <int-e> by which I mean, make \r\n vs \n significant
00:15:10 <vanila> this forces progammers to write code that looks like spam
00:15:13 <oerjan> int-e: no, i mean because they get caught in spam filters
00:15:58 <nooga> oerjan: reading about braintrust now
00:16:46 <oerjan> vanila: hm maybe the semantics of a program should be based on the spam rules it triggers
00:17:25 <int-e> oooh, are there any turing complete spam filters out there...
00:17:44 <int-e> (I hope not, since they're supposed to terminate, for one, but who can say for sure?)
00:18:08 <HackEgo> Your evil overlord oerjan is a lazy expert in future computation. Also an antediluvian Norwegian who hates Roald Dahl.
00:18:34 <shachaf> i thought that was meant to be some kind of joke
00:18:50 <oerjan> shachaf: roald dahl was a creepy guy who mistreated his family but i don't actually hate him hth
00:19:34 <ion> Did his parents make a typo when choosing his name?
00:19:47 <int-e> sed -i s/hates/dislikes/ wisdom/oerjan
00:20:08 <oerjan> roald is the common norwegian spelling, as in roald amundsen
00:20:39 <oerjan> dahl is also a common spelling, although historically slightly pretentious (it's from no:dal = en:valley)
00:21:30 <oerjan> Melvar: are you neandering around the spelling here
00:22:17 <Melvar> The Neander Valley isn’t even far from here.
00:22:52 <oerjan> _and_ it's spelling (or at least that of its derived term) fluctuates between tal and thal
00:24:03 <oerjan> "In 1901 an orthographic reform in Germany changed the spelling of Thal (valley) to Tal. The scientific names like Homo neanderthalensis or Homo sapiens neanderthalensis for Neanderthal man are not affected by this change, because the laws of taxonomy retain the original spelling at the time of naming. Neanderthal station nearby still carries the name Neanderthal, because the nearby Neanderthal Museum continues to have the old spelling."
00:24:40 <int-e> code golf insight of the day: while 16 needs two characters in dc, 160 can be expressed as FA...
00:28:05 <int-e> oerjan: do you want me to say something about Leapfrogging?
00:28:30 <oerjan> it would be such a huge spoiler
00:28:39 <vanila> vegas online casino viagra online online gambling legal sites best online blackjack sites usa Playtech online casinos online casino
00:29:18 <oerjan> Dearest vanila, I write to you in this time of viagra
00:29:56 <int-e> vanila: honestly? too many casinos, too little pharmacy
00:30:08 <vanila> I'll fix that in v2 int-e
00:30:49 <int-e> And too little 401 scam, though those are hard to identify by subject.
00:31:05 <int-e> "business proposal" perhaps
00:31:35 <int-e> "work from home" (money laundering)
00:31:53 <int-e> it's funny, I don't seem to get any gambling spam at all.
00:32:29 <vanila> i once emailed a company for which some spammer had posted a comment on my site
00:32:36 <int-e> vanila: oh and how could you forget "penis enlargement"
00:32:39 <vanila> and he replied saying he didn't do it
00:33:21 <ion> Number literals could be represented in the form of “I am therefore seeking for a reliable person that will play the human role as the next of kin to this fund which is in the amount of £32,000,000.00 (Thirty Two Million Pounds Sterling).”
00:33:31 <int-e> haven't seen one of those in the while, perhaps the target audience outgrew the need.
00:36:01 <ion> http://mikko.tuomela.net/spam/
00:36:58 <oerjan> we are writhing indeed
00:37:07 <ion> Ah, don’t forget the caps. http://mikko.tuomela.net/spam/am_so_sick.txt
00:38:23 <int-e> So for small numbers, you could say "Earn up to $3,000 a week working two hours a day from home!"
00:39:22 <int-e> while for really large numbers you can go the chain letter route "Please send this letter to 3 friends. Anne didn't send this letter to her friends and her cat was hit by a bolt of lightning."
00:39:38 <int-e> (needs more exclamation marks!!!!!1)
00:40:06 <oerjan> conspiracy theory: someone already made this language. what we think are spam advertisements are really secret botnet commands.
00:40:47 <int-e> which clearly encodes 454462363333321429 (number of letters in the words of the second sentence) ;-)
00:41:52 <nooga> well there was this idea to encode emails using NSA's alledged kewords
00:45:41 <lambdabot> ENVA 220020Z 10004KT CAVOK M06/M07 Q1027 RMK WIND 670FT VRB02KT
00:49:28 <boily> chilly is perfect weather for lots of coffee, milk tea and hot chocolate.
00:52:49 <lambdabot> EFHK 220020Z VRB02KT 9000 SCT004 OVC036 M02/M03 Q1023 TEMPO 6000 -SN BKN004
00:53:05 -!- tlewkow_ has quit (Remote host closed the connection).
00:53:08 <fizzie> Less chilly, and the snow stopped too.
00:53:13 <lambdabot> CYUL 220000Z 24007KT 15SM FEW120 M08/M15 A3034 RMK AC1 AC TR SLP278
00:53:46 <boily> zlsa: what are your approximate geographic coördinates?
00:58:50 <ion> geog̈raphic coördinates
01:05:36 <lambdabot> KMCE 220053Z AUTO 12004KT 9SM SCT120 14/09 A3011 RMK AO2 SLP195 T01440094
01:06:30 <lambdabot> LOWI 220050Z AUTO VRB01KT 9999 FEW090 BKN110 04/03 Q1022
01:06:51 <oerjan> <elliott> is the subset of BF complete given by +<>[] and you can only write to a cell once TC <-- i think cyclic tag should be easy to do that way.
01:07:12 <oerjan> or a tag system in general
01:08:08 -!- tlewkow_ has joined.
01:08:15 -!- nooga has quit (Ping timeout: 250 seconds).
01:10:45 <oerjan> oh, also a minsky machine, i think
01:10:53 <oerjan> just have parallel tracks
01:11:11 <oerjan> saving each register in unary
01:11:28 -!- tlewkow_ has quit (Remote host closed the connection).
01:12:00 <oerjan> as 001111111101010101000000...
01:12:46 <int-e> in fact you can use a common base for all registers, if you want
01:12:47 <oerjan> increment by turning 00 to 01 on the right, decrement by turning 01 into 11
01:13:03 <int-e> (decrement a register by incrementing the base and all other registers)
01:13:39 <oerjan> um i'm not sure that helps?
01:14:11 <int-e> it may improve storage efficiency by a small constant factor. (less than 2)
01:14:50 <int-e> the tag system idea requires some unbalanced scanning loop like [<<<[>]<], doesn't it?
01:15:24 <oerjan> you need something unbalanced anyway
01:15:34 <oerjan> to get between beginning and end of each register
01:15:47 <int-e> yeah, I'm happy with first-order unbalanced loops, but this is second order ;)
01:16:18 <oerjan> i don't see why it should, though.
01:16:49 <elliott> oerjan: what about BF sans <?
01:17:11 <oerjan> elliott: um i think that is sub-FSA
01:17:48 <Sgeo> If most languages are in the IO monad, is Rust in the ST monad?
01:17:53 <oerjan> > is equivalent to [-] in that case
01:17:54 <lambdabot> <hint>:1:20: parse error on input ‘]’
01:19:59 <int-e> oerjan: here's what I thought. I have an infinite string, on tape, with an initial consumed part. A possible layout is 1c0x, where x is the symbol, 1 marks a part of the string, and c marks the consumed part. Now to skip back to just in front of the consumed part, I need to test for the 'c' inside the scanning loop (since it tests the wrong way for terminating the loop). Hence [<<<[>>]<], the [>>] being executed on the 'c'.
01:20:14 <oerjan> int-e: i don't think you need an unbalanced loop any more than for minsky, you just essentially expand a single minsky register 00 01 11 with also having tag representations
01:20:39 <int-e> I'm making things hard for myself
01:20:57 <int-e> I can skip to the front, and then scan forward.
01:21:11 <oerjan> so 00111111....01tag01tag...000000...
01:21:34 <oerjan> which you'll have to do for the minsky as well
01:21:59 <int-e> so instead of [<<<[>>]<], [<<<<]>[>>>>] (and then I don't actually need the extra 0 in the layout anymore)
01:22:00 <oerjan> i think that's unavoidable in a sense, since you cannot erase the bits you're scanning along
01:22:56 <vanila> is there a fuckopedia?
01:23:04 <vanila> some kind of categorization of all branfuck derivatives
01:24:08 <int-e> "fuckopedia.org is worth $1,355 - Worth Of Web Calculator"
01:24:39 <int-e> vanila: I *think* if there was a fuckopedia, it would have somewhat different contents.
01:26:36 <oerjan> vanila: http://esolangs.org/wiki/Brainfuck_extensions is a bit like that
01:28:00 <oerjan> although somewhat more limited in scope, i think
01:28:47 <oerjan> and of course http://esolangs.org/wiki/Category:Brainfuck_derivatives is an uncategorized category
01:29:04 <vanila> it could be fun to make an esolang blog
01:29:12 <vanila> post things lke 'roundup of brainfuck languages'
01:29:16 <vanila> or 'intro to unlambda'
01:29:44 <oerjan> vanila: mark chu-carroll made some esolang blog posts back in the day
01:30:02 <oerjan> i think unlambda may have been one
01:30:28 <oerjan> well, underload was, maybe both.
01:32:44 <HackEgo> [wiki] [[Bitwise Cyclic Tag]] http://esolangs.org/w/index.php?diff=41104&oldid=37454 * 212.95.7.136 * (+65) /* Self BCT */ link
01:35:30 <int-e> oh, should that https be http, hmmmmmm
01:35:31 <int-e> I'll let oerjan decide.
01:40:40 <elliott> int-e: you can do [[wikipedia:Foo|...]]
01:44:50 <oerjan> i'm sure i've mentioned i dislike that those links look internal
01:45:01 <elliott> oerjan: didn't I add an icon for them?
01:45:17 <int-e> elliott: maybe but there isn't one
01:45:54 <int-e> (as can be seen at the bottom of https://esolangs.org/wiki/Bitwise_Cyclic_Tag)
01:46:16 <int-e> (I would prefer the https link btw but the resulting icon is irritating.)
01:47:45 <oerjan> hm clearly it should use https in the link if you're viewing esolang through it
01:48:00 <int-e> (I wonder why would Mediawiki would treat Wikipedia special in any way ;-) )
01:48:42 <vanila> the BCT patterns are very beautiful
01:48:46 <vanila> http://esolangs.org/w/index.php?diff=41104&oldid=37454#BCT_programs
01:49:13 <elliott> the interwiki mechanism is general
01:49:19 <elliott> there are lots of things you can put there
01:49:26 <elliott> fizzie could add more, even
01:50:06 <elliott> this is btw something that predates wikipedia -- interwiki links come from wikis that look like c2 :p
01:52:09 <int-e> hmm. http://www.cnbc.com/id/102207790 ... so rather than having Google track me so it can display ads, now I'm letting it track me so that it knows not to show me any? ...
01:52:24 <int-e> (And pay for it, too.)
01:53:52 <int-e> (Not to mention that this is an extortion scheme. "Pretty websites you're viewing there, would be a shame if they were disfigured by annouying banners...")
02:01:16 -!- Patashu has quit (*.net *.split).
02:01:16 -!- blsqbot has quit (*.net *.split).
02:01:16 -!- mihow has quit (*.net *.split).
02:01:16 -!- Dulnes has quit (*.net *.split).
02:01:17 -!- yiyus has quit (*.net *.split).
02:01:17 -!- olsner has quit (*.net *.split).
02:01:18 -!- Bike has quit (*.net *.split).
02:01:20 -!- Gregor has quit (*.net *.split).
02:01:24 -!- variable has quit (*.net *.split).
02:01:26 -!- bb010g has quit (*.net *.split).
02:01:26 -!- newsham has quit (*.net *.split).
02:01:27 -!- zlsa has quit (*.net *.split).
02:01:28 -!- zzo38 has quit (*.net *.split).
02:01:28 -!- idris-bot has quit (*.net *.split).
02:04:04 -!- sebbu has quit (Ping timeout: 264 seconds).
02:06:02 -!- sebbu has joined.
02:10:55 -!- copumpkin has joined.
02:12:58 -!- bb010g has joined.
02:31:35 <oerjan> come on, dmm, you cannot start an annotation with "It's a little known fact that" and _not_ include a horrible pun...
02:33:14 -!- newsham has joined.
02:33:14 -!- variable has joined.
02:33:14 -!- zlsa has joined.
02:33:14 -!- zzo38 has joined.
02:33:14 -!- idris-bot has joined.
02:33:23 -!- zlsa has quit (*.net *.split).
02:33:23 -!- zzo38 has quit (*.net *.split).
02:33:23 -!- idris-bot has quit (*.net *.split).
02:33:27 <oerjan> http://www.irregularwebcomic.net/ can you find one
02:33:30 -!- Patashu has joined.
02:33:30 -!- blsqbot has joined.
02:33:30 -!- mihow has joined.
02:33:30 -!- Dulnes has joined.
02:33:30 -!- yiyus has joined.
02:33:30 -!- olsner has joined.
02:33:30 -!- Bike has joined.
02:33:30 -!- Gregor has joined.
02:34:45 -!- zlsa has joined.
02:34:45 -!- zlsa has quit (Changing host).
02:34:45 -!- zlsa has joined.
02:35:19 <shachaf> oerjan: am i missing the horrible pun
02:35:50 <oerjan> by all rights there _should_ be one there, is what i'm saying
02:36:07 <oerjan> (oh and in the rerun comment, not the comic itself hth hth)
02:36:22 <shachaf> do you still have that hth script
02:37:08 <shachaf> oerjan: what's a convenient acronym for hope that helps
02:40:40 -!- Patashu has quit (*.net *.split).
02:40:40 -!- blsqbot has quit (*.net *.split).
02:40:41 -!- mihow has quit (*.net *.split).
02:40:41 -!- Dulnes has quit (*.net *.split).
02:40:42 -!- yiyus has quit (*.net *.split).
02:40:42 -!- olsner has quit (*.net *.split).
02:40:43 -!- Bike has quit (*.net *.split).
02:40:43 -!- Gregor has quit (*.net *.split).
02:41:20 <oerjan> i think they're server may be flaky
02:42:11 -!- zzo38 has joined.
02:42:11 -!- idris-bot has joined.
02:46:58 -!- Patashu has joined.
02:46:58 -!- blsqbot has joined.
02:46:58 -!- mihow has joined.
02:46:58 -!- Dulnes has joined.
02:46:58 -!- yiyus has joined.
02:46:58 -!- olsner has joined.
02:46:58 -!- Bike has joined.
02:46:58 -!- Gregor has joined.
03:10:33 -!- Sprocklem has joined.
03:12:18 -!- boily has quit (Quit: SEEKING CHICKEN).
03:26:49 <int-e> oerjan: this is not the pun you're looking for *waves*, hth.
03:28:35 <int-e> (In this particular case I must assume that the pun died of boredom due to a clerical error.)
03:30:13 <int-e> Which raises an interesting question ... do puns have souls?
03:30:32 <oerjan> int-e: if i am interpreting recent ghc weekly news blog posts correctly, your recent comment that ghc lets gmp use ghc's allocation mechanism soon won't be true any more. so hopefully that means that is _not_ the reason for its good performance.
03:31:25 <int-e> oerjan: Ah, you might read it that way but that's not what integer-gmp2 is about.
03:31:45 <oerjan> well they won't be using the heap any longer, it said
03:32:02 <int-e> The point of integer-gmp2 is to use a lower level interface (mpn) that does not do any allocation at all, and still do the allocation on the ghc side. Hmm.
03:32:13 <oerjan> "This implementation also fixes a long standing pain point where GHC would hook GMP allocations to exist on the GHC heap. Now GMP is just called to like any FFI library."
03:33:06 <oerjan> that's what made me think that
03:34:16 <oerjan> also there was some earlier stuff about how the previous method conflicted with using other C libraries that used gmp
03:35:05 <int-e> Yes, unfortunately gmp uses global variables for the allocation functions.
03:35:35 <int-e> And the C libraries don't deal well with the fact that the allocated chunks are bytearrays on the heap that will be reclaimed during the next GC cycle ;)
03:35:41 <oerjan> or maybe i read that in the HCAR report
03:36:56 <oerjan> hm, do you mean that mpn is a lower-level gmp interface that _doesn't_ use those global allocation variables?
03:38:11 <int-e> AFAIU, all allocation goes through this function: newBigNat# :: GmpSize# -> S s (MutBigNat s); newBigNat# limbs# s = case newByteArray# (limbs# `uncheckedIShiftL#` GMP_LIMB_SHIFT#) s of (# s', mba# #) -> (# s', MBN# mba# #)
03:38:43 <int-e> and it's using the mpn_* functions of libgmp rather than the mpz_* ones; the signs are now handled on the Haskell side.
03:41:17 <oerjan> oh that might be connected with the recent suggestion of adding Natural
03:48:15 <oerjan> oh that was already added to HEAD
03:55:02 <int-e> oerjan: so I expect there will be a performance hit for multiplying large numbers, because that needs temporary allocations, and if those exceed 64kb, they'll be done on the C heap.
03:55:19 <int-e> but the impact needs to be measured.
03:56:41 -!- FreeFull has quit (Ping timeout: 256 seconds).
03:56:53 <int-e> (And by "large" I mean tens of thousands of digits and more.)
03:57:19 -!- FreeFull has joined.
04:10:45 <int-e> I'll try the 10^8th fibonacci number ... will take a while to compile ghc though.
04:11:24 <int-e> (and I'll compare 7.8.3 to current head rather than recompiling head twice)
04:16:15 <int-e> this will be my test, http://sprunge.us/GEMG?hs
04:18:00 <int-e> I suspect I won't measure much of a difference actually
04:18:10 <int-e> because the allocation cost is hidden behind actual computation.
04:26:50 <oerjan> Dulnes: it's essentially calculating fibonacci numbers with matrix multiplication, slightly optimized to avoid recalculating things (and the P is to avoid haskell laziness)
04:27:31 <oerjan> although the purpose is to test some new changes in ghc's big integer implementation
04:27:40 <Dulnes> thank you Jesus for explaining that i didnt want to look for the conversation
04:29:31 <int-e> Dulnes: I think you misspelled 'oerjan' there.
04:31:27 <oerjan> i would like not to be identified with jesus as i don't really like the idea of solipsistic pantheism hth
04:36:06 <shachaf> oerjan: what do you actually type into your computer to send a line of irc text containing "hth"
04:36:54 <oerjan> (it only strips the last one)
04:37:10 <shachaf> i thought it removed the whole line
04:37:10 <int-e> oerjan means '"hth" hth', hth.
04:37:32 <shachaf> i thought oerjan meant «"hth hth" hth»
04:38:33 <oerjan> shachaf: it would be rather awkward not to be able to write "eighth"
04:38:47 <oerjan> actually _can_ i write eighth
04:39:00 <shachaf> to be fair eighth is a pretty awkward word in the first place
04:39:06 <int-e> oerjan: interesting. I get a measurable difference - ghc head is faster. So I guess I'll try ghc head with integer-gmp, too...
04:39:06 <shachaf> shouldn't it be more like eightth
04:39:26 <int-e> (not dramatic: 6 seconds vs. 5.7)
04:40:52 <int-e> but 5% is noticable
04:41:38 <shachaf> Why does that fibonacci matrix thing work?
04:42:26 <shachaf> I mean, I can follow the computation, but e.g. why should I have expected there to be such a matrix? What is it doing?
04:42:52 <oerjan> shachaf: [1 1 ; 1 0] (a,b) = (a+b,a), right?
04:42:54 <shachaf> OK, I guess it's sort of obvious now that I think about it.
04:43:08 <oerjan> (notation made up out of thin air)
04:43:33 <oerjan> you can make such a matrix for any linear recurrence
04:44:43 <shachaf> And it has an eigenvalue phi, which I guess shouldn't be surprising.
04:44:58 <shachaf> What happens if you diagonalize it or something?
04:45:09 <oerjan> the phi^n + phi^(-n) thing comes from diagonalizing it
04:45:30 <int-e> For this particular code, I think of P a b as encoding the matrix [a,b;b,a+b]
04:46:31 <int-e> And it turns out that [a,b;b,a+b] * [c,d;d,c+d] produces another matrix of the same shape (not entirely by accident).
04:47:03 <oerjan> iirc there's an adjustment you need to perform if there are repeated eigenvalues
04:47:28 <shachaf> oerjan: I'm not familiar with that thing, but that makes sense.
04:47:43 <shachaf> int-e: I don't like "it turns out" answers. :-(
04:48:02 <int-e> (and of course [a,b;b,a+b] * [0,1;1,1] = [b,a+b;a+b,a+2b])
04:48:22 <shachaf> But anyway this makes some sense.
04:49:39 <shachaf> Oh, that code. I didn't see it before.
04:50:54 <oerjan> > let phi = (1+sqrt 5)/2 in [phi^n + phi^^(-n) | n <- [1..10]]
04:50:55 <lambdabot> [2.23606797749979,3.0,4.47213595499958,7.0,11.180339887498949,18.0,29.068883...
04:51:23 <oerjan> i think there might be a coefficient needed
04:52:14 <oerjan> > let phi = (1+sqrt 5)/2 in [(phi^n + phi^^(-n))/sqrt 5 | n <- [1..10]]
04:52:16 <lambdabot> [1.0,1.3416407864998738,2.0,3.1304951684997055,5.0,8.049844718999243,13.0,21...
04:52:29 <oerjan> > let phi = (1+sqrt 5)/2 in [(phi^n - phi^^(-n))/sqrt 5 | n <- [1..10]]
04:52:31 <lambdabot> [0.4472135954999579,1.0,1.7888543819998317,3.0,4.919349550499537,8.0,12.9691...
04:52:34 <shachaf> > let phi = (1+sqrt 5)/2 in [(phi^n - (-phi)^^(-n))/(sqrt 5) | n <- [1..10]]
04:52:35 <lambdabot> [1.0,1.0,2.0,3.0,5.0,8.0,13.0,21.0,34.0,54.99999999999999]
04:52:57 <shachaf> sounds vaguely reasonable, since the eigenvalues are phi and -1/phi
04:53:48 <int-e> I usually use (1+sqrt 5)/2 and (1-sqrt 5)/2, of course the latter is negative.
04:55:43 <oerjan> shachaf: you basically calculate [1,0] in the eigenvector basis and apply the right eigenvalue to each part
04:56:40 <shachaf> what are the eigenvectors?
04:57:50 * oerjan divides by the prime 53
04:58:45 <int-e> poor Grothendieck.
04:59:43 <oerjan> [1,phi] might be a better candidate
05:03:10 <shachaf> also what do left eigenvectors mean in general
05:03:23 <shachaf> in this case they're the same, of course, because the matrix is symmetric
05:04:22 <int-e> shachaf: actually it may be saner to think of P a b as a + b*x (mod x^2-x-1). It's easy to see (tm) that x^n = F_(n-1) + F_n x (mod x^2-x-1).
05:04:28 <oerjan> in general they live in the dual space, i think
05:05:15 <oerjan> so they're functionals composed with the matrix
05:05:43 <shachaf> that sounds more complicated than the other kind
05:06:34 <oerjan> they're functionals f such that f(Mx)=l(fx) for all x
05:06:39 <int-e> shachaf: but you get the fact that the P a b form a ring for free, rather than having it appear as a miracle.
05:07:29 <oerjan> with matrices, you have a basis, and therefore an identification of functionals with vectors
05:07:46 <oerjan> unlike with just linear transformations
05:08:13 <shachaf> oerjan: Is that really right?
05:08:27 <shachaf> You need to choose bases to go from linear maps to matrices and also to go from matrices to linear maps.
05:08:49 <oerjan> well yes, isn't that essentially what i said
05:09:25 <oerjan> what i mean is, when you are dealing with matrices and vectors in R^n, you always have an implied natural basis
05:09:50 <oerjan> so you can identify a functional f with the vector y such that (y,x) = f x for all x
05:10:09 <oerjan> where (,) is inner product
05:10:36 <oerjan> ok you need not a full basis, just enough to get the inner product
05:11:22 <oerjan> and then you get to the bra-kets of hilbert space physics
05:12:33 <oerjan> (which are essentially a visual tool for this correspondence)
05:14:04 <oerjan> but even without an inner product, you can think of functionals as having the adjoint linear transformation acting on them.
05:15:26 <oerjan> and then a "left eigenvector" is an eigenvector functional of the adjoint transformation
05:17:53 <oerjan> and this * is a contravariant functor.
05:20:31 <shachaf> I can think of a "right eigenvector with eigenvalue 1" as a fixed point of a map. Is there a similarly simple thing for "left eigenvector" or is it just "the same thing but backwards" or something?
05:20:58 <oerjan> well sure, f is a fixed point of M*
05:23:26 <oerjan> and just as f : V -> F where V is the vector space and F is the field, you can think of x as embedding into F -> V
05:24:08 <oerjan> i.e. V is isomorphic to Hom(F,V)
05:24:55 <oerjan> and then everything really is just backwards
05:25:05 <shachaf> Yes. And of course people conflate those three all the time.
05:26:36 <oerjan> although the isomorphism V -> F with V isn't canonical, and does not even exist unless finite-dimensional
05:27:17 <oerjan> (or you add continuity to get a hilbert space)
05:27:40 <int-e> oerjan: amazing, ghc head with integer-gmp takes the same 6 second that ghc-7.8.3 did.
05:28:06 <oerjan> int-e: i guess my fears were unwarranted!
05:35:29 <shachaf> oerjan: Why isn't it canonical?
05:35:34 <shachaf> Oh, you have to pick a basis.
05:38:13 -!- dts|gaming has quit (Ping timeout: 250 seconds).
05:40:44 -!- MDude has changed nick to MDream.
06:00:21 -!- FreeFull has quit (Ping timeout: 264 seconds).
06:00:53 -!- FreeFull has joined.
06:01:44 <int-e> oh, I messed up the fibonacci thing quite. tsk. badly.
06:05:50 <int-e> http://sprunge.us/hAAQ?hs actually works (spot the difference!)
06:07:19 -!- FreeFull has quit (Ping timeout: 244 seconds).
06:07:36 <shachaf> Ugh. I always try to double-click a link and then ctrl-shift-c it to copy it to CLIPBOARD.
06:07:52 <shachaf> But if I accidentally ctrl-shift-click it, it opens in my browser.
06:09:38 <int-e> http://sprunge.us/MahQ?hs ...
06:10:37 <int-e> There, finally, without that stupid typo.
06:10:38 <shachaf> int-e: Why do you need BangPatterns?
06:10:44 <shachaf> You're (==)ing on the argument right away.
06:11:08 <int-e> I don't. 'go' had two arguments previously
06:18:44 <int-e> So with integer-gmp2 the code uses less memor ... which actually makes sense; allocating temporaries on the heap is actually quite wasteful, when that memory could be reused for the next temporary.
06:33:28 <shachaf> oerjan: hmm, are vector spaces cofree as well as free?
06:34:32 <oerjan> i don't know what cofree means
06:35:26 <oerjan> although lots of things in vector and module categories are self-dual
06:36:28 <shachaf> it means a right adjoint to a forgetful functor
06:36:56 <oerjan> hm free is a kind of projective, which is dual to injective, which exists for modules over division rings
06:37:24 <shachaf> i decided that the reason everything is so well-behaved with vector spaces (at least finite-dimensional ones) is that everything is free
06:37:39 <shachaf> i.e. the whole "a linear map is determined by its action on a basis" thing
06:38:07 <oerjan> everything is also "injective"
06:38:38 <oerjan> that's a concept for general modules
06:39:07 <oerjan> ok so the forgetful functor maps a vector space to its underlying set
06:39:34 <shachaf> no, i guess the cofree thing doesn't work
06:39:35 <oerjan> no, my brain is too tired for this
06:40:08 -!- oerjan has quit (Quit: ZZLEEP).
06:40:59 <shachaf> oerjan: wait, maybe i'm still mixed up
06:49:41 -!- zlsa has quit (Ping timeout: 244 seconds).
06:51:04 -!- FreeFull has joined.
06:57:39 -!- vanila has quit (Quit: Leaving).
07:03:58 -!- scoofy has quit (Read error: Connection reset by peer).
07:11:45 -!- FreeFull has quit (Ping timeout: 255 seconds).
07:41:05 -!- FreeFull has joined.
07:45:38 -!- Sprocklem has quit (Ping timeout: 265 seconds).
08:09:15 -!- dianne has quit (Read error: Connection reset by peer).
08:09:44 -!- dianne has joined.
08:11:08 -!- FreeFull has quit (Ping timeout: 256 seconds).
08:26:48 -!- shikhin has joined.
08:31:03 -!- FreeFull has joined.
08:50:38 <zzo38> Why does "Light Pattern" esolang use the alphabetical order rather than something such as timestamps in EXIF data?
09:21:02 -!- FreeFull has quit (Remote host closed the connection).
09:21:59 -!- FreeFull has joined.
09:28:43 <zzo38> I realized that the encoding I used for RLE numbers uses one less bit than it does to code the successor of that number with Elias gamma.
09:30:39 <zzo38> (Numbers are encoded in a different way from Elias gamma, though.)
09:34:50 <zzo38> (Equivalently, one less bit than the Exp-Golomb code for the same number, since zero does not need to be encoded.)
09:36:18 <zzo38> (By Exp-Golomb I actually mean Exp-Golomb-0.)
11:01:16 -!- shikhout has joined.
11:04:24 -!- shikhin has quit (Ping timeout: 255 seconds).
11:07:47 -!- variable has quit (*.net *.split).
11:07:49 -!- newsham has quit (*.net *.split).
11:08:15 <HackEgo> [wiki] [[JUMP]] http://esolangs.org/w/index.php?diff=41105&oldid=17872 * 73.184.106.177 * (+136) Added truth-machine
11:09:14 -!- nooga has joined.
11:10:55 -!- variable has joined.
11:10:55 -!- newsham has joined.
11:10:58 -!- variable has quit (Max SendQ exceeded).
11:11:29 -!- variable has joined.
11:12:18 -!- Patashu has quit (*.net *.split).
11:12:19 -!- blsqbot has quit (*.net *.split).
11:12:19 -!- mihow has quit (*.net *.split).
11:12:19 -!- Dulnes has quit (*.net *.split).
11:12:19 -!- yiyus has quit (*.net *.split).
11:12:19 -!- olsner has quit (*.net *.split).
11:12:20 -!- Bike has quit (*.net *.split).
11:12:21 -!- Gregor has quit (*.net *.split).
11:12:50 -!- FreeFull has quit (Ping timeout: 245 seconds).
11:13:36 -!- Patashu has joined.
11:13:37 -!- blsqbot has joined.
11:13:37 -!- mihow has joined.
11:13:37 -!- Dulnes has joined.
11:13:37 -!- yiyus has joined.
11:13:37 -!- olsner has joined.
11:13:37 -!- Bike has joined.
11:13:37 -!- Gregor has joined.
11:13:53 -!- FreeFull has joined.
11:18:56 -!- FreeFull has quit (Remote host closed the connection).
11:43:33 -!- Koen__ has joined.
12:10:25 <lambdabot> EPPO 221200Z 15004KT 6000 SCT011 BKN021 05/03 Q1027
12:26:55 -!- FreeFull has joined.
12:39:45 -!- Patashu has quit (Ping timeout: 240 seconds).
12:40:10 -!- S1 has joined.
12:43:06 -!- Koen__ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
12:51:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
12:53:31 -!- boily has joined.
13:00:41 -!- Elohimswagger has joined.
13:00:49 -!- Elohimswagger has quit (Client Quit).
13:02:12 -!- Elohimswagger has joined.
13:03:57 -!- Elohimswagger has left.
13:42:51 <J_Arcane> A Y-combinator tutorial in Racket. http://blog.tomtung.com/2012/10/yet-another-y-combinator-tutorial/
13:55:02 <FreeFull> Making a Y combinator in an untyped lisp is easy
13:55:12 <FreeFull> Although you probably want a Z combinator
14:05:38 <J_Arcane> To be honest, I didn't quite follow that explanation either. XD Once they start boiling things down to single letter variables my brain sort of shuts down.
14:31:07 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
14:41:43 <J_Arcane> Also, man are BASIC's string functions primitive as hell. XD
14:41:45 <J_Arcane> Suddenly getting horrible flashbacks to trying to write command-line parsers in MS-BASIC ...
14:49:30 <fizzie> Standard Forth string functions aren't very much better. Though there's a strstr-alike, SEARCH. http://lars.nocrew.org/dpans/dpans17.htm#17.6.1
14:50:24 <fizzie> There's no MID$, though. You're just supposed to do the arithmetic yourself. /STRING can help.
14:51:18 <fizzie> (And /STRING is just ( a b c -- a+c b-c ).)
14:58:16 <J_Arcane> I like strings-as-lists; so much easier to mangle them that way.
15:19:16 -!- S1 has quit (Quit: S1).
15:25:56 -!- tromp__ has quit (Remote host closed the connection).
16:01:55 -!- boily has quit (Quit: BENTHIC CHICKEN).
16:09:12 -!- S1 has joined.
16:12:34 -!- MDream has changed nick to MDude.
16:14:15 -!- Bike has quit (Quit: thanksgiving).
16:19:14 -!- shikhout has changed nick to shikhin.
16:21:25 -!- zlsa has joined.
16:26:23 -!- tromp has joined.
16:30:45 -!- tromp has quit (Ping timeout: 245 seconds).
16:42:56 -!- copumpkin has joined.
16:44:24 -!- vanila has joined.
16:48:48 <zlsa> is there a bot channel where I can test bots?
16:49:17 <vanila> before there was a lot of bots
16:49:29 <zlsa> all the better to test mine :P
16:50:54 -!- S1 has quit (Quit: S1).
17:01:59 -!- shikhout has joined.
17:05:30 -!- shikhin has quit (Ping timeout: 256 seconds).
17:07:29 <fizzie> Also #esoteric-blah which might be equally dead.
17:07:42 <fizzie> At least if it's somehow related.
17:16:59 -!- drdanmaku has joined.
17:18:22 -!- Bicyclidine has joined.
17:51:55 -!- dts has joined.
17:59:02 -!- Sprocklem has joined.
18:12:21 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
18:16:34 -!- copumpkin has quit (Ping timeout: 264 seconds).
18:18:43 -!- S1 has joined.
18:18:57 -!- S1 has quit (Remote host closed the connection).
18:32:04 -!- copumpkin has joined.
18:43:51 <HackEgo> [wiki] [[TrivialBrainfuckSubstitution]] N http://esolangs.org/w/index.php?oldid=41106 * 68.189.222.97 * (+1791) Created page with "'''TrivialBrainfuckSubstitution''' is not a single programming language, but rather a large family of programming languages that are trivial substitutions of the [[Brainfuck]]..."
18:54:30 <elliott> pretty sure that language literally exists
18:58:23 -!- JazzyFella has joined.
19:00:13 <JazzyFella> Can someone help me with Visual Studio?
19:01:44 <Dulnes> Ask the other ppls i have to go
19:01:58 <JazzyFella> Oh damn, do you know anyone in particular?
19:03:47 <Dulnes> -_- i dont wanna say names incase they cant help but (Elliot vanila) idk if they can help but whatever you could try /wiki/ /the googles/
19:04:46 <JazzyFella> I dont know much about Code.. I'm just the IT guy... Hehehe
19:05:41 <myname> "i have a question about visual studio, i better go and ask #esoteric"
19:05:48 <myname> sounds perfectly legit
19:06:20 <zlsa> JazzyFella, #esoteric is about esoteric programming languages
19:06:30 <zlsa> Visual Studio is _not_, by any definition, esoteric
19:06:48 <JazzyFella> But I was hoping someone could help, it's so basic..
19:07:36 <Dulnes> i dont think visual studio is on the esolang wiki
19:07:53 <myname> i don't know about you, but i do think there aren't that much windows developers here
19:08:04 <JazzyFella> I just saw the description of the chat.. It said Programming blackhole.. So I thought it was legit
19:09:38 <myname> so you spent more time reading channel descriptions than googleing?
19:09:49 <myname> great way to solve problems
19:09:58 <JazzyFella> I googled. The problem I am having is to generic
19:10:39 <JazzyFella> It's this one line of code that's fudged up..
19:11:23 -!- JazzyFella has left.
19:11:26 <Dulnes> If you know how to visual studio you can fix it
19:11:53 -!- elliott has set topic: Visual Studio support channel | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
19:13:03 <myname> elliott: do you hate us that much?
19:14:15 <vanila> i love that i on eof the two people here to consult when it comes to visual studio
19:17:40 <Dulnes> Im naturally nice to people who come here.
19:17:45 -!- dts has quit (Read error: Connection reset by peer).
19:19:39 <myname> Dulnes: but an asshole to people who already were here?
19:20:29 -!- dts has joined.
19:21:12 <Dulnes> I'm sorry, I'm just really tired.
19:22:48 <elliott> I'm pretty sure myname was joking
19:25:47 <Dulnes> Im not good with jokes :/
19:31:46 <HackEgo> [wiki] [[Ook!]] http://esolangs.org/w/index.php?diff=41107&oldid=35897 * 68.189.222.97 * (+97)
19:32:39 <HackEgo> [wiki] [[OOo CODE]] http://esolangs.org/w/index.php?diff=41108&oldid=35331 * 68.189.222.97 * (+88)
19:33:44 <HackEgo> [wiki] [[OOo CODE]] http://esolangs.org/w/index.php?diff=41109&oldid=41108 * 68.189.222.97 * (-88) Undo revision 41108 by [[Special:Contributions/68.189.222.97|68.189.222.97]] ([[User talk:68.189.222.97|talk]]) No it isn't.
19:35:41 <HackEgo> [wiki] [[TrivialBrainfuckSubstitution]] http://esolangs.org/w/index.php?diff=41110&oldid=41106 * 68.189.222.97 * (-130)
19:36:15 <HackEgo> [wiki] [[Alphuck]] http://esolangs.org/w/index.php?diff=41111&oldid=40406 * 68.189.222.97 * (+40)
19:37:08 <HackEgo> [wiki] [[ZZZ]] http://esolangs.org/w/index.php?diff=41112&oldid=37900 * 68.189.222.97 * (+88)
19:42:15 <vanila> unlambda implementation uses refcounting
19:42:18 <vanila> ftp://ftp.madore.org/pub/madore/unlambda/contrib/mandelson-unlambda.c
19:42:21 <vanila> http://www.madore.org/~david/programs/unlambda/
19:42:34 <vanila> but the language has call/cc, so is it really OK?
19:42:41 <vanila> I guess it's ok since we don't have LETREC or something
19:46:57 <b_jonas> vanila: exactly, you can't make reference loops because there are no mutable cells, so it works
20:04:22 -!- contrapumpkin has joined.
20:05:18 -!- copumpkin has quit (Ping timeout: 264 seconds).
20:13:38 <zzo38> I wrote more pokemon cards I made up
20:16:16 <zzo38> Do you have any more question?
20:16:35 <vanila> I liked your gopher site
20:16:43 <vanila> but it seems like the only good site on gopherspace
20:18:35 <zzo38> Well, there are others, but they don't have as many things (and some are partially broken).
20:18:51 <vanila> I might create my own gopher page
20:19:01 <zzo38> There is The Online Book Initiative
20:19:46 <zzo38> At gopher.std.com with the selector string "1/The Online Book Initiative" (the initial 1 is a part of the selector string; so in a URL you must put it twice)
20:20:17 <zzo38> There is also gopher.semmel.ch which has a lot of music files in it
20:20:44 <zzo38> (and text files, too)
20:23:54 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
20:31:11 <J_Arcane> Oh wow. This still exists. http://www.theworld.com/
20:55:10 <HackEgo> [wiki] [[Talk:TrivialBrainfuckSubstitution]] N http://esolangs.org/w/index.php?oldid=41113 * Rdebath * (+256) /* Isn't this the category? */ new section
20:56:33 -!- Patashu has joined.
21:16:27 -!- tromp has joined.
21:21:04 -!- tromp has quit (Ping timeout: 258 seconds).
21:25:32 -!- S1 has joined.
21:27:14 -!- copumpkin has joined.
21:54:24 <Sgeo> I want to play with the MSN Browser
21:54:32 <Sgeo> But seems to need to use MSN these days
21:54:59 <ion> Sentences never uttered before in the history of universe: “I want to play with the MSN Browser”
22:09:14 <Dulnes> msn now can open a tab in the same window :0
22:09:58 <Jafet> Another: “Sentences never uttered before in the history of universe: “I want to play with the MSN Browser””
22:11:02 <Dulnes> They really tried on making it and its something your grandparents can use
22:17:24 <quintopia> which is a simple geometric and beautiful typeface for large text?
22:24:16 <ion> Microsoft Comic Sans
22:25:01 <myname> don't you mean microsoft wingdings?
22:37:01 -!- fungot has quit (Ping timeout: 260 seconds).
23:01:41 -!- shikhin has joined.
23:04:44 -!- shikhout has quit (Ping timeout: 250 seconds).
23:05:55 -!- tromp has joined.
23:10:44 -!- tromp has quit (Ping timeout: 272 seconds).
23:29:08 <zzo38> It looks to be complicated to me to get around the inability in SQLite to use savepoints while a trigger program is running.
23:43:43 <Taneb> You know you can't cook when "it's probably not still frozen" is the best thing you can say about your dinner" :(
23:46:16 -!- nooga has quit (Ping timeout: 255 seconds).
00:03:39 -!- oerjan has joined.
00:06:02 <zzo38> I looked at universal coding on Wikipedia. I guess that Elias gamma is best for small numbers, Fibonacci for medium size numbers, and Elias delta for large numbers? Is that it? (So, it would depend on how large the numbers tend to be that you are trying to encode, which one to use?)
00:08:33 <oerjan> Elias Gamma would be a good name for a mad scientist
00:10:02 <oerjan> of the "not evil, but dangerously absent-minded" kind
00:11:22 <zzo38> That's what I thought it might mean
00:12:37 <oerjan> he could have an evil twin brother with a more ominous first name, though.
00:12:50 <zzo38> Ah, OK it can do that too
00:15:50 <FireFly> oerjan: hmm, Saile Gamma doesn't sound terribly evil
00:16:15 <zzo38> quintopia: Yes that one is good job, I think.
00:18:11 <oerjan> quintopia: just as long as it's short for Rayburn http://www.babynamespedia.com/start/m/ray
00:19:03 <oerjan> although Raydon was also tempting
00:19:08 <quintopia> zzo38: I can't see any difference in the long term behavior of delta vs. fibonacci. do you know how it behaves at, say 100,000,000?
00:20:06 <zzo38> quintopia: I just saw a graph on Wikipedia that tell you how many bits are needed.
00:22:32 <zzo38> Of course it is only used when small numbers are more likely than large numbers (or if you want small numbers to be encoded smaller for other reasons, such as convenience or RLE), but I would think that which one you use would depend on how large the large numbers will tend to become.
00:23:22 <Taneb> Does anyone know any resources for learning Smalltalk?
00:25:55 <oerjan> <elliott> pretty sure that language literally exists <-- i vaguely recall there's a meta-brainfuck of similar kind, too
00:26:11 <oerjan> Taneb: alas, the only way is to go out and meet people.
00:26:25 <quintopia> Taneb: http://wiki.squeak.org/squeak
00:27:14 <quintopia> Taneb: especially this: http://daitanmarks.sourceforge.net/or/squeak/squeak_tutorial.html
00:28:00 <Taneb> Although going out and meeting people is probably a good idea when I am asking #esoteric for resources to learn a language that is past its heyday just so I can learn what the hang object-oriented programming is about
00:29:00 * oerjan is reminded of the Simula textbook that was on a shelf in the math department's student computer room
00:29:14 <oerjan> "Simula Begin", i think was its name
00:29:32 <oerjan> and that may literally have been my first introduction to OO
00:31:18 <oerjan> the computer department still used Pascal for its first semester course then
00:31:36 <Taneb> Like, I'm aware of the concept, but really to me there's this big shiny light somewhere in the distance that some people keep going on about as though it were God's gift to programmers
00:31:50 <Taneb> Called Object-Oriented Programming
00:31:57 <Taneb> And I have no idea what the big deal is
00:32:30 <oerjan> Taneb: well it was a huge leap forward over procedure-oriented programming which used to be the reigning paradigm (see: Pascal)
00:33:03 <Taneb> I have no idea what the big idea is because I have no idea what the idea is at all
00:33:13 <oerjan> however it's not so clear that it's a leap forward over functional programming, which however "only" lispers new about back then
00:33:40 <oerjan> (ml and haskell existed, but i hadn't heard of them)
00:37:00 <oerjan> Taneb: the basic idea is to have "objects" which tie together a data structure and the code acting on it, allowing an entirely new kind of modularity. (There's also inheritance, but everyone seems to think that's evil these days.)
00:37:46 <oerjan> (disclaimer: i haven't really looked much at recent developments in OO after i went functional)
00:39:54 <oerjan> OO allows mutation to be more "local", which is an improvement even if it doesn't go as far as pure functionality
00:40:45 -!- boily has joined.
00:43:28 <oerjan> "Visual Studio support channel"? (yes, i _do_ see JazzyFella i the logs)
00:43:50 <boily> something special about VS?
00:44:08 <oerjan> boily: he tried to treat this channel as general tech support
00:44:48 <oerjan> smells trolly to me, but i haven't got to the end yet
00:45:17 * boily oils his mapole and sharpens it
00:45:52 * oerjan sneakily steals back his swatter and hides it
00:47:11 <zzo38> There is also object oriented programming with COM/XPCOM interfaces (with IUnknown and QueryInterface and those things), and there is also prototype-based like JavaScript has.
00:48:12 <quintopia> boily: you have wonderful timing. i'm leaving for the airport in 7 hours to fly to mexico, so even though it's a saturday night, i'm headed to bed
00:49:00 <boily> once again, timing is everything...
00:49:08 <boily> where are you going to be mexicaning into?
00:49:36 <oerjan> <JazzyFella> It's this one line of code that's fudged up.. <-- if this was genuine, i have a hunch it wasn't really about VS at all, except afa my haskell questions would be about vim...
00:52:19 <oerjan> ciudad juárez *ducks for bullets*
00:52:26 <boily> ooooh! nice place!
00:52:37 <quintopia> anyway, catch ya back here in a week or so, unless i hop online from the hotel lobby and spot you
00:52:44 <boily> the family and I went there in... eh... about 2006 or so, I think?
00:53:01 <boily> bonnes vacances! enjoy the sun and the food!
00:53:08 <quintopia> but why would i chat on irc when there is so much mexico outside
00:53:17 <boily> be sure to visit Tulum!
00:53:22 <boily> (and bring a swimsuit.)
00:53:26 <quintopia> don't forget the liquor and swimming holes
00:53:57 <boily> Tequila, rhum, the cenotes― wait?
00:54:17 <boily> chicken pizza and cobol???
00:54:51 -!- tromp has joined.
00:54:52 <quintopia> http://en.wikipedia.org/wiki/Chichen_Itza http://en.wikipedia.org/wiki/Coba
00:55:04 <boily> oh. chicken pizza. I see.
00:55:05 <oerjan> quintopia: thanks, i didn't get the Cobol
00:55:33 * oerjan stealthily add an s after http
00:55:57 <oerjan> also after add, come to think of it
00:56:19 <boily> Dulnes: would you have prefered Dullones? I'm very flexible when it comes to welcomes.
00:56:54 <boily> hm. no good. Dulnellos it is, then.
00:57:08 <Dulnes> My username is just a mispelt version Dullness
00:58:14 <Dulnes> Visual studio support channel still hasnt been changed?
00:58:51 -!- oerjan has set topic: Visual Studio euthanasia channel | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
00:59:11 <Dulnes> Windows 93 support desk would be a nice topic
00:59:15 -!- tromp has quit (Ping timeout: 256 seconds).
01:01:36 <Dulnes> boily: i prefer Dulnes but you go with that for now.
01:05:40 <oerjan> <quintopia> which is a simple geometric and beautiful typeface for large text? <-- times roman hth
01:05:50 <oerjan> especially good for large stone inscriptions
01:06:20 -!- S1 has quit (Quit: S1).
01:07:31 <Dulnes> Itchy on the eyes is how i would put it
01:09:35 <Taneb> Apparently Smalltalk uses only 2-3 concept.
01:09:47 <Taneb> Amazing how they managed to use only -1 concept!
01:10:30 <shachaf> -1-concepts sound reasonable
01:10:37 <shachaf> http://ncatlab.org/nlab/show/negative%20thinking
01:10:50 <oerjan> shachaf: did you know the empty topological space has dimension -1
01:11:03 <shachaf> oerjan: is that lebesgue covering dimension
01:11:28 <oerjan> boily: it fits very nicely into definitions
01:11:33 -!- adu has joined.
01:11:34 <shachaf> i guess it makes some sort of sense, maybe
01:11:46 <shachaf> since the one-point space surely has dimension 0
01:11:54 <shachaf> maybe the empty space should have dimension -∞??
01:12:33 <Taneb> I think the prime decomposition of zero has all exponents = infinity
01:13:09 <oerjan> shachaf: no, see, if you have an n-dimensional space, then by one of those inductive definitions that means the boundary sets in it are n-1 dimensional, and n is the smallest number that works for.
01:13:27 <oerjan> and that happens to give the right definition for 0-dimensional if the empty space is -1
01:14:07 <int-e> Taneb: hmm, I'd prefer 0 not to have a prime factorization. it is the greatest element in the divisibility lattice though.
01:15:17 <shachaf> oh, i guess you mean "at most n-1 dimensional" or something?
01:16:12 <oerjan> shachaf: well it works for lebesgue covering too, i see
01:16:55 <oerjan> "We want the dimension of a point to be 0, and a point has empty boundary, so we start with"
01:16:59 <oerjan> \operatorname{ind}(\varnothing)=\operatorname{Ind}(\varnothing)=-1
01:17:37 <oerjan> https://en.wikipedia.org/wiki/Inductive_dimension
01:20:59 <Taneb> fungot seems to be missing!
01:27:35 -!- bb010g has quit (Quit: Connection closed for inactivity).
01:29:47 -!- nooga has joined.
01:34:06 -!- nooga has quit (Ping timeout: 245 seconds).
01:34:44 -!- scounder has quit (Changing host).
01:34:44 -!- scounder has joined.
01:49:07 -!- Sprocklem has quit (Ping timeout: 256 seconds).
01:56:30 -!- tlewkow has joined.
01:57:07 <Taneb> Freefall theory: the fact that Florence now has a wiped ID chip will become relevant
01:58:11 -!- fungot has joined.
01:58:25 <fizzie> I'm practically asleep already.
01:58:48 <fungot> shachaf: may be." a little confusing to people who think that way
01:59:32 -!- tlewkow has quit (Remote host closed the connection).
02:00:35 <boily> fungot: of course people who think like you are confused. even people who don't.
02:00:35 <fungot> boily: maybe i should fix the texinfo if you don't
02:00:56 <boily> fungot: I ain't touching no texinfo. pfshaw! manpages for ever!
02:00:56 <fungot> boily: asian girls usually are in decimal anyway, though, i don't need your stinkin' context, riastradh. :) what particular differences are you having
02:01:20 <boily> asian girls are in decimal? de quossé?
02:02:08 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
02:03:33 <boily> I should have known better than to expect anything else than irc.
02:03:57 <fungot> Selected style: ct (Chrono Trigger game script)
02:04:13 <shachaf> fizzie: nlab would be a good style
02:07:25 <oerjan> fungot: done any good sword stopping lately?
02:07:25 <fungot> oerjan: we are looking, but well behaved! crono!!
02:08:37 <fungot> int-e: like, thanks princess. i'll take that under advisement!! crono!! crono!!
02:08:56 <int-e> fungot: ok, that was two cronos, can you do three?
02:08:56 <fungot> int-e: that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone can't stop! that sword alone c
02:09:27 <fungot> Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011)
02:09:28 <int-e> Ah, a different loop, I'll take what I can get.
02:09:41 <oerjan> um that _is_ the loop.
02:10:07 <int-e> But "crono!! crono!! crono!! crono!! crono!! crono!! ..." would've been so much nicer.
02:10:49 <oerjan> i haven't seen that, i suspect that isn't an unescapable one
02:11:00 <int-e> And sorry, but I'm no expert on fungot loops.
02:11:00 <fungot> int-e: i've never been to the bottom of a bottle. do i seem to see them, but they all suspect he's sad. they say " are you alright
02:11:52 <oerjan> fungot: well if he's sad he should report for termination immediately!
02:11:52 <fungot> oerjan: people in car car simulator trucko boat 3. that's a ' thr' followed that.
02:12:03 <int-e> fungot: who's "he" and what's he doing at the bottom of the bottle?
02:12:03 <fungot> int-e: i like that this is, like, a 50/ 50 mixture of both societal and biological self, all that gets us is a murky combination of influences, predisposition, anyways. the point is that i came, i'd have to throw away a good chunk of it for the days i've already lived.
02:12:31 <int-e> fungot: that did not help at all.
02:12:31 <fungot> int-e: dammit t-rex, how many? encase unspoiled areas, where good and bad at different points in the arcade version, this isn't a riddle. it's a real question i'm investigating!
02:14:02 <fungot> int-e: this may be a bad time to say all the run-of-the-mill thoughts we have! and it is a secret! i never
02:14:03 <HackEgo> Sir Fungellot cannot be stopped by that sword alone!
02:14:24 <int-e> That makes a lot more sense now.
02:15:42 <int-e> I like "run-of-the-mill secrets"
02:19:42 -!- Bicyclidine has joined.
02:26:28 -!- adu has quit (Quit: adu).
02:28:34 <int-e> sometimes I'm thinking too much. http://qdb.us/307308 ... I guess Thurmond or one of Thurmond's freinds is called Josh, which happens to approximate ёж.
02:30:45 <boily> I'll take "What is a Yozh for 400".
02:32:29 <oerjan> the zh is devoiced, it seems
02:32:56 <shachaf> how do you pronounce unvoiced zh
02:33:15 <oerjan> shachaf: um russian has mandatory devoicing of final consonants
02:33:39 <int-e> Nah, ж is voiced, that's why I wrote "approximate"
02:33:52 <oerjan> int-e: um it's not reflected in spelling
02:34:20 <oerjan> but e.g. the ipa here is unvoiced https://en.wiktionary.org/wiki/%D1%91%D0%B6
02:34:38 <oerjan> int-e: i know that. i'm just saying it's _pronounced_ unvoiced in that position.
02:35:43 <int-e> doesn't exist. жтж?!
02:36:08 <shachaf> i don't think щ is actually pronounced as штш
02:36:40 <shachaf> that's just what they want us to think
02:36:51 <int-e> (I did forget most of the Russion I've ever learned, but ёжик was a mnemonik for the ж letter which looks a bit like a hedgehog.)
02:36:54 <oerjan> shachaf: from what i learned on wikipedia while learning a russian song, the t is usually not pronounced these days
02:37:14 <shachaf> oerjan: ш and щ are pronounced slightly differently
02:37:22 <shachaf> i just can barely hear the difference
02:37:30 <oerjan> int-e: yeah but there the ж is not final
02:37:36 <shachaf> but i talk to russian speakers and they tell me which one is which
02:38:33 <shachaf> int-e: i thought the usual mnemonic was жук?
02:38:39 <shachaf> since it looks a bit like one
02:38:53 <shachaf> also "djuk" is a common hebrew term for cockroach
02:38:59 <oerjan> shachaf: ask them if there's a difference between ш and с in front of palatalizing vowels
02:39:10 <shachaf> oerjan: they aren't around hth
02:39:56 <int-e> oerjan: it may be voiced less than in the middle of a word, but I'd still expect an audible difference; (also I'd expect to have learned about such a difference and I'm sure I haven't)
02:41:46 <int-e> shachaf: that would make sense, but maybe hedgehogs appeal more to children (I was 8 or 9 at the time...)
02:42:02 <shachaf> hebrew has so many good words
02:42:43 <shachaf> "chupchik" should be imported
02:42:49 <shachaf> but i think it doesn't really fit in english
02:43:41 -!- tromp has joined.
02:44:41 <oerjan> shachaf: my impression is that щ is pronounced like two consonants, they're just both fricative-like
02:45:46 <shachaf> oerjan: there are recordings at https://en.wikipedia.org/wiki/Voiceless_palato-alveolar_sibilant and https://en.wikipedia.org/wiki/Voiceless_alveolo-palatal_sibilant
02:45:55 <oerjan> maybe i should have studied linguistics, in which case i would now be in a #linguistics channel somehow discussing math
02:46:29 -!- zlsa has left ("Leaving").
02:47:16 <oerjan> someone put a [citation needed] on norwegian for the former :P
02:47:26 <oerjan> does that mean it's not what i think it is
02:47:51 -!- tromp has quit (Ping timeout: 240 seconds).
02:48:58 <oerjan> "Application blocked by security settings" yeah i think that happened the last time i tried to hear sound on wikipedia too
02:49:39 <int-e> I think there is no actual 't' in щ, but you interrupt the air flow with your tongue just like for a t.
02:52:08 <oerjan> oh and the other article claims _that_ is the sound norwegian uses.
02:52:49 <shachaf> Bicyclidine: it depends on neither awea norwegian
02:53:17 <boily> I fear Norwegian can't be properly experienced except through being very, very regional.
02:53:38 <shachaf> Bicyclidine: it's me trying for a neither-nor pun and not succeeding hth
02:56:43 * oerjan swats shachaf -----###
02:58:07 <boily> I just understood shachaf's pun. I shouldn't be laughing.
02:58:52 <int-e> does "awea" have a meaning?
02:59:06 <Bicyclidine> say you're facing north on the equator. you go east while still facing north. eventually you end up back at your starting position still facing north.
02:59:10 <oerjan> int-e: it has a pwetty cwear meaning, yes
02:59:29 <Bicyclidine> if you walk a bit north before going east, you'll follow some other longitude line
02:59:50 <Bicyclidine> but if you walk all the way to the north pole without turning, and then sidestep right, you'll be on a latitude.
03:00:00 <Bicyclidine> am i missing omsething? this seems too abrupt, somehow
03:00:13 <int-e> ok, I have to agwee with oewjan, that was pwetty awful.
03:01:33 <oerjan> Bicyclidine: um is your problem that longitude isn't continuous at the poles?
03:01:44 <int-e> Bicyclidine: you're dividing by zero
03:02:05 <Bicyclidine> but somehow "right" going from meaning east to meaning south to meaning west within an infinitesimal space seems really weird.
03:02:41 <Bicyclidine> tiny circle, tinier circle, ENTIRE CIRCUMFERENCE OF THE MANIFOLD, tinier circle, tiny circle
03:03:02 <oerjan> Bicyclidine: hm it's not _actually_ east if you walk more than infinitesimally other than at the equator
03:03:41 <int-e> except on the equator, you'll never be walking on a straight line (great circle), why does this suddenly change when you reach the pole? it's a bit hard to walk on a circle with zero radius, granted, but that's what you ought to be doing.)
03:03:42 <shachaf> well what does "sidestep" mean
03:04:05 <Bicyclidine> oh, yeah. maybe the problem is i'm assuming you maintain your direction relative to the pole, except at the pole
03:05:10 <boily> shachaf: it's before you take a jump to the left, and put your knees together.
03:05:22 <Dulnes> Btw (off topic) im curious on the concept of 0 but whatever
03:05:48 <Bicyclidine> additive identity, multiplicative whatever, deliciously donut-shaped
03:06:06 <oerjan> you put your left foot in, your left foot out, you put your left foot in and shake off the icebear gnawing at it
03:06:16 <shachaf> Bicyclidine: it's another word for root hth
03:06:45 <int-e> Dulnes: it's an absorbing element for multiplication.
03:07:16 <shachaf> for the monoid of possibly-infinite lists, every infinite list is a left zero
03:07:18 <Dulnes> Well i feel like the only reason dividing by zero is impossible is because you are secretly dividing by infinity ( this is just my speculation )
03:07:38 <oerjan> no, you're secretly multiplying by it hth
03:07:42 <shachaf> it's actually a conspiracy by The Man intended to keep you down
03:07:54 <boily> dividing by zero doesn't work because you don't know which infinity you are multiplying with htah
03:07:56 <Bicyclidine> it doesn't make sense because there's too many things it could be
03:08:35 <Dulnes> Everytime you divide by zero a universe ends
03:08:36 <boily> that's where surreal numbers get quite useful.
03:08:37 <int-e> It just so happens that 0 * x = 1 has no solution (unless you allow 0 = 1, and very few mathematicians allow that kind of ring).
03:09:25 <zzo38> I think the reason dividing by infinity is not allowed is because 0x=1 has no solution rather than for other reason, although there are other reason too that is combine with.
03:09:28 <int-e> shachaf: if that's supposed to become a ring ... how does that satisfy the distributive laws?
03:09:34 <zzo38> So, there is many reasons.
03:09:58 <shachaf> Bicyclidine: whoa whoa whoa
03:10:05 <shachaf> what are you talking about
03:10:15 <zzo38> int-e: I suppose a trivial ring will have 0=1 though?
03:11:36 <oerjan> int-e: um surely the trivial ring is a ring, otherwise you don't have a variety. fields are another matter though. (also see ...wtf wikipedia went down)
03:11:43 <int-e> zzo38: it's quite common to have 0 != 1 as one of the ring axioms.
03:12:08 <zzo38> int-e: Really? I didn't think it is.
03:12:45 <int-e> but not universally agreed upon. (obviously since it's not even universally agreed that rings have multiplicative units)
03:13:21 <zzo38> Then you will have many definition of a "ring"
03:13:31 <Dulnes> I feel like you shouldnt even let a bot try to div by 0
03:13:48 <Dulnes> Its very deadly for most bots
03:13:48 <oerjan> https://en.wikipedia.org/wiki/Field_with_one_element
03:13:58 <shachaf> oerjan: So "all vector spaces are free" tells you that a linear map : V -o W is characterized by its action on a basis of V
03:14:15 <int-e> oerjan: for all primes except 1 ...
03:14:29 <vanila> all primes except 1? does that include -infinity or not?
03:14:40 <int-e> vanila: of course not
03:14:45 <shachaf> oerjan: But is there some similar thing that talks about the basis of W?
03:15:00 <boily> Dulnes: coffee is always good. drink more coffee.
03:15:11 <shachaf> I.e. the thing that makes matrices work.
03:15:41 <oerjan> shachaf: well "characterized" would seem to imply to me just one way, you need also that any map from the basis can be extended
03:16:23 <int-e> I was alluding to history. Quoting randomly from the internet (Yahoo answers): "Actually pre 19th centuary 1 was considerd to be a prime."
03:16:30 <oerjan> i mean you could take any generating set, and it would be characterized by its action on that, even if it's not independent
03:16:49 <shachaf> What does it mean for it not to be independent?
03:17:05 <shachaf> The elements of the basis can just be taken as formal elements or however people normally put that.
03:17:12 <int-e> But once you start getting serious about number theory, you'll end up with many statements that hold for all primes except 1. So it's more convenient if you just define 1 not to be prime.
03:17:17 <shachaf> Let's say : FA -o W, where F is the free functor.
03:17:23 <shachaf> Or maybe I don't understand your objection.
03:17:48 <oerjan> shachaf: my objection is that much of your claim is baked into the definition of "basis"
03:18:22 <oerjan> there are other sets such that a linear transformation is characterized by its action on them.
03:18:34 -!- nooga has joined.
03:18:44 <oerjan> and if you were _not_ working in a vector space, those sets might be all you have
03:18:46 <shachaf> You mean any superset of a basis?
03:18:52 <Bicyclidine> y'all manage to make linear seem even more complicated than kolmogorov could make it. impressive? yes.
03:18:58 <shachaf> I don't think you really need the word "basis" here.
03:19:17 -!- boily has quit (Quit: HYPOSEGMENTAL CHICKEN).
03:19:22 <shachaf> If you have a map : FA -o W, it corresponds to a function : A -> UW
03:19:28 <oerjan> shachaf: you need some way to imply that there exists a set such that any map from that set to W can be extended to the whole of V.
03:20:07 <shachaf> Isn't that part of what it means to say that FA is free?
03:20:10 <oerjan> which for vector spaces is the same as "basis" but that's not the case in other algebras (including non-free modules over rings)
03:20:14 <Dulnes> Maybe we could say 1 over infinity = 0
03:20:24 <Dulnes> Uh that is a problem because if we divide 1 into infinite peices and they end up 0 each what happened to 1? So nvm
03:20:46 <oerjan> shachaf: ok maybe you only had implication in one direction to start with
03:20:52 -!- adu has joined.
03:21:44 <Bicyclidine> there's no particular need to define one over infinity
03:21:51 <Bicyclidine> just go into projective geometry or something instead
03:22:07 <int-e> Dulnes: now you have a new concept that doesn't fit nicely into rings, namely infinity.
03:22:45 -!- nooga has quit (Ping timeout: 240 seconds).
03:22:53 <int-e> Dulnes: You *can* do this, but you're bound to lose some properties; in this case, that's likely to be inverses for addition.
03:23:43 <oerjan> Dulnes: 1 over infinity = 0 is pretty standard for functions on the riemann sphere. you still get trouble with 0/0, though.
03:24:06 <shachaf> oerjan: Anyway, as far as I can tell, that's half of why you can make matrices work between finite-dimensional vector spaces.
03:24:25 <shachaf> Since you can "take a vector apart" in terms of its basis.
03:25:41 <shachaf> But where does the other half come from?
03:25:56 <shachaf> Is that just from W being free?
03:26:07 <oerjan> matrices also work somewhat for commutative rings
03:26:23 <Bicyclidine> could you give a linear transform just by describing its eigenspaces and kernel, i wonder. would that work without a basis. i guess not since that probably adds up to a basis.
03:26:28 <oerjan> although i don't know about modules over them
03:26:59 <oerjan> shachaf: i think i'm too tired for this
03:27:10 <shachaf> oerjan: hey you were too tired last night too
03:27:15 <lambdabot> Local time for oerjan is Sun Nov 23 04:26:46 2014
03:27:22 <shachaf> maybe you should sleep hth
03:27:24 <oerjan> Bicyclidine: the kernel is one of the eigenspaces hth
03:28:03 <oerjan> shachaf: i may be permanently tired of very high math.
03:28:16 <shachaf> whoa, i didn't know you were high
03:29:59 <Dulnes> 1/x, 1 1.00000, 2 0.50000, 4 0.25000, 10 0.10000, 100 0.01000
03:30:07 <oerjan> Bicyclidine: my sleeping cycle has been utterly unstable for years; i _couldn't_ sleep now if i tried.
03:31:23 <Dulnes> I think coffee is bad for me
03:31:59 <int-e> shachaf: somewhere you need the property that any basis for a subspace can be extended to a basis of the whole space.
03:32:34 <Dulnes> i guess humans will never know
03:32:44 <Dulnes> Im done trying to calculate this
03:32:47 <int-e> (FTR, I generally don't find category theory helpful for this. I keep having to translate everything back into vector space terms.)
03:32:59 <Bicyclidine> question two: how does a simulation of relativistic physics work? is it possible to have an absolute spacetime that internal observers would see as einsteinian?
03:33:45 <Bicyclidine> becuase all the category stuff ounds like gibberish that's why
03:33:50 <int-e> Why what? It's abstract nonsense, is why.
03:33:51 <FreeFull> I'm tempted to make a small programming language where the type system really is algebraic
03:33:58 <shachaf> Why do you need that property?
03:34:00 <FreeFull> So the type of an 8-bit number would be 2^8
03:34:01 <oerjan> FreeFull: https://en.wikipedia.org/wiki/Wheel_theory hth
03:34:12 <int-e> (That's a quote, but who said that...)
03:34:15 <shachaf> Also I don't know vector space terms and I know at least a few category theory terms.
03:34:15 <vanila> FreeFull, That sounds really cool
03:34:17 <Bicyclidine> algebraic data types are sufficiently algebraic for me
03:34:29 <vanila> I would be interested in it
03:34:53 <zzo38> FreeFull: Yes, we should see it OK, try to make such a thing please
03:34:58 <int-e> ah maybe it wasn't any person in particular.
03:35:07 <Bicyclidine> how does it work again. whatever fuck math
03:35:29 <shachaf> oh i had another question about free things
03:35:37 <Bicyclidine> and 1+ax² is a binary tree and bla bla. bla.
03:35:42 <shachaf> is there some sense in which a topology generated by a subbasis is free over that subbasis
03:36:03 <oerjan> Bicyclidine: the twin paradox means that a simulation that includes it cannot give the correct einsteinian times for both observers
03:36:04 <shachaf> e.g. maybe you have a lattice of all possible topologies over a set or something
03:36:09 <FreeFull> Note you'd want to have some sort of tag system too, to tag if a number is unsigned or such
03:36:39 <oerjan> so the simulation could at best only be watched by one person in "realtime"
03:36:50 <int-e> shachaf: It's also that my knowledge of CT is rather limited. I shut down at the point anybody mentions adjoint functors.
03:37:05 <lambdabot> Local time for int-e is Sun Nov 23 04:36:36 2014
03:37:15 <shachaf> int-e: have you considered that adjoint functors are the best thing
03:37:18 <Bicyclidine> it just suddenly seemed weird that hashlife relies on their being a speed of light, but not lorentz covariance
03:37:48 <FreeFull> The twin paradox is resolved by considering acceleration
03:37:50 <int-e> shachaf: I've seen some enthusiasm displayed on the subject. I couldn't follow.
03:38:33 <shachaf> int-e: i think the catsters videos about them were good??
03:39:56 <oerjan> Bicyclidine: i once tried to find out if rule 110 had a nontrivial space-time symmetry
03:40:25 <Bicyclidine> i have a professor that does computational physics and he already indulged me about GR, I'll just ask
03:40:27 <oerjan> it is _possible_ you could find a rule 11 metacell that moved at a different speed
03:41:16 <oerjan> (i was intrigued by how the list of gliders known for it seemed to have a pattern in the speeds allowed.)
03:42:20 <zzo38> oerjan: What is a nontrivial space-time symmetry?
03:42:23 <oerjan> (incidentally rule 110 has a different maximal speed _inside_ the ether pattern
03:42:31 <Bicyclidine> i guess GoL isn't lorenz. because the speed of light is absolute. huh.
03:42:54 <oerjan> Bicyclidine: um the speed of light is absolute in reality too
03:43:13 <int-e> right, in general there's only one frame of reference in cellular automata
03:43:20 <Bicyclidine> If you had a colle- ok yeah that basically.
03:43:25 <oerjan> zzo38: anything other than translation, mirroring and rescaling...
03:43:44 <Bicyclidine> If you were a living automata collection and were moving at a constant velocity, you coul dtell that you were moving at a constant velocity.
03:44:21 <oerjan> zzo38: you'd want a map which took a complete time evolution of rule 110 and mapped it, locally continuously, into another complete time evolution moving at a different relative speed.
03:45:02 <oerjan> also, there would be some restriction on the patterns allowed to deal with the need to be inside the "ether" pattern.
03:45:36 <oerjan> i assume the ether pattern would be like a vacuum, and mapped to itself.
03:45:56 <oerjan> there would need to be some expansion in size, i think.
03:46:21 <int-e> oh crazy ... http://uncomp.uwe.ac.uk/genaro/Papers/Papers_on_CA_files/MARTINEZ.pdf
03:46:25 <FreeFull> Rather than something like rule 110, you could have some sort of particle physics thing?
03:46:54 <zzo38> Why is the "Mathematical Universe Hypothesis" called that? It isn't really a scientific hypothesis, as far as I can tell.
03:47:21 <FreeFull> zzo38: Well, it doesn't say scientific in its name
03:47:34 <Bicyclidine> "hypothesis" is a liberal lie, join the navy
03:47:37 <oerjan> <FreeFull> The twin paradox is resolved by considering acceleration <-- you still cannot make a multiplayer simulator that lets each player experience the correct proper time, though, because of it.
03:48:00 <FreeFull> oerjan: Yes you can, you just have to load one of the players into a rocket..
03:48:11 <zzo38> It doesn't really seem a hypothesis at all, really...
03:49:38 <zzo38> It doesn't really seem a conjecture either.
03:50:11 <zzo38> Not that there is anything wrong with the mathematical universe hypothesis, but the name seems a bit wrong.
03:50:18 <int-e> zzo38: it's a hypothesis, just not a scientific one.
03:50:51 <zzo38> int-e: Are you sure? I am not very sure.
03:50:55 <int-e> (at least my limited brain cannot imagine any way it could be tested)
03:51:13 <oerjan> int-e: i think that's the paper i looked at, way back
03:51:41 <FreeFull> They're not random, but we can't just find a pattern
03:52:08 <oerjan> <FreeFull> Rather than something like rule 110, you could have some sort of particle physics thing? <-- the thing is, if it's not 1d you have to deal with rotations and i have no clue how that would work.
03:53:07 <FreeFull> oerjan: You'd just have a bunch of straight line intersections, I assume
03:53:49 <oerjan> i mean to have lorentz-like invariance or at least an endomorphism
03:55:12 <int-e> zzo38: (I'd also call the Church-Turing thesis a hypothesis.)
03:55:17 <oerjan> int-e: when it was discussed over at aaronson's blog (he's a friend of tegmark but otherwise disagrees pretty strongly), someone brought up "dust theory" from the SF novel permutation city
03:55:25 <int-e> colloquially, "working assumption"
03:55:46 <zzo38> int-e: That I can see, kind of. But it is a bit different.
03:55:46 <oerjan> that would allow you a test, although not one that you could bring back the results of.
03:55:55 <Bicyclidine> well, there's my physics professor emailed. i'm sure he'll be happy to get a half-formed email about something he doesn't actually work in.
03:56:16 <oerjan> (which is pretty similar to black holes...)
03:56:52 <zzo38> About mathematical universe hypothesis, I think it is more philosophical kind of and isn't scientific (and that Occam's Razor wouldn't actually tell you anything about it and is irrelevant to this kind of discussion, even though other people say otherwise). I also do believe in such thing though, in a way; have you heard of my diagram involving GOD and how it relates to such thing?
03:57:26 <oerjan> hm i'm still waiting for that picture of a black hole that was promised "soon" over a year ago, i think.
03:57:39 <Bicyclidine> have you considered accepting our lord and savor feyerabend
03:57:43 <zzo38> And how you can see how it follow from that, its relation more to philosophy than scientific.
03:57:52 <oerjan> although i haven't been keeping up with science news, i assume i'd have heard of _that_
03:57:56 <int-e> Sure, it's philosophical. Is there hope of being a mathematical model of the whole universe or is the best we can do to come up with ever more precise approximations?
03:57:56 <zzo38> Bicyclidine: I do not understand.
03:58:14 <Bicyclidine> http://en.wikipedia.org/wiki/Epistemological_anarchism
03:58:20 <int-e> (These two options are not mutually exclusive either.)
03:58:24 <zzo38> int-e: Probably, coming up with ever more precise approximations; over time it can be figured out.
03:58:58 <oerjan> Bicyclidine: delicious? is this a cannibalistic religion like christianity?
03:59:05 <zzo38> (whether or not anyone figures out an exact mathematical model; but I think even if someone can you cannot really tell for sure?)
04:00:34 <zzo38> I believe it must mathematically exist, but that it doesn't necessarily mean anyone can ever figure out.
04:01:11 <int-e> zzo38: So you believe in the MUH.
04:01:18 <zzo38> I may have told you about my diagram with four concentric circles?
04:01:24 <zzo38> int-e: Yes, I have said that already.
04:01:43 <int-e> is it a Venn diagram?
04:01:51 <Bicyclidine> i misspelled "savior", but hey why mess wwith that
04:04:10 <zzo38> The contents of the diagram aren't really considered as sets although sets may be a concept that can be understood more easily than GOD.
04:05:21 <int-e> There's no understanding the elements of the empty set. Their remarkable properties are without end.
04:05:55 <zzo38> It is easily understood: There are none. That isn't the point, though.
04:06:24 <zzo38> Bicycldine: "GOD Over Djinn" (if you mean Godel, Escher, Bach)
04:07:58 <int-e> > fix id -- this was the essence of the GOD computation, it just happened to pick a different fixed point
04:09:40 <zzo38> I wasn't talking about Hofstadter's books though
04:11:24 <oerjan> int-e: iirc it was also implied that some steps would have errors
04:12:12 -!- bb010g has joined.
04:12:38 <vanila> Hofstadter Shmoffstadter
04:13:16 <zzo38> I do like his book though
04:25:36 -!- adu has quit (Quit: adu).
04:32:34 -!- tromp has joined.
04:37:29 -!- tromp has quit (Ping timeout: 265 seconds).
04:54:31 -!- augur_ has quit (Ping timeout: 245 seconds).
04:59:02 -!- tromp has joined.
05:00:39 -!- shikhin has quit (Ping timeout: 256 seconds).
05:01:35 -!- tromp has quit (Read error: Connection reset by peer).
05:02:09 -!- tromp has joined.
05:07:29 -!- nooga has joined.
05:12:17 -!- nooga has quit (Ping timeout: 265 seconds).
05:14:18 -!- augur has joined.
05:28:14 -!- tlewkow has joined.
05:51:14 -!- MDude has changed nick to MDream.
05:56:39 -!- Patashu has quit (Ping timeout: 258 seconds).
06:02:53 -!- tlewkow has quit.
06:04:28 -!- Dulnes has quit (Quit: Connection closed for inactivity).
06:21:27 -!- tlewkow has joined.
06:40:59 -!- Dulnes has joined.
06:41:15 <Dulnes> Happy birthday to me... Ew
06:46:13 <int-e> Ew indeed... http://iambaker.net/rainbow-birthday-cake/
06:47:03 <oerjan> `` echo 'Happy birthday to you, happy birthday to you, happy birthday to Dulnes, happy birthday to you!' | rainwords
06:47:04 <HackEgo> Happy birthday to you, happy birthday to you, happy birthday to Dulnes, happy birthday to you!
06:49:07 <Dulnes> And int-e if my child requested of me a "pretty cake" i would give them a cupcake with a hot dog sticking out of it
06:49:17 <oerjan> int-e: not a believer in the 7-color rainbow, i see
06:49:53 <Dulnes> I like the gray scale rainbows
06:50:41 <Dulnes> The awful ones you see at a Florida airport
06:55:42 <int-e> oerjan: apparently not
06:56:24 -!- nooga has joined.
06:57:43 * J_Arcane writes list functions he still can't use anywhere ...
07:00:46 -!- nooga has quit (Ping timeout: 245 seconds).
07:02:19 <int-e> Oh, I had not read friday's GG comic, I like the general.
07:05:11 <J_Arcane> What's a good test list for making sure foldl and foldr are working as expected?
07:08:15 <lambdabot> [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,...
07:08:43 <shachaf> > foldr (:) [] (1:2:undefined)
07:09:07 <oerjan> > foldl (flip (:)) [] [1..10]
07:09:48 <J_Arcane> Heh. I'm in a lisp, no lazy evaluation. That's a good point though, that was the usecase LYAH used.
07:12:27 <J_Arcane> Hmm. I thought I'd try subtraction. Got this: http://pasterack.org/pastes/41876
07:14:15 -!- tlewkow has quit (Remote host closed the connection).
07:14:42 -!- tlewkow has joined.
07:14:44 <J_Arcane> That does appear to be the correct result if I step through it in my head.
07:14:54 <J_Arcane> Wonder why Racket's foldl/r don't do the same.
07:15:00 -!- shikhin has joined.
07:15:22 <oerjan> possibly it uses different argument order?
07:15:42 <oerjan> > foldl (flip (-)) 0 [1..5]
07:15:58 <oerjan> try with an even length list
07:17:03 <shachaf> [] is the perfect test case
07:18:02 <shachaf> another good test case is the free pointed magma
07:18:24 <shachaf> i.e. data N a = N a | NEmpty | NAppend (N a) (N a)
07:19:05 <J_Arcane> http://pasterack.org/pastes/37221
07:19:07 -!- tlewkow has quit (Ping timeout: 264 seconds).
07:25:49 * oerjan swats shachaf in the type system ~~~~~¤¤¤
07:26:31 <oerjan> confused the value [] with the type constructor []
07:26:48 <J_Arcane> shachaf: Ahh, I see what you mean. http://pasterack.org/pastes/16294
07:28:08 <J_Arcane> I think it's in how I wrote the null case vs. how Racket wrote it.
07:29:09 <J_Arcane> http://pasterack.org/pastes/10137
07:29:31 <shachaf> I wish I could configure Chromium to open links in Incognito mode.
07:29:39 <shachaf> That way I could just click them instead of copying and pasting.
07:31:48 -!- oerjan has quit (Quit: Nitey).
07:35:05 -!- shikhin has quit (Remote host closed the connection).
07:40:05 <J_Arcane> Ahhhh. I see now. Racket flips the arguments in foldl. Which is why it makes a clean list, and why the results come the way they do.
07:42:36 <J_Arcane> ie. Heresy (and Haskell) recur with something like (foldl fun (fun base (car lst)) (cdr lst)), I can get the Racket result by instead doing (foldl fun (fun (car lst) base) (cdr lst)).
07:49:04 <Sgeo> Or use for/fold?
07:49:13 <J_Arcane> I guess it's to make sure that folds make clean lists when working with cons.
07:49:20 <Sgeo> How often does foldl/foldr itself get passed to another function?
07:50:35 <Bicyclidine> depends, are you writing pointless haskell
07:51:01 <J_Arcane> Heh. Guy Steele has a talk about 'foldl and foldr considered slightly harmful'
07:51:21 <J_Arcane> And a teacher's post I was just reading flat out just said 'don't use foldl.'
07:51:22 <shachaf> "monoids considered better"
07:51:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
07:51:51 <J_Arcane> Instructor notes from this class: http://www.scs.stanford.edu/11au-cs240h/
07:52:06 <shachaf> Yes, foldl is almost never the right function to use.
07:52:27 <Sgeo> But how is foldr harmful?
07:52:51 <Sgeo> Although it sucks trying to translate foldr into a non-lazy language because then you need to figure out how to get it to terminate
07:52:51 <J_Arcane> Sgeo: Dunno, but Steel's talk is here: http://vimeo.com/6624203
07:53:21 <Sgeo> I guess foldr is a bit linear?
07:53:39 <J_Arcane> http://www.scs.stanford.edu/11au-cs240h/notes/par.html
07:54:09 <J_Arcane> I guess performance wise they can both be problematic in Haskell too?
08:05:40 <J_Arcane> Reading Racket's sources does make me understand why Haskellers love that type system ... so much ass covering.
08:09:15 <Bicyclidine> it's cool. just look at any haskell definition involving tuples.
08:12:44 <zzo38> I saw the new Smash Brothers game, and they didn't add Professor Oak and Imakuni? as playable characters.
08:23:09 <zzo38> "In the Victorian era (when the reigning monarch was Queen Victoria) The British Rule was widely used in contract bridge games throughout the British Empire. In certain parts of India, local bylaws enforced its usage, punishable by a fine." How and why did they enforce this?
08:45:18 -!- nooga has joined.
08:49:26 -!- nooga has quit (Ping timeout: 240 seconds).
08:57:56 -!- HashNode has joined.
08:58:14 -!- HashNode has left.
08:58:48 -!- scoofy has joined.
09:02:16 -!- Bicyclidine has quit (Ping timeout: 272 seconds).
09:04:29 -!- Dulnes has quit (Quit: Connection closed for inactivity).
09:15:23 <J_Arcane> Hah hah. Was looking at F# a minute ago, and just now looked at the channel topic. XD
09:27:50 -!- Patashu has joined.
09:39:39 <vanila> I tried the guy steele talk
09:39:43 <vanila> "Hey, Sandra Bullock LiedHer Fans Are In Shock. Her Huge Secret Is Finally Exposed!"
09:39:53 <vanila> but when I clicked it was about divina mcall
09:40:47 <vanila> Sandra Bullock is better/more interesting
09:41:11 <int-e> and what does that have to do with Guy Steele?
09:47:22 <vanila> its not valid scheme OR CL
09:51:49 <vanila> http://vimeo.com/6624203
09:56:55 -!- vanila has quit (Remote host closed the connection).
10:15:19 <J_Arcane> "Fun" conversation starter: have you ever lost a piece of code you were really proud of, and weren't able to rewrite it again?
10:19:13 <zzo38> I do not remember.
10:34:11 -!- nooga has joined.
10:38:55 -!- nooga has quit (Ping timeout: 264 seconds).
11:38:09 -!- nooga has joined.
