00:00:27 <oerjan> i think it is impossible to force order in general unless your string starts with a special position marker.
00:01:00 <AndoDaan> Like my BF or MNNBFSL thue interpreter would by necessity be deterministic.
00:01:27 -!- zzo38 has joined.
00:03:47 <AndoDaan> Great! then I can use a deterministic implementation of Thue to implement my Markov Alg BCT code.
00:09:01 -!- oren has joined.
00:35:36 <fizzie> AndoDaan: You could classify a (deterministic) Turing machine to be a deterministic string-rewriting thing, if you consider the tape as a string (with the position of the head indicated as a special symbol, carrying the state along), and the transition function a set of rewrite rules.
00:35:45 <fizzie> As in, you have state set Q and tape alphabet T, so think of rewriting a (Q union T)*, and if there's a transition (q, t) -> (q', t', Right) then let there be a rewrite rule from "q t" to "t' q'" and so on.
00:35:50 <fizzie> (Add some seasoning to make the tape grow as necessary.)
00:38:45 <AndoDaan> Yeah. Watching the code running, it looks like it too. The whole sweeping back and forth looks familiar too.
00:40:34 <AndoDaan> I first thought that Tag systems were closer to what string wrting is, but I'm realizing that's wrong.
00:42:45 <AndoDaan> And now I'm realizing that I still won't be able to extend the esointerpreters chain.
00:43:15 <AndoDaan> DDammit, what dthe hell is Zetaplex anyway?
00:45:18 -!- Tritonio has quit (Ping timeout: 276 seconds).
01:17:19 -!- hjulle has quit (Ping timeout: 245 seconds).
01:20:58 <HackEgo> danddreclist 62: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
01:29:08 -!- AndoDaan has quit (Quit: Off to find the mythical clitoris.).
01:43:57 -!- MDude has quit (Ping timeout: 256 seconds).
01:43:58 -!- nisstyre has quit (Ping timeout: 256 seconds).
01:43:58 -!- oerjan has quit (Ping timeout: 256 seconds).
01:43:59 -!- aloril has quit (Ping timeout: 256 seconds).
01:43:59 -!- lifthrasiir has quit (Ping timeout: 256 seconds).
01:44:00 -!- q3k has quit (Ping timeout: 256 seconds).
01:44:00 -!- olsner has quit (Ping timeout: 256 seconds).
01:44:01 -!- Deewiant has quit (*.net *.split).
01:44:02 -!- MDream has joined.
01:44:03 -!- oerjan_ has joined.
01:44:04 -!- oerjan_ has changed nick to oerjan.
01:44:05 <oerjan> something tells me glogbot isn't quite well
01:44:05 -!- olsner_ has joined.
01:45:32 -!- aloril has joined.
01:45:34 -!- q3k has joined.
01:45:35 -!- nisstyre has joined.
01:46:19 -!- lifthrasiir has joined.
01:50:37 -!- nortti has quit (Ping timeout: 256 seconds).
01:50:37 -!- adu has joined.
01:50:38 -!- Deewiant has joined.
01:50:38 -!- nortti_ has joined.
01:56:43 <zzo38> oerjan: How is that?
01:57:30 <oerjan> zzo38: the log wasn't up to date
01:57:40 -!- oren has quit (Ping timeout: 264 seconds).
01:58:59 -!- oren has joined.
02:13:20 -!- MDream has changed nick to MDude.
02:19:05 -!- shikhin_ has joined.
02:22:16 -!- shikhin has quit (Ping timeout: 264 seconds).
02:37:45 -!- oerjan has quit (Quit: Najt).
02:45:11 -!- copumpkin has joined.
03:02:18 -!- nys has quit (Quit: quit).
03:46:31 <HackEgo> [wiki] [[Special:Log/newusers]] create * Bradenbest * New user account
04:15:46 <HackEgo> [wiki] [[Totally Accurate Malbolge]] N http://esolangs.org/w/index.php?oldid=41783 * Bradenbest * (+1670) Created page
04:16:53 <HackEgo> [wiki] [[User:Bradenbest]] N http://esolangs.org/w/index.php?oldid=41784 * Bradenbest * (+58) started user page
04:20:05 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41785&oldid=41563 * Bradenbest * (+43) /* General languages */
04:47:19 <HackEgo> [wiki] [[Totally Accurate Malbolge]] M http://esolangs.org/w/index.php?diff=41786&oldid=41783 * Bradenbest * (+14) added name
05:39:32 -!- adu has quit (Quit: adu).