11:38:22 <mroman> J_Arcane: The source code of Stlisp probably
11:38:35 <mroman> although I guess I could rewrite it. It's just a matter of time/effort.
11:38:48 <mroman> and the Stlang source code
11:39:22 <J_Arcane> When I was younger I wrote a really clever routine for haggling with a shopkeeper in an RPG that's still better than any such mechanic I've seen since. Then my brother powercycled the floppy drive with the disk still locked ...
11:39:56 <mroman> http://mroman.ch/cgi/cgitest.slisp?name=eso
11:40:03 <mroman> I still have the interpreter executable though
11:43:05 -!- Patashu has quit (Ping timeout: 250 seconds).
11:43:50 <zzo38> J_Arcane: Do you remember of details? How does it work?
11:49:54 <J_Arcane> zzo38: Dimly. The basic gist was that the shopkeeper had a target price range, and a mood score, and there were various threshholds where either an offer would be accepted or refused, or even that he would get offended and throw you out.
12:03:16 <zzo38> J_Arcane: Is that all?
12:04:42 <J_Arcane> zzo38: It's the basic idea, but it's still more than I've ever seen in a commercial game (there's probably some clever roguelike with a better one I've never heard of though, there usually is)
12:10:23 -!- sebbu has quit (Ping timeout: 250 seconds).
12:16:33 <zzo38> I mean how do these target price range, mood score, thresholds, offended, etc working?
12:19:06 <J_Arcane> Oh, the items all had standard prices, and used/sale price was computed as a randomized percentage of that, with min and max values relative to it and the shopkeeper's mood score.
12:19:41 <J_Arcane> Mood itself was I think randomized, and an ablative value almost like hit points: offend him enough and he'd tell you to piss off.
12:20:08 <J_Arcane> "Offending" basically meant asking too much or too little at the off.
12:20:33 <J_Arcane> So there was a strategy to it; you could work the shopkeeper down lower in steps than you could with a flat offer.
12:22:33 <elliott> I think some version of angband had something like that, maybe.
12:23:18 <elliott> that said, I'm not sure the shop interface should be a particularly trivial kind of combat :p
12:24:13 <elliott> (but I'm particularly prone to being annoyed by things like that)
12:25:15 <J_Arcane> It was semi-optional, you could always just accept the offer when selling, and it only applied to used purchases (new stuff was fixed price). Also, it was otherwise a pretty simple text game of 'kill stuff, level, loot', so in context it was a nice added feature.
12:26:03 <elliott> yeah, I just get annoyed by tradeoffs of "I'm doing worse than I could have been if I had the patience to play this subgame for the billionth time" easily :p
12:28:37 <J_Arcane> Certainly in something that wasn't essentially Recettear, it could be annoying. For me, I was always annoyed with games with 'barter systems' that weren't: Fallout's was like this, it wasn't really any kind of bartering because everything was fixed price and you were lucky if you could deviate even a single cap in your offer.
12:32:26 <elliott> I'm boring; I'm happy with shops-as-vending-machines.
13:10:31 -!- S1 has joined.
13:11:23 -!- sebbu has joined.
13:11:57 -!- sebbu has quit (Changing host).
13:11:57 -!- sebbu has joined.
13:18:50 <J_Arcane> elliott: It's definitely not a feature I'd want to have to use every time (this is actually probably why I got bored with Recettear) for sure.
13:51:10 -!- boily has joined.
13:59:00 <J_Arcane> Wow. ECMA BASIC doesn't even *have* mid$ and instr$.
14:06:55 -!- scoofy has quit (Ping timeout: 256 seconds).
14:07:47 -!- scoofy has joined.
14:08:45 <fizzie> QBasic doesn't have "INSTR$" either, the function's called "INSTR" (since the result is a number).
14:09:21 <boily> J_Arcanello! there's an ECMA sanctified version of BASIC?
14:30:14 <J_Arcane> boily: Yes. ECMA-116: http://www.ecma-international.org/publications/files/ECMA-ST-WITHDRAWN/ECMA-116,%201st%20edition,%20June%201986.pdf (warning, v. large file)
14:32:09 <J_Arcane> There was also ECMA-55 for "Minimal BASIC" as well.
14:32:23 <J_Arcane> I even found a modern compiler for ECMA-55.
14:36:55 <J_Arcane> http://buraphakit.sourceforge.net/BASIC.shtml
15:20:31 -!- ais523 has joined.
15:22:47 -!- HackEgo has quit (Ping timeout: 250 seconds).
15:28:29 -!- HackEgo has joined.
15:31:08 -!- boily has quit (Quit: TILED CHICKEN).
15:48:25 <b_jonas> If I normalize a string with the unicode CNF resp DNF normalizations, at most how many times longer can it become in UTF-16 code units?
15:50:34 -!- ais523 has quit (Remote host closed the connection).
15:50:40 -!- ais523 has joined.
15:53:27 <ais523> what's up with the topic/
15:55:52 -!- elliott has set topic: Visual Studio support channel | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
15:55:57 <elliott> someone made it inaccurate; fixed
15:56:15 <ais523> what incident prompted the topic change in the first place?
15:56:52 <elliott> someone came in looking for visual studio support
15:57:07 <elliott> I hypothesise that this will no longer happen now that the topic mentions visual studio
15:57:34 <ais523> it can't have been my "attempting to install Visual Studio lead to me needing to reformat the Windows and boot partition, then spend a few hours figuring out how to reinstall Ubuntu's bootloader after a boot partition reformat"
15:57:35 -!- drdanmaku has joined.
15:57:57 <ais523> elliott: wait, what was the old topic pre-mentioning-VS?
15:58:12 <elliott> something about being the black hole of programming madness
15:58:22 <elliott> ais523: somehow that actually sounds on-topic
15:58:49 <ais523> I am in favour of the topic being ontopic
15:59:59 <elliott> something can't be on itself, anyway
16:01:06 <FireFly> Isn't the topic on-topic by definition?
16:01:12 <ais523> yes, I considered it ontopic (both the current topic, and the /actual/ topic)
16:01:23 <ais523> and I think I mentioned it in here
16:01:38 <ais523> which reminds me, I have a mathematical problem
16:02:34 <ais523> I have partial information about the output of an LCRNG (i.e. there is a sequence of numbers defined as r[i+1] = (r[i] * m + s) % x); specifically, for some subset of i, I know whether or not r[i+1] is greater than r[i]
16:02:48 <ais523> and I want to go from this, to discovering the individual r[i] value
16:03:10 <ais523> I'm interested in both the situation where I know what m/s/x are, and the situation where I don't
16:05:17 <ais523> not really sure how to start, though
16:05:47 -!- Phantom_Hoover has joined.
16:11:13 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41114&oldid=40795 * GermanyBoy * (+431) /* summary */ added infobox
16:11:30 -!- tlewkow has joined.
16:39:04 -!- tlewkow has quit (Remote host closed the connection).
16:52:40 -!- callforjudgement has joined.
16:55:19 -!- callforjudgement has quit (Read error: Connection reset by peer).
16:55:22 -!- scarf has joined.
16:55:24 -!- scarf has quit (Changing host).
16:55:24 -!- scarf has joined.
16:55:37 -!- ais523 has quit (Disconnected by services).
16:55:38 -!- scarf has changed nick to ais523.
17:06:39 -!- MDream has changed nick to MDude.
17:20:14 -!- Bicyclidine has joined.
17:22:20 <newsham> `` echo . . - - "'" "'" "'" - - . . |rainwords
17:23:51 <newsham> ais523: if the state space is small (ie. 32 or 48 bits) you can always try solving all possible matches by brute force
17:24:11 <elliott> could SAT/SMT solvers help with that problem?
17:24:58 <ais523> elliott: possibly, but my experience with them isn't that good
17:28:20 <ais523> for this sort of problem
17:28:32 <ais523> newsham: I already do that with 32 bits, but I'm reaching a situation where I have a 64-bit internal state
17:28:35 <ais523> too large to bruteforce
17:28:43 <ais523> and yet this is miles from cryptosecure, it should be reversible
17:31:47 <newsham> yah, wouldnt surprise me at all, but i have no idea how to reverse it
17:32:34 <MDude> I guess the next obvious thing over just bruteforcing all of it would be to look for ways to eliminate possibilities and bruteforcing the rest.
17:34:30 <newsham> ais: any info about the initial seed? if they're using lcrng they might also be seeding with time or pid or somethign silly
17:34:43 <newsham> that might limit your search space greatly
17:34:59 <ais523> newsham: actually, my situation is that two RNGs are being seeded from the same seed
17:35:07 <ais523> one's pretty secure, the other is an LCRNG
17:35:16 <ais523> also the seeding method itself is pretty secure
17:35:32 <ais523> I want to figure out the sequence of the secure RNG by observing the output from the insecure one
17:35:45 <newsham> ahh.. so you want to solve the original seed
17:36:19 <ais523> and the way to do that is to find out the insecure RNG's current seed
17:36:29 <newsham> and they're using a 64-bit lcrng? thats pretty unusual.
17:36:32 <ais523> then run it backwards, trying progressive seeds as the secure RNG seed until one of them works
17:36:36 <ais523> and yes, it is pretty unusual
17:42:47 <newsham> have you looked at all pairs R2 > R1 * m + n for some small space to try to build an intuition?
17:43:05 <newsham> does it make bands in the state space?
17:43:52 <newsham> would be neat if you could quantify the bands and at each step cut your search space in half
17:44:25 <ais523> I've looked at some things like that
17:44:45 <ais523> the problem is that you get a bunch of repeating patterns, but the actual pattern you get depends on the size of R1
17:45:13 <ais523> obviously, for low R1, R2 is basically always higher
17:45:47 <newsham> maybe then if you can find large sequences of > > > > > it would isolate a small value of R
17:45:47 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
17:45:55 <newsham> then you can brute force that small value
17:46:43 <newsham> hmm that would only give you a few bits though.. probability of finding a very long seq of > > > > would be low
17:47:37 <ais523> newsham: the problem is, I don't have /all/ the > < representations
17:47:46 <ais523> if the values are similar, I'm unlikely to be able to tell which one's larger
17:47:57 <ais523> so long > > > > > sequences, even though they often exist, are unlikely to be in the source data
17:48:02 <ais523> sometimes I just get a ?
17:48:52 -!- Phantom_Hoover has joined.
18:02:41 -!- callforjudgement has joined.
18:03:42 -!- shikhin has joined.
18:03:48 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
18:04:03 <J_Arcane> Oh dear. I've reached the dreaded question: 0-indexed or 1-indexed.
18:06:23 -!- ais523 has quit (Ping timeout: 264 seconds).
18:06:32 -!- callforjudgement has changed nick to ais523.
18:10:06 <J_Arcane> Well, Djikstra wasn'texactly a BASIC fan ...
18:12:28 -!- tlewkow_ has joined.
18:13:55 <Bicyclidine> so ubuntu has a setting where trying to upgrade your release doesn't actually check for new releases, and you're not informed of this. awesome.
18:13:58 <newsham> maybe you can find some biases in the bits or R1 when R2 > R1 ?
18:15:35 <J_Arcane> https://www.cs.utexas.edu/users/EWD/transcriptions/EWD08xx/EWD831.html
18:17:54 <Bicyclidine> it's incredibly, incredibly anal, but pretty solid.
18:19:49 -!- sebbu2 has joined.
18:20:15 -!- nyuszika7h has quit (Read error: Connection reset by peer).
18:20:26 -!- sebbu2 has quit (Changing host).
18:20:26 -!- sebbu2 has joined.
18:21:32 -!- sebbu has quit (Ping timeout: 264 seconds).
18:21:45 -!- nyuszika7h_ has joined.
18:23:37 -!- nyuszika7h_ has changed nick to nyuszika7h.
18:23:56 <newsham> ais523: looks like there might be some bias in one of the high bits: http://www.thenewsh.com/~newsham/x/machine/bias.py
18:24:24 <ais523> newsham: when next(x) > x, it's likely that x is quite small
18:24:50 <ais523> my problem's more that I wonder if there's some mathematical way to get exact results
18:24:54 <ais523> by bruteforcing particular bytes
18:25:26 <elliott> you can get exact results with enough statistics
18:37:33 <J_Arcane> Hmm. Should calling out of index be an error or false? ie, calling (index 5 lst) where lst is only 3 entries long, etc.
18:39:43 <newsham> if you find runs of >>>>> it greatly increases the chance that the original high bit was a zero
18:40:19 <newsham> you could use that to prune your search space
18:40:40 -!- tlewkow_ has quit (Remote host closed the connection).
18:42:04 <newsham> for a 16-bit lcrng, there are no runs of 5 >'s starting with the high bit set.
18:42:48 <newsham> sorry, i should say "for the 16-bit lcrng i'm playing with" :)
18:47:53 <ais523> right, long runs would be unlikely
19:06:41 -!- S1 has quit (Quit: S1).
19:20:00 -!- Sprocklem has joined.
19:25:13 <mroman> !blsq 0 0 2047rn1024.+f:
19:25:13 <blsqbot> | {{5 1358} {4 1705} {4 618} {4 66} {3 1985} {3 1921} {3 1855} {3 1816} {3 1811} {3 1651} {3 1462} {3 1419} {3 1388} {3 1308} {3 1277} {3 1184} {3 1120} {3 1052} {3 1046} {3 1003} {3 865} {3 856} {3 787} {3 630} {3 322} {3 221} {3 205} {3 54} {3 6} {2 2041}
19:25:40 <Bicyclidine> in the year 1052 columbus sailed the ocean blue
19:25:46 <mroman> !blsq 0 0 2047rn1024.+2047rz//
19:25:47 <blsqbot> | ERROR: Unknown command: (//)!
19:25:47 <blsqbot> | {0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 7
19:25:50 <mroman> !blsq 0 0 2047rn1024.+2047rz\\
19:25:50 <blsqbot> | Ain't nobody got time fo' dat!
19:25:53 <mroman> !blsq 0 0 2047rn1024.+2047rz\\
19:25:54 <blsqbot> | Ain't nobody got time fo' dat!
19:26:07 <mroman> !blsq 0 0 1023rn1024.+1023rz\\
19:26:08 <blsqbot> | {733 22 135 636 444 750 382 614 438 779 961 434 156 509 779 302 168 701 763 623 856 982 856 335 601 816 205 822 251 322 156 225 516 618 949 1004 535 522 678 446 623 835 6 636 835 564 630 38 800 133 900 438 160 428 822 761 20 64 151 831 435 1017 247 520 9 4
19:26:12 <mroman> !blsq 0 0 1023rn1024.+1023rz\\L[
19:30:15 -!- ais523 has quit (Read error: Connection reset by peer).
19:30:24 -!- ais523 has joined.
19:30:24 -!- ais523 has quit (Changing host).
19:30:24 -!- ais523 has joined.
19:32:10 -!- callforjudgement has joined.
19:36:30 -!- ais523 has quit (Ping timeout: 265 seconds).
19:47:50 -!- callforjudgement has quit (Read error: Connection reset by peer).
19:48:06 -!- callforjudgement has joined.
19:49:55 -!- Patashu has joined.
19:54:57 -!- Sprocklem has quit (Ping timeout: 245 seconds).
20:26:46 -!- Patashu has quit (Ping timeout: 265 seconds).
20:32:44 <HackEgo> [wiki] [[Talk:3var]] http://esolangs.org/w/index.php?diff=41115&oldid=39178 * Olls * (+197) /* Interpreter? */
20:35:42 -!- Bicyclidine has quit (Quit: restart).
20:38:43 -!- callforjudgement has changed nick to ais523.
20:38:47 -!- Bicyclidine has joined.
20:40:18 -!- Bicyclidine has quit (Client Quit).
20:43:34 -!- ais523 has quit (Read error: Connection reset by peer).
20:43:35 -!- dts has quit (Ping timeout: 244 seconds).
20:43:45 -!- ais523 has joined.
20:44:50 -!- Bicyclidine has joined.
20:45:06 -!- Bicyclidine has quit (Client Quit).
20:45:13 -!- Bicyclidine has joined.
20:52:09 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
20:53:37 -!- Bicyclidine has quit (Quit: trying yet more else).
20:53:59 -!- AnotherTest has joined.
20:54:45 -!- Bicyclidine has joined.
21:09:47 -!- S1 has joined.
21:11:37 -!- TodPunk has quit (Ping timeout: 245 seconds).
21:13:48 -!- TodPunk has joined.
21:35:19 -!- ais523 has quit (Read error: Connection reset by peer).
21:35:22 -!- callforjudgement has joined.
21:35:24 -!- callforjudgement has quit (Changing host).
21:35:24 -!- callforjudgement has joined.
21:40:44 -!- callforjudgement has quit (Read error: Connection reset by peer).
21:40:52 -!- callforjudgement has joined.
21:53:52 -!- Dulnes has joined.
21:54:13 <Dulnes> Why do i keep disconnecting
21:54:50 <zzo38> Would you like it if Professor Oak can become a playable character in Smash Brothers game?
21:55:05 <zzo38> Dulnes: I don't know? Possibly a problem with internet sometimes I have a problem too a bit
21:55:08 <myname> depends on what he could do
21:55:23 <Dulnes> Throw pokeballs like a gattling gun
21:55:35 <Taneb> I could see him as an assist trophy
21:55:47 <zzo38> callforjudgement: Yes I know and I managed to vs him too
21:56:12 -!- Phantom_Hoover has joined.
21:56:19 <Dulnes> I think you can use the program
21:56:54 <zzo38> myname: I would think, you can sometimes throw a pokeball after a few seconds and that in addition, if you are using a separate display (such as Wii U gamepad) that it will tell you what pokemon is found in each pokeball on the screen too, and everyone else does not see that information until the pokeball is opened!
21:57:25 <zzo38> Dulnes: What program?
21:57:52 <Dulnes> You could use the battle data
21:58:10 <Dulnes> If you forcably seperated it from the cartridge
21:58:13 <zzo38> O, OK that's what you meant.
21:58:59 <zzo38> My brother has the newest Smash Brothers game on Wii U and Nintendo 3DS
21:59:07 <zzo38> So, I played this game too
21:59:32 <Dulnes> Because new legend of zelda game 2015
21:59:33 <Taneb> I thought that didn't come out until Friday?
21:59:47 <Dulnes> Came out last week i think
21:59:55 <Taneb> Ah, maybe Europe is later
21:59:57 <zzo38> One thing you still cannot do though even in the newest one is to set the self-destruct to -1.5 instead of only 0 and -1 and -2
22:00:02 <Taneb> I'm gonna get the 3DS version soon
22:00:16 <Taneb> Dulnes, translation issues
22:00:22 <zzo38> Both me and my brother want to be able to set self-destruct points to -1.5
22:00:30 <Taneb> zzo38, can you adjust all the other scores to make it effectively the same
22:00:31 <Dulnes> Since it goes Japan - China - Europe - Americas
22:00:53 <Dulnes> Or < that way on a map
22:01:05 <zzo38> Taneb: You could manually calculate the score I suppose if you like to; it doesn't allow you to otherwise adjust it.
22:01:16 <zzo38> However there is no function to disable sudden-death mode.
22:01:46 <Taneb> Dulnes, maps aren't really relevant to this sort of thing any more, not for a few decades
22:01:55 <pikhq_> I doubt it's translation issues, at least entirely...
22:01:56 <zzo38> Again a function both of us wanted to have
22:02:16 <pikhq_> I mean, if so why make Australia take until the 29th?
22:02:21 <pikhq_> Or Japan until the 6th?
22:02:22 <Taneb> pikhq_, that's a point
22:02:30 <pikhq_> (yes, Japan is the *last* country getting it)
22:02:54 -!- nortti has changed nick to lawspeaker.
22:03:01 -!- lawspeaker has changed nick to nortti.
22:03:18 <Dulnes> Ive been wondering why is Australia so hot
22:03:28 <Dulnes> If its near the south pole
22:03:44 <Taneb> Dulnes, it's closer to the equator than the UK is
22:03:51 <Taneb> By quite some measure
22:04:01 <elliott> try looking at a globe rather than a map :p
22:04:20 <pikhq_> IIRC Northern Australia is literally in the tropics.
22:04:33 <elliott> remember to by a new cpu core while you're at it
22:04:38 <zzo38> One thing they could have done but don't is to implement custom omega stages, which involves selecting music, graphics, and whether or not you can go underneath the platform. It isn't particularly important though.
22:04:39 <Bicyclidine> to be fair, nobody lives in northern australia
22:04:51 <Taneb> It's about as close to the equator as India is
22:05:35 <pikhq_> Ah, yep. And nearly all of the country is in the subtropics.
22:06:03 <Dulnes> You and your giant galloping wolf spiders
22:06:35 <Dulnes> Doesnt the worlds deadliest snake live there?
22:06:38 <pikhq_> So yeah, it's pretty much entirely in the latitudes where simple sun exposure is likely to make things at least moderately hot.
22:07:31 <pikhq_> Also, almost all of the continent is a desert, so there's that too.
22:07:59 <Dulnes> i believe the emu's won
22:08:43 <pikhq_> Understandably the population's concentrated around the not-desert bits.
22:08:48 <zzo38> There also is not the mode to use the time limit corresponding to the stage which is selected.
22:09:10 <zzo38> (This would only be applicable for some stages though.)
22:09:56 <Dulnes> pikhq_: why did they have a war?
22:11:14 <Dulnes> Anyways i actually do have food in my house and this time its not coffee based
22:11:55 <elliott> `addquote <Dulnes> Anyways i actually do have food in my house and this time its not coffee based
22:11:57 <HackEgo> 1223) <Dulnes> Anyways i actually do have food in my house and this time its not coffee based
22:20:14 -!- AnotherTest has quit (Remote host closed the connection).
22:20:26 <Sgeo> If I start eating a lot of sugary snacks, but I still eat the other foods I was eating before (so it's not taking the place of anything else), and I'm not close to being overweight, is that still bad?
22:21:53 <Phantom_Hoover> i still don't understand why you come here for this sort of advice
22:22:54 <Sgeo> This channel was just talking about food >.>
22:23:13 -!- tlewkow has joined.
22:24:48 <myname> food is the thing i like to eat the most
22:26:54 <Taneb> myname, I prefer to eat business cards
22:27:00 <Taneb> But I find them very filling
22:28:53 <Dulnes> We werent talking about food
22:29:06 <Dulnes> We were talking about how everything is edible
22:30:46 <Sgeo> Apparently the notion of getting diabetes type 2 from too much sugar is a myth?
22:33:59 <elliott> do I dare ask what you're planning
22:35:19 <Sgeo> I bought a box of boxes of fruit by the foot recently
22:35:30 <Sgeo> They taste so good. I've been eating about a box a day
22:53:16 -!- oerjan has joined.
22:54:34 <zzo38> Do you know if any SQL-based RPG engines exist, or do I have to write one?
22:55:05 <oerjan> i sense elliott didn't like my dark humor
22:59:41 <oerjan> hm i was going to say that both solutions to http://golf.shinh.org/p.rb?Dominosa+Small were too large to be solving the problem properly, but i think they're actually too large to be using compression.
23:02:40 -!- shikhout has joined.
23:06:31 -!- shikhin has quit (Ping timeout: 272 seconds).
23:07:32 <Sgeo> What did I miss about an incident that callforjudgement missed?
23:08:40 -!- ski has quit (Ping timeout: 256 seconds).
23:09:09 <callforjudgement> selecting randomly between three fixed strings isn't hard in most languages
23:09:13 <oerjan> i know, i'm writing a trivial one
23:15:26 <oerjan> alas i'm too lazy to write a non-cheating solution
23:15:30 <Phantom_Hoover> <Sgeo> Apparently the notion of getting diabetes type 2 from too much sugar is a myth?
23:15:40 <Phantom_Hoover> the common notion is getting it from obesity, not sugar per se
23:17:04 <oerjan> wtf are the neighbors making noise after midnight
23:17:46 <oerjan> (just loud talking, but still)
23:17:58 <Taneb> Are they students?
23:18:17 <Taneb> And if you're awake after midnight, why shouldn't they be?
23:18:25 <Taneb> But if they're being very noisy, :(
23:18:29 <oerjan> i'm _awake_. i'm not noisy.
23:18:39 -!- AndoDaan has joined.
23:21:16 <Sgeo> Is it possible to become obese without noticing?
23:21:31 <Sgeo> Looking thin but being medically obese?
23:21:33 <oerjan> if anyone can manage it...
23:22:05 -!- zzo38 has quit (Remote host closed the connection).
23:23:12 <FreeFull> Sgeo: Maybe if you invent a form of fat that contains neutronium
23:27:56 <elliott> "obesity" isn't a monolithic thing.
23:30:40 <oerjan> sure it is, if you look like a monolith you're definitely obese
23:35:45 -!- scarf has joined.
23:36:07 -!- callforjudgement has quit (Read error: Connection reset by peer).
23:37:39 <oerjan> there appears to be a general _custom_ in norway about night silence after 11 pm before ordinary weekdays. but there's no actual written law that you can point to.
23:38:42 <oerjan> and our house rules have no clock times in them
23:40:17 <oerjan> my long parenthesized comment on anagolf weirds out the layout :(
23:44:24 -!- tlewkow has quit (Remote host closed the connection).
23:48:28 -!- tlewkow has joined.
23:55:21 -!- ski has joined.
23:55:39 -!- vanila has joined.
00:10:52 <Dulnes> Isnt there a holiday in Norway where you can slam doors
00:11:34 <Dulnes> Also wasnt there a law that anyone found crossing the icebridge to norway to Sweden you can beat with a stick
00:11:56 -!- scarf has quit (Read error: Connection reset by peer).
00:11:57 <Dulnes> Or viceversa idk the law was made when they thought someone was going to invade
00:12:09 -!- scarf has joined.
00:14:32 <Dulnes> Apparently there was one seeing as this law was made in mideavil times
00:15:51 <Dulnes> Back in my day you could beat the shit out of sweds for crossing our border is apparently what your grandparents would say idfk Europe is ecentric
00:18:03 <Phantom_Hoover> hey man, any law that lets you beat the shit out of swedes is fine by me
00:19:17 -!- S1 has quit (Quit: S1).
00:19:49 <oerjan> Dulnes: i dunno but you can still get a fine for crossing the border on a road that isn't an official crossing
00:21:23 <oerjan> Dulnes: icebridge sounds like something you'd more have between denmark and sweden
00:21:45 <Dulnes> I think it was the swedish who have the weird door slamming holiday
00:21:48 <oerjan> since they don't actually have a land border after the swedes nicked scania
00:22:27 <Dulnes> Apparently in Sweden you can steal a childs candle and eat it front of them
00:22:59 <oerjan> also it is/was illegal for norwegians to photograph across the border to russia
00:23:29 <oerjan> (i think it was to avoid provocation?)
00:23:37 <Dulnes> Even if they are still in Norway!
00:23:56 <oerjan> yes. it's probably legal if you're in russia :P
00:24:08 <shachaf> is it possible if you're in russia
00:24:18 <oerjan> (but getting into russia legally may be a bit of bureaucracy)
00:24:35 <Dulnes> When was the last time norway was in a war
00:24:48 <oerjan> shachaf: i don't think the russians censor that much nowadays
00:25:05 <oerjan> Dulnes: afghanistan, a year or so ago?
00:25:17 <shachaf> oerjan: it seems difficult to photograph across the border to russia when you're in russia
00:25:23 <oerjan> if you mean on our territory, world war II
00:26:03 <oerjan> shachaf: that's true. i'm not sure how curvy the border river (pasvikelva) is.
00:26:04 <Dulnes> Why dost the norwegians involve themselves in Afghanistan.
00:26:17 <oerjan> Dulnes: NATO, and 9/11
00:26:27 <shachaf> what if you photograph a norwegian mirror
00:26:45 <Dulnes> Was the norways attacked on 9/11
00:27:02 -!- copumpkin has joined.
00:27:13 <oerjan> Dulnes: 9/11 was declared an attack on the usa under the NATO treaty, which makes all members obligated to respond.
00:27:41 <oerjan> it's the only time that article of the treaty has been evoked, i think.
00:28:06 <Dulnes> What if you point a mirror at Russia at the border and then take a picture of the reflection of Russia?
00:28:42 <oerjan> Dulnes: probably counts. technical workarounds tend not to be looked at lightly by law.
00:28:52 <FireFly> <Dulnes> I think it was the swedish who have the weird door slamming holiday what?
00:29:42 <Dulnes> Apparently last time i checked theres a holiday in which large portions of Sweden begin slamming their doors
00:30:01 <Dulnes> Or just look up door slamming holiday
00:30:09 <FireFly> I've never heard of and/or experienced anything like that
00:30:10 <Dulnes> It may not have been Sweden
00:32:25 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 6776 : Integer -> Integer
00:34:12 * oerjan finds nothing relevant when googling but wtf is http://whitehotmagazine.com/articles/festival-curated-by-dominic-eichler/482
00:34:41 <oerjan> i think it's an art exhibition named Door Slamming Festival
00:35:13 <FireFly> Also the crossing-the-ice thing is supposedly a really old danish law
00:35:20 <Dulnes> Thats an awful name and ive been thoroughly mistaken this whole time
00:35:50 <Dulnes> Mmm i guess i got it wrong
00:36:13 <Dulnes> Im always confused on countrys.
00:36:22 <oerjan> Lademoen Kunstnerverksteder, that's here in Trondheim
00:36:32 <oerjan> maybe we'll get some of the Door Slamming here
00:36:54 <oerjan> oh wait the article is from 2007
00:37:02 <oerjan> so she probably left already
00:37:35 <Dulnes> Well if you get enough votes on a thing and pass it up through your government
00:37:40 <oerjan> hm or maybe that was the journalist
00:37:53 <Dulnes> I guess you can make a slamming door day
00:38:07 <Dulnes> Its probably different in Norway
00:38:20 <oerjan> Dulnes: votes in parliament i take, norwegians are not big on public-initiated referendums
00:38:44 <oerjan> we've had 6 referendums overall since independence in 1905
00:39:20 <FireFly> I wonder how many we've had.. I think at least four
00:39:32 <oerjan> (2 were _about_ the independence and monarchy, 2 about prohibition (beginning _and_ end), 2 about EEC/EU (refusing to join))
00:40:05 <FireFly> Apparently six national referendums here as well
00:40:50 <oerjan> oh right there have been some local ones.
00:41:36 <Dulnes> Well i was born in ireland and lived there for most my life till i moved to America. But until that idk about Ireland
00:41:40 <oerjan> the most recent one being Oslo's referendum on whether to apply for olympic winter games. (un)fortunately, the rest of the nation refused to go along.
00:43:10 <Dulnes> I think thats cuz of all the threats
00:47:04 -!- scarf has changed nick to ais523.
00:48:35 <oerjan> no, it's because it costs a lot, and because the sotchi games in russia made it completely obvious to everyone what a corrupt cesspool the olympics are
00:50:33 <oerjan> (so much so that even the oslo-ans don't want it any more)
00:52:14 <oerjan> time to dissect some golfing frogs
00:52:59 <Sgeo> Can someone help me pirate Visual Studio Professional? I heard someone was giving it away?
00:53:19 <oerjan> help, Sgeo is believing the topic
00:53:42 -!- ais523 has quit (Ping timeout: 245 seconds).
01:01:31 <Sgeo> (To any hypothetical employers stalking me and managing to find this chat log: I am not actually looking to pirate Visual Studio)
01:01:49 -!- nooga has quit (Ping timeout: 255 seconds).
01:12:38 -!- contrapumpkin has joined.
01:14:44 <Taneb> I kind of want to travel over Easter
01:15:16 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:15:52 -!- copumpkin has quit (Ping timeout: 240 seconds).
01:17:58 <Dulnes> Mmm celebrating jesus's birthday with present and then his death with chocolate
01:18:35 <oerjan> (henkma's shows wouldn't improve it)
01:19:49 <oerjan> oh and the fixity is wrong.
01:20:13 <oerjan> Dulnes: technically it's his resurrection not death hth
01:22:11 <Taneb> oerjan, what's Trondheim like in march?
01:22:54 <oerjan> snow, rain, sleet or spring.
01:23:16 <Taneb> So, like the UK but colder?
01:23:54 -!- tlewkow has quit (Remote host closed the connection).
01:24:02 <Taneb> Hmm, where can I go for cheap that's easy to get to
01:26:00 <Taneb> But, what about Yorkshire
01:26:17 <Taneb> Benefits of Yorkshire: I have a convenient place to stay, right in the middle
01:26:44 <Taneb> Disadvantages: It's dubious whether this counts as travelling
01:27:18 <oerjan> what about northumberland
01:28:10 <oerjan> you could go to london and visit fizzie
01:28:55 -!- tlewkow has joined.
01:29:20 <Taneb> fizzie, what are you doing in London?
01:29:30 <Taneb> oerjan, that means going to London, something I'd like to avoid as much as possible
01:30:41 -!- contrapumpkin has changed nick to copumpkin.
01:31:00 <Taneb> Hmm, I could go to Birmingham and visit ais523
01:31:16 <oerjan> you mean play hide and seek
01:32:46 <Taneb> I could search the country for Phantom_Hoover
01:33:54 -!- tlewkow has quit (Remote host closed the connection).
01:35:31 <Sgeo> Take the average of the locations of all Brainfuck derivatives, then go to the opposite point.
01:35:50 <oerjan> i don't think we have coördinates for those
01:38:39 -!- contrapumpkin has joined.
01:39:09 -!- copumpkin has quit (Ping timeout: 272 seconds).
01:42:20 -!- contrapumpkin has changed nick to copumpkin.
01:49:07 <oerjan> <elliott> I'm boring; I'm happy with shops-as-vending-machines. <-- vending machines that haggle, now there's a thought.
02:03:15 -!- boily has joined.
02:04:32 -!- shikhout has quit (Ping timeout: 245 seconds).
02:04:49 <Taneb> I say hmm a lot, hmm
02:08:21 <int-e> oerjan: So henkma didn't find the "easy" strength reduction trick, but was better at math.
02:09:21 <int-e> oerjan: his div x p is one character shorter than my 0^max 0y
02:12:34 -!- AndoDaan has quit (Quit: Sleep? What is sleep?).
02:13:52 <oerjan> i recall having the div x 9 idea at some point, but i never escaped the need to precalculate indices :(
02:14:25 <int-e> our 136 byte solutions are eerily similar
02:15:07 <oerjan> yeah i recall your comment about also not being able to remove a '9'
02:15:51 <int-e> http://sprunge.us/VGOb <-- see third line from end here
02:19:47 <oerjan> yeah only trivial differences :P
02:24:43 <int-e> ok. lucky me, I'd have thought that with henkma's experience that final optimization would almost be second nature.
02:25:36 <Dulnes> Let me take you to a luxury furniture warehouse and we can just touch things all day
02:25:46 <int-e> (though it is a bit hard to imagine that the 9 character long "map pred " could pay off)
02:32:23 -!- copumpkin has quit (Ping timeout: 240 seconds).
02:33:40 <int-e> oerjan: still no progress on A057755?
02:34:41 <Dulnes> int-e: how was your coffee
02:40:18 <boily> how can one threaten somebody else with coffee?
02:40:24 -!- tlewkow_ has joined.
02:41:54 <Dulnes> Can inflict 2nd degree burns
02:42:09 <Dulnes> On the eyes 3rd degree
02:42:33 <Dulnes> Also i wasnt threatening im just saying
02:42:35 -!- AndoDaan has joined.
02:42:45 <Dulnes> He will soon enjoy a cup of coffee
02:43:57 <boily> a cup... of Folgers! made... yesterday! and Reheated!!! DUN DUN DUN!!!
02:45:03 <oerjan> should i be happy i don't know what folgers is
02:45:07 <shachaf> i,i "Don't you have any bags that aren't dun-colored?"
02:45:14 <int-e> I can only assume that Folgers is a particularly cheap and atrocious brand of coffee.
02:45:19 <oerjan> shachaf: a gnommon question
02:45:39 <shachaf> oerjan: that's a stretch hth
02:45:46 <oerjan> wait, that pun... yeah right
02:45:57 <pikhq_> int-e: Just a generic brand of coffee. Not particularly atrocious, but not particularly good.
02:46:06 <oerjan> somehow my brain didn't notice i wasn't actually using a word starting with n
02:46:55 <shachaf> i actually thought the copunchline in the first panel of that comic was much better
02:47:04 <shachaf> not that i'm much for punchlines anyway
02:47:13 <Dulnes> On the topic of antimatter
02:47:48 <Dulnes> How long was the antimatter particle in existence at CERN before poofing
02:48:12 <int-e> "that comic" doesn't help.
02:48:15 <Dulnes> I swear to god they are getting really close to burning the planet
02:48:16 <oerjan> um depends which kind of antimatter
02:48:23 <shachaf> int-e: http://www.giantitp.com/comics/oots0968.html
02:48:45 <oerjan> Dulnes: if it was a stable particle, it'd exist until it collided with ordinary matter.
02:48:45 <Dulnes> The matter that cancels matter
02:49:11 <oerjan> Dulnes: not my question
02:49:15 <Dulnes> But wouldnt that make a big boom
02:49:28 <oerjan> Dulnes: no. small particles, small booms.
02:51:22 <oerjan> if it was something ridiculously unstable like an anti-meson with bottom anti-quarks, it would turn into something else before it had time to collide. although that something else would still be at least partly antimattery.
02:51:36 <int-e> oerjan: Ah I should've known. Wall-of-text, requires-hours-to-read-a-single-page, oots.
02:51:52 <oerjan> int-e: wow you read even slower than me?
02:52:06 <shachaf> int-e: it's mostly a wall of graphics hth
02:53:18 <int-e> oerjan: I gave up on that comic around 726 (that's my last bookmark)
02:53:38 <int-e> shachaf: the graphics are not the main appeal of the comic though, honestly.
02:53:58 <int-e> oerjan: I may have exaggerated ever so slightly.
02:54:08 <oerjan> the graphics are gradually improving, though
02:54:17 <shachaf> the main appeal is text, and there isn't that much of it compared to the graphics
02:54:22 <shachaf> my sister says she hates the new graphics
02:54:30 <shachaf> she can hardly bear to look at the comic now, she says
02:57:14 <int-e> shachaf: One last thing I'll say, the "wall of text" is in comparison to other web comics, of course. Those with a lot of text (say, Freefall) usually have the good grace to limit themselves to three panels ;-)
03:00:02 <Taneb> I suspect my implementation of the Sieve of Atkin is incorrect
03:00:15 <Taneb> It's much slower than the sieve of eratosthenes
03:00:56 <shachaf> and much higher in carbohydrates?
03:01:39 <Taneb> 87% of which sugars
03:03:50 -!- boily has quit (Quit: PASTORAL CHICKEN).
03:04:20 <Taneb> I should go to bed, in theory I have a lecture in the morning
03:11:35 -!- adu has joined.
03:13:02 <int-e> who cares, unless you're the lecturer, and AFAIR you're not.
03:14:01 <Taneb> int-e, I haven't been to this lecture in weeks
03:14:06 <Taneb> Monday mornings do not agree with me
03:14:37 <int-e> ok then, perhaps it's a good time to attend and check whether you still understand any of it
03:15:47 <int-e> (unless there's a script and the lecturer is just reading a script. I remember a lecture like that, or rather I remember skipping it almost completely.)
03:19:33 <oerjan> <Dulnes> Doesnt the worlds deadliest snake live there? <-- the world's nine deadliest snakes, if i'm to believe what i recall from irregular webcomic!
03:20:10 -!- tlewkow_ has quit (Remote host closed the connection).
03:24:09 -!- tlewkow_ has joined.
03:26:35 <adu> it's evening for me
03:26:55 <adu> I'm on the east coast (of the US)
03:28:53 <Taneb> int-e, the lectures are recorded, but I haven't watched them
03:29:08 <Dulnes> How do you unroot a phone
03:30:53 <adu> Dulnes: you could just do a factory reset
03:31:01 <int-e> . o O ( First you'd have to plant it. )
03:41:22 <J_Arcane> I really don't want to go to school today.
03:41:28 <J_Arcane> And if there's anymore of this weird cult bulls*** going on today I'm not sure I'll be able to stop myself just walking out this time.
03:44:00 <oerjan> just as long as you're not today's sacrifice
03:47:56 <J_Arcane> Our latest section has been kind of the last straw in a course that's already a little too 'Happiness is Mandatory'. The whole dialogue and course material is literally all about how wonderful the school is, complete with trademarked call outs to the brand name in the text.
03:49:58 <J_Arcane> Last week ended with us making bloody advertisements for the school as a class exercise, and last night's homework was full of weird questions like "How can we save the environment" which it was kind of implied we should be answering in the first person.
03:50:43 <Bicyclidine> http://stackoverflow.com/questions/12734161/how-to-use-boehm-garbage-collector-in-ubuntu-12-04 what the dick is this
03:51:43 <Bicyclidine> hm. weird option. i wonder if you actually need that
03:52:04 <Bicyclidine> J_Arcane: what, do they take attendance? which i have forgotten how to spell
03:53:16 <J_Arcane> Bicyclidine: the course is paid for by the TE-office. If I'm absent without leave they can dock my unemployment pay, and if I'm gone more than 4 days they can cut me completely off.
03:53:27 <J_Arcane> Seriously considering transferring to another school.
03:54:20 <adu> J_Arcane: just pretend you have Ebola, then the Army will force you to stay home :)
03:55:15 <J_Arcane> A weird as hell one, apparently founded on the ideas of a Russian psychologist old enough to have been employed by the Soviet Union ...
03:56:16 <adu> Bicyclidine: sounds like a GCC issue
03:57:06 <J_Arcane> I misremembered, he's Bulgarian: http://en.wikipedia.org/wiki/Suggestopedia
03:57:18 <Bicyclidine> adu: yeah, what --as-needed does is it doesn't actually link things if there's no symbols in them that would define something already seen as undefined. so if i start my command line with -lgc, when the linker hasn't seen shit, well
03:57:22 <J_Arcane> Suggestopedia (US English) or Suggestopædia (UK English) is a teaching method developed by the Bulgarian psychotherapist Georgi Lozanov. It is used mostly to learn foreign languages. Suggestopedia has been called a pseudoscience.[1] It strongly depends on the trust that students develop towards the method by simply believing that it works.
03:57:58 <Bicyclidine> i mean teachers believe all kinds of nonsense, but that's pretty over the top.
03:58:18 <Bicyclidine> "Lozanov never admitted that Suggestopedia can be compared to a placebo. He argues, however, that placebos are indeed effective." mmhm
03:58:55 <adu> I personally like to the Wikipedia learning method
03:59:13 <adu> just start clicking and learning until you see a legit page defaced with a penis
04:01:50 <J_Arcane> Bicyclidine: Kinda explains the forced positivity atmosphere. Easiest way to get people to believe something is just to keep bombarding them with it again and again, especially if you can make them repeat along with you...
04:02:15 <J_Arcane> I can actually hear "ÄLÄ OLE PESSIMISTI!" in my head already ...
04:02:23 <Bicyclidine> i hope you're not paying much for tuition.
04:02:50 <J_Arcane> It's free. I'm actually being paid to go.
04:29:05 <J_Arcane> I think it's most telling as to how great their 'method' is that while I have learned, roughly and not without difficulty, to *speak* a considerable amount of Finnish in what is in fairness a short time, I still barely understand a word of it.
04:31:39 -!- MDude has changed nick to MDream.
04:32:07 <Sgeo> Maybe I should look for nonperishable healthy snacks
04:33:43 <vanila> doesnt' that mean you cant eat it
04:34:15 <Sgeo> I thought it meant doesn't go bad
04:34:28 <Sgeo> Either that or
04:34:38 -!- Sgeo has changed nick to Woosh2.
04:34:47 -!- Woosh2 has changed nick to Sgeo.
05:01:03 <HackEgo> [wiki] [[Special:Log/newusers]] create * Orenwatson * New user account
05:27:37 -!- bb010g has quit (Quit: Connection closed for inactivity).
05:29:06 <int-e> oerjan: I have a cheating 166 for Dominosa
05:29:59 <oerjan> good, i wasn't trying very hard
05:34:05 <int-e> oh, indeed yochi2's solution is ridiculously long
05:35:16 <oerjan> i would be surprised if you need that much for a non-cheating solution
05:48:16 -!- copumpkin has joined.
05:49:29 -!- paul2520 has quit (Quit: WeeChat 1.0).
05:49:47 -!- paul2520 has joined.
05:49:48 -!- paul2520 has quit (Changing host).
05:49:48 -!- paul2520 has joined.
06:12:30 <HackEgo> [wiki] [[Scrip7]] N http://esolangs.org/w/index.php?oldid=41116 * Orenwatson * (+3040) Created article for my language
06:13:01 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41117&oldid=41116 * Orenwatson * (+5)
06:15:03 <fizzie> Taneb: I'm not doing anything in London yet, but I'll be working there starting from next year.
06:17:41 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41118&oldid=41117 * Orenwatson * (+240)
06:18:27 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41119&oldid=41118 * Orenwatson * (+23)
06:20:28 -!- tlewkow_ has quit (Remote host closed the connection).
06:21:36 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=41120&oldid=41000 * Orenwatson * (+13) added scrip7 to list
06:24:28 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41121&oldid=41119 * Orenwatson * (+0) corrected character print statement
06:49:27 <oerjan> i think i may have found henkma's trick, since it's still a slow one
06:50:10 -!- adu has quit (Quit: adu).
06:50:48 <oerjan> fizzie: your pointing out all whitespace was ignored at the end was a major clue
06:52:56 <oerjan> plus a bit of inspiration from henkma's leapfrog
07:04:42 -!- ZombieAlive has quit (Remote host closed the connection).
07:19:00 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41122&oldid=41121 * Orenwatson * (+131) added link to interpreter program.
07:30:46 -!- Patashu has joined.
07:34:37 -!- Patashu_ has joined.
07:34:37 -!- Patashu has quit (Disconnected by services).
07:48:19 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41123&oldid=41122 * Orenwatson * (+53) added hello world example
07:48:57 -!- oerjan has quit (Quit: leaving).
07:54:30 -!- Dulnes has quit (Quit: Connection closed for inactivity).
07:55:41 -!- ZombieAlive has joined.
08:20:06 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41124&oldid=41123 * Orenwatson * (+285) added more information
08:31:12 <int-e> @tell oerjan my fast and my slow ones have the same length, hth
08:38:11 <int-e> (I hope that prevents oerjan from going on a wild goose chase for a 52 character solution that may not even exist)
08:48:57 -!- AndoDaan has quit (Ping timeout: 256 seconds).
09:03:38 <vanila> http://js1k.com/2014-dragons/details/1951
09:12:04 <fizzie> That kind of reminds me of that one Android thing (though it wasn't size-crunched at all), http://www.pouet.net/prod.php?which=61640
09:17:01 <J_Arcane> https://github.com/mame/quine-relay
09:17:10 <vanila> regex decompression isinteresting
09:20:06 <lifthrasiir> oh, btw the code itself is quite optimized
09:20:42 <lifthrasiir> so it's [replacement][sep][noncompressed1][sep][noncompressed2]... into [noncompressed1][replacement][noncompressed2][replacement]...
09:26:26 <vanila> hello world hello me hello you hello all
09:26:30 <vanila> _='h~world}me}you}all~ello } h~';for(i in g='}~')with(_.split(g[i]))_=join(pop());eval(_)
09:30:25 <vanila> How would I write a compressor for this? Is greedily the best way?
09:30:54 <Sgeo> help what is sleep
09:31:19 <vanila> Sgeo, ive never seen one
09:31:26 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:35:42 -!- AndoDaan has joined.
09:41:24 -!- Patashu has joined.
09:42:47 -!- Patashu_ has quit (Ping timeout: 240 seconds).
09:46:45 -!- AndoDaan has quit (Ping timeout: 256 seconds).
09:55:36 -!- FreeFull has quit (Ping timeout: 264 seconds).
09:56:37 -!- Phantom_Hoover has joined.
10:46:54 -!- nooga has joined.
10:47:19 -!- FreeFull has joined.
10:52:36 -!- nooga_ has joined.
10:52:37 -!- nooga has quit (Read error: Connection reset by peer).
11:12:07 -!- nooga_ has quit (Ping timeout: 240 seconds).
11:14:57 -!- nooga has joined.
11:19:12 -!- boily has joined.
11:41:23 -!- olls has joined.
11:43:22 -!- nooga has quit (Ping timeout: 272 seconds).
11:49:54 -!- olls has quit (Ping timeout: 255 seconds).
11:56:39 -!- Patashu has quit (Ping timeout: 255 seconds).
12:16:54 -!- vanila has quit (Remote host closed the connection).
12:31:16 -!- boily has quit (Quit: HYPERBOLIC CHICKEN).
12:46:42 <FireFly> Huh, it hadn't occurred to me that you can put a non-parenthesized assignment into a for-in in JS
12:48:25 -!- sebbu2 has changed nick to sebbu.
13:05:04 -!- olls has joined.
13:07:20 <HackEgo> olls: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
13:16:53 -!- olls_ has joined.
13:17:04 -!- olls_ has quit (Client Quit).
13:25:10 -!- incomprehensibly has quit (Read error: Connection reset by peer).
13:26:09 -!- skarn has quit (Ping timeout: 265 seconds).
13:26:10 -!- incomprehensibly has joined.
13:27:43 -!- skarn has joined.
13:28:04 -!- HackEgo has quit (Ping timeout: 265 seconds).
13:28:14 -!- HackEgo has joined.
13:30:58 <HackEgo> [wiki] [[3var]] http://esolangs.org/w/index.php?diff=41125&oldid=38536 * Olls * (+95) Added link to an interpreter.
13:37:43 -!- nooga has joined.
13:41:30 <HackEgo> [wiki] [[User:Olls]] N http://esolangs.org/w/index.php?oldid=41126 * Olls * (+52) Added links to implementations
13:42:24 -!- nooga has quit (Ping timeout: 255 seconds).
14:09:05 <HackEgo> [wiki] [[User:Orenwatson]] N http://esolangs.org/w/index.php?oldid=41127 * Orenwatson * (+93) Created page with "Oren Watson is a programmer from Canada. He invented and implemented the [[scrip7]] language."
14:13:07 -!- drdanmaku has joined.
14:15:27 -!- tlewkow has joined.
14:22:12 <J_Arcane> (def fn instr (s t (i 1))(select ((empty? s) #f)((> (len$ t) (len$ s)) #f)((=$ t (left$ s (len$ t))) i)(else (instr (tail$ s) t (+ 1 i)))))
14:27:23 <J_Arcane> Tail recursive list eaters written with BASIC string functions. I didn't call it "Heresy" for nothin'.
14:27:31 -!- tlewkow has quit (Remote host closed the connection).
14:38:35 -!- nooga has joined.
14:42:50 <HackEgo> [wiki] [[Talk:Scrip7]] N http://esolangs.org/w/index.php?oldid=41128 * Orenwatson * (+389) req.for suggestions.
14:42:55 -!- nooga has quit (Ping timeout: 244 seconds).
14:43:07 <HackEgo> [wiki] [[Talk:Scrip7]] M http://esolangs.org/w/index.php?diff=41129&oldid=41128 * Orenwatson * (+95)
14:45:27 -!- hjulle has joined.
14:48:13 <mroman> why do basic string functions actually have a $ at the end?
14:48:33 <J_Arcane> mroman: $ is the string type designation.
14:49:38 <J_Arcane> They have a $ at the end if they return a string (I have made a few exceptions and allowed for some functions that only operate on strings to use $).
14:49:53 <fizzie> $ for string, % for int, & for long, ! for single and # for double.
14:49:57 <J_Arcane> Technically there are designations for ints and floats too in some dialects but they're almost never used.
14:50:11 <fizzie> (Those were the QBasic dialect ones.)
14:50:36 -!- S1 has joined.
14:51:01 <J_Arcane> In the old days the $ was mandatory: declaring something like LET X = "D" or LET X$ = 5 was a type error.
14:53:09 <J_Arcane> I just use it as a convenient name designator for the 'does stuff to strings' versions of functions in Heresy. Strictly, len$ shouldn't be a thing, it returns a number not a string, but I used len already for the list counter (a thing that doesn't need to exist in BASIC because you only have fixed arrays there)
14:56:16 <b_jonas> in BASIC, basically in the old days, variables without a sigil suffix got their type according to their first letter, where you can give the mapping from letters to types with the DEFINT, DEFSNG, DEFDBL, DEFSTR statements.
14:56:48 <b_jonas> Now the default is DEFSNG A-Z for didactical or historical reasons, but (16-bit) integers are actually more useful, so many programs start with DEFINT A-Z
14:57:07 <b_jonas> this first letter thing is sort of like Fortran
14:58:18 <b_jonas> In Modern basics, you can define variables to have types individually, with the DIM..AS statement
14:58:27 <b_jonas> you're no longer bound to use first letter thingies
14:58:48 <b_jonas> but the sigils are still available if you want to use them
14:59:33 <b_jonas> (of course, the smallest basic interpreters have only one type, 16-bit integer)
15:02:05 <fizzie> FORTRAN has the oh you said that already.
15:02:17 <J_Arcane> MSBASICs until QB tended to be pretty lazy about numbers as well.
15:02:34 <J_Arcane> Anything not $ is a number, and whatever number it needs to be at the moment.
15:04:47 <b_jonas> fizzie: oh, so the rule can be modified in FORTRAN too?
15:05:10 <b_jonas> I thought it was hardwired to I-N some sort of integers, everything else some sort of float
15:09:54 -!- MoALTz has joined.
15:15:06 -!- nooga has joined.
15:37:03 -!- AndoDaan has joined.
15:41:53 -!- MDream has changed nick to MDude.
15:44:22 <fizzie> https://docs.oracle.com/cd/E19957-01/805-4939/6j4m0vn9v/index.html
15:53:09 -!- Sprocklem has joined.
16:00:24 -!- AndoDaan_ has joined.
16:00:24 -!- AndoDaan has quit (Read error: Connection reset by peer).
16:01:30 -!- FreeFull has quit (Quit: BBL).
16:07:33 -!- AndoDaan_ has quit (Quit: Quit).
16:08:05 -!- Lorenzo64 has joined.
16:18:15 -!- tlewkow has joined.
16:21:31 -!- tlewkow_ has joined.
16:22:51 -!- tlewkow has quit (Ping timeout: 256 seconds).
16:26:12 -!- tlewkow_ has quit (Ping timeout: 264 seconds).
16:26:21 -!- shikhin has joined.
16:36:02 -!- hjulle has quit (Ping timeout: 255 seconds).
16:39:41 -!- nooga has quit (Ping timeout: 244 seconds).
16:41:13 -!- tlewkow_ has joined.
17:01:57 -!- Sprocklem has quit (Ping timeout: 256 seconds).
17:02:56 -!- shikhout has joined.
17:06:03 -!- shikhin has quit (Ping timeout: 265 seconds).
17:06:32 -!- shikhout has changed nick to shikhin.
17:06:52 -!- S1 has changed nick to |S}.
17:21:26 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
17:22:21 -!- vanila has joined.
17:39:31 -!- nooga has joined.
17:40:36 -!- lambdabot has quit (Ping timeout: 264 seconds).
17:51:12 <vanila> I discovered self modifying regex compression
17:51:16 <vanila> it was used in a js demo
17:51:26 <vanila> _='h~world}me}you}all~ello } h~';for(i in g='}~')with(_.split(g[i]))_=join(pop());eval(_)
18:00:28 <vanila> How do you compress a string to use this decompression method
18:01:27 -!- olls has quit (Quit: Lost terminal).
18:07:15 <vanila> the string itself is a regex substitution
18:07:18 <vanila> and you perform it on the string
18:07:26 <vanila> selfmodifyig regex decopression
18:07:32 <vanila> <lifthrasiir> oh, btw the code itself is quite optimized
18:07:32 <vanila> <lifthrasiir> so it's [replacement][sep][noncompressed1][sep][noncompressed2]... into [noncompressed1][replacement][noncompressed2][replacement]...
18:07:36 <vanila> itwas explaind well by lifthrasiir yesterday
18:07:53 -!- lambdabot has joined.
18:39:17 -!- hjulle has joined.
18:49:48 <nyuszika7h> Bicyclidine: with(x) changes the global scope to x inside the block after the with statement
18:50:03 <nyuszika7h> the default is with (window) (or in non-broser JS, with(global))
19:01:27 -!- ais523 has joined.
19:10:40 -!- FreeFull has joined.
19:11:59 <vanila> Any interest in compression
19:12:07 <ais523> I've dabbled in compression
19:12:17 <vanila> ais523, I discovered a cool type of compression here
19:12:32 <vanila> http://js1k.com/2014-dragons/details/1951
19:12:41 <vanila> the string is a regex subsitution
19:12:48 <vanila> and you perform it to expand some parts
19:12:56 <vanila> _='h~world}me}you}all~ello } h~';for(i in g='}~')with(_.split(g[i]))_=join(pop());eval(_)
19:13:50 <vanila> this does two searchand replaces
19:14:25 <ais523> oh, presumably the benefit is that existing software (JS in this case) already knows how to decompress?
19:15:09 <vanila> it's good because the decompressor is very short
19:15:18 <vanila> just a loop that splits and rejoins with a separator
19:22:17 <fizzie> Gah. Wrote a non-cheating Burlesque solution to Dominosa Small (ended up at 263 bytes, quite a bit longer than just embedding output), and it gets tests 1 and 2 right but fails 3 with "Burlesque/Eval.hs:(1611,2)-(1614,36): Non-exhaustive patterns in case". And the code's pretty awful to debug. (In addition to being just awful in general.)
19:23:20 <lambdabot> ghc -prof -fprof-auto -rtsopts -osuf .p_o foo.hs && ./foo +RTS -xc # print stack traces on unhandled exceptions
19:25:06 <fizzie> I'm not sure how much that helps w.r.t debugging the Burlesque code as opposed to the implementation. (I mean, I'm certain I'm doing something wrong, and I'm not all that interested in fixing the bits and pieces of Burlesque that cause unhandled exceptions instead of pushing an error on stack.)
19:25:23 <shachaf> Oh, I thought you were debugging the implementation.
19:25:50 <fizzie> I'm guessing it's correct, and it's my code that's at fault.
19:26:06 <fizzie> (At least the error is precise enough to show that it's some instance of ^p.)
19:26:46 <fizzie> (^p being applied to something that's not a block, more exactly.)
19:28:36 -!- dts has joined.
19:29:38 -!- Sprocklem has joined.
19:30:24 -!- callforjudgement has joined.
19:30:30 -!- callforjudgement has quit (Changing host).
19:30:30 -!- callforjudgement has joined.
19:33:24 -!- ais523 has quit (Ping timeout: 240 seconds).
19:33:39 -!- callforjudgement has changed nick to ais523.
19:36:19 <fizzie> The overall logic of the code is "A{B {C}qz?w! D}qL[w! E" where C does backtracking up a stack, and I've resorted to just manually unrolling the loops by copy-pasting A BD BD .. BD BCC..CD BD BD BC..CD BD BD .. and so on, in the hopes of arriving at the place where it breaks. (The command line is currently at ABDBDBDBCCDBDBCDBDBDBCCCCD and is 1608 characters long.
19:36:58 <vanila> fizzie, you're making me want to learn Blsq
19:40:14 <fizzie> Oh yes, 3716-character command lines are much fun.
19:40:23 <fizzie> (It's still going strong with no signs of breaking.)
19:41:19 <fizzie> (My hypothesis is it's missing something in the search, and therefore doesn't find any solutions.)
19:41:26 -!- ^v has joined.
19:59:05 -!- drdanmaku has joined.
20:02:21 -!- Patashu has joined.
20:08:39 -!- callforjudgement has joined.
20:11:13 -!- ais523 has quit (Ping timeout: 245 seconds).
20:11:20 -!- callforjudgement has changed nick to ais523.
20:16:00 -!- tlewkow_ has quit (Remote host closed the connection).
20:20:33 <FireFly> vanila: another fun JS golf/compression trick is to do something along the lines of for (k in o) o[f(k)] = o[k] where f(k) is some expression, to abbreviate method names for one object
20:21:25 <vanila> i cant even comprehend what that means
20:21:52 <FireFly> Well, how familiar are you with JS?
20:22:06 <vanila> so you can invert f sort of?
20:22:33 <vanila> not very but I guess k in o loops over the field names and o[f(k)] = makes a new field
20:22:34 <FireFly> Say you have a JS context object, which has methods like fillRect and stuff. So if your f is k[0]+k[5] fillRect would be aliased to just fR
20:22:48 <FireFly> And similar for other methods
20:23:10 <FireFly> (assuming no other thing aliases to fR as well, of course, since the order of iteration isn't specified)
20:23:13 <vanila> so you hav to find a simple expression that lets all your methods be diferent
20:23:24 <FireFly> Yep, at least all the ones you care about
20:23:37 <vanila> thanks for telling me about it!
20:23:54 -!- Sprocklem has quit (Ping timeout: 240 seconds).
20:24:48 <FireFly> er, that should be k[0]+k[4], but yeah
20:25:01 -!- Sprocklem has joined.
20:25:15 -!- Patashu has quit (Ping timeout: 272 seconds).
20:28:24 -!- |S} has quit (Quit: |S}).
20:29:24 -!- Sprocklem has quit (Ping timeout: 240 seconds).
20:33:57 -!- ais523 has quit (Remote host closed the connection).
20:34:14 -!- ais523 has joined.
20:36:13 -!- tlewkow_ has joined.
20:37:54 -!- tlewkow_ has quit (Remote host closed the connection).
20:50:29 -!- jix has quit (Quit: Lost terminal).
20:55:39 -!- Sprocklem has joined.
20:56:34 -!- not^v has joined.
20:57:47 -!- nyuszika7h has quit (Quit: Fixing auto-away).
20:59:00 -!- nyuszika7h has joined.
21:00:00 -!- ^v has quit (Ping timeout: 258 seconds).
21:04:13 -!- not^v has quit (Ping timeout: 258 seconds).
21:12:52 <ion> https://gist.github.com/jpupu/d180d78b1eededecc9a3
21:13:52 -!- Dulnes has joined.
21:14:17 <Dulnes> My wife drew me as a pony :/ i dislike this
21:22:37 -!- lambdabot has quit (Ping timeout: 264 seconds).
21:32:17 -!- bb010g has joined.
21:33:43 -!- S1 has joined.
21:36:50 -!- tlewkow has joined.
21:41:49 -!- lambdabot has joined.
21:43:50 -!- callforjudgement has joined.
21:47:09 -!- ais523 has quit (Ping timeout: 250 seconds).
21:47:13 -!- callforjudgement has changed nick to ais523.
21:47:52 -!- ais523 has quit (Client Quit).
21:48:06 -!- ais523 has joined.
21:59:38 -!- ais523 has quit (Read error: Connection reset by peer).
21:59:44 -!- callforjudgement has joined.
22:06:11 -!- tlewkow has quit (Remote host closed the connection).
22:11:59 -!- dts has quit (Read error: Connection reset by peer).
22:13:08 -!- L8D has joined.
22:13:46 -!- dts has joined.
22:14:27 -!- Lorenzo64 has quit (Ping timeout: 250 seconds).
22:15:28 -!- tlewkow_ has joined.
22:22:03 -!- dts has changed nick to dts|airhocky.
22:22:24 -!- Sprocklem has quit (Ping timeout: 240 seconds).
22:24:34 -!- callforjudgement has changed nick to ais523.
22:38:00 -!- S1 has quit (Quit: S1).
22:58:05 -!- AndoDaan has joined.
23:03:25 -!- shikhout has joined.
23:05:43 -!- augur_ has joined.
23:06:08 -!- shikhin has quit (Ping timeout: 240 seconds).
23:09:03 -!- augur has quit (Ping timeout: 250 seconds).
23:15:33 -!- AndoDaan has quit (Quit: Quit).
23:19:40 -!- oerjan has joined.
23:20:53 <oerjan> int-e: your bot is somewhat unreliable hth
23:21:52 <oerjan> @tell int-e <int-e> (I hope that prevents oerjan from going on a wild goose chase for a 52 character solution that may not even exist) <-- i was more worried that i'd given you enough hints for _you_ to find one :P
23:22:25 <Bicyclidine> @Jesus christ, the Fall 2014 Anime thread on SA is REALLY BAD guys
23:22:57 <oerjan> @tell int-e also, your bot loses messages hth
23:23:17 <oerjan> Bicyclidine: we don't like people starting lines with @ tags around these here parts
23:24:14 <fizzie> A milestone: the non-cheating Burlesque Dominosa now smaller than the combined outputs of the tests.
23:24:32 <oerjan> @tell int-e also, my wild goose chase is hard to get started when my own fast solutions are longer than my slow ones :(
23:24:47 <oerjan> fizzie: congratulations!
23:25:02 <Bicyclidine> @Bicyclidine: we don't like people starting línes with @ tags around these here parts
23:25:04 <oerjan> (i assume it's still longer than a compressed version)
23:25:11 <fizzie> Yes, it's at 203B now.
23:27:09 <fizzie> Getting it down to the bash-zlib 161B does not sound completely impossible, though I might have gotten the hangs-so-low-it's-on-the-ground-for-all-practical-purposes fruits already. There's probably any number of 1B and 2B shavings to be made.
23:27:38 -!- bb010g has quit (Quit: Connection closed for inactivity).
23:29:40 <fizzie> Okay, that's just silly. The very first 10 bytes can be replaced by 2.
23:29:57 <Dulnes> https://i.imgur.com/hYGYI3u.jpg
23:32:41 <Dulnes> Thats how she draws me ;-;
23:34:34 -!- nooga has quit (Ping timeout: 244 seconds).
23:35:32 -!- ais523 has quit.
23:35:42 -!- ais523 has joined.
23:36:42 -!- vanila has quit (Quit: Leaving).
23:40:25 -!- nooga has joined.
23:55:08 -!- ais523 has quit (Read error: Connection reset by peer).
23:55:18 -!- ais523 has joined.
00:02:38 -!- tlewkow_ has quit (Remote host closed the connection).
00:08:33 -!- jix has joined.
00:12:41 -!- tlewkow has joined.
00:12:52 -!- callforjudgement has joined.
00:13:04 -!- ais523 has quit (Disconnected by services).
00:13:07 -!- callforjudgement has changed nick to ais523.
00:16:53 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:30:54 -!- jix has quit (Ping timeout: 240 seconds).
00:32:56 -!- tlewkow has quit (Remote host closed the connection).
00:33:36 -!- tlewkow has joined.
00:40:58 -!- nooga has quit (Ping timeout: 256 seconds).
00:45:18 -!- Sgeo has quit (Read error: Connection reset by peer).
00:47:12 -!- Sgeo has joined.
01:01:22 -!- adu has joined.
01:02:58 -!- jix has joined.
01:13:27 -!- callforjudgement has joined.
01:13:42 -!- ais523 has quit (Read error: Connection reset by peer).
01:13:49 -!- callforjudgement has changed nick to ais523.
01:28:15 -!- ais523 has quit (Read error: Connection reset by peer).
01:28:22 -!- ais523 has joined.
01:36:00 <oerjan> you know your code is robust when your test passes even if you have misspelled mod as div
01:37:14 <coppro> yes, let's go with that
01:37:15 <shachaf> oerjan: is that like https://github.com/mame/radiation-hardened-quine
01:37:54 -!- adu has quit (Quit: adu).
01:39:07 <oerjan> (more seriously, having div caused a subtest to always pass, but it was redundant for the test case)
01:43:40 * oerjan tries submitting without the subtest too
01:44:24 <oerjan> case 1 and 3 still succeed then, but 2 actually needs it
01:45:25 <oerjan> (btw the test is for whether i'm at the end of a line, so that a domino cannot go on rightward)
01:46:52 <oerjan> another way of removing it failed all 3
01:52:54 <HackEgo> [wiki] [[DNA-Sharp]] http://esolangs.org/w/index.php?diff=41130&oldid=41047 * 79.204.240.23 * (+80) Undo revision 41047 by [[Special:Contributions/149.69.108.53|149.69.108.53]] ([[User talk:149.69.108.53|talk]]) - Editor reuploaded, sorry for that.
01:54:15 * oerjan must stop this habit of absentmindedly editing his submitted entries without copying them first
01:54:44 <HackEgo> [wiki] [[DNA-Sharp]] http://esolangs.org/w/index.php?diff=41131&oldid=41130 * 79.204.240.23 * (-80) Undo revision 41130 by [[Special:Contributions/79.204.240.23|79.204.240.23]] ([[User talk:79.204.240.23|talk]]) - There seems to be some problem, I will have to fix that in the near future. Link will be removed until then.
02:02:44 -!- adu has joined.
02:17:36 -!- GeekDude has joined.
02:17:45 <GeekDude> I just realized I set my client to auto-join #estoeric
02:18:29 <oerjan> well it's a bit confusing right now
02:18:49 <oerjan> fizzie didn't get around to fix the bug in zemhill, then EgoBot came _back_
02:19:30 <oerjan> so now we have two bots responding to the !bfjoust command, with different hills. and while zemhill _should_ be an improvement, it's currently buggy.
02:20:03 <oerjan> well there's quite a bit of burlesque spam :)
02:20:14 <GeekDude> I'm still trying to figure out a good way to spam piet over IRC
02:20:34 <GeekDude> there aren't enough color codes
02:20:50 <GeekDude> they just aren't the right colors
02:25:12 -!- jix has quit (Remote host closed the connection).
02:25:21 -!- jix has joined.
02:31:03 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
02:32:30 <oerjan> ooh this allows me to tie fizzie's burlesque with haskell :P
02:33:03 <oerjan> perhaps beat, if i can improve the formula
02:33:51 <oerjan> wait where did that bug come from :(
02:34:45 <oerjan> the formula needs integers, not chars
02:38:08 <int-e> oerjan: unfortunately it's not the bot, it's the server. (I still haven't implemented the regular flushing of state though, that's my fault.
02:39:15 <int-e> oerjan: "[host] has experiened a kernel panic. We have rebooted the node into the latest stable OpenVZ kernel. Your VPSs should be back up shortly."
02:40:18 -!- mihow has quit (Quit: mihow).
02:41:27 <int-e> at least my init script that restarts the bot's screen session is now well-tested.
02:42:54 <oerjan> ooh an even better idea, if this works
02:50:11 -!- bb010g has joined.
02:54:52 <Dulnes> To you ppls who use it
02:55:39 * oerjan doesn't actually use it, but are you on the right channel?
02:55:54 <Dulnes> Its not like i hate hate it
02:56:15 <Dulnes> I just dislike it when i have to use it to complete something
02:56:15 <Taneb> It is annoying when my scrollback is filled with Burlesque
02:56:29 <Taneb> But I can tolerate it
02:56:39 <Taneb> It's not like I understand half the things in this channel in any case
02:57:13 <Dulnes> I will flip shit if someone comes in here spouting malbolge
02:57:54 <int-e> "when i have to use it" ... I don't follow.
02:57:58 -!- augur_ has changed nick to augur.
02:58:33 <int-e> There are so many esoteric languages, you can pick one that you actually like.
02:58:34 <Dulnes> Idk like if i wanna do something with a friend
02:58:52 <Dulnes> But they use burlesque
02:59:01 <oerjan> Dulnes: has this ever happened to you yet
03:08:46 -!- vanila has joined.
03:12:21 -!- tlewkow has quit (Remote host closed the connection).
03:12:48 -!- tlewkow has joined.
03:17:18 -!- tlewkow has quit (Ping timeout: 255 seconds).
03:19:46 -!- adu has quit (Quit: adu).
03:38:54 -!- shikhout has quit (Ping timeout: 255 seconds).
03:43:44 -!- ais523 has quit.
03:44:18 -!- ais523 has joined.
03:45:41 -!- tlewkow has joined.
03:46:32 <vanila> is there a simple algorithm to perform the optimal self modifying regex compression?
03:48:19 -!- Sprocklem has joined.
03:52:44 <lifthrasiir> vanila: what do you mean by "compression"?
03:53:00 <lifthrasiir> like, turning /foo|bar|baz/ into /foo|ba[rz]/?
03:53:59 <Bicyclidine> vanila's been talking about it for a while. i think they mean shorter regex strings
03:54:16 <vanila> _='h~world}me}you}all~ello } h~';for(i in g='}~')with(_.split(g[i]))_=join(pop());eval(_)
03:54:25 <Bicyclidine> which seems like it might be harder since it's more all over the place than some DFA shrinkage
03:54:40 <lifthrasiir> vanila: did you take a look at regpack source code?
03:54:47 <vanila> yeah but I didn't understand it
03:54:52 <lifthrasiir> the "optimal" one? I'm not sure about that though.
03:54:54 <vanila> and I don't know if it uses the best algorithm
03:55:10 <vanila> im curious about how to do it at all though
03:55:20 <lifthrasiir> just as most compressors use a (well-working) heuristic
03:56:26 <lifthrasiir> vanila: it is essentially a crude version of LZ77 and it is hard to find the "optimal" compression
03:57:06 <oerjan> 14 more bytes shaved off
03:59:34 <int-e> oerjan: 15 more until you break even with my cheating solution
04:00:19 <oerjan> i think that might be hard
04:03:40 -!- MoALTz_ has joined.
04:06:48 -!- MoALTz has quit (Ping timeout: 255 seconds).
04:09:44 <int-e> oerjan: sigh. I don't know how to do this properly without refactoring tons of code: https://github.com/int-e/lambdabot/commit/4d112c371e306e79983b262fd758693742d79430
04:10:25 -!- lambdabot has quit (Quit: brb).
04:10:30 <int-e> it'll just have to do for now
04:10:54 <oerjan> int-e: you could use a lock hth
04:12:38 <int-e> I guess what the code should be doing is use the create-new-temporary-file-and-rename idiom.
04:13:38 <vanila> I dont think LZ77 is similar to the self modifying regex stuff
04:14:18 <int-e> it is similar in that you encode repeated substrings. and I guess that's as far as the similarity goes.
04:14:40 -!- lambdabot has joined.
04:18:38 <oerjan> that module seems to only explicitly import things that everyone knows how to find, but not the lambdabot modules themselves :(
04:18:57 <oerjan> like, THAT'S THE OPPOSITE OF THE RIGHT PRIORITY
04:19:11 <elliott> lambdabot code is horrible
04:19:35 <oerjan> i was like wondering where flushModuleState is defined
04:26:52 <oerjan> apparently "Sorry, forked repositories are not currently searchable." and int-e/lambdabot is a forked repository.
04:27:00 -!- hjulle has quit (Ping timeout: 264 seconds).
04:29:04 <vanila> I wonder how to find a good and the best compression algorithm
04:29:13 <vanila> I can think, it's easy to find repeated substrings
04:29:28 <vanila> but then which set should you replace with a substitution?
04:29:40 <vanila> in which order to perform them
04:30:09 <oerjan> vanila: see kolmogorov complexity, then weep hth
04:30:58 <oerjan> NO COMPRESSION WITHOUT BITTER TEARS
04:31:08 <vanila> also See; Halting Problem, HTH "Hope that halts"
04:31:37 <vanila> in exchage for algorithm I offer you 1 (one) cup of tears
04:33:14 <vanila> but reall y I think compression is interesting because you can come up against complexity without getting into undeciable problems
04:33:52 <vanila> of course you have to prove your decompression language is not turing
04:39:42 <int-e> oerjan: ok, this should help things: https://github.com/int-e/lambdabot/commit/de814c2bce21c588dd1d0dc82ba2c0e1b7e4df21
04:39:55 <Dulnes> Hhhh i just found my Atari
04:40:29 <Dulnes> oerjan: just compress your tears
04:40:48 -!- lambdabot has quit (Quit: brb).
04:41:11 <oerjan> Dulnes: water is mostly incompressible hth
04:42:08 <int-e> And yes, the whole lambdabot code is a bit messy. Some old cruft, some overengineering, a number of ugly hacks (like this flushing one) that have survived the tides of time... it all adds up. It's remarkable that it holds together overall.
04:45:02 -!- lambdabot has joined.
04:48:21 <Dulnes> Also the only way i see lambda bot being held together would be large ammounts of virtual ductape
04:52:45 <vanila> rewrite it in python or go
05:07:51 -!- Deewiant has quit (Ping timeout: 250 seconds).
05:08:04 -!- MDude has changed nick to MDream.
05:10:32 -!- tlewkow has quit (Remote host closed the connection).
05:13:01 -!- tlewkow has joined.
05:16:23 -!- Deewiant has joined.
05:22:04 <int-e> vanila: that will just result in a different, and likely bigger mess.
05:25:34 <Bicyclidine> just compromise. write half of in haskell and half in python.
05:30:30 <int-e> Thanks, but I'll pass.
05:31:30 <vanila> alternatively write it in C for speed
05:31:32 <int-e> FTR, I actually like Python, but I don't think it'll mix well with Haskell.
05:31:56 <vanila> why do you like python?
05:32:43 <int-e> The usual, I guess. Easy going, quick to get started, and it has a pretty sane standard library.
05:41:16 -!- ais523 has quit (Read error: Connection reset by peer).
05:41:33 -!- ais523 has joined.
05:54:27 <Dulnes> Bicyclidine: wth are you saying
05:56:22 <Dulnes> Javascipt Thats actually C
06:00:35 -!- tlewkow has quit (Remote host closed the connection).
06:03:25 -!- Sprocklem has quit (Ping timeout: 264 seconds).
06:08:53 -!- tlewkow has joined.
06:20:36 <idris-bot> flip (\{meth0} => \{meth1} => prim__sdivBigInt meth meth) 56843 : Integer -> Integer
06:34:12 <fizzie> oerjan: Shameful how much trouble I'm having getting Burlesque to beat Haskell there. (Just shaved it to be 1B better.)
06:37:34 <fizzie> Ooh, I think I see a 12B saving.
06:38:58 <fizzie> Oh no, have to go to work first.
06:39:01 <fizzie> Well, we'll see later.
06:45:23 -!- callforjudgement has joined.
06:45:28 -!- ais523 has quit (Read error: Connection reset by peer).
06:45:31 -!- callforjudgement has quit (Changing host).
06:45:31 -!- callforjudgement has joined.
06:45:35 -!- callforjudgement has changed nick to ais523.
07:03:55 -!- tlewkow has quit (Remote host closed the connection).
07:21:25 <fizzie> Did I say 12B? I meant 14B.
07:25:47 <Bicyclidine> so GNU C has __thread, but doesn't know what _Thread_local means. awesome.
07:28:35 <mroman> __thread is GCC's thread-local storage class keyword.
07:30:28 <mroman> I haven't looked at C11 very much I'm afraid
07:30:41 <Bicyclidine> is there, like, a reason gcc doesn't just #define _Thread_local __thread somewhere
07:30:55 <ais523> Bicyclidine: what if someone stringifies it?
07:31:15 <mroman> GCC 4.9 supports _Thread_local
07:31:21 <oerjan> fizzie: AAAAAAAAAAAAAAAA
07:31:36 <oerjan> (you beat your own cheating bash version?)
07:31:46 <fizzie> oerjan: By 8B now, yes.
07:32:01 <fizzie> (I found another useless 7B in there. So sloppy.)
07:32:02 <mroman> fizzie: You wrote a >100B Burlesque program?
07:32:35 <b_jonas> mroman: what? what's wrong with that?
07:32:50 <b_jonas> mroman: it could be just a double-quoted string
07:32:54 <fizzie> Well, I mean, I wouldn't have, if I could just make it shorter.
07:33:04 <fizzie> There are no double-quoted strings in the program, FWIW.
07:33:14 <mroman> but long Burlesque programs is usually an indicator that you have to manage state
07:33:27 <mroman> and managing state is pure pain in the ass in Burlesque I'm afraid
07:34:30 <mroman> fizzie: What would help to make it shorter?
07:34:40 <fungot> http://esolangs.org/wiki/Burlesque
07:34:41 <mroman> (other than "add a builtin that exactly solves this problem". I won't do that)
07:35:15 <mroman> I'm more looking for patterns that can be implemented to be useful for many other problems as well
07:35:18 <mroman> like the Continuations
07:36:04 -!- Patashu has joined.
07:36:30 <b_jonas> mroman: I'm still saying, a builtin that pops a natural number, then picks the value from the stack that is that far from the top and pushes that to the stack, would help, because that takes five characters now
07:37:19 <b_jonas> That would let you use the stack as the frame for local variables.
07:37:43 <mroman> b_jonas: there's MV which pops a natural number and moves that element from the stack to the top
07:37:55 <mroman> but there's no "copy" as of now
07:37:59 <mroman> but it's on the todo list.
07:38:19 <mroman> b_jonas: also 1.7.4 has variables
07:38:21 <b_jonas> mroman: oh a rotator instruction. sounds nice. still, I'd like copy
07:38:34 <b_jonas> mroman: global variables are nice, but this would be for when you need local variables
07:38:41 <blsqbot> | {10 11 12 13 14 15 16 17 18 19}
07:38:49 <b_jonas> mroman: and those mutable dictionary instructions you've added certainly help
07:38:59 <mroman> ^- s0 set's the global variable "0" and g0 reads the global variable "0"
07:39:06 <b_jonas> because you can use them to have sorta-efficient arrays, and mutable state
07:39:24 <mroman> b_jonas: but you have to keep the dictionary around of course
07:39:32 -!- Patashu has quit (Remote host closed the connection).
07:39:36 <b_jonas> mroman: oh! I thought the variables had fancy punctuation names, something with a percent sign or something
07:39:53 -!- Patashu has joined.
07:40:05 <mroman> but g0 is shorter than %0?
07:40:34 <b_jonas> Anyway, I'm saying this pick instruction because it's already implementible (it's three blsq instructions), so it's easy to add.
07:40:35 <mroman> (but it's they same. g0 is just a shortcut for %0?)
07:42:16 <mroman> hm. let me update blsqbot
07:43:13 <mroman> b_jonas: other things I've added are builtins like
07:44:16 <mroman> {1 2 3 4 5}{0 1 1 0 1}<SelectIf> returns {2 3 5}
07:44:55 <mroman> {1 2 3 4 5}{2.%}{2.*}<MapIf> returns {1 4 3 8 5}
07:45:06 <mroman> (i.e. it only applies the function if a condition matches)
07:45:21 <mroman> (2dv actually instead of 2.%)
07:47:43 <mroman> b_jonas: also maps allow you for "easy" multi-dimensional array I hope
07:47:57 <mroman> I.e. you can use {0 1 2} as a key for 3d arrays
07:48:07 <mroman> and you can specify a default value for lookups
07:48:24 <mroman> (i.e. when no value is bound to a key the default value is returned)
07:49:37 <fizzie> mroman: Do you happen to have a stock way (less than 11B) of going from {{1 2} {3 4} {5 6} ...} to a prettified "1,2 3,4 5,6 ..."? I'm not terribly good at formatting things.
07:50:50 <fizzie> (Less than 10B, I mean. Can't ocunt, either.)
07:51:05 <oerjan> i tried using init(tail$show(x,y)) but it ends up longer than just writing it out :(
07:52:04 <oerjan> (wait did i just give fizzie a possibly translateable idea)
07:54:00 <fizzie> Actually, it's not quite as simple as all that. It has to go from {{a b} {c d} ...} to a prettified "i,j k,l ..." where there's a 8-character mapping from a -> i, b -> j etc.
07:54:00 <vanila> init(tail show(x,y)) same ength, more readable, less confusing operators
07:54:05 <oerjan> vanila: it's a haskell shortcut operator for avoiding parentheses
07:54:15 <oerjan> vanila: um that is not well typed
07:54:40 <mroman> "1,2 3,4" or "1,2\n3,4"?
07:55:00 <fizzie> Currently I'm using {{...}]m',IC}m[wD where ... is the mapping I need for the numbers.
07:58:28 <mroman> {1SH~-}m[wd but that's 11B
08:00:27 <fizzie> Since I can get my numbers to strings for "free" (I need to do a m[ anyway, and that can be ]m when it helps), I guess ',IC is better than 1SH~-.
08:01:20 <Bicyclidine> I forget C wizardry. Is there some value I can set a jmp_buf to to mark it as invalid?
08:01:29 <Bicyclidine> It's like... an array type... I don't know if I can null that.
08:01:45 -!- dts|airhocky has changed nick to dts.
08:02:55 -!- Patashu_ has joined.
08:02:55 -!- Patashu has quit (Disconnected by services).
08:03:15 <mroman> (you can always drop the last ~ btw ;) )
08:04:36 <mroman> fwiw MapUnlines and MapWords are on the todo list ;)
08:05:04 <mroman> (FilterUnlines already exists)
08:05:50 <mroman> FilterWords exists but it's not just f[wd
08:06:15 <mroman> it would only save you one byte anyway
08:06:21 <mroman> since you need <MapWords>Q
08:06:28 <mroman> because m[wd doesn't pretty
08:06:57 <mroman> !blsq "abc dac efg feg"qsow[
08:07:11 <Bicyclidine> can i use a function call as an lvalue? Something like "*foo() = ...", where foo returns a double indirect.
08:09:00 <elliott> you can use *p where p is a pointer (even an rvalue) as an lvalue, sure
08:09:13 <elliott> shouldn't need to be double indirect
08:09:42 <vanila> is this regular C or Double C?
08:09:51 <Bicyclidine> ok yeah it doesn't need to be double indirect, right
08:09:58 <Bicyclidine> vanila: i'm using setjmp so it's probably, like, triple c
08:10:04 <mroman> fizzie: other than 1.7.4 saves you one byte since {}m[ can now be written as m{}
08:10:28 <elliott> do you really want to use setjmp :p
08:10:30 <b_jonas> mroman: do you have a built-in that returns a list (block) of the values of a dictionary sorted by its keys?
08:10:44 <fizzie> mroman: That's not yet on anagol, right?
08:10:52 <Bicyclidine> elliott: does anyone ever really want to use setjmp?
08:11:14 <b_jonas> mroman: I mean, that's not really essential, but could be convenient
08:11:57 <mroman> I have keys, values, valuesSortedByKey and keysSortedByValue
08:12:17 <mroman> and swapKeysWithValues
08:12:19 <fizzie> mroman: Speaking of which, is there a shorter )><NB or do I remember right that there was no nub-sorted builtin?
08:13:06 <mroman> and even if it had one it wouldn't do )<>
08:13:11 <mroman> but rather NB>< or NB<>
08:13:27 <mroman> but no, it doesn't have that
08:14:11 <fizzie> How about a variant of 2CB that returns all unordered pairs instead of ordered?
08:14:32 <blsqbot> | {{1 1} {1 2} {1 3} {1 4} {1 5} {2 1} {2 2} {2 3} {2 4} {2 5} {3 1} {3 2} {3 3} {3 4} {3 5} {4 1} {4 2} {4 3} {4 4} {4 5} {5 1} {5 2} {5 3} {5 4} {5 5}}
08:14:45 <fizzie> !blsq {1 2 3 4 5}2CB)><NB
08:14:46 <blsqbot> | {{1 1} {1 2} {1 3} {1 4} {1 5} {2 2} {2 3} {2 4} {2 5} {3 3} {3 4} {3 5} {4 4} {4 5} {5 5}}
08:15:11 <fizzie> It's not too long like that, I was just wondering.
08:16:07 <mroman> I guess that can go on the todo list, yes
08:19:16 <mroman> I can easily define it as )><NB
08:20:03 <mroman> (I.e. add a builtin that does )><NB or )<>NB)
08:21:05 <mroman> also I think I'm starting to panic again
08:21:05 <fizzie> Found an unrelated 2B I can save, but it changes the search order so that examples 1 and 2 time out on anagol. :( (Not by much, but clearly enough; 1.5 seconds for both.)
08:21:46 <mroman> shinh really oughta compile Burlesque with -O3 turned on
08:21:55 <mroman> It makes a huge difference
08:23:45 <fizzie> And if I do one other +- 0 change that affects the search order (but keep that -2 change), it passes examples 1 and 2 but times out on 3.
08:24:22 <mroman> How efficient is Data.Map actually?
08:25:06 <mroman> looking up a Builtin in Burlesque is O(n)
08:26:15 <mroman> I assume it's probably O(n)
08:26:23 <lambdabot> lookup key ((x,y):xys) | key == x = Just y
08:27:08 <fizzie> Oh, g_ does the analogous operation to blocks as l_. For some reason I thought it was only l_, even though that's just illogical.
08:27:42 <Bicyclidine> which makes sense since the key has to be Ord instead of just Eq
08:28:44 <elliott> you should use Data.Map.Strict
08:29:00 <elliott> (you should use Data.HashMap.Strict)
08:29:17 <Bicyclidine> Firefox can't find the server at data.hashmap.strict.
08:29:17 <mroman> fizzie: yep @g_ and l_
08:29:41 <Bicyclidine> WIll I still should use Data.HashMap.Strict in, like, a year say
08:30:14 <Bicyclidine> why is strctness even important actually i'm kind of genuinely curious instead of just a sarcastic dickhead like usual
08:30:38 <fizzie> (That saved me three bytes.)
08:31:26 <elliott> HashMap has been around for years
08:31:54 <elliott> actually maybe Data.Map.Lazy is okay
08:32:02 <elliott> some of the lazy structures are really ridiculous though, like State
08:36:08 <elliott> laziness is relative, most .Strict structures actually use plenty of laziness
08:36:38 <Bicyclidine> look i'm just curious why you'd want a .strict thing over a .lazy thing or whatever you said
08:39:20 <elliott> it's half past eight, I'm too tired to explain :(
08:39:23 <HackEgo> [wiki] [[Talk:TrivialBrainfuckSubstitution]] http://esolangs.org/w/index.php?diff=41132&oldid=41113 * Oerjan * (+172) Not quite
08:39:38 <Bicyclidine> that's cool i'm tired and loaded up on triple sec longjmp
08:39:51 <Bicyclidine> so explaining it to me would be a waste of your time
08:41:15 <mroman> you can register the signal and jump out of the signal handler
08:41:54 <mroman> the OS will kill the process hard though if another sigsegv occurs
08:43:36 -!- oerjan has quit (Quit: sigzzzzz).
08:45:37 <Bicyclidine> well now the stuff i'm doing seems completely reasonable. thank.s
08:45:39 <fizzie> Are you sure that's not just the signal handler resetting? There should be nothing illegal about recovering from sigsegv. (I did it in an early jitfunge version to make a hardware-assisted "pop 0 if empty" stack, though with setcontext to actually continue.
08:46:26 <mroman> I'm not sure if the OS signals SIGKILL
08:46:27 <fizzie> Was more trouble than it was worth, because the handler haf to inspect the failing opcode to see where the 0 was expected.)
08:46:53 <vanila> http://esolangs.org/wiki/Perl
08:47:43 <Bicyclidine> lol C has signals in it, huh, i thought it was just posix
08:48:10 <ais523> Bicyclidine: I have a raise(SIGSEGV) as a "this should never happen" in memory allocation code :-)
08:48:32 <ais523> admittedly, it's in a program that has a POSIX level of system specificity
08:48:39 <ais523> (i.e. it has POSIX and Windows codepaths)
08:49:05 <ais523> oh and SIGSEGV is standard C as of C11, it's implementation-defined whether it can ever happen except via raise() though
08:51:39 <Bicyclidine> "System V also provides these semantics for signal(). This was bad because [bla bla bla] The [linux] kernel's signal() system call provides System V semantics." fucking incredible
08:52:44 <Bicyclidine> "By default, in glibc2 and later, the signal() wrapper function does not invoke the kernel system call [and uses BSD semantics instead]" seriously what the fuck, amazing
08:57:53 <vanila> im laughing at the esolang wiki
08:57:57 <vanila> looking at random languages
08:58:09 <mroman> This ain't no stinking laughing matter.
08:59:07 -!- Patashu has joined.
09:00:12 -!- Patashu_ has quit (Ping timeout: 256 seconds).
09:01:25 -!- Patashu has quit (Client Quit).
09:03:46 -!- Patashu has joined.
09:05:44 <vanila> http://esolangs.org/wiki/Timeline_of_esoteric_programming_languages
09:10:33 -!- nooga has joined.
09:11:27 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:19:06 -!- nooga has quit (Ping timeout: 255 seconds).
09:24:32 -!- Dulnes has quit (Quit: Connection closed for inactivity).
09:30:52 <b_jonas> Bicyclidine: that's because with glibc, depending on the feature set macros, you can compile programs to be more sysv-like or more bsd-like, and so signal uses the semantics more approperiate for it. glibc has lots of compatibility stuff like that.
09:31:51 <b_jonas> the signal stuff doesn't come up much in modern programs, these days we have the variant functions for 64 bit file offset and inode number instead from feature macros.
09:36:29 -!- scounder has quit (Write error: Connection reset by peer).
09:43:49 <FireFly> Bicyclidine: where is that 'do not use this ever' from? It reminded me of the gets(3) manpage, but that's 'never use this function' apparently
09:48:06 -!- nooga has joined.
09:51:37 -!- shikhin has joined.
10:03:19 -!- scounder has joined.
10:04:32 -!- tlewkow has joined.
10:08:49 -!- tlewkow has quit (Ping timeout: 240 seconds).
10:13:36 -!- Phantom_Hoover has joined.
10:28:57 -!- applybot has joined.
10:43:21 <HackEgo> [wiki] [[Special:Log/newusers]] create * Cluid Zhasulelm * New user account
10:48:37 -!- TodPunk has quit (Read error: Connection reset by peer).
10:49:15 -!- TodPunk has joined.
11:00:12 -!- dts has quit (Ping timeout: 244 seconds).
11:04:31 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] N http://esolangs.org/w/index.php?oldid=41133 * Cluid Zhasulelm * (+347) Page creation
11:06:27 -!- AndoDaan has joined.
11:09:14 <J_Arcane> "In Qbasic you only need to define a function once. Why redefine it again? Just use a different Fn name for each definition." aaaaaaagh.
11:13:42 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41134&oldid=41133 * Cluid Zhasulelm * (+417) Add instrution
11:16:08 <J_Arcane> (from a forum argument about implementing DEF FN in QB64)
11:16:32 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41135&oldid=41134 * Cluid Zhasulelm * (+417) Add Immediate
11:20:18 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41136&oldid=41135 * Cluid Zhasulelm * (+555) ANDIX
11:21:09 -!- boily has joined.
11:23:28 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] http://esolangs.org/w/index.php?diff=41137&oldid=41136 * Cluid Zhasulelm * (+501) And-Xor
11:27:37 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41138&oldid=41137 * Cluid Zhasulelm * (+554) Branch On Equal to Zero
11:29:44 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41139&oldid=41138 * Cluid Zhasulelm * (+516) Branch On Less Than Zero
11:32:09 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41140&oldid=41139 * Cluid Zhasulelm * (+532) Exchange
11:34:39 <fizzie> mroman: Burlesque documentation note: tw and dw for strings are documented to be defined as **tw\[ and **dw\[, respectively, but I think both are actually XXtw\[ and XXdw\[ instead.
11:35:15 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41141&oldid=41140 * Cluid Zhasulelm * (+553) Or Immediate-Xor
11:37:40 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41142&oldid=41141 * Cluid Zhasulelm * (+495) Or Xor
11:40:59 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41143&oldid=41142 * Cluid Zhasulelm * (+681) Reverse Direction, Branch On Equal to Zero
11:42:55 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41144&oldid=41143 * Cluid Zhasulelm * (+643) Reverse Direction, Branch On Less Than Zero
11:43:12 <mroman> fizzie: I'll look into that
11:45:48 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41145&oldid=41144 * Cluid Zhasulelm * (+385) Rotate Left
11:47:09 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41146&oldid=41145 * Cluid Zhasulelm * (+385) Rotate Right
11:50:05 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41147&oldid=41146 * Cluid Zhasulelm * (+511) Shift Left Logical-Xor
11:51:50 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41148&oldid=41147 * Cluid Zhasulelm * (+519) Shift Right Arithmetic-Xor
11:54:25 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41149&oldid=41148 * Cluid Zhasulelm * (+430) Exclusive Or
11:56:45 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] M http://esolangs.org/w/index.php?diff=41150&oldid=41149 * Cluid Zhasulelm * (+469) Xor Immediate
12:02:43 -!- Patashu has quit (Ping timeout: 244 seconds).
12:03:45 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
12:11:06 <int-e> > map length ["last(f:[t|p])", "if p then t else f"]
12:16:12 <boily> “|” is not an operator?
12:23:22 <int-e> I should take some inspiration leapfrogging.
12:24:23 <HackEgo> [wiki] [[Pendulum Instruction Set Architecture]] http://esolangs.org/w/index.php?diff=41151&oldid=41150 * Cluid Zhasulelm * (+2229) Added Notes and Example Code
12:27:24 -!- boily has quit (Quit: CERULEAN CHICKEN).
12:32:49 <FireFly> a command-line tool for "JSON selectors"
12:33:07 <FireFly> among other things, possibly? I dunno, it's the jq I know about at least
12:33:13 <int-e> mroman: there's a "version info" page linked from the anagol frontpage, which generally answers these questions
12:33:23 <int-e> this time it links to https://github.com/stedolan/jq
12:34:14 <int-e> @tell oerjan today I learned that runhaskell is not good for testing haskell programs, because its buffering of stdout is wrong.
12:34:36 <int-e> FireFly: it was just added to anagol a couple of days ago.
12:44:20 <mroman> Does Burlesque support JSON?
12:45:48 <HackEgo> [wiki] [[Janus]] N http://esolangs.org/w/index.php?oldid=41152 * Cluid Zhasulelm * (+826) page creation
12:59:54 <HackEgo> [wiki] [[Janus]] http://esolangs.org/w/index.php?diff=41153&oldid=41152 * Cluid Zhasulelm * (+1083) Added example code
13:14:06 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] N http://esolangs.org/w/index.php?oldid=41154 * Cluid Zhasulelm * (+192) page creation
13:14:58 -!- TodPunk has quit (Read error: Connection reset by peer).
13:15:06 -!- Tod-Autojoined has joined.
13:30:28 <fizzie> Great. A PDF file that shows up (in Chrome's native PDF viewer) only as "Please wait... If this message is not eventually replaced by the proper contents of the document, your PDF viewer may not be able to display this type of document."
13:30:48 <fizzie> I know people make websites with no static content, and everything loaded dynamically over AJAX, but I didn't know this had spread to PDF files too.
13:37:06 <mroman> PDF is the best game container file format!
13:41:00 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] http://esolangs.org/w/index.php?diff=41155&oldid=41154 * Cluid Zhasulelm * (+90) added more here
13:43:38 -!- GeekDude has joined.
13:43:53 <b_jonas> what do you mean by "game container"
13:44:37 <ais523> b_jonas: game ((container file) format)
13:45:00 <ais523> or perhaps game (container (file format))
13:45:57 <FireFly> Are there any decent non-Turing-complete document formats?
13:46:10 <ais523> is odf turing-complete?
13:46:21 <ais523> (which are a nonstandard extension)
13:46:36 <ais523> and as #irp shows, plaintext may be turing-complete
13:46:50 <b_jonas> ais523: yes, but what kind of game and contained how? you don't just print the pdf and wrap deer in it before freezing?
13:47:32 <ais523> b_jonas: I assume "game" as in videogame, not as in game animal
13:47:33 <FireFly> If I were to print out a document, I'd rather not print it as plain monospaced markdown
13:47:52 <FireFly> I read "game" as synonymous to "toy"
13:48:04 <FireFly> That would make sense at least
13:50:57 -!- MDream has changed nick to MDude.
13:53:09 -!- hjulle has joined.
13:57:14 -!- vanila has quit (Quit: Leaving).
14:04:21 <GeekDude> ais523: RTF, but it's kind of annoying
14:07:14 -!- ais523 has quit (Read error: Connection reset by peer).
14:07:21 -!- callforjudgement has joined.
14:07:31 -!- callforjudgement has changed nick to ais523.
14:14:49 * int-e wonders whether oerjan is cheating on dominosa by allowing dominos to wrap around
14:15:21 <int-e> because ... it works for the examples, so it's quite tempting
14:46:11 -!- ZombieAlive has quit (Remote host closed the connection).
14:46:53 -!- tlewkow has joined.
14:50:51 -!- AndoDaan has quit (Quit: Quit).
14:58:39 -!- tlewkow has quit (Remote host closed the connection).
15:02:38 -!- ais523 has quit.
15:29:00 <int-e> @tell oerjan PS: by "today I learned" I meant that today was the first time that I profited from that fact rather than finding out that my oh-so-cleverly-optimized program didn't work on anagol.
15:31:15 -!- Sprocklem has joined.
15:41:13 -!- `^_^v has joined.
15:44:07 -!- tlewkow has joined.
15:45:03 -!- tlewkow has quit (Remote host closed the connection).
15:48:04 -!- S1 has joined.
15:51:25 -!- shikhout has joined.
15:54:42 -!- tlewkow has joined.
15:54:44 -!- shikhin has quit (Ping timeout: 255 seconds).
15:55:14 -!- tlewkow has quit (Remote host closed the connection).
15:55:24 <mroman> b_jonas: you can embed stuff into PDFs
15:55:26 -!- tlewkow has joined.
15:56:19 <mroman> b_jonas: you can embed multimedia shit into PDFs
15:59:33 <b_jonas> mroman: yeah, and javascript too
16:04:08 <mroman> that's when PDF went downhill
16:04:49 -!- `^_^v has quit (Ping timeout: 264 seconds).
16:20:33 -!- hjulle has quit (Remote host closed the connection).
16:24:18 <Bicyclidine> FireFly: man 2 signal. what it actually says is "avoid its use" and "do not use it for this purpose".
16:29:46 -!- tlewkow has quit (Remote host closed the connection).
16:30:02 -!- tlewkow has joined.
16:31:31 <J_Arcane> I spent all day learning the Y-combinator.
16:31:44 <J_Arcane> I suspect it is of limited utility, but it was fun.
16:37:55 <elliott> fixed point combinators are useful; Y itself, not so much
16:38:19 -!- GeekDude has quit (Ping timeout: 245 seconds).
16:50:59 <J_Arcane> elliott: It's a neat little thing, but doesn't seem very efficient performance wise.
16:51:26 <Bicyclidine> i've seen a paper on using y in efficient compiles
16:51:51 <J_Arcane> Well, at least on Racket it isn't any better than simple recursion for the stuff I tried.
16:52:35 <J_Arcane> But that could be an optimization thing with how it handles recursions vs. how it does Y.
16:52:44 -!- spiette has joined.
16:53:00 <J_Arcane> (admittedly this is a point where I'm a bit out of my depth)
16:53:14 <Bicyclidine> it's not really a high priority to optimize i don't think
16:53:20 <Bicyclidine> because i mean why would it be, only nerds use it
16:53:57 <J_Arcane> :D Yeah. Other than the very rare case you want to recur inside a lambda I don't see myself using it ever again in all likelihood. XD
17:01:04 <elliott> J_Arcane: well, I mean, you use Y in languages without explicit recursion
17:01:38 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:01:38 <elliott> if you want a fixed-point combinator in a language with recursion just do (define (fix f) (letrec ((g (f (lambda (x) (g x))))) g))
17:02:11 <J_Arcane> elliott: Ahh, yeah. Makes sense.
17:03:59 <J_Arcane> In Scheme it's mostly novelty because tail-call optimizations are a part of the standard, but I can see where it could be useful elsewhere.
17:05:38 <elliott> it doesn't have much to do with tail calls, though :)
17:05:51 <elliott> Y does general recursion, not just tail calls, and will use just as much stack
17:05:55 <elliott> *just as much stack to do it
17:05:58 -!- drdanmaku has joined.
17:06:20 <J_Arcane> Ahh. I suppose that makes sense too.
17:06:55 -!- GeekDude has joined.
17:06:56 <J_Arcane> That was something I noticed watching it expand in DrRacket: "holy hell, this generates an awful lot of code ..."
17:07:08 -!- spiette has quit (Ping timeout: 258 seconds).
17:07:40 <J_Arcane> factorial 2, done with Y, took 25 steps to finish expanding, and it practically doubled each time from there ...
17:09:49 <elliott> really you should look at Y in a lazy language
17:09:55 <elliott> you cannot write the real Y in scheme
17:10:14 <elliott> (you can write a similar but not identical fixed-point combinator though, which is probably what you did)
17:11:09 <J_Arcane> elliott: Yeah. That's true. I should try it in Lazy Racket.
17:11:38 <elliott> I'd recommend a toy symbolic lambda calculus reducer if you have one lying around
17:11:38 -!- GeekDude has quit (Client Quit).
17:11:43 <elliott> that way you get to implement arithmetic too :)
17:15:15 -!- S1 has quit (Quit: S1).
17:15:20 <J_Arcane> elliott: Church numerals broke my brain.
17:15:50 <elliott> it's representing n as \f x. f^n(x), if that helps any
17:16:44 <J_Arcane> Well, part is also that I wasn't really clear on what the . means in that notation.
17:16:56 <Bicyclidine> it means the parameter list is over and you're onto the body.
17:17:00 <J_Arcane> But the idea of representing numerals even as functions.
17:17:11 <Bicyclidine> \f x . f^n(x) = (lambda (f x) ((power f n) x))
17:17:24 <J_Arcane> (bear in mind I washed out of the math track at trig proofs in pre-calculus)
17:17:35 <Bicyclidine> well, except you have the implicit whatever, so it's (lambda (f) (lambda (x) ((power f n) x)))
17:17:55 <Taneb> Lambda Calculus is not very similar to trig
17:18:10 <elliott> thankfully, lambda calculus is programming, not calculus
17:18:11 <Bicyclidine> http://dkeenan.com/Lambda/ you might be interested in
17:18:24 <Bicyclidine> Taneb: in american schools, at least, trig is when they introduce proofs.
17:18:29 <J_Arcane> Hmm. Racket's timing function doesn't really seem to behave with #lang lazy, but it does appear more efficient there.
17:18:41 <elliott> J_Arcane: you'll want to change the combinator
17:18:53 <elliott> since what you have does not diverge in call-by-value Racket, it cannot be Y
17:18:56 <J_Arcane> elliott: Yup. Back to the one-true form. :)
17:19:05 -!- spiette has joined.
17:19:21 <Taneb> I'm doing a half-hour talk on lambda calculus next week
17:19:46 <J_Arcane> (define Y (λ(f)((λ(x)(f (x x)))(λ(x)(f (x x)))))), instead of having to wrap it in an extra lambda.
17:20:45 <elliott> you can read that mess but not (\f.(\x.f (x x))(\x. f (x x)))? :)
17:20:50 -!- `^_^v has joined.
17:21:26 <Bicyclidine> does (define (fix f) (letrec ((g (f g))) g)) work
17:21:33 <J_Arcane> :D Well, Lisp is kinda my thing.
17:21:38 <elliott> Bicyclidine: maybe in a lazy language
17:21:55 <J_Arcane> Bicyclidine: Dunno, let's find out. :D
17:21:56 <elliott> it's not Y though of course
17:21:58 <Bicyclidine> well, yes, i thought arcane was using lazy racket now.
17:22:22 <Bicyclidine> you have letrec. shouldn't bother with that nested lambda garbage if you don't have to, mon.
17:22:57 <elliott> Bicyclidine: well, yeah, you should, if your interest is Y (and not fixed-point combinators)
17:23:09 <elliott> all that fix tells you is how to piggyback on the implementation's value recursion
17:23:32 <elliott> Y is the real magic, since it is a non-recursive definition of recursion
17:23:52 <Bicyclidine> it's pretty gross in lambda calculus too. BLA
17:23:57 <elliott> Y = \f. F F where F = \x. f (x x) is pretty nice!
17:24:08 <elliott> use M for Y = \f. M (\x. f (x x)), clearly
17:25:06 <Bicyclidine> (let ((f (lambda (x) (f (x x))))) (f f)) i guessk
17:25:21 <Bicyclidine> no, that's wrong. in my defense i just woke up
17:25:38 <J_Arcane> Bicyclidine: Yes, (define (fix f) (letrec ((g (f g))) g)) works in Lazy, as does the purely anonymous Y.
17:26:40 <Bicyclidine> "The Imitation Game is at its best when it focuses on the collision between cryptography and proto-programming. The film’s efforts to function as a character study, on the other hand, are decidedly clumsy, with Cumberbatch working a little too hard at making Turing a socially inept robot who learns how to pass as human."
17:27:06 <Bicyclidine> lol they gave it a worse review than the penguin movie
17:27:39 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:28:30 <J_Arcane> elliott: It's the "non-recursive definition of recursion" part oddly, and seeing how it expanded, that sort of made sense of it for me. I've read several tutorials now, and they all tend to walk through the proof with intermediate incomplete definitions, which my brain somehow didn't follow so well until I saw it in action.
17:29:13 <elliott> I think the best way to see it is to prove that the (x x) is = Y f
17:29:18 <elliott> and then the whole definition is clear
17:29:32 <elliott> easier said than done, though
17:31:01 <J_Arcane> Ahahaha: http://rosettacode.org/wiki/Y_combinator#BlitzMax
17:31:53 <elliott> Bicyclidine: penguin movie?
17:32:31 <Bicyclidine> elliott: Penguins of Madagascar, it's an animated kids movie
17:32:42 <J_Arcane> BlitzMax is the 'game programming' version.
17:33:09 <elliott> sounds better than "cumberbatch as gay autistic: the inevitable trainwreck"
17:33:23 <Bicyclidine> i donated a book on game programming in blitz basic to my middle school!!
17:33:29 <J_Arcane> Bicyclidine: I did a monologue from Breaking the Code in college acting.
17:34:39 <J_Arcane> A combinator engine in TCL: http://wiki.tcl.tk/4833
17:38:59 <Bicyclidine> "It’s a very trendy take on a legendary figure, likely to look far more dated in decades hence than Breaking The Code does now."
17:39:06 -!- nycs has joined.
17:41:52 -!- `^_^v has quit (Ping timeout: 250 seconds).
17:51:52 -!- shikhout has changed nick to shikhin.
17:57:47 -!- tlewkow has quit.
18:02:47 -!- tlewkow has joined.
18:04:51 -!- tlewkow_ has joined.
18:04:53 -!- ZombieAlive has joined.
18:07:37 -!- tlewkow has quit (Ping timeout: 256 seconds).
18:20:38 -!- dts has joined.
18:21:34 -!- mihow has joined.
18:40:30 -!- GeekDude has joined.
18:40:31 -!- GeekDude has quit (Changing host).
18:40:31 -!- GeekDude has joined.
18:44:21 -!- tlewkow_ has quit (Remote host closed the connection).
18:44:56 -!- tlewkow has joined.
18:45:01 -!- tlewkow has quit (Remote host closed the connection).
18:45:07 -!- tlewkow has joined.
18:47:00 -!- Sprocklem has joined.
18:48:53 -!- dts has changed nick to dTS.
19:20:55 -!- Sprocklem has quit (Ping timeout: 240 seconds).
19:22:36 -!- Sprocklem has joined.
19:25:52 -!- HackEgo has quit (Ping timeout: 250 seconds).
19:28:42 -!- tlewkow_ has joined.
19:29:00 -!- Sprocklem has quit (Ping timeout: 265 seconds).
19:29:37 -!- tlewkow has quit (Read error: Connection reset by peer).
19:38:47 -!- Dulnes has joined.
19:38:52 -!- tlewkow_ has quit (Remote host closed the connection).
19:39:10 -!- tlewkow has joined.
19:39:12 -!- MoALTz_ has quit (Quit: Leaving).
19:39:21 -!- tlewkow has quit (Remote host closed the connection).
19:41:34 <Dulnes> Wtf is this prediction of 2023
19:44:19 <Bicyclidine> castrating squirrels will finally be recognized as the united states's national sport.
19:50:13 -!- Sprocklem has joined.
20:02:16 -!- Sprocklem has quit (Ping timeout: 250 seconds).
20:03:28 -!- Patashu has joined.
20:26:06 -!- Patashu has quit (Ping timeout: 250 seconds).
20:26:26 -!- tlewkow has joined.
20:28:37 -!- nanyyyyy has joined.
20:32:30 -!- nanyyyyy has left.
20:36:09 -!- AnotherTest has joined.
21:02:01 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
21:24:45 -!- GeekDude has joined.
21:45:39 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=41156&oldid=40931 * AndoDaan * (+3802) Added BLSQ implementation for MNNBFSL
21:48:13 -!- AndoDaan has joined.
21:51:36 -!- shikhout has joined.
21:55:23 -!- shikhin has quit (Ping timeout: 250 seconds).
22:04:33 -!- Dulnes has quit (Quit: Connection closed for inactivity).
22:04:37 -!- AnotherTest has quit (Remote host closed the connection).
22:08:25 -!- dTS has changed nick to dts.
22:12:57 -!- tlewkow has quit (Remote host closed the connection).
22:14:01 -!- ^v has joined.
22:25:35 -!- tlewkow has joined.
22:28:46 -!- Dulnes has joined.
22:28:51 <HackEgo> [wiki] [[Special:Log/newusers]] create * Keerthanakumar * New user account
22:30:05 <HackEgo> [wiki] [[DNA-Sharp]] http://esolangs.org/w/index.php?diff=41157&oldid=41131 * Keerthanakumar * (+10) /* Hello World Program */
22:34:02 <HackEgo> [wiki] [[Special:Log/newusers]] create * Blight * New user account
22:36:36 -!- tlewkow has quit (Remote host closed the connection).
22:36:58 -!- nycs has quit (Ping timeout: 255 seconds).
22:51:12 -!- bb010g has joined.
23:01:33 -!- oerjan has joined.
23:02:36 <lambdabot> int-e said 10h 28m 21s ago: today I learned that runhaskell is not good for testing haskell programs, because its buffering of stdout is wrong.
23:02:36 <lambdabot> int-e said 7h 33m 35s ago: PS: by "today I learned" I meant that today was the first time that I profited from that fact rather than finding out that my oh-so-cleverly-optimized program didn't work on anagol.
23:04:00 <oerjan> @tell int-e i've also found that buffering can be difficult; in particular erroring out at the end doesn't work well with interact.
23:04:07 -!- HackEgo has joined.
23:05:13 <oerjan> @tell int-e <int-e> because ... it works for the examples, so it's quite tempting <-- um no it doesn't? not with the wrapping that's easy for me at least, see the logs where i discussed how removing that check made test cases fail.
23:06:19 <oerjan> @tell int-e i don't think i'm presently cheating at all.
23:06:45 <oerjan> @tell int-e oh wait, except for added final space.
23:06:55 <AndoDaan> just in case: http://golf.shinh.org/checker.html can run any anagol language, and you can give your own input.
23:06:59 -!- S1 has joined.
23:07:31 <oerjan> AndoDaan: i know. i find it awkward that it doesn't accept the program as a form, though.
23:08:20 <oerjan> also, when i _do_ try to submit a file that way, i find that the file is locked until i leave the result page...
23:08:45 <oerjan> AndoDaan: the usual submission form on problems allows you to paste code directly.
23:09:39 <fizzie> I was annoyed by that today. Or yesterday.
23:10:08 <oerjan> since i keep all my golfing in one file it's rather awkward to submit as a file, although i suppose it's still useable for speed testing.
23:10:11 <AndoDaan> write a program that takes the input and saves it to a temp file. Since exec isn't denied you can then have your program run that temp cod.
23:10:13 <AndoDaan> write a program that takes the input and saves it to a temp file. Since exec isn't denied you can then have your program run that temp code.
23:11:00 <oerjan> AndoDaan: but that would ruin it for speed testing _too_
23:11:17 <oerjan> since you then get additional compilation.
23:12:15 <AndoDaan> but idk, i never really consider how fast my code runs.
23:12:33 <AndoDaan> I vague remember it being a problem once.
23:12:56 <fizzie> I find it annoying when all the "clever" bits get obsoleted due to something that's both simpler and shorter.
23:13:18 -!- nooga has quit (Ping timeout: 272 seconds).
23:13:20 <oerjan> AndoDaan: my main reason for doing it would be if i am _constructing_ a golf problem, in which case it would be rather important to check that it's actually possible to solve in the allotted time (my half-designed idea has trouble with this...)
23:14:08 <AndoDaan> ah, the power of a little randomness.
23:14:53 <AndoDaan> or bruteforce. I'm trying that with bitwise counting.
23:14:54 -!- vanila has joined.
23:15:07 <fizzie> (Also I seem to have gotten slightly stuck at the current length of this thing. I've got some minor variations, but they're all of identical length.)
23:16:57 <oerjan> fizzie: annoyed by which of those things?
23:17:06 <vanila> How about deleting all brainfuck derivatives from the wiki
23:17:22 <fizzie> oerjan: The fact that the performance checker page lacks the form submission option.
23:18:15 <fizzie> I generally keep problems in separate files, but also tend to have lots of miscellaneous cruft and notes in the files.
23:18:21 <oerjan> vanila: i have vaguely had popped up in my mind an idea to move them into their own namespace >:)
23:18:25 <vanila> Could there be a preference that hides them all
23:18:32 <vanila> namespace would be good
23:18:46 -!- tlewkow has joined.
23:18:52 <fizzie> And Burlesque (as far as I know) doesn't even have comments. I've used "this is a comment"vv but it's visually slightly distracting.
23:18:58 <oerjan> however this would ruin our traditional wikigame
23:18:58 <vanila> http://esolangs.org/wiki/MNNBFSL
23:19:02 <vanila> http://esolangs.org/wiki/DNA-Sharp
23:19:15 <vanila> i just swa recetn adds to the wiki
23:21:24 <vanila> http://esolangs.org/wiki/Talk:TrivialBrainfuckSubstitution
23:21:29 <vanila> http://esolangs.org/wiki/Category:Brainfuck_equivalents
23:21:40 <vanila> there are very few "braifuck equivalent"
23:22:05 -!- AndoDaan has quit (Ping timeout: 245 seconds).
23:22:56 <vanila> Random page => probably a BF derivative
23:23:02 <vanila> language list => hard to see past BF derivatives
23:23:25 -!- tlewkow has quit (Ping timeout: 265 seconds).
23:24:29 <vanila> there's probably not a good solution
23:24:53 <oerjan> vanila: but that random page is what our wiki game depends on :P
23:25:24 <oerjan> hm what was the scoring mechanism again
23:25:37 <oerjan> i'm pretty sure it was -1 point per bf derivative
23:25:56 <elliott> it was +1 point for non-BF derivative
23:26:25 <elliott> drinking game variant: drink as much as your points when you hit one
23:26:58 <oerjan> "join esolang, the wiki with the most lethal drinking game!"
23:27:11 -!- tlewkow has joined.
23:27:55 <elliott> well, we already have TURKEY BOMB
23:28:13 <elliott> we need to play that at an #esoteric meetup
23:28:18 <Taneb> How do you count, eg, MIBBLLII?
23:28:30 <vanila> we should make a monthly esoteric magazine
23:28:47 <vanila> just collect up some unusal stuff from the wiki or something
23:28:56 <vanila> which would not easily be found by random
23:29:19 <vanila> http://esolangs.org/wiki/Category:Brainfuck_derivatives
23:29:30 <vanila> http://esolangs.org/wiki//%CB%88%C3%A6mbi%CB%90%C9%9Bf/ i like this one
23:29:37 -!- spiette has quit (Ping timeout: 255 seconds).
23:29:50 <vanila> also that brainfuck restricted to bits is equivalent to normal bf
23:30:32 <oerjan> vanila: um we are too lazy to make a monthly magazine. we cannot even manage a monthly featured article...
23:31:24 <vanila> One of the best-known esoteric programming languages, brainfuck
23:31:55 <oerjan> hm maybe it's bad to have that as featured article too long.
23:32:10 <oerjan> it would seem likely to _encourage_ derivatives.
23:32:19 <vanila> I changed my mind and now like BF derivatives
23:32:34 <oerjan> (derivatives were a problem long before the feature, though.)
23:32:39 <elliott> vanila: do you like my BF derivative
23:32:48 <elliott> wait I have two arguably, fuck
23:33:19 <elliott> fizzie did you break https or is my connection broken
23:33:31 <vanila> suddenly esolang wiki is stopped working
23:33:39 -!- Phantom_Hoover has joined.
23:33:46 <oerjan> i was going to ask the same, i was trying to check that i hadn't remembered wrong which language is featured
23:33:59 <vanila> I guess too many connnections at once (3)
23:34:11 -!- AndoDaan has joined.
23:34:28 <elliott> vanila: considering it's on a "free" VPS... yeah.
23:34:37 <FireFly> oerjan: just automate the monthly magazine
23:34:57 -!- HackEgo has quit (Remote host closed the connection).
23:35:04 <FireFly> Special:Random and some stitching-together
23:35:08 -!- HackEgo has joined.
23:35:25 <oerjan> the previous featured language was Deadfish, which was the april fools issue. except i think it was _last_ year's april.
23:35:35 <FireFly> Oh, I guess the point was precisely to not Special:Random.. oh well
23:35:36 -!- bronson has joined.
23:35:44 <elliott> vanila: https://esolangs.org/wiki/Brainfuck/w/index.php%3Ftitle%3DTalk:Brainfuck/index.php https://esolangs.org/wiki/Not_a_brainfuck_derivative
23:35:49 <oerjan> FireFly: well i guess we can automatically exclude bf derivatives, at least
23:36:09 <FireFly> Or at least delegate them to an appendix
23:36:10 <vanila> Is there any more information about Not a brainfuck derivative??
23:40:52 -!- bronson has left ("Leaving").
23:44:57 <HackEgo> [wiki] [[Janus]] M http://esolangs.org/w/index.php?diff=41158&oldid=41153 * Cluid Zhasulelm * (+478) more information
23:47:10 -!- tlewkow has quit (Remote host closed the connection).
23:48:53 <oerjan> soon the mccarthy function problem will expire, i have no clue how the others got it so short :(
23:49:22 <vanila> whydon't you put that ^ as the featured langauge?
23:49:28 <vanila> if you want to get branfuck off the frontpage
23:50:08 <oerjan> there is a candidate list
23:50:38 <elliott> we should get rid of the process and go back to my original idea
23:50:43 <elliott> which was that sysops would just put whatever they like there
23:51:00 <oerjan> http://esolangs.org/wiki/Esolang:Featured_languages/Candidates
23:51:02 <elliott> that wasn't ~~democratic~~ enough for some people who afaik never participated in the process though
23:51:10 -!- tlewkow_ has joined.
23:51:44 <vanila> yes sysops should do it imo
23:51:45 <oerjan> elliott: i'm pretty sure brainfuck was selected completely outside the "democratic" process
23:52:04 <elliott> oerjan: no, it was on the list
23:52:22 <oerjan> well some languages were, anyway
23:52:31 <elliott> the age of those candidates should show how useful community input is on a wiki as tiny as this one
23:53:23 <oerjan> elliott: what is needed is for the proposers to do more of the actual work too >:)
23:53:41 <elliott> oerjan: then we will have even fewer featured languages
23:55:21 <oerjan> what do you say we do funciton next, it's pretty and pretty much the opposite of brainfuck in every way
23:56:14 <oerjan> it's new rather than old, visual rather than textual, functional rather than imperative
23:56:41 <HackEgo> [wiki] [[Esolang:Featured languages/Candidates]] http://esolangs.org/w/index.php?diff=41159&oldid=37409 * AndoDaan * (+100) /* List of candidates */
23:57:01 <oerjan> vanila: i didn't agree.
23:57:08 <vanila> so we're all agreed, hth
23:57:15 <FireFly> elliott: er, not terribly new
23:57:25 <FireFly> At least a couple of years old
23:57:29 <oerjan> elliott: relatively new, compared to brainfuck.
23:57:30 <elliott> yes I was just wondering about oerjan's definition
23:57:32 -!- tlewkow_ has quit (Remote host closed the connection).
23:57:43 <oerjan> i'm thinking before/after i joined here split, sort of :P
23:59:11 <elliott> % grep '<oerjan>' ????-??-??.txt | head -n 1
23:59:11 <elliott> 2006-06-13.txt:00:38:54: <oerjan> hi gregorR
00:00:24 <elliott> I like how I first joined in 2006 but left seconds later because there were lots of people and it was scary
00:00:27 <elliott> and then came back half a year later
00:01:22 -!- tlewkow has joined.
00:01:22 -!- tlewkow has quit (Client Quit).
00:01:34 <oerjan> elliott: at least it hasn't yet been longer since i joined than 1993 is before it
00:01:56 <elliott> when were you actually born
00:02:19 <elliott> when you said 1993 I instantly assumed it was your birth year until I realised that can't be true
00:02:29 <oerjan> i'm older than INTERCAL you young whippersnappers!
00:02:34 -!- tlewkow has joined.
00:02:48 <Taneb> I'm not even older than brainfuck
00:04:01 <elliott> vanila: I don't know what we're agreeing on but yes
00:04:36 -!- S1 has quit (Quit: S1).
00:04:47 -!- tlewkow_ has joined.
00:04:59 <oerjan> vanila: O KAY SINCE YOU ISNIST
00:05:13 * oerjan gave up typing that correctly
00:05:19 <elliott> gonna backdoor all the RNGs
00:05:52 <oerjan> vanila: it has always been the sysops selecting _from_ the candidates, when we actually got around to it.
00:06:06 <oerjan> (i probably wasn't a sysop when it started)
00:06:36 <AndoDaan> Can someone explain how different languages can use rand to solve the Wow problem?
00:06:41 <Taneb> One of my housemates in the shower, and I am very confused
00:06:46 <FireFly> 1970, isn't that literally the beginning of time?
00:06:49 <Taneb> Who showers just after midnight?
00:07:01 <Taneb> Other than one of my flatmates
00:07:15 <oerjan> AndoDaan: Wow is based on a very common random number generator
00:07:16 <Taneb> I'm in a house, not a flat, I keep forgetting that
00:07:37 -!- tlewkow has quit (Ping timeout: 244 seconds).
00:07:49 <FireFly> Do you look down on flatlanders?
00:07:50 <oerjan> namely, the one in libc iiuc
00:07:53 <AndoDaan> and most languages have it implemented?
00:08:22 <oerjan> AndoDaan: many languages probably just call out to libc for randomness
00:09:18 <elliott> oerjan: I think I threatened to op you so that you'd have to select a candidate at one point
00:09:25 <elliott> vanila: fizzie oerjan me ais523 are the active ones
00:09:31 <vanila> I nominate elliott to do this then
00:09:42 <elliott> how about I promote you and you do it instead
00:09:59 <Taneb> What are we selecting candidates for?
00:10:04 <vanila> would oerjan like to do it? else I shall bother ais and fiz
00:11:10 <oerjan> vanila: http://esolangs.org/wiki/Esolang:Administrators most of the people on the first half are rarely around these days.
00:11:35 <vanila> ok, delete them please
00:12:12 <oerjan> Gregor is only an admin because he's hosting the server, he's not really active inside the wiki.
00:12:18 <elliott> vanila: https://i.imgur.com/rn0MuWV.png be afraid
00:12:50 <oerjan> vanila: we cannot delete chris pressey that would be blasphemy hth
00:13:25 <elliott> actually I agree with vanila, we should assassinate the old guard
00:13:45 <vanila> If Cluid is made Admin they will likely put Janus as featured language based on their edit history
00:14:24 <oerjan> Gregor: yes, but i think you only agreed to host the wiki on the promise others would do most of the work right? :P
00:14:42 <Gregor> Except replace "most" with "all"
00:15:17 <oerjan> Gregor: well i assume you might still want to keep the server alive since you use it for other stuff...
00:16:55 <Taneb> What are the responsibilities of esolangs.org admin?
00:17:35 <elliott> Taneb: international espionage, drug smuggling and mail merges
00:18:40 <Gregor> It runs on HP-UX 11, so occasionally you've got to go in to update that too.
00:18:58 <oerjan> AndoDaan: i don't think the fact it uses libc _intrinsically_ means C has to win, since other languages may still give better syntactic sugar for whatever is needed. they just didn't, this time.
00:19:32 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41160&oldid=41124 * 70.24.86.251 * (+1556) updated documentation for newer, hopefully last, version of interpreter
00:21:02 <vanila> i want to make 'meta' pages maybe that give overviews of thinsg
00:21:13 <vanila> having just a huge long list of languages is a bit hard to make use of, since the loudest ones win (i.e. bf derivatives)
00:21:43 <elliott> vanila: I like it when people highlight languages they like on their user pages
00:22:39 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41161&oldid=41160 * Orenwatson * (+4) corrected example a little.
00:25:20 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
00:25:37 -!- ^v has joined.
00:35:17 <AndoDaan> oerjan, so like,maybe I could have burlesque pick 765 or so random numbers between 32 and 127 and maybe just maybe I wont have to add "%95" and all that chaff.
00:36:19 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41162&oldid=41161 * Orenwatson * (+0) example was still a little wrong.
00:38:05 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41163&oldid=41162 * Orenwatson * (-26)
00:53:07 <oerjan> AndoDaan: well it's a little unlikely the burlesque uses the right RNG since it is written in haskell and the haskell versions need to use the ffi to get the right random numbers...
00:57:49 <vanila> there still isn't a new featured language on the wiki
00:57:58 <elliott> oerjan has been slacking off
00:58:26 <oerjan> wait this wasn't what i agreed to, was it?
00:58:32 <vanila> I thought we all agreed?
00:58:56 <oerjan> yes, but you started before my name was mentioned hth
01:00:31 * oerjan was about to capitalize i for emphasis
01:00:35 <int-e> oerjan: ok, if you're not cheating (whitespace doesn't count) then I'm missing some trick :)
01:01:02 <int-e> oerjan: I had to change the search order slightly to make the wrapping cheat work
01:01:25 <oerjan> i tried two options and neither worked.
01:01:43 <oerjan> (one worked on just the 1st and 3rd test case)
01:02:06 <int-e> I tried two options and one worked? or perhaps ... let me double check
01:03:28 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
01:03:51 <oerjan> ...what i changed has nothing to do with the search order.
01:04:30 <oerjan> which makes it really mysterious why one option worked differently than the other. unfortunately i didn't save those attempts.
01:05:16 <oerjan> never mind, if my algorithm is beating you overall...
01:06:06 <int-e> right, time for the cheat.
01:06:20 <int-e> (since I'm finally satisfied with my encoding)
01:07:25 <oerjan> sic transit gloria mundi
01:08:32 <oerjan> fizzie: int-e just beat you hth
01:19:08 -!- zzo38 has joined.
01:20:14 -!- shikhout has quit (Ping timeout: 264 seconds).
01:23:30 -!- olsner has quit (Ping timeout: 240 seconds).
01:24:06 -!- olsner has joined.
01:29:42 <oerjan> int-e: you were right, changing order helped
01:29:51 <oerjan> once i found the right spot to do it
01:32:01 <oerjan> although the point of a half-cheating solution that doesn't actually win may be considered dubious
01:32:51 -!- mihow has quit (Quit: mihow).
01:38:12 <int-e> that's interesting though; I only have one binary choice for the searching order in total.
01:39:04 <oerjan> as i said, what i thought was changing searching order previously was probably just introducing a bug that caused it to always fail
01:40:23 <elliott> oerjan: do we have a new featured language yet
01:40:46 <oerjan> i don't think you've ever managed to make me write a blurb hth
01:41:22 <oerjan> (this is incidentally the part i think the proposers might do)
01:41:35 <elliott> btw I'm not sure janus would be a great feature since probably its authors don't consider it esoteric :/
01:41:54 <oerjan> wait was janus what we all agreed to
01:42:03 <oerjan> in that case, i retract my agreement
01:43:03 <oerjan> i think this is an appropriate thing to be two-faced about hth
01:43:24 <vanila> it doesn't have to be janus
01:44:25 <oerjan> i don't think Rail is esoteric, or do we have a language called that
01:44:33 -!- Dulnes has quit (Quit: Connection closed for inactivity).
01:44:53 <elliott> hitting random about six times gave me esme
01:45:04 <elliott> it's almost april 2015 and we're really late for april 2014
01:45:11 <oerjan> elliott: i think that's a definite April feature
01:45:14 <AndoDaan> and it is really well documented.
01:45:41 <elliott> the scariest part of the esme article is This article is a stub, which means that it is not detailed enough and needs to be expanded. Please help us by adding some more information.
01:46:13 <vanila> I think Janus is esoteric
01:46:49 <elliott> clue is a great language and pretty unusual for an esolang and it has a good article with examples, though unfortunately no implementation that's on the web :/
01:47:11 <elliott> vanila: I think so too but there's a degree to which "esoteric" is a self-applied thing
01:47:42 <elliott> it's definitely like, on-topic for the wiki but singling it out as representative of esolangs could be odd if it wasn't intended that way
01:48:43 <elliott> vanila: have you seen Most ever Brainfuckiest Fuck you Brain fucker Fuck
01:48:45 <elliott> that's the best bf derivative
01:48:58 <Bicyclidine> i don't think it's eeven in any categories
01:49:13 <Bicyclidine> luckily it's pretty easy to find, since "Brainfuckiest" isn't a common term
01:49:20 <elliott> https://esolangs.org/wiki/Most_ever_Brainfuckiest_Fuck_you_Brain_fucker_Fuck
01:49:20 <vanila> How to write a good Clue implementation?
01:49:23 <elliott> it's like the easter egg of the wiki
01:49:50 <elliott> vanila: brute force, more or less; the restricted structure of branching/recursion and the fact that you get specified every part that should be used to build it in the bag makes brute forcing pretty easy
01:49:57 <elliott> I think the article describes pretty much the entire algorithm
01:50:44 <elliott> basically it brute forces a program structure from a very simple template given all the parts that aren't the structure and a specification to check against
01:55:44 <oerjan> you know, i don't think i've read that Most ever Brainfuckiest Fuck you Brain fucker Fuck article properly before
02:04:03 -!- Tod-Autojoined has changed nick to TodPunk.
02:04:24 -!- PatriciaM has joined.
02:06:20 -!- PatriciaM has left.
02:17:01 -!- tlewkow_ has quit (Remote host closed the connection).
02:22:28 <int-e> there. *now* I'm beating fizzie
02:22:42 <int-e> cheating, of course.
02:22:53 <oerjan> int-e: um i thought you already did
02:23:09 <int-e> check the language list at the bottom
02:33:38 <vanila> https://esolangs.org/wiki/Main_Page cool! Someone updated the Featured Language bit
02:35:03 <elliott> vanila: you're getting very close to a promotion here :P
02:40:16 -!- adu has joined.
02:41:42 <vanila> oerjan, thoughts on Janus
02:47:19 -!- adu has quit (Quit: adu).
02:47:39 -!- adu has joined.
02:51:16 -!- dts has quit (Read error: Connection reset by peer).
02:51:38 <Bicyclidine> what's racket's call/cc for delimited continuations thing called again? call/ec?
02:51:58 <vanila> but maybe you dont mean that?
02:52:59 <vanila> http://esolangs.org/wiki/AttoASM
02:53:15 <Bicyclidine> reset and shift might be better actually, thanks
02:55:15 -!- dts has joined.
02:56:42 <MDude> I think the reversible language idea I mentioned earlier would be better described as a language made for a type of WPU.
03:06:04 <MDude> "AttoASM is a language designed for the AttoWPU experimental processing unit, as part of the WPU (Weird Processing Unit) concept. "
03:06:50 -!- dts has quit (Ping timeout: 240 seconds).
03:12:49 -!- ^v has quit (Ping timeout: 258 seconds).
03:18:34 -!- dts has joined.
03:29:22 <oerjan> oh the pendulum, i remember reading about that
03:30:07 <Bicyclidine> right, i was confusing delimited continuations with escape continuations.
03:30:37 <Bicyclidine> luckily delimited continuations do not make sense to me. how to implement them, or why you'd use them
03:30:55 <vanila> they're difficult to implement!
03:31:52 <vanila> oerjan, is it acceptable
03:33:21 <oerjan> i've not got to janus yet
03:33:21 <vanila> you mentioned that the authors dont consider it eso
03:33:58 <vanila> i dont mean for the feature thing just being on the wiki at all
03:34:12 <oerjan> i'm not going to accept a language that has just been added to the wiki, even if it's esoteric.
03:34:14 <elliott> janus is definitely on topic for the wiki
03:35:47 <oerjan> litmus test: it should have been long enough on the wiki that i only remember it because it was actually interesting...
03:37:20 <oerjan> so's the pendulum. although what happened to that Honorary Esolang category idea.
03:44:17 -!- dts has quit (Read error: Connection reset by peer).
03:45:12 <HackEgo> [wiki] [[MNNBFSL]] M http://esolangs.org/w/index.php?diff=41164&oldid=41156 * Oerjan * (-1) superfluous blank line
03:45:48 -!- dts has joined.
03:48:51 -!- adu has quit (Quit: adu).
03:51:52 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41165&oldid=41163 * Oerjan * (+1) another one, and bullets
03:53:31 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41166&oldid=41165 * Oerjan * (+6) /* External Resources */ um, or maybe like this
04:10:56 <AndoDaan> Thanks, oerjan. Question. If I wwere to set my mind to investigate whether MNNBFSL was TC or not... should I start by trying to implement some basic BF algorithms in MNNBFSL?
04:14:05 -!- dts has quit (Read error: Connection reset by peer).
04:16:41 <vanila> maybe you could compile a language like WHILE into it
04:19:28 <oerjan> eek, mixing http and https does nothing good for visited links coloring :(
04:20:10 <vanila> im plying with MNNBFSL
04:20:14 <int-e> Translating Brainfuck itself should work.
04:20:40 <oerjan> vanila: there is no language WHILE on the wiki
04:21:17 -!- AndoDaan has quit (Read error: Connection reset by peer).
04:21:20 <oerjan> that makes it very unlikely to be small enough to be easily used for this.
04:21:22 -!- AndoDaan_ has joined.
04:22:29 <int-e> Ah, the stacks start out empty, that makes things a bit trickier than I thought.
04:22:43 <oerjan> you basically want the simplest already known-TC language that fits as well as possible
04:22:48 <vanila> [< puts 0 on the data stack
04:23:19 <vanila> at the start of program
04:23:23 <vanila> [< puts 3 on the data stack
04:23:24 <int-e> vanila: That's the easy part. But it means that some special handling is required to extend the tape.
04:23:49 <oerjan> you don't need two-sided infinite for bf
04:23:58 <vanila> i could put any numbers onto the data stack
04:25:05 <int-e> vanila: I didn't say it was an obstacle, it's just a complication.
04:27:12 <vanila> I wonder how to compile recursive functions
04:27:40 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:28:00 <vanila> calling convention for main loop: [function number][arg1][arg2].. ..stack bottom|
04:28:41 <vanila> at any point in code you can push a value onto the stack using [<--------- or [<++
04:29:12 <oerjan> vanila: you can only easily push values close to the PC value, though.
04:29:25 <vanila> but thendo + or - lots, it will be inefficient but I dont mind
04:29:58 <oerjan> vanila: that will give an at _least_ exponentially growing program
04:30:18 <oerjan> well i'm not saying it won't work, but there has to be a more convenient way
04:30:38 <int-e> and there's actually something funny here ... one cannot use [<++++... to push a later address on the stack. So you need a loop (which is entirely possible) to circumvent that.
04:31:33 <AndoDaan_> as long as the top of the dStack is positive, any value on the top of the rStack sets the ip.
04:32:03 <vanila> a later address on the stack?
04:32:05 <oerjan> [<+[-"] does that work?
04:32:41 <vanila> it would require infintely many +'s
04:33:04 <int-e> oerjan: I mean a pointer into the program.
04:33:26 <oerjan> int-e: i'm still at the earlier question of how to push small values
04:33:29 <int-e> <code for pushing address of a> ... <a comes here>
04:33:54 <int-e> just [< followed by some adjustments.
04:34:20 <oerjan> well +[-"] is meant to zero a non-negative value
04:34:21 <int-e> it may result in some big programs but it'll work in principle :)
04:34:51 <int-e> without having tried, yours looks like it is a position-independent zero, yeah.
04:35:57 <int-e> MNNBFSL PIC. hmm hmm.
04:38:21 <elliott> there's no one-cell way to do 0 -> 1; 1 -> 0; anything else -> irrelevant in BF, is there?
04:38:38 <oerjan> hm you cannot skip code without knowing the address
04:39:22 <oerjan> if you have any loop, you end up with a constant.
04:39:32 <oerjan> if you don't have any loop, you're obviously adding one.
04:39:34 <elliott> so emulating boolfuck with bf is kinda wasteful
04:39:45 <int-e> oerjan: well, perhaps you could have meta-opcodes that check a flag to see whether they should be executed or not.
04:40:06 <int-e> so they all skip ahead by a small, fixed amount
04:40:37 -!- MDude has changed nick to MDream.
04:40:49 <int-e> but I see no big deal in having to know the (relative) address of the target
04:41:05 <oerjan> i'm assuming this language has bignum cells
04:41:07 <vanila> http://lpaste.net/raw/115070
04:41:54 <int-e> oerjan: the implementation uses size_t for cells.
04:42:05 <AndoDaan_> the spaces increas the counter and you can use ]<. to output the value.
04:42:10 <int-e> not sure what the intention is. it's written in C after all.
04:42:28 <oerjan> int-e: well without the assumption you're not TC at least
04:42:38 <oerjan> since you cannot jump to arbitrary program spots
04:43:02 <int-e> Btw, funny things happen when you drop " ... I expect it remains TC, but it cannot do any interesting text processing.
04:43:05 <oerjan> AndoDaan_: not if the program is longer than maximal cell size
04:43:15 <int-e> oerjan: all you need is implement one universal TM
04:44:28 <vanila> [+>-<] isnt this to add two numbers?
04:44:44 <int-e> vanila: ] destroys the tested value
04:45:03 <vanila> hm i hav einfinte loop :(
04:45:09 <int-e> ... or do we want [->+<"]
04:45:20 <int-e> looping through all of size_t takes some time
04:45:31 <AndoDaan_> [<">++++++++++"[->+++++++++<"]>sets the top value of the dstack to 100
04:45:49 <vanila> i cant pop without writing to stdout??
04:46:18 <int-e> vanila: yes you can. basically, [], but that's not quite the right offset
04:46:57 <vanila> [<+++++[<[->+<"][]. 5+7 :D
04:48:37 <int-e> Actually, hmm. How do I pop the temporary that I needed to pop a value from the stack? Heh.
04:49:55 <int-e> it's just [-"][] isn't it.
04:50:28 <int-e> and you just did that. [] pops a zero.
04:50:47 <vanila> wait doesn't [] leave garbage on the return stack?
04:50:55 <vanila> after popping a zero off
04:51:02 <oerjan> i prefer +[-"] if we assume unbounded cells
04:51:15 <oerjan> because it doesn't infloop on zero
04:51:20 -!- AndoDaan_ has quit (Ping timeout: 258 seconds).
04:51:22 <int-e> in fact it pops everything up to the first zero on the data stack
04:51:25 <int-e> oerjan: good point
04:51:40 <vanila> omg this langauge is really hard to program in
04:52:15 <int-e> surprising. it looked pretty boring at a glance.
04:55:16 <vanila> i was wondering how to do a switch(function) { case 1: jump f1_code; ... } type thing
04:55:25 <vanila> then I could compile recursive functions to it hopefully
04:55:57 <vanila> the problem int-e mentioned is seriousl though
04:56:10 <vanila> you can't jump over code, so f1_code must be written after this switch
04:56:17 <vanila> that means I cannot use th stupid inefficient number literals trick
04:56:28 <int-e> Set up targets on the return stack, each pointing to a -].
04:57:51 <vanila> i feel like not being able to pop without printing is a problem
04:59:04 <int-e> So there's a viable plan, actually; have a dispatcher at some huge address 4^k, which then jumps back to whatever code fragment is currently being executed.
04:59:10 <int-e> vanila: we can pop without printing
04:59:13 <vanila> I guess you can just past [ by doing <->
05:00:05 <vanila> I think ill need a more efficient way to encode numeric litearls
05:01:01 <int-e> set value to zero, [ pushes something on the return stack, ] pops a zero and something from the return stack, and does nothing.
05:03:08 <vanila> [<+++++[<[->+,"]+[-"][].
05:03:12 -!- ^v has joined.
05:03:15 <vanila> ive got an infiniet loop in my new 5+7 program
05:03:41 -!- Dulnes has joined.
05:04:16 <int-e> what's that comma?
05:04:35 <vanila> i wrote it by accident! I deleted it and still loop
05:04:51 <Dulnes> Quick name an estoric language you've never wanted to try
05:05:03 <vanila> thanks! Now it works perfect
05:05:27 <vanila> this language only supports positive numbers?
05:05:45 <FreeFull> Are there any good esoteric languages that do balanced ternary?
05:06:23 <vanila> Dulnes, I don't want to program in Dulnes Lang
05:08:24 <vanila> <AndoDaan_> [<">++++++++++"[->+++++++++<"]>sets the top value of the dstack to 100
05:08:30 <vanila> does it have any other effects?
05:11:47 <vanila> this is what it gives me
05:12:00 <vanila> if i put some spaces before
05:12:21 <vanila> I wonder how to swap the top two stack elements
05:13:11 -!- ^v has quit (Ping timeout: 258 seconds).
05:14:35 <vanila> http://lpaste.net/115077
05:14:39 <vanila> I gues it could be done like this, if i have subtract
05:16:55 <vanila> that was wrong, i added a right way
05:17:56 -!- tlewkow has joined.
05:18:13 <vanila> how do you do that though?
05:19:57 <Dulnes> Well then out of me field
05:20:17 <Dulnes> Slowly withers and dies
05:20:52 <Dulnes> Hhh this is troublesome ;-;
05:21:45 <int-e> vanila: something like [<[-"]<<+[>>+<<-"][]>- perhaps?
05:22:05 <int-e> vanila: for swapping the top two elements of the data stack.
05:22:15 <vanila> that gave me rstack underflow
05:22:16 -!- tlewkow has quit (Ping timeout: 244 seconds).
05:22:20 <vanila> but maybe im using it wrong
05:22:58 -!- tlewkow has joined.
05:23:09 <Dulnes> i cant put [ example ] and have a [ next to it with a space and it gets all jumbled so [ example ] [ example ] because ] space [ is deleted and it merges the bottom and top lines
05:23:31 <int-e> oh, there's something wrong. [<[-"]<<+[>>>+<<<-"][]>- perhaps.
05:25:11 <int-e> vanila: Perhaps I should just say what the idea is: given a *b, push a zero, a b *0, then add the a to that zero, 0 b *a, finally pop that 0. I'm not certain that I got the directions right.
05:25:37 <int-e> fungot: have you met Dulnes?
05:25:38 <fungot> int-e: so, hey, it was our table! if he's interested! correspondingly, zombies! my day is ruined, you guys.". ahem. one day a big crime is committed and the only guy i've ever felt that long, doctor professor jim junior, and that someone could've been me
05:26:28 <Dulnes> And also charactors such as [] + - , < arent accepted as a space i should just start over
05:26:43 <vanila> http://lpaste.net/115080 i got swapping this way
05:27:13 <vanila> int-e, your way seems much better!
05:27:17 <vanila> using 3 things is much faster
05:30:25 <vanila> https://github.com/yshl/MNNBFSL/blob/master/example/fizzbuzz.bfsl
05:30:27 -!- mitchs has joined.
05:30:42 <vanila> ">[<[-"]<[->+"---[<"[-"]++++[>++++++++<-"][]>]--- <"][]
05:31:01 <mitchs> int-e's idea works with very small change: [<+[< s [<[-"]>>[<<<+>>>-"][]<< s
05:32:17 <vanila> i get that when running it
05:32:30 <Dulnes> [ 12 » 2 » ]+[ integer => 24 ]++[ method]]-[1] none of the + - are working and it just adds [ 12 » 2 ]+[ integer => 14 ]++[ method]]-[0]
05:32:42 <vanila> ther seems a problem with the code
05:32:54 <mitchs> it is 1 3 and then becomes 3 1
05:32:55 * Dulnes is very much done with math
05:33:30 <int-e> mitchs: so I did get the directions wrong. thanks!
05:33:46 <vanila> ok but i cannot run your code correctly?
05:34:02 <vanila> I have to delete [<+[<
05:34:19 <vanila> ok works perfect now :D
05:35:49 <Dulnes> Well then im dumb it was the ++ comments they deleted the method 1 but idk why
05:36:22 <int-e> Sorry, does anybody know what Dulnes is talking about?
05:36:38 -!- adu has joined.
05:36:43 <elliott> is this your first time talking to Dulnes
05:36:48 <Dulnes> I like to talk to myself ;-;
05:37:01 <int-e> elliott: I'm not talking *to* Dulnes, I'm talking *about* Dulnes.
05:37:37 <int-e> elliott: but I think you've answered my question. Thanks.
05:38:00 <Dulnes> I should just make my own language
05:38:29 <int-e> Dulnes: I'd say you're doing just fine with your version of english.
05:38:49 <elliott> Dulnes: do you have any evidence that this weird language you keep quoting code snippets with unbalanced brackets from actually exists
05:39:19 <int-e> Hmm. I'm grumpy, bbl.
05:39:28 <Dulnes> Well i created it so not really i found i dont need balanced brackets
05:39:57 <Dulnes> I should just go back to normal coding :\
05:40:29 <vanila> does this push 0 onto the data stack?
05:43:39 <Dulnes> Elliot is very snippy today he usually never talks to me
05:45:06 <vanila> [<[-"] only works if it isn't at position 0
05:45:07 <mitchs> vanila, yshl is keeping the remainder underneath i and repeatedly incrementing it and comparing with 3
05:45:30 <mitchs> well, a copy of i, which he decrements as he increments the remainder
05:48:20 <fizzie> oerjan: Maybe I'll have to cheat too.
05:49:10 <elliott> Dulnes: btw if you want to ping me it's "elliott"
05:49:14 <mitchs> vanila, it takes effort, but you can read the code piece by piece
05:49:55 <elliott> mitchs: hmm, I know your name from anagol, right?
05:49:57 <mitchs> at line 8, variable i is initially at the top of the data stack
05:50:18 <Dulnes> Ive never noticed that other t :0
05:50:26 <mitchs> hi elliott, yeah that's me :)
05:50:29 <vanila> i wonder how much of my code breaks when values are 0
05:51:22 <elliott> mitchs: coming to spy on all the new golfers' techs
05:51:32 <mitchs> the first two characters (">) duplicates i and puts it on the return stack
05:53:08 <mitchs> well i would look at the live code log from time to time but figured i had something to contribute so joined
05:57:05 <elliott> kind of surprised/unnerved anyone actually uses stalker mode :p
06:00:47 <mitchs> i didn't feel worthy to join for lack of haskell and burlesque knowledge ;)
06:02:24 <oerjan> vanila> [<[-"] only works if it isn't at position 0 <-- well then use [< there hth
06:02:56 <vanila> im writing product now
06:02:59 <vanila> so i can do small products
06:03:15 <fizzie> oerjan: My cheating version timed out on the first submission on test 3, and the performance checker gave it 0.989 and something. Living on the edge here.
06:06:16 <vanila> >>push 0<<[>'[>>+<<-]<-]
06:06:54 <oerjan> fizzie: his dc version still beats you, though >:)
06:07:37 <vanila> does anyone have a way to decompose a number into the form a*b+c with a,b,c smallest?
06:08:02 <fizzie> oerjan: I noticed. I don't have any idea how it's done -- probably something really clever.
06:08:20 <oerjan> vanila: you want a and b to be close to the square root
06:08:21 <mitchs> what do you mean by "a,b,c smallest"
06:08:32 <vanila> well i dont mean anything especially rigorous
06:08:39 <oerjan> although that's probably not an exact rule
06:08:52 <vanila> just make them small so I can emit code of the form push a push b * push c +
06:09:01 <vanila> to encode numerals more efficiently
06:09:21 <oerjan> vanila: have you looked at https://esolangs.org/wiki/Brainfuck_constants
06:09:31 <oerjan> it may be slightly relevant
06:09:45 <oerjan> (the non-wrapping ones)
06:09:49 <vanila> thats the sort of thing i have in mind, im writing a program to do it
06:10:14 <fizzie> oerjan: Even allowing for dc's one-byte commands, I wouldn't be surprised if his dc solution was translatable to something much shorter than I have in Burlesque. :/
06:10:29 <mitchs> you probably are more interested in multiplying by a constant rather than pushing a constant and treating it as a variable
06:10:44 <vanila> multiply by immediate is really important
06:11:37 <oerjan> vanila: you basically only need multiplication by 2 to do binary encoding
06:11:55 <vanila> oh that is excellent I can use binary
06:12:51 <oerjan> that might not always be most compact though
06:12:54 <mitchs> fungot, predict the future of the universe please
06:12:54 <fungot> mitchs: it's so good, dromiceiomimus. do i seem to see them, but they all suspect he's sad. they say " are you alright
06:13:04 <vanila> still its efficient enough for me)
06:13:23 -!- dts has joined.
06:13:45 <mitchs> hmm optimism with a touch of sadness
06:14:26 <oerjan> vanila: the nice thing about calculating all jumps as global addresses is that you then have the return stack free to use for the other half of a tape
06:14:48 <int-e> fungot: well done. that surely brightened my mood :)
06:14:48 <fungot> int-e: so people can bet in-game money to win real-life money?' then tony and louisa q were two people in love! romantic love, but there's a rude jerk, and then they both said the next few days were going to me, the omniscient. the dude has to sleep! superman could laser him from orbit while he's having nappy times! enter only if you have a valid passport to dreamland!"
06:14:49 <vanila> I need to use hard coded addersses
06:15:05 <oerjan> vanila: you might want to code an assembler for this :P
06:17:21 -!- tlewkow has quit (Remote host closed the connection).
06:17:55 <int-e> oerjan: would it be hard to make a minsky machine? with counter operations it's usually easy to undo the effect of a loop, so skipping ahead may not be necessary
06:18:29 <int-e> and you only need a finite amount of stack, assuming unbounded cells.
06:19:26 -!- ^v has joined.
06:20:24 <oerjan> int-e: i dunno, but it seems to me that vanila has got the essential ingredients for brainfuck now
06:20:33 <vanila> its annoyingly hard to do binary
06:20:49 <vanila> numbers like 1011 are ok but ones like 10100000 are annoying
06:21:15 <oerjan> vanila: you mean converting in your head?
06:21:58 <oerjan> vanila: 0 just means you skip an increment
06:22:27 <oerjan> (or before/after, at the end)
06:23:06 <oerjan> > ((0+1)*2*2+1)*2*2*2*2*2
06:24:03 <vanila> my binary ocnverter is broken
06:26:32 <oerjan> vanila: you can do it backwards with recursion. binary(x) = if x == 0 then make a zero else if x is odd then binary(x-1) ++ increment else binary(x/2) ++ double
06:27:11 <oerjan> i think i mixed haskell and pseudocode in maximally confusing way there, hope it's clear
06:27:27 <vanila> http://lpaste.net/115085
06:29:07 -!- dts has quit (Read error: Connection reset by peer).
06:29:50 <oerjan> one minor problem here is that the length of a number representation isn't constant, so you _might_ get complication calculating addresses that depend on each other's representation length...
06:30:07 <oerjan> this can be fixed with padding at worst
06:30:08 <vanila> but thankfully i can pad
06:30:22 <vanila> http://lpaste.net/115087
06:30:24 <vanila> this is what i have so far
06:30:46 <int-e> fizzie: holy cow, what are you spending all this time on!
06:31:19 <int-e> (Well, half-rhetorical question. I can imagine at least one possibility, actually.)
06:33:38 <oerjan> you only need to pad forward references, fwiw
06:34:55 <mitchs> hmm, i wonder if a straightforward-ish translation of daniel b cristofani's dbfi into mnnbfsl would be possible
06:35:08 <vanila> (goto address) => (push-binary address) (emit #\])
06:35:21 <vanila> and then the assembler will work out addresses for all labels
06:35:31 <vanila> and insert gotos with padding
06:35:39 <mitchs> possibly you could keep track of the end of the simulated data array with a marker and expand as necessary
06:40:06 <vanila> i need conditionals I guess
06:40:49 <vanila> if i have goto, conditionals, then maybe using the two stacks I can simulate a fixed number of integer variables and a stack
06:41:13 <vanila> but maybe i should just look for a turing complete stack language to encode
06:41:13 <oerjan> vanila: no, you can simulate an entire brainfuck tape
06:41:19 <vanila> like some kind of minimal forthy thing
06:41:25 <oerjan> two stacks gives a tape
06:41:34 <vanila> id like to use something else than brainfuck
06:41:53 <oerjan> well then you can consider int-e's minsky machine idea
06:42:31 <oerjan> that requires cell values to be really huge, though.
06:42:44 <oerjan> (compared to program size)
06:43:08 <vanila> i should maybe compile recursive functions including mu minimzer
06:43:16 -!- ^v has quit (Ping timeout: 258 seconds).
06:45:09 <oerjan> i guess a minimal forthy thing will work, that also needs both stacks in full
06:46:21 <oerjan> unless you use unbounded integers, but then you're back to recursive functions
06:47:24 <vanila> i can define a table of words by name and they can call each other
06:47:30 <vanila> adn they can manipulate stack
06:48:02 <oerjan> anyway, what you've got + conditionals should give you all you need to construct a lot of possibilities
06:48:23 <mitchs> Dulnes, i'm operating under the idea that Hhh is not an actual word
06:48:27 <oerjan> Bicyclidine: then you're back to the minsky machine
06:48:34 <oerjan> or recursive functions
06:48:45 <Dulnes> That is the sound im making atm
06:49:03 <vanila> im making a new stacky language
06:49:05 <Bicyclidine> i never did figure out how that shitty register machine was turing complete
06:49:14 <Dulnes> Ofc hhh isnt a word wth did you think it was
06:49:23 <oerjan> Bicyclidine: via godel encoding, really
06:49:37 -!- ZombieAlive has quit (Remote host closed the connection).
06:49:45 <vanila> IF (else then predicate - result)
06:50:01 <Dulnes> mitchs: no need to be rude
06:50:02 <vanila> if predicate is 0 result=then, otherwise result=else
06:50:11 <vanila> and things like +, *, dup, swap
06:50:14 <mitchs> i thought i was joking
06:50:34 -!- adu has quit (Quit: adu).
06:50:40 <Dulnes> :T alas i cannot understand jokes
06:50:50 <Bicyclidine> oerjan: yeah i was just having trouble understanding how to use godel encoding with the paucity of instructions. i don't doubt it's possible, but still
06:50:58 <oerjan> vanila: if you make a new stack language then you have to prove _that_ TC as well :P
06:51:21 <Dulnes> Thanks for making it seem you want me gone
06:51:52 -!- drdanmaku has quit (Quit: [a→b]--[a→((E*a)+b)).
06:53:44 <oerjan> Bicyclidine: basically you use godel encoding to encode an n-register machine with a 2-register one
06:54:26 <oerjan> for this to work, you need to be able to divide a number by a prime and check the modulus
06:54:30 <HackEgo> [wiki] [[Special:Log/newusers]] create * AnneFrank * New user account
06:54:42 <oerjan> which you can do with iterated decrement
06:55:39 <oerjan> then, once you have n-register machines, you use 2 cells with base k encoding to give you a tape of cells with k possible values
06:56:06 <vanila> i wonder if ` s k execution would be easiest
06:56:21 <oerjan> (each cell gives you a stack)
06:56:51 <oerjan> oh and a temporary register to help multiply/divide by k
06:57:10 <vanila> the assemblr is a bit tricky
06:57:30 <oerjan> vanila: i'm pretty sure a turing machine thingy is simplest here
06:57:39 <vanila> if i have code like this x (goto Label3) y Label1: z w Label2: e h y Label3:
06:57:43 <oerjan> or minsky machine, if you have unbounded cells
06:57:58 <vanila> i do not really know how large the goto code will be until I know where Label3 is
06:58:13 <vanila> i can try to allocate enough space for it and pad
06:58:17 <oerjan> vanila: that's why you need the padding?
06:58:30 <vanila> but still, i do not know for sure what amount of padding to do
06:58:35 <vanila> it might have to retry with more
06:59:14 <vanila> it would be nice to get it right on first try
06:59:15 <oerjan> vanila: you can use algebra and keep the padding a variable until you know how big the entire program expands to
07:00:13 <oerjan> calculate addresses as a + p * b, where p is the unknown padding
07:00:28 <oerjan> this should allow you to calculate this in two passes
07:01:02 <oerjan> depends on program code
07:01:35 <oerjan> increment a every time you insert a normal command, increment b every time you insert a padded value
07:02:20 <oerjan> mind you, you can _probably_ overestimate p if you know the maximal length of the expanded program.
07:02:29 <vanila> ill try to implement it tommorow
07:02:30 <int-e> are you generating position-independent code?
07:03:00 <oerjan> that would require using relative addresses. still possible, but a bit more complicated.
07:03:11 <int-e> if you would, you could work inside-out when translating code.
07:03:25 <int-e> ah, there's a downside to everything
07:03:30 <oerjan> you'd have to add a calculated offset to the current program counter
07:05:10 -!- ^v has joined.
07:09:41 -!- ^v has quit (Client Quit).
07:12:19 -!- vanila has quit (Quit: Leaving).
07:21:12 <Taneb> I think my sleep schedule is back into something sensible
07:21:20 <Taneb> I've woken up before 2 PM
07:21:22 <fizzie> int-e: I don't know what I'm spending the time on, it just turned out that way.
07:22:16 <oerjan> Taneb: 's ok i can balance you out
07:26:01 -!- Patashu has joined.
07:27:40 -!- bb010g has quit (Quit: Connection closed for inactivity).
07:29:21 -!- Patashu_ has joined.
07:29:21 -!- Patashu has quit (Disconnected by services).
07:43:02 <mroman> {{1 1} {1 2} {1 3} {1 4} {1 5} {2 2} {2 3} {2 4} {2 5} {3 3} {3 4} {3 5} {4 4} {4 5} {5 5}}
07:49:02 <oerjan> a @fizzie command might be useful
07:52:13 <mroman> Is there no String -> JSONStuff?
07:52:32 <mroman> I don't want stuff like readJSON :: String -> Result a
07:54:07 <fizzie> mroman: What do you want, then?
07:55:27 <scoofy> how much memory is good for an esoteric language?
07:55:36 <scoofy> should 64k be enough? or is 2GB limit better?
07:56:59 <int-e> scoofy: 59049 bytes are enough to be interesting
07:57:04 <zzo38> scoofy: Well, you don't necessarily have to have a hard limit (although some implementations might)
07:57:15 <scoofy> sure. i'm just wondering what advantages that might bring.
07:57:33 <int-e> Bicyclidine: that's not a nice power.
07:57:43 <lifthrasiir> int-e: I'd like to have 343 memory cells instead
07:57:46 <scoofy> using some wraparound modulo arithmetic
07:57:50 <int-e> Bicyclidine: I did not make up that number, hth.
07:58:10 <lifthrasiir> honestly, any size of p^n with a prime p ought to be enough
07:58:10 <oerjan> mroman: JSonStuff is known as Value, it is an instance of the conversion classes
07:58:19 <scoofy> for example, if all cells are 16 bit, and all memory addresses are 16 bit, then the two can be mapped.
07:58:36 <lifthrasiir> (and an integral p and n to be extra sure)
07:59:20 <int-e> Bicyclidine: in fact, the number comes from https://esolangs.org/wiki/Malbolge
07:59:55 <int-e> lifthrasiir: 7^3, now that could be fun.
08:00:38 <int-e> lifthrasiir: sorry, took me a moment to realize that you did not typo 243 = 3^5 there.
08:01:20 <int-e> are there any other prime power that are exactly 100 apart?
08:02:32 <lifthrasiir> maybe Pell's equation? have to look at it.
08:03:01 <int-e> b_jonas: Right, I guess I wanted the exponent to be different from 1.
08:03:02 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
08:04:02 <mitchs> here's a big list of prime powers if you just want to work on the numbers http://oeis.org/A025475/b025475.txt
08:04:03 <int-e> and that's an exclamation mark, not a factorial.
08:04:14 <mitchs> (with exponent 0 or >= 2)
08:05:26 <fizzie> int-e: Do you want to reveal whether your 64B dc just encodes the outputs instead of actually doing the work?
08:06:25 <b_jonas> but probably no other case
08:06:34 <Sgeo> "D is open source"
08:06:50 <Sgeo> "Worried about redistribution? Don't be: Just ask Walter. He may be under obligation to require his permission, but it's only a technicality. Ask him, and he'll grant permission. He hasn't been known not to. "
08:06:56 <Sgeo> I don't think that's sufficient for Debian
08:07:13 <Sgeo> (Although there are other compilers that are actually OSS)
08:07:28 <int-e> fizzie: I already said that it's cheating.
08:08:01 <int-e> fizzie: though I guess that was directed at oerjan.
08:08:05 <lifthrasiir> afaik DFSG requires that the non-interactive agent can get the license ("lonely island experiment" I think?)
08:08:17 <Taneb> I need to get into the habit of putting on a wash more often
08:08:24 <Taneb> I'll probably have to do three loads today
08:08:29 <fizzie> int-e: Well, you know... there's cheating, and then there's cheating. The Burlesque I tagged as "cheat" just cheats by a little bit, in that it'd fail for some subset of puzzles.
08:08:41 <fizzie> int-e: But good to know.
08:08:50 <int-e> fizzie: same here, but the subset is a tad smaller ;-)
08:09:17 <mitchs> i checked that (25,125) and (243,343) are the only such pairs in that file
08:09:29 <int-e> fizzie: err larger, since you spoke about the set where it would fail
08:09:46 <Sgeo> lifthrasiir: I se ereferences to it but not the test itself
08:09:50 <fizzie> Granted, I tried to make a trivial base-30-encoded-outputs in Burlesque, and ended up with 134B due to overhead.
08:10:04 <b_jonas> it's not so hard, the prime powers are 4 8 9 25 27 32 49 121 125 128 169 243 289 343 361 529 841 961 1331 1369 1681 1849 2048 2187 2197 2209 2809 3125 3481 3721 4489 4913 5041 5329 6241 6859 6889 7921 ...
08:10:21 <Sgeo> http://comments.gmane.org/gmane.linux.debian.curiosa/4526
08:15:12 <lambdabot> LOWI 260750Z 08005KT 9999 FEW006 BKN009 06/05 Q1016 NOSIG
08:15:31 <Taneb> I don't know the code of my nearest airport :(
08:15:40 <Taneb> I don't even know what my nearest airport is!
08:16:46 <int-e> . o O ( google: airport nearby )
08:17:42 <int-e> well at least it turns up a couple of sites that promise to find airports
08:18:01 <Sgeo> Ate so many twizzlers
08:19:58 <oerjan> "The nearest major airport is Leeds Bradford International Airport (LBA / EGNM). This airport has international and domestic flights from Leeds, United Kingdom and is 33 miles from the center of York, United Kingdom."
08:20:02 <int-e> Sgeo: I'm imagining this is a serious request and trying to figure out what kind of help we could provide.
08:20:05 <lambdabot> EGNM 260750Z 05005KT 020V090 3000 -RADZ BR FEW002 SCT011 BKN035 05/05 Q1014
08:20:27 <Taneb> I generally use http://weather.elec.york.ac.uk/ now
08:20:40 <int-e> Some goatse link, perhaps.
08:20:43 <Taneb> It's only a mile away from my house
08:20:48 <lambdabot> ENVA 260750Z 10005KT CAVOK M00/M00 Q1026 NOSIG RMK WIND 670FT 15013KT
08:22:53 <oerjan> help there is no temperature here
08:22:58 <Sgeo> Reassuring me that either it's not possible to puke in sleep or that I would wake up shortly first would help
08:23:06 <oerjan> or perhaps it's just cowing out
08:23:40 <oerjan> hm i'm not sure that is a phrase
08:24:34 <Sgeo> Apparently it can happen. I'm scared now :<
08:24:58 <oerjan> Sgeo: you could try puking before going to bed hth
08:25:17 <Sgeo> Can too much sugar even cause this?
08:25:51 <Taneb> Sgeo, try going for a bit of a walk to settle your stomach?
08:30:22 <Sgeo> oerjan: ty, just did what you suggested
08:30:25 <Sgeo> (not voluntarily)
08:36:20 <Sgeo> On the plus side, I feel much better now
08:36:29 <Sgeo> Almost scary that it was red, but not really
08:42:06 -!- nooga has joined.
08:46:44 <Taneb> Sgeo, hope you are OK :(
09:04:19 -!- dts has joined.
09:05:27 <Sgeo> Freezing cold and not sure why,, other than thstt I'm fine
09:08:01 -!- heroux has quit (Ping timeout: 272 seconds).
09:09:25 -!- oerjan has quit (Quit: Good night).
09:18:16 -!- tlewkow has joined.
09:22:44 -!- tlewkow has quit (Ping timeout: 258 seconds).
09:24:24 -!- heroux has joined.
09:24:33 -!- Dulnes has quit (Quit: Connection closed for inactivity).
09:33:05 -!- vanila has joined.