05:44:17 -!- adu has joined.
05:47:47 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
06:03:41 -!- adu has quit (Quit: adu).
06:07:38 -!- ProofTechnique has joined.
06:12:44 -!- J_Arcane has quit (Read error: Connection reset by peer).
06:13:12 -!- J_Arcane has joined.
06:24:11 -!- ^v^v has quit (Read error: Connection reset by peer).
06:24:37 -!- ^v^v has joined.
06:28:39 -!- adu has joined.
07:03:39 -!- MDude has changed nick to MDream.
07:15:12 -!- adu has quit (Quit: adu).
07:28:25 -!- SopaXT has joined.
07:34:06 -!- shikhin_ has changed nick to shikhin.
07:55:14 -!- Deewiant has quit (Quit: Viivan loppu.).
07:55:23 -!- Deewiant has joined.
08:03:22 -!- SopaXT has changed nick to SopaXorzTaker.
08:19:26 -!- shikhin_ has joined.
08:22:22 -!- shikhin has quit (Ping timeout: 245 seconds).
08:38:10 -!- dianne_ has joined.
08:38:20 -!- int-e_ has joined.
08:38:36 -!- mitchs has joined.
08:39:27 -!- int-e has quit (Disconnected by services).
08:39:33 -!- int-e_ has changed nick to int-e.
08:39:50 -!- heroux_ has joined.
08:45:19 -!- copumpkin has quit (*.net *.split).
08:45:19 -!- lambdabot has quit (*.net *.split).
08:45:19 -!- TieSleep has quit (*.net *.split).
08:45:20 -!- mitchs_ has quit (*.net *.split).
08:45:20 -!- j-bot has quit (*.net *.split).
08:45:20 -!- blsqbot has quit (*.net *.split).
08:45:20 -!- SopaXorzTaker has quit (*.net *.split).
08:45:21 -!- heroux has quit (*.net *.split).
08:45:21 -!- Lymia has quit (*.net *.split).
08:45:22 -!- dianne has quit (*.net *.split).
08:45:22 -!- EgoBot has quit (*.net *.split).
08:45:23 -!- heroux_ has changed nick to heroux.
08:47:15 -!- SopaXorzTaker has joined.
08:48:08 -!- Lymia has joined.
08:49:10 -!- copumpkin has joined.
08:50:32 -!- EgoBot has joined.
08:50:58 -!- lambdabot has joined.
09:02:41 -!- TodPunk has quit (Read error: Connection reset by peer).
09:03:04 -!- TodPunk has joined.
09:04:36 -!- weissschloss has quit (Ping timeout: 276 seconds).
09:05:09 -!- sebbu has quit (Ping timeout: 275 seconds).
09:06:54 -!- weissschloss has joined.
09:30:48 -!- nortti_ has changed nick to nortti.
09:32:10 <PinealGlandOptic> Hi everybody. Noob question about halting problem. Am I right that it's easy to detect infinite loops in TM LBA using TM LBA with bigger tape (just to write down all states and find out if one is repeating)? If so, does it mean that halting problem exist only for TM with infinite tape?
09:50:28 <Jafet> There is no LBA that determines whether any LBA halts, so in another sense, no
09:50:44 <elliott> ok by precisely I meant close enough
09:50:53 <elliott> need to read questions more closely in future :p
09:51:00 <Jafet> (Clearly, an unbounded Turing machine can determine whether any LBA halts.)
09:53:23 <J_Arcane> This page irritates me. See if you can guess why by about half way down the page. http://www.stencyl.com/
09:59:42 <PinealGlandOptic> Jafet: but bigger LBA with sufficient tape? why not? if we've got toy-level CPU with tiny registers and memory, it's easy to detect infinite loop in it and stop
10:04:36 <PinealGlandOptic> I mean, it's easy to run something on that toy CPU and wait for halt or for infitie loop detection and all that in finite time. if to track toy CPU state on the CPU with larger RAM.