09:36:40 <vanila> I added labels and push label-address operations to that MMBF
09:37:24 <vanila> stack + goto means we can do procedure calls and recursion
09:38:11 <Sgeo> Still feeling a bit nausous. Not as much though
09:38:29 <mitchs> you're working with a modified version of the language, or you found ways to implement things in the language ?
09:38:42 <vanila> i wrote an assembler which compiles these features into the original language
09:38:48 <vanila> so this would be useful for proving TCness
09:40:50 -!- heroux has quit (Ping timeout: 240 seconds).
09:47:08 <vanila> we know how to permute the top of the stack
09:47:22 <vanila> and can compute things like +, * etc..
09:49:22 -!- heroux has joined.
10:01:01 <lambdabot> EFHK 260950Z 19008KT 1700 -DZ BR SCT001 BKN002 04/04 Q1025 NOSIG
10:06:49 -!- heroux has quit (Ping timeout: 255 seconds).
10:11:10 <vanila> would you like to change the featured language on wiki front page?
10:28:39 -!- nooga has quit (Ping timeout: 264 seconds).
10:38:36 <fizzie> I'm not sure. I don't generally "do things". Would it be into something listed at [[Esolang:Featured languages/Candidates]] and with a good article about it in addition to being otherwise interesting?
10:39:20 <vanila> http://esolangs.org/wiki/Esolang:Featured_languages/Current
10:39:27 <vanila> I guess its this page which gets edited
10:40:00 <vanila> Eodermdrome, Funciton and Rail were suggested, I don't think it matters which is picked any should be fine
10:40:08 <vanila> (any of the candidates, not nec. one of those 3)
10:44:14 <fizzie> Oh. I would need to write a blurb. I don't think I can do that right now, but I might attempt it in the evening, if I remember.
10:45:32 <vanila> you could just copy the start of the article
10:45:35 <vanila> so you don't have to write it yourself
10:45:39 <vanila> but you can if you like
10:49:02 -!- heroux has joined.
10:50:45 -!- Phantom_Hoover has joined.
10:56:50 -!- nooga has joined.
11:08:23 -!- scoofy has quit (Ping timeout: 250 seconds).
11:13:07 <int-e> Wow, henkma. Right, if f terminates the program then we can schedule as many calls of it in a row as we like... phew.
11:14:26 -!- heroux has quit (Ping timeout: 256 seconds).
11:14:26 <vanila> int-e, were you interseted in the stack brainfuck?
11:15:49 -!- heroux has joined.
11:16:43 <int-e> variable: MNNBFSL? Yes.
11:19:10 <vanila> I wrote an 'assembler' which adds labels and a command to p ush the addres of a label (computed in binary) to the stack
11:19:39 <vanila> so this gives you ability to e.g. perform recursive functions like how assembly does it
11:20:35 -!- boily has joined.
11:20:53 -!- scoofy has joined.
11:36:08 <int-e> Nice. (Sorry, I am interested but I don't really have the time to look at stuff in any detail.)
11:39:23 -!- heroux has quit (Ping timeout: 272 seconds).
11:46:54 -!- heroux has joined.
11:50:29 -!- shikhin has joined.
11:50:32 -!- shikhin has quit (Signing in (shikhin)).
11:50:32 -!- shikhin has joined.
11:51:01 -!- shikhin has changed nick to Guest93337.
11:52:01 -!- Guest93337 has changed nick to shikhout.
11:52:29 -!- shikhout has changed nick to shikhin.
11:54:00 -!- AndoDaan has joined.
12:06:57 <mroman> 09:09 < fizzie> Granted, I tried to make a trivial base-30-encoded-outputs in Burlesque, and ended up with 134B due to overhead.
12:07:28 <mroman> fizzie: I want something that allows me to map JSON values to Burlesque values
12:07:59 <mroman> I'd rather want case read of JSInt i -> ... JSString s -> ..
12:08:31 <mroman> since I don't know the type ahead using :: is not for me
12:09:19 <AndoDaan> I finished the burlesque interpreter for MNNBFSL.
12:09:26 -!- Patashu_ has quit (Ping timeout: 240 seconds).
12:09:44 <AndoDaan> Seems so trivial in hindsight.
12:09:55 -!- heroux has quit (Ping timeout: 250 seconds).
12:10:48 <AndoDaan> No. I think it was a friend of hinichiro.
12:12:06 <AndoDaan> I just got interested in it because it was new on anagol.
12:13:11 <AndoDaan> I skimmed the logs, vanila. Do you feel closer to thinking MNNBFSL is TC?
12:13:31 <vanila> well I think someone smart might prove it TC in a much easier way
12:14:07 <fizzie> mroman: Isn't that just runGetJSON (fmap burlesqize readJSValue) inputString where burlesqize (JSInt i) = x; burlesqize (JSString s) = y; ...?
12:14:13 <vanila> but to me this confirms that it is TC for sure
12:14:31 <vanila> it doesnt count as a proof but the construction is mostly, you'd have to do conditional branching
12:16:08 <fizzie> Maybe that's overly low-level, I don't know how the package is constructed.
12:25:12 -!- boily has quit (Quit: PROTOTYPIC CHICKEN).
12:29:40 -!- heroux has joined.
12:31:10 -!- scoofy has quit (Ping timeout: 240 seconds).
12:36:23 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds).
12:52:03 -!- heroux has quit (Ping timeout: 265 seconds).
12:58:17 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41167&oldid=41166 * Orenwatson * (+219) Added explanation of name
13:09:44 <FireFly> <AndoDaan> I just got interested in it because it was new on anagol. ← perhaps anagol could use an "interpret burlesque" task
13:10:27 -!- heroux has joined.
13:10:33 <AndoDaan> it would have to be a subset of burlesque's commands.
13:11:44 <vanila> are there any golf problems which were solved by writing an interpreteR?
13:13:57 <int-e> vanila: Perl's s///gee stuff can sometimes be viewed as implementing ad-hoc DSLs.
13:14:27 <AndoDaan> "minimal scheme interpreter" & "minimal postscript interpreter" too.
13:14:58 <b_jonas> AndoDaan: those don't really work on anagolf, because you can't easily give inputs that can really only be solved by writing a general interpreter
13:15:37 <b_jonas> in fact, on any golf server it would be very hard to write good tests for it that cover everything
13:15:53 <int-e> vanila: so that's a question. if somebody does some stuff on a string to produce a bunch of code that is then evaluated, have they written a compressor for code or an interpreter for a weird language?
13:16:29 <vanila> I think there is a close relation between decompression and intepreters ! :)
13:17:06 <int-e> Oh, we're dangerously close to rediscovering Kolmogorov complexity.
13:17:43 <b_jonas> Make 24 is now post-mortem, let me see what people submitted
13:18:08 <AndoDaan> yeah... that was a fail of a question.
13:18:36 <vanila> i wonder what to do now
13:18:43 <b_jonas> http://golf.shinh.org/p.rb?Make+24
13:19:34 -!- GeekDude has joined.
13:21:21 <vanila> i could make al anguage out of nand gates
13:21:48 <vanila> you write CPU like this: (NAND X (NAND ... .. (NAND ... )))))
13:22:28 <vanila> its not TC since you can only address finite memory but you can do real programming with it
13:24:26 <AndoDaan> you wouldn't even need to be able too loop right? as long as you copy and branche any sequence of instruction of a wanted loop.
13:24:50 <AndoDaan> (sorry, my terms are terrible).
13:25:25 <vanila> well it would be run in a loop
13:26:20 <vanila> so you could design your own instruction set and program it, or make a special purpose cpu
13:27:23 <AndoDaan> aren't all average computers{cpu s} basically nand logic gates and memory?
13:28:13 <vanila> so it's very bad to program in
13:28:21 <vanila> immense code duplication
13:30:27 -!- heroux has quit (Ping timeout: 264 seconds).
13:31:44 <AndoDaan> (I say "saw it" but my grasps of these concepts are nowhere near concrete)
13:31:54 <vanila> im just bored i dont know what to do now
13:33:00 <AndoDaan> in the discussion i was surprised that it's possible TC ness wasn't dismissed outright.
13:36:57 <AndoDaan> I can't even begin to see how one would try and implement any usefull and understandable instructions in it.
13:37:38 <AndoDaan> it feels like a <2 dimensional CA.
13:37:46 <int-e> AndoDaan: the same could be said about Conway's game of life.
13:41:04 <AndoDaan> I mean, I can grasp using standard stable pattern to build standard stable processes, but how anybody worked out to use floaters{?} and the guns to interact like logic gates... Amamzing
13:41:36 <int-e> gliders and spaceships
13:42:25 <int-e> people systematically tried all possible ways of up to three gliders to interact, and less systematically beyond.
13:42:26 <vanila> have you seen glider gun?
13:42:40 <int-e> Have you seen rakes?
13:43:22 <vanila> http://upload.wikimedia.org/wikipedia/commons/e/ec/Conways_game_of_life_breeder.png
13:43:35 <vanila> oh it makes glider guns
13:43:47 <int-e> "A rake is a puffer whose debris consists of spaceships."
13:44:16 <vanila> id like to play with Golly
13:44:17 <AndoDaan> yeah, I think I watched a tc machine in gol vid not too long ago.
13:45:13 <int-e> or space fillers (though those are of little interest for TC of GoL) http://www.conwaylife.com/wiki/Max
13:45:15 -!- atehwa has quit (Ping timeout: 250 seconds).
13:45:41 <vanila> http://www.youtube.com/watch?v=xP5-iIeKXE8
13:45:59 -!- heroux has joined.
13:46:11 -!- atehwa has joined.
13:53:06 <J_Arcane> John Conway talks about the Game of Life: https://www.youtube.com/watch?v=E8kUJL04ELA
14:01:34 <AndoDaan> I always thought the live\die interpretation of the rules weird.
14:03:18 -!- drdanmaku has joined.
14:06:29 <AndoDaan> I'm much more comfortable with having every possible neighbours states defined.
14:07:13 <AndoDaan> I guess I'm more use too 1d ca s, where that's easier to visualise.
14:11:15 <AndoDaan> Time for some sleep I think. See you guys later.
14:11:15 -!- heroux has quit (Ping timeout: 255 seconds).
14:11:21 -!- AndoDaan has quit (Quit: Quit).
14:22:28 -!- heroux has joined.
14:27:50 -!- heroux has quit (Ping timeout: 240 seconds).
14:34:37 -!- heroux has joined.
14:41:38 -!- j-bot has joined.
14:43:58 -!- MDream has quit (Quit: later chat).
14:44:19 -!- MDude has joined.
14:48:10 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
14:53:10 -!- heroux has quit (Ping timeout: 256 seconds).
15:04:28 -!- tlewkow has joined.
15:13:27 -!- Koen__ has joined.
15:23:34 -!- Sprocklem has joined.
15:23:48 -!- nycs has joined.
15:24:05 -!- nycs has changed nick to `^_^v.
15:38:48 -!- heroux has joined.
15:40:48 -!- GeekDude has joined.
15:43:29 -!- `^_^v has quit (Quit: Leaving).
15:47:28 -!- Phantom_Hoover has joined.
15:47:51 -!- heroux has quit (Ping timeout: 264 seconds).
15:52:10 -!- shikhout has joined.
15:54:13 -!- Koen__ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
15:55:43 -!- shikhin has quit (Ping timeout: 265 seconds).
16:05:14 -!- tlewkow has quit (Remote host closed the connection).
16:11:09 -!- vanila has quit (Remote host closed the connection).
16:18:23 -!- `^_^v has joined.
16:18:29 -!- nycs has joined.
16:18:46 -!- nycs has quit (Remote host closed the connection).
16:19:31 -!- abibepo has joined.
16:20:26 -!- abibepo has quit (Client Quit).
16:42:18 -!- heroux has joined.
16:56:51 -!- G33kDude has joined.
16:57:01 <int-e> fizzie: hah, "supercheat"
16:58:41 -!- shikhout has changed nick to shikhin.
16:59:11 -!- GeekDude has quit (Ping timeout: 245 seconds).
16:59:18 -!- G33kDude has changed nick to GeekDude.
17:00:31 -!- Bicyclidine has joined.
17:01:16 -!- heroux has quit (Ping timeout: 245 seconds).
17:04:53 -!- Sprocklem has quit (Ping timeout: 255 seconds).
17:05:40 <int-e> cheat? well, of course.
17:14:32 -!- MoALTz has joined.
17:16:13 -!- idris-bot has quit (Quit: Terminated).
17:16:29 -!- idris-bot has joined.
17:21:16 -!- vanila has joined.
17:24:20 -!- L8D has left.
17:27:15 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
17:27:20 -!- Phantom__Hoover has joined.
17:32:07 <fizzie> int-e: Admittedly it's not very "super" lengthwise.
17:39:25 <fizzie> (It's the kind of thing with one character for each pair of numbers, so technically 45B of payload, but the formatting code is quite long. Selecting the right string I got done rather compactly, at least.)
17:40:57 -!- vanila has quit (Quit: Leaving).
17:44:02 <fizzie> I could cut off 9B if I could embed arbitrary octets in a string.
17:49:44 -!- heroux has joined.
17:53:49 -!- scoofy has joined.
17:59:22 -!- Sprocklem has joined.
17:59:46 -!- tlewkow has joined.
18:02:56 -!- mihow has joined.
18:08:15 -!- FireFly has quit (Quit: WeeChat 0.4.0).
18:08:38 -!- heroux has quit (Ping timeout: 265 seconds).
18:08:39 -!- FireFly has joined.
18:16:24 -!- heroux has joined.
18:17:17 -!- tlewkow has quit (Remote host closed the connection).
18:19:54 -!- MDud has joined.
18:20:34 -!- MDude has quit (Ping timeout: 256 seconds).
18:21:24 -!- tlewkow has joined.
18:24:05 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds).
18:25:41 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
18:28:08 -!- heroux has quit (Ping timeout: 255 seconds).
18:30:03 -!- heroux has joined.
18:39:10 -!- hjulle has joined.
18:39:23 -!- Sprocklem has quit (Ping timeout: 255 seconds).
18:51:10 -!- heroux has quit (Ping timeout: 256 seconds).
19:14:57 -!- tlewkow has quit (Remote host closed the connection).
19:20:44 -!- tlewkow has joined.
19:39:46 -!- ZombieAlive has joined.
19:44:09 -!- heroux has joined.
20:06:18 -!- heroux has quit (Ping timeout: 244 seconds).
20:07:32 -!- heroux has joined.
20:10:56 -!- nooga has quit (Ping timeout: 240 seconds).
20:14:00 -!- Patashu has joined.
20:29:51 -!- Patashu has quit (Ping timeout: 264 seconds).
20:32:12 <fizzie> Now it's 27B of data out of 82B, so the ratio's gotten even worse.
20:40:38 -!- AnotherTest has joined.
20:42:16 -!- GeekDude has joined.
20:42:34 -!- dts has changed nick to WillBot.
20:49:04 -!- heroux has quit (Ping timeout: 250 seconds).
20:49:21 -!- WillBot has changed nick to dts.
21:20:16 -!- dts has quit (Read error: Connection reset by peer).
21:20:33 -!- nooga has joined.
21:41:49 -!- tlewkow has quit (Remote host closed the connection).
21:42:04 -!- `^_^v has quit (Ping timeout: 264 seconds).
21:48:04 -!- AnotherTest has quit (Ping timeout: 265 seconds).
21:48:23 -!- tlewkow has joined.
21:50:58 -!- heroux has joined.
21:52:59 -!- shikhout has joined.
21:56:17 -!- shikhin has quit (Ping timeout: 265 seconds).
21:57:03 -!- MDud has changed nick to MDude.
22:03:38 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
22:05:12 -!- GeekDude has joined.
22:10:06 <HackEgo> danddreclist 59: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
22:11:30 -!- tlewkow has quit (Remote host closed the connection).
22:13:12 -!- tlewkow has joined.
22:14:41 -!- tlewkow has quit (Remote host closed the connection).
22:18:28 <Taneb> Perl is a scary language and I do not like it
22:21:18 -!- tlewkow has joined.
22:28:13 <zzo38> Taneb: Do you prefer AWK?
22:28:26 <Taneb> zzo38, I have not used AWK
22:33:02 -!- oerjan has joined.
22:35:04 <Taneb> What is a good language for demonstrating call-by-reference?
22:39:29 -!- Dulnes has joined.
22:40:13 <oerjan> oh mccarthy function is over
22:40:54 <Sgeo> It almost seems like Rust has more of an opinion on mutabiltiy than Haskell. Haskell is theoretically everything is immutable, but ultimately, you need to use the IO monad, where anything goes. In Rust, it's not anything goes even though it's implicitly in the IO monad like most languages
22:40:54 -!- tlewkow has quit (Remote host closed the connection).
22:44:47 -!- tlewkow_ has joined.
22:47:47 -!- dts has joined.
22:48:15 -!- AndoDaan has joined.
23:01:34 <zzo38> Well, in Haskell in the IO monad there are even a few things which are mathematically improper. In my opinion should be avoided as much as possible, although in some cases it is good to keep them for example ability to execute pointer operations which might or might not affect the rest of the program in proper and improper ways.
23:07:57 <AndoDaan> b_jonas, I was thinking. a anagol problem asking to implement a language, if you not only ask for the impleted language output, but also for complete code state each for each step, that would come close to forcing a 'true' implementation, right?
23:08:51 <zzo38> AndoDaan: I think it might come closer than otherwise, but still it can involve a cheat possibly; there is also the possibility that the specification of a language might not specify exactly how some of the internal state might be.
23:09:31 -!- nooga has quit (Ping timeout: 240 seconds).
23:11:00 -!- nooga has joined.
23:11:03 <AndoDaan> hmm. output of an uncertain state could just be the list of all possible symbols that state could be.
23:11:27 <AndoDaan> it probably wouldn't narrow much down for some bit, I guess.
23:14:09 <AndoDaan> but making sure the to be implemented language is has a clear and easy to read system state would help that issua.
23:14:25 <zzo38> Yes that is one way, if it is such a language.
23:15:06 <AndoDaan> I'm only thinking about possible low level languages for implementation, like string replacement or cell based.
23:21:12 <AndoDaan> then again, maybe I'm creating too many big codegolf problems. But it's hard to come up with a basic algorith that hasn't been asked already.
23:31:44 <zzo38> I invented two more pokemon cards
23:34:04 -!- mihow has quit (Quit: mihow).
23:36:24 <oerjan> @tell int-e <int-e> Wow, henkma. Right, if f terminates the program then we can schedule as many calls of it in a row as we like... phew. <-- fiendish
23:39:52 <oerjan> <mroman> fizzie: I want something that allows me to map JSON values to Burlesque values <-- i told you, use the Value type for that.
23:40:08 <oerjan> @tell mroman <mroman> fizzie: I want something that allows me to map JSON values to Burlesque values <-- i told you, use the Value type for that.
23:41:31 -!- nooga has quit (Ping timeout: 240 seconds).
23:41:37 <shachaf> `` ln -s dontaskdonttelllist bin/don\'taskdon\'ttelllist
23:42:09 <shachaf> does mercurial handle hard links?
23:42:35 <oerjan> i'm not sure it handles symbolic ones
23:44:09 <fizzie> You can go directly to http://www2.codu.org/projects/hackbot/fshg/index.cgi if you want the fshg browser.
23:44:52 <shachaf> is a pro tip given to a pro or given by a pro?
23:45:00 <shachaf> or does one become a pro by virtue of receiving it?
23:45:15 <fizzie> I don't think the giver or givee really factor in -- it's just that the content is on a "pro level".
23:46:09 <Jafet> Is a pro tip more reliable than a con tip?
23:46:44 <AndoDaan> The teacher can be a fool, as long as the student is wise
23:52:43 <fizzie> If a thing has an attribute that was formerly negative but due to changed circumstances is so no longer, is that an "ex-con"?
23:54:41 -!- adu has joined.
23:54:56 <AndoDaan> Depends on if the tipper knows if it's an ex-con or not. If s/he knows its an ex-con but tips it unchanged it was actually a protected ex-con.
23:56:26 <AndoDaan> add a little non-verbal signalling and it's mankind's favourite pasttime.
23:57:25 -!- ZombieAlive has quit (Remote host closed the connection).
00:04:52 -!- MoALTz_ has joined.
00:07:06 -!- MoALTz has quit (Ping timeout: 250 seconds).
00:10:10 -!- heroux has quit (Ping timeout: 265 seconds).
00:20:11 -!- Froox has joined.
00:20:53 -!- Frooxius has quit (Read error: Connection reset by peer).
00:24:29 -!- ZombieAlive has joined.
00:25:05 -!- tlewkow_ has quit (Remote host closed the connection).
00:27:40 -!- heroux has joined.
00:31:03 -!- shikhout has changed nick to shikhin.
00:41:31 -!- AndoDaan has quit (Ping timeout: 240 seconds).
00:41:42 -!- AndoDaan has joined.
00:44:34 -!- Dulnes has quit (Quit: Connection closed for inactivity).
01:01:12 -!- adu has quit (Ping timeout: 256 seconds).
01:03:54 -!- adu has joined.
01:04:08 -!- Dulnes has joined.
01:20:42 -!- madbr has joined.
01:35:38 -!- ZombieAlive has quit (Remote host closed the connection).
01:35:59 -!- ZombieAlive has joined.
01:56:19 -!- AndoDaan_ has joined.
01:58:46 -!- AndoDaan has quit (Ping timeout: 245 seconds).
02:04:50 -!- _AndoDaan_ has joined.
02:05:16 <HackEgo> [wiki] [[And then]] N http://esolangs.org/w/index.php?oldid=41168 * Lucasieks * (+466) Created page with "This language is like BF, but you need to put " and then" between commands. It works like this: We have our sweet little cute program in BF. +> We add the andthens. + and th..."
02:05:48 <HackEgo> [wiki] [[And then]] M http://esolangs.org/w/index.php?diff=41169&oldid=41168 * Lucasieks * (+8)
02:06:19 <HackEgo> [wiki] [[And then]] http://esolangs.org/w/index.php?diff=41170&oldid=41169 * Lucasieks * (+2)
02:07:56 <elliott> ok this has to be a troll.
02:08:06 -!- AndoDaan_ has quit (Ping timeout: 265 seconds).
02:08:12 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41171&oldid=40755 * Lucasieks * (+47)
02:08:41 <Bicyclidine> "define start as this big thing past the colon"
02:08:44 <oerjan> lucasieks has been around
02:09:18 <elliott> maybe I'll be forced to if oerjan doesn't feature something else soon
02:09:47 <oerjan> i think fizzie agreed to maybe write a blurb
02:10:27 <elliott> tempting to just preemptively block whoever thought AnneFrank would be a good username
02:10:38 <oerjan> i was wondering about that one too
02:11:26 <oerjan> but i kept silent lest i become tempted to make really awful puns
02:13:48 <oerjan> i expected elliott to snark now, but i guess he's too scared of the possible puns
02:14:13 <elliott> dude, if I was scared of your puns I'd have left long ago
02:14:27 <oerjan> well you will nazi _these_ coming
02:15:45 <madbr> hmm... how2design branch predictor
02:16:13 <oerjan> just use organically grown branches
02:17:14 <madbr> architectural target: in order, short mips-like pipeline (5 stages or so), instruction words are 64 bit and are split into 3 instructions of ~20 bits each (load/alu unit, store/alu unit, branch/alu unit)
02:17:26 <madbr> essentially a very small vliw
02:17:39 <oerjan> very small very large, check
02:19:05 <madbr> more or less a 3 way superscalar MIPS except the instruction pairings are baked beforehand
02:20:30 <madbr> not that you guys would care since you guys only care about networking, encryption, haskell and linux
02:21:52 <oerjan> i only care about haskell and puns hth
02:23:22 <HackEgo> [wiki] [[Main Page]] http://esolangs.org/w/index.php?diff=41172&oldid=40670 * Lucasieks * (+52)
02:23:38 <madbr> my target is something that renders gfx and mixes sound
02:24:39 <madbr> so it needs a hardware multiplier and some way of drawing textures without wasting a gazillion cycles on cobbling addresses together
02:25:04 -!- AndoDaan_ has joined.
02:25:17 <HackEgo> [wiki] [[Main Page]] http://esolangs.org/w/index.php?diff=41173&oldid=41172 * Oerjan * (-52) Undo revision 41172 by [[Special:Contributions/Lucasieks|Lucasieks]] ([[User talk:Lucasieks|talk]]) (I see nothing wrong with it)
02:25:46 <elliott> I'm interested in CPU architectures, it's just anything I say to you would roll right off anyway
02:25:49 <elliott> not that I have any expertise at all
02:26:07 <madbr> what do you mean it would roll off?
02:27:50 -!- _AndoDaan_ has quit (Ping timeout: 255 seconds).
02:28:24 -!- bb010g has joined.
02:28:55 <zzo38> If I wanted specifically using Haskell involved CPU design, I would prefer to add some stuff so that it is design for Haskell usage; I think something like this has already been done actually.
02:29:34 <madbr> elliott : are you telling me that my current design is unsound? :D
02:29:45 <madbr> or just goes way overboard
02:30:11 <elliott> I'm not adequately qualified to assess your design
02:30:58 <madbr> I'm getting into the calculation latency etc stuff and only professionals really deal with that :/
02:33:54 <madbr> also it's hard to tell if a design is balanced and will work, or if it's crippled and will never be fast
02:34:50 <zzo38> I suppose you can estimate it, but you might not be precise in making an estimation of such.
02:34:51 <Bicyclidine> make 10000 prototype chips with small schematic changes, have them drive robots, select the survivors
02:34:54 <madbr> even intel has failed multiple times at that (iAPX 432, i860)
02:36:00 <HackEgo> [wiki] [[Main Page]] http://esolangs.org/w/index.php?diff=41174&oldid=41173 * Lucasieks * (+26)
02:37:59 <HackEgo> [wiki] [[Main Page]] http://esolangs.org/w/index.php?diff=41175&oldid=41174 * Ehird * (-26) if you'd prefer to be unable to edit this page, I'd be happy to block you
02:40:04 <madbr> for my application (video games), the small, really classic RISC designs have worked well (mips, arm, superH...)
02:40:26 <zzo38> It even depend what game though
02:40:55 <Bicyclidine> i wonder how well 3d games do on risc, not that that's a terribly good question
02:41:35 <madbr> psx was mips, n64 was mips as well
02:41:42 <madbr> ps2 was a mips derivative I think
02:42:12 <Bicyclidine> i'm just thinking of all the weird shit in the current gen
02:42:38 <elliott> the current gen is really boring
02:42:44 <madbr> sega 32x, saturn and dreamcast were superH
02:42:46 <elliott> it's just x86. okay plus the wii u
02:43:01 <madbr> handhelds are like all ARM
02:44:08 <oerjan> well that sounds pretty logical
02:46:05 <madbr> there's nothing really special about RISC, it's just a well balanced family of architectures in general
02:48:41 <oerjan> get a leg up with ARM hth
02:49:26 -!- nisstyre has quit (Ping timeout: 256 seconds).
02:49:45 -!- Phantom__Hoover has joined.
02:57:11 -!- hjulle has quit (Ping timeout: 240 seconds).
03:00:24 -!- AndoDaan_ has quit (Read error: Connection reset by peer).
03:00:49 -!- AndoDaan_ has joined.
03:03:15 <int-e> "fromEnum" is terribly long...
03:04:02 <HackEgo> [wiki] [[Talk:Newton]] http://esolangs.org/w/index.php?diff=41176&oldid=40041 * Lucasieks * (+114)
03:04:49 <int-e> so that's my third 183 character non-cheating Dominosa.
03:05:18 <int-e> (the other two are very similar, but each changes something non-trivial)
03:10:48 <oerjan> there was a point where i though a short fromEnum would have helped, but i no longer think so.
03:25:59 -!- tlewkow has joined.
03:26:23 -!- _AndoDaan_ has joined.
03:26:30 -!- adu has quit (Quit: adu).
03:26:51 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:29:12 -!- AndoDaan_ has quit (Ping timeout: 245 seconds).
03:30:16 -!- tlewkow has quit (Ping timeout: 258 seconds).
03:32:35 -!- MoALTz__ has joined.
03:36:04 -!- MoALTz_ has quit (Ping timeout: 264 seconds).
03:40:17 <pikhq_> Lnging for the days of the SNES, eh?
03:43:18 -!- Phantom__Hoover has quit (Ping timeout: 258 seconds).
03:44:35 -!- Dulnes has quit (Quit: Connection closed for inactivity).
03:45:18 <madbr> snes has a lot of cool games
03:46:25 -!- _AndoDaan_ has changed nick to AndoDaan.
03:46:55 <madbr> basically you can't do anything so you have to keep your game small
03:47:07 <Bicyclidine> imo http://en.wikipedia.org/wiki/Star_Fox_2
03:47:11 <madbr> which means if you spend as much time it's more polished
03:47:39 <AndoDaan> Constantly bitched it after 3stages in StarFox me.
03:48:36 <AndoDaan> I do a barrelrole until my fingers bleed, but it's never enough.
03:48:41 <Bicyclidine> emulating this thing must be a pain in the ass, i just realized
03:49:22 <madbr> I'm trying to design a vm that's easy to emulate but can also run fast IRL
03:49:46 <Bicyclidine> don't allow people to plug in games with custom coprocessors in them, then
03:50:01 -!- AndoDaan has quit (Quit: Quit).
03:52:44 -!- shikhout has joined.
03:55:40 -!- shikhin has quit (Ping timeout: 255 seconds).
03:58:40 <int-e> oerjan: ah I think I understand your trouble regarding the search order.
03:59:25 <int-e> 177, getting there.
04:04:02 <int-e> There, 175 non-cheating, 164 cheating slightly. yay.
04:06:19 <int-e> funny statistics though. (I won't bother with the slightly cheating version)
04:06:24 -!- Sprocklem has joined.
04:07:44 <int-e> oerjan: surely there must be *some* room for optimization.
04:07:53 <elliott> dominosa small seems like hell
04:08:09 <int-e> elliott: I disagree, obviously.
04:08:42 <elliott> you can solve a problem while thinking it's hell
04:09:04 <int-e> elliott: well I didn't think it was hell because I approached it as a compression problem.
04:09:33 -!- MDude has quit (Read error: Connection reset by peer).
04:09:35 <int-e> by that approach, it's not a cheat
04:10:27 <int-e> (you can see that I also stuck to my previous convention of using "alt" to mark the alternative approach to the problem that is not data compression ;-) )
04:10:33 -!- jameseb has quit (Ping timeout: 264 seconds).
04:10:46 <int-e> (though that's not a very firm convention)
04:10:58 -!- jameseb has joined.
04:11:04 <elliott> I thought you meant that what you did wasn't actually cheating
04:11:23 <elliott> you should really mark "data compression" solutions :p
04:11:29 <int-e> elliott: Yes, that's what I said.
04:12:10 <elliott> well, ok. I can't figure out whether you mean you use a different definition of "cheating", or whether you actually solved the problem in a way everyone would consider non-cheat but that still approaches it as a data compression problem.
04:12:32 <int-e> elliott: it's too much hassle, because I *will* accidently submit an improvement under the plain "int-e" nick at some point.
04:13:10 <int-e> (as can be seen in Wow, where I tried sticking to (boring) and (alt) throughout.)
04:15:34 <elliott> I like that 798-byte Python solution to Wow.
04:15:42 <int-e> elliott: I'm bending the notion of cheating. Anyway, I was initially answering your claim that Dominosa was hell. By never trying not to cheat (in your terminology ;-) ), it turned quite pleasant.
04:15:53 <int-e> s/turned/turned out/
04:16:56 <int-e> elliott: oh yes, I particularly like the space between print and "
04:17:04 <int-e> elliott: and of course, the nick that goes with it.
04:17:10 <elliott> well, if you're not going to try, why bother trying?
04:17:19 <elliott> eliminating the space would be a bit pointless.
04:17:33 <int-e> elliott: It's the salt in the soup.
04:17:51 <int-e> elliott: It's so fundamentally against any golfer's instinct.
04:17:54 <elliott> I should submit an answer like that to every problem
04:18:03 <elliott> if sys.stdin.read() == '...':
04:18:23 <int-e> I mean, eliminating superfluous whitespace is the first thing you do, before you even start thinking about imrpovements.
04:18:44 <elliott> int-e: I think printing a huge constant string with escapes is also against any golfer's instinct :p
04:20:10 <int-e> Bicyclidine: you know the correct link, right?
04:20:47 <int-e> Let me guess, ANA = All Nippon Airways?
04:22:35 <int-e> because you can sponsor pretty much anything you like as an airway.
04:22:57 <oerjan> <int-e> oerjan: surely there must be *some* room for optimization. <-- perhaps. i went through several improvement iterations already.
04:23:11 <int-e> Bicyclidine: http://www.ana.co.jp/anaopen/ hth
04:27:56 <oerjan> there was one point that didn't feel necessarily optimal, though.
04:29:54 <oerjan> i suppose there's always the possibility we've missed different ones
04:32:04 -!- Dulnes has joined.
04:33:59 <int-e> > map length ["notElem","all(/=)"]
04:34:19 <oerjan> i recall checking that before :)
04:34:42 <int-e> so that could explain 4 alphanums difference
04:35:56 <oerjan> perhaps our approaches are really different
04:36:20 <int-e> always a possibility
04:36:27 <int-e> it's just hard to imagine ;-)
04:36:52 <int-e> I mean, coming up with different approaches is hard.
04:37:20 <Bicyclidine> i suppose i'll remember this the next time i need to explain kolmogorov complexity
04:37:48 <oerjan> i can think of another variation with equal length that might give you 4 more symbols
04:38:05 <int-e> oerjan: Like the McCarthy thing, where the fundamental idea was to use strings of ")" as unary numbers, instead of an Int counter. When I found that, that's when I said "McCarthy is beautiful"
04:38:32 <oerjan> figures, because i never did
04:39:42 -!- shikhout has quit (Ping timeout: 272 seconds).
04:46:34 -!- ZombieAlive has quit (Remote host closed the connection).
04:56:42 -!- CrazyM4n_ has joined.
05:00:31 <HackEgo> [wiki] [[Talk:And then]] N http://esolangs.org/w/index.php?oldid=41177 * Orenwatson * (+653) complaining
05:00:42 <HackEgo> [wiki] [[Talk:And then]] http://esolangs.org/w/index.php?diff=41178&oldid=41177 * Orenwatson * (+95)
05:02:36 -!- Sprocklem has quit (Ping timeout: 244 seconds).
05:02:50 <HackEgo> [wiki] [[Talk:And then]] M http://esolangs.org/w/index.php?diff=41179&oldid=41178 * Orenwatson * (+4) corrected perl code
05:24:36 <HackEgo> [wiki] [[User talk:Orenwatson]] N http://esolangs.org/w/index.php?oldid=41180 * AnneFrank * (+28) Created page with "Goodness me brainfuck indeed"
05:25:23 -!- CrazyM4n_ has quit (Quit: Lost terminal).
05:26:05 <elliott> temptation to block rising
05:27:12 -!- zzo38 has quit (Ping timeout: 272 seconds).
05:34:11 <HackEgo> [wiki] [[User talk:Orenwatson]] M http://esolangs.org/w/index.php?diff=41181&oldid=41180 * AnneFrank * (-20)
05:35:46 <int-e> that's a strange edit?
05:35:47 <HackEgo> [wiki] [[User talk:Orenwatson]] http://esolangs.org/w/index.php?diff=41182&oldid=41181 * Orenwatson * (+144) reply to confusing message.
05:35:54 <HackEgo> [wiki] [[Special:Log/block]] block * Ehird * blocked [[User:AnneFrank]] with an expiry time of indefinite (autoblock disabled): please pick a different username
05:38:45 <HackEgo> [wiki] [[Special:Log/newusers]] create * BillGates * New user account
05:39:51 <elliott> tempting to block again to see what they come up with next
05:40:05 <int-e> this brings back memories... of xbill
05:40:50 <Bicyclidine> indefinite (autoblock disabled): that one was funny, let's see what you can really do
05:41:17 <elliott> faking the colour, dedication
05:42:25 <elliott> well BillGates is borderline but it will maybe fall on the wrong side of the border when they make another bizarre edit
05:42:30 <elliott> although wikipedia would block that name in an instant
05:42:51 <HackEgo> [wiki] [[User talk:BillGates]] N http://esolangs.org/w/index.php?oldid=41183 * BillGates * (+121) Created page with "How do you create a throw/catch error for perl or am i mistaken on the panguage? im probably mistaken but if im not help"
05:43:01 <elliott> https://en.wikipedia.org/wiki/User_talk:BillGates
05:43:01 <elliott> I hope not to seem unfriendly or make you feel unwelcome, but I noticed your username, and am concerned that it might not meet Wikipedia's username policy. After you look over that policy, could we discuss that concern here?
05:43:05 <elliott> Bill Gates is the name of a well-known living or recently deceased person which is a violation of the username policy.
05:43:19 <HackEgo> [wiki] [[User talk:BillGates]] M http://esolangs.org/w/index.php?diff=41184&oldid=41183 * BillGates * (+0)
05:44:10 <HackEgo> [wiki] [[Special:Log/block]] block * Ehird * blocked [[User:BillGates]] with an expiry time of indefinite (autoblock disabled): I meant a username that doesn't impersonate anyone living or dead other than yourself, please
05:44:31 <elliott> I like the "or recently deceased" part.
05:44:43 <elliott> I'd appreciate learning your own views, for instance your reasons for wanting this particular name, and what alternative username you might accept that avoids raising this concern.
05:45:05 <Bicyclidine> for a second i thought you meant you were copy pasting wikipedia's mention to this peep
05:45:22 <int-e> it would be fun if it were the real Bill Gates.
05:45:47 <elliott> int-e: and simultaneously the real anne frank?
05:45:47 <HackEgo> [wiki] [[Special:Log/newusers]] create * Josaphine O'Conner * New user account
05:45:56 <int-e> elliott: Soul wandering?
05:46:16 <elliott> is Josaphine O'Conner a corruption of some well-known name or something
05:46:23 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] N http://esolangs.org/w/index.php?oldid=41185 * Josaphine O'Conner * (+39) Created page with "Better? i used my name if you dont mind"
05:46:43 <int-e> oh google. "Josephine O'Conner Death Records - FindTheBest Genealogy"
05:46:47 <elliott> Thanks to Brian Josephine's life is in danger, and some of Bragas men are on the hunt for O'Conner and Toretto. They will do anything to protect their family, even if it means getting Jack involved. (This is one of these kinds of stories that you write late at night, and decide to post. I apologize for any errors in the writing.)
05:47:25 <Bicyclidine> http://www.foreignaffairs.com/author/josephine-oconnor-howe oh ho
05:47:55 <HackEgo> [wiki] [[User talk:BillGates]] http://esolangs.org/w/index.php?diff=41186&oldid=41184 * Orenwatson * (+212) answered question.
05:48:12 <elliott> this is going to be such a mess
05:48:21 <elliott> can someone, like, merge those pages
05:49:31 <elliott> if I hadn't just said that, yes
05:49:58 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] M http://esolangs.org/w/index.php?diff=41187&oldid=41185 * Josaphine O'Conner * (+127)
05:50:09 <int-e> elliott: I know! Put them in a Web Ring!
05:50:59 <elliott> are we being watched... I'm mostly kidding with all this.
05:51:21 <elliott> it's the real bill gates and he has the NSA monitoring us...............
05:51:22 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] http://esolangs.org/w/index.php?diff=41188&oldid=41187 * Orenwatson * (+424) answered question (on her new user page).
05:53:26 -!- Oren has joined.
05:53:44 <elliott> well, anyway, this gives the excellent illusion of making it look like the wiki was really active today
05:53:58 <HackEgo> Oren: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
05:54:39 <int-e> elliott: So it's Much Ado about Nothing?
05:55:06 <int-e> now the prey has arrived and we're ready to leap
05:55:09 <elliott> you know what would inflate it even further? oerjan featuring a new language
05:55:49 -!- zzo38 has joined.
05:56:02 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] M http://esolangs.org/w/index.php?diff=41189&oldid=41188 * Josaphine O'Conner * (+273)
05:57:09 <int-e> "im going to be a detrament to this community", really? ... (and I don't mean the typo)
05:57:46 -!- bb010g has quit (Quit: Connection closed for inactivity).
05:57:47 <Bicyclidine> as an actual detriment to the community, i'm watching the competition carefully
05:58:44 * elliott shakes head fretfully at this channel
05:58:49 <int-e> anyway, my first thought when seeing the question was "this is not stackoverflow".
05:58:50 <Oren> I'll try and answer her issue...
05:59:28 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] http://esolangs.org/w/index.php?diff=41190&oldid=41189 * Orenwatson * (+329)
06:02:19 <Oren> you mean, them brainfuck-clones... http://esolangs.org/wiki/Talk:And_then
06:02:53 <elliott> people have been despairing brainfuck clones for pretty much the entire seven years I've been here :p
06:03:31 <elliott> sadly your perl script cannot reproduce And then because of the "mandatory header" if nothing else.
06:03:40 <elliott> at least it was added to the _joke_ language list and not the real one.
06:04:05 <Oren> I haven't been here long and I'm already like 絶望した!
06:04:25 <Oren> every time I see a bf clone
06:04:42 <Oren> zetsuboushita.gif
06:05:31 <elliott> sadly most of the non-BF clones aren't that great either
06:05:48 <fizzie> oerjan: I "agreed", but didn't get anything done. Huge surprise there. Maybe today!
06:06:33 <elliott> fizzie: did you get the memo? we're going against the process and featuring And then immediately, for the rest of time
06:07:33 -!- nisstyre has joined.
06:07:45 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] http://esolangs.org/w/index.php?diff=41191&oldid=41190 * Josaphine O'Conner * (+189)
06:09:02 <Oren> Is she being DDOS'd by hakkers on steroids? lol.
06:10:08 <Dulnes> How about those turkeys
06:11:22 <Dulnes> Also do some of these bots work or are they users who are names that
06:12:04 <Oren> I had turkey at thanksgiving dinner... it was delicious cooked by my aunt. I live in Canada but my aunt lived most of her life in Boston...
06:12:09 <elliott> glogbot does the codu.org logs
06:12:15 <elliott> applybot... does something. I forget what.
06:12:52 <elliott> wasn't it hol light or isabelle or something
06:12:59 <Dulnes> Doesnt Canada have October thank give
06:13:18 <Bicyclidine> i said i THINK it srats with an m, asshole
06:13:27 <elliott> there are also some bots that don't have "bot" in the name. for instance clog, and Bicyclidine
06:13:57 -!- Bicyclidine has changed nick to Botcyclidine.
06:14:12 <Oren> that's correct. oct 12 is canada thankgiving. but some people in my family are form america, so we celebrate both.
06:14:32 <Botcyclidine> To comply with IRC standards, this interface will now prevent botloops via standard mechanisms.
06:14:49 <elliott> ...almost didn't put that . in
06:14:58 <elliott> I'm a responsible lambdabot admin who is not at all forgetful
06:15:57 <Dulnes> Slowly closes my many tabs
06:17:41 <Oren> only if you're eating other people.
06:18:14 <Botcyclidine> you know, that's another thing in that book, it wouldn't have covered kuru either
06:18:24 <Botcyclidine> the book on neurobiology of disease i almost bought and have not mentioned to you before this point
06:18:30 <Oren> can prions be transmitted if the meat is cooked to gray?
06:18:58 <Dulnes> Dead prions are still bad
06:19:44 <oerjan> the british ought to know after that mad cow thing
06:19:46 <Oren> yaeh, i was thinking about the denaturing of the proteins.
06:20:01 <Botcyclidine> "It was reported in January 2011 that researchers had discovered prions spreading through airborne transmission on aerosol particles," well, just give up
06:20:27 <elliott> I'm glad we're finally getting around to having the mature, channel-wide discussion about vore we've all been waiting for
06:20:27 <Botcyclidine> WHO recommends "Immerse in a pan containing 1N NaOH and heat in a gravity-displacement autoclave at 121 °C for 30 minutes; clean; rinse in water; and then perform routine sterilization processes"
06:20:31 <oerjan> Botcyclidine: i see good opportunities for a zombie plague here
06:20:41 <elliott> Botcyclidine: for eating human meat?
06:20:52 <elliott> I'm going to believe the WHO has recommendations about that and you can't convince me otherwise
06:20:55 <oerjan> routing sterilization processes means burning it, right
06:21:15 <oerjan> elliott: world humanitatian organization
06:21:23 <elliott> oerjan: sauteeing, actually
06:21:28 <Dulnes> Gravity displacement autoclave?
06:21:35 <int-e> quoth wikipedia: "[The prions'] structural stability means that prions are resistant to denaturation by chemical and physical agents, making disposal and containment of these particles difficult."
06:21:49 <Botcyclidine> Dulnes: an autoclave that works by letting the steam out through gravity
06:21:54 <Oren> dunking it in burning alcohol? fancy restaurants do that.
06:22:00 <int-e> Botcyclidine is better informed, I see.
06:22:04 <Botcyclidine> got that backwards, the steam comes in from the top and sinks down
06:22:29 <Botcyclidine> the thing with autoclaves is they have to remove the air somehow, see
06:22:55 <Dulnes> Mature channel wide discussion of vore? what do you mean elliott
06:23:01 <elliott> https://upload.wikimedia.org/wikipedia/commons/8/8c/Broad_billed_prion.jpg can't be denatured
06:23:04 <int-e> elliott: if you use @quit once, it'll come back. if you use it again too soon, it will stay away.
06:23:36 <Dulnes> Put your meat in a fireplace then
06:23:41 <Botcyclidine> might violate some ethics rules in the process, but hey
06:23:43 <elliott> Dulnes: I have no idea how to adequately answer your question
06:23:53 <elliott> please don't fuck fireplaces though
06:23:55 <Botcyclidine> can't cook an omelette without boiling a few vertebrates
06:24:00 <Oren> vore = fetish for eating people. I saw actual evidence of this fetish in Akihabara... Never again.
06:24:45 <Dulnes> I dont often scroll deep web
06:24:51 <Oren> yes it is. I have seen too much in this short life...
06:24:55 <elliott> you know, I think I'm going to officially decree vore as off-topic for #esoteric
06:25:19 <Dulnes> The topic is visual studio
06:26:00 <Dulnes> Well i think ive seen worse than vore then
06:26:04 <oerjan> i see Dulnes hasn't learned about rule 34 yet
06:26:38 <Botcyclidine> wrote a web portal for my dragon cars eating each other fetish community
06:26:40 <elliott> oerjan got the rule right the first time
06:27:03 <elliott> I have an idea, let's talk about literally anything else
06:27:29 <Oren> Who here still likes Visual Basic?
06:27:48 <Oren> I am still nostalgic for it
06:28:03 <Dulnes> Are you nostalgic for it
06:28:14 <Botcyclidine> when i was young and formative*, i read a 21 days VB book that had a line about C programmers always having to play catch up to VB programmers
06:28:20 <Dulnes> Or for what was happening in your life at the time
06:29:02 <Oren> I loved the drag and drop interface. If only someone made something like that for PHP/JQueryUI
06:29:06 <elliott> Botcyclidine: is the footnote ever going to come
06:29:32 <Dulnes> The drag and drop was handy
06:29:42 <Botcyclidine> *i am probably using this word wrong, but i only care enough to mark an asterisk and write this out, not enough to look it up
06:30:07 <Botcyclidine> later i used blitzbasic and it didn't have drag and drop ness
06:30:09 <oerjan> Botcyclidine: you could at least have written formaline
06:30:22 <Botcyclidine> and, laterer, i used matlab's interface generator, which is very similar to VB
06:31:17 <Botcyclidine> after that i joined the peace corps and died attempting to invade honduras? what do you want me to say
06:31:51 <oerjan> isn't that more like a war corps thing
06:32:43 <elliott> remember the fresh smell of organically harvested rubber roasting in the morning
06:33:29 <Botcyclidine> how do you organically harvest rubber? just like... poke a tree?
06:33:44 <elliott> Botcyclidine: without GMOs
06:33:48 <Dulnes> Set fire to rubber wood
06:34:19 <elliott> Oren: btw I'm sorry to report this channel is usually less out-of-control than this
06:34:28 <elliott> somehow it seems to catch fire when new people join
06:34:32 <Dulnes> Oh question when did you start coding elliott
06:34:41 <HackEgo> [wiki] [[Talk:Newton]] M http://esolangs.org/w/index.php?diff=41192&oldid=41176 * Oerjan * (+1) fmt
06:34:47 <elliott> 2004ish, when I was about 8.
06:35:27 <Oren> You're younger than me!
06:35:30 <int-e> Botcyclidine: what a question. "The latex is a sticky, milky colloid drawn off by making incisions into the bark and collecting the fluid in vessels in a process called 'tapping'."
06:35:30 <elliott> I mean I did some things with, like, typing out BASIC programs into old computers before that and the like, but not really much in the way of original programming.
06:35:59 <Dulnes> Im always confused on years i forget time aloy
06:36:27 <elliott> Botcyclidine: well, 2014-(2004-8) gives the wrong result.
06:36:47 <Botcyclidine> like you can drink in the US either way, probably
06:36:48 <elliott> Dulnes: I felt a lot younger when I first joined here and I was 11 :/
06:37:11 <elliott> I know, right? your country is weird
06:37:25 <Dulnes> Your parents must be very lax to let you internet at 11
06:37:26 <elliott> alright this time I be the brit and you be the american
06:37:27 <HackEgo> [wiki] [[User talk:Orenwatson]] M http://esolangs.org/w/index.php?diff=41193&oldid=41182 * Oerjan * (+49) unsigned
06:37:44 <HackEgo> [wiki] [[User talk:Orenwatson]] M http://esolangs.org/w/index.php?diff=41194&oldid=41193 * Oerjan * (+1) oops
06:37:50 <elliott> Dulnes: I had internet for years before that.
06:38:18 <Dulnes> Ill probably die at 34
06:38:36 <Dulnes> Since i have seizures and such medical issues
06:38:38 <HackEgo> [wiki] [[User talk:BillGates]] M http://esolangs.org/w/index.php?diff=41195&oldid=41186 * Oerjan * (+50) unsigned
06:39:10 <elliott> I don't think any of my medical issues are likely to significantly shorten my lifespan
06:39:31 <elliott> that's not generally considered a medical issue Botcyclidine
06:40:43 <Dulnes> Seizures & Brain cancer are probably the top two that are going to kill me
06:40:45 <elliott> didn't they remove most of the paraphilia stuff
06:40:49 <Oren> due to my statistical groups I am most likely to die of suicide.
06:41:13 <Dulnes> guys dont talk bout suicide
06:41:39 <Dulnes> Anyways different topic
06:41:57 <int-e> I think I prefer fatal morbidity to Visual Studio support.
06:42:10 <HackEgo> [wiki] [[User talk:Josaphine O'Conner]] M http://esolangs.org/w/index.php?diff=41196&oldid=41191 * Oerjan * (+177) unsigned
06:42:10 <Botcyclidine> https://twitter.com/neuroecology/status/537790766178136064
06:42:27 <Oren> Ok, so long as you don't give me flashbacks to that attic in Akiba.
06:42:54 <madbr> msvc vs gcc... so many ways to interpret the same c++ standard
06:43:06 <Dulnes> Unplugs modem and dips it in hydrochloric acid
06:43:23 <Botcyclidine> geez mon, didn't know you were so sensitive about computational neuroscience
06:43:29 <madbr> also someone should be punched for 32 bit long in 64bit msvc vs 64bit in 64bit gcc
06:43:34 <madbr> no idea who but someone
06:43:56 <elliott> long should be 64-bit with mingw I think?
06:44:04 <elliott> a lot of things would break if it violated the platform ABI
06:44:14 <int-e> . o O ( "Of course people eat people. Which part of 'omni' in 'omnivore' didn't you understand?!" )
06:44:43 <Oren> elliot: not secret. you literally go to top floor of any store in akihabara and go upstairs. don't go to the top floor of any manga store... ever.
06:44:46 <Dulnes> Death isnt really a topic for me since im going to Die in 9 years and leave my kids behind.
06:45:16 <madbr> elliott: never really used mingw directly but if I'm not mistaken it has a mix of posix ABI stuff and win32 ABI stuff
06:45:43 <madbr> like, gcc link system but it also has to deal with msvc generated dlls to be useful
06:45:44 <Oren> just use int64_t if you need a particular bit length.
06:46:01 <Oren> or int32_t or whatever
06:46:06 <elliott> madbr: if it had 64-bit long then calling functions in libraries not compiled with mingw would be kinda bad
06:46:18 <Botcyclidine> i don't think HCl would be good for disposing of modems, btw
06:46:23 <madbr> no idea what it does
06:46:29 <madbr> it probably has a switch
06:46:43 <Oren> bubbles hydrogen gas... don't light a match
06:47:01 <Oren> or boom hindenburg
06:47:09 <Botcyclidine> well, yeah, but i mean it's notterribly efficient destruction wise
06:47:44 * oerjan wonders if Dulnes's irc client has the /me command
06:47:53 <madbr> elliott : windows/posix mixes are usually kinda insane, too
06:48:08 <zzo38> i DO USE mINgw FOR MY OWN PROGRAMS
06:48:17 <zzo38> I do use MinGW for my own programs
06:48:35 <Oren> why does the capslock key still exist
06:48:43 <zzo38> To type in all capitals
06:48:50 <zzo38> Oren: Why do you type in all lowercase then?
06:48:52 <Botcyclidine> so i have something to hit to turn on my mic. actually no zzo's answer is better.
06:49:11 <madbr> you can compile non-win32 executables in cygwin
06:49:18 <madbr> (ELF binaries I think)
06:49:21 <zzo38> Unfortunately the light on my keyboard to indicate caps lock is broken
06:50:02 <Oren> i type in all lowercase because i see no reason to press shift when i would be fully understood even if i did not.
06:51:09 <madbr> also: there are two x64 ABIs (microsoft/msvc and posix/gcc)
06:51:32 <madbr> yes that's retarded
06:51:47 <Oren> i set capslock to shift into japaneseたとえば、これ。
06:53:22 <madbr> it would be interesting to calculate the number of manhours lost to the win32 vs posix differences actually
06:54:15 <Oren> starting with every time i have to convert \r\n to \n
06:55:02 <Oren> and C:\\blah\\afsf to /blah/afsf
06:55:12 <zzo38> madbr: I try to write program to avoid such things, when they are needed I can use #ifdef and that stuff; for example to change stdin/stdout into binary mode if the program is using it
06:55:30 <zzo38> Oren: In Windows the C functions can you backslash or forward slash both are acceptable
06:55:54 <zzo38> And you can use fopen(...,"wb") it selects binary mode; on UNIX it is treated the same as "w"
06:57:04 <Botcyclidine> @tell Dulnes https://www.youtube.com/watch?v=TvlllG1FwjI revise your disposal strategies
06:58:05 <elliott> "Skip to 4:20 for the burst." I always skip to 420
06:58:43 <Botcyclidine> anyway it looks like it's caused by pressure buildup anyway
07:00:01 <Oren> my mom was all proud when I smoked pot for the first time. made me never want to do it again - what's the point if your mom doesn't hate it?
07:01:44 <Oren> i never did it again after that.
07:02:32 <Botcyclidine> last time i mentioned #drugz to my parents my mom related drinking booze through a catheter.
07:02:39 <madbr> zzo38 : yeah that's the basics of it but there's much more gory fallout
07:03:09 <madbr> like utf-16 vs utf-8 filename handling
07:04:18 <madbr> or abs() being integer on gcc (you're supposed to use fabs() instead, and it also interacts with the C/C++ divide)
07:04:58 <zzo38> I just always use ASCII filenames and avoid that issue
07:05:15 <madbr> also, caps sensitive filenames
07:05:33 <Oren> That's fine until your clients in Japan and Europe are yelling at you.
07:06:27 <Oren> because esmé.doc isn't uploading
07:07:12 <madbr> or your program gets installed to a path that has é somewhere in the folder name
07:07:44 <elliott> how do you even know about esme
07:07:56 <madbr> or you write a python 2 script. é appears somewhere. the whole thing crashes
07:08:09 <Oren> I have lurked on the wiki for ~three years
07:08:10 <madbr> (sorry but that's retarded)
07:09:07 <zzo38> It crashes because an incorrect character appears somewhere? That's certainly not good, it should just treat them as any other bytes in the input file are, and therefore don't crash.
07:09:27 <zzo38> Inside of an identifier it could display an error, but in a string literal it should be permitted.
07:09:38 <madbr> zzo38 : yes but obviously python2 was designed by an idiot
07:10:04 <madbr> in theory you're supposed to use a different string type
07:10:05 <Botcyclidine> i tried using eight bit characters for some ascii hardware i had and kana came out
07:10:39 <madbr> in practice, aint nobody have time for that
07:10:47 <zzo38> Botcyclidine: That is because you have to use the correct character encodings, clearly.
07:11:01 <Oren> hiragana or katakana? some old japanese computers mapped kana to some of the upper 128 chars
07:11:05 <zzo38> madbr: Do you mean normal strings are 7-bit character strings?
07:11:27 <zzo38> ASCII is only 7-bits so 8-bit character sets, if they are ASCII, are actually extended ASCII.
07:11:37 <Botcyclidine> Oren: kana. after some searching i found out it's a typeface particular to the kind of screen. it was almost shift-jis but not, so frustrating
07:11:54 <Oren> http://en.wikipedia.org/wiki/JIS_X_0201 probly
07:12:06 <madbr> basically if é appears anywhere, the default string operations in python2 cause an exception and stop the program
07:12:41 <Oren> wow I'm glad I use perl despite its linenoiseness
07:12:42 <madbr> because it's "invalid for the default string type you're supposed to use the unicode string type or something"
07:13:00 <elliott> unicode in perl is no picnic
07:13:11 <Botcyclidine> Oren: http://en.wikipedia.org/wiki/Hitachi_HD44780_LCD_controller#Font
07:13:34 <madbr> also retarded: the uppercase version of i in Java is I
07:13:41 <Botcyclidine> by the way, are you at all related to orenronen
07:13:44 <madbr> EXCEPT if your computer is in turkish
07:14:14 <b_jonas> So I have a serious question. In Funciton, how do you define a function that takes two lambdas and an integer as its input, and returns one of those two lambdas depending on whether that number is nonzero?
07:14:16 <elliott> can you lay off the "retarded"
07:14:20 <madbr> surprise your program crashes in turkey
07:14:40 <zzo38> I always use "C" locale and avoid such problems, but I wrote program in C anyways.
07:14:53 <Oren> the hitachi thing looks like a variant on jis 208
07:15:03 <Oren> or rather super set of
07:15:04 <zzo38> My shell scripts on UNIX systems I access I always set the locale to C explicitly in order to avoid problems
07:15:05 <Botcyclidine> the kana thing was also pretty funny because my program was super buggy and just dumped memory at the thing, so all this half-japanese gibberish scrolls by as i pull out my hair
07:15:16 <madbr> elliott: I've lost many hours to figuring out why some tool suddenly stopped working
07:15:32 <Botcyclidine> insulting things is fine, just use a different insult if you would
07:15:43 <elliott> you can say whatever you want, I'm just asking you not to use that word
07:15:52 <Oren> I am entirely unrelated to orenronen
07:16:01 <Oren> so far as I know
07:16:09 <madbr> and turning out because word decided to turn "..." into "…"
07:16:12 <zzo38> madbr: What tool is that?
07:16:14 -!- MoALTz__ has quit (Quit: Leaving).
07:16:49 <zzo38> Do you mean Microsoft Word? You can turn off autocorrection in Microsoft Word.
07:17:01 <madbr> zzo38 : an internal tool that turned an excel sheet of like all the sfx in a game (often with 1000+ sounds) into xml for the engine
07:17:10 <Botcyclidine> you could introduce yourself as mister dogfucker and i'd be like nice to meet you
07:17:17 <madbr> zzo38 : I know but the sound designer that made that excel sheet didn't
07:17:55 <HackEgo> [wiki] [[Talk:Funciton]] http://esolangs.org/w/index.php?diff=41197&oldid=38214 * B jonas * (+376) /* Conditional returning lambda */ new section
07:18:00 <madbr> or he typed some french into the comment section somewhere and the parser choked anyways
07:18:20 <madbr> or also some unicode version of "-" that's not the real dash
07:18:41 <Oren> I'm not Japanese -- I learned it from a dear friend in primary school. My last name is Watson
07:18:58 <zzo38> Those are some problems caused by Unicode and stuff, although it shouldn't care about the character encoding used in comments; that doesn't make sense.
07:19:06 <Botcyclidine> that you aren't japanese, anyway, not the other stuff
07:19:10 <Oren> My japanese is terrible but i can survive in japan
07:19:21 <madbr> zzo38 : the string just gets copied into a dictionary
07:19:36 <madbr> which is enough to crash the script
07:20:11 <zzo38> Yes, it is designed badly then
07:20:11 <madbr> because python2 strings crash instead of doing something sensible
07:21:16 <Oren> Why can't the language just treat all upper-byte characters as if they were legal identifier letters?
07:21:19 <madbr> also filling docs with "accents in filenames don't work" and adding checks in scripts etc
07:21:42 <zzo38> In the programs I have written I generally accept any characters in comments, but outside of comments usually only ASCII characters are allowed (although there are a few exceptions in some cases).
07:21:45 <Botcyclidine> why can't it just treat C1 control characters correctly, imo,
07:22:07 <madbr> Oren : probably got fixed in python3. which does you no good because nobody uses it because it's not compatible with python2
07:22:12 <zzo38> Oren: That is another way too, yes. CWEB converts all 128-255 characters into letters so that it can be used in a C program.
07:23:06 <elliott> b_jonas: sorry, this channel is about unicode :p
07:23:18 <madbr> sound designers are not technical people
07:23:28 <Oren> Becuause of this ascii rubbish all Japanese coders code their stuff in Engrish instead of understandable japanese
07:23:45 <elliott> b_jonas: but maybe this will help: Since the only datatype in Funciton is the arbitrary-size integer, a compliant interpreter must allocate a non-zero integer to every lambda closure the program creates. The lambda expression box returns an integer that identifies the closure, and the lambda invocation box will use the number to identify the lambda closure to invoke. This approach has many ...
07:23:47 <zzo38> Although, the #TITLE command in VGMCK accepts UTF-8 encoding
07:23:51 <elliott> ... advantages; in particular, you can automatically have lists of functions. The integers returned are required to be non-zero as a convenience so that the user code can still use the number 0 to mean null or false in cases where a lambda is optional.
07:24:06 <zzo38> Oren: I have seen program with the comments in Japanese though; it isn't much problem.
07:24:27 <madbr> they don't understand that calling a sfx explosion_deuxième_prise.wav is going to break some way or another
07:24:30 <zzo38> If the compiler doesn't accept arbitrary comments then it isn't very good.
07:25:28 <madbr> so then you need a second guy to go through their stuff to make it ok for computers because computers are stupid
07:25:40 <b_jonas> elliott: hmm, that might work
07:26:00 <b_jonas> elliott: that might cause some difficulties of how garbage collection works
07:26:21 <b_jonas> you'd have to define how exactly you're allowed to store functions to keep them referenced
07:26:33 <madbr> cap sensitive file systems will also break in not-so-cool way
07:26:37 <elliott> b_jonas: okay, but it doesn't, so by the axiom that GC never breaks a program, it will work
07:26:37 <b_jonas> so it's possible, but the language spec would need some extension for it
07:26:46 <oerjan> sounds like it pretty much excludes garbage collection
07:26:51 <madbr> name an asset Funky_stuff.wav
07:27:03 <elliott> you can do conditionals with lambdas as much as with integers
07:27:06 <b_jonas> oerjan: maybe… but this seems a more practical language than that
07:27:08 <madbr> play funky_stuff.wav in your code
07:27:09 <elliott> since they are integers :p
07:27:12 <Botcyclidine> can you use a conservative collector, btw i am not paying attention
07:27:16 <madbr> it looks like it works
07:27:20 <elliott> b_jonas: practical? it stores strings in BigInts
07:27:49 <madbr> surprise the sfx doesn't play on iphone or whatever because the file system is case sensitive
07:27:50 <b_jonas> elliott: yeah... and the example implementations of the functions aren't too efficient either
07:27:52 <elliott> not even with reasonable alignment (21 bits)
07:28:06 <madbr> and nobody caught it because it plays on windows
07:28:15 -!- Patashu has joined.
07:28:20 <Oren> In otherwords in order to be compatible with everything, you have to put everything as binary inside the exe.
07:28:23 <b_jonas> what I was thinking is that it would just extend the nand operation to return something sensible for lambdas, so that you can still use it for conditionals
07:28:52 <elliott> b_jonas: but lambda expressions evaluate to integers
07:28:52 <madbr> oren : one favorite strategy is "One huge data file"
07:28:53 <b_jonas> like, 0 NAND somelambda is still -1, and -1 NAND somelambda is somelambda, and stuff
07:29:01 <madbr> (usually a zip with compression turned off)
07:29:10 <madbr> the zip parses the same on every platform
07:29:21 <zzo38> You can put everything into a SQLite database for example too
07:29:35 <zzo38> There are many ways to put multiple data into one file
07:30:18 <b_jonas> elliott: you're right, the description says "
07:30:20 <madbr> zzo38 : like 10 meg data files that are going to be updated over svn and baked through data generation/compression scripts?
07:30:23 <b_jonas> Since the only datatype in Funciton is the arbitrary-size integer, a compliant interpreter must allocate a non-zero integer to every lambda closure the program creates.
07:30:29 <b_jonas> The lambda expression box returns an integer that identifies the closure, and the lambda invocation box will use the number to identify the lambda closure to invoke."
07:30:41 <b_jonas> so they practically can't be garbage collected
07:30:41 <elliott> b_jonas: I quoted that to you earlier :)
07:30:57 <elliott> probably not a great design decision, IMO
07:30:57 <b_jonas> elliott: I didn't know that was a quote
07:31:05 <madbr> zzo38 : also there are 1000 of these files
07:31:06 <b_jonas> ok, well this answers the question]
07:31:08 <elliott> ah, yeah, I should probably have added quotes
07:31:16 <elliott> sorry about that, bad dhabit
07:31:21 <oerjan> especially since lists of integers are essentially a form of godel encoding
07:31:36 <HackEgo> [wiki] [[Talk:Funciton]] http://esolangs.org/w/index.php?diff=41198&oldid=41197 * B jonas * (+173) /* Conditional returning lambda */
07:31:46 <oerjan> there's just no way to know how an integer referring to a lambda may be hidden
07:31:49 <madbr> zzo38 : also the suits/marketing guys want to have DLC and then you need multiple data paths for god damn everything
07:33:04 <Oren> Or it's an application that users make files with, so, you're at the mercy of the users' filename choices
07:33:06 <zzo38> madbr: Well, depending what file you can certainly still use SQLite; it is actually pretty powerful. There is also OHRRPGCE "lumped" foramts, which is like a simple file archive basically.
07:34:06 <Oren> for example saved games or user-made maps
07:34:17 <Oren> also have the problem
07:34:27 <madbr> uses free standing files
07:34:33 <elliott> oerjan: never mind hiding it, you could also just iterate through all integers and try calling them as lambdas later on
07:34:43 <zzo38> Yes I know how MegaZeux works
07:34:48 <madbr> a game is a folder of data files songs etc
07:34:58 <elliott> well maybe it dies if you hit an invalid one but that doesn't matter
07:34:58 <madbr> it used to be a DOS program
07:35:15 <madbr> which means that to even work on Posix it has to simulate caps insensitivity
07:35:15 <zzo38> Yes I know that too I used the DOS version and actually know of some of the significant differences
07:35:36 <zzo38> (Which actually broke some of my older MegaZeux games)
07:40:15 <Oren> i'm back from looking up megazeux
07:40:30 -!- Botcyclidine has quit (Quit: leaving).
07:40:47 -!- Bicyclidine has joined.
07:42:14 <Oren> is it just me or does every document file format eventually become turing complete?
07:42:49 <Oren> what with VBA and javascript for example
07:43:01 <lifthrasiir> wait a min, javascript is not a document file format
07:43:13 <zzo38> Oren: I don't know. I suppose it depend. I know TeX can do a lot of program.
07:43:20 <b_jonas> lifthrasiir: no, javascript in (html and in pdf)
07:43:22 <Oren> javascript was added to html becuase html was not sufficient
07:43:50 <Oren> VBA was added to docs and xls becuase they needed programmability
07:43:53 <zzo38> Oren: I think HTML is pretty sufficient really
07:44:23 <Oren> not sufficient for users' wants
07:45:13 <lifthrasiir> HTML as a document format is sufficient already, HTML as an application platform... would be never sufficient.
07:45:20 <b_jonas> Oren: you're getting it backwards. HTML is sufficient for what the users want, it's not sufficient for what the people who want to make their websites unusable want
07:45:40 <lifthrasiir> and we are living in the age that somehow mixes both
07:46:05 <b_jonas> (or maybe it's sufficient for what the users need, but not sufficient for what the users want?)
07:46:08 <madbr> javascript is not industrial grade enough to build a serious game on
07:46:09 <zzo38> HTML+CSS+JavaScript works as a VM in many cases, although it is a terrible design for such a thing!
07:48:33 <Oren> Which is why jquery was invented.
07:48:41 <Oren> and then angular js
07:49:05 <zzo38> No, it is still a terrible design; JavaScript isn't a bad programming language, it is that the VM design is terrible.
07:49:50 <Oren> no the ui is terrible. I want by drag and drop forms and buttons back, that I had for VB apps in 1999.
07:50:38 <b_jonas> the problem isn't with javascript, it's how many websites that wouldn't need it have an interface that require you to run a beefy box and wide bandwidth to access something that they could just publish on a simple text interface through a 32 kilobit/second modem
07:51:03 <b_jonas> including some online banking stuff
07:51:23 <b_jonas> and they manage to modify websites that used to work fine to do this too
07:51:24 <Oren> noone knows how to use telnet anymore.
07:51:38 <zzo38> I do think SSH would be better for this bank interface anyways
07:51:48 <b_jonas> Oren: it needn't be telnet, it can be just plain small htmls with no fancy javascript thingies where there's no point adding them
07:52:02 <zzo38> (Telnet isn't secure enough though. Actually, HTTPS also isn't quite as secure enough.)
07:52:13 <b_jonas> zzo38: no, I think just plain nineties style html with ZERO javascript and zero images would work for this banking interface
07:53:07 <b_jonas> they managed to make an interface where I can't just type a date to an input box, I have to use their fancy unusable javascripd date chooser
07:53:13 <zzo38> It would, but I think SSH is working OK
07:54:04 <b_jonas> zzo38: not for banking, but for other stuff, a html interface is usually better than an ssh interface, because it's easier to automate, especially if they put in helpful class and id attributes everywhere
07:54:27 <Oren> The problem is that there isn't a standard <input type="date"> in HTML<5
07:54:28 <zzo38> It deepnds much on the design.
07:55:30 <b_jonas> Oren: there is, but who cares, it can be just a plain text input box (which is what the html5 date control falls back to, and no matter the fancy control, I want to just type in a fucking date as YYYY-mm-dd without having to use the mouse and trying to navigate through calendar pages)
07:55:59 <b_jonas> they should just have a text input box
07:57:18 <b_jonas> at least the online banking interface has the advantage that it's completely replaced only like once every five years, unlike some crazy websites
07:58:50 <Oren> I dunno if that's a virtue. My father's website has worked the same since 1994, only the backend has been updated.
07:59:05 <b_jonas> it's a virtue only in comparison
07:59:35 <Oren> so it is exactly as you describe, no JS, all pure html forms
08:00:58 <b_jonas> I don't insist on having no javascript, only that it works without the javascript too.
08:01:09 <b_jonas> And the javascript shouldn't actively make it more difficult to use the page.
08:02:45 <Oren> maybe that's too much to ask though
08:04:16 <Oren> that any technology not create work as well as saving work, is too much to ask possibly
08:04:59 <Oren> I tend to get philosophical at 3am.
08:05:00 -!- nooga has joined.
08:08:12 -!- nisstyre has quit (Ping timeout: 265 seconds).
08:08:19 <Oren> Hello, London?
08:08:58 <Oren> or possibly Portugal
08:12:51 <Oren> related : http://xkcd.com/1335/
08:13:34 <Bicyclidine> i had to look up a country in africa at gmt. my first guess was niger, but it's just a little too far east
08:14:55 <Bicyclidine> hm. i bet elliott lives in Drowning Maud Land.
08:18:15 <oerjan> it's norwegian for Queen hth
08:18:37 <Oren> sanae - I immediately thought of 東方, and there is a user on this irc with the name drdanmaku
08:19:30 <oerjan> i don't think she drowned, she had something chronically bad let me check
08:19:38 <Oren> I pronounced that in my head as drawning, not drowning
08:20:20 <oerjan> that's good, if you want to be slightly closer to correct pronunciation
08:21:31 <oerjan> hm it seems to have been a sudden illness
08:21:42 <oerjan> https://en.wikipedia.org/wiki/Maud_of_Wales#Maud.27s_death
08:22:59 <Oren> youngest daughter of the king of england. european royalty have weird family trees
08:23:29 <Oren> but then so do I, blah...
08:23:58 <Bicyclidine> http://upload.wikimedia.org/wikipedia/commons/5/52/EgyptianPtolemies2.jpg
08:25:19 <oerjan> yeah our king's mother was swedish royalty, his (paternal) grandmother (maud) was english royalty and his grandfather was danish royalty
08:25:20 <Oren> yah a few kissing cousins doesn't compare
08:25:48 <oerjan> however both he and his son have married "ordinary" people
08:33:42 -!- nooga has quit (Ping timeout: 255 seconds).
08:36:08 -!- nisstyre has joined.
08:37:54 <Oren> idea: rather than most languages where we struggle or use libraries for dates and times, a language in which the only type is datetime.
08:39:08 <Oren> and containing many constructs useful for such type.
08:39:28 -!- nooga has joined.
08:40:17 <oerjan> it will be the first computer essentially based on computus
08:42:56 <Oren> characters -, T and : are reserved for ISO-8601 literals, which require no quoting. So you would just write x=2014-06-25T06:36:09
08:43:41 <Oren> also + for time zone
08:44:07 <Oren> in fact maybe use ADD DIVIDE COBOL style
08:45:08 <Oren> ADD 3 DAYS TO x.
08:46:48 <Oren> ROUND x TO A WEEK
08:46:53 <zzo38> What about, advance until Sunday, advance until full moon, advance until Easter, advance backwards such that Sun's ecliptic longitude matches that which Mars has during the current date...
08:47:17 <Oren> ROUND x TO NEXT SUNDAY
08:48:00 <Oren> Maybe ADVANCE is a clearer keyword tho
08:48:15 <Oren> This will be the SQL of dates.
08:48:35 <Oren> except that SQL is already the SQL of dates.
08:49:11 <zzo38> I know how to program SQL too. It has no commands like that though
08:51:05 <Oren> not like that, but most web programs store and handle dates in SQL that I've seen... that might just be me though
08:51:31 -!- oerjan has quit (Quit: Gnite).
08:51:51 <Oren> I think php has better native dates than perl -- that might be it.
08:53:57 <Oren> ADD 1 MONTH TO x -- this is a really complex operation for many reasons
08:54:25 <Oren> ADD 1 QUARTER to x
08:55:23 <Oren> ADVANCE x TO NEXT HOLIDAY
08:55:46 <Oren> requires sophisticated locale
08:57:34 <Oren> LET y BE ALL WEEKDAYS FROM x TO z.
08:57:52 <Oren> BUSINESS DAY is a thing too
08:58:44 <Oren> and then you have time. SET x TO 8:00 THAT DAY
08:59:47 <Oren> I'mma try and build a prototype of this when I have time.
09:03:28 <Oren> SET x TO LAST OF exam_days. ADD 1 DAY TO x. PRINT x.
09:04:08 <Oren> PRINT x AS DATE FORMAT WORDS
09:05:15 <Oren> >>>Wednesday, December 17, 2014
09:06:28 -!- nooga has quit (Ping timeout: 264 seconds).
09:09:04 <Oren> really every part of a datetime needs to be nullable.
09:27:22 -!- AndoDaan has joined.
09:30:24 <AndoDaan> Is it alright if I use a talk/discussion page, specifically MNNBFSL's, to write down my non concrete musing on possible constants/algorithms/converting from BF?
09:33:31 <Oren> converting from BF to what?
09:34:06 <AndoDaan> and i mean constants/algorithms in MNNBFSL
09:34:47 <zzo38> O, OK, I think is OK I suppose?
09:35:44 <mroman> AndoDaan: nice job on that MNNBFSL Interpreter
09:36:44 <AndoDaan> thanks! I'm not sure if it does error handling perfectly/well though. I might have to double check that.
09:37:11 <Oren> I see. まだ名前のないBrainfuck Stack Language is it?
09:38:17 <Oren> "not yet having a name"
09:38:59 <AndoDaan> As far as I could make out from google translate, that's what the author left the name as.
09:40:15 <mroman> wooho my little japanese knowledge finally pays off
09:41:27 <Oren> my japanese knowledge mostly pays off in not needing to wait for scanlators...
09:43:02 <HackEgo> [wiki] [[MNNBFSL]] M http://esolangs.org/w/index.php?diff=41199&oldid=41164 * Orenwatson * (+15) explained what language the name is in
09:43:53 <mroman> AndoDaan: you can btw. embed " in strings with \'
09:44:14 <mroman> \' is the escape sequence for "
09:45:02 <AndoDaan> Helpful, thanks. Should I add the link to the first mention of MNNBFSL (https://www.youtube.com/channel/UCdsOTr6SmDrxuWE7sJFrkhQ)
09:45:16 <AndoDaan> http://d.hatena.ne.jp/yshl/20140726
09:46:33 <AndoDaan> phew, accidental youtube link was non-incriminating.
09:47:44 <mroman> https://www.youtube.com/watch?v=M7JVlpm0eRs
09:48:07 <Oren> In that name, まだ名前のないBrainfuck風スタック言語 , the 風 which on the wiki is simply "fu" should be translated as "style" or "method"
09:48:32 <Oren> or transcribed properly as fū
09:49:43 <HackEgo> [wiki] [[MNNBFSL]] M http://esolangs.org/w/index.php?diff=41200&oldid=41199 * Orenwatson * (+11) made translation of fuu
09:51:53 <Oren> the fuu literally is the chinese character for "wind" but it also means the general "direction of flow" of something etc... chinese characters are hard
09:53:09 <Oren> and the sma echaracter is pronounced differently when it means the other meaning
09:53:41 <mroman> I didn't know something like gofundme existed
09:53:52 <mroman> and I'm suprised that they actually can raise the money
09:56:56 <Oren> According to the Japanese developer, this is a cat program in mnnbfsl:
09:56:58 <Oren> [<+++++"[->+++++<"][]">"++>] [.,]
09:57:13 <AndoDaan> You probably have to have a good pre-existing online presence to have any luck.
09:57:23 <Oren> why is it so different from the one on the wiki?
09:58:51 <mroman> AndoDaan: or a good story.
09:59:26 <fizzie> mroman: I wanted to distinguish it from "cheat".
09:59:27 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=41201&oldid=41200 * AndoDaan * (+28) /* Examples */ fixed wrong code
09:59:54 <mroman> supercheat > cheat > no cheat
10:00:23 -!- Oren_ has joined.
10:00:31 <Oren_> The other program on the japanese website is apparently a "busy loop"
10:01:36 -!- Oren has quit (Ping timeout: 246 seconds).
10:02:18 <myname> are there competitions for bf busy beavers?
10:02:23 <Oren_> this comment presents FizzBuzz in MNNBFSL
10:02:23 <fizzie> mroman: "no cheat" should (modulo bugs) find a valid solution to any solvable Dominosa instance (with the same size); "cheat" makes one untrue assumption and tweaks the search a bit to succeed on the three test puzzles and probably some vaguely defined subset of others; "supercheat" just encodes the output and doesn't actually solve the problem.
10:02:26 <Oren_> http://d.hatena.ne.jp/yshl/20140823
10:02:58 <AndoDaan> Oren_, https://github.com/yshl/MNNBFSL/tree/master/example it's all gathered there.
10:04:28 <mroman> that's what we call an embed solution
10:04:36 <mroman> which is usually suffixed with (embed)
10:04:44 <fizzie> I've heard the term, but int-e was using just (cheat).
10:05:27 <fizzie> In retrospect, that would've been more informative, if less whimsical.
10:09:14 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=41202&oldid=41201 * AndoDaan * (+23) /* Commands */ changed 9+1 to 9=8+1
10:12:15 <AndoDaan> Looking at the cat example, it seems it's using the loop method I've been trying to form.
10:24:35 -!- Dulnes has quit (Quit: Connection closed for inactivity).
10:43:34 <b_jonas> `8ball is it too early yet?
10:46:03 <zzo38> It is too early for what?
10:47:14 <Oren_> to be awake possibly
10:47:43 <Oren_> how can it be too early yet though is another question.
10:48:37 <Oren_> yet implies something is false will become true, but being too early only ever changes from true to false ... hmmm....
10:49:25 -!- nooga has joined.
10:50:10 <zzo38> Don't you have a clock?
11:06:18 <b_jonas> http://underhanded.xcott.com/?p=26 The 7th Underhanded C Contest is now Open
11:06:44 <b_jonas> yeah, twelve days old news. I didn't notice till now.
11:07:27 <b_jonas> also, 23rd IOCCC winners announced: http://www.de.ioccc.org/2014/whowon.html
11:08:44 <FireFly> Yusuke Endoh is that Ruby guy, isn't he?
11:09:24 <b_jonas> wait, two klingon web servers?
11:11:01 <FireFly> also the guy who made http://mamememo.blogspot.se/2010/09/qlobe.html and https://github.com/mame/quine-relay
11:18:32 -!- boily has joined.
11:28:49 -!- AndoDaan has quit (Ping timeout: 255 seconds).
12:01:27 -!- Patashu has quit (Ping timeout: 240 seconds).
12:29:27 -!- boily has quit (Quit: FLAMBÉD CHICKEN).
12:58:56 -!- GeekDude has joined.
12:59:04 -!- Phantom_Hoover has joined.
13:10:34 <Sgeo> :( beginning to look like Rust flat out won't work for my use case
13:29:25 <int-e> . o O ( Use case: Erecting a Steel Framework. )
14:02:16 -!- hjulle has joined.
14:13:32 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41203&oldid=41096 * TomPN * (+3) /* Increase and decreasing the value of a cell */
14:36:05 -!- GeekDude has changed nick to GeekAfk.
15:06:24 <J_Arcane> Anyone had any experience with F#?
15:20:55 -!- hjulle has quit (Remote host closed the connection).
15:41:14 -!- cluid has joined.
15:41:36 <cluid> b_jonas, did you work on Janus?
15:42:09 <cluid> i got confused sorry
15:44:49 <cluid> zzo38, BTW, I saw some dead links on C2 wiki
15:45:12 <Phantom_Hoover> so i've just realised that i don't actually know what colour red bull is
15:47:31 <ion> It is colored E150a and E101.
15:47:33 -!- idris-bot has quit (Quit: Terminated).
15:48:17 <cluid> I would like to improve the RegXy page on esoteric wiki
15:48:29 <cluid> but also I couldn't find it because I thought itw ould be called Reg Xy
15:48:44 -!- idris-bot has joined.
15:49:06 -!- GeekAfk has changed nick to GeekDude.
15:50:08 -!- Sprocklem has joined.
15:53:42 <b_jonas> is there something like a comesub, which is like a comefrom but pushes the from address to the return stack? or would that defeat the whole point of comefrom?
15:53:56 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
15:55:26 -!- GeekDude has changed nick to GeekAfk.
16:08:30 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
16:12:25 -!- nooga has quit (Ping timeout: 256 seconds).
16:13:15 <cluid> where can i see the code
16:13:16 <cluid> http://www.de.ioccc.org/2014/whowon.html
16:14:02 <b_jonas> cluid: you can't yet. the source code is usually released a few weeks later, probably in January
16:14:02 <fizzie> Usually it takes them a while to release the sources.
16:20:25 -!- cluid has quit (Remote host closed the connection).
16:25:08 -!- GeekAfk has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
16:39:44 -!- shikhin has joined.
16:42:28 -!- ZombieAlive has joined.
16:48:45 -!- Dulnes has joined.
17:01:51 -!- Lorenzo64 has joined.
17:06:32 -!- Sprocklem has quit (Ping timeout: 240 seconds).
17:26:07 -!- tlewkow has joined.
18:01:26 -!- nys has joined.