10:09:28 <J_Arcane> elliott: scratch is cool, but it's totally coding ...
10:09:42 <elliott> J_Arcane: yeah but coding is a scary word
10:09:51 <elliott> and doing drag-drop fill-in stuff is nothing like the typical conception of "writing code"
10:10:07 <elliott> I think it's fine. it's making it accessible to people who would be turned off by the idea of coding
10:12:39 <Jafet> You are probably just annoyed because it's ripping off tried-and-true visual programming interfaces seen in LabView, Alice and other highly successful and productive systems
10:14:25 <J_Arcane> Naw, it was just the 'Make games with no coding!' then pictures of code.
10:15:43 <Jafet> PinealGlandOptic: usually the halting problem is phrased as: is there one machine M that determines whether any (suitably encoded) input machine halts
10:16:29 <Jafet> Since there is no single LBA that works for all LBAs, this version of the halting problem is unsolvable
10:18:44 <Jafet> You could add more memory to your LBA after you know the input size, but that just turns your LBA into a sort of Turing machine, so it's not very interesting
10:23:07 <Jafet> Note that "writing down all states" doesn't work since it doesn't use linear space, but you can probably use Floyd's or Brent's cycle detection methods.
10:31:35 <Jafet> Non-profit organisation name of the day http://www.astronauts4hire.org
10:31:39 -!- ^v^v has quit (Read error: Connection reset by peer).
10:32:04 -!- ^v^v has joined.
10:32:48 -!- AnotherTest has joined.
10:47:57 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
10:49:23 -!- SopaXorzTaker has joined.
11:03:04 -!- sebbu has joined.
11:03:56 -!- sebbu has quit (Changing host).
11:03:56 -!- sebbu has joined.
11:09:31 -!- shikhin_ has changed nick to shikhin.
11:10:22 -!- EgoBot has quit (Ping timeout: 240 seconds).
11:10:34 -!- EgoBot has joined.
11:41:44 -!- Patashu has quit (Ping timeout: 244 seconds).
11:50:48 -!- oerjan has joined.
11:53:31 <oerjan> <PinealGlandOptic> Hi everybody. Noob question about halting problem. Am I right that it's easy to detect infinite loops in TM LBA using TM LBA with bigger tape (just to write down all states and find out if one is repeating)? If so, does it mean that halting problem exist only for TM with infinite tape?
11:55:21 <oerjan> @tell PinealGlandOptic If you consider how that interacts with the proof of the halting problem, that is the essence of https://en.wikipedia.org/wiki/Space_hierarchy_theorem
11:55:58 -!- mitchs_ has joined.
11:57:38 <oerjan> @tell PinealGlandOptic basically, since a TM with (enough) more space can decide the halting problem for one with less, they cannot be the same computational class.
11:59:19 -!- SopaXorzTaker has quit (Remote host closed the connection).
11:59:27 -!- mitchs has quit (Ping timeout: 264 seconds).
12:13:46 -!- TieSoul has joined.
12:20:59 <oerjan> and darths & droids are right right back at confounding reader expectations again
12:21:39 -!- idris-bot has quit (Quit: Terminated).
12:22:54 -!- idris-bot has joined.
12:40:07 -!- Qfwfq has quit (Ping timeout: 244 seconds).
12:46:10 -!- Qfwfq has joined.
12:53:15 -!- boily has joined.
13:16:58 -!- SopaXorzTaker has joined.
13:38:57 -!- sebbu2 has joined.
13:39:17 -!- sebbu has quit (Ping timeout: 256 seconds).
13:39:34 -!- sebbu2 has quit (Changing host).
13:39:34 -!- sebbu2 has joined.
13:47:30 <FreeFull> oerjan: But it's possible to write a program that might use infinite space for certain inputs
13:47:49 <fizzie> "Examples of Winter Sports activities not covered are: -- Use of Skeletons"
13:48:39 <oerjan> this is not about arbitrary programs.
13:49:59 -!- Tritonio has joined.