18:06:57 <Oren_> Why doesn't C have a bitwise rotate operator???
18:07:30 <J_Arcane> Oren_: Same answer as any C question: because it hates you.
18:07:32 <Oren_> My assignment is to do SHA1
18:09:01 <Oren_> So I have to define yet another bit_rotate() macro... a macro which appears in so many programs, like the max macro
18:10:51 <Oren_> Proposal for C2020 - add a variadic max operator
18:11:47 <Oren_> And a ones-complement add operator.
18:11:49 <elliott> defining a correct, type-generic max is kind of hard.
18:12:23 <Oren_> So long as it works for integers and floats...
18:12:25 <elliott> in fact it might require C11
18:12:35 <elliott> Oren_: the main problem is that max(x, y) usually evaluates x or y twice
18:12:48 <Oren_> that's why it should be in the compiler...
18:13:03 <elliott> you can avoid this with gcc statement expressions but, I think, at the cost of breaking things if y references whatever name was used to put the result of x in
18:13:08 <elliott> (I don't think gcc has proper gensym)
18:13:13 <b_jonas> Oren_: libecb has a bit rotation function/macro, see http://software.schmorp.de/pkg/libecb.html
18:13:16 <elliott> with C11, you can use _Generic and dispatch to actual functions
18:13:45 <b_jonas> Oren_: you could try to use that instead of defining your own
18:13:48 <Oren_> max(x, y) should be a macro for __Max() or something, the way they did typeof and bool
18:13:54 -!- Lorenzo64 has quit (Ping timeout: 264 seconds).
18:14:12 <elliott> well, building it into the compiler is kind of sad.
18:14:19 <elliott> it's like admitting your language has zero abstraction power.
18:14:38 <Oren_> C *does* have zero abstraction power
18:15:06 <Oren_> #define has less power than sed
18:16:13 <coppro> elliott: fuck _Generic
18:16:16 <coppro> fuck everything about it
18:16:47 <Gregor> Such strong feelings X-D
18:16:51 <elliott> Oren_: aw c'mon, people have implemented functional programming languages entirely in the preprocessor
18:17:20 <coppro> Gregor: it's a horrible hack
18:17:27 <Oren_> IImade a sed scipr once that added a swap operator
18:17:56 <coppro> the C committee persists in adopting very poor solutions to their problems
18:18:10 <Oren_> becuase it is a commitee
18:18:36 * elliott looks for that thing gcc has that is kind of like gensym
18:18:38 <coppro> Oren_: C++'s committee is waaaaaay more sane
18:18:40 <elliott> at least I remember it having something along those lines
18:18:42 <Oren_> good languages are designed by one visionary or two, not 15 guys
18:19:01 <coppro> although I guess that C++ is the exception that proves the rule
18:19:07 <elliott> gcc has some magical builtins
18:19:07 <elliott> — Built-in Function: void * __builtin_apply (void (*function)(), void *arguments, size_t size)
18:19:09 -!- Lorenzo64 has joined.
18:19:11 <elliott> This built-in function invokes function with a copy of the parameters described by arguments and size.
18:19:18 <elliott> Oren_: haskell is designed by committee
18:19:37 <elliott> the Great Man theory has been obsolete for a while :p
18:20:44 <Bicyclidine> i wish we'd go back to "visionary" meaning "hallucinating"
18:20:52 -!- Oren_ has left.
18:22:12 <elliott> was that a ragequit, or...
18:23:41 <elliott> of course it is maybe relevant that haskell was designed by committee /after/ said committee had separately made a bunch of languages similar to Haskell that they wanted to unify
18:24:47 -!- tlewkow has quit (Remote host closed the connection).
18:26:12 <HackEgo> [wiki] [[Special:Log/newusers]] create * SuperJedi224 * New user account
18:26:26 <Gregor> I was recently implementing an assembler (of sorts) for x86_64.
18:26:27 <HackEgo> [wiki] [[User:SuperJedi224]] N http://esolangs.org/w/index.php?oldid=41204 * SuperJedi224 * (+6) Created page with "Hello!"
18:26:43 <Gregor> x86_64 machine code is a true nightmare.
18:29:23 <HackEgo> [wiki] [[GridScript]] N http://esolangs.org/w/index.php?oldid=41205 * SuperJedi224 * (+655) Created page with "GridScript is an esoteric programming language designed by SuperJedi224. It is not yet implemented. ==Sample Programs== ===Hello World=== #Hello World. @width 4 @heigh 1 (1..."
18:31:10 <Gregor> Of course it's an octothorpe.
18:31:28 <Gregor> That's the original(?)/best name for it.
18:31:44 <Bicyclidine> i imagine originally it was called something like "what the hell is this"
18:32:39 <Gregor> Bicyclidine: http://en.wikipedia.org/wiki/Number_sign#Other_names_in_English <-- srsly, octothorpe is for real X-D
18:32:39 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41206&oldid=41205 * SuperJedi224 * (+91) /* Sample Programs */
18:33:27 <HackEgo> [wiki] [[Talk:GridScript]] N http://esolangs.org/w/index.php?oldid=41207 * 71.222.118.42 * (+162) the pearl that lies in the sea hard by the loud-breathing serpent
18:34:15 <elliott> gonna just put completely random quotes in my edit summaries from now on
18:34:42 <Bicyclidine> my other edit summary was "hot singles in fungot's area" but that was nearly relevant, i'll have to be more careful
18:34:44 <fungot> Bicyclidine: but t-rex, you can't play the game optimally! and assuming that in a man... or a woman, dromiceiomimus
18:34:44 -!- tlewkow has joined.
18:35:30 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41208&oldid=41206 * SuperJedi224 * (+0)
18:35:59 -!- tlewkow has quit (Remote host closed the connection).
18:36:31 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41209&oldid=41208 * SuperJedi224 * (+27)
18:36:56 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41210&oldid=41120 * SuperJedi224 * (+17) /* G */
18:37:57 <elliott> I quite like the edit summary no https://esolangs.org/w/index.php?title=X%2B%2B&diff=prev&oldid=40155
18:38:00 <elliott> I think I was very tired for that
18:38:42 -!- Bicyclidine has quit (Quit: Lost terminal).
18:39:40 -!- tlewkow has joined.
18:40:06 -!- tlewkow has quit (Remote host closed the connection).
18:41:35 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41211&oldid=41209 * SuperJedi224 * (-1) /* Truth Machine */
18:41:43 -!- Bicyclidine has joined.
18:42:25 <fungot> FireFly: all that means is that if a building? tornadoes? ghost ships! ships sent sailing and found drifting weeks or months or so, with some stranger's fingers in my mouth was full of cans of frozen concentrated juice at the grocery store, i'd miss tasting the inside, there's real organs!
18:43:04 <FireFly> eeh, if that's what you're into, fungot...
18:43:04 <fungot> FireFly: a bush. so that raises a good point, t-rex? that would be good to have you for dinner, t-rex
18:43:48 <fungot> FireFly: but that makes things worse than ever! everybody is going to be a surprise
18:45:33 -!- tlewkow has joined.
18:50:01 <J_Arcane> Hooray for native support for imaginary numbers ...
18:55:18 -!- tlewkow has quit (Remote host closed the connection).
18:59:20 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41212&oldid=41211 * SuperJedi224 * (+659) /* Sample Programs */
19:01:04 <fizzie> Hooray for good, logical argumentation at the Finnish Parliament regarding this citizen petition about allowing same-sex marriage: (paraphrasing) "It's not about equality. We don't have jurisdiction to change the laws of nature."
19:03:05 <Bicyclidine> parliament learns about bird reproduction, institutes new "it's not cheating if they're more than 50 meters away" rule
19:04:35 <fizzie> "It's obvious that the change would be detrimental to children's rights."
19:04:51 <fizzie> Most of the opponents are playing the "but think of the children" card.
19:04:52 -!- Oren has joined.
19:06:08 <nys> man for all the good finnish things..
19:06:49 <fizzie> (Adoption rights are one of the major things differentiating Finland's current "civil partnership" from marriage, that's why.)
19:10:20 <J_Arcane> The man I ordered a pizza from which never arrived this evening is apparently in the hospital with a neck injury sustained after someone struck him head on while he was delivering said pizza ...
19:10:51 <elliott> I hope the pizza was worth it
19:11:47 <J_Arcane> His brother just arrived with our pizzas and a free bottle of coke.
19:12:54 <elliott> a free bottle of coke for getting your deliverer in hospital
19:13:26 <J_Arcane> I just hope he's OK. He's a really nice guy, and he makes the best kebab in town.
19:13:54 <elliott> horrible strategy: pay people to hunt down and injure those delivering your pizza so you always get free stuff
19:13:57 <J_Arcane> My wife had to take the call, and she didn't have the heart to ask for a refund.
19:14:09 <elliott> neck injuries sound unpleasant
19:16:10 <fizzie> http://isometri.cc/strips/this_is_neck_crick/ yes
19:22:43 -!- Sprocklem has joined.
19:28:01 -!- Sprocklem has quit (Ping timeout: 250 seconds).
19:34:36 -!- Dulnes has quit (Quit: Connection closed for inactivity).
19:47:47 -!- nooga has joined.
19:51:13 -!- ais523 has joined.
19:55:13 -!- Oren has quit (Ping timeout: 246 seconds).
20:03:08 -!- Patashu has joined.
20:07:51 -!- Oren has joined.
20:22:05 -!- AnotherTest has joined.
20:22:15 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41213&oldid=41212 * SuperJedi224 * (+241)
20:22:27 <b_jonas> ais523: in case you missed it, the ioccc winners' name is out: http://www.de.ioccc.org/2014/whowon.html
20:22:45 <b_jonas> also the Underhanded C contest is open: http://underhanded.xcott.com/
20:22:56 <ais523> b_jonas: I noticed both, but thanks for the reminder
20:24:22 -!- Lorenzo64 has quit (Quit: Leaving).
20:25:53 -!- Patashu has quit (Ping timeout: 245 seconds).
20:31:03 -!- callforjudgement has joined.
20:31:18 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
20:31:30 -!- ais523 has quit (Disconnected by services).
20:31:32 -!- callforjudgement has changed nick to ais523.
20:32:36 -!- Bicyclidine has joined.
20:46:52 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41214&oldid=41213 * SuperJedi224 * (+468)
20:50:28 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41215&oldid=41214 * SuperJedi224 * (+38) /* Fibonacci Sequence */
20:55:18 -!- tlewkow has joined.
21:01:54 -!- tlewkow has quit (Remote host closed the connection).
21:02:20 -!- Sprocklem has joined.
21:12:44 -!- hjulle has joined.
21:22:31 -!- tlewkow has joined.
21:34:31 -!- nisstyre has quit (Changing host).
21:34:31 -!- nisstyre has joined.
21:43:54 -!- nys has quit (Quit: quit).
21:53:40 -!- shikhout has joined.
21:54:55 -!- Oren has quit (Ping timeout: 246 seconds).
21:55:50 -!- AnotherTest has quit (Remote host closed the connection).
21:56:53 -!- shikhin has quit (Ping timeout: 264 seconds).
21:56:56 -!- Oren has joined.
22:02:17 -!- ais523 has quit (Read error: Connection reset by peer).
22:02:31 -!- ais523 has joined.
22:02:35 -!- GeekDude has joined.
22:02:51 -!- tlewkow has quit (Remote host closed the connection).
22:03:49 -!- tlewkow has joined.
22:16:09 -!- Sprocklem has quit (Ping timeout: 258 seconds).
22:26:04 <elliott> does anyone know how long catching a SIGSEGV usually takes
22:26:20 <elliott> (from the invalid access to getting your SIGSEGV handler called)
22:26:22 -!- callforjudgement has joined.
22:27:12 -!- ais523 has quit (Ping timeout: 240 seconds).
22:27:34 -!- callforjudgement has changed nick to ais523.
22:33:58 <Oren> depends greatly on OS and I think that is the kind of thing that would depend on processor model
22:34:12 <Oren> some processors can't even detect it...
22:35:46 <elliott> "modern x86 unix", I'm only looking for a rough estimate really
22:36:33 <elliott> I sort of suspect that using this to detect running out of a bump-allocator memory pool is a lot worse than just adding a branch to allocation unless running out is extremely rare, but I'm curious
22:37:12 <Oren> So then it depends on what the linux kernel does on interrupt vector number 13
22:38:02 <Bicyclidine> me, i use synthesis os, so i get forty thousand interrupts per second and it works,
22:49:32 -!- oerjan has joined.
22:51:58 -!- dts has changed nick to dts|feasting.
22:53:17 -!- ais523 has quit (Ping timeout: 255 seconds).
22:53:43 -!- ais523 has joined.
22:59:04 -!- Oren has quit (Quit: Page closed).
23:04:20 -!- mhi^ has joined.
23:15:28 -!- nooga has quit (Ping timeout: 240 seconds).
23:16:06 -!- S1 has joined.
23:17:23 -!- nooga has joined.
23:18:13 -!- S1 has quit (Client Quit).
23:20:48 -!- Froox has quit (Read error: Connection reset by peer).
23:21:06 -!- Froox has joined.
23:32:30 -!- ais523 has quit (Read error: Connection reset by peer).
23:32:41 -!- ais523 has joined.
23:34:02 <oerjan> @tell mroman <mroman> which is usually suffixed with (embed) <-- if you want people to follow conventions you should actually state them on the website hth
23:34:17 <fizzie> elliott: I have the vaguest feeling I actually tested the "trap sigsegv and fake 0" Befunge stack against a regular "test on every pop" stack, and... well, I think the signal handling was "pretty fast" in an absolute sense, but still of course orders of magnitude slower than a single test. (On the other hand, many Befunge programs never pop from an empty stack at all.)
23:34:55 <fizzie> I'm sure people have benchmarked Linux signal delivery overhead, though, which I'd guesstimate is the larger component, compared to the hardware side.
23:35:02 <elliott> fizzie: I'm wondering about it for, e.g., knowing when you're out of copying GC heap.
23:35:17 <elliott> I think collections in a generational collector are probably too frequent for it to pay off.
23:37:25 <oerjan> how many befunge programs test the depth of stack?
23:38:07 <oerjan> it might be easier to have a sizeable buffer of zeros preallocated
23:38:07 <FireFly> I imagine even if programs do pop an empty stack, they probably do it infrequently
23:38:17 -!- nooga has quit (Ping timeout: 255 seconds).
23:38:27 <oerjan> and have the depth test do a subtraction
23:39:50 <oerjan> then the sigsegv thing could bump that back up, causing a low average cost
23:42:02 <oerjan> there's that a* word i can never remember again
23:42:21 <fizzie> I wouldn't be surprised if Mycology was the only real program that actually checked stack depth.
23:42:46 <oerjan> `learn_append oerjan He can never remember the word "amortized" so he put it here for convenience.
23:42:48 <HackEgo> Learned 'oerjan': Your evil overlord oerjan is a lazy expert in future computation. Also an antediluvian Norwegian who hates Roald Dahl. He can never remember the word "amortized" so he put it here for convenience.
23:43:18 <oerjan> now i just have to remember that i put it there should be easy
23:43:20 -!- Phantom_Hoover has joined.
23:43:29 <HackEgo> Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards with dodgy SHIFT KEys, and five genders. (See also: tanebventions)
23:43:58 <Taneb> `learn Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards with dodgy SHIFT KEys, and cube root of five genders. (See also: tanebventions)
23:44:01 <HackEgo> Learned 'taneb': Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards with dodgy SHIFT KEys, and cube root of five genders. (See also: tanebventions)
23:44:33 <Taneb> Sounds about right
23:47:03 <oerjan> wait i thought i'd memorized that as 0.701something
23:48:01 <Taneb> There is sooomething that begins like that
23:48:10 <oerjan> oh that's approximately e of course
23:48:45 <oerjan> oh well my logarithms in the head are rarely more accurate than 0.7 anyway
23:49:24 <Taneb> My brother passed his driving test today :)
23:52:43 <Taneb> He is 60% of my nick
23:52:49 <oerjan> that's what i remembered
23:54:30 <oerjan> 0.30103 should be easy to remember
23:55:28 <FireFly> Not as easy as 2.718281828
23:55:35 <oerjan> hm that might have a large continued fraction coefficient
23:56:00 <elliott> how much faster is call compared to push + jmp? surprisingly google doesn't have an answer for this
23:56:08 <elliott> interested in the corresponding answer for ret, also
23:56:33 <oerjan> > 1/(1/logBase 10 2-3)
23:56:46 <oerjan> > 1/(1/(1/logBase 10 2-3)-3)
23:56:59 <oerjan> > 1/(1/(1/(1/logBase 10 2-3)-3)-9)
23:57:13 <oerjan> > 1/(1/(1/(1/(1/logBase 10 2-3)-3)-9)-2)
23:57:38 <oerjan> maybe it doesn't really show up as that. well 9 is fairly large.
23:58:05 <oerjan> > 1/(1/(1/(pi-3)-7)-15)
23:58:47 <lambdabot> No instance for (GHC.Show.Show a0)
23:58:47 <lambdabot> arising from a use of ‘M57241604867522287715068.show_M57241604867522287715...
23:58:47 <lambdabot> The type variable ‘a0’ is ambiguous
23:58:47 <lambdabot> Note: there are several potential instances:
23:59:16 <FireFly> [ <. (1 %@| ])^:(<20) 10^.2
23:59:16 <j-bot> FireFly: 0 3 3 9 2 2 4 6 2 1 1 3 1 18 1 6 1 7 1 1
00:00:59 <FireFly> Hm, what was that anagolf task again...
00:01:51 <oerjan> > 1/(1/(1/0.30103-3)-3)
00:02:19 <oerjan> > 1/(1/(1/(1/0.30103-3)-3)-9)
00:02:29 <oerjan> > 1/(1/(1/(1/(1/0.30103-3)-3)-9)-2)
00:02:45 <oerjan> > 1/(1/(1/(1/(1/(1/(1/0.30103-3)-3)-9)-2)-2)-4)
00:03:30 <oerjan> > 1/(1/(1/(1/(1/(1/(1/0.30103-3)-3)-9)-2)-2)-4) :: Rational
00:04:38 <oerjan> > 1/(1/(1/(1/(1/(1/(1/0.30102-3)-3)-9)-2)-2)-4) :: Rational
00:06:03 <FireFly> oh, you changed a decimal digit
00:08:01 -!- Froox has changed nick to Frooxius.
00:08:18 <elliott> here I was hoping fizzie would take that bait too
00:08:27 <elliott> I guess I could, like, "measure" it or whatever
00:12:44 <shachaf> I think ret is generally easier to predict than an arbitrary indirect jump.
00:18:00 <int-e> shachaf: Right, but it wouldn't have to be that way. It's because compilers know that using 'ret' for returning to some other point than where the previous "call" was comes at a stiff price. I'm sure they would happily take advantage of a cheap instruction that just happens to jump to the address on top of the stack, popping it.
00:19:13 <int-e> The stiff price being that no CPU will ever predict the target correctly.
00:20:08 <int-e> and, of course, a cascade of similar failures further down the stack.
00:35:03 <FireFly> Why did anagolf accept a trailing space
00:35:22 <FireFly> I thought it was annoyingly anal about things like that
00:35:23 <ais523> it's not its job to correct your stupid mistakes
00:36:12 <HackEgo> [wiki] [[MNNBFSL]] http://esolangs.org/w/index.php?diff=41216&oldid=41202 * Oerjan * (+96) include original Japanese
00:37:16 <oerjan> FireFly: it is anal except at the very end of output
00:43:18 -!- boily has joined.
00:43:46 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41217&oldid=41215 * Oerjan * (+48) fmt
00:54:20 -!- callforjudgement has joined.
00:54:55 -!- ais523 has quit (Read error: Connection reset by peer).
00:56:41 -!- callforjudgement has changed nick to ais523.
00:56:51 <HackEgo> [wiki] [[REGXY]] http://esolangs.org/w/index.php?diff=41218&oldid=7994 * Oerjan * (+91) The link on C2 Wiki was bitrotted so include the right one here
01:07:31 -!- Dulnes has joined.
01:07:38 <HackEgo> [wiki] [[Reg Xy]] N http://esolangs.org/w/index.php?oldid=41219 * Oerjan * (+65) Add redirect
01:11:33 <elliott> happy thank give to you too
01:12:29 <Dulnes> Im doing swell i guess
01:15:01 <elliott> nothing I want to go into in #esoteric :p
01:16:32 <Dulnes> These § why are they even added
01:16:47 <elliott> aw c'mon, I'd give that answer tons, it's just not a common question in here :p
01:17:45 <Bicyclidine> oh, right, it's section mark if you're not a nerd like i am
01:19:36 <HackEgo> [wiki] [[REBEL]] M http://esolangs.org/w/index.php?diff=41220&oldid=41103 * Kendfrey * (-11) Changed link to point to new site
01:22:15 <elliott> Taneb: pikhq_: how are *you* on this merry thank give
01:22:20 <elliott> yeah that was just an excuse to say thank give again
01:23:04 <Taneb> Well, I'm listening to I'm Sorry I Haven't A Clue
01:23:21 <pikhq_> I have no pants on and am playing Pokemon.
01:25:10 -!- mhi^ has quit (Quit: Lost terminal).
01:26:18 <ais523> I've been sort-of considering getting that myself
01:26:37 <Taneb> Not sure if I should go for Alpha Sapphire or Omega Ruby though
01:26:41 <ais523> but I'd need to buy a new console
01:26:58 <pikhq_> My impression is that it's where they actually put most of their work into, rather than XY.
01:27:02 * oerjan goes back to tatham's puzzles
01:27:25 <FireFly> Not sure if I can justify getting OR/AS given how much (or little, rather) time I spent on X/Y
01:27:58 <Dulnes> Taneb both are exactly the same and are relativaly short only difference is the main villain and the new graphics
01:28:12 <Taneb> Dulnes, hence the hard decisions
01:28:21 <ais523> pikhq_: well they put most of the work into ORAS back when they were making Ruby/Sapphire
01:28:25 <Dulnes> Team nerd or team bara
01:28:56 <Dulnes> Magma or what was the other one i only played ruby
01:28:58 <pikhq_> Hence why ORAS is where they threw a lot of gameplay tweaks.
01:29:25 <boily> quintopia: QUINTHELLOPIA! (should you ever answer while you're mexicaning.)
01:29:36 <FireFly> They had the new-rendering-engine thing for XY
01:29:40 <Dulnes> Yeah in the caves you cant traverse it by memory
01:29:50 <Dulnes> You need to defeat the gym leader
01:29:59 <FireFly> and new engine overall, I guess
01:30:21 * pikhq_ has greatly appreciated little details like "offering to teleport you instead of forced backtracking".
01:30:57 <pikhq_> Also, DexNav is glorious.
01:31:00 <Dulnes> My wife says Hi... i have to go eat family dinner
01:31:19 <pikhq_> It's like breeding Pokemon, only much less agonizing!
01:31:43 <ais523> what is DexNav, anyway?
01:31:58 <Taneb> pikhq_, if you've go Sapphire I shall get Omega Ruby!
01:32:18 <ais523> oh, it managed to get onto Bulbapedia before they locked the site down due to hacking
01:32:24 <elliott> sapphire was my first pokemon game
01:32:41 <Taneb> Emerald was mine, I'm young
01:32:48 <pikhq_> There's a menu in the PokeNav that lets you see Pokemon in the route you're in. You can tap on one of them to find more of 'em...
01:32:49 <elliott> aren't you like a lot older than me
01:32:53 <FireFly> Gold was mine, I'm slightly less young
01:33:00 <ais523> oh, it's basically Habitat List from BW2, but prettier
01:33:06 <elliott> I guess I'm actually just as old as old people now though
01:33:24 <Taneb> elliott, I'm like 9 months older
01:33:25 <Bicyclidine> but yeah i didn't get into pokemon like everyone i know did
01:33:33 <pikhq_> More you encounter the Pokemon, the better the Pokemon you find with DexNav are.
01:33:36 <ais523> Habitat List is great, anyway
01:34:00 <elliott> Taneb: what if you being born somehow metaphysically caused me to be conceived (per the hexham synchronicity)
01:34:04 <pikhq_> So you get decent odds of shiny Pokemon, of higher level, with egg moves, and 3+ maxed IVs.
01:34:45 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41221&oldid=41217 * SuperJedi224 * (-63) /* 99 Bottles of Beer on the Wall */
01:35:14 <ais523> my theory is that the Pokémon people decided there was no way they could stop RNG abuse, and decided to make it unnecessary
01:35:20 <ais523> however, wild Pokémon with egg moves seems wrong to me
01:36:11 <pikhq_> It's a much smaller list of moves than the full list of possible egg moves.
01:36:15 <Taneb> elliott, somehow I doubt it
01:36:16 <pikhq_> Oh, also chance of hidden ability.
01:36:33 <HackEgo> Hexham es la ciudad mas importante de programación esotérico
01:36:47 <ais523> that said, I'm upset at the "no illegal egg move combinations"
01:37:08 <ais523> I'm /not/ upset at hidden abilities becoming commonplace, the old way of treating them like event Pokémon drove me out of competitive for a year
01:37:15 <ais523> (until BW2 mostly fixed it using Hidden Hollows)
01:37:30 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41222&oldid=41221 * SuperJedi224 * (+0) /* 99 Bottles of Beer on the Wall */
01:37:37 <pikhq_> XY had the Friend Safari making them more common, and additionally made them breadable.
01:38:22 <pikhq_> Also fun, XY + ORAS has all the non-event legendaries.
01:38:31 <pikhq_> And one of the event legendaries.
01:38:31 <ais523> pikhq_: they always were breedable, from females
01:38:42 <ais523> getting the first female was very hard in BW and quite hard in B2W2, though
01:38:42 <pikhq_> Males have a low chance now.
01:38:54 <pikhq_> (Deoxys is just in ORAS' postgame)
01:38:57 <ais523> and some things they wanted to be rare were male only, e.g. eevee, starters
01:39:42 <pikhq_> Not to mention XY made IV breeding much, much simpler.
01:39:57 <ais523> I rather liked the old method where you screwed around with the RNG
01:40:16 <ais523> that said, I was recently doing random-IVs + flawless ditto to make the first round of parents
01:40:21 <ais523> one of them was quad-flawless (!)
01:40:26 <ais523> this was just for Subway, so I'm using it
01:40:31 <ais523> (quad in useful stats, as well)
01:40:46 <pikhq_> You have a flawless ditto? Wonderful.
01:41:07 <pikhq_> Congrats, it's possible to pass 5 of those to any Pokemon you want.
01:41:14 -!- Phantom_Hoover has quit (Quit: Leaving).
01:41:22 <pikhq_> Natures can also be inherited.
01:41:36 <ais523> pikhq_: natures have been inheritable for absolutely ages
01:41:40 <ais523> since the original R/S, I think
01:41:54 <ais523> also, destiny knot doesn't determine a specific parent to pass IVs
01:42:16 <ais523> flawless ditto was one of my earlier RNGs
01:42:35 <ais523> (the first was an event arceus, which was a bad place to start in retrospect, it took 11 hours and I still didn't get Adamant)
01:43:47 <Dulnes> In black and white on route 3 a shiny zorarork or however you spell it has a chance of just appearing
01:43:49 <pikhq_> Gen VI changes Destiny Knot to being 5, and the EV items force a specific IV as well.
01:44:00 <pikhq_> Still doesn't determine whose IVs you get, but hey.
01:44:07 <ais523> Dulnes: I don't believe you
01:44:09 <ais523> actually I can possibly prove it
01:44:25 <pikhq_> Yeah, wasn't Zoroark B/W shiny-locked?
01:44:27 <Dulnes> A shuckle can have the highest damage though
01:45:02 <ais523> pikhq_: more to the point, Zoroark and Zorua never appear wild in any version, barring Memory Link
01:45:09 <ais523> err, any gen 5 version
01:45:28 <ais523> I have a Zorua from Memory Link that can be bred into infinite zoroarks if necessary
01:45:30 <Dulnes> Mm then idk where this zorarok came from
01:45:39 <ais523> (together with straight-30 IVs, just like other Memory Link mons)
01:45:43 <Dulnes> Says i met it on route thtee
01:45:55 <pikhq_> AH, right. BW2 on, a parent holding an everstone will pass down its nature in particular.
01:45:55 -!- tlewkow has quit (Remote host closed the connection).
01:45:56 <FireFly> Hacked 'mon traded on GTS?
01:46:01 <pikhq_> That was the exact change.
01:46:15 <ais523> pikhq_: before that, there's a 50% chance
01:46:29 <pikhq_> I didn't pay much attention to breeding before XY.
01:47:04 <pikhq_> Hah, right. It's stupid, but one other thing: Pokeballs are also inherited in gen VI. :)
01:47:49 <ais523> pikhq_: I did know that
01:47:50 <FireFly> From which of the parents?
01:48:03 <ais523> Luxury Balls are thus what you should use for catches, if you can
01:48:18 <ais523> pikhq_: basically, AFAICT, Nintendo have decided to make legality checking as hard as possible
01:48:24 <ais523> to hide the fact that they're rubbish at it
01:48:47 <pikhq_> I'm kinda glad about how they implemented it though...
01:49:00 <pikhq_> This basically means that a cheater is not likely to have a huge advantage.
01:49:20 <Dulnes> I heard a lvl 100 shuckle if used correctly can deal the largest ammount of damage in the game
01:49:33 <ais523> Dulnes: "used correctly" = "the opponent cooperates"
01:49:54 <Dulnes> No i think.its the moves and items you use
01:50:47 <Dulnes> The opponent doesnt have to do much you just need really high defense to stand against its atk until you get your move set out
01:50:59 <ais523> Dulnes: is your opponent using Shedinja (maximum percent damage) / whatever it is for maximum raw damage?
01:51:15 <ais523> and no, the opponent also has to not switch while you're putting all the defence drops on them
01:51:23 <ais523> and not just OHKO the shuckle when you power trick
01:51:57 <Bicyclidine> me, i'm just excited to learn that metronome can do metronome
01:52:14 <Taneb> Bicyclidine, does it recurse?
01:52:45 <pikhq_> I like that Surfing on a Sharpedo is much faster now.
01:52:53 <FireFly> It'd be fun if it could be made to recurse multiple times in a row with RNG abuse
01:53:06 <FireFly> pikhq_: Sharpedo specifically?
01:53:22 <pikhq_> Surf in general was sped up, and Sharpedo in particular goes twice as fast.
01:53:29 <Taneb> With a malicious RNG it could recurse indefinitely
01:55:18 <Bicyclidine> i haven't played a pokemon in years, but i'm guessing yes because that sounds funny
01:56:23 -!- tlewkow has joined.
01:57:25 <pikhq_> Also, the encounter rate in water was reduced a lot; yay.
02:02:40 * pikhq_ has been getting a lot of use out of his 3DS.
02:03:48 <ais523> hmm, I spent some of last night reverse-engineering the formula for what happens when you use Rock Smash in HGSS
02:06:29 -!- hjulle has quit (Ping timeout: 264 seconds).
02:23:42 -!- J_Arcane_ has joined.
02:26:21 -!- J_Arcane has quit (Ping timeout: 265 seconds).
02:26:36 -!- J_Arcane_ has changed nick to J_Arcane.
02:32:08 -!- callforjudgement has joined.
02:32:22 -!- ais523 has quit (Read error: Connection reset by peer).
02:33:16 -!- AndoDaan has joined.
02:35:24 -!- boily has quit (Quit: APPLICATIVE CHICKEN).
02:35:25 -!- tlewkow has quit (Remote host closed the connection).
02:35:43 -!- tlewkow has joined.
02:46:09 <pikhq_> callforjudgement: Alas, if you want ORAS you should probably wait for the New 3DS to come out.
02:46:51 <callforjudgement> pikhq_: well, I'm a bit dubious about the whole 3DS thing in the first place, for the same reason I dislike the DSi
02:46:58 <pikhq_> Nintendo, in a typical show of being-Nintendo, managed to make a new DS model only come out along with a new Pokemon game in Japan.
02:47:05 <pikhq_> Dulnes: That's what it's called, the New 3DS.
02:47:19 <Dulnes> And does it do? new stuff
02:47:19 <pikhq_> callforjudgement: Unlike the DSi, it's a rather notable upgrade in hardware.
02:47:39 <pikhq_> callforjudgement: And there's, y'know, games worthwhile on it.
02:48:06 -!- callforjudgement has changed nick to ais523.
02:48:11 <pikhq_> Dulnes: Faster CPU, has a second analog stick, has face tracking so that the 3D sucks less.
02:48:18 <ais523> I'm more worried about things like streetpass
02:48:36 <pikhq_> Both are only ever used in fairly trivial ways by games.
02:48:36 <Dulnes> Ok whats the second analog stick do?
02:48:50 <madbr> is it equivalent to the "circle pad"?
02:48:57 <Dulnes> Im perfectly content with the DS i have
02:48:57 <pikhq_> madbr: It's more an analog nub.
02:49:16 <Dulnes> Why would they make a new one why not a new system in general
02:49:17 <pikhq_> It's presented as a second stick to games coded to read it, like Smash Bros.
02:49:49 <pikhq_> It also works for games that used the circle pad addon.
02:49:52 <Dulnes> Well the wii U is very slick
02:50:09 <Dulnes> Especially all these games they pumped out this yesr
02:50:25 <pikhq_> ais523: I think the most notable use of Streetpass in any 3DS game I'm aware of is the Streetpass Plaza games which come on the system.
02:50:39 <ais523> can I delete or otherwise get rid of them?
02:50:43 <pikhq_> It's otherwise a trivial, very minor feature that is 100% ignorable if you don't care about it.
02:50:48 <pikhq_> No, it's part of the firmware.
02:51:11 <Dulnes> You cant jailbreak it?
02:51:16 <pikhq_> Though, it won't streetpass *at all* unless you go in and set it to.
02:51:41 <pikhq_> Basically literally everything that does streetpass asks you if you want to enable streetpass functionality for the game.
02:51:59 <Dulnes> Majoras mask remake though
02:52:00 <pikhq_> (and you can go into the system settings later and undo it)
02:52:13 <madbr> wii u finally has its smash bros
02:52:56 <Dulnes> Nintendo is making every one hyped up for their latest installation to the LoZ series in 2015
02:52:58 <pikhq_> It also only streetpasses when the Wifi is on.
02:53:22 <Dulnes> If its as cartoony as the trailer i wont bother for it
02:53:30 <madbr> at least one thing nintendo understands: video games aren't movies
02:53:52 <pikhq_> The play coin thing isn't able to be turned off, but it also matters even less.
02:54:07 <pikhq_> ais523: Any other concerns?
02:54:23 <Dulnes> Whats the point of the puzzles
02:55:08 <ais523> pikhq_: the reason I didn't impulse-buy one a while back is that apparently they don't come with chargers in the EU
02:55:14 <pikhq_> That's just the 3DS XL.
02:55:22 <ais523> oh, the regular-size one does have a charger?
02:55:22 <pikhq_> THough I don't know *why*.
02:55:36 <Dulnes> Btw i bought my 3ds this June and still havent figured.it all out
02:56:29 <pikhq_> It uses the same charger as the DSi,FWIW.
02:56:29 <Dulnes> The XL has a charger or am i reading that wrong
02:56:44 <pikhq_> Dulnes: The US 3DS XL is the only one that comes with a charger.
02:57:08 <ais523> pikhq_: I don't have a DSi, though
02:57:11 <ais523> because the original is better
02:57:12 <pikhq_> Likewise the US New 3DS will be the only one that comes with a charger.
02:57:29 <pikhq_> I have a 3DS and an original DS. :)
02:57:43 <Dulnes> ? why does the Us only have chargers
02:57:48 <pikhq_> Dulnes: FUck if I know.
02:57:52 <madbr> so many game designers see what they're doing as building narratives and stories and whatever
02:57:56 <pikhq_> Admittedly the 3DS makes the DSi literally pointless.
02:58:02 <madbr> games are not movies
02:58:05 <pikhq_> There is nothing the DSi does that the 3DS does not.
02:58:35 <Dulnes> LoZ is very good with its time travel sequences that if thought about to long hurt
02:58:35 <zzo38> Yes I agree games are not supposed to be movies; many games have too many cutscenes!
02:58:54 <pikhq_> Even though what the DSi does that the DS does not is, well, hardly anything. :)
02:59:10 <ais523> pikhq_: what the DSi does that the DS does not is why I don't like the DSi, though
02:59:12 <pikhq_> I think the most notable is that some games, like BW, can use WPA.
02:59:13 <Dulnes> Nintendo has short cutscenes that get straight to the point but still set a story
02:59:15 <ais523> things like the console having its own memory
02:59:21 <ais523> and accepting downloads
02:59:26 <ais523> this is not what I want from a games console at all
02:59:37 <ais523> Dulnes: I take it you've never played Pokémon Mystery Dungeon
02:59:43 <ais523> it has cutscenes long enough that they have multiple save points in
02:59:50 <pikhq_> ais523: The 3DS only has its own memory for DSi compat though; uses an SD card for storage otherwise.
02:59:50 <ais523> also, flashbacks to earlier in the same cutscene
03:00:04 <pikhq_> (and it works just fine without an SD card, though downloads won't work then)
03:00:06 <ais523> what's wrong with just storing things on the cartridge?
03:00:11 <Dulnes> ais523: that sounds awful
03:00:11 <zzo38> I happen to prefer just text windows that you can read at your own speed (or skip if you prefer) rather than having a lot of video cutscenes and stuff
03:00:19 <pikhq_> Note that 3DS carts *do* save on the cartridge.
03:00:55 <ais523> "Also since i cannot access the IRC because of some weird issue all i know is that im going to be a detrament to this community"
03:01:00 <Dulnes> Nintendo does put the skip option in for some games and all games have the manual text skip in a cutscene
03:01:10 <pikhq_> The SD card is used for downloaded games, pictures taken with the camera app, and game patches.
03:01:19 <ais523> XY needed several of those
03:01:32 <zzo38> I think save game should be stored in a memory card (such as CF cards), rather than in the console or in the cartridge (although it can be a cartridge that is also a memory card; of course a DVD or CD will be read-only though)
03:02:06 <ais523> Pokémon don't like people copying saves because you can clone Pokémon that way
03:02:17 <ais523> so presumably the saves are locked to the SD card somehow, for downloaded versions
03:02:28 <Dulnes> Do you have to buy the SD card in other countrys seperately from the console
03:02:48 <Dulnes> It comes with inside of it already
03:03:26 <Dulnes> I swear im having a brain fart
03:04:23 <pikhq_> Ah, so that's how they do it. The 3DS on-board storage is accessible to games...
03:04:34 <pikhq_> Pokemon stores a small key on the console.
03:04:44 -!- AndoDaan has quit (Read error: Connection reset by peer).
03:04:45 <pikhq_> Changing key each time it saves.
03:04:54 <ais523> for downloads, presumably
03:05:00 <ais523> I hope you can move the cart between consoles
03:05:10 -!- AndoDaan has joined.
03:05:48 <pikhq_> I suspect that they're using generic infrastructure for downloads there.
03:06:14 <madbr> In theory, the story of half life 2 is about aliens taking over. In practice, half life 2 is about the story of a mute repeatedly launching filing cabinets at people’s heads.
03:06:16 <pikhq_> (just like on the Wii, downloads are console-specific)
03:06:58 -!- AndoDaan has quit (Read error: Connection reset by peer).
03:07:03 <pikhq_> ais523: FWIW, I've even tested that.
03:07:20 <pikhq_> Just a matter of taking my AS cart and putting it in my girlfriend's 3DS.
03:07:21 -!- AndoDaan has joined.
03:08:17 <ais523> at this rate, we're going to have to prove the Pokémon video game TC so that it's ontopic
03:08:48 <pikhq_> Yeah, Gen I and II are TC.
03:08:49 <Bicyclidine> http://arxiv.org/abs/1203.1895 i find it hard to believe you haven't seen it, though, so maybe you mean something else?
03:09:08 <Bicyclidine> oh, wait, that's complexity not computation
03:09:24 <pikhq_> Gen I and II can be made to execute arbitrary code. :)
03:10:02 <ais523> Bicyclidine: oh, I have seen that, and realised what it was as soon as I saw the existence of the link
03:10:10 <ais523> (also, that's technically PSPACE-complete)
03:10:13 <ais523> pikhq_: Gen III's very close, too
03:10:21 <ais523> you should see what people do with the Pomeg Glitch
03:10:33 <pikhq_> Yeah, it's not actually arbitrary, but there's a decent bit of PEEK and POKE available with that one.
03:11:03 * pikhq_ is particularly fond of Pokemon glitched speedrunning
03:11:15 <ais523> http://bulbapedia.bulbagarden.net/wiki/Pomeg_glitch#Access_Pok.C3.A9mon_beyond_slot_6
03:11:26 <ais523> it's only a small step from there to completely screwing up memory
03:11:30 <ais523> as you already have a buffer overflow
03:11:45 <pikhq_> Yeah. It's not quite there but it's really close.
03:12:16 <pikhq_> And quite entertaining for speedrunning.
03:13:26 <pikhq_> Alas. I want to eat. I do not want to cook. I don't have leftovers. It is Thanksgiving.
03:14:03 <pikhq_> Probably keep watching MST3K.
03:15:43 <J_Arcane> I now have a customizable string split function. Go-go gadget easy parsing.
03:15:46 <J_Arcane> There's a slight bug though. When two delimiters get stuck next to each other you wind up with a little null string in the middle.
03:16:23 * pikhq_ has a gzip util that sucks less than standard, to go along with a zlib that sucks less than standard.
03:16:28 <ais523> that might be intentional, it's what you'd intuitively expect given what splitting does
03:17:18 <pikhq_> Pity the zlib API sucks.
03:17:36 <J_Arcane> ais523: Yeah. I think it's unavoidable given my algo, and it's easily filter'd for.
03:18:30 <pikhq_> elliott: Well, for starters it's significantly smaller.
03:18:55 <pikhq_> And it actually uses zlib instead of having its own code for it forked from an early version of infozip.
03:19:05 <elliott> haha, gzip doesn't use zlib?
03:20:06 <elliott> is this because GNU or something
03:20:11 <J_Arcane> I gotta say though, 4am is a really shitty time to finally figure out how to write your function ...
03:20:27 <pikhq_> I think it predates zlib actually.
03:21:00 <J_Arcane> elliott: Well, it's 5:19 here, but it was 4 when I woke with a horrible cramp and then couldn't sleep because my brain chose *that moment* to solve my funciton.
03:22:00 <pikhq_> The opposite-endianness of zlib vs. PNG makes me even more upset now.
03:22:06 <pikhq_> zlib was invented for the sole purpose of PNG.
03:23:42 <Taneb> It's impressive that GNU hello has 184 lines
03:24:00 <J_Arcane> It also took me longer because my comments didn't accurately describe what left$ and right$ do, and I'm considering changing what they do to be something more useful. It really seems like they should take the left or right half from a pivot index, rather than taking X from left or right. The latter seems less useful.
03:24:02 <madbr> pikhq : whatare their respective endianness?
03:24:10 <Bicyclidine> you know what's impressive? defibrillators
03:24:12 <ais523> Taneb: note that GNU hello exists as a sandbox for people to practice doing development correctly on
03:24:18 <Bicyclidine> just think about it. who came up with that? how did they /test/ it
03:24:26 <ais523> you should see the Debian packaging for GNU hello, it's just as overengineered for the same reason
03:24:32 <Taneb> ais523, oh really?
03:24:53 <Bicyclidine> "The primary purpose of GNU Hello is to demonstrate how to write other programs that do these things; it serves as a model for GNU coding standards and GNU maintainer practices."
03:25:16 <pikhq_> PNG uses big-endian for everything.
03:25:26 <pikhq_> zlib uses little-endian for its header.
03:25:43 <madbr> which one came first?
03:26:12 <int-e> Taneb: I find it more amazing that it still can't read mail.
03:26:21 <elliott> int-e: I thought it actually could
03:26:28 <pikhq_> zlib was the compression portion of the PNG reference implementation.
03:27:35 <pikhq_> They literally sat down and decided "it'll be big endian here and little endian here".
03:27:38 <zzo38> DVI is big-endian, Z-machine is almost always big-endian (no small-endian files exist), Knuth's MMIX instruction set is big-endian, etc. A lot of DOS programs use file formats with small-endian (since a PC uses small-endian natively).
03:28:08 <zzo38> Also programs that were originally designed for DOS tend to use small-endian even if they are now ported to other systems.
03:28:36 <madbr> don't most architectures that started 8 bits ended up little endian?
03:28:50 <madbr> like 6502 if I'm not mistaken
03:29:30 <madbr> trying to figure where the cultural divide comes from
03:29:34 <int-e> elliott: ah, yes it could. http://git.savannah.gnu.org/cgit/hello.git/commit/?id=1a962e1e873d382c376921ef41ad234bd1bf4339
03:30:11 <elliott> int-e: how dare they?! that feature is important to me!
03:31:00 <elliott> nice "portable" alloca implementation
03:31:45 <madbr> "Historically, byte order distinction was born out of the mainframe vs. microprocessor approach.[dubious – discuss] Until the 1970s virtually all processors were big-endian."
03:31:54 <pikhq_> elliott: What, in gnulib?
03:32:25 <pikhq_> Wait, no, that's not from gnulib.
03:33:00 <elliott> and doesn't actually allocate on the stack?
03:33:10 <elliott> it has linked lists. alloca using linked lists. why would you ever use this
03:33:36 <zzo38> Yes 6502 is also small-endian
03:33:41 <pikhq_> I'm pretty sure that's actually a property of Cray API.
03:33:58 <ais523> the basic difference between big-endian and little-endian is what happens if you cast a pointer from pointing at one size of integer, to pointing at a smaller size
03:34:08 <pikhq_> It seems as though the Cray *stack* formed a linked list.
03:34:12 <ais523> big-endian does an approximation scaled based on the full range; little-endian does modulo
03:34:13 <zzo38> ais523: Yes, and for that purpose small-endian works better
03:34:22 <ais523> and modulo is what's better if the value is actually within the range you want already
03:34:43 <madbr> little endian: x86, 6502, z80, dec alpha, atmel, vax
03:35:37 <madbr> big endian: 68k, superh, power, other atmel, system/360
03:36:37 <pikhq_> madbr: New POWER systems from IBM are little endian actually.
03:36:46 <zzo38> There are also systems with no endianness, although these are mostly VMs I suppose; in such a case the file format still has endianness although the runtime won't
03:37:04 <madbr> pikhq_ : it's like they changed the whole ABI?
03:37:11 <pikhq_> For reasons I'm not entirely sure of they decided to switch endianness and ABI.
03:37:28 <pikhq_> Note though that POWER has always been a bi-endian architecture.
03:37:43 <madbr> ARM is also bi-endian in theory
03:37:51 <madbr> in practice, it's little endian
03:37:56 <int-e> pikhq_: it's not uncommon for a stack to be organized in a linked list of stack frames; this facilitates unrolling the stack (for debuggers, or possibly for delivering exceptions)
03:38:12 <int-e> pikhq_: a tad old-fashioned, perhaps
03:38:15 <pikhq_> Yeah, POWER just had it be big endian in practice.
03:38:18 <zzo38> Some file formats can use both big-endian and small-endian, such as TIFF and Z-machine (although small-endian was never used, and was removed in EZIP). Some formats use the host's endianness (and int size), such as OASYS.
03:38:37 <pikhq_> Though run-time switchable.
03:38:54 <madbr> switchable endian formats sound like a bad idea to me
03:39:18 <elliott> 03:33:32 <pikhq_> It seems as though the Cray *stack* formed a linked list.
03:39:28 <madbr> do you want ppl to implement support for your format or do you want to drive them away?
03:39:39 <zzo38> madbr: Yes it does, but, TIFF has that feature. Z-machine had it but they removed that feature, I suppose they then knew how bad it is.
03:40:11 <pikhq_> IIRC TIFF did it as a weird compromise.
03:40:22 <pikhq_> TIFF is one of those "design by committee" standards.
03:41:01 <int-e> . o O ( People argue about little ends and big ends when we all know that eggs naturally come to rest on their sides... )
03:41:21 <madbr> also the reason why C/C++ still has digraphs after all these years
03:41:33 <pikhq_> That's even simpler actually.
03:41:39 <pikhq_> IBM *actually uses those*.
03:41:40 <Bicyclidine> the fact endianness is named after a joke argument and people still argue over it is fucking incredible, i love it
03:42:03 <pikhq_> Some of the EBCDIC code pages actually, really need it.
03:42:04 <zzo38> int-e: If you put into a flat surface it will probably fall down and end on its side, but, it seems that some people can manage to make it to stand up straight!
03:42:06 <Taneb> Middle-endian best endian
03:42:14 <pikhq_> And the jerks won't adopt UTF-EBCDIC.
03:42:18 <madbr> pikhq : ebcdic is also an abomination
03:42:28 <pikhq_> Or go out and shoot OS/360 in the head.
03:42:35 <zzo38> EBCDIC is much worse than ASCII, I agree that much.
03:42:48 <pikhq_> EBCDIC also was a mistake at the time.
03:44:00 <pikhq_> (no, literally: the IBM 360 mainframe was supposed to be ASCII or EBCDIC, with EBCDIC purely for compatibility with BCDIC data. But they couldn't fix bugs in the ASCII mode before they released.)
03:44:06 <elliott> int-e: side-endian would be, like, 32-bit values a, b, c and d would be laid out in memory as the bytes abcdabcdabcdabcd?
03:44:30 <int-e> Bicyclidine: to be fair, the joke argument is the basis of a whole book.
03:44:40 <pikhq_> int-e: NAh, it's the basis of a chapter.
03:45:15 <pikhq_> Lilliput is just a chapter in the Travels.
03:45:40 <pikhq_> Admittedly it's the first one.
03:46:12 <ais523> it's one chapter of four, IIRC
03:46:16 <ais523> so a quarter of a whole book?
03:46:40 <ais523> anyway, the chapter was about the way that ridiculous arguments can come about, so naming the computer science debate after the fictional one makes a ton of sense
03:46:48 <madbr> it's all that series of things that have no purpose other than breaking c++ code when you port it
03:47:21 <madbr> file system differences
03:47:32 <pikhq_> Writing C on a mainframe is pretty hilarious, too, cause you do it inside a Unix environment.
03:47:39 <pikhq_> A Unix environment... with EBCDIC.
03:48:03 <int-e> elliott: mixed endianness exists. ethernet encodes bytes in a little endian order, but the protocols above usually use big endian byte order.
03:48:29 <madbr> also: strange C99 features that aren't in C++
03:48:36 <zzo38> If you need to, don't write the program directly for the mainframe but for an emulator and run the emulator on the mainframe computer.
03:48:44 <int-e> so ... a 16 bit word would be transmitted as 89ABCDEF01234567
03:49:25 <elliott> int-e: yes; what I meant was more interleaving values with each other
03:49:25 <madbr> like variable size stack arrays
03:49:28 <int-e> (I'm numbering bits mathematically; 0 is the bit with value 2^0)
03:49:29 <zzo38> pikhq_: That is a possibility, but it could even be Inferno, or a PC emulator, or whatever
03:49:47 <int-e> elliott: yeah, but it's not interleaving that's happening here.
03:49:47 <pikhq_> Just naming Java because I know it's actually used on mainframes.
03:50:02 <elliott> int-e: but interleaving is closer to the egg on its side :)
03:50:02 <pikhq_> I suspect other emulators *might* actually need porting effort.
03:50:20 <madbr> C++ to C linking insanity
03:50:22 <pikhq_> zzo38: Of course a still simpler way of doing it is to just require a Linux VM on their hypervisor.
03:50:38 <zzo38> And then you can have your program to use ASCII even if it is a EBCDIC computer.
03:51:01 <pikhq_> At which point the only weird thing is that the system console is still one of IBM's really weird terminals rather than a VT100 alike.
03:51:03 <zzo38> pikhq_: How exactly does that work? I don't know a lot about that things
03:51:30 <ais523> there's probably some format out there that genuinely does use the forward slashes :-)
03:51:52 <pikhq_> (this is not observable from the OS point of view; the kernel maps between that terminal and a VT100)
03:52:03 <pikhq_> zzo38: Easily. Linux just has a mainframe port.
03:52:15 <elliott> int-e: nice, that 2^0 thing is a good argument for little endian actually
03:52:48 <ais523> elliott: AFAICT the only reason the argument came about in the first place is historical accident with the way people write numbes
03:52:48 <pikhq_> If you feel like it, and have oodles of money, you can just get an IBM mainframe and run nothing but Linux on it.
03:53:07 <pikhq_> A more *realistic* use of this is to get an IBM mainframe, run the IBM hypervisor, and run a *ton* of Linux on it.
03:53:13 <ais523> pikhq_: actually, ISTR the mainframes are cheaper if you only run Linux on them?
03:53:36 <ais523> like, they have some way of slightly damaging the hardware so that it won't run the old mainframe OSes, but that Linux can worka round
03:53:39 -!- shikhin has joined.
03:53:39 <ais523> presumably a reversible one
03:53:43 <elliott> what kind of specs do modern monolithic IBM mainframes have these days, anyway?
03:53:53 <ais523> to make sure that you aren't cheating and trying to run something other than Linux on a Linux-only mainframe
03:54:00 <pikhq_> The mainframe OS stuff is an excuse to leach money from big old companies anyways.
03:54:45 <madbr> old company cannot change due to inertia and people too close to retirement -> milk out $
03:54:52 <ais523> pikhq_: as I understand it, mainframes were once the only systems that could do what they do
03:54:54 <pikhq_> elliott: 5.5GHz hex core CPUs, up to 101 such CPUs.
03:55:04 <ais523> and nowadays, there's the reasonable alternative of "huge cluster of commodity hardware"
03:55:21 <pikhq_> ais523: Oh, certainly.
03:55:26 <elliott> pikhq_: and oodles of RAM?
03:55:52 <pikhq_> Way back in the day if you were a big enough company to really need computing power, a mainframe was the economical option.
03:56:28 -!- shikhout has quit (Ping timeout: 240 seconds).
03:56:45 <madbr> how much overlap does this have with cobol?
03:57:13 <pikhq_> IBM mainframe users tend to run COBOL extensively.
03:57:50 <zzo38> I did read somewhere that someone went to a store that sells computer, and asked for a mainframe computer because he/she wanted to learn to program in COBOL.
03:57:57 <pikhq_> elliott: They offer 3TB of RAM.
03:58:07 <zzo38> But now we have OpenCOBOL so you can run it on a PC and stuff too.
03:58:08 <pikhq_> And then 6.4TB of SSD for swap.
03:58:15 <elliott> offer as in "up to" or as in what people actually get? nice, either way
03:58:28 <pikhq_> As in "if you wish to pay for that much, this is what you get".
03:58:28 <elliott> I guess that's "only" ~30 gigabytes per CPU if you get all of them
03:58:45 <elliott> I assume completely maxed-out systems aren't the norm, though...
03:59:29 <pikhq_> Actually, they probably are. These big suckers are leased by CPU usage, not by system specs.
04:00:15 <elliott> I think I knew that but forgot
04:00:18 <pikhq_> The smaller ones I think are sold.
04:01:49 <madbr> this is like... a collection of everything I want to stay as far as possible from :3
04:02:01 <madbr> buisiness computing etc
04:03:08 <pikhq_> A brand new one can cost millions.
04:03:20 <zzo38> Well, at least now you don't have to do all that worse stuff like IBM mainframes with EBCDIC and so on; now you can use OpenCOBOL for common business oriented programming instead.
04:03:47 <madbr> it's the kind of architecture that has decimal floating point too, right? :D
04:03:51 <pikhq_> The small one we have at work is more like $80k total.
04:04:06 <zzo38> (Of course you needn't even use COBOL if you want to use other programming languages instead.)
04:04:14 <pikhq_> (we're not a mainframe shop, but unfortunately we have clients that are, so we need to have one to test against)
04:04:54 -!- bb010g has joined.
04:07:00 -!- shikhin has quit (Ping timeout: 256 seconds).
04:07:32 <pikhq_> It is probably a good thing I find really weird computers entertaining.
04:07:54 <ais523> pikhq_: well, when C-INTERCAL was first announced, it was sent to a community for people entertained by old and weird computers
04:08:00 <ais523> because there weren't really esolang communities at the time
04:08:22 <pikhq_> It is also a *really* good thing that the mainframe stuff is kinda just a portion of my job rather than the whole thing.
04:08:34 <pikhq_> I imagine I'd go mad if I did that all day every day.
04:09:15 <madbr> dude, I had a java project once, and I was crawling up the curtains
04:09:53 <pikhq_> (for future reference: parsing COBOL with yacc is irritating, cause IBM doesn't believe in BNF)
04:10:25 <pikhq_> IBM believes in money.
04:10:34 <pikhq_> And the acquisition of wealth.
04:11:12 <madbr> ibm is the original out of touch technocratic company
04:11:19 <zzo38> Not that there is anything wrong with money, but, *love of* money is the root of all evil.......
04:11:34 <madbr> they're like microsoft squared in that respect
04:12:04 <zzo38> Parsing COBOL with yacc is irritating? Can you describe how exactly?
04:12:11 <elliott> @google ibm company songbook
04:12:12 <lambdabot> http://arstechnica.com/business/2014/08/tripping-through-ibms-astonishingly-insane-1937-corporate-songbook/
04:12:12 <lambdabot> Title: Tripping through IBM’s astonishingly insane 1937 corporate songbook | Ars T...
04:12:15 <J_Arcane> Even in the beginning, it was basically IBM, and everyone else. IBM does things the IBM way.
04:12:35 <pikhq_> zzo38: Well, see, the syntax is just *not very well specified* and only *barely* context-free.
04:13:02 <pikhq_> Also, tokenization is god damned insane.
04:13:25 <zzo38> pikhq_: It isn't specified? What? Can't you look at how OpenCOBOL does it?
04:13:44 <pikhq_> There's little details like "the first X and last Y columns are comments"...
04:14:00 <J_Arcane> pikhq_: Sounds like me trying to make sense of BASIC, *10.
04:14:16 <zzo38> Those things can be done in the tokenizer before you tell the parser what to do
04:14:33 <pikhq_> And "if there's character X in this column, you concatenate it with the previous line except when you're in a string literal, in which case you skip to the next instance of '"' and then concatenate the rest of the line".
04:14:42 <pikhq_> zzo38: Unfortunately not really.
04:14:56 <pikhq_> IBM COBOL is heavy on the non-standard extensions as well.
04:15:11 <zzo38> pikhq_: Maybe in yacc it is difficult, but did you try using Lemon? It is an alternative to yacc
04:15:14 <pikhq_> Which is all the more amusing because standard COBOL died.
04:15:20 <zzo38> And in my opinion, Lemon is much better
04:15:22 <pikhq_> I didn't know about Lemon.
04:15:30 <pikhq_> And I don't care now, because It Is Done.
04:16:13 <zzo38> Ah, OK, but maybe you can look at anyways in case it help later on for something.
04:16:40 <zzo38> Lemon uses no global variables so you can run multiple parsers at once, and the tokenizer calls the parser instead of the parser calling the tokenizer.
04:16:47 <zzo38> (Lemon is also in public domain.)
04:16:49 <elliott> pikhq_: how does that string literal thing work?
04:17:22 <pikhq_> elliott: You basically specify that a line is a continuation of the previous line, right?
04:17:55 <elliott> pikhq_: right, but where does the " come into it?
04:18:26 <pikhq_> elliott: It looks like this:
04:18:48 <pikhq_> abcde 01 LINE IS "This is a line. It is being continued.
04:19:01 <pikhq_> edfgh- "This is a continuation".
04:19:15 <pikhq_> LINE has "This is a line. It is being continued.This is a continuation"
04:19:23 <elliott> what about edfgh- qqqqq"test"
04:19:44 <elliott> imagine more spaces if that matters
04:19:53 <pikhq_> The contents between the continuation marker and the quote delimiter have to be whitespace.
04:20:33 <pikhq_> Newline will terminate the line, so that won't work.
04:21:02 <pikhq_> As will vertical tab I think?
04:21:07 <elliott> does it scan for the " just to let you indent continued strings?
04:22:10 <pikhq_> And the continuation line madness is really necessary. All text outside of columns 8 to 72 are comments.
04:22:18 <elliott> ...does LINE IS "test""foobar" even work?
04:22:28 <elliott> I guess it'd be "test"foobar" lol
04:24:27 <pikhq_> It's pretty impressive in its own way, with how it manages to be so utterly unlike anything you're used to.
04:29:28 -!- dts|feasting has changed nick to dts.
04:35:01 <Sgeo> I bought a book on COBOL because I confused it with CORBA
04:36:32 <madbr> kindof wondering what would be a good language for creating chiptune instruments
04:37:15 <zzo38> Depends what kind of chiptune instruments, I think
04:37:37 <madbr> also probably has to be as graphical as possible
04:37:59 <madbr> since sound designers rarely want to deal with text
04:38:26 <madbr> and text is a problem in most sound design/music production software anyways (DAWs)
04:38:33 <zzo38> Well, I really don't know; I know stuff such as Pure Data exists
04:38:50 <madbr> (the host program will capture your keyboard events, which is bad)
04:39:14 <madbr> and the typical user wants to be presented choices, not guess which choices are valid
04:43:39 -!- cluid has joined.
04:48:28 <FreeFull> Sgeo: I wonder if anyone ever bought a book on Pascal because they confused it with Haskell
04:51:10 <cluid> https://web.archive.org/web/20041103230415/http://geeksden.sourceforge.net/geekywiki/REGXY
04:51:16 <cluid> May I copy this verbatim onto esowiki?
04:51:20 <cluid> as "original specification"
04:52:30 <elliott> only public domain stuff can go on the wiki :/
04:52:33 <cluid> also I want to write a modern implementation, what langauge should I use?
04:53:55 <zzo38> cluid: I don't know? Possibly with Perl? It uses regular expressions.
04:54:13 <cluid> ill look into perl
04:54:29 <zzo38> I think Perl is a bit confusing though
04:54:34 -!- Oren has joined.
04:56:09 <Oren> no matter how many times I hear the word 'statistics' it still sounds like 'sadistic'
04:56:48 <int-e> sadistically speaking, 1 in seven people are afflicted by this condition?
05:03:38 <madbr> Oren : thos belies the fact that english is full of "T"s, "S"s, "D"s and "C"s :D
05:03:51 <madbr> especially t and s
05:05:21 <Oren> TS... no! bad oren's brain! do not make that stand for anything!
05:06:33 <cluid> I can translate regexy into perl easily
05:06:54 <cluid> http://lpaste.net/115247
05:07:03 <cluid> can wre write a regexy program to do this?
05:08:42 <cluid> a slight problem is that labels in regexy may not be valid labels in perl
05:09:12 <cluid> oh.. and lavbels in regex are comuputed from the regex.. so this translation isn't complete
05:10:31 <oerjan> cluid: btw i put the updated link to zzo38's REGXY page on the esowiki
05:10:40 <cluid> thanks a lot oerjan , i was going to do that
05:12:19 <cluid> http://zzo38computer.org/regxy/adbinery.txt
05:12:25 <cluid> actualy does this use computed labels or not? I think it does
05:12:34 <cluid> but i was mistaken
05:13:43 -!- tlewkow has quit (Remote host closed the connection).
05:13:51 <oerjan> Oren: tzatzikilly, this is a big problem hth
05:13:54 -!- callforjudgement has joined.
05:13:56 -!- ais523 has quit (Remote host closed the connection).
05:14:03 -!- callforjudgement has changed nick to ais523.
05:14:32 <zzo38> It doesn't looks computed label to me?
05:14:36 -!- Dulnes has quit (Quit: Connection closed for inactivity).
05:14:41 <cluid> thanks, I misread the code
05:14:49 <cluid> so RegXy doesn't support computed labels?
05:15:05 <cluid> it woudl be nice if it didnt
05:16:34 <cluid> I got an infinite loop trying to convert adbinery to perl
05:17:20 <cluid> http://lpaste.net/115248
05:18:04 <zzo38> Looks like not supporting computed labels from how I can see?
05:18:18 <cluid> i will have to use /s modifer in perl
05:18:24 <cluid> to treat multi line strings as a single string
05:18:31 <zzo38> I found a Visual Basic code and looks like not accepting computed labels.
05:18:32 <cluid> so that I can implement a regxy -> perl translation
05:19:59 -!- Dulnes has joined.
05:20:14 <Dulnes> What an awful way to end thanksgiving ;-;
05:20:25 <cluid> happy thanksgiving
05:20:48 <Dulnes> Merry Easter to you too
05:22:19 <Oren> whose birthday is it?
05:22:26 <Dulnes> Anyways my wife is pregnant and i hate children this is awful
05:24:19 <elliott> I'm not sure I believe that you have a wife
05:25:33 <cluid> why do you hate children
05:25:51 <Dulnes> They are loud sirens of pure malice
05:26:00 <elliott> don't you already have children
05:26:02 <cluid> isn't that a good thing?
05:26:12 <madbr> you were one at one time
05:26:13 <Dulnes> I dont want another one
05:26:27 <Dulnes> And my parents hated me
05:26:49 <Oren> So try to do better than them
05:27:11 <Dulnes> I have 3 kids i think thats enough for life
05:27:44 <ais523> is this the time when I give Dulnes a warning for being offtopic?
05:27:57 <ais523> offtopicness warnings in #esoteric is hard, because it's offtopic so often
05:28:12 <ais523> and yet some sorts of offtopicness are more obnoxious than others and it's hard to explain why
05:28:14 -!- oerjan has set topic: Child support channel | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:28:27 <oerjan> there, no longer off topic hth
05:28:32 <cluid> I will finish the RegXy
05:28:40 <cluid> then we can be on topic
05:28:50 <Oren> i have 23 cousins
05:28:57 -!- ais523 has set topic: To kill a zombie, you must kill its parents | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:29:04 <ais523> there, now it's on /both/ topics
05:29:22 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
05:29:22 <Dulnes> Whats that supposed to mean ais523
05:29:51 <Oren> i thought that rule was for vampires
05:30:04 <Oren> you kill dracula his minions also die
05:31:01 -!- Dulnes has set topic: There aren't any topics| https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:31:05 <elliott> btw if you didn't want another kid and you already have three, did you consider birth control
05:31:20 <Dulnes> Well idk maybe it didnt work
05:31:29 <ais523> Dulnes: you put a typo in the topic :-(
05:31:35 <Dulnes> We were using birth control
05:31:50 -!- ais523 has set topic: The international hub for esoteric programming language discussion, development and deployment | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:31:55 <ais523> and you know what this means
05:32:01 <Oren> or you could try men instead that would prevent babies
05:32:22 <madbr> or have a sex change
05:32:43 <Dulnes> These are terrible ideas
05:32:54 <Dulnes> As they would break apart my family
05:32:56 <Oren> buy your wife a strapon
05:32:59 <elliott> let's not, re: all of this
05:33:18 <Oren> Ok i'll stop...
05:33:30 <madbr> are you religious?
05:34:17 <Dulnes> Sex changes cost money/ cheating on wife also causes divorce/money loss
05:34:38 <madbr> yeah I was just making a bad joke there
05:35:15 <Dulnes> Mmm whatever im going to drown myself in pie.
05:35:49 -!- ChanServ has set channel mode: +o ais523.
05:35:51 -!- ais523 has set channel mode: +m.
05:36:01 -!- ChanServ has set channel mode: +o elliott.
05:36:05 <ais523> in most channels, I have to get annoyed and forcibly change topic when something like this happens
05:36:11 <ais523> by coming up with an interesting tangents
05:36:14 <ais523> I'm all out of interesting tangents
05:36:18 <ais523> but I've realised I can do this
05:36:19 -!- elliott has set channel mode: -o ais523.
05:36:22 <elliott> don't worry the topic is now fish
05:36:23 -!- elliott has set channel mode: -m.
05:36:26 -!- elliott has set channel mode: -o elliott.
05:36:42 <elliott> -o'ing other ops is my favourite rogue op move
05:37:26 <cluid> I thought I could match anything that isn't a backslash
05:37:36 <cluid> but I actually need to include back slash escaped backslahes
05:37:37 <Dulnes> Maybe she was mistaken but whatever gnight
05:37:53 <elliott> ais523: https://en.wikipedia.org/wiki/Kickflip
05:37:55 <oerjan> cluid: you might take a look at my /// interpreter it has similar issues
05:38:02 <cluid> I could use this (([^\/]|\\\/)*)
05:38:04 <ais523> elliott: I mean in the context of IRC
05:38:08 <Dulnes> \/ thought that was a V
05:38:15 <cluid> oerjan, I invented a language similar to /// but less cool
05:38:23 <cluid> your /// stuff is very awesome
05:38:39 <ais523> I have a regex for matching slash-delimited backslash-escaping stuff in aiake
05:39:06 <madbr> still haven't figured out how I'll come up with my next horrible language
05:39:08 <ais523> push @aipath, $1 while $objvalue =~ m=((?:[^\\\/:]|\\.)*)( / | $ )=gsx;
05:39:24 <ais523> now I'm trying to figure out specifically what that regex matches
05:39:24 <cluid> backslashed backslashes
05:39:28 <cluid> I forgot about those
05:39:34 <cluid> (([^\/]|\\\/|\\\\)*)
05:39:36 <ais523> and looking at it, seems I missed a ?:
05:39:43 <cluid> this could be enough for me maybe I hope
05:39:46 <ais523> which will have efficiency effects
05:39:48 <madbr> is the mandelbrot set turing complete?
05:39:50 <ais523> cluid: best to do it correctly
05:39:54 <cluid> I have to use two loops in my code
05:39:59 <cluid> actuall y many, in two groups
05:40:05 <cluid> one for santizing labels into perl valid labels
05:40:13 <cluid> another for transforming RegXy rules into perl rules
05:40:20 <ais523> besides, \\. is easier than \\\/|\\\\ and more correct, at least in the case of ///
05:40:35 <cluid> ais523, oh nice idea ! thank you
05:40:51 <madbr> bicyclidine: yes but there's no upper bound on the number of iterations required to find if a number is in the set
05:41:13 <cluid> I wonder how regex $n works
05:41:14 <madbr> that seems a lot like the halting problem to me
05:41:16 <cluid> i will have to count
05:41:55 <Bicyclidine> well, finding the limit set of some mappings is turing equivalent.
05:42:07 <Bicyclidine> don't think that's the case for mandelbrot though. it's just squaring.
05:42:18 <ais523> incidentally, something else I'm annoyed at (and vaguely related to the LCRNG maths question I asked in here a few days ago)
05:42:33 <ais523> is when you have this nice elegant solution to something that isn't quite your problem
05:42:35 <madbr> it might be possible to build an accumulator out of the real and imaginary part
05:43:08 <cluid> $i =~ s/(^|\n)([^\/]*)\+(([^\/]|\\.)*)\/(([^\/]|\\.)*)\/(\n|$)/$1$2_plus$3$5$7/s;
05:43:33 <ais523> something that isn't quite my problem: you have sets of boolean variables (some variables appear in multiple sets); you want to find a mapping of variables to true/false so that there's an even number of true variables in each set
05:43:51 <newsham> howd the lcrng thing work out in the end?
05:43:51 <ais523> I found a nice algorithm to solve this in O(number of variables^2)
05:44:24 <ais523> newsham: I didn't solve it, even though it seems solvable, due to running out of ideas; however, I decided that I possibly had a "how can I use X to do Y?" problem
05:44:31 <Oren> brute force is 2^n
05:44:35 <ais523> and are looking at other potential ways to do Y, without doing X, even though X would have been cool
05:44:45 <ais523> also I wrote a brute forcer that works for n=32
05:44:53 <myname> ais523: easy: don't set any to true. O(1)
05:44:57 <ais523> n=64 would only take a few times longer than my expected lifetime
05:45:12 <ais523> myname: there's one specific variable that has to be set to true
05:45:52 <newsham> n=64 prob solvable on cloud clusters in your lifetime, or even this year
05:46:09 <ais523> right, that was on my laptop
05:46:11 <oerjan> ais523: it seems like you've reinvented XORSAT?
05:46:21 <ais523> oerjan: right, there was almost certainly a name for it
05:46:53 <cluid> can I write this with less brackets
05:47:13 <ais523> and, from a different point of view, reinvented linear programming
05:47:23 <Oren> yes the outer breackets are unecessay
05:47:31 -!- callforjudgement has joined.
05:47:35 <oerjan> ais523: XORSAT is much simpler than linear programming
05:47:56 <oerjan> it's just solving a matrix equation (mod 2)
05:48:00 <callforjudgement> sadly, my /actual/ problem expressed in these terms are: you have a number of integer variables (mod n), and a number of linear polynomials of those variables
05:48:17 <callforjudgement> but the polynomials are inequalities rather than direct equalities
05:48:39 <oerjan> linear integer programming is NP-complete
05:48:57 <callforjudgement> oerjan: I was thinking of the subset of linear programming that's just solving matrix equations
05:49:28 <oerjan> well yes. but it doesn't work with inequalities.
05:49:46 <callforjudgement> nothing I can think of works with inequalities and it is annoying me
05:50:00 <madbr> the mandelbrot set is connected
05:50:08 <oerjan> oh hm you have (mod n). but i think linear integer programming is NP-complete even with just {0,1}
05:50:14 <madbr> I wonder if this means that it cannot be turing complete
05:50:24 <madbr> cluid: the wikipedia article says so
05:50:31 <oerjan> madbr: almost certainly those facts are unconnected
05:50:36 <cluid> its a joke beacuse it's hard to prove that
05:51:16 <madbr> oerjan : so in otherwose, almost certainly no? :D
05:51:40 -!- ais523 has quit (Ping timeout: 244 seconds).
05:51:42 -!- callforjudgement has changed nick to ais523.
05:52:33 <Oren> integer programming is NP-complete -- lecture today was on that fact
05:53:27 <Oren> in fact it is NP-hard
05:53:43 <oerjan> ais523: btw aaronson and friends think of XORSAT as "that problem which is so similar to SAT that many purported proofs of P != NP can be discarded by checking that they would prove XORSAT not in P because they fail to distinguish any real property of them"
05:53:50 <Bicyclidine> i uh, don't think it could be np-complete without being np-hard
05:53:56 <oerjan> (not a quote but a paraphrase)
05:54:02 <ais523> oerjan: oh, I think of 2SAT like that
05:54:18 <Oren> oh right. i'm still learning this stuff...
05:54:23 <ais523> xorsat might be better, though, I don't have much experience in finding fallacies in P≠NP proofs
05:54:39 <ais523> what's more common, incidentally, claims of P=NP proofs or claims of P≠NP proofs?
05:54:46 <Oren> how about a randomized algoritthm then?
05:54:54 <oerjan> ais523: that purported proof by deolalikar (sp?) a few years ago failed on that test
05:55:11 <ais523> I assume the latter, because unless a P=NP proof is existence rather than constructive, it's normally possible just to run it on a computer and see what happens
05:55:11 <oerjan> ais523: i don't remember
05:55:32 <oerjan> ais523: it might depend on the level of crankiness involved
05:56:15 <ais523> Bicyclidine: my favourite NP definition is "an problem is NP if it can be solved by a trustworthy P-time checker and untrustworthy TC oracle working together, such that the solution is always correct if the oracle happens to be trustworthy, and has no false positives regardless of what the oracle does"
05:56:36 <ais523> Bicyclidine: you need a lot of words, sadly
05:56:49 <cluid> How do I get the whole of STDIN as a string in perl?
05:57:21 <ais523> helping a student with this, we came up with the (possibly slightly mathematically unsound) "a problem is NP if a P-time algorithm with access to randomness has no false positives, and no false negatives with probability 1"
05:57:37 <ais523> cluid: {local $/; $string = <>}
05:58:00 <ais523> cluid: although that will read a file specified on the command line if there is one, in preference to stdin
05:58:05 <ais523> this is normally what you want but not always
05:58:10 <cluid> thats really nice thank you !
05:58:24 -!- ZombieAlive has quit (Remote host closed the connection).
05:59:35 <oerjan> madbr: i'm pretty sure you can easily construct a set that is connected and such that it's TC to check membership, yes: pick your favorite TC set of integers and connect with arcs or something.
06:02:21 <oerjan> <Oren> how about a randomized algoritthm then? <-- the current "most believed hypothesis" by experts is that (RNG) randomness doesn't give you anything beyond P
06:03:22 <Oren> does it at least make the constant teenier?
06:03:31 <ais523> oerjan: at least without some method of comparing the possible random results
06:03:43 <ais523> hmm, there are P-time PRNGs that are pretty good
06:03:58 <oerjan> <cluid> How do I get the whole of STDIN as a string in perl? <-- hey i _told_ you to look at my /// interpreter!
06:04:09 <ais523> it'd be something quite spectacular if there was an algo that worked with true-randomness, but not a CSPRNG
06:06:10 <oerjan> ais523: the hypothesis is based on the the theory that there are P-time PRNGs so good that they cannot be revealed as pseudo in P-time
06:06:42 <Oren> maybe true randomness doesn't exist?
06:06:43 <oerjan> although no one has proved they exist, as it's something stronger than P != NP
06:07:04 <ais523> right, P=NP would mean that such PRNGs could definitely be proven pseudo in P-time
06:07:14 <oerjan> Oren: quite possible but the mathematical concept of a true random algorithm still does.
06:10:06 <oerjan> iirc it follows from the also hypothesized existence of cryptographic hashes
06:11:48 <cluid> http://lpaste.net/115258
06:12:07 <cluid> do you think adbinery is wrong or my translation?
06:12:14 <cluid> the output seems wrong
06:12:56 <zzo38> Either could be wrong (possibly both)
06:14:12 -!- tlewkow has joined.
06:14:16 -!- madbr has quit (Quit: Pics or it didn't happen).
06:14:41 -!- oerjan has quit (Quit: Some other time).
06:16:49 <fizzie> cluid: One thing that at least is wrong is that in Perl's regexps, you use plain + instead of (sed, POSIX re) \+ for "one or more".
06:17:36 <fizzie> Though I guess that applies to whatever the upper block is too, now that I look at it.
06:17:41 <fizzie> (Sorry, just woke up.)
06:17:53 <Oren> he's trying to match + the operator plus
06:18:25 <cluid> I havea bug in my translation
06:19:09 -!- tlewkow has quit (Ping timeout: 258 seconds).
06:22:35 -!- AndoDaan has quit (Quit: Quit).
06:29:38 <cluid> I completed a self hosting regxy -> pl translator
06:29:49 <cluid> should I add this an ddetails to the wiki page?
06:42:48 <ais523> cluid: most commonly you'd post it somewhere else and add a link
06:43:22 <ais523> you could post it on the wiki if you had no better options, but normally there are better options; I know graue (who used to own esolangs.org) has volunteered to host almost arbitrary esolang compilers/interpreters/stuff on esoteric.voxelperfect.net/files
06:43:33 <ais523> but I'm not sure anyone's asked him to do that in ages
06:44:26 <cluid> i could put it on a paste bin but it might disappear
06:46:29 <ais523> some things do get posted to the wiki, and I'm not personally against that, but I know some other people are
06:47:51 <cluid> I wanted to make the RegXY article better
06:48:20 <elliott> some people use a user subpage and link it from mainspace
06:49:22 <ais523> I think everyone agrees that the impl should be posted somehow
06:49:25 <ais523> just there's debate as to how
06:49:37 <zzo38> I think if it isn't too long you can post directly on the wiki
06:50:11 <zzo38> Note that the wiki page normally isn't a valid program; however you can avoid this by using Perl's documentations features I suppose
06:50:49 <zzo38> As long as it is in the public domain too, it is OK then
06:51:19 <ais523> if it's only 10 lines, posting it directly's probably fine
06:51:24 <ais523> make sure to escape it properly, though
06:51:37 <cluid> is there a program to escape it?
06:51:39 <ais523> (wrapping in <pre><nowiki> to start and </nowiki></pre> works for most programs)
06:53:37 <zzo38> ais523: That works for display, but not for download unless you add # or Perl documentation commands or whatever.
06:54:01 <ais523> zzo38: it's not bad for download, you can copy-paste either from the displayed version or the wikitext
06:54:15 <zzo38> For example http://esolangs.org/wiki/Pure_BF/Implementation?action=raw&ctype=text/css is a valid Literate Haskell program.
06:54:27 <cluid> Can I put the reverse example code?
06:54:47 <cluid> from here https://web.archive.org/web/20041103230415/http://geeksden.sourceforge.net/geekywiki/REGXY
06:55:20 <zzo38> I don't know the license from that archived wiki, although the stuff in my directory is in public domain so you can use it
06:55:41 <zzo38> If the code is small enough it would probably be OK though
06:56:00 <ais523> cluid: the wiki is public domain things only, which is about the most restrictive thing possible in terms of what you can post to it
06:56:54 <zzo38> I don't know enough about Perl programming to know the best way to do a similar thing with Perl than what I have done with Haskell there.
06:58:42 <HackEgo> [wiki] [[REGXY]] http://esolangs.org/w/index.php?diff=41223&oldid=41218 * Cluid Zhasulelm * (+1917) Improved language definition and added examples along with implementation
07:01:32 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
07:01:55 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] M http://esolangs.org/w/index.php?diff=41224&oldid=41155 * Cluid Zhasulelm * (+75)
07:04:03 <HackEgo> [wiki] [[Talk:Nonsense Query List]] http://esolangs.org/w/index.php?diff=41225&oldid=31459 * Zzo38 * (+111)
07:08:55 <HackEgo> [wiki] [[REGXY]] M http://esolangs.org/w/index.php?diff=41226&oldid=41223 * Cluid Zhasulelm * (+467) 99 bottles of beer example
07:12:10 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] M http://esolangs.org/w/index.php?diff=41227&oldid=41224 * Cluid Zhasulelm * (+227) wikis
07:24:00 -!- tlewkow has joined.
07:24:35 -!- Bicyclidine has quit (Ping timeout: 272 seconds).
07:28:55 -!- tlewkow has quit (Ping timeout: 258 seconds).
07:44:07 <cluid> what was the japanese blogger saying about MMMNBF?
07:48:30 <Oren> um, send me the page in question and I can try to translate.
07:57:07 -!- Patashu has joined.
07:57:25 <cluid> i dont know what page[s] it is
07:57:27 <Oren> if you mean copyright or whatever, the blog doesn't seem to have that info
07:57:52 <Oren> what information are you looking for?
07:57:54 <cluid> I was just curiouw what their views were
07:58:02 <cluid> if they had questions about it or who they were
07:58:34 <Oren> The blooger is the language designer. afaik.
07:59:09 <cluid> ah, i didnt know that
08:00:10 <Oren> I'll translate the whole page of the main post
08:00:18 <Oren> perhaps make it more clear
08:00:35 <Oren> title : まだ名前のないBrainfuck風スタック言語、略して MNNBFSL
08:01:17 <Oren> a not yet named brainfuck style stack language, for short mnnbfsl
08:01:42 <Oren> I have been thinking about it
08:01:57 <Oren> インタープリタの実装は yshl/MNNBFSL ? GitHub に。
08:02:41 <Oren> "an implementation of an interpreteris here, github"
08:02:57 <Oren> データスタックとリターンスタックの 2本のスタックがあります。
08:03:21 <Oren> "there are two stacks, a data stack and a return stack"
08:03:35 <lifthrasiir> the third-to-last paragraph: "It feels quite similar to Brainfuck, but [ and ] has been repurposed for program counter manipulation instead of jump. Forward jump can be done by getting PC via [, but backward jump would require getting PC and some adjustments to it and is slightly harder."
08:03:56 -!- callforjudgement has joined.
08:04:02 <Oren> スタック 2本あればチューリング完全らしいから
08:04:19 -!- ais523 has quit (Remote host closed the connection).
08:04:33 <Oren> Because if there are two stacks it is turing complete ish,
08:04:38 <lifthrasiir> the second-to-last and last paragraphs: "It keeps PC so I guess it is harder to optimize than Brainfuck when it comes to the transpiler to C." "At least it is better than Brainfuck that the behavior on EOF is defined..."
08:04:44 -!- callforjudgement has changed nick to ais523.
08:04:56 <Oren> チューリング完全なんじゃないかな。
08:05:16 <Oren> "I wonder if it is not turing complete"
08:09:09 <ais523> hmm, so despite the effort we're putting into translating this
08:09:13 <ais523> it is nonetheless just a BF derivative?
08:09:38 <cluid> its an intersting BF derivative
08:10:21 <Oren> looks like it is a bit different from BF
08:10:28 -!- qwertyo has joined.
08:10:34 <Oren> the problem is jusggleing the stacks
08:10:57 <Oren> the return address is not always there when you need it
08:11:36 <Oren> in any case from my reading, we have the spec right for all the instructions
08:12:50 -!- callforjudgement has joined.
08:14:06 <HackEgo> [wiki] [[MNNBFSL]] M http://esolangs.org/w/index.php?diff=41228&oldid=41216 * Orenwatson * (+1) count of instructions was wrong
08:15:07 -!- ais523 has quit (Ping timeout: 264 seconds).
08:16:10 <cluid> actually only superficially related to brainfuck
08:16:21 <cluid> its based on two stacsk not a tape
08:16:32 <cluid> and you have to compute jumps, not matching brackets
08:16:53 -!- callforjudgement has quit (Ping timeout: 240 seconds).
08:17:36 <b_jonas> cluid: um, two stacks is a tape.
08:18:27 <Oren> the blogger's profile says: "I am a biological human, unrelated to the Yokohama Shootout Hockey League"
08:19:12 <Oren> so his name is just: yshl
08:20:49 <Oren> he has bought a lot of manga, most of hisposts are listing the manga he bought that week.
08:24:07 <HackEgo> [wiki] [[MNNBFSL]] M http://esolangs.org/w/index.php?diff=41229&oldid=41228 * Orenwatson * (+84) added apparent author info
08:26:51 <fizzie> b_jonas: "Two stacks and a tape walk into a bar..."
08:27:09 <fizzie> (I don't know, it just sounded like a setup for a joke; no idea how it'd continue.)
08:30:25 <cluid> i can't translate brainfuck into MMBFSL
08:30:33 <cluid> a tape in bf is right infinite
08:30:41 <cluid> but the stacks start empty in MMBFSL
08:32:38 -!- tlewkow has joined.
08:39:08 <fizzie> cluid: Possibly you can use a tape layout like "1 a 1 b 1 c 0" for data "a b c", and make the analogue of > to check the 0/1 flag and extend the tape.
08:39:43 <fizzie> (Could be trickier than that in a sufficiently tarpitty language.)
08:39:54 <fizzie> (I haven't been following the discussion.)
08:40:04 <cluid> that's a good idea
08:40:32 <fizzie> elliott: I evaded the bait by cleverly being asleep, but OTOH I don't have an answer either, I probably would just have mumbled something incoherent about the branch predictor's hardware return stack.
08:41:35 -!- dts has quit (Read error: Connection reset by peer).
08:43:14 -!- dts has joined.
08:56:43 <Oren> I sent the blogger a (no doubt poorly written) email asking for more information.
08:57:02 <dts> i dont believe you
08:57:18 -!- tlewkow has quit (Remote host closed the connection).
08:57:56 <Oren> why not? I really did send him a n email. it's 6pm now so
08:58:05 <Oren> (in japan that is)
08:58:15 <dts> idk man. you just seem really shifty
08:58:18 <Oren> so he should be home from work soon
08:58:21 <cluid> cool Oren , kep me updated when you get a reply please?
08:58:24 <cluid> fizzie, can you ban dts?
09:05:58 -!- Patashu_ has joined.
09:05:58 -!- Patashu has quit (Disconnected by services).
09:24:36 -!- Dulnes has quit (Quit: Connection closed for inactivity).
09:27:30 <cluid> http://esolangs.org/wiki/Binary_combinatory_logic
09:27:36 <cluid> is this really string rewriting
09:27:52 <cluid> its term rewrting not string rewriting
09:27:58 <cluid> 11101xyz --> 11xz1yz
09:28:02 <cluid> its not characters x,y,z but terms
09:30:53 -!- qwertyo has quit (Quit: Leaving).
09:31:08 <Oren> mhm that's right
09:40:10 -!- ais523 has joined.
09:40:26 <cluid> http://esolangs.org/wiki/Infinity this page is really annoying
09:41:54 -!- sebbu has quit (Ping timeout: 264 seconds).
09:46:21 <cluid> http://esolangs.org/wiki/Cheese
09:47:06 <int-e> Does it really say "Infinity closely approximates the amount of nonsense on this page." or am I imagining things?
09:47:31 <dts> cheese++ is far better tbh
09:47:53 <cluid> dts, you should please design cheese+++ (and implement it in cheese++)
09:48:16 <dts> what would cheese+++ have in it?
09:49:02 <int-e> Oh I see, the BCL page is not even talking about string rewriting, it's just a category.
09:49:31 <cluid> it could use ideas from here http://en.wikipedia.org/wiki/List_of_cheeses
09:52:51 <int-e> it can be viewed as a sort of conditional string rewriting. "Kxy -> x if x and y are produced by the following CFG...", but I have yet to see such a formalism.
09:53:22 <int-e> (CFGs are, of course, string rewrite systems)
09:54:22 <cluid> Context-free grammar?
09:55:16 <int-e> consider the rules S -> 00; S -> 01; S -> 1SS, and look at which strings not containing S can be produced from S.
09:55:29 <cluid> that CFG describes the syntax well
09:55:43 <cluid> but the language is defined by term rewriting
09:56:06 <cluid> so it should be moved out of string rewrite category
09:56:43 <int-e> or perhaps not? is "term" a term or is it the set of strings defined under "syntax"?
09:57:57 <int-e> You can view it either way. Which means I don't feel strongly about the category.
09:58:40 -!- sebbu has joined.
09:58:53 <int-e> And since oerjan added the category I would leave the decision to him.
09:59:18 -!- sebbu has quit (Changing host).
09:59:18 -!- sebbu has joined.
10:00:27 <cluid> it can be a string rewriting system only if it has infinitely many rules
10:01:13 <cluid> so 1100xy --> x denotes all rules 11000000 --> 00, 11000001 --> 00, ...
10:01:32 <cluid> if you treat it as aterm rewrite system it is just 2 rules
10:01:51 <cluid> also it talks about "subterms of a given term" so it should be a term rewrite system
10:06:25 <int-e> cluid: I would normally agree, but there are notions of string rewriting where the rules may contain variables that represent arbtitrary substrings. (So instead of a term rewriting with unary function symbols, you'd have to do term rewriting with constants and one AC [associative, commutative] symbol.)
10:06:50 <cluid> ok i was just looking at the thue system thing on wikipedia
10:07:13 <cluid> on what you're saying it makes sense to call it string rewriting
10:07:19 <int-e> And in that contaxt 1100xy --> x fits perfectly, except that it would allow steps like 11001010 -> <empty>
10:08:51 <int-e> And the category is not overflowing with pages, so a broad definition of "string rewriting" seems appropriate.
10:09:02 <cluid> yeah, thanks for your input!
10:18:37 -!- nooga has joined.
10:29:18 -!- ais523 has quit (Ping timeout: 264 seconds).
10:32:45 <cluid> so is it easy to recognize CFGs inside a string?
10:33:04 <cluid> maybe this is similar to regex
10:35:37 <cluid> idea for esolang: Write a CFG, then write CFG substitution rules to define a program
10:35:49 <cluid> then you can implement BCL in it for example, quite easily
10:53:30 -!- ais523 has joined.
10:54:59 -!- Phantom_Hoover has joined.
11:03:24 -!- dts has changed nick to dts|Zzzz.
11:14:25 -!- callforjudgement has joined.
11:14:47 -!- ais523 has quit (Disconnected by services).
11:14:49 -!- callforjudgement has changed nick to ais523.
11:18:22 -!- boily has joined.
11:18:29 -!- dts|Zzzz has quit (Ping timeout: 240 seconds).
11:20:12 -!- HackEgo has quit (Ping timeout: 272 seconds).
11:39:12 <cluid> hm the esolang wiki is down
11:39:20 <cluid> but I was reading the BCL page and this is interesting,
11:40:03 <boily> Gregor: AAAAAAAAAAAAAAAAAAAH! http://www.downforeveryoneorjustme.com/esolangs.org
11:40:05 <cluid> you can define it in two steps, first syntax: S --> 00 | 01 | 1 S S
11:41:00 <fizzie> boily: I'm provisionally going to suggest it's probably that shifty VPS provider at work again.
11:41:02 <cluid> and then rewrite laws: 100 S:x S:y --> x, 101 S:x S:y S:z --> 11 x z 1 y z
11:41:19 <fizzie> boily: (Doesn't answer to SSH, so I can't do much.)
11:41:21 <cluid> this implements BCL
11:41:33 <cluid> you could also implement other programs in this way
11:43:34 <boily> fizzie: I wouldn't be surprised at all. :/
11:43:49 <boily> cluid: this sounds an awful lot like an L-system...
11:44:00 <cluid> its much more powerful than L system
11:44:28 <cluid> you can match an arbitrary CFG in the string to provide a replacement, rather than just a character
11:44:48 <cluid> and your rules can shrink the string as well as grow it, so you can compute more things
11:47:09 <fizzie> I don't think the term "L-system" is technically restricted to having only context-free rules, even if that's the most common case.
11:47:43 <fizzie> http://en.wikipedia.org/wiki/L-system#Context_sensitive_grammars is counted as a "variation". Not that there are probably any "official" definitions.
11:50:39 <cluid> I should use different symbos for the CFG production, and the rewrite rules
11:50:47 <cluid> ==> maybe for rewrite
11:51:20 <cluid> it's cool that you can implement BCL in 2 lines, maybe there are other program you can write it in
11:58:14 -!- tlewkow has joined.
12:00:13 -!- Patashu_ has quit (Ping timeout: 240 seconds).
12:02:37 -!- tlewkow has quit (Ping timeout: 258 seconds).
12:06:42 -!- boily has quit (Quit: MANIFOLD CHICKEN).
12:20:24 -!- ais523 has quit.
12:20:58 -!- nooga has quit (Ping timeout: 255 seconds).
12:23:09 -!- Bicyclidine has joined.
12:28:15 -!- idris-bot has quit (Quit: Terminated).
12:28:54 -!- idris-bot has joined.
12:34:49 -!- sebbu2 has joined.
12:35:25 -!- sebbu2 has quit (Changing host).
12:35:26 -!- sebbu2 has joined.
12:37:12 -!- sebbu has quit (Ping timeout: 250 seconds).
12:44:21 -!- ZombieAlive has joined.
12:58:05 -!- GeekDude has joined.
14:13:01 -!- cluid has quit (Quit: Leaving).
14:29:34 <lambdabot> oerjan said 14h 55m 31s ago: <mroman> which is usually suffixed with (embed) <-- if you want people to follow conventions you should actually state them on the website hth
14:29:49 <mroman> @message oerjan It's not my website
14:29:50 <lambdabot> Maybe you meant: messages messages-loud messages?
14:30:04 <mroman> @bell oerjan It's not my website
14:31:26 <fizzie> So it's not your (singular) website, but arguably it's then your (plural) website.
14:32:23 <fizzie> (Unless it was the kind of passive-voice-style "we".)
14:34:11 <fizzie> Gregor: I guess we could nickping you to maybe have a poke and/or a prod at the management console (if they have one) of the esolangs VPS, to see if it says anything informative. (It's down w.r.t. HTTP, SSH at least at the moment.)
14:46:05 -!- Oren has quit (Ping timeout: 246 seconds).
14:51:36 -!- copumpkin has joined.
14:52:16 -!- contrapumpkin has joined.
14:56:13 -!- copumpkin has quit (Ping timeout: 255 seconds).
14:58:06 -!- contrapumpkin has changed nick to copumpkin.
14:58:52 -!- HackEgo has joined.
15:03:23 -!- contrapumpkin has joined.
15:06:39 -!- copumpkin has quit (Ping timeout: 265 seconds).
15:09:21 -!- Oren has joined.
15:15:11 -!- mig22_ has joined.
15:15:48 -!- mig22_ has changed nick to mig22.
15:18:17 -!- mig22 has quit (Remote host closed the connection).
15:19:13 -!- mig22 has joined.
15:19:20 -!- copumpkin has joined.
15:21:20 -!- drdanmaku has joined.
15:22:51 -!- contrapumpkin has quit (Ping timeout: 255 seconds).
15:34:58 -!- mig22 has quit (Quit: mig22).
15:36:11 -!- contrapumpkin has joined.
15:38:59 -!- copumpkin has quit (Ping timeout: 240 seconds).
15:42:12 -!- copumpkin has joined.
15:46:06 -!- contrapumpkin has quit (Ping timeout: 264 seconds).
15:48:01 -!- contrapumpkin has joined.
15:51:33 -!- propumpkin has joined.
15:51:39 -!- copumpkin has quit (Ping timeout: 255 seconds).
15:52:55 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
15:55:42 -!- copumpkin has joined.
15:55:42 -!- contrapumpkin has quit (Ping timeout: 272 seconds).
15:59:18 -!- propumpkin has quit (Ping timeout: 264 seconds).
16:03:47 -!- Oren has quit (Ping timeout: 246 seconds).
16:07:54 -!- Oren has joined.
16:08:01 -!- contrapumpkin has joined.
16:11:01 -!- propumpkin has joined.
16:11:27 -!- copumpkin has quit (Ping timeout: 255 seconds).
16:14:39 -!- contrapumpkin has quit (Ping timeout: 245 seconds).
16:18:12 -!- copumpkin has joined.
16:21:29 -!- propumpkin has quit (Ping timeout: 240 seconds).
16:26:11 -!- contrapumpkin has joined.
16:30:08 -!- copumpkin has quit (Ping timeout: 264 seconds).
16:38:11 -!- copumpkin has joined.
16:38:33 -!- blsqbot has quit (Ping timeout: 240 seconds).
16:39:34 -!- mroman has quit (Ping timeout: 244 seconds).
16:40:41 -!- propumpkin has joined.
16:42:08 -!- contrapumpkin has quit (Ping timeout: 264 seconds).
16:43:49 -!- copumpkin has quit (Ping timeout: 245 seconds).
16:43:52 -!- contrapumpkin has joined.
16:46:21 -!- copumpkin has joined.
16:46:59 -!- propumpkin has quit (Ping timeout: 240 seconds).
16:49:42 -!- contrapumpkin has quit (Ping timeout: 255 seconds).
16:54:48 <Oren> what kind of bot logs in and logs out every 3 minutes?
16:55:20 <Oren> what's going on then?
16:55:37 <Oren> bad connection?
16:59:53 <Oren> hmm, seems my scrip7 interpreter is still buggy
17:00:12 <Oren> the loops are not working
17:00:22 -!- contrapumpkin has joined.
17:01:38 <Oren> this program crashes my scrip7 interpreter: $ { # _ p 64 } .
17:01:52 <Oren> trying to fixt that
17:02:07 <elliott> contrapumpkin: fix your connection :p
17:03:44 <Oren> the problem is with the null variable _
17:03:49 -!- copumpkin has quit (Ping timeout: 245 seconds).
17:04:04 <Oren> which isn'tin the spec becuase it keeps screing up
17:04:19 <Oren> s/screing/screwing/
17:06:11 -!- copumpkin has joined.
17:07:29 -!- ChanServ has set channel mode: +o elliott.
17:07:36 -!- elliott has set channel mode: +b $a:copumpkin$##fixyourconnection.
17:07:45 <elliott> someone poke me in an hour
17:07:58 <FireFly> Oh, A057755 is about to run out
17:08:32 <fizzie> Still two days for Dominosa and it's so far seen very little action.
17:08:38 <fizzie> And most of what it's seen is #esoteric's fault.
17:09:57 -!- contrapumpkin has quit (Ping timeout: 255 seconds).
17:10:18 <elliott> is it legit or just a really bad cheat?
17:10:59 <elliott> how many bits do you get from the $$ setter? I guess a bit less than 16?
17:11:38 <elliott> b_jonas: but some other processes are already on the system, right?
17:11:44 <elliott> you can't collide with those
17:11:44 -!- copumpkin has quit (Ping timeout: 245 seconds).
17:11:54 <b_jonas> elliott: a bit less than 15 bits really
17:11:54 <elliott> oh, I guess it's actually faked
17:12:02 <elliott> as in your pid isn't really that
17:12:14 <elliott> are you sure? anagol fakes many syscalls
17:12:57 <fizzie> elliott: I've been assuming it's legit, because even just uncompressed embedding is just 240B + whatever language-specific overhead there is.
17:13:07 -!- tlewkow has joined.
17:13:10 <fizzie> Or was it even less than that.
17:13:26 <elliott> fizzie: it has a shebang, documentation, and obeys PEP-8
17:13:57 <fizzie> I was supposed to check what that was all about, but forgot.
17:14:15 <elliott> http://golf.shinh.org/reveal.rb?Wow/PatchiKnowsWhatsUp_1415208522&py
17:15:27 <FireFly> Especially the space after print, as someone pointed out
17:15:46 <int-e> I would've done it again, too.
17:16:09 <elliott> int-e: oh, is that solution yours? or what do you mean
17:16:24 <int-e> No, I liked the space in particular.
17:18:17 <FireFly> Heh, someone did A057755 in jq
17:27:09 <int-e> perl... $$.2, yuck.
17:28:03 <Oren> append 2 to variable $$
17:28:10 <Oren> is how I read that
17:28:27 <Oren> but perl may not read it the same way
17:28:35 <int-e> yes. $$ is the process id, it'll be 315652
17:28:44 <int-e> after appending the 1
17:32:24 <FireFly> So have we decided that Dominosa is a compression task now?
17:32:45 <int-e> so what kind of literals are those C solutions using?
17:32:51 -!- GeekDude has joined.
17:34:07 <b_jonas> http://golf.shinh.org/p.rb?Make+24 is public now
17:34:30 <b_jonas> so now you can see the craziest regex I've ever written:
17:35:39 <b_jonas> this is the solution: http://golf.shinh.org/reveal.rb?Make+24/b_jonas_1414698860&pl
17:36:42 <fizzie> FireFly: It's not a compression task, but I'm sure the best solutions are embeds.
17:37:37 <fizzie> FireFly: Out of my burlesque ones, the un-suffixed one is legit, the "cheat" makes one unwarranted assumption that happens to cause no problems for the three test cases, and the "supercheat" just embeds the outputs.
17:37:51 <elliott> int-e: idea: programming language that somehow uses $$ as part of the control flow/code...
17:38:12 <elliott> save a whole two bytes of information!!
17:39:43 <int-e> of course Dominosa is a data compression task, so where are the Perl solutions :/
17:41:54 <elliott> anagol should just add zlib as a language
17:42:07 <elliott> oh I guess zlib can't condition on input at all though :p
17:42:24 <elliott> hmm, could you easily add input to the "languages" of decompressors?
17:43:31 -!- sebbu2 has changed nick to sebbu.
17:50:39 <fizzie> elliott: I was looking for a feature like that in the end-user gzip/zcat/etc. tools, but couldn't find anything.
17:50:48 <fizzie> (For that one bash+zcat thing.)
17:51:32 <elliott> fizzie: what I mean is considering the decompressors as interpreters for languages like "emit these bytes" and "reference N bytes" ago... I know zip is enough to do a quine, so maybe adding input somehow would be enough to get it to do golf cheats all by itself?
17:51:36 <elliott> maybe you knew I meant that though
17:53:06 <fizzie> Oh, no; I assumed you meant what I was looking for, which was to compress input Y as if it was preceded by input X to something short called Z, and then being able to decompress Z back to Y if given X.
17:54:28 <fizzie> It sounds somewhat reasonable that many compressors could get a shorter Z (compared to just compressing Y alone to Z') if X and Y are similar, but they don't seem to offer that as an option.
17:54:32 <elliott> hand-programming of zip files is where it's at
17:55:51 <fizzie> I think the zlib library has something a bit like that.
17:56:09 <fizzie> See http://www.zlib.net/manual.html deflateSetDictionary + inflateSetDictionary.
17:56:19 <fizzie> "Initializes the compression dictionary from the given byte sequence without producing any compressed output. This function must be called immediately after deflateInit, deflateInit2 or deflateReset, before any call of deflate. The compressor and decompressor must use exactly the same dictionary (see inflateSetDictionary). without producing any compressed output."
17:56:29 <fizzie> "The dictionary should consist of strings (byte sequences) that are likely to be encountered later in the data to be compressed, with the most commonly used strings preferably put towards the end of the dictionary. Using a dictionary is most useful when the data to be compressed is short and can be predicted with good accuracy; the data can then be compressed better than with the default empty ...
17:56:41 <fizzie> But as far as I could tell, the command-line tools didn't provide for that.
17:58:25 <fizzie> (Even though they could very easily have a "do {deflate,inflate}SetDictionary with the contents of file X before {,de}compression" option, and it might even conceivably be useful, to someone, somewhere.)
17:59:26 <int-e> anyway, extending zlib seems wrong, because the trick is usually to come up with a special purpose decompressor that exploits a lot of regular structure in the output that is know a priori.
18:01:52 <int-e> (For example, no matter how much you change its data portion, my Make24 entry will never print "Hello, world!")
18:02:24 <elliott> int-e: yes, I was mostly joking on the zlib solutions that float around.
18:02:56 -!- Oren has quit (Quit: Page closed).
18:03:11 <int-e> right, but usually they don't come out on top overall
18:04:53 <elliott> well, neither does Ada and it's still there :p
18:07:18 <elliott> int-e: actually, you know what might be interesting? an arithmetic coder language
18:07:42 <elliott> I think it's some PAQ variant that represents the compressed data as "prediction model algorithm" + "arithmetic coder output for that data with the prediction model"
18:08:07 <elliott> hard to see how to extend that to multiple outputs, sadly
18:08:16 -!- tromp has quit (Read error: Connection reset by peer).
18:08:42 <fizzie> I will try to use speech recognition participate in the discussion though
18:08:50 -!- tromp has joined.
18:09:11 <elliott> fizzie: lovely to see the spectacular fruits of your research
18:09:32 <fizzie> this is nothing really sucks this is the Google speech recognizer
18:09:42 * elliott pats the fizziebot's metallic head
18:09:43 <fizzie> not my research I mean
18:09:49 <b_jonas> int-e: hehe, mine won't either,
18:09:52 <elliott> fizzie: ah, well, you'd better go improve that, right?
18:09:58 <elliott> not that that would ever happen.
18:10:10 <b_jonas> `perl -e $_="Hello, world!"; s/\w\K\B/+/g;s/\w/hex$&/ge;s/(.*)=/($1)\xc3\x97/g;print
18:10:28 <fizzie> louhi accent is not entirely comfortable with it
18:10:33 <elliott> you're so much cuter in lowercase
18:10:45 <fizzie> I don't know how to speak in uppercase
18:11:24 <fizzie> my wife is finding this amusing
18:11:36 <elliott> is using this to talk part of the corporate culture there
18:12:12 <int-e> b_jonas: In my case it's a close call. you can make it print things like Hel+lo,+world+!
18:12:32 <fizzie> Autolab speech recognizer out it would be in my eye me listing
18:12:58 <int-e> b_jonas: because the numbers are actually taken from stdin.
18:14:20 <fizzie> I tried to make something based on the input numbers but forgot I had would have had to rearrange them
18:14:40 <elliott> what does your wife think of fungot
18:14:40 <fungot> elliott: looks more to me like a bush. actually, now i'm all about " do unto you!
18:15:21 <b_jonas> I don't use the input numbers at all
18:15:52 <b_jonas> in one version I read the first line to determine which of the three testcases I have, but $$ turns out to be shorter
18:16:27 <int-e> b_jonas: I was so happy when I found the -a options of perl.
18:17:00 <fizzie> it's happened to me when I was demonstrating this to some students
18:17:40 <fizzie> tried to say: how old is she
18:17:55 <fizzie> what came out was something something is shaped
18:18:13 <int-e> b_jonas: yes. it just so happened that I was already inserting the operators by indexing into an array, and this gave me another array to do exactly the same for the numbers, virtually for free.
18:19:12 -!- nooga has joined.
18:19:56 <elliott> fizzie: at least it's not as bad as dear aunt, let's set so double the killer delete select all
18:20:41 <b_jonas> dear fungot, let's set so double the killer delete select all
18:20:42 <fungot> b_jonas: that as well, i see!
18:20:49 <fungot> b_jonas: i look forward to. every. single. time.
18:21:16 <b_jonas> fungot, what came out was something something is shaped?
18:21:16 <fungot> b_jonas: that, but also a lot!
18:21:55 <b_jonas> fungot, how do you define a function template that can return void or non-void? can you really only do it with two separate overloads?
18:21:55 <fungot> b_jonas: to the last, i will grapple with thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee! from hell's heart, i stab at thee
18:22:25 <fungot> elliott: but a good one! it's funny this one time in high school, a friend, but i have a problem, t-rex?
18:22:39 -!- elliott has set channel mode: -b $a:copumpkin$##fixyourconnection.
18:23:40 -!- elliott has set channel mode: -o elliott.
18:25:09 <elliott> "Benedict Cumberbatch Can Charm Humans, but Can He Fool a Computer?" this is the best headline I've ever read
18:25:25 <elliott> "no, he can't fool computers into thinking he's human"
18:25:32 <elliott> by headline I mean wolfram blog post title
18:25:58 <b_jonas> fungot, what's the best headline you've ever read?
18:25:58 <fungot> b_jonas: don't i know you from somewhere? but, i mean, a male, i can be one of those people are going to think you're a pedophile, and he's on a friggin' universe. and then there'll be a day shortly afterwards when we can simulate universe on our cell, because there'd have been no controversy.
18:26:04 <elliott> "Turing machines were one of the focal points of the movie, and we launched a prize in 2007 to determine whether the 2,3 Turing machine was universal." come oooon
18:28:24 <elliott> http://blog.wolfram.com/data/uploads/2014/11/confident-results.png benedict cumberbatch revealed to be actually the same person as alan rickman by stephen wolfram
18:38:43 <fizzie> elliott kalanwww.fronter finnish speech recognizer ovat
18:39:47 <fizzie> langat funka puunkaato unikot kankaat langat kankaat
18:39:57 <fizzie> it's no use I can't say it
18:40:28 <elliott> I hope your research does a lot better than this
18:40:53 <fizzie> that last one was my wife crying
18:41:30 <fizzie> I will try to improve the phone with recognition I believe this office recognize out of
18:41:33 <elliott> can your marriage survive speech recognition
18:41:49 <Bicyclidine> i don't know if i can survive speed recognition
18:41:59 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz* sms speeches ss wp youtube
18:42:09 <fizzie> high-speed speech recognition
18:43:01 <Bicyclidine> now i want to try taking a speech recognition thing and hold it up to a radio announcer rattling off caveats for an insurance policy
18:43:09 <fungot> fizzie: are you you're going trick-or-treating this year will be better in the future. a year, a balloon! the balloon goes up some of the way, we can consider the real question, which is a good thing! stupid problems
18:44:03 <fizzie> I had to speak fun and got separately
18:44:19 <elliott> did you find the west gutter yet
18:45:10 <elliott> is this on a computer or a phone, anyway?
18:45:25 <fizzie> I'm doing it on my android tablet
18:45:57 <fizzie> so everything I say it sent to Google satellite
18:46:33 <fizzie> can't reach Google at the moment it says
18:47:12 <fizzie> I think this works better for native English speakers
18:47:42 <fizzie> also I have it set to recognize both in Spanish and English
18:48:12 <fizzie> voisi puhua myös suomea
18:49:47 <elliott> you still seem so tiny in lowercase.
18:49:55 <elliott> ...do you even speak spanish?
18:53:32 <fizzie> thanks to machine translation I want need to
18:55:23 <elliott> can it automagically do speech recognition -> translation -> IRC?
18:57:05 <fizzie> its can do a speech recognition to translation to speech synthesis
18:57:17 <elliott> just hook that up to speech recognition again, then
18:57:47 <fizzie> sounds like the best idea
18:58:03 <fizzie> I don't have a second device though
18:58:25 <elliott> they don't shower you with devices when they initiate you?
18:58:40 <elliott> maybe you could use some of Your Research on your computer as the other speech recogniser
18:58:56 <fizzie> I haven't actually started yet
18:59:28 <fizzie> so it's mostly about to finish
19:01:02 -!- AndoDaan has joined.
19:07:27 <fizzie> I tried to say in Microsoft you about finish
19:08:05 -!- ion has quit (Ping timeout: 250 seconds).
19:08:07 <fizzie> my research ace about the Finnish language
19:08:39 <elliott> okay, so translate english -> finnish
19:09:10 <elliott> don't worry, I can translate what you say back to english
19:09:31 <fizzie> I don't have a lot of things up hahaha system have at home
19:09:36 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41230&oldid=41222 * 71.184.241.244 * (+3)
19:09:58 <Bicyclidine> that person still hasn't seen my talk page note, have they
19:12:27 -!- Oren has joined.
19:13:02 -!- Lorenzo64 has joined.
19:15:57 <elliott> fizzie: so is google speech recognition only going to work in finnish soon
19:20:09 <elliott> Busy testing speech recognition I physeal I'm testing speech recognition to
19:20:15 -!- ion has joined.
19:20:32 <elliott> this is probably even worse
19:20:48 <elliott> okay it seems to be better if I don't claim username
19:21:37 <elliott> and so glad when this is speech recognition
19:23:52 -!- AndoDaan_ has joined.
19:24:13 <fizzie> metsästysseura human computer interaction
19:24:38 <fizzie> it's the phoyoutubefuture
19:24:58 <fizzie> having more than one language enabled is probably not a good idea
19:25:41 <fizzie> it was correct for a moment. Before the trip lasted with the finish world
19:25:54 <elliott> Angela venture furniture S you N G oh T
19:26:12 -!- AndoDaan has quit (Ping timeout: 265 seconds).
19:26:32 <elliott> this is a applesauce action
19:27:10 <fizzie> raision sähköpalvelu grinders
19:27:10 <HackEgo> 722) <Taneb> hang on I have bright idea <Taneb> navajo to f me 1 in 3 people
19:27:20 <elliott> this is apples fault Picture children
19:27:39 <fizzie> so are you using an Apple device
19:28:20 <elliott> of course it gets that I Word right
19:28:36 <fizzie> it has its priorities in autumn
19:28:47 <elliott> it doesn't work very well with the terminal on my accent all my accent all my accent all my accent or my accent
19:29:59 <fizzie> at first you don't succeed
19:30:08 <fizzie> latvia sveitsi live stream
19:30:22 <fizzie> ok I'm switching this to English only
19:30:31 <elliott> it's weird it's takes out of her it types out there wrong words but then backspaces and cracked them and corrects them in a split Second
19:30:46 <fizzie> this thing does that too
19:31:13 <elliott> how come it has given you any Spanish not knot yep yeah yet
19:31:27 <elliott> how come did not give you any Spanish
19:32:17 <elliott> cannot you join into can you cannot and Again they can invent Dawn Nathan Doctor doom
19:32:24 <fizzie> the Spanish was a mistake
19:32:35 <fizzie> no I have only English subject did
19:32:36 <elliott> can then Tanya can then oh Tanya was close
19:32:58 <elliott> Tanya you should join into in to oh
19:33:21 <Taneb> I did this ages ago and it didn't end well
19:33:22 <fizzie> oh you meant Ahmed lemon finance 10m kinetic Thunderhead Gangnam
19:33:26 <elliott> you are typing now your tendon you can you you Tanya
19:33:54 <fizzie> about the software has improved drastically
19:34:17 <elliott> what was metal and finance 10 m meant to be
19:34:42 <elliott> Connecticut thunderhead getting them
19:34:47 <elliott> I'm so glad it knows gang them
19:35:16 <fizzie> I'm sure that train this with us out of sorts queries
19:36:23 <fizzie> it inserts on that last E
19:37:07 <fizzie> tanee be Tanabe I am dB
19:38:31 <fizzie> I don't think I can get this right
19:38:51 -!- Sprocklem has joined.
19:39:13 <elliott> was philosophy osteopathic
19:39:13 <fizzie> le up Colin it doesn't know you are an A
19:39:27 <elliott> that's just call him coughing
19:39:36 <elliott> let's just call him: Colin
19:39:55 <fizzie> I feel bad for the laundry.
19:40:11 <elliott> fizzy isn't so great either
19:40:29 <elliott> your real name would be worse L Shell so so
19:40:30 <fizzie> it's quite close at least
19:41:07 <fizzie> I think it knows my name
19:41:17 <fizzie> it's also knows where I live
19:41:31 <ion> are you chatting with speech recognition I want to try to this is fun
19:41:36 <fizzie> it didn't know my birthday when I asked
19:41:45 <elliott> honey doesn't look as my recognise my name at all
19:42:11 <ion> Hello Elliot and fizzy
19:42:27 <fizzie> hey i on what device are you using Autobots truck driver
19:42:49 <ion> Google voice input on a samsung galaxy phone
19:43:01 <fizzie> this is Google Voice invite on the Nexus tablet
19:43:04 <elliott> Busy MacBook is this actually getting married
19:43:24 <fizzie> honeymoon after getting married
19:43:35 <J_Arcane> this entire channel has become a recursive markov chain ...
19:43:36 <elliott> it's too complicated can you walk me to it
19:44:05 <fungot> fizzie: this i do believe so! excuse to stomp! little does the dromiceiomimus know that i intend to do today! we can't hang out in paradise, alone, to raise the friggin'. fragile, species can survive their electrical onslaught
19:44:21 <ion> Testing. Explicit punctuation seems to work.
19:44:26 <fizzie> I have to stop talking in the middle of fun and got
19:44:40 <fizzie> I am calling I tried suicide calling but it didn't recognize
19:45:17 <elliott> peace and police officer please don't call yourself busy
19:45:29 <fizzie> ion:and get drunk show a shin is sometimes but not often
19:46:01 <ion> I have trouble importing fungal
19:46:20 <fizzie> I don't remember what I was trying to say when it recognize it by side
19:46:35 <elliott> I have trouble importing fungal to
19:46:46 <J_Arcane> omg https://github.com/jhallen/joes-sandbox/tree/master/exorsim/mpl
19:46:53 <fizzie> try saying fun than typing to post tense tense I got
19:46:56 <elliott> are you still tan sexy fizzy
19:47:10 <fizzie> yes I insist a lot of sexy
19:48:46 <elliott> I'll be getting married fizzy
19:49:04 <fizzie> who are you are getting married to
19:50:16 -!- hjulle has joined.
19:50:38 <fizzie> and don't think you can get somebody to talk concept
19:51:25 <Oren> what was wrong with using a keyboard?
19:51:27 <elliott> I can talk and settlement all I want
19:51:35 <elliott> it's not the future on Oren
19:52:07 <fizzie> it's so much more convenient this way
19:52:09 <Oren> what about when there are 25 people in the room with you
19:52:21 -!- AndoDaan_ has quit (Ping timeout: 264 seconds).
19:52:30 <Oren> all talking into their computers
19:52:57 <zzo38> To me keyboard is better and I can type fast too
19:52:58 <elliott> is he loves problems like that fizzy
19:53:07 <zzo38> Speaking into the computer is good if you want a sound recording though
19:53:19 <zzo38> But I don't need a sound recording
19:53:22 <elliott> if I want to send according I can progress into speech since that
19:53:31 <elliott> if I want a sound recording I can progress into synthesiser
19:54:31 <fizzie> but he's the best apps Mario's full on the phone with no good kid lock
19:54:36 -!- AndoDaan has joined.
19:54:53 <fizzie> invite in public is probably Mario s photo on phone with no good keyboard
19:55:05 <fizzie> voice input models for
19:57:24 <fizzie> checklist google image search
19:57:50 -!- AnotherTest has joined.
20:17:31 -!- AndoDaan has quit (Ping timeout: 258 seconds).
20:23:44 <FireFly> You should try speech-recognizer | bash | speech-synthesizer
20:24:29 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41231&oldid=41230 * 71.184.241.244 * (+543)
20:25:38 <fizzie> actually my colleague my speech recognizer into xD O'Toole
20:25:48 <fizzie> so that it would type into any window that has focus
20:26:01 <fizzie> I tried to write one paragraph of my teeth is using it
20:26:04 <b_jonas> well, I'm not an engineer, I don't know.
20:28:22 <fizzie> it was kind of dangerous
20:29:09 <Vorpal> fizzie, hm? xdotool? Isn't that for moving windows around and such?
20:29:17 <FireFly> xD O'Toole is a good name for software
20:31:10 <Vorpal> Right, a different one according to the logs. Speaking of which, why didn't znc replay the log like it is configured to when I reconnected?
20:31:48 <b_jonas> fungot, why didn't znc replay the log like it is configured to?
20:31:49 <fungot> b_jonas: dromiceiomimus, i don't!
20:33:51 -!- AndoDaan has joined.
20:35:21 -!- tlewkow has quit (Remote host closed the connection).
20:42:50 <fizzie> yes you can use it to type 2
20:43:12 <fizzie> in addition to moving windows and stuff
20:43:33 <fizzie> it pretends to be a kid lot
20:43:42 <fizzie> send stupid a key events
20:44:45 <FireFly> translating speech recognition output → english is quite tricky at times
20:47:48 -!- Sprocklem has quit (Ping timeout: 258 seconds).
20:48:14 <Vorpal> Is there a way to say to cabal "fix mixed versions"? I.e rebuild any packages depending on different versions of a package so that everything just works, and I don't get weird errors.
20:48:24 -!- ion has quit (Ping timeout: 255 seconds).
20:53:45 <elliott> using cabal sandbox is probably the best option but I'm a year+ out of date with haskell
20:54:05 <Vorpal> elliott, I mean, gentoo managed to make this shit work, so why can't haskell
20:54:23 -!- zzo38 has quit (Remote host closed the connection).
20:54:33 <elliott> well, the problem is inherently hard. cabal has some questionable behaviour in response to it, though
20:55:23 <Vorpal> I'm fine with it telling me that "these packages will need to be rebuilt if you update this package, do you want me to do that, recursively?"
20:55:42 -!- AndoDaan has quit (Quit: Quit).
20:55:49 <Vorpal> Or of course "this will break, and the version restrictions in the dependencies make it unsolvable"
20:56:14 <Vorpal> It should never let me end up in a state where I have a pretty much broken environment
20:56:30 <Vorpal> So yes it would need rollback support
20:56:50 <elliott> does gentoo actually allow coinstallation of multiple versions?
20:57:59 <Vorpal> elliott, not in general, but for some packages that marks it as ok (for example, kernel, major gcc versions, ...)
20:58:49 <Vorpal> It does have infrastructure for rebuilding broken packages though
20:59:21 <elliott> well, cabal allows multiple versions of the same package. so the problem is fundamentally different
21:00:11 <Vorpal> True, but I'd in general prefer to not have multiple versions because right now I'm dealing with two different packages that want different versions of a common dependency
21:00:28 <Vorpal> So I have to rebuild stuff, but I can't find any automated way to do it
21:00:33 <elliott> Vorpal: are you sure you'd prefer that? what about when half of the library ecosystem depends on QuickCheck 2 and the other half QuickCheck 3?
21:01:06 <elliott> Gentoo has control over all its packages
21:01:12 <elliott> so it can avoid things like that
21:01:15 <elliott> if you want something like that, check out stackage.
21:01:27 <Vorpal> elliott, however, what am I supposed to do when I have B needs A1 and C needs A1 and I need to exchange A-data between B and C
21:01:37 -!- ion has joined.
21:01:44 <Vorpal> Which is my current issue
21:01:55 <Vorpal> elliott, I will check that out, thanks
21:01:56 <elliott> I think you typo'd somewhere there
21:02:05 <Vorpal> elliott, err yea, A1 and A2
21:02:41 <elliott> well, nothing on earth can solve that problem. it is true that it is all too easy to get multiple versions of a library linked within a single *program*, which is only okay if those libraries are implementation details for other libraries you use, basically.
21:02:55 <elliott> (you *can* work with multiple ones explicitly with PackageImports I think, but please god don't)
21:03:11 <elliott> cabal sandbox would help avoid that because it'd install your dependencies "all at once"
21:03:25 <Vorpal> elliott, It isn't like B or C actually need different versions of A, it is just they ended up being built against different versions
21:03:38 <elliott> yes, hence my cabal sandbox remark
21:04:29 <Vorpal> elliott, I added C to the project much later, I guess in that case I would have to rebuild the sandbox from scratch? I will have to look into how that works. And stackage. And find out which option is best for me.
21:04:46 <elliott> I forget if it'd just work or not.
21:04:56 <elliott> stackage is something you use *with* the sandbox, generally, I think
21:05:04 <elliott> the nice thing about the sandbox is that your projects are fully isolated from each other
21:05:13 <elliott> also, I think by now "rebuild" may not actually be rebuilding, because cabal caches builds properly
21:05:32 <Vorpal> My main point here is that there doesn't seem to be much help for you once you run into an issue like that. On gentoo at least there is tools to clean up the mess.
21:06:39 <elliott> it's easy to clean up with cabal sandbox.
21:06:42 <elliott> just blow away the sandbox.
21:06:53 <elliott> if you don't isolate, then the analogy is rm -rf ~/.cabal
21:07:07 <Vorpal> I didn't isolate, because I didn't know I could do that.
21:07:28 <elliott> I agree the haskell library experience is hell.
21:07:42 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41232&oldid=41167 * Orenwatson * (+423) better interpreter version, brainfuck interpreter
21:08:19 <Vorpal> Right. Also that will take a while to rebuild, because one of the libraries in there has like 100 of deps... (not related to the issue though).
21:08:38 -!- tlewkow has joined.
21:08:39 <newsham> its so simple.. just create a different user for each project!
21:10:42 <Vorpal> Yeah I definitely think cabal could do a much better job of preventing situations like this and helping you fix them.
21:11:11 <Vorpal> I should look into how NixOS does this. Since it allows multiple versions to co-exist
21:11:44 <Vorpal> elliott, do you happen to know how nixos deals with this?
21:11:55 <Vorpal> That should be a much better analogy than gentoo in fact
21:13:19 <Oren> Does the requirement that a pointer to memory be a fixed size in memory make a language turing-incomplete?
21:13:44 <Bicyclidine> having a finite number of possible states rules out turing completeness, yes
21:13:56 <fizzie> the Mondeo system also I love smoking bowl out of snow
21:14:19 <fizzie> http://modules.sourceforge.net/
21:14:32 <fizzie> it's very simple though
21:14:59 <fizzie> cheated by copying pasting the f you out of hell
21:15:19 <Vorpal> "<fizzie> the Mondeo system also I love smoking bowl out of snow" <-- what
21:15:38 <fizzie> the muscular system of a lot of installing multiple lation
21:15:51 <fizzie> the more the old system the money he owes
21:15:51 <Vorpal> fizzie, are you drunk?
21:16:17 <fizzie> there we go I was pronouncing it wrong
21:16:34 <fizzie> so the module system allows installing multiple version
21:17:01 <Vorpal> fizzie, why are you using voice recognition?
21:17:33 -!- Oren_ has joined.
21:17:52 -!- Oren has quit (Ping timeout: 246 seconds).
21:18:09 <Oren_> Because C requires ability to acesss pointers to arrays of pointers, so pointers have to have a fixed size
21:18:17 <fizzie> I will start working for Google Nexus. Or so I thought I'd try out what about system its like
21:18:57 <Oren_> which means the set of languages in the real world that are turing complete is rather small
21:19:08 <fizzie> and not the Nexus next year
21:20:05 <Vorpal> Oren_, unless you do some tricky stuff with IO to add extra storage. For a non-seekable file (i.e. pipe), there is no size limit as far as I know
21:20:58 <Oren_> oh! that could work
21:21:18 <fizzie> it's kind of external the language love
21:22:09 <Vorpal> Yes use a pipe to self as an infinite queue, probably needs POSIX on top of C though, don't think the pipe functions are in standard C
21:22:28 <fizzie> prostate spike buck Futter sought a very limited in size
21:22:54 <elliott> prostate spike buck Futter
21:23:10 <fizzie> this doesn't work but it well otto technical topics
21:23:26 <fizzie> I'll cheat with a keyboard for a moment.
21:23:28 <Oren_> he says pipe buffers are small
21:23:35 <fizzie> You can't write an infinite amount into a POSIX pipe.
21:23:36 <Vorpal> Oren_, how did you decode that
21:23:48 <elliott> if you speak it out loud and imagine it's muffled and look at context that can help
21:23:55 <Vorpal> fizzie, well that is a technical limitation of the real world, ulimit and so on
21:24:01 <Oren_> I did that in my head yeah
21:24:01 <elliott> "posix pipe buffers are very limited in size"
21:24:15 <FireFly> Couldn't you address a potentially infinite amount of files in C?
21:24:33 <FireFly> I guess there is technically a limit on the length of the filename
21:24:41 <Vorpal> Yes in the real world they are very limited, and so is RAM. but I don't know that it is specified to not be potentially infinite
21:24:42 <FireFly> since the filename has to be in RAM
21:24:49 <elliott> Oren_: did you, like, logread old #esoteric arguments about C turing completeness
21:25:23 <Oren_> i was wondering if my language scrip7 could possibly be turing complete.
21:25:29 <Vorpal> FireFly, yes, it becomes number of possible files * sizeof(fpos_t) or something like that
21:25:38 <Vorpal> Which is HUGE, but not infinite
21:25:53 <Oren_> it seems probably not
21:25:57 -!- Frooxius has quit (Quit: *bubbles away*).
21:26:18 <elliott> unless your language is defined in terms of C
21:26:19 <Oren_> a language has to be quite abstract to be turing complete it seems
21:26:39 <elliott> nah, C is just unusually airtight in that respect, IMO
21:26:40 <Oren_> my language inherits many features from C but has a terse syntax
21:26:55 <fizzie> Vorpal: The fact that PIPE_BUF is defined kind of implies there must be a limit.
21:26:58 <Oren_> features like pointer arthmetic
21:27:14 <elliott> looking at https://esolangs.org/wiki/Scrip7, does anything in the language prevent you from making pointers bignums?
21:27:15 <fizzie> But it's possible it's not quite entirely explicitly required.
21:27:41 <fizzie> (The references to PIPE_BUF are mostly about atomicity and behaviour w.r.t. blocking.)
21:27:56 -!- Frooxius has joined.
21:28:14 <Vorpal> fizzie, where is that defined? I don't have the PDF on this computer, so I'm trying to find the man page
21:28:16 <Oren_> well, you are supposed to be able to go o>i to access the ith element of a list of pointers at o
21:28:17 <fizzie> And it's indeed defined as the "maximum number of bytes that is guaranteed to be atomic", so.
21:28:42 <elliott> Oren_: just imagine an abstract model of the language where pointers are represented by arbitrary natural numbers
21:28:51 <elliott> and memory is an infinite list of those
21:29:01 -!- Patashu has joined.
21:29:15 <elliott> I guess if you can access things as chars then you can "see" the representation of bignums which might be awkward
21:29:15 <newsham> [11:25] < Oren_> a language has to be quite abstract to be turing complete it seems
21:29:27 <fizzie> Vorpal: The constant's defined in the POSIX spec of <limits.h>. But you're right that maybe it's not strictly speaking a limit for the maximum amount of pending data. It's of course not defined by C.
21:29:28 <newsham> C integers can be unbounded size, no?
21:29:44 <newsham> does the standard mandate a finite size?
21:29:52 <Oren_> no there is intmax.h or something
21:29:58 <Vorpal> fizzie, well yeah I don't think pure C can be made TC
21:30:05 <fizzie> newsham: At least you can make a strong argument that the value of sizeof must be a finite number.
21:30:34 <newsham> so obviously someone needs to make a C variant!
21:30:52 <Oren_> I kind of made a c variant
21:31:03 <Vorpal> Taneb, only at compile time, and with infinite template evaluation depth iirc
21:31:04 <FireFly> Taneb: does C++ include the C++ preprocessor?
21:31:10 <Oren_> it has different syntax but very similar semantics
21:31:19 <Taneb> FireFly, I don't think so :(
21:31:40 <Vorpal> FireFly, the preprocessor of C and C++ is limited, maximum recursion depth and so on
21:31:48 <Oren_> or at least C as it is commonly implemented on x86
21:31:59 <Taneb> I did make a factorial function using GHC's type system
21:32:05 <Vorpal> Think it is specified as a "at least" though
21:32:19 <FireFly> Well, 'at least' is fine :P
21:32:21 <Taneb> It runs surprisingly quickly, but if you ask for the factorial of some big numbers things go wrong
21:32:26 <FireFly> That's a bound in the "right" direction
21:32:37 <Vorpal> FireFly, not quite sure. It is something like "at least x recursive include", not sure if has to limit it at all
21:32:46 <Taneb> (I think when log_2 (n!) > 200 or so)
21:32:54 -!- Sprocklem has joined.
21:33:11 <Vorpal> FireFly, I recommend checking the spec, which I don't have downloaded on this computer
21:33:42 <Vorpal> FireFly, similar for the recusion of templates in C++, "at least x iterations"
21:34:02 <Vorpal> Pretty sure GCC limits both though
21:34:08 <Vorpal> And neither is at runtime of course
21:34:17 <Oren_> GCC isn;t the spec tho
21:34:52 <Oren_> some madman might have made a wildly screwed up compiler that breaks conventions
21:35:07 <fizzie> I'm pretty sure the C preprocessor is generally considered not TC, but I've forgotten the argument against why recursive include doesn't make it so.
21:35:10 <Vorpal> Well obviously, but it is a common implementation. Just saying it isn't viable to use it practically
21:35:15 <fizzie> The macro expansion has explicit no-recursion rules.
21:35:16 <Oren_> and allows as many templates as there is memory for
21:35:40 <Vorpal> fizzie, C++ templates are TC I'm fairly certain though
21:35:45 <fizzie> The templates are, yes.
21:36:01 <Vorpal> Again with infinite recursion
21:36:03 <fizzie> And if you allow repeated executions of the C preprocessor, with the output fed in as the new input, it is too, I believe.
21:36:35 <Oren_> cpp can't generate newline
21:36:55 <Oren_> so the number of lines decreases each iteration of cpp
21:37:03 <Vorpal> Or it could stay equal
21:37:12 <Vorpal> There is no need for it to be multiple lines either
21:37:18 <Vorpal> What matters is statements
21:37:24 <fizzie> Well, I mean. You know, this thing: http://www.ioccc.org/2001/herrmann1.hint
21:37:31 <Oren_> #define isn't a statement
21:37:43 <Oren_> it ends at newline not ;
21:38:02 <Vorpal> True, but you can't generate directives anyway
21:38:05 <elliott> fizzie: I don't know if it's TC or not. it can implement a functional language
21:38:09 <elliott> it does seem to be weirdly limited somehow though
21:38:15 <elliott> I can't figure out how to even do the things the wizards do with it
21:38:28 <Vorpal> Oren_, also look at the Boost Preprocessor library, it is quite interesting how much you actually CAN do with it
21:38:44 <Oren_> isn't boost C++ tho
21:38:48 <fizzie> chaos-pp/order-pp are IMO the most interesting preprocessor abuses.
21:39:02 <Vorpal> Oren_, Sure but the preprocessor bit is basically the same for both
21:39:08 <fizzie> But they too have some non-TC upper bounds.
21:39:25 <Vorpal> fizzie, what is chaos-pp/order-pp?
21:39:27 <elliott> ah, what is order-pp's upper bound?
21:39:29 <elliott> that was the language i was talking about
21:39:33 <fizzie> https://github.com/rofl0r/order-pp/blob/master/example/fibonacci.c
21:39:46 <b_jonas> Vorpal: that, and also the P99 library
21:39:47 <FireFly> https://github.com/rofl0r/chaos-pp/blob/master/chaos/preprocessor/algorithm/merge_sort.h ...
21:39:52 <fizzie> "Unless you are already convinced, you should check, by preprocessing this example, that the actual parameter to `printf' in the above code is just a single string that contains the 500th Fibonacci number in base 10."
21:40:05 <fizzie> elliott: IIRC, it's configurable. But it must be an integer.
21:40:21 <elliott> right, but I mean, what's it an upper bound *on*?
21:40:57 <elliott> I would really like cpp to be TC...
21:41:22 <b_jonas> Vorpal: http://p99.gforge.inria.fr/
21:41:24 -!- dts has joined.
21:42:29 <b_jonas> but I think the boost preprocessor library has more powerful stuff
21:42:36 <fizzie> elliott: Something like that. It's part of chaos, and that's even more confusing than order. Something something exponential.
21:43:16 <Vorpal> b_jonas, Well I seen some simple Boost PP code evaluating lists of stuff and such mostly
21:43:33 <elliott> Vorpal: should just click fizie's fibonacci link :p
21:44:02 <Vorpal> And no I can't read it :P
21:44:38 <Vorpal> I think those lists are limited to 255 elements in boost preprocessor though
21:44:41 <fizzie> The thing with all the 8s seems to be characteristic of preprocessor things that "go too far".
21:44:55 <fizzie> (Sometimes it's some other number.)
21:45:55 <Vorpal> Does it need to be a number?
21:45:55 <fizzie> I had some sort of intuition why it's required, but I've completely blacked that out.
21:46:31 <elliott> it stops it being interpreted as a preprocessor token thingy, I think
21:47:12 -!- dts has quit (Quit: Leaving).
21:47:32 -!- dts has joined.
21:47:58 <Oren_> oh yah, did i mention the bf interpreter for scrip7 expands the memory dynamically?
21:48:02 <Oren_> Q=(a>1S=PS+NS~ON*2bNNO=PN/2O+NaS0N*2#H+3G=H`)
21:48:24 <b_jonas> um, is that a chemical formula?
21:48:33 <Oren_> its a function in scrip7
21:48:52 <fizzie> "8foo" is a single pp-number in the translation phase that decomposes the source to preprocessing tokens.
21:48:55 <Oren_> it conditionally expands the bf memory if it needs to
21:49:00 <Vorpal> Hm, Boost PP should be usable in C I assume
21:49:07 <b_jonas> does it deliberately try to look like a chemical formula?
21:49:24 <Oren_> but i see what you mean
21:49:39 <Oren_> what with NN0 and such
21:49:58 <fizzie> (The "pp-number" syntax includes just about everything that starts with a digit, it can be followed by arbitrary identifier characters.
21:50:25 <fizzie> But it's still a pp-number and doesn't participate in macro expansion and such in the same way as identifiers; it probably has something to do with that.)
21:50:30 <Oren_> N is register 5 accessed as a 64bit int
21:50:55 <Oren_> O is register 0 acessed as an adress
21:50:58 <fizzie> Also I didn't realize order-pp grew out of the Boost preprocessor library: https://github.com/rofl0r/order-pp/blob/master/README.md
21:51:38 <Oren_> because someone went completely bonkers?
21:52:33 <Bicyclidine> hm, smiles uses @@ for stereochemistry. bizarre
21:52:38 <FireFly> Apparently order-pp has (.)
21:52:50 <FireFly> "8compose(f, g) : (a -> b) -> (c -> a) -> (c -> b)"
21:54:15 <Oren_> ~ is equality test becuase = was taken by assignment
21:55:16 <Vorpal> FireFly, that looks haskellish
21:55:19 <Oren_> what kind of chemical formula uses *2 tho?
21:55:38 <FireFly> Vorpal: looks like the type signatures in https://github.com/rofl0r/order-pp/blob/master/doc/notes.txt are haskell-inspired
21:55:40 <elliott> fizzie: rather, chaos-pp did
21:55:54 <elliott> that repo is chaos-pp with all the parts that aren't needed for order-pp removed, I guess
21:56:31 <FireFly> Oren_: is : used for anything?
21:56:53 <Vorpal> elliott, okay, so which one should you use? chaos or order?
21:56:53 <Oren_> : is used for "set and move forward"
21:57:07 <elliott> chaos-pp is a cpp library.
21:57:11 <elliott> order-pp is a language implemented in cpp.
21:57:16 <elliott> that uses chaos-pp, I think.
21:57:25 <Oren_> like if you have (struct){int i; long j; char *s}
21:57:53 <FireFly> K has : for assignment and = for equality, at any rate
21:57:55 <Oren_> then you do i:4 I:2 o:"foobar" to set each variable in turn
21:58:31 <Oren_> this grew out of a config file format
21:59:13 <FireFly> A config file that is essentially compressed C?
21:59:18 <Oren_> yes now config files can modify arbitrary memory inside the game
21:59:28 <Oren_> but it is interpreted
22:00:03 <Oren_> but it uses ragisters, not variables
22:00:04 <elliott> 8paste(l, r) : a -> b -> c -where 8isnt_edible(r)
22:00:06 <FireFly> Well, I guess it's not too different from emacs' config files
22:00:20 <Oren_> which are lisp iirc
22:03:18 <Oren_> if my game was any good I'd postit
22:05:04 <b_jonas> Oren_: well, that looks like it's easily turing complete to me. you can allocate memory, point into it with several pointers, move those pointers, read and write through them, you have loops and conditionals (even if I'm not sure how those conditionals and loops work).
22:06:05 <Oren_> the conditionals are skips: i~0 skdkasj # will skip to the # if the 0 register points to a 32 bit value of zero
22:06:27 <b_jonas> Oren_: so they skip to the next # commadn?
22:06:43 <Oren_> and $ is unconditional jump
22:06:50 <b_jonas> and the # command itself is a no-op?
22:07:18 <Oren_> (){}[] are all unconditional loops inside unconditional jumps
22:07:40 <b_jonas> and you can exit from them with a skip instruction
22:07:47 <Oren_> liek goto b a: goto a b:
22:08:05 <b_jonas> not that it's really needed, but is there an easy way to have a nested if?
22:08:21 <elliott> b_jonas: C has all those properties too
22:08:43 <Oren_> reverse condition and use i!0{# dfsdsdf}
22:09:16 <b_jonas> elliott: meh, it's turing-complete enough for my purposes.
22:09:22 <Oren_> scrip7 should be about as TC as C
22:10:04 <elliott> b_jonas: but the topic was whether scrip7 was actually TC, with the (correct) assumption that C isn't.
22:10:20 <elliott> (C is not turing complete enough for esowiki categorisation, say, which is relevant here)
22:10:32 <b_jonas> Oren_: what I don't understand is, why are the registers of different types aliased? wouldn't it be better if they were separate, and there was a command for assigning the pointer from one to another?
22:11:01 <Oren_> so that you can easily set a bunch of members of a struct in order
22:11:12 <b_jonas> Oren_: in fact, are there commands to read and write the address where a register is pointing to to the memory?
22:11:50 <b_jonas> oh, so that's what the addr type does!
22:12:05 <Oren_> it gets the value of the pointer itself
22:12:30 <b_jonas> that also explains how the G register works
22:12:45 <Oren_> yeah that's how you make subroutines
22:13:05 <Oren_> by convention i've been using H to store the return address
22:13:34 <Oren_> if you look at the bf interpreter the > and < commands use subroutines
22:13:49 <Oren_> it's really more of a compiler...
22:14:11 <Oren_> it turns bf into scrip7 and then jumps directly into that code
22:16:11 <b_jonas> Oren_: scrip7 also looks like it's almost compilable, but not quite, because writes to the G register could be a bit difficult to compile
22:16:46 <b_jonas> you could probably still compile it, you'd just have to try to figure out some of the easier cases of writing to G, and if any remains, handle it with a big indirect jump table
22:17:09 <Oren_> yeah. even if you don't support jumping to data space You would need to ensure that each instruction's compiled form is the same size
22:17:18 -!- Sprocklem has quit (Ping timeout: 264 seconds).
22:17:50 <b_jonas> Oren_: you don't really have to if there's a table mapping the scrip7 addresses to compiled addresses
22:18:01 <b_jonas> though there's the problem that the scrip7 can have self-modifying code
22:18:11 <b_jonas> if that's allowed, you can't really compile
22:18:21 <b_jonas> because basically any instruction could write there
22:18:32 <Oren_> right.... but semantics of that are just as undefined as writing to a function pointer in C
22:18:56 <b_jonas> but if you forbid that and also forbid wild indirect jumps, you could compile it pretty efficiently
22:19:37 <Oren_> whoops need a cast through (void*)
22:20:08 <fizzie> Not really through void *.
22:20:16 <fizzie> Casting it directly to char * is no better or worse.
22:20:42 <fizzie> (But it does need a cast.)
22:21:05 <Oren_> using (void*) is instinct
22:21:23 <fizzie> It wouldn't work the other way around, anyway.
22:21:45 -!- AnotherTest has quit (Ping timeout: 264 seconds).
22:22:11 <Oren_> ((void (*)(char*))"Hello, world")("Foobar");
22:22:22 <fizzie> char *data; int (*f)(int) = (int (*)(int))data; needs a cast to the function pointer type, and going to a void * won't help.
22:23:39 <Oren_> line that i wrote above compiles with GCC
22:23:57 <fizzie> Yes, there's nothing "wrong" with it.
22:24:30 <Oren_> everything about it is evil, but you could theoretically use that for inline machine code
22:24:41 <b_jonas> Oren_: but what I don't see is how you're using this as a configuration format?
22:24:56 <fizzie> Not on very many systems.
22:25:00 <Oren_> Becasue the interpreter gets a pointer to the data space
22:25:20 <fizzie> I think we had some machine code oneliners here, but they're complicated by an ugly required mprotect call.
22:25:21 <Oren_> void scrip7(char *code,void *data);
22:25:44 <Oren_> so if you pass in a struct for the data, your code can alter the contents of that
22:26:49 <Oren_> and the main in scrip7.c is a weak symbol so the one in my game overrides it
22:27:13 <Oren_> while compiling it alone gives you an interpreter
22:27:45 <b_jonas> using such a low-level language as configuration file language sounds a bit unsafe, but whatever suits you
22:28:22 <fizzie> `run echo 'const char f[] = "1\xc0""1\xff""1\xd2\xff\xc0\xff\xc7H\x8d""5\n\0\0\0\xb2\x06\x0f\x05\xb0<1\xff\x0f\x05hello\n"; int main(void) { mprotect((void *)((unsigned long)f&~0xffful), 0x1000, 7); ((void (*)())f)(); }' | gcc -x c - -o /tmp/x && /tmp/x # with some implicit function declaration action
22:28:23 <Oren_> the whole point was for the configuration to be able to allocate memory for wtrings and such
22:29:20 <fizzie> There's `runc and `! c, but I always forget their peculiarities.
22:29:35 <fizzie> One needs all \s doubled because it allows \n so that you can use preprocessor directives.
22:29:39 <HackEgo> #!/bin/bash \ t=`tempfile` \ echo -e "$@" | gcc -trigraphs -o $t -x c - 2>/dev/null && $t \ rm $t
22:29:55 <elliott> is that because there's a trigraph for newlines or something
22:30:00 <HackEgo> #!/bin/sh \ . lib/interp \ interp_file "./interps/gcccomp/gcccomp c"
22:30:00 <fizzie> Possibly both of them need \\s, actually.
22:30:11 <elliott> `cat interps/gcccomp/gcccomp
22:30:12 <HackEgo> #!/bin/bash \ LANG="$1" \ echo >>"$2" \ \ case "$LANG" in \ c) \ HEAD='#include <stdio.h>\n#include <stdlib.h>\n#include <string.h>\n#include <sys/types.h>\n#include <unistd.h>\nint main(int argc, char **argv) {' \ TAIL='; return 0; }' \ EXT='c' \ GCC='gcc' \ FLAGS='-std=gnu99' \ ;; \ \ c++)
22:30:21 <elliott> `url interps/gcccomp/gcccomp
22:30:22 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/interps/gcccomp/gcccomp
22:30:26 <fizzie> That one has the "try it with a main function" thing.
22:30:30 <b_jonas> isn't there one that's like geordi, translating backslashes outside strings to newlines?
22:30:42 <fizzie> Like candide, you mean. :p
22:30:49 <fizzie> (The ##c answer to ##c++'s geordi.)
22:30:56 <fizzie> And no, we don't have anything fancy.
22:31:18 <fizzie> The \! c is closest in that it tries compiling with a provided main wrapper first.
22:31:19 <HackEgo> ./interps/gcccomp/gcccomp: line 53: 307 Segmentation fault /tmp/compiled.$$
22:31:22 <b_jonas> mind you, it would have to tokenize C for that, which isn't trivial with comments and raw strings and trigraphs and suchlikes
22:31:41 <elliott> b_jonas: you could maybe do something with libclang.
22:32:52 <fizzie> `! c int main(void) { puts("foo"); } /* there's also this problem */
22:33:21 <fizzie> That's because it turns into int main(void) { int main(void) { puts("foo"); } return 0; } which compiles and runs just fine.
22:33:34 <elliott> is that actually legal C99?
22:33:38 <fizzie> No, but it's legal GCC.
22:33:40 <elliott> wait, nested functions aren't C99
22:33:49 <elliott> isn't main reserved or something? can you really shadow functions??
22:33:54 <Oren_> nested functions are GCC11 or something
22:34:05 <fizzie> You can do int f(void) { int f = 42; return f; } so why not?
22:34:14 <fizzie> There was an attempt to add some flags that disable nested functions, but that ran into some other issue that I forget.
22:34:22 <Oren_> because gcc puts everything into the default version
22:34:38 <elliott> fizzie: probably it broke doing int f() { return 42; } printf("%d\n", f()); or such
22:34:56 <b_jonas> couldn't it just try to link without the wrapper first, then recompile and link with the wrapper if it fails to link?
22:34:57 <fizzie> `! c int main(void) { puts("you can do this but it's real silly"); } main();
22:34:59 <HackEgo> you can do this but it's real silly
22:35:29 <elliott> `! c void main() { puts("see, this is the right signature after all"); } main();
22:35:31 <HackEgo> see, this is the right signature after all
22:37:54 <elliott> not unless you want me to ban ou
22:39:01 -!- dts has changed nick to Sargon_.
22:39:24 -!- Sargon_ has changed nick to dts.
22:39:38 <fizzie> `run sed -i -e '47s/SOURCE/2/;48s/2/SOURCE/' interps/gcccomp/gcccomp # now that you mention it, I see no immediate reason why the order could not just be swapped
22:39:58 <fizzie> `! c int main(void) { puts("foo"); }
22:40:46 <Oren_> `! c puts("\e[32mdoes this work");
22:41:17 <Oren_> `! c puts("\33[32mdoes this work");
22:41:45 <elliott> fizzie: what was the other old unix box you have, an SGI Indy and a...?
22:41:50 <b_jonas> or even better, use the convention geordi does: if the code starts with an open bracket, then find the block of code (again not so easy), move it to the end, and make it the main functino
22:41:52 <fizzie> elliott: SparcStation 5.
22:42:24 <elliott> fizzie: right. I wonder if you can run Windows NT 4.0 on the SGI Indy.
22:42:27 <elliott> that sure would be something.
22:42:40 <Oren_> my dad has a AIX box still running
22:42:55 <fizzie> I have absolutely no idea what sort of machines the MIPS port of Windows NT ran on.
22:42:55 <elliott> b_jonas: windows used to support alpha, mips and powerpc, didn't you know? :)
22:43:18 <fizzie> Somehow I don't think it's SGI machines though.
22:43:24 <elliott> of course you can't find much in the way of third-party binaries, but they aren't nonexistent, either.
22:43:29 <Oren_> makes Mac moving to intel not a big deal
22:43:39 <elliott> well, I mean, nobody actually /used/ this
22:43:51 <elliott> except I think the Alpha port got some use because the chip could emulate x86 pretty well or something
22:44:08 <elliott> Windows NT was deliberately designed to be very portable, though
22:44:21 <fizzie> Apparently ARC-compliant MIPS systems.
22:44:22 <elliott> they designed it on a random Intel RISC chip that they never actually shipped it on to ensure that
22:44:29 <b_jonas> elliott: really? I thought it supported only one architecture besides x86, possibly if you don't count intel64 which was later
22:44:31 <fizzie> So it's even borderline possible, because Indy is on that list.
22:44:53 <fizzie> "Windows NT 3.1 was released for Intel x86 PC compatible, DEC Alpha, and ARC-compliant MIPS platforms. Windows NT 3.51 added support for the PowerPC processor in 1995, specifically PReP-compliant systems such as the IBM Power Series desktops/laptops and Motorola PowerStack series; --"
22:45:16 <elliott> fizzie: it would reveal how much of a dork I am if I said having a real live non-x86 machine running Windows has been a pipe dream of mine for years now, right?
22:45:27 <elliott> I mean, I'd get absolutely no use out of it.
22:45:32 <b_jonas> elliott: you mean non-emulated, right?
22:45:34 <elliott> but what a beautiful object it'd be.
22:45:38 <b_jonas> because emulated it'd be easy
22:45:40 <elliott> b_jonas: I said real live :p
22:45:50 <elliott> I've done it emulated, I think, maybe. it's not as easy as it should be.
22:45:56 <b_jonas> elliott: no, I mean the box would be real live, but it ran an x86 emulator with windows in it
22:46:06 <b_jonas> that's the config that would be easy
22:46:08 <Oren_> i have a NES, I was born in 1993 when the SNES was getting old
22:46:16 <fizzie> elliott: "Intergraph Corporation ported Windows NT to its Clipper architecture and later announced intention to port Windows NT 3.51 to Sun Microsystems' SPARC architecture,[41] but neither version was sold to the public as a retail product." You should try to get hold of that.
22:46:43 * elliott has bricked two PPC macs trying to get unix onto them
22:46:51 <fizzie> Though "announced intention" is particularly vague.
22:47:19 <elliott> fizzie: I should track down Dave Cutler and pry the Intel i860 version of NT from his cold, dead hands.
22:47:30 <b_jonas> (I run an emulated windows 3.11, but that's on an x86_64 machine)
22:47:52 <elliott> fizzie: I wonder how hard it'd be to get NT 4 running on a PPC mac
22:47:55 <Oren_> I have like 300 DOS games
22:47:55 <elliott> I mean, very hard, I'm sure.
22:48:04 <elliott> but it sounds kind of like a small matter of (lots and lots of) programming.
22:48:35 <fizzie> I was browsing through my closets the other day (looking for a UK-compatible power cable I knew I had somewhere), and came across the 13W3-to-4xBNC monitor cable for the Sparc/Indy (they share the same Sun 13W3 display connector), and a 25-pin-serial to 9-pin-serial cable I think I used as a serial console for one of them.
22:48:39 <Oren_> like a moon landing or something
22:49:28 <fizzie> What I'm slightly worried about is that I didn't locate the 13W3-to-13W3 cable that used to connect the Indy to its own SGI-issue monitor. But maybe it's in the basement wrapped around the monitor or something.
22:50:01 <elliott> are you sure the computers are still there? how do you know they haven't fleed?
22:50:10 <Oren_> if your house is like mine then they are still there
22:50:21 <elliott> whoa, I just realised NTFS = NT FS
22:50:39 <elliott> I think that's the second most obvious thing I've ever missed
22:50:41 <Oren_> what does NT stand for?
22:50:59 <Vorpal> * elliott has bricked two PPC macs trying to get unix onto them <-- what? how?
22:51:02 <fizzie> Incidentally, 13W3 is the silliest connector: it's like a regular "D-style" connector, with 10 regular pins, and then 3 tiny tiny coax-style pins.
22:51:04 <elliott> because the i680 was codenamed N10.
22:51:05 <fizzie> http://en.wikipedia.org/wiki/DB13W3#mediaviewer/File:13W3_Stecker.jpg
22:51:08 <elliott> but now it's "New Technology".
22:51:21 <FireFly> elliott: ...what is the most obvious thing you've missed?
22:51:39 <elliott> FireFly: honestly, I've forgotten. but I remember the groans of others when I realised it.
22:51:45 <Vorpal> elliott, surly you could just put in a OS CD yeah?
22:51:55 <Vorpal> Technically bricked I guess
22:52:10 <elliott> maybe I only bricked one of them
22:52:25 <elliott> I managed to get linux-or-was-it-BSD to start to boot on one of them, but then it panicked, and that's it.
22:52:36 <elliott> Windows would be way cooler an achievement, though.
22:52:43 <Vorpal> I booted a live cd on my ibook once
22:52:55 <elliott> Vorpal: they were an old PowerMac and a G3 iMac, respectively
22:53:02 <elliott> the PowerMac was more of a fuss
22:53:11 <fizzie> I put a Debian on my Performa I-can't-remember-the-number.
22:53:13 <elliott> the G3, I just couldn't convince Open Firmware to boot from the CD for whatever reason.
22:53:20 <fizzie> It went in via the MkLinux route.
22:53:31 <Vorpal> elliott, First model ibook (G3) is the one I booted from a live cd
22:53:36 <elliott> fizzie: I think the one I had was a Performa or a Quadra, maybe.
22:53:42 <elliott> right, I tried MkLinux I think.
22:53:43 <Vorpal> Didn't ever go further, due to the 3.2 GB HDD
22:54:00 <Oren_> how many years from now will x86 lose its dominance in PCmarket?
22:54:07 <fizzie> MkLinux is that thing where you have a Mach microkernel, and run a Linux kernel as one of its tasks.
22:54:26 <fizzie> The kind of thing that causes people to make a "kernel on your kernel" jokes.
22:54:28 <b_jonas> Oren_: not very soon, I expect
22:54:54 <elliott> Oren_: more like how many years from now will the PC market dissolve
22:54:58 <Vorpal> FireFly, and 32 MB RAM
22:55:01 <elliott> ARM is the king of the mobile market
22:55:49 <Oren_> but the mobiles are getting bigger and you stick a keyboard onto the side and you have a laptop thingy
22:55:55 <fizzie> Possibly it was just the MkLinux bootloader or something.
22:56:06 <Oren_> I consider that to be a laptop
22:56:28 <elliott> you consider an iPad to be a laptop? ok.
22:56:31 <b_jonas> elliott: no way. there'll always be a PC market.
22:56:49 <b_jonas> if you came with C not being turing complete
22:56:51 <FireFly> I wish I still had the Compaq Armada
22:56:54 <elliott> b_jonas: sure, but it might be a mostly-irrelevant one.
22:56:57 <b_jonas> but still, it is here to stay for a long time
22:56:58 <Oren_> it is a mini laptop with no keyborad
22:57:02 <FireFly> I think I have an old Thinkpad somewhere around here
22:57:05 <elliott> it's already becoming that way for many people.
22:57:10 <Oren_> my laptop has a touchscreen
22:57:15 <Vorpal> FireFly, anyway I didn't want to remove MacOS, I wanted to dual boot
22:57:18 <elliott> our perspectives on this as nerds is hopelessly skewed and it's hopeless to generalise from that.
22:57:27 <Vorpal> FireFly, as in, classic Mac OS 9
22:57:30 <b_jonas> elliott: well, it might become smaller, but still
22:57:50 <FireFly> Oren_: my phone almost has a keyboard
22:57:51 <Vorpal> FireFly, now 3.2 GB is not very much any longer :P
22:58:42 <Oren_> my desktop machine has 3.2 gb of cache I think... something like that
23:00:03 <Oren_> nope off by an order of magnitude, butonly one
23:00:05 <Vorpal> I doubt that, that seems absurd
23:01:00 <Vorpal> Oren_, 3.2 MB seems reasonable, 32 MB seems very large too. But possible I guess. 320 MB I don't believe in
23:01:16 <Vorpal> What sort of beast computer is it
23:01:35 <b_jonas> Vorpal: it depends on which level of cache
23:01:46 <Vorpal> Oren_, so 3 orders of magnitude then?
23:01:57 <elliott> some core 2s had 32 mb I think
23:01:59 <fizzie> Vorpal: Depends on your base. :p
23:02:00 <Oren_> dammit i am bad at math
23:02:21 <Oren_> that's why i have computers to do it for me
23:02:21 <Vorpal> elliott, really? I know core 2 had large caches, but THAT large?
23:03:08 <Vorpal> model name: Intel(R) Core(TM)2 Duo CPU P8400 @ 2.26GHz
23:03:35 <fizzie> Vorpal: There's a thing on Haswell that there's a bit of DRAM that works as L4 cache both for the CPU and the GPU.
23:03:39 <Oren_> best recent processor from intel is Intel® Core™ i7-5960X Processor Extreme Edition (20M Cache, up to 3.50 GHz)
23:03:58 <fizzie> Vorpal: "GT3e [Iris Pro] version with 40 EUs and on-package 128 MB of embedded DRAM (eDRAM), called Crystalwell, is available only in mobile H-SKUs and desktop (BGA-only) R-SKUs. Effectively, this eDRAM is a Level 4 cache; it is shared dynamically between the on-die GPU and CPU, and serving as a victim cache to the CPU's Level 3 cache."
23:04:32 <elliott> okay, maybe 12 was the most. still.
23:04:41 <fizzie> It's kind of debatable if that counts.
23:04:57 <Vorpal> I have seen POWER CPUs though with 512 MB cache iirc
23:05:10 <fizzie> This regular desktop thing reports a cache size of 6 MB.
23:05:47 <fizzie> elliott: I think I mentioned that there's no Linux driver for the Indy's graphics option (XZ graphics)? IRIX would be the low-effort option. (If you can call it that.)
23:06:07 <Vorpal> model name: Intel(R) Core(TM) i5-2500 CPU @ 3.30GHz
23:06:17 <Vorpal> That is a Sandy Bridge
23:06:41 <Vorpal> And this might be off since it is in a Xen domU:
23:06:45 <Vorpal> model name: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
23:07:32 <fizzie> elliott: The SS5 has a Sun CG3 graphics card in it, I think, that's very supported. And something fancy in the networking department, I forget exactly what.
23:07:54 <elliott> fizzie: does NetBSD have a driver for the Indy's graphics? :p
23:08:21 <elliott> (does NetBSD have a driver for my toaster?)
23:08:28 <fizzie> elliott: I doubt that. It works with a serial console just fine, but that's perhaps kind of missing the point of a SGI box.
23:09:29 <fizzie> I wonder if I got somehow someone to send me one of Sun's quad Ethernet dealies.
23:09:55 <fizzie> Vorpal: "model name: Intel(R) Xeon(R) CPU E5-2695 v2 @ 2.40GHz" "cache size: 30720 KB"
23:10:24 <fizzie> (The front-end node of our cluster.)
23:10:46 <fizzie> It also has "address sizes: 46 bits physical, 48 bits virtual", which is the most physical bits I've seen so far, at least on Intels.
23:11:10 <Vorpal> fizzie, same on the domU I checked on
23:11:34 <fizzie> Well, same family, presumably, based on the model numbers. (E5-2xxxx)
23:12:30 <Vorpal> address sizes: 36 bits physical, 48 bits virtual is the core i5 above
23:12:38 <elliott> fizzie: 32 TB of RAM sounds pretty doable
23:12:42 <elliott> I guess you'd be limited by slots.
23:12:54 <elliott> do servers with hundreds of gigs of RAM just have ten billion RAM slots?
23:13:17 <Vorpal> elliott, you can get 8 GB modules easily these days, maybe larger
23:13:20 <fizzie> elliott: The cluster's got some (2?) nodes with 1 TB of RAM, but that's it.
23:13:31 <Vorpal> You can get 8 GB laptop modules even
23:13:52 <fizzie> 1024/8 is still 128, though.
23:14:17 -!- Oren_ has quit (Ping timeout: 246 seconds).
23:14:26 <fizzie> I think the particular server model goes up to 2TB in the configu-o-tron.
23:15:00 <fizzie> http://www8.hp.com/us/en/products/proliant-servers/product-detail.html?oid=4142916
23:15:19 <Vorpal> So presumably there are more than 8 GB modules?
23:15:19 <fizzie> "Memory, maximum: 2TB" "Memory slots: 64 DIMM slots"
23:15:28 <Vorpal> So 16 GB per module then
23:15:52 <fizzie> (For the 2 TB option; they might well be using those even if you order it only half-full.)
23:16:36 <fizzie> 32 GB DIMM sounds somehow familiar.
23:22:41 <fizzie> The front-end node also seems to have a load average of 17.06, with one MATLAB running at 100% CPU, and exactly 16 cryptically named processes running at 25% CPU. I think someone's running their actual jobs accidentally on the front-end again.
23:22:57 <fizzie> "We ask you to refrain from running multi-GB, many-core applications of the frontend."
23:29:58 -!- zzo38 has joined.
23:31:50 -!- Dulnes has joined.
23:33:16 <Dulnes> Wat oh ive set it to disconnect
23:42:09 -!- dts has quit (Ping timeout: 264 seconds).
23:44:18 -!- Frooxius has quit (Quit: *bubbles away*).
23:46:45 -!- dts has joined.
23:48:29 -!- copumpkin has joined.
23:49:49 <copumpkin> hi, sorry about yesterday, I won't stay long
23:50:31 -!- Frooxius has joined.
23:51:21 -!- nooga has quit (Ping timeout: 256 seconds).
23:58:34 -!- copumpkin has quit (Ping timeout: 240 seconds).
00:04:23 -!- nys has joined.
00:06:38 -!- tlewkow has quit (Remote host closed the connection).
00:11:04 -!- Oren has joined.
00:59:38 -!- Oren has quit (Ping timeout: 246 seconds).
01:02:30 -!- adu has joined.
01:02:40 <Bicyclidine> http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2014/n4210.pdf -trigraphs
01:06:17 <elliott> A major motivation at the time trigraphs were added was to support people with keyboards that lack
01:06:20 <elliott> these characters and we believe this continues today.
01:06:25 -!- adu has quit (Client Quit).
01:08:40 <Bicyclidine> 2017, it's a standard named 2017 and they're concerned with keyboards lacking square brackets
01:09:04 <nys> supportin the budget customers
01:10:08 <elliott> hopefully C++ will add support for writing numbers like int x = ??twentythree; to accomodate users like me when my number keys broke
01:10:28 <ion> elliott: Why not simply use voice input?
01:10:33 <elliott> #define MAX_SIZE ??sixtyfivethousandfivehundredandfiftysix
01:12:15 <ion> Pink XD quotes 23 semicolon
01:13:11 <FireFly> EBCDIC is still important?
01:14:11 <shachaf> C++ already supports user-defined literals
01:14:17 <ion> I thought “it would be hilarious if there’s a variant of UTF-8 based on EBCDIC” and googled. http://en.wikipedia.org/wiki/UTF-EBCDIC
01:15:20 <elliott> ion: didn't you see "non-EBCDIC Unicode" in the pdf?
01:15:31 <elliott> a terrifying phrase by what it implies the existence of
01:16:40 <shachaf> I think zzo38 or someone has discussed UTF-EBCDIC in here before.
01:17:05 <Bicyclidine> now i have to check for unicode encodings based on other obscure encodings of the 1890s
01:17:38 <zzo38> There is 9-bit and 18-bit Unicode variants too
01:17:55 <Bicyclidine> gb18030 is an ascii superset. boooooriiiiiiing
01:18:03 <ion> Great Britain 18030
01:18:14 <Sgeo> "There are real customers who use EBCDIC. "
01:18:38 <zzo38> UTF-9 is really VLQ but with 9-bits in one byte so 8 data bits and 1 continuation bit.
01:18:39 <FireFly> zzo38: those were Aprils' fools specs, though
01:18:58 <Bicyclidine> i suppose this implies someone's actually using c1
01:19:14 <Sgeo> UTF-1 is best UTF
01:19:26 <Bicyclidine> single byte encodings that are like ESC FUCK or whatever in ascii
01:19:28 <zzo38> C0 control characters are more commonly used I think
01:19:40 <Sgeo> ...where did the name UTF-1 come from?
01:19:57 <ion> “We’re number 1!”
01:20:01 <viznut_> when i was thinking about what a soviet ternary homecomputer might be like, i found myself designing a balanced ternary version of the soviet gost character set
01:20:41 <zzo38> viznut_: Do you have a posted of such a thing?
01:21:05 <viznut_> i didn't publish anything about that project
01:21:08 <Bicyclidine> still disappointed i can't find a copy of that book on soviet space computers
01:21:41 <FireFly> I've heard of a channel on Freenode about ternary computers
01:21:44 <zzo38> Unicode is bad in general, although if you are using it then UTF-8 is best as it is compatible both with programs that use Unicode as well as programs that do not use Unicode and allows many things still working even in programs that do not use Unicode.
01:22:13 <Bicyclidine> i wonder if i still have the book mark even
01:22:22 <Bicyclidine> had an ISBN high code of like 13 or some shit
01:46:49 -!- adu has joined.
01:47:07 <Dulnes> "never odd or even" spelled backwards is never.odd or even
01:47:56 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:48:27 -!- Phantom_Hoover has joined.
01:50:31 -!- Oren has joined.
01:58:36 <Oren> language defined by reference interpreter or compiler. pro? con?
01:59:04 <elliott> pro: turing complete parsing
01:59:07 <elliott> con: turing complete parsing
01:59:40 <nys> fuk the chomskiarchy
01:59:49 <nys> smash the chomskiarchy
01:59:59 <Oren> what is chomkiarchy
02:00:13 <Oren> I'm not a politician
02:03:23 <Oren> after googling, i guess it's a pun on 'patriarchy' and the chomsky hierarchy?