13:51:35 <FreeFull> As long as the space is finite, it is decidable
13:51:53 <FreeFull> But the time would be exponential/superexponential probably
13:57:29 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
14:18:52 -!- shikhin_ has joined.
14:18:56 -!- shikhin_ has quit (Changing host).
14:18:56 -!- shikhin_ has joined.
14:21:52 -!- shikhin has quit (Ping timeout: 255 seconds).
14:24:30 <oerjan> @tell shachaf mission accomplished *MWAHAHAHA*
14:24:56 <oerjan> (ghc 7.10 is being delayed, partly due to the bugs we found)
14:26:33 <FreeFull> Having a new Prelude sounds interesting
14:29:05 <boily> I'm still hoping for the AMP to be in full effect.
14:29:32 <oerjan> i don't think the AMP is in much question
14:30:18 <oerjan> as the removel of the haskell2010 and haskell98 packages show, it had to be done entirely or not at all.
14:32:10 <oerjan> i'm sure that means something in russian.
14:32:44 <oerjan> except it's actually pronounced like rasmavyel
14:33:43 <boily> probably. GT isn't very helpful hth
14:34:10 <boily> but yeah, we're overdue for a new Prelude.
14:34:50 <J_Arcane> if the Prelude gets refactored, is that gonna obsolete what few good guides are already out there for Haskell?
14:35:11 <oerjan> it suggests растовел but has no actual meaning for it
14:36:09 <oerjan> J_Arcane: probably, but many of them were obsolete already.
14:36:26 <J_Arcane> This is true. I know RWH is getting a bit long in tooth already.
14:36:30 <oerjan> also, the BBP is supposed to be pretty backwards-compatible except for some type ambiguities.
14:37:27 <oerjan> i don't like that the neighbor's dog is occasionally barking again.
14:37:40 <oerjan> not _constantly_ like the first months, but still...
14:38:00 <oerjan> i hope it's not the start of a slippery slope
14:38:12 <boily> a well oiled dog barks best.
14:38:47 <oerjan> in fact, the BBP has been so well designed to be backwards compatible that many of the suggestions for how to partially backpedal on it will break _more_ code than it.
14:39:26 <oerjan> and also, as edwardk has repeatedly mentioned, a _lot_ of packages have already been adapted to it.
14:40:45 <oerjan> i think it's definitely in "even if it went too far in one step, going back is now even worse" territory.
14:44:44 <oerjan> b_jonas: the Burning Bridges Proposal, implemented in the upcoming 7.10 release candidate, adds Foldable and Traversable to the Prelude and generalizes most functions in the Prelude to the functions of the same name in Data.Foldable and Data.Traversable
14:44:56 -!- nortti has changed nick to mhi^_^.
14:45:00 -!- mhi^_^ has changed nick to nortti.
14:45:45 <lambdabot> Monad m => (a -> m b) -> [a] -> m [b]
14:45:55 <oerjan> :t Data.Traversable.mapM
14:45:56 <lambdabot> (Traversable t, Monad m) => (a -> m b) -> t a -> m (t b)
14:46:11 <b_jonas> I know they made Monad dependent on Applicable now
14:46:16 <oerjan> but even functions like sum and product are affected
14:46:36 <b_jonas> do they have type defaults that default to list?
14:47:02 <oerjan> nope, that's possibly the main non-backwards-compatible issue
14:48:20 <oerjan> i'm not sure if the ghc defaulting mechanism supports * -> * kind defaults
14:48:57 <b_jonas> oerjan: even if it doesn't no, maybe they'll change that? I mean, they're extending the type system all the tiem
14:51:16 -!- GeekDude has joined.
14:52:23 <oerjan> it does seem like something that shouldn't be too hard to do
14:56:40 <Lymia> Why is it called the Burning Bridges Proposal
14:58:43 <oerjan> because it changes a lot of the haskell Prelude module, which is usually considered part of the language itself.
14:59:50 <oerjan> i think it's sort of a "we're already modifying the Prelude incompatibly by making Applicative a superclass of Monad, why not go all in"
15:01:17 <oerjan> the original proposal was supposedly even more radical, in a less backward-compatible way
15:01:37 <oerjan> (e.g. in the end they did not merge map and fmap)
15:12:30 <b_jonas> oerjan: oh, like changing (.) to be an alias to fmap ?