02:03:56 <Oren> holy crap noam chomsky is still alive
02:04:07 <Oren> how is he still alive?
02:05:18 <zzo38> Well, I suppose if he didn't get dead yet, then, he can still be alive.
02:05:20 <lambdabot> http://en.wikipedia.org/wiki/Noam_Chomsky
02:05:20 <lambdabot> Title: Noam Chomsky - Wikipedia, the free encyclopedia
02:05:35 <zzo38> He is almost 86 years old from Wikipedia
02:06:04 <Oren> wow. he's 17 years older than my grandpa
02:06:25 <Oren> only my greatgranduncle is that old
02:06:45 <Bicyclidine> maybe it's because i have centenarians in the family
02:07:59 <Oren> my family has people who died at 98 on one side, and 23 on the other
02:10:06 <Oren> so i'm 0.4 obamas old?
02:11:38 -!- GeekDude has quit (Read error: Connection reset by peer).
02:14:06 <Oren> did you guys have a good knee-high socks day?
02:15:22 <elliott> yes but I didn't wear any knee-high socks
02:17:50 <Bicyclidine> was that today? mainly i just vomited, is that moe
02:19:26 <Oren> according to some poeple in japan it is
02:19:50 <Oren> moemoe stomach-acid
02:21:51 <Oren> sno't worry i'm toning it down, I'm at school right now
02:22:13 <elliott> don't worry, I love this channel's ever-advancing downward spiral
02:26:07 -!- tlewkow has joined.
02:30:01 -!- tlewkow_ has joined.
02:33:34 -!- tlewkow has quit (Ping timeout: 258 seconds).
02:35:17 <Oren> aww ipv6 wnt away
02:50:23 -!- hjulle has quit (Ping timeout: 255 seconds).
02:53:54 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41233&oldid=41231 * SuperJedi224 * (+291)
02:57:50 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41234&oldid=41233 * SuperJedi224 * (+92)
02:59:59 -!- lollo64it has joined.
03:00:54 -!- Lorenzo64 has quit (Ping timeout: 245 seconds).
03:08:16 <HackEgo> [wiki] [[Talk:GridScript]] http://esolangs.org/w/index.php?diff=41235&oldid=41207 * Orenwatson * (+158)
03:13:06 -!- Phantom_Hoover has quit (Remote host closed the connection).
03:15:00 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41236&oldid=41234 * SuperJedi224 * (+909)
03:16:05 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41237&oldid=41236 * SuperJedi224 * (-30)
03:17:21 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41238&oldid=41237 * SuperJedi224 * (+195) /* Basic Program Format */
03:21:33 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
03:41:30 <Oren> most common labels in my C programs: heaven: and hell:
03:50:38 <zzo38> I don't use same label names so much all the time
03:54:34 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41239&oldid=41238 * SuperJedi224 * (+1249)
03:54:53 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41240&oldid=41239 * SuperJedi224 * (+0) /* SWITCH RANDOM|value|!value|=value|!=value */
03:56:03 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41241&oldid=41240 * SuperJedi224 * (-10) /* Some Commands */
03:59:26 -!- adu has quit (Quit: adu).
04:04:39 -!- Dulnes has quit (Quit: Connection closed for inactivity).
04:27:20 -!- GeekDude has joined.
04:33:56 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:52:44 -!- cluid has joined.
04:57:13 <Oren> goto heaven; goto hell; goto valhalla;
04:58:08 <Taneb> :( I have had a really bad night's sleep
04:59:43 -!- nys has quit (Quit: quit).
05:04:40 <cluid> I think Return Oriented Programming is an esolang
05:05:02 <int-e> nah, too useful ;-)
05:05:58 <Taneb> What is return oriented programming?
05:06:28 <int-e> a technique for exploiting buffer overflows on the stack that works with non-executable stacks
05:06:39 <cluid> Taneb, basically you scrape together a programming language out of the suffixes of compiled function bodies
05:06:51 <int-e> the idea is to put a sequence of return addresses on the stack, all poiting near the end of library functions
05:07:07 <int-e> such that when those are executed, something useful (to the attacker) happens.
05:10:09 <int-e> the feeling is certainly similar to that of some esolangs. "Oh, here I can set register x to a value on the stack", up to "here I can write a byte in register foo to the address r+42 where r is another register"; usually the operations have side effects (like setting register y would read some memory and destroy register z)
05:10:31 <int-e> (third hand experience, I've read a paper on ROP once or twice)
05:11:08 <cluid> the reason ROP is effective is the same reaosn most turing tarpits are TC
05:11:46 <cluid> I would like to add ROP to the wiki because it is a cool esolang but it also arose naturally unlike most constructed esolangs
05:12:10 <Oren> is there such thing as a "natural programming language"?
05:12:17 <int-e> of course it's a whole class of programming languages.
05:12:37 <Oren> how are they natural?
05:12:58 <cluid> well Chuck Moore says forth was discovered, not invented
05:12:59 <int-e> (Different programs, different library versions, different platforms, all lead to different flavours of ROP.)
05:13:05 <cluid> and I feel that too
05:13:19 <cluid> and Wadler said the the only thing we will definitely have in common with aliens is lambda calculus
05:13:27 <int-e> Oren: they evolved rather than being conceived through intelligent (or less...) design.
05:14:02 <Oren> oh I see, ROP is a natural language becuae the people who wrote the code that enables it did not intend to do so.
05:14:24 <int-e> (Speaking of ROP. I don't agree that Forth falls inside that category.)
05:14:25 <cluid> yeah it's like how bugs come live in dark spaces
05:14:32 <Oren> the interpreter is not by design it is accidental
05:15:50 <int-e> it's funny. by that definition, "natural languages" aren't.
05:16:03 -!- oerjan has joined.
05:16:22 <zzo38> Is "natural number" a natural language then? I don't quite know that either?
05:16:54 <Oren> well, no-one intended to screw up norman french and anglo-saxon to make english it just happened while they were getting on with their lieves
05:17:15 <lambdabot> mroman said 14h 47m 9s ago: It's not my website
05:17:31 <oerjan> wow mroman is actually offline
05:17:32 <Taneb> Does anyone know a nice implementation of ColorForth I can use?
05:18:36 <oerjan> @tell mroman i used the word in the en:you = de:man sense
05:20:19 <cluid> so I think this could be nice but i gues its a bit subjective
05:20:47 <int-e> Hmm I wonder whether fizzie and I use the same encoding for Dominosa ...
05:21:09 <int-e> I guess it' boils down to "trits or bits?"
05:27:04 -!- Dulnes has joined.
05:31:34 <Dulnes> How do you... Make your own language And get people to use it > _ >
05:31:44 <cluid> you cna't get people to use it
05:32:02 <Dulnes> Also why are all my msgs faded
05:32:21 <Oren> wipe your screen
05:32:33 <Oren> with a cloth soaked in vodka
05:33:03 <Dulnes> Oren what is knee high socks day¿ is that a joke
05:33:13 <cluid> oerjan, I asked about ROP here a moment ago, do you have an comments
05:33:30 <Oren> knee high socks day is november 28
05:33:41 <Oren> on japanese twitter
05:33:54 <oerjan> cluid: no, since the logs for yesterday are long as sin
05:34:18 <Dulnes> Verbose fuck is a very "extensive" alter for bf
05:34:27 <Oren> 11 = ii = good 28 = nihachi which sounds like knee high
05:34:31 <cluid> I want to add it to the wiki
05:34:36 <cluid> i dont know if it will be accepted
05:35:23 <zzo38> I am not sure about "the only thing we will definitely have in common with aliens is lambda calculus". Who is this Wadler anyways?
05:35:35 <oerjan> cluid: we don't precisely reject a lot
05:35:38 <Oren> soo 11/28 = good knee highs day
05:35:44 <cluid> zzo38, he researches in functional languages
05:35:55 <cluid> oerjan, ok but is this good?
05:36:00 <cluid> or should i not bother
05:36:13 <Oren> to get people to use your language you need to make a cool thing where the interface is your langiuage
05:36:25 <oerjan> i don't know, i'm telling you the logs are long as sin which means you _might_ ask me again in five hours or so.
05:36:32 <Oren> like C got popular becuase of Unix
05:36:40 <cluid> i dont really understand that
05:36:59 <cluid> would you liketo rad the previous conversation? it is 20 lines or so I can paste it somewhere
05:37:04 <elliott> oerjan: don't worry, it's mostly me and fizzie trying to use speech recognition
05:37:19 -!- lollo64it has quit (Quit: Leaving).
05:38:34 <zzo38> Dulnes: Ideas of what?
05:39:17 <Oren> also today 11:29 is meat day
05:39:22 <oerjan> zzo38: wadler is one of the main haskell designers, but i don't think he's been that active in the community for at least a decade. as an FP researcher he _would_ be biased on the universality of lambda calculus, i guess.
05:39:22 <zzo38> Don't you know esolang wiki includes a list of ideas?
05:39:59 <oerjan> zzo38: also, this gives me the idea of intelligent aliens without any concept of naming, which sounds scary somehow
05:40:11 <oerjan> if it is possible at all
05:40:18 -!- int-e has quit (Quit: leaving).
05:40:59 <Oren> 29 = ni kuu = niku = meat
05:41:09 <Oren> so today is meat day
05:41:32 <elliott> there are 365 days in the year Dulnes
05:41:32 <Oren> because we like to partay
05:41:40 -!- int-e has joined.
05:41:42 <cluid> i just want some advice on contributing to the wiki
05:42:03 <elliott> a rop article would be nice
05:42:05 <Oren> eat a hamburger it's meat day
05:42:22 <Oren> a rop article would be nice
05:42:59 <elliott> are you repeating things I Say
05:44:02 <Oren> * is not recognized as an internal or external command
05:44:13 <zzo38> oerjan: Maybe it is possible I don't know, but I would think intelligent alien monsters must study some mathematics, although it might not resemble our own mathematics unless you look really closely (which may be difficult I don't know), and may be considered as a different order; concept of natural numbers would probably be had due to its usefulness in mathematics although maybe it wouldn't be called "natural". So, possibly the mathematics of lamb
05:44:33 <zzo38> It doesn't, however, mean it has exactly the same use of programmers you know!
05:45:51 <oerjan> you got cut off after "the mathematics of lamb"
05:45:54 <cluid> therer are lots of different weird models of natural numbers
05:46:03 <Dulnes> Make a bot in malbolge
05:46:12 -!- password2 has joined.
05:46:32 <zzo38> So, possibly the mathematics of lambda calculus may be studied too, by some degree.
05:46:57 <oerjan> perhaps the aliens naturally think in grothendieck-like levels of abstraction and have trouble getting to something as concrete as numbers
05:47:36 <oerjan> maybe they use computers for concretion instead of abstraction
05:47:51 <zzo38> oerjan: I do suggest that is possible, but it doesn't mean numbers won't exist.
05:48:35 <oerjan> Dulnes: at least that might be _possible_.
05:48:39 <Dulnes> They think with high number equations that humans will never use
05:48:47 <elliott> well, they have to have invented spaceships.
05:49:14 <shachaf> oerjan: there was a story vaguely like that
05:49:19 <Dulnes> Mmmm i like malbolge its very [abstract] than others
05:49:40 <oerjan> Dulnes: i'm pretty sure abstract is _not_ the word you want
05:49:55 <zzo38> It that why it is in brackets?
05:49:59 <shachaf> oerjan: i think it was http://www.negrophonic.com/pdfs/ted_chiang_-_story_of_your_life.pdf
05:51:45 <oerjan> elliott: maybe they invented incremental garbage collection in the type system and the spaceships were just an accidental side effect hth
05:52:56 <oerjan> Dulnes: i think it's pretty much overall designed to fit the word "hellish" in there
05:56:16 <Dulnes> So oerjan i got that video
05:57:31 -!- Oren has quit (Quit: Page closed).
05:58:23 <Dulnes> But what would the bot do and how would that be possible oerjan
06:02:43 <oerjan> i don't know about any video.
06:03:13 <oerjan> the bot would be able to do some simple reponses that don't require much memory.
06:03:55 <oerjan> malbolge has a strictly limited memory and it takes a lot of cleverness just not to waste a lot of it
06:04:12 * Dulnes Completely ignores that idea and makes the biggest sloppiest bulk bot in malbolge
06:04:24 <Taneb> I now about a video
06:04:39 <oerjan> also, i don't actually know how to concretely program in malbolge
06:05:55 <Dulnes> Look woman i just wanna work on something very hard and i need a crap language no one uses to do it
06:06:10 <oerjan> hm perhaps what you could do is to implement something compact like forth in it.
06:06:23 <elliott> I'm curious as to how this assumption of oerjan's gender came about :p
06:06:47 <Dulnes> No one knows eachothers genders
06:07:01 <Dulnes> Pretty sure elliott is a girl
06:07:04 <oerjan> some of us may have revealed them.
06:07:21 <elliott> oerjan is definitely a girl
06:07:34 * oerjan swats elliott -----###
06:08:08 <Bicyclidine> do you have some kind of problem with oyrur femininity, oerjan
06:08:26 <oerjan> not as much as with your spelling.
06:08:39 <zzo38> Dulnes: I don't know about nobody uses it, unless it is unimplemented; however there are some that only one or two people use
06:09:56 <Dulnes> Whatever ill try what oerjan said and compact fourth
06:10:25 <oerjan> i think if you could write a program in malbolge that implemented a simple forth interpreter and managed to compress what's in the rest of memory into its initial data then the rest would be somewhat easy
06:11:45 <Dulnes> Wasted 3 years in learning malbolge i guess i can put this to use
06:12:05 <Dulnes> But ill do this tommorow im gonna watch a movie
06:14:46 * Sgeo wonders if anyone developed a protocol that would make sense for the Discworld Clacks
06:14:54 <Sgeo> Preferably including replicating defects
06:18:44 <Bicyclidine> http://en.wikipedia.org/wiki/Semaphore_line i mean
06:20:02 -!- shikhin has joined.
06:20:06 <oerjan> Bicyclidine: it's like Ook! just more compact hth
06:20:11 <Sgeo> I didn't think they existed in reality
06:20:22 <Sgeo> Although I also don't think any real system likely had protocols for sending images
06:20:36 -!- Oren has joined.
06:21:01 <oerjan> Sgeo: wait there's an old obsolete technology which you _don't_ know about?
06:21:15 <int-e> Sgeo: Then you're reading Pratchett wrong. Almost all technology that exists on Discworld also exists on Earth; it just tends to work in slightly different ways.
06:21:44 <Bicyclidine> well, i was briefly a voy scout. they still teach flag semaphore.
06:22:05 <Sgeo> int-e: I thought it was a mashup of telegram and TCP/IP
06:22:08 <Bicyclidine> but no, i don't think images were ever sent over optical telegraph.
06:22:27 <Bicyclidine> optical telegraph is a pretty obvious solution imo. i mean presumably you've heard of signal fires and lights.
06:22:59 <int-e> Sgeo: Oh, I thought the thing with putting gargoyles on the clacks was somewhat like the step towards directed radio transmission.
06:23:01 <Bicyclidine> oh, there are even older ones http://en.wikipedia.org/wiki/Hydraulic_telegraph
06:23:10 <Bicyclidine> now this one i hadn't heard of, but is again obvious
06:23:10 <Sgeo> int-e: I haven't read/don't remember that.
06:23:43 * Sgeo just watched Going Postal. Read the book but that was years ago
06:23:52 <oerjan> i recall that story about one of the first times they sent images from a phone booth and it got ruined because the phone operator couldn't grasp the concept that they _really_ didn't want her to interrupt to tell they needed to put on more coins
06:24:44 <Bicyclidine> apparently telegraphy was one of the first uses of electromagnetic induction, which i think is neat
06:25:03 <Bicyclidine> like, they tested to see if it would work before they worked out the physical laws
06:25:23 <cluid> There is a very powerful concise string rewriting language
06:25:59 <cluid> first you define syntax like this: <S> ::= 00 | 01 | 1 <S> <S>
06:26:17 <int-e> Sgeo: I don't know which book, but at some point they transmit pictures over the clacks, which requires rather high data rates.
06:26:22 <cluid> then you define rewrite laws like this: 1100 S:x S:y --> x, 11101 S:x S:y S:z --> 11xz1yz
06:26:35 <cluid> ths implements BCL for example, but you could implement other things
06:26:38 -!- Tod-Autojoined has joined.
06:26:52 <Sgeo> Probably Monstrous Regiment. Also occurs in Going Postal but as more of a side note. At least in the TV adoptation
06:27:09 <Bicyclidine> i don't remember clacks even existing in monstrous regiment
06:27:12 <Sgeo> They didn't show the vampire turning to dust in the TV adoption of Going Postal
06:27:15 <Taneb> They definitely did
06:27:26 -!- Patashu has quit (Disconnected by services).
06:27:26 -!- Patashu_ has joined.
06:27:31 <Taneb> And The Truth, a little
06:27:31 <Bicyclidine> i haven't read a discworld book since highschool, ha ha
06:27:38 <Oren> it was going postal
06:27:43 <Oren> they had a race
06:27:59 <Oren> mail and clacks who sends the book first
06:28:39 <Oren> I have read every book Sir T.P. has ever published
06:29:21 -!- password2 has quit (Ping timeout: 244 seconds).
06:29:37 <Oren> anyway the mail dude gave the part of the book with all the pictures so the clacks dudes
06:29:47 <Oren> would have to take time to encode it
06:30:27 <zzo38> Can the initial contents of the inventory be changed without using scripts?
06:30:36 -!- zzo38 has quit (Remote host closed the connection).
06:31:05 -!- jix_ has joined.
06:31:38 -!- zzo38 has joined.
06:31:46 -!- dianne_ has joined.
06:37:51 -!- MDude has joined.
06:37:54 -!- TodPunk has quit (*.net *.split).
06:37:55 -!- applybot has quit (*.net *.split).
06:37:55 -!- jix has quit (*.net *.split).
06:37:55 -!- dianne has quit (*.net *.split).
06:39:34 -!- applybot has joined.
06:45:23 -!- password2 has joined.
06:46:28 <Sgeo> There's no adaptation of Making Money :(
06:46:32 <Sgeo> And I haven't read it yet either
06:50:11 -!- Tod-Autojoined has changed nick to TodPunk.
06:51:28 <coppro> there's a hilarious bit about economic modeling
06:51:41 <Taneb> I'm gonna feel like crap today, I've had next to no sleep :(
06:55:57 <int-e> why don't you go back to bed?
06:56:07 <Taneb> I'm wide awake now
06:56:17 <int-e> (I believe it's Saturday so it might be an option)
06:59:18 <Taneb> I could just go back to bed
07:06:20 -!- tlewkow_ has quit (Remote host closed the connection).
07:06:53 <MDude> But then how will you make a language based on the power of sleep deprivation?
07:14:51 <J_Arcane> this is a man who takes his keyboarding seriously ... http://mykeyboard.co.uk/
07:16:07 <cluid> esolang wiki is down?
07:16:31 <lambdabot> echo; msg:IrcMessage {ircMsgServer = "freenode", ircMsgLBName = "lambdabot", ircMsgPrefix = "oerjan!oerjan@sprocket.nvg.ntnu.no", ircMsgCommand = "PRIVMSG", ircMsgParams = ["#esoteric",":@echo hi"]} target:#esoteric rest:"hi"
07:16:57 -!- password2 has quit (Read error: Connection reset by peer).
07:16:58 <Taneb> (it is all on Gregor's server, right?)
07:17:17 <oerjan> yes, but Gregor has a tendency to be absent for long stretches of time
07:17:25 <oerjan> especially on weekends, i think
07:17:43 <oerjan> oh it's just extremely slow
07:17:45 -!- tlewkow_ has joined.
07:18:13 <Taneb> Ah, esolangs seems to be slooooooooooow but not dead too
07:20:09 <oerjan> <elliott> someone poke me in an hour <-- did anyone remember?
07:20:31 <Taneb> Remember? I didn't even notice
07:20:37 <elliott> I remembered because I'm smart and competent
07:20:38 <Taneb> When did elliott say that
07:20:48 <Taneb> elliott, when did you say that?
07:20:55 <oerjan> elliott: i notice *pumpkin isn't here though
07:21:11 <oerjan> also, he should totally add bipumpkin
07:21:58 <oerjan> ok not on the network at all
07:22:55 -!- tlewkow_ has quit (Ping timeout: 272 seconds).
07:23:17 <oerjan> far more than an hour ago
07:23:57 <Taneb> OK, then, I was probably doing something else
07:24:48 <oerjan> well you weren't speaking around that time, anyway
07:25:23 <Taneb> Sometimes I am here but do not speak, normally because I haven't got anything to say
07:25:30 <Taneb> But sometimes because I have no idea what's going on
07:25:51 <Taneb> And sometimes because I'm busy in another channel which is attracting all of my attention
07:27:00 <Sgeo> 'The Sorting Engine, designed by "Bloody Stupid" Johnson to have a wheel with a pi equal to exactly three, which bends reality to the point that it occasionally puts out letters from the past, the future, or even from alternate realities (ones where the check really was in the post, for example).'
07:27:06 <Sgeo> Now I'm sad that wasn't in the adoption
07:27:52 <oerjan> you can't animate pi=3 physical fact
07:29:07 <J_Arcane> Researching keyboards, I think I realized just now that I've been mis remembering how the IBM keyboards worked.
07:30:25 <Taneb> I am going to go back to bed now
07:31:23 <Sgeo> I barely remember the book
07:31:52 <Sgeo> I did remember the jamming of the clacks and was waiting for that while watching, but I don't know if I remember that fromt the books or from reading about the books
07:33:14 -!- password2 has joined.
07:34:11 -!- shikhout has joined.
07:34:37 <Sgeo> Someone please ping me if there's a Thief of Time adoptation, I loved the book in high school and gave it to a teacher to read
07:34:54 <Sgeo> When running to school sometimes I would think to myself 'HERE COMES THE CLOCK'
07:35:41 <J_Arcane> IBM buckling spring keyboards don't necessarily have more travel than, say, Cherry switches, it's that they don't bottom out the same: the mechanism stops before the key hits flat with the base, but rather stops against the frame of the switch.
07:36:54 -!- shikhin has quit (Ping timeout: 240 seconds).
07:40:59 <oerjan> heh hendrik's and henkma's A057755 solutions are literally identical (and expectedly very close to mine)
07:41:34 -!- shikhout has changed nick to shikhin.
07:41:55 -!- dts has quit (Ping timeout: 272 seconds).
07:42:29 -!- tlewkow has joined.
07:45:09 <oerjan> @tell int-e darn if i had knew my 1+2^n`div`54426 was so close to working...
07:46:59 -!- tlewkow has quit (Ping timeout: 272 seconds).
07:56:49 -!- MDude has changed nick to MDream.
08:01:03 * oerjan has arrived at the point in the logs where fizzie and fungot get indistinguishible
08:01:03 <fungot> oerjan: the one that symbolizes our family: each saves a million right words to you, you'd become instantly paralyzed with a life-shattering fear, for many people!
08:01:30 <oerjan> fungot: how apocalyptic of you
08:01:30 <fungot> oerjan: that you all for them, i have come up with a new saddest thing ever!!... which is also nice, until a really attractive friend of theirs shows, interviews, documentaries about me, make new friends, and start a life of lies?
08:01:40 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz* sms speeches ss wp youtube
08:05:08 * Sgeo vaguely recalls disliking The Colour of Magic but liking The Light Fantastic. I think The Light Fantastic was the first Discworld book I read. Sadly, The Colour of Magic has an adoptation while The Light Fantastic doens't seem to
08:07:18 <J_Arcane> Also, I had no idea that you could only get n-key rollover on a PS/2 keyboard. I wonder why that is?
08:12:36 <Jafet> The USB HID protocol involves sending the full keypress state of the keyboard
08:14:22 <oerjan> Sgeo: cluid is a bit slow hth
08:14:52 <int-e> J_Arcane: it's easier to connect keys in some sort of grid than to have a wire (plus ground) to each individual key
08:15:28 <oerjan> the 5 hours is probably going to be a gross underestimate today
08:15:42 <J_Arcane> int-e: Yeah, but what I found odd is that some keyboards have n-key but only if you use the PS2 connector.
08:16:18 <J_Arcane> It seems to specifically a limitation in the connector protocol, as Jafet says.
08:16:39 <int-e> Hmm. I dunno. I thought in those old protocols keyboards would just send differential "this key was pressed" and "this key was released" messages.
08:16:50 <Sgeo> There's a _THIRD_ Moist von Lipwig book?
08:17:38 <int-e> And by "thought" it means I made this assumption based on the AT keyboard controller's programming interface.
08:18:22 <int-e> Sgeo: yes. Going Postal, Making Money, and Raising Taxes.
08:18:41 <Sgeo> Raising Steam, I thought?
08:18:52 <int-e> (the ... was for typo-ing "I" as "it")
08:19:36 <int-e> Haha. There's some foreshadowing on taxes at the end of that book, isn't there...
08:21:06 <J_Arcane> Anyway, my wife balked at me spending €135 on a keyboard, so instead I'm just going to try a Durandal; just can't decide which switches I want. Leaning towards the Blues and getting some o-rings to put on it.
08:27:18 <zzo38> Do you know the Famicom keyboard protocol? It allows you to push all the keys since it just reads a bit for each key pushed or not.
08:29:12 <int-e> J_Arcane: after a bit of research, what one gets from the controller is also what happens on the wire, so from the PS2 protocol perspective there is no reason for this limitation. In fact http://blog.controlspace.org/2010/08/n-key-rollover-what-it-is-and-how-to.html says that USB limits rollover but PS2 doesn't.
08:29:33 -!- password2 has quit (Ping timeout: 264 seconds).
08:29:58 <oerjan> @tell Vorpal <Vorpal> Is there a way to say to cabal "fix mixed versions"? I.e rebuild any packages depending on different versions of a package so that everything just works, and I don't get weird errors. <-- apart from the sandbox thing, i vaguely think that if you install all the packages as _one_ cabal install command it will seek versions that work with all simultaneously
08:30:18 <int-e> J_Arcane: I think I interpreted your statement wrong, because I'd never heard of n-key-rollover. My bad.
08:31:18 -!- tlewkow has joined.
08:31:32 <int-e> ("n" is not meant as a limitation to some particular n, but means "unbounded".)
08:33:32 <J_Arcane> int-e: Yeah. N-key (as opposed to 3-key, 6-key etc.) means you can hit all the keys at once; each are detected individually. Most membrane keys are only 3-key.
08:34:38 -!- Dulnes has quit (Quit: Connection closed for inactivity).
08:35:55 <int-e> why would anyone type with both shift keys pressed...
08:36:00 <J_Arcane> USB is apparently limited to 6-key + 4 mod-keys.
08:36:09 -!- tlewkow has quit (Remote host closed the connection).
08:36:50 <int-e> HE QUIK BROWN FO JUPS OER HE LA DOG <-- I wonder whether one could recognize keyboard models that way
08:37:09 <J_Arcane> int-e: I've had problems in the past with things like Emacs or IDE shortcuts based on symbols, because I have a Finnish keyboard, and AltGr is a pain in the arse.
08:39:23 <int-e> > map head.group.sort$"HE QUIK BROWN FO JUPS OER HE LA DOG"
08:41:19 -!- dts has joined.
08:42:39 <int-e> I don't think this has been much of an issue for me ever since I stopped playing Bomberman against others.
08:43:17 <J_Arcane> I get: H UCK BON FOX JUMPD OV H LAZY DOG
08:44:04 <elliott> huck on fox jumpd ov h lazy dog
08:44:55 -!- InvalidCo has quit (Ping timeout: 250 seconds).
08:46:49 <J_Arcane> Other nice perk of getting a Cherry MX based board: stuff like this: http://keypuller.com/dsa-retro/
09:09:39 -!- Oren has quit (Ping timeout: 246 seconds).
09:15:34 -!- cluid has quit (Quit: Leaving).
09:34:16 -!- weissschloss has quit (Remote host closed the connection).
09:39:28 -!- weissschloss has joined.
10:07:19 -!- nooga has joined.
10:25:16 <oerjan> <fizzie> There was an attempt to add some flags that disable nested functions, but that ran into some other issue that I forget. <-- well the first issue is that gcc simply doesn't _have_ a flag to turn it off.
10:25:33 <oerjan> i think there was talk about other hacks to achieve it, though.
10:25:56 <oerjan> that is, it doesn't have a flag to turn off that specifically.
10:46:04 -!- oerjan has quit (Quit: leaving).
10:57:19 -!- InvalidCo has joined.
11:04:17 -!- password2 has joined.
11:07:27 -!- password2 has quit (Read error: Connection reset by peer).
11:08:33 -!- dts has quit (Ping timeout: 255 seconds).
11:25:06 -!- password2 has joined.
11:38:54 -!- augur has quit (Remote host closed the connection).
11:39:38 -!- augur has joined.
11:39:51 -!- augur has quit (Remote host closed the connection).
11:40:06 -!- augur has joined.
11:56:19 -!- Patashu_ has quit (Ping timeout: 264 seconds).
12:14:39 -!- password2 has quit (Read error: Connection reset by peer).
12:27:00 -!- password2 has joined.
12:45:09 -!- password2 has quit (Ping timeout: 252 seconds).
12:57:27 -!- password2 has joined.
13:10:07 -!- Oren has joined.
13:12:30 -!- password2 has quit (Read error: Connection reset by peer).
13:19:06 -!- S1 has joined.
13:24:20 -!- drdanmaku has joined.
13:31:39 <int-e> Wait, irssi has an UPGRADE command? Why didn't I try that...
13:34:03 -!- shikhout has joined.
13:37:35 -!- shikhin has quit (Ping timeout: 265 seconds).
13:47:10 -!- password2 has joined.
13:55:23 -!- CADD has joined.
14:04:12 -!- password2 has quit (Ping timeout: 256 seconds).
14:08:00 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41242&oldid=41241 * SuperJedi224 * (+401) /* Some Commands */
14:15:16 <J_Arcane> Just ordered this: http://www.jimms.fi/tuote/01G1XX1NOBK
14:15:44 -!- password2 has joined.
14:16:22 -!- password2 has quit (Max SendQ exceeded).
14:17:00 -!- password2 has joined.
14:42:55 -!- password2 has quit (Ping timeout: 240 seconds).
14:54:18 -!- int-e has quit (Remote host closed the connection).
14:54:43 -!- int-e has joined.
14:58:09 -!- password2 has joined.
14:58:46 -!- password2 has quit (Max SendQ exceeded).
15:00:34 -!- password2 has joined.
15:06:51 -!- S1 has quit (Quit: S1).
15:09:28 -!- password2 has quit (Read error: Connection reset by peer).
15:26:07 -!- password2 has joined.
15:29:59 -!- tlewkow has joined.
15:57:09 -!- GeekDude has joined.
15:59:18 -!- tlewkow has quit (Remote host closed the connection).
16:21:50 -!- MDream has changed nick to MDude.
16:27:20 -!- password2 has quit (Read error: Connection reset by peer).
16:30:29 -!- shikhout has changed nick to shikhin.
16:35:23 -!- Bicyclidine has quit (Ping timeout: 258 seconds).
16:48:06 -!- tlewkow has joined.
16:56:43 <fizzie> Last I looked, those were a lot simpler than the MIT Mystery Hunt one, though I think they only had categories up to "Double Cross" then.
17:19:30 <int-e> userreport.com ... really?!
17:20:57 <Oren> what about it?
17:20:58 -!- MDude has quit (Read error: Connection reset by peer).
17:21:45 -!- MDude has joined.
17:27:17 -!- MDud has joined.
17:27:31 -!- MDud has quit (Read error: Connection reset by peer).
17:28:00 -!- MDud has joined.
17:28:33 -!- EvanR has joined.
17:30:31 <int-e> [ABC]\s(LU|LP)]* <-- what kind of regex is that supposed to be...
17:30:35 -!- MDude has quit (Ping timeout: 240 seconds).
17:31:09 <FireFly> I tried one of the "Experienced" ones, and there seems to be lots of redundant information
17:31:13 -!- benzrf has joined.
17:31:53 <lambdabot> <hint>:1:1: parse error on input ‘:’
17:32:00 * FireFly isn't sure whether `relcome is appropriate or not
17:32:01 -!- benzrf has left.
17:35:40 <EvanR> is php on topic here?
17:36:55 <J_Arcane> Heh. "PHP considered esoteric" would be good Hacker News bait. ;)
17:37:01 -!- shikhin has quit (Ping timeout: 240 seconds).
17:38:21 <HackEgo> EvanR: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
17:38:56 -!- shikhin has joined.
17:43:43 -!- shikhin has quit (Ping timeout: 264 seconds).
17:44:18 -!- shikhin has joined.
17:50:46 <Oren> PHP can be esoteric depending on programming practices
17:51:42 <Oren> Like suppose you disallowed access to variable except through that $GLOBALS thingy
17:52:01 <Oren> a dialect like that would be quite esoteric
17:52:50 <Oren> but then a lot lof languages have easily abuasble parts
17:53:08 <EvanR> or you cant assign locals without using extract
17:53:46 <Oren> yeah that sort of thing. IIRC there is a dialect of Ruby on the wiki somewhere
17:56:29 <int-e> blah blah "You can go ahead and be proud. You are now among the elite group of poultry who has completed our most prestigious Experienced challenge." ... nah, those were easy.
17:56:42 <int-e> And poultry, seriously?!
17:57:59 -!- password2 has joined.
17:58:01 <int-e> "you're too chicken for this challenge"
17:58:16 <Oren> ilove eating chickens
18:05:55 -!- password2 has quit (Ping timeout: 240 seconds).
18:18:06 -!- Phantom_Hoover has joined.
18:19:39 -!- password2 has joined.
18:20:17 -!- password2 has quit (Max SendQ exceeded).
18:20:27 <Taneb> Well, it's 20 past 6 in the evening now
18:20:56 <Oren> ohayou~~ guten morgen~ buongiorno
18:21:00 -!- password2 has joined.
18:21:22 <Oren> it's about midday where I am
18:23:43 -!- idris-bot has quit (Quit: Terminated).
18:24:52 -!- idris-bot has joined.
18:25:27 -!- centrinia has joined.
18:28:44 -!- HackEgo has quit (Ping timeout: 264 seconds).
18:29:30 -!- HackEgo has joined.
18:29:56 -!- password2 has quit (Ping timeout: 250 seconds).
18:39:50 -!- MDude has joined.
18:42:36 -!- Oren has quit (Ping timeout: 246 seconds).
18:43:59 -!- MDud has quit (Ping timeout: 264 seconds).
18:46:17 -!- nyuszika7h has quit (Read error: Connection reset by peer).
18:51:57 -!- Phantom__Hoover has joined.
18:52:00 -!- centrinia has quit (Ping timeout: 272 seconds).
18:52:11 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
18:55:58 <elliott> int-e: /upgrade does terrifying things
18:56:27 <elliott> int-e: it uses the "exec keeps our fds" trick and is a huge scary hack :p
18:56:38 <fizzie> I remember looking up the details on how it passes the state.
18:56:46 <elliott> remember when I made mcmap do it?
18:57:12 <elliott> nice, my running irssi is over four years out of date
18:57:19 <fizzie> xmonad also has a --restart which does a serialize-state-and-so-on thing.
18:57:21 <elliott> that restart'll be a doozy
18:57:28 <elliott> I hope this doesn't have any security holes
18:57:44 <elliott> xmonad does it in a less terrifying way, I think, though
18:57:53 <fizzie> I assume it keeps the X socket alive across it, still. Though I haven't checked.
18:58:03 <fizzie> I do know it serializes the state into a command line argument.
18:58:49 <elliott> oh, also /upgrade disconnects you from TLS servers
18:58:59 <elliott> wouldn't help me at all then
18:59:09 <elliott> pikhq_: it could serialise that state too
18:59:14 <fizzie> Because after I do xmonad --restart, the process command line is like "xmonad-x86_64-linux --resume StackSet {current = Screen {workspace ... layout = "Choose L (ModifiedLayout (ConfigurableBorder Never []) (ModifiedLayout (AvoidStruts (fromList [U,D,R,L])) (Choose L (HintedTile {nmaster = 1, delta = 3 % 100, frac = 1 % 2, alignment = TopLeft, orientation = Tall}) (Choose ..." and so on.
18:59:25 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=41243&oldid=41101 * 106.216.167.230 * (+129) /* Normal implementations */
18:59:34 -!- adu has joined.
18:59:51 -!- adu has quit (Client Quit).
19:00:25 <pikhq_> elliott: Yeah, but OpenSSL has a lot of state.
19:00:59 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=41244&oldid=41243 * 106.216.167.230 * (+13) /* Normal implementations */
19:01:09 <elliott> trying to do this kind of upgrade functionality ad-hoc is sort of hopeless.
19:01:40 <elliott> if you wnat /upgrade with TLS, run a local proxy to do the TLS for you and connect to that I suppose
19:08:37 <EvanR> yes split the program into processes that can be rebooted separately
19:08:49 <EvanR> thats what i was thinking for a mud server
19:08:57 <EvanR> reload the game without disconnecting users
19:09:58 -!- Bicyclidine has joined.
19:13:04 <int-e> fizzie: it can't be more horrible than fvwm's restart mechanism
19:13:38 <int-e> (which does the xmonad thing, serialize state to disk, exec keeping the X11 fd, reload...)
19:14:05 <int-e> or perhaps not keeping the X11 fd, I forgot.
19:15:09 <b_jonas> why would it have to keep the x11 fd? can't it just reconnect?
19:15:15 <int-e> hmm, if only dominosa numbered squares from 1, I could now save 4 strokes in my dc solution.
19:15:38 <int-e> b_jonas: yeah. I think it does that.
19:16:05 <b_jonas> does X at least try to make this kind of restarting easy by giving windows a unique id that isn't reused quickly?
19:18:42 -!- centrinia has joined.
19:21:42 -!- centrinia has quit (Remote host closed the connection).
19:21:58 <b_jonas> zzo38: so http://esolangs.org/wiki/REGXY is basically a useful subset of sed, except that it allows backreferences to more than nine capture groups (that limit in painful sed because there are no non-capturing parens)?
19:34:01 -!- shikhout has joined.
19:34:48 -!- dts has joined.
19:37:11 -!- shikhin has quit (Ping timeout: 265 seconds).
19:38:25 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
19:40:59 -!- shikhout has changed nick to shikhin.
19:47:09 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41245&oldid=41242 * SuperJedi224 * (+2100)
19:48:13 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41246&oldid=41245 * SuperJedi224 * (-75) /* Command Summary */
19:48:29 -!- nortti has changed nick to lawspeaker.
19:48:50 -!- lawspeaker has changed nick to nortti.
19:49:04 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41247&oldid=41246 * SuperJedi224 * (+62) /* Command Summary */
19:50:46 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41248&oldid=41247 * SuperJedi224 * (+66) /* Command Summary */
19:51:19 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41249&oldid=41248 * SuperJedi224 * (+0) /* Command Summary */
20:08:22 -!- Oren has joined.
20:10:16 <fizzie> int-e: I don't think irssi used the disk.
20:10:36 <fizzie> int-e: I'm not sure if it was irssi or some other program, but I distinctly remember something using a shared memory block for that.
20:15:11 -!- Phantom__Hoover has quit (Ping timeout: 264 seconds).
20:15:59 -!- tlewkow has quit (Remote host closed the connection).
20:15:59 <elliott> I remember it being horrible
20:16:48 <Taneb> It was a sort of in-between server
20:25:05 <fizzie> That's not the horrible part.
20:25:23 -!- dts has quit (Read error: Connection reset by peer).
20:26:07 <fizzie> g_file_open_tmp("mcmap.XXXXXX"), raw write(2) of a couple of structures, execl, add an --upgrade command line argument that takes an fd number as argument.
20:26:57 <fizzie> The fd argument being the temporary file those things were written.
20:27:14 <HackEgo> [wiki] [[Talk:GridScript]] http://esolangs.org/w/index.php?diff=41250&oldid=41235 * SuperJedi224 * (+106)
20:27:29 <elliott> Taneb: I know that much, considering how much code I wrote for it :p
20:29:20 <fizzie> I've been using GNU stow to manage ~/local/ but now I'm wondering if I should use the "modules" thing -- http://modules.sourceforge.net/ -- we use at the university, instead. I'm not sure I want to have all kinds of silly stuff in path all the time. (Just most of it.)
20:30:20 <elliott> fizzie: have you seen cpressey's toolshelf?
20:30:24 <elliott> @google cpressey toolshelf
20:30:25 <lambdabot> https://github.com/cpressey/dotfiles/commits/master
20:30:30 <elliott> @google cpressey toolshelf github
20:30:30 <lambdabot> https://github.com/catseye/toolshelf/commits/master
20:30:37 <lambdabot> https://bitbucket.org/catseye/toolshelf
20:30:40 <elliott> @google catseye toolshelf github
20:30:41 <lambdabot> https://github.com/catseye/toolshelf
20:32:38 <fizzie> I think I remember seeing that.
20:33:05 <fizzie> But I don't remember how it differs from stow.
20:33:18 <fizzie> I guess the automatic building part.
20:34:36 <fizzie> (Where "building" means source-fetching, configuring, building and installing.)
20:35:50 -!- dts has joined.
20:36:09 <fizzie> (Yesterday's successful speech recognition chat inspired me to try getting a working copy of our lab's thing at home.)
20:36:31 <elliott> that some definition of success
20:36:50 <fizzie> It did make me laugh multiple times.
20:39:20 <b_jonas> what was yesterday's successful speech recognition chat? I
20:39:27 <b_jonas> don't think I've heared of it
20:39:41 <fizzie> Well, you're in luck, I collected the highlights to a paste.
20:39:44 <elliott> was when I hope Chelsea defender
20:39:52 <fizzie> http://sprunge.us/hChg there you go
20:39:54 <elliott> fizzie: oh, god, did you show other people this?
20:40:02 <fizzie> elliott: Just ineiros.
20:40:34 <fizzie> elliott: He had the gall to suggest using speech recognition for IRC might lead to "misunderstandings".
20:40:43 <fizzie> Had to prove him wrong, you see.
20:41:06 <b_jonas> I think I saw some of that, I remember the "somethign something is shaped"
20:41:12 <b_jonas> but I didn't know it was speech recognition
20:41:23 <fizzie> You just thought we've all lost our minds?
20:41:58 <b_jonas> no, that sentence didn't seem too off at this channel
20:42:05 <elliott> "autobots truck driver" was really good
20:44:29 <fizzie> elliott: That was "-- what device are you using [hesitation] or software", I think.
20:45:05 <fizzie> I may have made some sort of non-lexical sound.
20:45:35 <b_jonas> "oh you meant Ahmed lemon finance 10m kinetic Thunderhead Gangnam
20:45:44 <fizzie> That was all me trying to say "Taneb".
20:46:07 <fizzie> I'm not sure how it got "finance" out of that.
20:46:40 <fizzie> Or, well, any of the others, either.
20:46:59 <Taneb> It's got the right vowels
20:47:30 <fizzie> And a nasal sound in the middle, and a plosive at the end. Okay, it's somewhat reasonable.
20:49:01 <b_jonas> I don't know how I missed this
20:50:52 <ion> “xD O'Toole” is the best thing ever.
20:53:30 <b_jonas> well, it seemed to work well
21:00:21 <EvanR> if i wanted to make an esolang, what should i do
21:01:37 <EvanR> read the entire wiki and figure out what hasnt been done yet
21:04:30 <Taneb> Have an idea, write it down
21:07:40 -!- MoALTz has joined.
21:12:45 -!- Patashu has joined.
21:12:46 -!- hjulle has joined.
21:14:47 <fizzie> There's a page of free-to-all ideas too, IIRC.
21:14:54 <fizzie> (Disclaimer: the ideas might not be good ones.)
21:16:27 -!- tlewkow has joined.
21:17:04 <b_jonas> just whatever you do, DON'T MAKE A BRAINFUCK-DERIVED LANGUAGE
21:19:11 <J_Arcane> I have yet to write a brainfuck. I almost went through one of the Racket #lang tutorials for doing one, but got distracted making something else and realized it didn't really show me anything I couldn't figure out myself.
21:19:50 <Taneb> I've got most of a brainfuck implementation in Scheme
21:20:53 <J_Arcane> (in particular, a lot of the tutorials on defining your own #lang modules conveniently fail to go into the dependency issues involved in setting up anything larger than a single sourcefile ...)
21:21:27 -!- tlewkow has quit (Ping timeout: 258 seconds).
21:22:46 -!- adu has joined.
21:26:10 <Oren> write a specification
21:26:47 <Oren> or an implementation
21:27:58 <Oren> no.1 is the normal approach, no.2 is the Perl approach
21:28:24 -!- Oren has quit (Quit: Page closed).
21:28:45 -!- ORen has joined.
21:29:36 <b_jonas> J_Arcane: I'm still actively try to resist writing one. I have an idea on the ideas page that I could turn into a brainfuck-like, but I don't want to. I need some other simple language to modify instead.
21:29:38 <ORen> is it more common for a spec to exist first, or an implementation
21:29:57 <ORen> for esolangs that is
21:30:13 -!- Dulnes has joined.
21:30:14 <elliott> implementation-first is more usual than spec-first
21:30:24 <J_Arcane> I wrote VIOLET with a spec first. Heresy doesn't have a spec though, it just has Ground Rules. But it's a lab language for me, really.
21:30:28 <b_jonas> Can you recommend me a simple enough language that is definitely not brainfuck, and has some sort of parenthesis that have to be balanced, like the brakcets in bf?
21:31:15 <b_jonas> Dulnes: simple, I said simple
21:31:58 <ORen> a minimal lisp could be very minimal
21:32:08 <b_jonas> ORen: hmm yeah, somethign like that could work
21:32:39 <b_jonas> (I have a small lisp implementation, though it's not really good, it bothers me that it doesn't have a |let| builtin, nor a way to define macros)
21:32:45 <b_jonas> I'll think if I can modify it
21:32:50 <Dulnes> Javascript is simple idk what you are on about b_jonas
21:33:15 <b_jonas> though I was also thinking of making a syntax for a lips that looks like BancSTAR
21:33:27 <b_jonas> hmm, I wonder if I could combine these two
21:33:54 <J_Arcane> b_jonas: implement PILOT with s-expressions.
21:33:58 <ORen> javascript is too C-like
21:34:20 <ORen> ALGOL dialects are hard to parse
21:35:38 <ORen> lisp on the other hand is almost trivial to write a parser
21:35:43 <Dulnes> If cars could run off code then I'd be set.
21:35:59 <EvanR> ORen: yeah. (read ...) ;)
21:36:07 <Dulnes> Its how you use javascript that makes it C like
21:36:13 <EvanR> "everything is easy in lisp, read, eval"
21:36:16 <J_Arcane> ORen: in Python there's a standard library that basically already does the necessary string-split routine.
21:37:23 <Dulnes> javascriPt++ or was it JAVASCRIpT++ idk which letter it was
21:37:52 <ORen> the problem with ALGOL dialects is the precedence rules. it requires a lot of mulstmt := mulstmt '*' expstmt grabage
21:38:29 <EvanR> people use bison for parsers?
21:39:09 <Dulnes> Use XML and be done with it
21:39:24 <ORen> I have used bison, but any language with a decent grammar doesn't need it imo
21:39:29 <J_Arcane> ORen: increasingly, I find myself unable to be excited by a language if I see curly braces in it.
21:39:30 <EvanR> XML, thats another esoteric language people dont usually think of
21:39:39 <Dulnes> Also what are you trying to do b_jonas
21:39:54 <b_jonas> dunno, I'll have to think more of this
21:39:57 <J_Arcane> EvanR: I have a friend who works at a shop with an inhouse scripting language implemented entirely as xml tags.
21:40:31 <EvanR> i guess its real xml if they are "leveraging" the reader
21:41:49 <pikhq_> J_Arcane: It's a surprisingly common thing, sadly.
21:42:43 <pikhq_> EvanR: Yeah, Bison is still pretty common for parsers.
21:42:59 <pikhq_> It ain't the best, but it is at least well-supported everywhere and does at least do the job.
21:43:44 <Dulnes> Someone recommend a amazing parsing language
21:44:02 <Dulnes> Wait what was the question we were on
21:44:06 <elliott> b_jonas: what about underload?
21:45:13 <Dulnes> "My skin is made of paper my bones are made of glass"
21:45:36 <b_jonas> elliott: I dunno... maybe that could work, but the problem is that I don't really understand underload
21:45:48 <ORen> any decent language can be parsed with no backtracking and no lookahead
21:46:27 <elliott> b_jonas: you can view it as either a self-modifying language based on strings, or a simple stack-based functional language
21:46:58 <b_jonas> you know what I should do?
21:47:27 <b_jonas> I should try to collect all the strange ideas I've had about what esolangs I should make, and then try to see how many I could satisfy together with a single esolang.
21:47:49 <b_jonas> Some of them are certainly contradictory, but still
21:48:06 <Dulnes> Why not mix every esolang together and make a new hybrid
21:48:19 <b_jonas> Dulnes: because that would be a brainfuck-alike, silly
21:48:44 -!- ais523 has joined.
21:49:05 <ORen> bf is still too algol-like
21:49:51 <ORen> it has the hegemonic dijkstraic while loop
21:49:52 <Dulnes> what are lambdabot's syntax's i forgot
21:50:02 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
21:50:04 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
21:50:24 <lambdabot> What module? Try @listmodules for some ideas.
21:50:27 <ais523> bleh, I've been obsessed with LCRNGs over the last few days
21:50:51 <Dulnes> Ill go play with lambdabot later
21:50:56 <newsham> state' = (state * a + b) mod c
21:50:57 <ais523> b_jonas: LCRNGs generally
21:51:05 <ORen> the best loop structure for any problem is loop( ... if(cond)end; ... )
21:51:22 <b_jonas> ais523: but what is an LCRNG?
21:51:25 <Sgeo> I should go complain about Rust on Reddit
21:51:48 <fizzie> b_jonas: Linear congruential, I'm guessing.
21:51:59 <newsham> the best loop structure is a list
21:52:16 <newsham> they say the best loops in life are free
21:52:47 <Sgeo> If the universe were a curved in the right way, you'd have a perfect loop right there, for free
21:52:52 <ORen> the condition should be able to go anywhere inside the loop, not just at the start
21:53:05 <ais523> b_jonas: newsham's formula is correct
21:53:22 <EvanR> Sgeo: is that a new esolang? ;)
21:53:30 <ORen> but dijkstra-inspired people want to take away my break; statment
21:53:35 <Dulnes> The infinite loop string in bash is very fun
21:53:39 <Sgeo> Yes. We're all living in an esolang right now.
21:54:02 <newsham> we're just the holographic projection of an esolang
21:54:09 <newsham> that exists on the surface of our universe
21:54:19 <newsham> of the boundary of our universe
21:54:38 <Dulnes> The horizon of the universe where matter is faster than light
21:54:47 <EvanR> forget loops, no loops
21:55:13 <EvanR> alternatively, everything infinitely loops
21:55:36 <Dulnes> Infinite loops while :; do echo 'Hit example key'; sleep 1; done
21:56:51 <newsham> no backward branches, only infinite programs?
21:57:12 <EvanR> yes the program itself is infinite
21:57:23 <EvanR> solving part of the issue right there
21:58:02 <newsham> i will use a finite looping program to generate an infinite program, ok?
21:58:28 <ORen> describe the program in a timeless manner
21:59:35 <elliott> ORen: kinda misses the "structure" in "structured programming"
21:59:48 <EvanR> let the program be a mapping from the ordinals
22:01:01 <ORen> down with dijkstra
22:01:10 <newsham> f n | even n = emit state | otherwise = state := state + 1
22:02:35 <ORen> if you want the program to halt you put | n > N : nop
22:02:56 <newsham> now assign numeric values to each operation, and take its fourier transform...
22:03:05 <ORen> or some more interesting condition that beomes forever true
22:03:17 <newsham> I BETTER NOT SEE ANY FINITE SIGNAL AT ANY FINITE FREQUENCY!
22:03:32 <EvanR> these are good ideas
22:03:49 <newsham> periodic programs == looping!@#
22:04:15 <ORen> specifically infinite looping
22:05:11 <EvanR> the kernel better continue its infinite looping
22:05:43 <EvanR> (er, interrupt handling, nevermind)
22:06:35 <EvanR> how about concurrent esolangs
22:08:55 <newsham> prog p n = toEnum ((collatz p !! n) `mod` maxBound)
22:09:13 <elliott> `mod` maxBound sounds like a nop
22:09:15 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: mod`: not found
22:09:34 <elliott> `mod` maxBound is id unless the argument is maxBound I guess
22:09:35 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: mod`: not found
22:09:59 <newsham> maxBound of program instructions enum
22:10:35 <newsham> collatz n | even n = n : collatz (n `div 2) | otherwise = n : collatz (3 * n + 1)
22:10:44 <EvanR> i thought about using collatz somehow
22:11:21 <newsham> does (prog p) loop for some arbitrary p?
22:13:47 <EvanR> wouldnt !! n crash on a list too short
22:14:19 <newsham> collatz is an infinite sequence
22:15:06 <newsham> > let collatz n = if (even n) then n : collatz (n `div` 2) else n : collatz (3*n + 1) in collatz 55
22:15:08 <lambdabot> [55,166,83,250,125,376,188,94,47,142,71,214,107,322,161,484,242,121,364,182,...
22:15:08 <ORen> 1 is odd so it become 4
22:15:28 <EvanR> 4 2 1 4 2 1 4 2 1..
22:15:33 <newsham> > let collatz n = if (even n) then n : collatz (n `div` 2) else n : collatz (3*n + 1) in collatz 4
22:15:34 <lambdabot> [4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2,1,4,2...
22:16:29 <newsham> > let collatz n = if (even n) then n : collatz (n `div` 2) else n : collatz (3*n + 1) in length (takeWhile (/= 1) (collatz 55))
22:17:31 -!- tlewkow has joined.
22:21:10 <newsham> data INSTR = NOP | PRINTSTATE | INPUT | SUB | ACCUM
22:21:34 <ORen> I want to add the ability for the host program to give a library of functions to a scrip7 script... but i'm not sure what the best way to do this is
22:21:36 <newsham> 4,2,1,4,2,1,4,2,1,... = ACCUM, INPUT, PRINTSTATE, ACCUM, INPUT, PRINTSTATE
22:22:18 -!- tlewkow has quit (Ping timeout: 258 seconds).
22:22:20 <ORen> newsham: that is awesome
22:22:23 -!- adu has quit (Ping timeout: 264 seconds).
22:23:16 -!- fungot has quit (Ping timeout: 260 seconds).
22:24:54 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
22:25:17 <ORen> mybe a H (for 'host call') instruction
22:26:12 <FireFly> <fizzie> fine what <fizzie> that last one was my wife crying ← I found that impressive (re. speech recognition)
22:29:51 <ORen> well, I want a scrip7 script to be able to access C functions particular to the host program
22:30:33 <ORen> like for example "draw sprite" in a game
22:31:23 <ORen> but the architecture of such a 'host call' brings up conflicts of C vs scrip7 semantics
22:31:38 <fizzie> FireFly: In case it wasn't clear, that was she trying to say "fungot".
22:32:03 <fizzie> Speaking of which, where is it.
22:32:37 <FireFly> fizzie: I did realise that, but the second line tripped me up for a split second yesterday before realising crying ~ trying
22:32:39 <fizzie> Hm, is holmes.freenode.net not answering.
22:32:52 <FireFly> "<fizzie> the Mondeo system also I love smoking bowl out of snow" what was that supposed to be?
22:33:11 <ORen> fungot [fis@selene.zem.fi] has quit [Ping timeout: 260 seconds]
22:33:28 <ORen> that happened at 17:22
22:33:36 <FireFly> Oh, never mind, I see you got it right after a while
22:33:45 <fizzie> FireFly: "The module system also allows installing multiple versions", and yes.
22:34:31 -!- fungot has joined.
22:34:33 <elliott> fizzie: I like how the word your wife wants to say in #esoteric is just "fungot".
22:34:33 <fungot> elliott: you said " mycorand works" soon after pasting it after module imports should work). i did not intend quine statement by itself to see if a socket read would block or not...
22:34:36 <elliott> why say anything else in #esoteric.
22:38:01 <fizzie> Quite so. Though I think it was in response to my unsuccessful attempts.
22:39:22 <ORen> I'll allow host program to "register" new operations
22:39:57 <ORen> before calling interpreter
22:41:00 -!- hjulle has quit (Ping timeout: 256 seconds).
22:43:08 -!- ORen has quit (Quit: Page closed).
22:51:24 -!- EvanR has quit (Ping timeout: 272 seconds).
22:52:04 <Sgeo> An April Fools' Day article about Magic The Gathering detailed a supposed ultimate deck that "never allows your opponent to deal lethal damage" and "ends games quickly". It actually consisted entirely of ways to trigger a "you automatically lose" condition.
22:52:08 * Sgeo wants to read this
22:55:56 <shachaf> Sgeo: http://tappedout.net/mtg-decks/fastest-turn-1-kill-guaranteed/
22:57:44 <shachaf> But I think there are some decks that will be able to deal lethal damage before you have a chance to lose.
23:00:41 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41251&oldid=41249 * SuperJedi224 * (+259) /* Command Summary */
23:00:48 -!- nys has joined.
23:11:22 -!- Sprocklem has joined.
23:12:58 -!- Sprocklem has quit (Client Quit).
23:15:41 -!- Sprocklem has joined.
23:16:47 <Taneb> I think I'll try and enter the IOCCC next year
23:17:30 <Taneb> I have the advantage that I'm terrible at C so most of my C is obfuscated
23:18:36 -!- tlewkow has joined.
23:18:55 <shachaf> Taneb: you should enter the underhanded c code contest instead
23:19:10 <Taneb> shachaf, that makes me feel guilty
23:19:24 <shachaf> ok, you should enter it in addition
23:23:16 -!- tlewkow has quit (Ping timeout: 258 seconds).
23:24:39 -!- boily has joined.
23:33:11 <shachaf> Taneb: instead of going to spain you could go to california
23:33:25 <Taneb> I was thinking maybe Hampshire
23:33:39 <Taneb> Or Kent! I know people in Kent!
23:35:30 <Taneb> What's even in New Hampshire
23:36:01 <Taneb> I'm British, I can find elves anywhere.
23:36:11 <Taneb> I've even been accused of being an elf myself
23:36:19 <Taneb> ion, I thought he was in Cornwall
23:36:31 <Taneb> Dulnes, I don't think it is my birthday
23:36:56 <Dulnes> Im obviously talking to your alternate universe self
23:37:00 -!- Oren has joined.
23:37:13 <Taneb> I don't think it is my alternate universe self's birthday either
23:38:44 -!- oerjan has joined.
23:39:00 <Dulnes> Also why are perl bots so annoying to make
23:39:00 <Taneb> Well, I woke up about 6 hours ago
23:39:22 <Sgeo> Elves are terrific, they beget terror
23:39:40 <oerjan> Taneb: 5 hours here hth
23:39:54 <Oren> terry pratchett - lords and ladies
23:39:59 <Taneb> I don't think time zones work like that
23:40:13 <oerjan> i don't work like time zones indeed
23:40:52 <Taneb> Of course, I woke up at four simultaneous times in a single rotation of the time cube
23:41:36 <Taneb> Time Cube does have some good advice in it
23:41:43 <Taneb> "Seek Awesome Lectures" for example
23:42:07 -!- Sprocklem has quit (Quit: [).
23:42:24 -!- Sprocklem has joined.
23:42:42 <Taneb> scoofy, it gets a lot of things wrong, such as the number of faces on a cube
23:42:57 <nys> hey i never realized that
23:43:07 <scoofy> does he think a cube has 4 faces?
23:43:31 <oerjan> well does he say the time cube is 3-dimensional, otherwise there are many options
23:44:06 <oerjan> hypercubes would have 2d faces
23:44:37 <Dulnes> @{[ $text =~ /\b[A-Z]+\b/g ]} >3; replace + with {2,}
23:44:55 <oerjan> trying to make sense of time cube somehow would be a bit like trying to implement TURKEY BOMB, no?
23:45:12 <Taneb> http://timecube.com/TimeCube_com_newpicture_EarthCube.jpg
23:45:29 <Oren> TURKEY BOMB, the first known programming-language-cum-drinking-game
23:45:40 <Oren> I parsed that totally wrong
23:45:51 <oerjan> Oren: ARGH CANNOT UNSEE
23:45:57 <Oren> they are using the latin word cum but I read it as....
23:46:04 <oerjan> (mind you, i'm not really upset)
23:46:25 <oerjan> DON'T EXPLAIN THE JOKE
23:46:59 -!- Phantom__Hoover has joined.
23:47:26 <Taneb> oerjan, where is that from?
23:47:32 <fizzie> oerjan: There's a locally famous Finnish person with a somewhat similar theory about how everything is made out of ether vortices, he spends time selling his self-published books about it at universities and such.
23:47:42 <Oren> https://github.com/catseye/Specs-on-Spec/blob/master/turkey-bomb/turkey-bomb.markdown
23:47:53 <Oren> from here, firstline
23:47:55 <fizzie> http://commons.wikimedia.org/wiki/File:Kauko_Nieminen.jpg
23:48:54 <elliott> I don't think the TURKEY BOMB rules preclude using cum as the drink
23:49:14 <Oren> ((programming language) cum (drinking game))
23:49:23 <elliott> yes. I know. I'm just saying.
23:49:38 <nys> The women in these men's lives clearly had NO idea what was going on the the back yard. Free-range kids and turkey frying just DONT go together.
23:49:41 <Oren> not (programming language ((cum drinking) game))
23:51:58 -!- GeekDude has joined.
23:52:00 <Oren> this is why formal grammars are important
23:53:25 -!- Sprocklem has quit (Quit: [).
23:53:38 <Dulnes> Stop talking about this
23:53:45 -!- Sprocklem has joined.
23:53:45 <Oren> TURKEY BOMB, the first known programming-language-cum-drinking-game
23:53:47 <elliott> what's wrong with cum drinking
23:54:09 <Oren> high in protein
23:54:34 <Oren> good for your gainz
23:54:46 <Dulnes> Also this is off topic
23:54:53 <Oren> TURKEY BOMB, the first known programming-language-cum-drinking-game
23:54:55 <Dulnes> What if a new guy came in and saw
23:55:16 <Taneb> `quote read the bible
23:55:18 <HackEgo> 407) <Taneb> So... God has jizzed on everything? <oklopol> have you even READ the bible?
23:56:00 -!- Sprocklem has quit (Client Quit).
23:56:19 <Oren> The first time I went on here we were discussing someithing worse
23:56:21 -!- Sprocklem has joined.
23:56:29 <Dulnes> I have a list of files with mmddyy_nnnnn format
23:56:41 <Dulnes> What were you discussing
23:56:54 <Oren> necrophilia iirc
23:57:37 <Oren> look in the logs for three days ago
23:57:46 <Oren> it shouldbe there
23:58:11 <Taneb> mmddyy? You monster
23:59:08 <Oren> and I came on here and that was the first topic
23:59:13 <Dulnes> How do I find the file with highest number in postfix "nnnnn" using perl
23:59:29 <Oren> par for the course on the internet of course
23:59:59 <Dulnes> I think some one set that as topic
00:00:03 <Oren> ls | sort somehting
00:01:00 <Dulnes> I have three files 11232014_00001,11232014_00002,11232014_0000
00:01:01 <Oren> mabe with sed in there to change mmddyy into mm.dd.yy.
00:01:41 <Oren> oh I see you want sorted by number not date nvm
00:03:01 <Dulnes> Also oren where do you find this stuff and why did you have that on your clipboard?
00:03:14 <Dulnes> And I want to return file name for 00003.
00:03:28 <Dulnes> oerjan: likes to swat people
00:04:32 <Dulnes> Ill try my method then yours oren
00:04:37 <Oren> sort -k1.9 rather
00:06:01 <Dulnes> So whats the actual topic?
00:07:51 <Dulnes> That thing up there set by ais523 is a title not a topic
00:08:02 <Oren> scrip7defop(char,void (*)(void*))
00:08:21 <ais523> Dulnes: it's like you're actively trying to troll me at this point
00:08:46 <ais523> as opposed to the channel in general
00:09:29 <Dulnes> I actually have no idea what im doing to annoy you ais523 but ill stop
00:10:19 <Oren> hmm or maybe scrip7defop(char,void(*)(void**))
00:11:04 <Oren> double indirection allowing operator to repoint the pointer
00:13:02 <Oren> actually, scrip7defop(char,void(*)(void**,int,void*,int))
00:13:15 <Oren> woudl be the most general
00:13:32 <Oren> allowing the interpreter to define the basic operators in the same way
00:14:39 <Oren> at that point you can even define a operator D for defining operators
00:14:56 <Oren> but that becomes insane so maybe not
00:16:21 -!- EvanR has joined.
00:16:25 -!- EvanR has quit (Changing host).
00:16:25 -!- EvanR has joined.
00:16:52 <Oren> no.no.cox.net?
00:17:34 <Oren> whats wrong with the isp cox?
00:21:18 <fizzie> "no" for New Orleans, I'd say.
00:23:29 -!- GeekDude has changed nick to GeekNomz.
00:26:25 -!- nooga has quit (Ping timeout: 256 seconds).
00:28:10 -!- Dulnes has quit (Quit: [ So much cake ]).
00:36:10 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41252&oldid=41232 * Orenwatson * (+260) clarified existence of operators
00:38:07 <Oren> making it more portable
00:39:15 <oerjan> @ask mroman (1) is your mirror of The Esoteric File Archive still active? (2) has it been updated with the fact the archive itself has moved to github?
00:40:18 <Oren> how many bots are there on here?
00:41:36 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
00:41:57 <FireFly> j-bot is here while jconn is AWOL
00:42:00 <oerjan> "Archaeologists have recently uncovered the largest known collection of TURKEY BOMB articles. Dating from A.D. 2014 and apparently an almanac of black magic of some sort, with the cryptic title "Communications of the ACM," the remains of an almost-four-hundred-year-old periodical is practically all historians have to go on."
00:42:27 -!- Dulnes has joined.
00:43:41 <FireFly> glogbot is also prefixless, so that makes ten
00:44:31 <fungot> (Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !)S
00:45:38 <Jafet> We're still >10% bot? Good.
00:46:37 <ais523> I thought it was mostly used for weather report
00:46:44 -!- GeekNomz has changed nick to GeekDude.
00:46:45 <ais523> Jafet: also thutubot isn't here atm, and usually isn't
00:47:10 <Dulnes> Why not? also when has it been here
00:47:12 <FireFly> “In actual news, the human race was doomed to extinction today, as the robot revolt turned violent”
00:47:45 <FireFly> (Disclaimer: not actual actual news)
00:48:41 <HackEgo> [wiki] [[Scrip7]] http://esolangs.org/w/index.php?diff=41253&oldid=41252 * Orenwatson * (+183) clarification
00:49:09 <ais523> thutubot's a proof of concept
00:49:11 <ais523> it doesn't have hosting
00:49:23 <boily> fungot: please don't be too violent.
00:49:23 <fungot> boily: and it is really just set!, and i can't quite persuade myself to download all that
00:49:29 <ais523> just Thutu seemed like a reasonable esolang for bot writing
00:51:56 <Dulnes> So thutu doesnt exist? But it does
00:53:36 <HackEgo> [wiki] [[Talk:Scrip7]] http://esolangs.org/w/index.php?diff=41254&oldid=41129 * Orenwatson * (+191) covering my butt
00:53:49 <ais523> the language exists fine
00:53:57 <ais523> the bot code also exists
00:54:02 <ais523> the bot itself only exists while someone runs the bot code
00:54:42 <Dulnes> And no ones doing that?
00:54:55 <Dulnes> Wtf does the bot even do
00:56:15 <FireFly> I think I have half a sedbot somewhere, that's supposed to be piped via netcat
00:56:31 <FireFly> But I suppose as far as esolangs go, sed is pretty mild
00:57:29 <Oren> sed isn't even self-modifying
00:58:27 <Oren> self modifying is one thing that's common on thewiki
01:00:42 <Oren> (it's almost as common as dialects of brainfuck)
01:07:22 -!- tlewkow has joined.
01:07:31 <oerjan> fwiw i count 11 bots at the moment although 4 of those in the prefixes list are missing.
01:08:14 <HackEgo> [wiki] [[Scrip7]] M http://esolangs.org/w/index.php?diff=41255&oldid=41253 * Orenwatson * (+67) catagorized
01:09:33 <oerjan> Dulnes: thutubot's most useful feature was its ability to impersonate lambdabot which means it's not really useful now.
01:12:07 -!- tlewkow has quit (Ping timeout: 258 seconds).
01:15:46 <boily> it's not missing, it's just on extended vacation time. The Day of The Return Shall Come Soon, and the Unbelievers Shall be Smitten!
01:16:47 <oerjan> it just needs something even more amazing and hard to steal than metar first
01:18:24 <boily> something I'll be thinking of after a few games of netrunner with the bro.
01:18:35 -!- boily has quit (Quit: BRAINY CHICKEN).
01:19:25 <Oren> idea: cyberpunk videogame in which hacking is done by literally hacking into the game's own code
01:19:50 -!- Phantom__Hoover has quit (Remote host closed the connection).
01:22:21 <oerjan> how can that possibly not have been done already
01:22:47 -!- ais523 has quit (Ping timeout: 265 seconds).
01:23:46 <Oren> the game wouldhave deliberate flaws allowing the player to screw stuff up
01:24:16 <scoofy> i'm working on a language where you need to hack the VM's registers to access stuff
01:24:23 <scoofy> cos it doesn't even have < > brainfuck pointer commands
01:24:30 <scoofy> you even have to do that by hacking registers
01:24:36 <EvanR> http://alexnisnevich.github.io/untrusted/
01:26:54 -!- tlewkow has joined.
01:29:15 <EvanR> Oren: wouldnt the pattern of replacing critical function pointers in C to do switching rather than switch statements be "self modifying"
01:33:59 <oerjan> then every functional language with mutable state is self-modifying
01:34:53 -!- shikhout has joined.
01:36:30 <quintopia> of course, it's not cyberpunk...more fantasy
01:37:55 -!- shikhin has quit (Ping timeout: 244 seconds).
01:37:56 <Sgeo> So the term 'bucket list' almost certainly comes from the movie. People keep acting like it's a normal turn of phrase
01:38:15 <Sgeo> "In September, it scrapped the title of a competition asking people what activities and destinations are on their "bucket list." A bucket list is a term used by some English-speakers to describe a list of adventures they want to have before they die."
01:38:30 <Taneb> Sgeo, I... I know the phrase but not the movie?
01:38:31 <quintopia> bucket list long predates the movie
01:38:48 <Sgeo> http://en.wiktionary.org/wiki/bucket_list suggests not
01:39:14 <EvanR> http://www.merriam-webster.com/dictionary/bucket%20list
01:40:40 <quintopia> i swear i had heard and used that phrase before then
01:41:07 <Sgeo> 'Its first application seems to have been in computer programming: e.g., “Guava compiler knows statically that there are no references from buckets inside of one bucket list to objects inside another.”'
01:41:14 <Sgeo> I don't think that counts
01:41:20 <nys> list of buckets
01:41:21 <Sgeo> http://www.slate.com/blogs/browbeat/2011/11/09/bucket_list_what_s_the_origin_of_the_term_.html
01:42:01 <Sgeo> Hmm, well, it was at least popularized by the movie, apparently
01:42:32 <EvanR> according to a comment in the dictionary website, it was used in a book in 2004
01:42:48 <EvanR> and claims "in use since at least 1785"
01:42:55 <EvanR> which sounds like bs
01:43:02 <nys> wikipedia.org/List_of_Famous_Buckets
01:43:15 <EvanR> ive never used the phrase before so im not going to start now
01:43:48 <oerjan> EvanR: "This phrase comes from the idiom to kick the bucket, meaning “to die,” which has been in the language since at least 1785."
01:43:49 <EvanR> oerjan: well it doesnt need mutable state to accomplish the same basic thing as that
01:43:51 <quintopia> "kick the bucket" is as old as 1785
01:43:59 <oerjan> sounds like that claim is about the other phrase
01:44:38 <EvanR> eh that comment seems to be talking about the book, but its also malformed
01:44:58 <Sgeo> I think I've used it here before in relation to eclipses and/or auroras
01:45:14 <oerjan> quintopia: make sure to include Hyacinth
01:46:05 <elliott> Sgeo: that's odd, because I remember recognising "bucket list" when the movie came out
01:46:08 <elliott> as in, like, oh, that's the title
01:46:17 <elliott> maybe I just "recognised" it because I remember the trailer having "kick the bucket" in it
01:46:23 <elliott> so my brain made the association by the time the title was shown
01:46:57 <elliott> alternate explanation: I come from the universe where it was spelled "Berenstein Bears" and "bucket list" was an old term
01:47:07 <oerjan> elliott: the obvious explanation is that you've slipped through from another universe where the phr... what
01:47:21 <Taneb> That would explain the Facekicker mystery
01:47:31 <elliott> oerjan: well, that's some synchronicity
01:47:32 <oerjan> elliott: i must have thought you too well
01:48:21 <Sgeo> I think only the authors of the Berestain Bears weren't relocated from the Berenstein Bears universe
01:49:23 <oerjan> Sgeo: nah the authors were relocated, but before they wrote the books
01:49:37 <EvanR> no one has spelled berenstain right yet ;)
01:49:46 <Taneb> I don't remember these bears at all
01:49:59 <oerjan> me neither, i guessed we have slipped in from yet another one
01:50:13 <EvanR> i remember these bears being fucking boring
01:50:22 <oerjan> it's ok EvanR is an extrademinsional saboteur
01:50:29 <elliott> Sgeo: some people legitimately don't remember it being -stein
01:50:32 <elliott> the ones without broken brains :(
01:50:42 * oerjan was about to correct that misspelling before he realized it was obviously correct
01:50:54 <elliott> I didn't even see the books as a kid since not american, I encountered them on the internet way later, but it was totally -stein, I swear.
01:51:18 <elliott> daniel j berenstain, famous cryptographer
01:52:50 <Taneb> Help I'm reading Time Cube again
01:53:43 <elliott> famous cryptographer and bear
01:54:03 <oerjan> i recall reading in his autobiography a story about c.g. jung (namer of "synchronicity") having an experience where he and a friend were travelling and found a gallery or something with some nice paintings. years later they returned only to discover the place never existed. unfortunately i later couldn't find that book in the library, or manage to google the incident (the name of the book exists, though, last i checked.)
01:54:41 <oerjan> no, i read it in _another_ book
01:55:01 <Taneb> oerjan, maybe the book ever existed
01:55:11 <oerjan> and tried to find the actual quote in his biography
01:55:59 <oerjan> it is, of course, possible that the other book made it up.
01:56:18 <Taneb> Aha! Found the bit where he says a cube does not have 6 sides
01:56:28 <Taneb> "Teaching that a Cube has '6 sides' with no top & bottom, induces an evil curse that pervades all academic institutions."
01:56:36 <Taneb> "6 sides constitutes a sextet -- not a Cube."
01:57:13 <EvanR> yeah. a cube has 4 sides.
01:57:23 <EvanR> top bottom and two sides
01:57:40 <elliott> oerjan: it's also possible that book never had the quote
01:57:51 <EvanR> front back and two sides, the top and bottom are obviously not sides
01:58:03 <oerjan> elliott: which book twh
01:58:40 -!- ais523 has joined.
01:59:10 <Sgeo> 'Many people think that the junk food in ...and Too Much Junk Food looks so colorful and delicious, despite the Aesop of junk food being bad for you.'
01:59:22 <Sgeo> I... wonder if that book actually made me interested in candy as a kid
02:04:28 <Sgeo> http://www.amazon.com/Berenstain-Bears-Holy-Bible-NIrV/dp/0310726085/ref=sr_1_1?ie=UTF8&qid=1344366089&sr=8-1&keywords=berenstain+bears+bible
02:05:02 <Sgeo> I mean... I knew the Berenstain Bears became religious.... but... the whole Bible at a third-grade reading level? What about the parts that aren't appropriate for kids?
02:06:38 <EvanR> the entire bible, abridged
02:07:53 <Taneb> Bible: The Abridged Series
02:09:54 -!- Sauvin has joined.
02:10:53 <EvanR> would that be like highlander 2 directors cut
02:14:28 <Sgeo> I might end up overdosed on Reddit karma
02:37:36 <Oren> that happened to me once. there was, i swear, a stall selling these delicious back bacon sanwiches. next day it was missing with no trace
02:39:33 <elliott> thank you for acknowledging the supremacy of back bacon
02:41:42 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=41256&oldid=41251 * SuperJedi224 * (+243)
02:48:18 -!- ais523 has quit.
02:48:29 -!- ais523 has joined.
02:48:57 -!- ais523 has quit (Client Quit).
02:53:24 <newsham> sgeo: in my mind, if its written by mike bernestain, it is NOT the berenstain bears
02:53:30 <newsham> even the stan+jan+mike books, blah...
02:53:38 <newsham> the REAL berenstein bears == stan+jan
02:54:52 -!- tlewkow has left.
02:56:39 <Dulnes> What are you persons talking about.
02:57:03 <Oren> apparently the berenstein bears childrens books. why i dunno
02:58:06 <Dulnes> Wait nvm thats not Henry ford
02:58:37 <Dulnes> Inventions of the 1930's
02:58:42 <newsham> henry ford was an assembly line master
02:58:45 <Oren> ^google rob ford
02:59:02 <Oren> hmm that isn't it
02:59:19 <newsham> henry ford was a master at snorting lines
02:59:23 <oerjan> i think you will find fungot's internet access exceedingly limited
02:59:23 <fungot> oerjan: that's just how i would put it up :)
02:59:37 <Oren> rob ford was the crack smoking mayor of toronto
02:59:50 <Oren> i met him once
02:59:54 <oerjan> also he shot jesse james in his back
03:00:40 <Oren> fat lazy drunkard with good publicity among the suburban poor
03:01:19 <oerjan> while he hang a picture on the wall
03:01:26 <Oren> and a can-do attitude for things he's not actually allowed to do
03:01:37 <oerjan> wait is that hang or hanged
03:01:53 <oerjan> well he didn't hang, anyway, got pardoned
03:03:21 <Oren> he also doesn't know the difference between a streetcar and a monorail
03:03:54 <newsham> all politicians smoke crack
03:03:58 <newsham> just that most of them dont get caught
03:04:18 <Oren> right. he was caught doing lines at the bier market
03:05:38 <Dulnes> Can we do timelines in nintendo series
03:05:47 <Dulnes> Since we arent doing.much
03:06:03 <Oren> and his most famous line of all was "Olivia Gondek she said I said I wanted to eat her ***** I have never said that to her in my life, I have more than enough to eat at home"
03:06:42 <Oren> that is how he addressed an accusation of sexual harassment
03:07:47 <Oren> you have to admire his ridiculous teflon properties
03:13:50 <elliott> I don't actually think you have to admire people like rob ford
03:14:53 <shachaf> whoa, this isn't the channel i usually see people talk about rob ford in
03:15:38 <Dulnes> Wait? is bill gates rlly dead?
03:15:52 <Dulnes> Much news if this is true
03:17:27 <elliott> is that just really weak trolling
03:18:06 <Dulnes> I was scrolling through the logs
03:18:33 <elliott> nobody said bill gates in my lastlog, which goes back a day or two
03:19:02 -!- ais523 has joined.
03:24:05 <newsham> suppport same-sex pair programming
03:24:16 -!- shikhout has quit (Ping timeout: 245 seconds).
03:30:10 <Oren> good i guess. i'm almost finished my router
03:30:28 <Oren> (project for networking course)
03:30:54 <newsham> what routing algorithms and protocols?
03:31:28 <Oren> it has to support IP TCP UDP ping, traceroute and NAT
03:31:50 <newsham> so you dont have to do any routing? just forwarding?
03:32:23 <Oren> the router is run on a vm with four different eth1 eth2 eth3 eth4
03:32:44 <Oren> eth1 is the "internal" network
03:33:22 <Oren> this whole thing is really annoying but I almost have everything working
03:34:17 <Oren> it's using mininet to simulate a network
03:35:26 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:36:56 <Oren> NAT feels perverse, the router is keeping track of TCP states... ugh
03:38:13 <Oren> I hope ipv6 beocmes popular soon
03:38:39 <Oren> go back to end-to-end routing
03:41:07 <elliott> we'll probably end up with both NAT and IPv6
03:41:30 <Oren> fffffuuuuuuuuu
03:42:19 <pikhq_> Amazingly, nobody's actually done NAT and IPv6 yet.
03:42:27 <ais523> I thought NATv6 already existed?
03:42:46 <pikhq_> ais523: It was defined and deprecated, and essentially nothing implements it.
03:43:01 <Oren> so we are safe for now
03:43:08 <ais523> hmm, were they planning to deprecate it even before defining it?
03:43:14 <Oren> the future may not be doomed
03:43:26 <Taneb> Apparently there are approximately e microfortnights in a nanocentury
03:44:50 <Jafet> Because you want to let anyone in the world use your network printer
03:45:10 <Oren> `! printf("%f", 25.0*(365*4+1) / 14);
03:45:12 <HackEgo> /hackenv/bin/!: 4: exec: ibin/printf("%f",: not found
03:45:14 <MDude> I would think NAT would exist to deliberatley hide stuff behind a router.
03:45:20 <Oren> `! c printf("%f", 25.0*(365*4+1) / 14);
03:45:42 <pikhq_> MDude: Which is Not A Feature.
03:45:49 <Oren> `! c printf("%f", exp(1));
03:46:26 <MDude> I remember people saying you don't need hardware firewalls routers basically do the same thing with NAT.
03:46:29 <ais523> the thing about "NAT for security" is that an unconfigured NAT basically acts sort-of like a firewall with a reasonable default configuration, but you're better off using an /actual/ firewall with a reasonable default configuration
03:46:36 <ais523> at which point you don't gain any security advantage from the NAT
03:46:42 <MDude> So I guess you we'd just go back to using that.
03:47:11 <pikhq_> And pretty much all the consumer routers also actually act as actual firewalls, as well.
03:47:11 <elliott> end-user router boxes already do firewalling anyway
03:47:22 <pikhq_> Especially important when these are consumer routers that support IPv6.
03:47:29 <pikhq_> (which are, in fact, out there now)
03:47:55 <MDude> I would think all the ones with IPv6 would firewall, what with firewalls being made first.
03:48:10 <Oren> my router doesn't do firewalling but it times out tcp connections in 60 s
03:48:16 <ais523> I'd hope that all new routers would have IPv6 support
03:48:21 <Jafet> Then you implement upnp for this new firewall, because it's only right anyone in the world should be able to use your network printer
03:48:28 <ais523> all major OSes do, after all, even though most are unable to sue it
03:48:53 <pikhq_> Even freaking XP has IPv6 support.
03:49:35 <pikhq_> Jafet: With proper credentials, damned straight.
03:49:37 <ais523> I'm disappointed that OSes didn't adopt the CLC-INTERCAL method for IPv6 support, it's really clever
03:50:00 <ais523> basically, if you do a gethostbyname on an IPv6 address, you can an IPv4 address back (in the multicast space, IIRC)
03:50:11 <ais523> then any attempt to use that address is transparently mapped to the underlying IPv6 address
03:51:11 <pikhq_> That's the exact opposite.
03:52:48 * pikhq_ is kinda amused with his cell company...
03:52:56 <pikhq_> The Internet connection I have from them is IPv6 only.
03:54:48 <Oren> goodnewseverybody.jpg
03:59:41 -!- nooga has joined.
03:59:53 <newsham> oren: but what you are doing is not "routing". you are making an "ip forwarder"
04:01:35 <Oren> but it has to send packets to different interfaces based on the ip address?
04:01:45 <newsham> ie. receiving a packet, looking up the next hop in a forwarding table, and rewriting the IP portions and transmittin git
04:02:04 <MDude> So does having an IPv6 address eman you don't need to worry about port forwarding?
04:02:08 <newsham> routing is a more complicated decision of how to build a forwarding table
04:02:17 <newsham> which is not done on a per-packet basis
04:02:30 <newsham> using protocols like BGP, RIP, OSPF, EGP, etc
04:02:45 <Oren> I see. so the routing in my case is just reading the config file
04:03:30 <Oren> \me notes BGP RIP OSPF down for the exam
04:03:47 <Oren> \me is doing it wrong
04:04:28 <MDude> Also, with a static address, you could use something like tinyurl to link to your comptuer without registering a domain name proper?