15:12:47 <b_jonas> and (++) to, um, mplus or whatever it is?
15:13:09 <oerjan> no, they wouldn't change (.) to that, seeing as Control.Category uses it in a way incompatible to fmap
15:13:19 <oerjan> maybe ++ was considered
15:13:45 <oerjan> :t (Control.Category..)
15:13:46 <lambdabot> Category cat => cat b c -> cat a b -> cat a c
15:14:54 <oerjan> although the generalization of ++, mappend, has the alternative name <> now.
15:15:55 <oerjan> hm they probably also included Monoid in the Prelude, it's needed for Foldable to be defined.
15:16:19 <boily> Monoid is pretty much harmless.
15:35:41 -!- boily has quit (Quit: SPECIFIC CHICKEN).
15:41:28 -!- MDream has changed nick to MDude.
15:41:47 -!- SopaXorzTaker has quit (Remote host closed the connection).
15:49:22 -!- shikhin_ has quit (Ping timeout: 240 seconds).
15:50:24 -!- copumpkin has joined.
16:03:25 -!- ais523 has joined.
16:11:40 -!- SopaXorzTaker has joined.
16:14:30 -!- callforjudgement has joined.
16:17:33 -!- ais523 has quit (Ping timeout: 265 seconds).
16:17:39 -!- callforjudgement has changed nick to ais523.
16:18:19 <oerjan> "Honestly? The Prelude is just the set of stuff in scope by default. If the entire prelude consisted of one function that drew an ASCII fish and nothing else, I could live with that."
16:20:09 <idris-bot> Data.HVect.(++) : HVect ts -> HVect us -> HVect (ts ++ us)
16:20:10 <idris-bot> Prelude.List.(++) : List a -> List a -> List a
16:20:10 <idris-bot> Prelude.Strings.(++) : String -> String -> String
16:20:10 <idris-bot> Data.VectType.Vect.(++) : Vect m a -> Vect n a -> Vect (m + n) a
16:22:08 <ais523> oerjan: depends on what said function is named
16:22:18 <ais523> if it has a name that's likely to clash with other things, I might be annoyed
16:22:37 <oerjan> no, because you can do import Prelude ()
16:27:55 <oerjan> god this low frequency noise from somewhere in the neigbors' apartments is annoying
16:29:02 <oerjan> it's of course strongest precisely where i'm sitting.
16:34:17 -!- oerjan has quit (Quit: leaving).
17:08:49 <b_jonas> depends on what type of fish
17:09:37 <b_jonas> like, whether it's one of those crypto-fish in fashion back when the US had those export regulations about software
17:10:02 <b_jonas> that would get very old fast and show how out-dated language Haskell was
17:31:44 -!- j-bot has joined.
17:45:53 -!- Qfwfq has quit (Remote host closed the connection).
17:47:57 -!- Qfwfq has joined.
18:05:49 -!- SopaXorzTaker has quit (Ping timeout: 265 seconds).
18:07:39 -!- nys has joined.
18:09:52 -!- SopaXorzTaker has joined.
18:18:29 -!- arjanb has joined.
18:26:25 <J_Arcane> lord help me, I think I kinda like JavaScript.
18:28:32 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:33:55 -!- ais523 has quit (Read error: Connection reset by peer).
18:34:05 -!- ais523 has joined.
18:35:26 -!- shikhin has joined.
18:40:14 <oren> Why should anything be in scope by default?
18:42:09 <oren> In any language?
18:44:30 <oren> Generality suggests keeping the base language minimal (like C). Ease of use suggests having lots of default stuff (like Perl).
18:45:38 <oren> I think a good middle ground is to have a "import basic stuff" line at the top of programs
18:48:26 <oren> Which is what they did in C++ with "using namespace std"
18:52:12 <arjanb> I would say import nothing by default, and let an IDE do most of the importing for you
18:53:32 <oren> J_Arcane: It's not worse than PHP or C++...
18:54:19 <J_Arcane> oren: I think maybe it's also just refreshing to deal with after C# ...