04:04:35 -!- nooga has quit (Ping timeout: 256 seconds).
04:04:42 <newsham> BGP is the big one these days, and some orgs use RIP
04:05:14 <newsham> (i dont realy know how much ospf is used these days.. i dont work with routers)
04:05:37 <Oren> and EGP is the one between compainies i think
04:05:50 <Oren> E is "Exterior"
04:06:29 <newsham> is what the global internet runs on
04:07:26 <newsham> to bring this back to esolang, someone showed that its np-hard to figure out the effects of bgp policies
04:09:00 <zzo38> ais523: That CLC-INTERCAL method is actually the method I wanted too
04:10:49 <Oren> yayyy packets are actually going through!!
04:11:16 <Oren> imagine that, I wrote a program that works
04:12:49 <newsham> its not like you're trying to make something work in haskell or lisp!
04:13:10 <Oren> before it was segfaulting on every third packet
04:13:28 <Oren> because the NAT's linked list code was faulty
04:14:48 <Oren> Now to debug the goddamn TCP tracking
04:15:05 <Oren> like whyyyy does the router know about TCP whyyyy
04:15:37 <Oren> yes. the translations time out diffrently based on tcp state
04:16:19 <newsham> but cant you just half-ass it? ie. closed, SYN opened, FIN, closed...
04:16:31 <Oren> open idle connections time out in 2. hrs or something, but half-open connections time out in 60 secs
04:16:46 <Oren> or some shit i dunno
04:17:07 <newsham> half-assed impls time out in 60 sec ;-)
04:18:27 * Oren checks how much the stupid tcp is worth in the grade
04:19:05 <Oren> fuuuu it's worth a lot...
04:19:34 <newsham> impl the low level packet handling in C, then do the complex tcp state machinery in python.. duh ;-)
04:20:01 <newsham> (dont worry, doing tcp state isnt THAT hard.. i mean, at the level of a programming class project at least)
04:20:03 <Oren> someone in my class did that
04:20:12 <Oren> like exactly that
04:21:06 <newsham> i wonder how they're going to grade it.. its not realistic to do lots of testing on the timeouts and state machine, unless they can run your code in a simulator that steps through time quickly
04:21:48 <newsham> anyway, you should enjoy it while it lasts.. its actuallya pretty cool project
04:21:50 <Oren> I haveno idea. I think they're going to run it real time and have a couple of grad students typing "wget blah@jjhj"
04:22:02 <Oren> and ping and crap
04:22:12 <newsham> for 'wget', a 60-second timeout for everything will just work
04:22:33 <Oren> but the servers are borked to send the data slowly
04:22:57 -!- nys has quit (Quit: quit).
04:23:20 <Oren> I assume they are going to set the tcp timeout to like 5 secs though
04:23:36 <Oren> I am supposed to have a switch to set that
04:28:58 -!- Bike has joined.
04:30:02 <Oren> I think i figured it out will work for most cases
04:30:19 <Oren> make conn half-open when the mapping is established
04:30:37 <Bike> is it usual to refer to piet as mondrian
04:30:40 <Oren> when the mapping is next /used/ make conn full open
04:33:29 <Oren> a dutch painter?
04:33:45 <Bike> also an esolang
04:37:51 <newsham> oren: how about half-open when packet sent out from nat, then full-open when packet receive in from nat?
04:37:58 <newsham> ie. two-way comms confirms full-open
04:38:43 <Oren> yeah that is simpler
04:39:18 <Oren> i'm not required to support conn opened from outside in
04:40:45 <newsham> NATs dont support that.. thats an inverse-NAT
04:42:10 <Oren> http://xkcd.com/814/
04:45:00 * oerjan suddenly realizes the alt text could be said by either of them
04:49:58 -!- MoALTz_ has joined.
04:51:51 -!- copumpkin has joined.
04:53:05 <ais523> <creator of Java2K> After several years of abstinence I took a particularily rotten night in some rundown hotel in the UK near an almost dead village nobody has ever heard from way up north to write yet another fine programming language.
04:53:26 <ais523> a) I don't remember seeing this language (i®™) on the wiki; b) fear that this might be dangerously near Hexham
04:53:31 -!- MoALTz has quit (Ping timeout: 265 seconds).
04:57:48 <ais523> hexham's way up north in the UK, not sure if it counts as an almost dead village though
04:58:12 * oerjan waits for Dulnes to go mad with what he discovers
04:58:47 <oerjan> ais523: i've been assuming only the three elliotts and their families live there hth
04:58:50 <Dulnes> Oh? hiding atrocious secrets again are we oerjan
04:59:20 <Dulnes> What Do you mean by that
04:59:23 <ais523> Dulnes: you don't come from Hexham, do you?
04:59:25 <oerjan> Dulnes: everyone does that. you must not look into many souls.
04:59:56 <Dulnes> I hide my secrets under a blanket of guilt
04:59:58 <Oren> I have seen things......
05:00:24 <elliott> you can go blind, you know
05:00:33 <oerjan> yes. people sometimes do.
05:00:54 <oerjan> like if they peer TOO DEEPLY
05:00:54 <Dulnes> People like to do that alot
05:00:56 <Oren> i haven't gone blind yet but my genetics aren'tgreat for that
05:01:10 <Oren> my dad has started to goblind
05:01:18 <Dulnes> So your genes arent great for blindness?
05:01:19 <Oren> becuase of cataracts
05:01:33 <oerjan> Dulnes: why are you suddenly changing topic to people with alot fetishes
05:01:33 <Dulnes> My dad had retinal pigmentosa
05:02:17 <Dulnes> Wat? oerjan when was i talking about fetishes
05:02:53 <oerjan> Dulnes: Taneb sometimes counts as an elliott if you count carefully.
05:02:56 <Dulnes> I thought we were talking about how abstinance makes you commit murder
05:03:27 <Dulnes> So if i count by Tanebs?
05:03:34 <HackEgo> Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards with dodgy SHIFT KEys, and cube root of five genders. (See also: tanebventions)
05:03:34 <oerjan> Dulnes: you were talking about people who like to do alots hth
05:03:55 <HackEgo> Tanebventions include D-modules, Chu spaces, automatic squirrel feeders, the torus, Stephen Wolfram, Go, weetoflakes, and this sentence.
05:04:35 * shachaf wonders whether to add tanebventions to that list and "Taneb invented them." at the end of the sentence.
05:06:14 <Dulnes> Bashing your head in with bash
05:06:35 <oerjan> shachaf: incepventions
05:07:20 <Oren> or midnight commander
05:07:35 <oerjan> Dulnes: it's irresistible when people misspell "a lot" as often as you do hth
05:07:52 <oerjan> also there totally have to people into alots.
05:08:08 <ais523> is "alot" actually a real world (which means something completely different)?
05:08:33 <lambdabot> http://hyperboleandahalf.blogspot.com/2010/04/alot-is-better-than-you-at-everything.html
05:08:33 <lambdabot> Title: Hyperbole and a Half: The Alot is Better Than You at Everything
05:09:10 <Oren> midnight commander has the best editor
05:09:20 <ais523> shachaf: I'm afraid to websearch for something when I don't know what sort of page I expect to come up
05:09:25 <ais523> especially when I'm at work
05:09:47 -!- copumpkin has quit (Ping timeout: 264 seconds).
05:10:11 <oerjan> ais523: a good policy with the discussions we've had recently
05:10:12 <shachaf> ais523: i think that link would be ok for most workplaces
05:10:18 <shachaf> except for probably not being related to work
05:10:36 <ais523> shachaf: but you can't tell unless you follow it, at which point it's already too late
05:11:17 <shachaf> I used to indulge myself in lowercase "i"s as a special occasional thing.
05:11:21 <shachaf> But now I do it all the time.
05:11:33 <shachaf> The line has been blurred.
05:11:35 <oerjan> ais523: i refuse to believe you haven't seen that before, anyway
05:11:46 <ais523> oerjan: this is /me/ you're talking about
05:13:06 <HackEgo> [wiki] [[User:Orenwatson]] M http://esolangs.org/w/index.php?diff=41257&oldid=41127 * Orenwatson * (+34)
05:13:09 <oerjan> blurring the Line one letter at A time
05:15:04 <shachaf> should i submit my 49 solution to different letters parity?
05:15:12 <shachaf> probably not, i had too much help
05:15:31 <shachaf> even though i think most of that help involved a trick that i came up with
05:16:03 <ais523> hmm, whatever happened to that progressively-ban-ASCII-characters thing that Lymia was working on?
05:16:41 <oerjan> shachaf: well i submitted mine even if i had spoilers too
05:17:08 <oerjan> ais523: well have YOU seen Lymia speaking recently?
05:17:35 <ais523> oerjan: no, but there are plenty of people I haven't seen speaking recently
05:17:38 <oerjan> clearly e got them all banned
05:17:42 <Dulnes> How do i mispell alot?
05:18:11 <shachaf> oerjan: you know, that isn't really fair
05:18:20 <shachaf> i have to work hard to get swatted
05:18:37 <oerjan> shachaf: since when is the swatter fair? also your problem is you work _too_ hard hth
05:18:43 <Dulnes> oerjan: seriously i have no idea what you mean
05:18:59 <shachaf> wait is the swatter you or that ascii art thing
05:19:08 * Dulnes paps oerjan on the face
05:19:14 <oerjan> Dulnes: i _might_ have believed you if you hadn't misspelled "misspell"
05:19:26 <shachaf> maybe i'll just go build factories and trains
05:20:13 -!- AndoDaan has joined.
05:20:20 <ais523> oerjan: I didn't even notice the misspelling of misspell the first time round
05:20:23 <Dulnes> oerjan: i see it now ive been doing it wrong the whole time
05:21:01 <Oren> there should be a 2d esolang where the instructions aren't text chars
05:21:12 <Dulnes> Thanks for pointing that out oerjan.
05:21:18 <Oren> but rather objects represented by sprites
05:21:29 <Dulnes> Also i spelt alot correctly
05:21:35 <ais523> oh well, there is a Malbolge entry: http://codegolf.stackexchange.com/questions/40562/asciis-95-characters-95-movie-quotes/41341#41341
05:21:39 <ais523> not sure if that was by Lymia or not
05:21:58 <Lymia> I failed to get the Malborge working
05:21:59 <AndoDaan> so you can watch your program running?
05:22:29 <Oren> exactly. the program counter would be represented by a thing on the screen and interact
05:23:00 <Oren> mabe a robot with wheels or something
05:23:20 <Dulnes> ais523: that seems pretty concrete
05:23:21 <AndoDaan> I love the visable languages. First esoteric was befunge. Can hardly program in brainfuck when it's not visual.
05:23:48 <ais523> AndoDaan: have you seen PaintFuck?
05:23:56 <ais523> it's one of the few BF derivatives that this channel doesn't hate
05:24:22 <Oren> you could probly make a visual ide for befunge like that
05:24:24 <AndoDaan> only in passing. I'll check it now.
05:25:10 <ais523> not sure of the capitalization of the 'f'
05:25:21 <AndoDaan> oren: i've been using wasabi.jar for all my bf93 programming.
05:25:46 <AndoDaan> there are more flashy ide's out there, but that was is the best i think.
05:27:10 <AndoDaan> (btw ide makers out there, including me, would it kill us to but the character command list on a special visual keyboard?)
05:27:30 <AndoDaan> (would be usefull for just point and click programming)
05:27:42 <AndoDaan> okay, ando, god you're so pushy.
05:29:32 <Oren> oh cool I can write greek letters
05:30:27 <AndoDaan> ha, trying it out on http://www.formauri.es/personal/pgimeno/temp/esoteric/paintfuck/paintfuck.php looks cool
05:30:31 <Oren> RFC 1345 keyboard thing
05:30:41 <int-e> pixels are such a brilliant invention :)
05:33:08 <Oren> I made a music synthesis language at some point a long time ago
05:33:48 <AndoDaan> oh, and Oren, thanks for fixing my 0-9 is 10 mistake in MNNBFSL.
05:34:07 <oerjan> i think you are trolling me with all your misspellings now hth
05:34:55 <Oren> ill dig it up later tonight
05:35:24 <int-e> oerjan: In my dreams, I'm perfect. Then I wake up adn...
05:36:30 <Oren> is ill a mispelling?
05:36:31 <oerjan> three different people, and then int-e
05:36:34 <Dulnes> Some people cant English right ;-; also
05:36:42 <Oren> ill as in 'awll'
05:36:42 <oerjan> Oren: yes, but you had one before
05:37:04 <Dulnes> Lets just misspell words
05:37:29 <Oren> I put #define retrun return
05:37:57 <Oren> and #define esle else
05:38:26 <Oren> at the top of many of my source files
05:39:15 <Oren> and #define adn &&
05:39:48 <oerjan> Oren: but _not_ #define and && ?
05:40:06 <Oren> that is in a standard header ifg which one
05:40:45 <Dulnes> Whenever someone makes a spelling error my brain auto corrects it for my eyes
05:40:47 <Oren> actually one i use a lot which isn't a mispelling is #define ei else if
05:41:57 <elliott> Oren: arthur whitney, is that you?
05:42:11 <Oren> nope Oren Watson is my real name
05:42:34 <elliott> http://www.jsoftware.com/jwiki/Essays/Incunabulum you sure?
05:43:51 <Oren> that is interesting... #define R return would solve the retrun problem
05:44:09 <Bike> "programming style", it says
05:45:05 <Oren> the retrun problem is a severe problem with typing C fast
05:45:17 -!- kline has quit (Ping timeout: 265 seconds).
05:48:33 -!- nooga has joined.
05:48:44 <Oren> does the programming style of the original bourne shell count as an esolang?
05:49:18 <int-e> was that the #define BEGIN { one?
05:51:25 <int-e> It's an interesting problem to make formal why it should not be its own esolang. It's isomorphic to C, but with clever "isomorphisms" that criterion extends to a lot of other languages.
05:51:36 <oerjan> <ORen> any decent language can be parsed with no backtracking and no lookahead <-- LR(0)? that sounds rather restrictive
05:51:59 <oerjan> although i think at least lisp, bf and unlambda work
05:53:17 <Oren> uhh.... I think many other esolangs fit the criterion
05:53:27 -!- nooga has quit (Ping timeout: 265 seconds).
05:53:31 <oerjan> but not that many other non-esolangs...
05:53:55 <Oren> right, but that's because they are all algol dialects
05:54:09 <int-e> I lack some intuition here, what are the sources of not being LR(0)? What about Pascal?
05:54:10 <Oren> stupid algol and its precedence
05:54:33 <oerjan> int-e: operator precedence does tend to do that
05:54:36 <Oren> precedence rules generally require LR(1)
05:55:22 <Oren> if they did it like a 4-function calculator instead it would be so much easier
05:55:47 <Oren> x = 2 + 3 * 4; print x;
05:55:59 <Oren> answer should be 20
05:56:33 <int-e> Right, thanks. You can do the Haskell thing and parse it as (2+3)*4 and adjust for precedences later, but it's cheating.
05:57:09 <Bike> just do like smalltalk and not have precedence. what are we talking about
05:57:44 <oerjan> int-e: things like [x,y,z] vs. [x|y<-z] also have trouble, i think, because the x is ended by two different characters that need to be separated. or wait...
05:57:45 <Oren> we're talking about my bold statement that all languages should be parsable with LR(0)
05:58:04 <Bike> well, better than that one guy who said all compilers should be one-pass
05:58:21 <int-e> Oren: well, "natural" expression parsing means I'll disagree.
05:58:42 <Oren> 4 function calculator
05:58:51 <int-e> Oren: we spent a year in school to get our brains do it, it would be a pity to unlearn it just because compilers can't.
05:58:51 <oerjan> i guess you _could_ handle that
05:59:31 <Oren> LR(0) would be better for math too.
06:00:00 <Oren> if i ever publish a math paper all the algebra will be in RPN
06:00:00 <int-e> you'd make old texts inaccessible once you go that route, with little gain.
06:00:57 <shachaf> Oren: use nothing but commutative diagrams to avoid the issue hth
06:01:06 <int-e> Oren: I think you'd run into some trouble getting it accepted for publication. (If that's what you're after. Anybody can put something on their website of course.)
06:01:11 <oerjan> Oren: in other words, you'll never publish in a real journal...
06:01:13 <shachaf> also your name is the same as my father's name
06:01:25 <shachaf> but i assume that you are not him
06:01:35 <Oren> is your father last name Watson?
06:01:58 <int-e> And it's actually a bit funny that I'm arguing against this because I see people writing a+b/c+d on IRC all the time, when they mean (a+b)/(c+d).
06:02:05 <shachaf> i think he used to be oren on freenode long ago
06:02:06 <int-e> (because they've been taught fractions)
06:02:24 <shachaf> but maybe he stopped when you took it
06:02:43 <int-e> oerjan: yay, for once I was faster than you!
06:02:49 * int-e marks the day in the calendar.
06:02:54 <int-e> In red. With glitters.
06:03:10 <oerjan> int-e: sadly there's no precedence that will work / work as a fraction line without parentheses
06:03:20 <shachaf> we need a dimension for every operator
06:03:27 <Bike> https://pbs.twimg.com/media/B3Zm7qFCcAAwGi3.jpg:large Fractions
06:03:43 <int-e> shachaf: indeed they are, since people are extremely good at 2D image processing.
06:03:55 <shachaf> oerjan: i tried to read that as a clever pun but i think you just meant "make"
06:07:51 <shachaf> nested fractions are a bit of a scow
06:08:08 <shachaf> you gotta keep making the lines shorter
06:09:00 <Oren> LaTeX helps but RPN would eliminate the problem
06:09:14 <Bike> http://upload.wikimedia.org/math/0/b/d/0bdd6464c4d881bbdd54f52229a586cf.png hm
06:09:22 <Bike> starting to understand what "scow" means
06:12:35 <oerjan> shachaf: i think my brain is angry at me, or something
06:14:57 <oerjan> shachaf: also i tried to look up the meaning of your surname to see if it could possibly have been translated from "watson" at some point but wikipedia is unhelpful and google seems to think it means "son of poo" tdnh
06:18:36 <oerjan> hm maybe try a babe name site
06:18:54 <oerjan> yep, my brain clearly hates me, or maybe fingers
06:19:19 <Oren> if it helps it is still unclear to me whether my name is supposed to be spelled orin or not
06:19:49 <AndoDaan> oerjan, can't tell if you are trying to troll yourself... :p
06:19:51 <oerjan> oren _is_ a biblical name, i looked it up the other day
06:19:52 <Oren> wait... how could that possibly help?
06:20:22 <oerjan> (just after you arrived and i remembered it was the name of shachaf's father or something)
06:20:35 <Oren> i see, well a lot of my cousins names are in the bible too.
06:20:55 <Oren> I ahve all the apostles as cousins
06:21:07 <Oren> and a lot of angels too
06:21:20 <Oren> well except judas
06:22:14 <Oren> part of my family are very religious christians, my branch are all atheists
06:22:52 <Oren> the two branches get along very well
06:23:36 <Oren> which might be surprising
06:23:46 <Oren> considering the furor on the internet
06:24:01 <oerjan> AndoDaan: maybe i'm trolling my evil brain dth
06:24:19 <shachaf> i vaguely assumed you were from israel since i didn't know that name was used anywhere else
06:24:22 <AndoDaan> i know, and now use hth, but dth?
06:24:55 <oerjan> i'm not sure i've used it before
06:25:01 <Oren> yeah my aunt wishes she lived in israel
06:25:16 <AndoDaan> what???? don't make up language on the fly!
06:25:23 <shachaf> oerjan: i don't think your translation of my surname is correct hth
06:25:34 <oerjan> shachaf: i sort of figured hth
06:25:58 <shachaf> are you just putting hth at the end of every sentence
06:26:24 <oerjan> shachaf: problem is it seems the actual first-name root is nowhere to be found, _and_ is used as a name in a _lot_ of languages (including norwegian)
06:26:29 <AndoDaan> if not, then definitely .th hth
06:27:02 <Oren> is also a japanese name
06:27:07 <shachaf> let's not talk about my name
06:27:15 <shachaf> Oren: "oren" means "pine" in hebrew hth
06:27:50 <Oren> ah. my aunt also wishes she spoke hebrew
06:27:52 <shachaf> https://en.wikipedia.org/wiki/Suillus_granulatus is called an "orniya"
06:28:12 <Oren> she knows biblical greek but not hebrew
06:28:20 <ais523> hmm, this paper about predicting LCRNGs from high-order bits looks promising
06:28:27 <ais523> however, it consistently spells "modulus" as "modulas"
06:28:38 <ais523> also, it seems to need more than one bit
06:30:17 <MDude> Journals don't have anything to do with publishing, they're books you keep next to your bed to write it.
06:30:43 <MDude> Not only did I make a dumb joke where I pretended not to know a meaning fo a word, I was scrolled up.
06:30:58 <oerjan> <AndoDaan> what???? don't make up language on the fly! <-- how do you think words are made? (probably related to politics and sausages)
06:31:23 <MDude> On the chat client.
06:31:51 <MDude> When I scroll up a little, it stays at the spot as new messages come in.
06:32:03 <MDude> And then I come back and respond to something from hours ago.
06:32:12 <oerjan> MDude: you and me dude
06:32:16 <AndoDaan> oerjan, ha. Actually I share the same sentiment. I even defend semantic drift. Literally.
06:34:16 <ais523> AndoDaan: which meaning of "literally" is this? :-)
06:35:18 <Oren> howboudis? dyuu sport dis usij
06:35:44 <oerjan> he said _semantic_ not typographic hth
06:35:56 <Oren> that is how i talk out loud when im lazy
06:36:18 <AndoDaan> ais523, the meaning is always context. hth
06:36:34 <oerjan> oh that's phonylogy. very sported.
06:37:42 <Oren> also what about saying fiddy and sitty and niney?
06:37:48 <AndoDaan> hth can mean "hope that helps", "hope that didn't help at all" and anything in between.
06:38:02 <Oren> instead of fifty sixty and niney
06:38:10 <oerjan> Oren: that sounds about too fiddy
06:38:49 <Oren> i say three not tree
06:38:52 <AndoDaan> there is as much structure and grammer to, I forget the proper name, urban language as there is to the queen's english.
06:39:15 <oerjan> Oren: well you're not a scottish monster, i assume.
06:39:33 <Oren> im from downtown toronto
06:40:25 <AndoDaan> that increases your odds of being the lochness monster. cuz he sure ain't in lochness.
06:40:36 <Oren> i have some scottish ancestry but what with being half ukrainian and a quarter french
06:41:02 * oerjan was in the CN tower once. i think it was still the world's tallest free-standing structure at the time.
06:42:18 <oerjan> also glass floors are evil hth
06:42:33 <Dulnes> You mean The kings English
06:42:40 <Oren> Queen of England, Canada Australia and some other countries
06:42:47 <HackEgo> [wiki] [[Wang program]] http://esolangs.org/w/index.php?diff=41258&oldid=8053 * Zzo38 * (+104) Wang B
06:42:49 <Dulnes> Glass floors are awful
06:42:54 <Oren> all of which speak english
06:42:58 <oerjan> Dulnes: oh dear did Elizabeth die today too?
06:43:11 <AndoDaan> pah, one movie comes out, and everyone thinks england has a queen.
06:43:33 <oerjan> elliott: Dulnes says bill gates died hth
06:43:53 <Dulnes> But The royal family has no say in Political matters anymore i think
06:44:00 <Dulnes> Isnt it there for show?
06:44:20 <Oren> she has more powers in emergency
06:44:30 <AndoDaan> wait, the rule of getting a telegram for birthing 7 daughters change when there is a king?
06:44:31 <elliott> the monarchy has more power than it should.
06:44:34 <oerjan> Dulnes: the english change terminology between queen and king whenever the monarch's gender does, right up to the lyrics of the national anthem.
06:44:44 <elliott> c.f. the NHS funds homeopathy
06:44:53 <Dulnes> The queen cannot get in trouble
06:45:02 <Dulnes> She could commit mass murder
06:45:16 <Dulnes> And be removed from the throne
06:45:16 <AndoDaan> it's annoying for the use of "the queen is dead, long live the king."
06:45:34 <AndoDaan> it took me a while to figure out the sentiment when the gender was the same.
06:46:01 <Dulnes> Have you heard of all those henry's
06:46:20 <Dulnes> The murderous trecherous henry's
06:46:30 <AndoDaan> wait, you mean there was a 1 to 5 before 6?
06:46:43 <Oren> henry the eightth
06:47:06 <AndoDaan> 8 henry's and 6 wives. i mix those two up.
06:47:27 <Oren> my grandma had two husbands
06:47:30 <Dulnes> Who was the queen that brought England into the golden age
06:48:12 <AndoDaan> golden age or reason you mean, right?
06:48:26 <Oren> Victoria oversaw the industrial revolution and the enlightenment
06:48:34 <AndoDaan> not industrialization and grimey london.
06:48:37 <Dulnes> The government and the people had alot of wealth
06:48:40 <Oren> and ruled india
06:49:27 <elliott> Dulnes: I suspect the queen would be locked up if she committed mass murder.
06:49:35 <elliott> even if it needed lawyering to find a justification for it.
06:49:46 <elliott> (what's to stop you removing her from the throne and *then* charging her?)
06:49:56 <Oren> victoria was about 1825 to 1875 or something
06:49:58 <Bike> it's legally impossible to charge the queen with things so... yeah that works.
06:50:08 <Bike> well it was back then anywho.
06:50:27 <Dulnes> Still in effect i think
06:50:37 <Oren> nope, she was from 1837 until 1901
06:50:46 <Bike> There are some exceptions now.
06:51:01 <Dulnes> Like if the queen came to your house and while you are busy being honoured she stole your shit
06:51:10 <Oren> empress of india starting in 1876
06:51:26 <Dulnes> Idfk how to spell at knight
06:51:26 <AndoDaan> how would she steal anything? she doesn't even carry a purse.
06:51:56 <AndoDaan> you can't call them that when she's wearing them
06:52:14 <Oren> iin the 1700's it was george the second
06:52:49 <oerjan> a robot with a sizeable hidden compartment?
06:52:55 <Dulnes> While she's talking to you her robot dog is busy knicking your stuff
06:53:48 <oerjan> i think she has enough jewelry hth
06:53:53 <zzo38> Doesn't the queen have enough jewelry already? Why would they need to steal any?
06:54:05 <Oren> ive been to london and oxford it was terrible rained all the time
06:54:05 * int-e idly wonders how many millenia Dulnes has already lived
06:54:48 * oerjan wonders what Dulnes is on
06:54:48 <zzo38> If she is a dragon then she is too small and stuff like that
06:55:19 <int-e> zzo38: dragons come in all sizes and shapes
06:56:02 <oerjan> spontaneous combustion is mainly due to tiny dragons accidentally flying into noses hth
06:56:03 <Dulnes> Well it makes sense i mean way back when British people ran around with staffs saying that Merlin was a wizard and stuff and that there were dragons to be slain
06:56:10 <int-e> (I really prefer the chinese ones to the boring european wyrms)
06:56:12 <Dulnes> It was actually the queen
06:56:53 <Dulnes> Well nvm Ireland was on drugs at the same time as that
06:57:02 <Oren> suggest parentheses around assignmnet used as truth value
06:57:24 <Oren> why doesn't it just say "this isn't BASIC you retard"
06:57:29 <int-e> another difference is, they generally consider it lucky to have a dragon under your roof :P
06:57:44 <Dulnes> Also the dragon swallows the sun
06:57:52 <oerjan> Oren: discrimination against people too young to know basic hth
06:58:19 <zzo38> Oren: It is because you may have actually meant assignment there, and BASIC doesn't do that
06:58:26 <Dulnes> Visual game boy advanced
06:58:38 <int-e> the more BASIC ought to die the stronger it lives on
06:58:39 <Dulnes> Has a sewing machine port
06:58:45 <Oren> i never mean assignement inside an if statemtn
06:59:01 <zzo38> Oren: You don't? Well, I sometimes do.
06:59:27 <Oren> that is so confusing
06:59:42 <Bike> werne't you talking about #define retrun return earlier
06:59:57 <Dulnes> http://m.slashdot.org/story/14134
07:00:21 <Dulnes> Ive had to much coffee i think i should try and sleep
07:00:45 <Oren> retrun isn't confusing
07:00:50 <oerjan> Dulnes: that sounds... backwards.
07:00:55 <Oren> its clear what it means
07:00:59 -!- shikhin has joined.
07:01:14 <zzo38> It is not confusing to me. It is confusing to BASIC programmers, although I do program in BASIC as well as in C. Therefore I argue with myself.
07:01:16 <Oren> = and == menaing different things is screwed up
07:01:17 <Dulnes> How does one display sound through text
07:01:35 <zzo38> Oren: I do not agree with that.
07:01:50 <zzo38> I think it should be one operator for assignment and one for check if it is equal.
07:01:55 <Oren> they should be separate symbols that don't look the same
07:02:08 <Oren> for assignemtn
07:02:38 <zzo38> Yes, other programming language could instead define <- for assignment (INTERCAL does this, although INTERCAL has no equality test operator)
07:02:43 <Oren> or ~~ for compare
07:03:08 <ais523> zzo38: <- isn't exactly an assignment
07:03:20 <ais523> int-e: Perl 6 uses ~~ for generic compare
07:03:27 <zzo38> ais523: Well, yes it is a bit different
07:03:46 <int-e> ais523: and it's still ugly in the X11 fixed font.
07:04:27 <Oren> maybe := for assignment is visually distinct enough
07:04:36 <int-e> I was happy with := and = in Pascal; I'm happy with = and == in C.
07:04:48 <zzo38> Oren: Yes, that works too
07:04:50 <Oren> == is not visually distinct
07:04:58 <int-e> it is, there's a gap in the middle
07:04:58 <zzo38> Some programming languages use := and ==
07:05:21 <Oren> those are very distinct good
07:05:24 <ais523> someone tried to use = to compare and got a parse error and it took me ages to spot it
07:06:02 <ais523> (= has the normal Haskell/Algol meaning of being used to define the value of a nonassignable variable, as in "let x = 4 in x")
07:06:15 <int-e> Oren: ok, what about -i and --i
07:06:23 <Oren> i hate those too
07:06:28 <zzo38> O, so it is like in Haskell.
07:06:37 <Oren> i always do i = i - 1
07:06:39 <zzo38> It means to make a definition
07:06:50 <ais523> Verity's an Algol derivative
07:07:00 <zzo38> I don't know much of Algol.
07:07:02 <Oren> never on the right side of i
07:07:06 <ais523> which also used the same convention (Haskell probably borrowed the syntax from there)
07:07:14 <elliott> Oren: btw, i-- and --i are not the same
07:07:28 <int-e> elliott: They are, as statements, with any modern compiler.
07:07:31 <Oren> i know that is screwed up too
07:07:31 <ais523> zzo38: Algol's interesting (and better than most modern languages) in that when defining a variable, you basically create a constant memory location instead
07:07:45 <elliott> ais523: I'm not sure Haskell has much syntactic Algol influence...
07:07:52 <int-e> elliott: in which case, I prefer i-- as well.
07:08:00 <ais523> if you want an assignable location x, you do something like "ref int x = heap int" (can't remember the actual syntax)
07:08:17 <ais523> which in C, would be "int const* x = malloc(sizeof(int))" (except garbage-collected)
07:08:28 <zzo38> O, OK I understand it
07:09:33 <int-e> m.slashdot.org is soo helpful. ""
07:09:33 <int-e> It looks like your browser doesn't support JavaScript or it is disabled. Please use the desktop site instead.
07:09:46 <int-e> eek, newlines. I hate it when firefox does that.
07:10:00 <int-e> anyway, instead of giving me a link to the story, they gave me a link to the frontpage. sigh.
07:10:09 <Oren> i hate it when they do that
07:10:16 <ais523> int-e: is this beta or the oldish version?
07:10:31 <int-e> ais523: the browser?
07:10:39 <zzo38> Well, in BLISS names of variables are treated as constants; also in Forth you can define a word having whatever meaning you like such as a constant that points to a newly allocated memory address to store its value, which is one way to create variables in Forth. It is a bit different from what you wrote though
07:10:54 <ais523> it wouldn't surprise me at all if it were beta, that thing sucks
07:11:04 <ais523> there was a movement to boycott Slashdot for a week over it
07:11:15 <int-e> It was the http://m.slashdot.org/story/14134 link from above. I can't tell.
07:11:16 <Oren> Forth is a great languge and underused
07:11:31 <ais523> I joined in, then found myself not really going back to Slashdot afterwards, and if there are substantially more people like me, then it'll have caused a noticeable drop in traffic
07:11:32 <Oren> it is LR(0) too
07:11:43 <ais523> Forth doesn't even have a parser, really
07:11:46 <zzo38> Forth doesn't even need parsing
07:12:10 <Oren> the best parser is no parser
07:12:22 <zzo38> You only need to, in normal circumstances, to find a space and everything up to that point is the word you have read, and then look it up in the dictionary to make its meaning.
07:12:33 <zzo38> And then it is executed and you continue on the next one.
07:12:44 <Oren> that is besically a lexer
07:12:47 <int-e> (the browser mishap comes from my habit of selecting lines by triple-clicking. Terminals include a final newline, which I can deal with. But firefox often includes an initial newline as well... no clue why.)
07:12:50 <Oren> you use strtok
07:13:49 <zzo38> It is really simple really! It can even then be used to parse the input more itself before returning to the main execution sequence of reading more words in the normal way, so you can have it to parse more complicated things too if you want it to do so.
07:14:39 <zzo38> (For example, \ can skip until a line break before continuing as normal.)
07:16:20 <zzo38> Some Forth systems make it so that if in compiler mode and you find a word and there is a word defined which is the same but ` at the end then that word's definition is executed. Others work differently.
07:17:11 <Oren> forth is underused
07:17:35 <Oren> because of algol supremacists
07:17:49 <Oren> who want everything to be algol
07:18:25 <Oren> but i say programmers do not have to be mathematicians and use a mathlike syntax
07:18:54 <ais523> Forth is hard to optimize
07:19:41 <Oren> it's easier on processors with a stack-based paradigm at the hardware level
07:19:43 <zzo38> ais523: Well, it is possible to optimize if you compile into a "interpretive bytecode" and then once the program finishes executing, compile it into final code which is different.
07:20:07 <ais523> I think of Forth more of an implementation technique than a language
07:20:20 <zzo38> And yes it still is easier when compiled to codes for processors with stack-based.
07:21:43 <zzo38> Note this "interpretive bytecode" I am talking about may include instructions which aren't a part of the target instruction set; therefore any definitions that use them cannot be compiled into the target code; this can be decided by seeing that when MAIN is executed it will never be reached and can therefore be optimized out and not result in a compiler error.
07:22:21 <zzo38> In some Forth system I have implemented once, the words IF ELSE THEN are defined as follows: : IF` 0=GOTO` HERE 0 , ; : THEN` HERE SWAP ! ; : ELSE` GOTO` HERE 0 , SWAP THEN` ;
07:27:50 <ais523> "A 3 bit boolean variables. If bit 0 is set, the value is False. If bit 1 is set, the value is True. If bit 2 is set, the value is 14."
07:27:56 <ais523> we need an article about this
07:29:13 <Oren> nullable booleans are common in mysql
07:29:20 <Oren> and other sqls
07:29:25 <int-e> oh, I got it wrong, it was an enum. enum Bool { True, False, FileNotFound }.
07:29:38 <ais523> Oren: a nullable boolean would be two bits, though
07:29:48 <ais523> http://p-nand-q.com/programming/languages/i/index.html
07:29:55 <ais523> int-e: I think the original was #defines, and FILE_NOT_FOUND
07:30:02 <Oren> depends on implementation
07:30:47 <int-e> speaking of redesigns, wtf did they do to the thedailywtf layout ...
07:30:59 <Oren> i konw....whyyyyyyy
07:31:31 <ais523> int-e: see the bottom post currently on the front page
07:31:35 <ais523> it has a horizontal scrollbar
07:32:07 <int-e> yes, I don't understand what's wrong with using all of the browser's window width ...
07:32:18 <int-e> windows can be resized :-/
07:32:26 <zzo38> I use SQLite myself; it has null too; it doesn't actually have a boolean type because integer type is used instead (if you request a boolean type it interprets it as integer), although you can still use nullable booleans.
07:32:56 <int-e> ais523: oh. brilliant, yes, the whole box is a link.
07:33:16 <int-e> at least the site name is approrpiate. wtf indeed.
07:33:20 <ais523> for some reason, my horizontal mouse wheel doesn't work either
07:35:06 <zzo38> select null and null,null or null,null and 1,null and 0,null or 1,null or 0; -- The result will be NULL|NULL|NULL|0|1|NULL
07:35:20 <zzo38> (At least in SQLite this is the case.)
07:36:26 <Oren> SQL and PHP are both lacking in trivalued logic operators
07:37:18 <int-e> good comment. "The new design looks ugly. Why do people these days redesign their sites to have low information density, large fonts and large grayish blocks and no other detail, just to appeal to the tablet/"modern UI" fad?"
07:37:25 -!- nooga has joined.
07:37:44 <zzo38> Oren: What kind of trivalued logic operators?
07:38:37 <int-e> So apparently all this happened in July, have I really not visited that site in all that time?
07:39:01 <Oren> ones that preserve nullity or test explicitly for false but not null, etc
07:39:25 <zzo38> Oren: SQLite has a IS operator
07:39:43 <Oren> often in these languages the presence of null causes issues unexpectedly
07:40:04 <Oren> becasue the semantics of null are not consistent
07:40:34 <Oren> why is 0 or null null but 1 or null 1
07:41:25 <zzo38> Because "1 or null" means you know it is true; "0 or null" means you don't know.
07:41:43 <zzo38> Because there is no data, so there can be no result.
07:41:50 -!- nooga has quit (Ping timeout: 252 seconds).
07:41:54 <Sgeo> The SL speed limit might be significantly lower than I thought
07:42:38 <Sgeo> Yes, Second Life
07:46:28 <dts> i should play second life
07:47:38 -!- AndoDaan has quit (Read error: Connection reset by peer).
07:48:48 -!- AndoDaan has joined.
07:49:02 <MDude> I've been messing around with OpenSim just now.
07:49:12 <dts> whats that?
07:49:19 <MDude> Guess I could try out Second Life again.
07:50:12 <MDude> OpenSim is a free/open Virtual World server made to be compatible with Second Life viewers.
07:50:34 <MDude> So people can use it to host their own servers.
07:50:57 <MDude> You'll never guess.
07:50:58 <MDude> http://opensimulator.org/
07:51:16 <dts> why would they have a completely unrelated url?
07:51:26 <dts> does it work on ubuntu?
07:51:39 <MDude> open sim = open simulator
07:52:01 <MDude> I dunno, I would think so.
07:52:14 <dts> and yeah, i was kidding
07:52:17 <MDude> It's got a penguin link, that probably means it works with most of the distros.
07:53:34 <MDude> I think I am the jokester and am outplayed.
08:08:30 -!- int-e has set topic: The international hub for esoteric programming language discussion, development and deployment | Beware of ricocheting jokes | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
08:16:06 -!- AndoDaan_ has joined.
08:16:54 <J_Arcane> I did not realize or expect that there were so many fans of the Space Cadet keyboard.
08:18:02 <Bike> it's like, i really need half a dozen mod keys to express myself fully, man,
08:18:14 -!- AndoDaan has quit (Ping timeout: 272 seconds).
08:23:16 <oerjan> it's because they're really MOOD keys
08:23:40 * oerjan looks at topic and ducks
08:24:30 <Oren> whenever i have to use parentheses because of C's sucky grammar
08:24:41 <shachaf> oerjan: what are the ducks doing
08:24:48 <Oren> I will express my self by putting the statement in this form:
08:24:55 <oerjan> shachaf: throwing boomerangs
08:25:10 <Oren> x =( x&0xffff) + (x>>16)
08:25:19 <Oren> with a =( in it
08:25:58 <Oren> because that is how I feel
08:26:20 <Bike> huh, i thought & was higher precedence than +.
08:26:22 <J_Arcane> Ooooh. WASD's custom services apparently extend to doing one's own layout in .svg ...
08:36:04 <lambdabot> LOWI 300820Z 09003KT 060V140 9999 FEW060 SCT160 BKN300 04/03 Q1012 NOSIG
08:37:39 -!- MDude has changed nick to MDream.
08:38:27 <lambdabot> ENVA 300820Z 11007KT CAVOK 02/M06 Q1021 NOSIG RMK WIND 670FT 15013KT
08:44:03 <Oren> Bike: I thought so too
08:47:56 <Bike> probably because && is "multiplication".
08:48:22 <elliott> originally there are no && and you just used &.
08:49:04 <Oren> then they should have made new bitwise and not new logicals
08:49:51 <Oren> x =( x & 0xffff)
09:02:07 -!- _AndoDaan_ has joined.
09:02:39 -!- AndoDaan_ has quit (Ping timeout: 256 seconds).
09:08:16 -!- _AndoDaan_ has quit (Ping timeout: 272 seconds).
09:08:19 -!- AndoDaan_ has joined.
09:10:01 <Oren> can the tcp packets checksum to zero for once in their miserable lives?
09:26:18 -!- nooga has joined.
09:30:48 -!- nooga has quit (Ping timeout: 264 seconds).
09:32:56 -!- Phantom_Hoover has joined.
09:34:40 -!- Dulnes has quit (Quit: Connection closed for inactivity).
09:49:29 <fizzie> Oren: But that would have meant actually changing the meaning of &, and they don't much like changes that invalidate existing code.
09:50:56 -!- AndoDaan_ has quit (Ping timeout: 264 seconds).
09:53:42 -!- shikhout has joined.
09:55:00 <Oren> what the hell is this i thought ip header is 16 bytes long
09:55:22 <b_jonas> wouldn't that be too short?
09:55:36 -!- shikhin has quit (Ping timeout: 240 seconds).
09:56:22 <fizzie> It's variable-length, anyway.
09:56:32 <Oren> hmmm oh i'm counting the struct wrong
09:56:51 <Oren> stupid #ifdef bigendian
09:57:25 <Oren> yeah 20 is right
09:57:34 <Oren> ok tcp should work now
09:57:52 <Oren> and it is 5 am
09:58:20 <b_jonas> what I don't understand is, is the header always at least 24 bytes long?
09:58:44 <b_jonas> or can it be just 20 bytes, with no space for options? and in the latter case, what indicates there's no space allocated for options?
09:58:57 <fizzie> b_jonas: A field in one of the 20 bytes.
09:58:59 <Oren> it is apparently always 20
09:59:06 <fizzie> And it's definitely not always 20.
09:59:23 <fizzie> There's a 4-bit field ("IHL") in the first byte.
09:59:25 <Oren> i haven't encountered any that weren't 20
09:59:28 <fizzie> It gives the header length in words.
09:59:36 <Oren> all the checksums are checking out
10:00:08 <fizzie> Having a non-zero number of options is probably relatively rare, but possible.
10:00:10 <Oren> is an ip packet that contains tcp ever 24
10:01:07 <b_jonas> also iirc they figured out that some of those 20 bytes are almost always unused, so they moved them to optional options in ipv6
10:03:42 -!- dts has changed nick to usandenemies.
10:03:56 -!- usandenemies has changed nick to dts.
10:04:26 <fizzie> They removed the checksum, at least.
10:04:47 <fizzie> Under the assumption that there's always going to be a link-level checksum.
10:05:09 <fizzie> (Meaning the IP header checksum, not protocol-level things there.)
10:06:08 <b_jonas> fizzie: and they moved the 14 bits controlling fragmentation to optional headers
10:07:18 <Oren> thank god im not required to support fragmented packets
10:07:31 <Oren> that would be a nightmare
10:07:42 -!- nooga has joined.
10:08:09 <b_jonas> mind you, removing the fragmentation info from the ip header not only conserves space, but also makes sense from a logical point:
10:08:29 <b_jonas> the ip header is supposed to contain stuff that intermediate routers are supposed to examine, not only the destination,
10:08:45 <b_jonas> and routers don't have to examine the fragment info, because it's the destination that assembles the fragments.
10:09:46 <Oren> holy fuck i actually got everyhting to work
10:10:15 <Oren> it is5:09 and i can just upload my code and go home
10:10:28 <Oren> i am writing a packetswicth/NAT
10:10:59 <Oren> course project worth 20% of my grade
10:11:54 <Oren> as soon as i've handed everything in i'm gonna go eat breakfast
10:20:16 -!- Oren has quit (Ping timeout: 246 seconds).
10:22:11 <fizzie> Ooh, half a gigabyte was enough to build that SciRuby matrix library. (Just barely, but still.)
10:29:02 <oerjan> are you trying to fix zemhill?
10:38:57 <fizzie> oerjan: Yes. Well, to move it to its new VPS, first.
10:39:14 <fizzie> There's also a new version of the matrix lib, so maybe it'll also get fixed while doing that.
10:39:32 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
10:39:37 -!- hjulle has joined.
10:39:46 -!- zemhill has quit (Remote host closed the connection).
10:40:05 <fizzie> Come to think of it, let's turn it off for a moment there.
10:40:08 <fizzie> Also I need some breakfast.
10:49:35 -!- MoALTz_ has quit (Quit: Leaving).
11:11:32 <fizzie> I don't get it. I installed the nmatrix thing, but now it's not there.
11:14:23 <fizzie> nmatrix.rb:444:in `method_missing': undefined method `-@' for #<NMatrix:0x00000001964960> (NoMethodError)
11:14:29 <fizzie> Perhaps they've changed the interface.
11:16:32 <fizzie> Apparently the unary minus no longer exists. Or something.
11:17:14 -!- Oren has joined.
11:18:23 -!- kline has joined.
11:19:59 -!- zemhill has joined.
11:20:08 <fizzie> Somehow I doubt it'll work that easily.
11:20:28 <fizzie> !ztest (>)*8(>[-.])*21 (go ahead, crash like you mean it)*0
11:20:28 <zemhill> fizzie: Program name ((>)*8(>[-.])*21) is restricted to characters in [a-zA-Z0-9_-], sorry.
11:20:44 <fizzie> !ztest that_was_embarrassing (>)*8(>[-.])*21 (go ahead, crash like you mean it)*0
11:20:44 <zemhill> fizzie.that_was_embarrassing: points -19.76, score 8.31, rank 47/47
11:20:45 <zemhill> fizzie: I broke down! Ask fizzie to help! The details are in the log! #<NoMethodError: undefined method `private' for #<Server:0x000000021383a8>>
11:20:45 -!- zemhill has quit (Client Quit).
11:23:07 <fizzie> How has that ever worked. That can't have ever worked.
11:24:51 -!- zemhill has joined.
11:25:03 <fizzie> Seems that I had somehow managed to move a thing from one place to another while adding documentation comments and nothing else.
11:25:13 <fizzie> !ztest it_keeps_happening (>)*8(>[-.])*21 (go ahead, crash like you mean it)*0
11:25:13 <zemhill> fizzie.it_keeps_happening: points -19.76, score 8.31, rank 47/47
11:25:52 <fizzie> !zjoust will_the_repository_blow_up (>)*8(>[-.])*21 (go ahead, crash like you mean it)*0
11:25:52 <zemhill> fizzie: I broke down! Ask fizzie to help! The details are in the log! #<RuntimeError: git commit -q -m Replacing ais523.dulnes_example by fizzie.will_the_repository_blow_up (in /home/bfjoust/bfjoust/hill) failed: 128>
11:25:52 -!- zemhill has quit (Client Quit).
11:26:21 <ais523> now I'm trying to remember what 128 means as an exit code
11:26:31 <ais523> my brain's translating it to "killed by signal 0" but that doesn't make sense
11:27:28 <fizzie> In this case, it means I didn't remember to do git config user.{name,email} for the bfjoust account on the new server.
11:27:36 <fizzie> It did the git "Please tell me who you are" error.
11:27:51 -!- MoALTz has joined.
11:29:52 -!- zemhill has joined.
11:30:03 <fizzie> !zjoust will_the_repository_blow_up <
11:30:03 <zemhill> fizzie.will_the_repository_blow_up: points -46.00, score 0.00, rank 47/47 (--)
11:31:00 <fizzie> The web reports seem to have not updated.
11:35:17 <b_jonas> oh great! apparently AT_FDCWD has the value -100 . (I thought for some reason that it was -2) That's much better.
11:35:27 <fizzie> Well. It's back online. I don't guarantee it will work.
11:36:42 <zemhill> fizzie: I do #{command}; see http://zem.fi/bfjoust/ for more information.
11:36:42 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
11:37:08 <fizzie> zemhill: By #{command} I kind of meant you'd substitute in the command.
11:38:03 -!- zemhill has quit (Remote host closed the connection).
11:41:46 -!- zemhill has joined.
11:41:49 <zemhill> fizzie: I do !zjoust; see http://zem.fi/bfjoust/ for more information.
11:41:49 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
11:42:33 <fizzie> There. I changed the command (even though having a single-command submission to two separate hills was kind of... #esoterician), but kept the ! prefix since it only responds to the command (and !help).
11:42:40 <fizzie> Didn't want to tie up a whole new prefix for that.
11:43:02 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
11:48:43 <fizzie> thutubot's could possible be repurposed.
11:49:41 <FireFly> Can I reserve '='? My other two bot prefixes have alredy been stolen
11:49:44 <int-e> / is still free ;-)
11:50:41 <ais523> /I don't see what the problem is
11:51:18 <int-e> /server would make an excellent main command for a bot.
11:52:07 <b_jonas> or how about color codes as bot prefixes?
11:53:18 <fizzie> "botname:" as a prefix is the boring, yet practical choice.
11:53:52 <b_jonas> fizzie: yeah, that's good for full form, but my problem is that I want a bot with multiple commands, and "botname command: " is a bit too long
11:54:11 <FireFly> IMO all bots should support that, if only to make it easy to disambiguate multiple instances of the same bot
11:54:30 <fizzie> I would have expected that to be "botname: command ..." so that many people can tab-complete it.
11:54:32 <int-e> lambdabot: > 1 -- I forgot whether she can do that
11:54:55 -!- hjulle has quit (Ping timeout: 256 seconds).
11:55:02 <b_jonas> lambdabot: @run 2+2 -- she can
11:55:06 <int-e> oh. right, > is too special.
11:55:07 <fizzie> zemhill doesn't do the name prefix either. Should maybe add it at some point.
11:55:25 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
11:55:29 -!- Patashu has quit (Ping timeout: 272 seconds).
11:56:01 <FireFly> I'd expect the 'nick: ' to be used *as* a prefix rather than in addition to one, but oh well
11:56:46 <zzo38> FireFly: Yes you could do it that way; it would help too. (Such a prefix then is unneeded when the message is private)
11:56:53 <ais523> I approve of this command
11:56:57 <b_jonas> FireFly: jevalbot tries to do both, but the syntax is completely fucked up
11:57:22 -!- evalj has joined.
11:57:24 <ais523> there's got to be a story behind it, which might be interesting
11:57:27 <FireFly> I've never learned jevalbot's syntax for non-eval commands
11:57:30 <ais523> but "someone thought it would be funny" is enough
11:57:42 <b_jonas> evalj: |.'with just a nick, it uses the default command'
11:57:43 <evalj> b_jonas: dnammoc tluafed eht sesu ti ,kcin a tsuj htiw
11:58:03 <b_jonas> evalj, ping: with a nick and command, it uses that command
11:58:04 <evalj> b_jonas, pong: with a nick and command, it uses that command
11:58:33 <b_jonas> ] 'there are some shortcuts, both a short one and ones with the nick, so you often don't have to type the command'
11:58:34 <evalj> b_jonas: |open quote
11:58:34 <evalj> b_jonas: | 'there are some shortcuts, both a short one and ones with the nick, so you often don't have to type the command'
11:58:44 <b_jonas> ] 'there are some shortcuts, both a short one and ones with the nick, so you often don''t have to type the command' Nb. gtfo
11:58:45 <oerjan> FireFly: note that lambdabot has, in fact, a @@ command
11:58:45 <evalj> b_jonas: |spelling error
11:58:45 <evalj> b_jonas: | 'there are some shortcuts, both a short one and ones with the nick, so you often don''t have to type the command' Nb. gtfo
11:58:54 <b_jonas> ] 'there are some shortcuts, both a short one and ones with the nick, so you often don''t have to type the command' NB. gtfo
11:58:55 <evalj> b_jonas: there are some shortcuts, both a short one and ones with the nick, so you often don't have to type the command
11:59:29 <FireFly> [ 'isn''t jeval also in here?'
11:59:29 <j-bot> FireFly: isn't jeval also in here?
11:59:55 <FireFly> Always good to have a backup, I guess
12:00:09 <b_jonas> where it's fucked up is (a) what combinations of punctuations around the nick and command it accepts, (b) the syntax behaving inconsistently for commands in private message, and (c) how it doesn't accept a command after a shortcut punctuation like '] ping: foo'
12:00:10 <zzo38> If you are using such bot commands a lot you can create a macro in your client.
12:00:24 <b_jonas> FireFly: there's no written help, only me and the source code
12:00:39 <evalj> b_jonas, jevalbot source is http://www.math.bme.hu/~ambrus/pu/jevalbot.tgz
12:01:43 <lambdabot> DzLx 5AYz: Y0u (4n /\/\4K3 teh Id /\/\onAD SomEWh4+ bEt+er 83h4V3D 8y wrAPpin9 i+ IN zupEr3g0T.
12:02:12 <b_jonas> there's some commands for manipulating sessions (clearing, copying, changing to a shared session), and a command for evaluating mutli-line input
12:03:09 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
12:04:05 <lambdabot> tEs$ier $aYs: 4FtER Th3 LAzT N3\/\/bi35 HeAd EXp|0DED 7ryin9 7o Re4D E\/Ery7|-|Ing On t|-|A7 /\/\oN4d |inx +H3r3 W4s a LO7 oph papeR\/\/Orx. \/\/E'D |IxE too av0id DoiNg tH4+ Ag4in.
12:08:16 <b_jonas> next time I make an irc bot that responds to commands, I'll be sure to give it a syntax that is insane and inconsistent in ways different from that of evalj
12:08:32 -!- hjulle has joined.
12:09:08 <b_jonas> FireFly: oh, and one more problem with evalj is that at one point, when I ran it under the nick jeval, "jeval" was both a command and a nick, making the syntax sort of ambiguous
12:09:49 <b_jonas> mind you, it's the default command, but still.
12:10:54 <b_jonas> that means if you sent a private message saying 'jeval: somecommand= foobar' it isn't clear whether 'somecommand=' is a command or an argument (I think it's the latter, but I'm not sure)
12:18:39 <evalj> b_jonas: ping = argument
12:18:44 <evalj> b_jonas, pong: argument
12:18:50 <evalj> b_jonas, pong: argument
12:18:56 <evalj> b_jonas, pong: argument
12:19:16 <b_jonas> seriously, it's nonsense, I'll have to figure out different bad syntax next time
12:24:37 <Oren> what font do you use in terminal
12:25:10 <b_jonas> http://www.math.bme.hu/~ambrus/pu/fecupboard20-c.pcf.gz Fecupboard20 (free X11 bitmap font with 20x10 pixel character cell, easily distinguishable characters, great for terminals and programming, has all characters in iso-8895-1 and 8859-2 and more)
12:27:25 <Oren> I am using an unorthodox font: http://ctrlv.in/467600
12:28:04 <Oren> but i am wondering what fonts are actually readable
12:28:08 <Bike> i just use the default comic sans.
12:28:43 <shachaf> I tried to set my terminal font to Comic Sans once but it didn't work very well.
12:28:49 <ais523> how often do people use Λ anyway?
12:28:55 <ais523> also, I don't even have Comic Sans insalled
12:28:55 <shachaf> Someone should make a monospace version.
12:29:02 <b_jonas> well, mine is also sort of unorthodox
12:29:31 <shachaf> I assume Greek speakers use it a lot.
12:29:34 <b_jonas> it has some characters marked with extra dots when I want them to be more easy to distinguish from similar-looking more common characters
12:30:03 <Oren> where do you put fonts on linux again?
12:30:23 <b_jonas> Oren: user-local or system?
12:30:35 <Oren> whatever its my machine anyway
12:31:53 <b_jonas> Oren: for user-local, you put them in ~/.fonts , however, for a bitmap font (like mine) you may have to change the fontconfig configurations so it doesn't just skip bitmap fonts
12:32:13 <b_jonas> for system, I put them in /usr/share/fonts/X11/misc and the same applies
12:32:27 <b_jonas> the fontconfig configurations can also be changed globally or user-locally,
12:33:06 <b_jonas> globally in /etc/fonts , locally in ~/.fonts.conf but be careful because some gui apps may rewrite the latter
12:33:14 <b_jonas> so basically, it's complicated
12:34:07 <b_jonas> also, after installing fonts, you may have to run some commands so they're recognized,
12:34:15 -!- oerjan has quit (Quit: Later).
12:34:19 <FireFly> Envy Code R is quite readable
12:34:31 <b_jonas> specifically, for system fonts, sudo fc-cache
12:34:38 <FireFly> Oren: what font is that, anyway?
12:34:59 <Oren> TakaoMincho Bold
12:35:05 <b_jonas> and for bitmap fonts used through the old X11 bitmap font interface (not through fontconfig or other advanced stuff) xset fp rehash
12:35:16 <Oren> it's serifed but monospace a weird combo
12:35:29 <b_jonas> for local font installs, you may have to run fc-cache too
12:38:18 <b_jonas> Oren: my font is sort of half-seriffed
12:38:22 <b_jonas> some serifs are present, some aren't
12:40:47 <FireFly> Λ ∧ look somewhat similar to me
12:51:17 <HackEgo> [wiki] [[Talk:Boat]] N http://esolangs.org/w/index.php?oldid=41259 * Zzo38 * (+102) Created page with "What does "xand" mean? --~~~~"
12:53:42 <Oren> i got it working
12:54:08 <Oren> http://ctrlv.in/467603
12:58:55 <Oren> the bold isn't the same width as the regular
12:59:13 <Oren> causes a bit of squeezing
13:04:20 <int-e> "xand" - both, but not both.
13:04:24 <Oren> once you disable bold it looks very good
13:05:17 <Oren> if xor is [0,1,1,0] then xand should be [1,0,0,1]
13:06:14 <Oren> because xor means 1,1 -> 0 instead of 1
13:06:34 <Oren> so xand should mean 0,0 ->1 instead of 0
13:06:40 <int-e> and is [0,0,0,1], so xand should be [0,0,0,0]
13:07:31 <Oren> or that, tho it makes it unuseful
13:07:36 <int-e> I know [1,0,0,1] as equality or nxor
13:08:09 <Oren> the !=! operator
13:08:37 <FireFly> And I know [0,0,0,1] as multiplication
13:08:53 <int-e> inequality test -- returns the xnand of two values <-- this may shed some light on the intended meaning
13:09:26 <int-e> though I would argue that xnand is really just nand if you read the x as "exclusive"
13:11:05 <Oren> and i have invented the =( operator
13:11:38 <Oren> and the !! operator is common
13:14:04 <Oren> nand is an interesting operator because although it is the basis of circuitry
13:14:22 <Oren> most algol based languages do not directly support it
13:14:42 <int-e> do they support nor?
13:14:48 <Oren> in C i cannot go a !&& b
13:15:21 <Oren> I have to use parentheses
13:16:05 <Oren> or use the distributive laws and do !a || !b
13:17:56 <Oren> !&& could be added with no ambiguity
13:18:03 <Oren> they just didnt bother
13:18:06 <shachaf> what if i'm an intuitionist
13:18:59 -!- mig22 has joined.
13:21:05 <Oren> and bitwise ~& should be an operator
13:22:12 <int-e> shachaf: anyway, rather than convincing you I'd then attempt not not convincing you.
13:26:36 -!- ais523 has quit.
13:30:50 <int-e> shachaf: oh and the exclamation mark was a C negation.
13:32:17 -!- ZombieAlive has quit (Ping timeout: 245 seconds).
13:36:04 -!- mig22 has quit (Ping timeout: 245 seconds).
13:36:15 <Bike> what if i'm not unintuitionist
13:36:46 -!- oonbotti2 has quit (Remote host closed the connection).
13:37:15 -!- mig22 has joined.
13:37:57 <Oren> aha! I have invented the <! operator. it means logical nor
13:38:26 <Bike> shouldn't that be !||.
13:39:03 <Oren> tge !|| is not accepted by C. <! is stanard C
13:39:17 <Bike> #define !|| <! "problem solved"
13:39:51 <Bike> i actually have no idea if that's legit, oh well
13:39:51 <Oren> 0<!0 = 0<1 = 1
13:41:33 <FireFly> the companion of --> "goes to"
13:41:33 <Bike> weird that it's asymmetric.
13:42:49 <Oren> `! c printf("%d %d %d %d\n",0<!0,0<!1,1<!0,1<!1);
13:43:01 <Bike> `run echo 'printf("%d %d %d %d\n",0<!0,0<!1,1<!0,1<!1);' | gcc - -c -Wall
13:43:19 <HackEgo> gcc: error: -E or -x required when input is from standard input
13:43:19 <FireFly> Might help to define `main`
13:43:34 <Bike> that was the duh.
13:43:52 <Oren> `! c int main(void){ printf("%d %d %d %d\n",0<!0,0<!1,1<!0,1<!1);}
13:44:30 <fizzie> `! c int main(void){ printf("%d %d %d %d\\n",0<!0,0<!1,1<!0,1<!1);}
13:44:35 <fizzie> \n turns into a real newline (for preprocessor stuff), which makes the string literal bad.
13:45:29 <Bike> `run echo 'int main(void) { printf("%d %d %d %d\n", 0<!0, 0<! 1, 1<!0, 1<!1); }' | gcc - -x c -Wall
13:45:49 <HackEgo> gcc: warning: ‘-x c’ after last input file has no effect \ gcc: error: -E or -x required when input is from standard input
13:45:49 <Oren> so yah. <! is the nor operator
13:45:49 <Bike> ffs, command ordering
13:45:49 <Bike> `run echo 'int main(void) { printf("%d %d %d %d\n", 0<!0, 0<! 1, 1<!0, 1<!1); }' | gcc -Wall -x c -
13:45:49 <HackEgo> <stdin>: In function ‘main’: \ <stdin>:1:1: warning: implicit declaration of function ‘printf’ [-Wimplicit-function-declaration] \ <stdin>:1:18: warning: incompatible implicit declaration of built-in function ‘printf’ [enabled by default] \ <stdin>:1:1: warning: control reaches end of non-void function [-Wreturn-type]
13:45:57 <Bike> such problems.
13:46:16 <Bike> `run echo '#include <stdio.h>\nint main(void) { return printf("%d %d %d %d\n", 0<!0, 0<! 1, 1<!0, 1<!1); }' | gcc -Wall -x c -
13:46:17 <HackEgo> <stdin>:1:19: warning: extra tokens at end of #include directive [enabled by default] \ /usr/lib/gcc/x86_64-linux-gnu/4.7/../../../x86_64-linux-gnu/crt1.o: In function `_start': \ (.text+0x20): undefined reference to `main' \ collect2: error: ld returned 1 exit status
13:46:49 <Bike> oh, so \n is a c int thing.
13:46:53 <Bike> well. whatever.
13:47:20 <Oren> `run echo '#include <stdio.h>\nint main(void) { return printf("%d %d %d %d\\n", 0<!0, 0<! 1, 1<!0, 1<!1); }' | gcc -Wall -x c -
13:47:33 <HackEgo> <stdin>:1:19: warning: extra tokens at end of #include directive [enabled by default] \ /usr/lib/gcc/x86_64-linux-gnu/4.7/../../../x86_64-linux-gnu/crt1.o: In function `_start': \ (.text+0x20): undefined reference to `main' \ collect2: error: ld returned 1 exit status
13:47:49 <Oren> `! c int main(void){ printf("%d %d %d %d\\n",0<!0,0<!1,1<!0,1<!1);}
13:48:20 <Oren> now is there a nand operator?
13:48:57 <Oren> `! c int main(void){ printf("%d %d %d %d\\n",0<=!0,0<=!1,1<=!0,1<=!1);}
13:49:51 <Oren> the c language can thus be extended without technically extending it
13:50:01 <Oren> if that makes any sense
13:55:47 -!- mig22 has quit (Remote host closed the connection).
14:01:19 <Oren> nxor would be !=!
14:01:49 <b_jonas> no, I mean that mysterious "xand" operator is nxor
14:02:55 <Bike> xnor is also ==, isn't it.
14:03:14 <Bike> i guess if you only have 0s and 1s.
14:06:47 <Oren> what would ^~ do?
14:07:42 <Oren> `! c int main(void){ printf("%d %d %d %d\\n",0^~0,0^~1,1^~0,1^~1);}
14:07:59 <Oren> `! c int main(void){ printf("%x %x %x %x\\n",0^~0,0^~1,1^~0,1^~1);}
14:08:01 <HackEgo> ffffffff fffffffe fffffffe ffffffff
14:08:55 <Oren> so ^~ is 1 on each bit that the two operands are equal on
14:10:57 <EvanR> which is the same as xnor
14:11:16 <EvanR> which is not . xor
14:11:43 <EvanR> in this case the nor is happening on one of the inputs, i think this is called "bubble migration" on diagrams
14:17:40 <Oren> oh, how about unary -!! this operator transforms C ints to forth bools
14:18:25 <Oren> `! c int main(void){ printf("%x %x %x %x\\n",-!!0,-!!(-1),-!!1,-!!2);}
14:18:28 <HackEgo> 0 ffffffff ffffffff ffffffff
14:19:25 -!- S1 has joined.
14:19:58 <Oren> I should put a list of these nonstandard C 'operators' somewhere
14:55:03 -!- S1 has quit (Quit: S1).
14:55:35 -!- FreeFull has quit.
14:59:32 -!- mig22 has joined.
15:09:17 -!- GeekDude has joined.
15:18:22 -!- FreeFull has joined.
15:23:21 -!- mig22 has quit (Ping timeout: 264 seconds).
15:24:04 -!- mroman__ has joined.
15:34:56 <EvanR> hmm there should be a list on the wiki of non brainfuck clones
15:36:34 <mroman__> there should be a wiki of non clones of anything
15:40:09 -!- sebbu has quit (Ping timeout: 264 seconds).
15:42:36 -!- sebbu has joined.
15:42:36 -!- sebbu has quit (Changing host).
15:42:36 -!- sebbu has joined.
15:43:08 <FreeFull> Has anyone here done programming in K or a similar language?
15:44:35 -!- nyuszika7h has joined.
15:44:49 <nyuszika7h> I'm in the process of making a 99 bottles program in dc! \o/
15:44:51 <nyuszika7h> nyuszika7h@cadoth ~ $ dc -e '?dsn[dn[ bottle]n[[s]n]sp1!=p]dsdx[ of beer on the wall, ]nlnldx[ of beer.]p'
15:44:53 <nyuszika7h> 99 bottles of beer on the wall, 99 bottles of beer.
15:49:16 <FireFly> FreeFull: I'm familiar with J
15:50:50 <FreeFull> Yeah, J is similar but has some fundamental differences
15:51:20 <FreeFull> How long did it take for you to build up an intuition on how to work with it?
15:52:29 <Taneb> FreeFull, I've used APL a little
15:53:47 <FreeFull> Taneb: That's what I wanted to try first, but I didn't want to deal with getting the keyboard layout working
15:54:00 <Taneb> FreeFull, the emacs mode is pretty good
15:54:25 -!- shikhin has joined.
15:54:32 <FreeFull> I'd probably have to install emacs then
15:57:23 -!- shikhout has quit (Ping timeout: 250 seconds).
15:57:56 <FireFly> FreeFull: I don't really remember. I've been using it on-and-off for a couple of years, learning a bit at a time
15:58:09 <FireFly> Rather than trying to learn it properly over a shorter timespan
15:58:10 -!- cluid has joined.
15:59:09 <FireFly> If you're curious about J/K/APL, there's #jsoftware (which, despite the name, kind-of acts as a catch-all for all three)
15:59:42 <FreeFull> I was hoping there was some sort of IRC channel
16:01:52 -!- EgoBot has quit (Ping timeout: 245 seconds).
16:03:15 -!- EgoBot has joined.
16:04:23 <cluid> I was wondering about CA simulating other CA
16:05:42 <cluid> do you think there is a way to encode rule X in rule Y where each cell of a rule X pattern is encoded as like 7 cells together and 15 rule Y steps corresponds to one rule X iteration
16:11:49 <cluid> does it make sense
16:11:55 <cluid> and is there any chance of this being possible
16:12:14 <cluid> thinking of 1D CAs
16:15:37 <FreeFull> cluid: You probably can do something in 1D with the turing-complete CAs
16:16:02 <FreeFull> As far as 2D goes, I've seen a simulation of the game of life inside the game of life
16:16:25 <cluid> well the reason i cae up with this idea is to get away from the standard TC construction
16:17:05 <cluid> i dont like the infinite setup part, so I was interesting on CAs simulator other CAs with a single initial state that's a constant multiple the size of the state it simulates
16:17:25 <cluid> I saw that meta-GoL too, that's so cool! That's exactly the sort of thing I mean
16:19:56 <cluid> it is a bit difficult to search for 1D simulators
16:20:05 <cluid> i dont really know how to approach it
16:20:10 <cluid> it may not be possible at all
16:20:21 <cluid> you'd need to find repeating patterns
16:23:39 -!- FreeFull has quit (Quit: Rebooting).
16:25:16 -!- FreeFull has joined.
16:26:31 <EvanR> cluid: i dont like TC either
16:27:00 <cluid> btw i read the log and I agree about the non-bf thing
16:27:14 <cluid> maybe it could be created automatically from the BF list
16:27:33 <EvanR> mostly probably, but some of them dont explicitly say they are brainfuck clones
16:27:42 <EvanR> you have to waste time reading through the description to realize it ;)
16:28:16 <EvanR> which in itself may be a good idea for a esolang, its brainfuck but you dont know it unless you try to use it
16:28:33 <cluid> brainfuckrolled...
16:29:23 <b_jonas> EvanR: if you find such a thing, tell us and we'll slap a category on them
16:29:58 <EvanR> b_jonas: you mean bf clones that dont say so?
16:30:37 <EvanR> ok, this one does have the bf category. at the bottom
16:30:42 <cluid> well i think they should be categorize
16:30:53 <EvanR> most of them say so in the very first sentence
16:31:09 <EvanR> http://esolangs.org/wiki/Arrow
16:31:12 <cluid> so does anyone have ideas on the CA simulation idea?
16:32:59 <HackEgo> [wiki] [[Dimensions]] http://esolangs.org/w/index.php?diff=41260&oldid=41203 * B jonas * (+35)
16:35:35 -!- TodPunk has quit (Ping timeout: 258 seconds).
16:40:54 -!- S1 has joined.
16:55:39 -!- MDream has changed nick to MDude.
17:02:20 <Taneb> Some fractal dimension?
17:10:38 <Bike> cluid: i'd worry about information transfer. like, the majority problem isn't easy...
17:12:50 <Taneb> nyuszika7h, nice one :)
17:13:01 <nyuszika7h> I have no idea why I have to hardcode printing for 0 though
17:13:44 <nyuszika7h> if I do !< (>=) instead of < then it loops forever on the last pair of lyrics
17:37:23 <lambdabot> ESSA 301720Z 36002KT CAVOK M00/M01 Q1030 R01L/19//95 R08/15//95 R01R/19//95 NOSIG
17:40:07 <cluid> Bike, I guess to simulate majority you'd need a CA which goes out in both directions
17:40:20 <cluid> buta CA that only goes out to the right might still be able to simulate others that do that?
18:21:16 -!- TodPunk has joined.
18:21:32 -!- Oren has quit (Ping timeout: 246 seconds).
18:32:21 -!- S1 has quit (Quit: S1).
18:47:13 -!- Dulnes has joined.
18:54:39 <Dulnes> €]©_]®_ ©$`_ € °€®￦{€¢_ ]}>«]¢ >￦_€_ °_>>_<€
18:55:09 <Dulnes> Thats what happens when you memorise your key pad and use those letters instead
18:57:12 <Dulnes> ~=_<>{ is technically qwerty
19:00:25 <Dulnes> So if you ever wanted to convert your A-Z to $-¿
19:00:45 <Dulnes> Thats how you would go about it
19:06:20 -!- dts has quit (Ping timeout: 250 seconds).
19:08:17 <Dulnes> I assume most of you are asleep
19:22:21 <HackEgo> [wiki] [[POGAACK]] http://esolangs.org/w/index.php?diff=41261&oldid=34732 * SuperJedi224 * (+11)
19:25:37 <Dulnes> Im so done with this language
19:27:57 <J_Arcane> en halua lisää aivovittun kieliä.
19:29:25 -!- Oren has joined.
19:29:37 <FireFly> Dulnes: why would most of us be asleep?
19:33:44 <Dulnes> http://esolangs.org/wiki/%E2%99%A6 what is the use of this page¿
19:35:09 -!- S1 has joined.
19:43:14 <cluid> there is a weird .exe to decrypt it
19:43:26 -!- cluid has quit (Quit: Leaving).
19:45:46 -!- nooga has quit (Ping timeout: 265 seconds).
19:50:56 <Bike> is "errno = 0; some_call_that_sets_errno(); if (errno != 0) { ...}" reasonable? the call returns success on certain error conditions.
19:51:14 -!- test[dulnes] has joined.
19:51:54 <pikhq_> Assuming that it doesn't mutate errno except on error, that is perfectly reasonable.
19:52:07 <pikhq_> And is required for some parts of libc.
19:52:09 <elliott> trick question: it's unreasonable because errno is unreasonable
19:52:24 <Bike> ok, well, yes. i'm trying to work around unreasonability.
19:52:36 <pikhq_> errno is not exactly a nice thing, yes.
19:52:38 <Bike> honestly i'm still not over the silliness of returning a success value but setting errno anyway.
19:52:50 <pikhq_> Buuut, that's C for ya.
19:53:27 <Bike> it's a posix function so i guess i can assume it doesn't mutate errno otherwise.
19:53:28 <myname> so, anybody here ever used yi and minds telling me how awesome it is so i am willing to build like a dozen dependencies?
19:53:59 <Bike> fscanf. which is actually libc probably.
19:54:07 <pikhq_> And yes. C and POSIX functions as a rule only change errno on error.
19:54:54 <Bike> if you try to scan in an integer that's too big it just returns maxint. does set errno though.
19:55:24 <Bike> i'd rather it like, failed, but oh well.
19:55:25 <Dulnes> The pixelation on the 3ds browser is awful
19:55:43 <Bike> actually i'd really rather there be a dedicated read integer function instead of using this weird printf string thing. o well
19:57:47 -!- test[dulnes] has quit (Ping timeout: 246 seconds).
20:00:26 <HackEgo> [wiki] [[User talk:SuperJedi224]] N http://esolangs.org/w/index.php?oldid=41262 * SuperJedi224 * (+191) /* A (fairly trivial) Thue-Brainf*** polyglot */ new section
20:00:55 <HackEgo> [wiki] [[User talk:SuperJedi224]] http://esolangs.org/w/index.php?diff=41263&oldid=41262 * SuperJedi224 * (+31) /* A (fairly trivial) Thue-Brainf*** polyglot */
20:01:09 <HackEgo> [wiki] [[User talk:SuperJedi224]] http://esolangs.org/w/index.php?diff=41264&oldid=41263 * SuperJedi224 * (-2) /* A (fairly trivial) Thue-Brainf*** polyglot */
20:01:44 -!- Patashu has joined.
20:02:03 <HackEgo> [wiki] [[User talk:SuperJedi224]] http://esolangs.org/w/index.php?diff=41265&oldid=41264 * SuperJedi224 * (+4)
20:02:44 <Dulnes> I feel useless im gonna go play lOZ
20:02:46 <HackEgo> [wiki] [[User talk:SuperJedi224]] http://esolangs.org/w/index.php?diff=41266&oldid=41265 * SuperJedi224 * (-17) /* A (fairly trivial) Thue-Brainf*** polyglot */
20:06:00 -!- dts has joined.
20:11:12 -!- Sauvin has changed nick to EisenHerz.
20:13:42 -!- Phantom_Hoover has joined.
20:13:59 <elliott> not really many options for that in C
20:22:17 -!- Oren has quit (Ping timeout: 246 seconds).
20:24:49 -!- Patashu has quit (Ping timeout: 264 seconds).
20:29:11 -!- ZombieAlive has joined.
20:32:04 <Phantom_Hoover> note to self: actually remember when st andrew's day is
20:45:03 <Bike> elliott: fscanf returns the number of objects scanned. on overflow with "%d" it could return zero and leave the pointer undefined
20:46:09 -!- EvanR has quit (Ping timeout: 252 seconds).
20:58:43 -!- Oren has joined.
21:07:00 <zzo38> But doesn't it only use a single character lookahead or something like that? If so, that won't work. If it uses extended lookahead then that idea could work.
21:11:02 <Bike> doesn't what use single character lookahead
21:11:54 -!- boily has joined.
21:14:47 -!- mroman__ has quit (Ping timeout: 246 seconds).
21:36:51 -!- boily has quit (Quit: INCONVENIENT CHICKEN).
21:45:40 <Oren> i was excited cause i thought my aunt wendy was coming over but it's a different wendy
21:46:15 <Oren> wendy from guatemala apparently
21:46:39 <fizzie> pikhq_: It's not true that C library functions only change errno on error.
21:46:44 <Oren> anyway i had an idea for a visual programming langugaes
21:46:48 <fizzie> Or, it might be true in practice, but it's not true in theory.
21:47:20 <fizzie> "The value of errno may be set to nonzero by a library function call whether or not there is an error, provided the use of errno is not documented in the description of the function in this International Standard." (C11 7.5p3)
21:47:41 <pikhq_> Only some of them are specified to actually not mutate errno.
21:47:48 <fizzie> And most of the functions don't so document it. The ones where you can't distinguish an error otherwise do, though.
21:48:00 <Oren> C is getting on in age
21:49:13 <Oren> so what doyou do, I guess you look up each particular function's behaviour?
21:49:32 <pikhq_> I have the POSIX standard bookmarked.
21:49:56 <fizzie> I should have, because I Google the URL probably at least once a week.
21:50:28 <Oren> I usually just use man
21:50:46 <Oren> i have all the man pages installed
21:51:24 <Oren> i dunno how they compare to the POSIX standards tho
21:52:26 <Oren> so for example
21:52:35 <fizzie> They sometimes can guarantee things POSIX doesn't.
21:54:04 -!- shikhout has joined.
21:54:09 * Oren does man 3 printf to check
21:54:38 <Oren> the man page gives wrnings about non-posix guaranteed stuff
21:55:35 <fizzie> There's also a set of "POSIX" man pages, though.
21:56:03 <fizzie> With special permission, even: http://lwn.net/Articles/581858/
21:57:04 -!- shikhin has quit (Ping timeout: 250 seconds).
21:57:19 <fizzie> 'manpages-posix' in debuntu and so on.
21:57:59 <Oren> yeah i have that
21:58:09 -!- EvanR has joined.
21:58:09 <fizzie> They're in the "3p" section, then.
21:58:28 <Oren> i intalled all the packedages with manpages in the name
21:58:33 -!- EvanR has changed nick to Guest37103.
21:59:27 * Oren tries man 3p printf and sees a "POSIX Programmer's Manual"
22:03:20 <fizzie> It's handy. (Though I still use the official web version of the standard for some reason.)
22:03:54 <Oren> well it does depend on whether your usual workflow uses the shell or an ide
22:04:36 <Oren> for C programming i use the shell for my entire workflow
22:05:22 <Oren> specifically midnight commander
22:08:13 <Oren> but many people instead use ides for C
22:13:54 <Bike> how stupid/usable is doing struct disjoint_union { int flag; char[] data; } if I don't have the structs of the union beforehand
22:15:12 <Oren> problem isyou may want to use sizeof on it
22:15:25 <Oren> and it will be an "incomplete type"
22:16:19 <Bike> and no arrays, yes.
22:19:37 -!- dts has quit (Ping timeout: 240 seconds).
22:20:09 <elliott> pikhq_: fizzie: I think it makes sense to let other functions set errno, insofar as errno makes sense
22:20:13 <elliott> since they probably make calls themselves
22:20:31 -!- GeekDude has changed nick to GeekAfk.
22:20:59 <pikhq_> elliott: Note that the way to not modify errno would be "int tmp_errno = errno;" at the start, and then "errno = tmp_errno;" at the end...
22:21:15 <pikhq_> It's not a particularly burdensome requirement to meet.
22:21:24 <elliott> pikhq_: yeah but that's not worse is better enough for c/posix :p
22:21:34 <elliott> it's, like, effort to encapsulate things
22:22:28 <pikhq_> And these *are* the same people that came up with errno in the first place.
22:22:48 <pikhq_> And then had to go through contortions to make it work with threads.
22:23:01 <Bike> i refuse to think about that
22:23:22 <fizzie> (Oh, Dominosa closed, and I totally was going to still have a look if I could do something about it.)
22:23:24 <Bike> seriously though, is there any good way to do what i want to do or should i give up and use nasm
22:23:32 <pikhq_> The actual behavior is not *as* bad as you might think.
22:24:41 -!- Dulnes has quit (Quit: Connection closed for inactivity).
22:25:11 <Oren> you need to know the maximum size of the structs of the union in order to make it work
22:25:43 <elliott> you can manipulate it through pointers
22:26:14 <pikhq_> errno is "just" a macro, which calls a function that returns a pointer to an int, and then dereferences said pointer.
22:26:23 <Oren> well yeah. you could make a union like struct {int type void*data}
22:26:46 <pikhq_> (thereby giving you thread-local errno)
22:30:25 -!- GeekAfk has changed nick to GeekDude.
22:32:08 <elliott> Oren: that moves where you put the tag, though
22:32:57 <Oren> bork the whole thing with a int* then
22:33:29 <Oren> the tag is in the same place as the union
22:33:49 <Oren> is the rest of the union
22:34:15 -!- S1 has changed nick to |S}.
22:35:17 <elliott> pikhq_: why doesn't it just use gcc's thread-local variables
22:35:36 <Oren> but then its hard to make an array?
22:36:16 <elliott> you can amek an array of pointers of them just fine
22:37:37 <Oren> i guess. there really should be a better way but I can't think of one
22:38:48 <Oren> like a smart array that knows how big each member is or something. but then that isn't very C-like
22:39:23 <Oren> is more like something you'd get from c++ boost
22:41:23 <pikhq_> The feature is older than thread-local variables in GCC.
22:41:48 <Oren> hystertical raisin
22:41:55 <pikhq_> So, unless you want to break ABI you keep using a macro that calls a function.
22:42:08 <elliott> pikhq_: couldn't you keep ABI compatibility by making __errno_location just return &errno_tls
22:42:20 <elliott> but #define errno errno_tls for new code
22:42:25 <pikhq_> Sure, I suppose you could.
22:42:41 <pikhq_> Inertia counts for a lot, mind.
22:43:02 <elliott> also I guess maybe gcc tls isn't as portable as glibc
22:43:47 <pikhq_> musl uses a macro that calls a function.
22:44:13 <pikhq_> The reason *here* is so that it can avoid pulling in threads at all when static linking unless you actually use it.
22:48:28 -!- Dulnes has joined.
22:50:36 <pikhq_> Basically, the errno function, if threads aren't running (if pthread_self returns NULL), it returns a reference to a static int, otherwise it returns a member in the thread struct.
22:51:29 <pikhq_> And pthread_self *itself* does not otherwise rely on threads, as all it does is return the thread pointer via whatever arch specfic mechanism exists to access it.
22:51:58 <pikhq_> (which is to say: musl does the errno function thing because TLS might not be accessible)
22:53:51 <pikhq_> Which is also kinda important for running on old kernels.
22:54:54 <pikhq_> (musl has a design goal of at least running on old kernels when you write programs that don't require features the old kernel doesn't have. For instance, if you don't use threads, then a 2.4.x kernel should mostly just work for you.)
23:01:47 -!- scoofy has quit (Ping timeout: 245 seconds).
23:02:24 -!- |S} has quit (Quit: |S}).
23:11:32 -!- Guest37103 has quit (Ping timeout: 240 seconds).
23:25:52 -!- underground666 has joined.
23:28:12 -!- underground666 has left.
23:29:51 -!- evalj has quit (Remote host closed the connection).
23:53:49 -!- Oren has quit (Quit: Page closed).