18:56:26 <oren> C# has some... problems with syntax
18:57:23 <oren> but it is better than C++
18:58:50 <J_Arcane> Yes. I'd rather do C# than C++ or Java, but it's still a question of degrees ...
19:01:00 <b_jonas> oren: oh come on, import basic stuff is just four lines in C++
19:01:15 <b_jonas> ok wait, twenty lines of #include and THEN four lines
19:04:27 <b_jonas> #include <cstdlib> \ #include <cstdint> \ #include <algorithm> \ #include <utility> \ #include <limits> \ #include <array> \ #include <vector> \ #include <string> \ #include <memory> \ #include <iostream> \ #include <fstream> \ #include <sstream> \
19:05:35 <b_jonas> using std::cerr; using std::abort; using std::swap; using std::move; using std::min; using std::max; using std::abs; using std::sqrt; using std::exp; using std::log; using std::sin; using std::cos; using std::atan2; using std::array; using std::vector; using std::string; using std::unique_ptr; // and that's about it
19:06:54 <b_jonas> it's not really long, it is?
19:07:21 <b_jonas> then you need ten more lines of task-specific includes for what you actually want to do
19:21:03 <oren> There should be a #include <> <> <> <>... statement
19:22:52 <oren> Apparently there was some sort of important handegg game recently
19:24:19 <b_jonas> oren: and a using std::cerr, std::abort, std::swap, std::move, std::min, std::max; statement
19:24:47 <elliott> dear god: for 2k15, please make "showing off how little you [pretend to] know about sports" not be the top form of nerd brag any more
19:25:10 <b_jonas> fungot, how little do you know about sports?
19:25:10 <fungot> b_jonas: alice did not like shaking my head requires more power but the computer, fnord of the fnord here, so i don't see big contradiction: if soviets created
19:26:10 <oren> elliott: I know a lot about HOCKEY, the only IMPORTANT sport.
19:26:26 <b_jonas> elliott: it's easier here, because we don't have to pretend we know nothing of american football, baseball, basketball and hockey ( http://www.xkcd.com/1107/ ), but only of soccer, handball and water polo.
19:27:35 <oren> In Canada that chart would only include hockey and, in the city, football.
19:27:37 <b_jonas> Now water polo is played mostly underwater so even the judges know nothing about it and have to guess (but they have to pretend they know everything anyway), and soccer is played on such a large field you and the judges have no hope to see everything, it's not hard to pretend you can't follow them.
19:31:08 <oren> Hockey is interesting because it's dominated mostly by American teams, which consist mainly of Canadian players.
19:31:57 <b_jonas> oren: how does that make it interesting or different from other sports?
19:32:04 <oren> So you have crowds of Canadians cheering on Russians as they beat up Canadians
19:33:05 <oren> Whereas in football the teams consist of citizens of the country they represent
19:35:07 <b_jonas> oren: no, that's only the national teams in the championships, and there's one of those only every two years. the normal teams which participate in the leagues are made mostly of foreigner players who can make more of a carrier abroad.
19:35:42 <b_jonas> oren: and that's not even counting people in national teams that are granted citizenship easier just so they can be part of the national soccer team.
19:36:27 <oren> b_jonas: well, that's less interesting....
19:36:30 <b_jonas> We don't have many Chinese in European soccer teams yet, but only because they prefer other sports.
19:37:12 <oren> b_jonas: what about south americans?
19:37:45 <b_jonas> oren: dunno, I don't really follow sports, I'm not the right person to ask about the details
19:37:57 <oren> I only follow hockey
19:38:35 <J_Arcane> Everyone wants a Brazillian player in soccer. Some of the Brit clubs have paid non-trivial sums to get one ...
19:39:54 <J_Arcane> I know a Brazillian-English bodybuilder by way of my former language class, and he said he was more or less told he could sign up to just about any club he wanted, because, essentially, racism. ;)
20:02:59 -!- Patashu has joined.
20:11:38 -!- sebbu2 has quit (Ping timeout: 245 seconds).
20:19:30 -!- shikhin_ has joined.
20:22:36 -!- shikhin has quit (Ping timeout: 265 seconds).
20:22:59 <oren> It would be nice if people describing an algorithm with code and equations used the same variable names in both,rather than expecting me to guess
20:23:05 -!- shikhin_ has changed nick to shikhin.
20:25:49 -!- Patashu has quit (Ping timeout: 250 seconds).
20:27:37 <b_jonas> fungot, how many substitutions do I need?
20:27:38 <fungot> b_jonas: i, myself, will bring an end to all. ghosts lurk in the ruins were in truth, and everything in readiness for fnord. under these is concerned, the use of " coup" here is one that only takes predicates and has not named a
20:29:08 -!- nys has left ("Leaving").
20:29:14 -!- nys has joined.
20:37:32 <fungot> fizzie: i just wrote :p ( what was i thinking there.... :d), i really care... a time portal? what in the...! ozzie's stumped!
20:37:56 <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
20:38:05 <fizzie> The 'ct' style is well-represented in the overall 'fungot' style.
20:38:05 <fungot> fizzie: so, let's say i call them mindless games. if we hit every stupid person, any person going to use funge-93 because tusho said i well, bully hector?
20:48:09 -!- Tritonio has quit (Remote host closed the connection).
20:50:54 <b_jonas> `8-ball is it wise to you for financial advise and predicting the stock market?
20:51:18 <b_jonas> `8-ball is it wise to you to predict the result of big sport events?
20:51:46 <b_jonas> fungot, how much do you know about sports?
20:51:46 <fungot> b_jonas: agora alice c64 ct darwin discworld europarl ff7 fisher ic irc* jargon lovecraft nethack pa speeches ss wp youtube
20:52:15 <b_jonas> fungot, do you like handball?
20:52:15 <fungot> b_jonas: his birthday is in the same as the word " crazy" " not exactly the daycare-place i was just about to do it when i wake up long lol
20:52:43 <b_jonas> fungot, do you like waterpolo?
20:52:43 <fungot> b_jonas: is that something you know and and the cases that required to actually mutate the original ( sorted, perhaps, it may be said that particularly here, parliament will give a single instance,
20:54:28 <b_jonas> fungot, can you control the path of meteorites?"
20:54:28 <fungot> b_jonas: if that is not used commonly and carries with it an array subscript was too easy heh one time i figured if it's possible, notify the notary.
20:54:52 <b_jonas> fungot: ok, then direct this one to the shores of Greenland
20:56:09 -!- ais523 has quit (Read error: Connection reset by peer).
20:56:13 -!- callforjudgement has joined.
20:58:03 -!- olsner_ has changed nick to olsner.
21:08:04 -!- callforjudgement has quit (Read error: Connection reset by peer).
21:08:16 -!- callforjudgement has joined.
21:15:29 <Sgeo> "Please check back here on February 1st for an update on our study, and on LessWrong for a ProveItForReal.org update on March 1st."
21:20:31 <FreeFull> I can't decide on an algorithm for rotating the digits of a number (24983 becoes 32498), but I don't even need it to be fast. I'm just indecisive
21:21:08 -!- ^v^v has changed nick to ^v.
21:21:29 -!- callforjudgement has quit (Read error: Connection reset by peer).
21:21:31 -!- scarf has joined.
21:22:02 <FreeFull> Which is base 10 log, followed by a mod, division and addition
21:24:41 -!- scarf has quit (Read error: Connection reset by peer).
21:24:57 -!- scarf has joined.
21:27:53 <J_Arcane> Huh. JavaScript's object model seems a lot like Heresy's ...
21:29:58 -!- Tritonio has joined.
21:30:09 -!- ais523 has joined.
21:30:38 -!- AndoDaan has joined.
21:31:14 -!- bb010g has joined.
21:34:15 -!- scarf has quit (Ping timeout: 264 seconds).
21:48:37 <oren> using katakana in equations feels liberating, because there are so many
21:48:53 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
21:51:45 <J_Arcane> 65% through the codecademy JS course now ... XD
21:52:10 -!- callforjudgement has joined.
21:52:13 -!- ais523 has quit (Read error: Connection reset by peer).
21:57:01 <int-e> oren: it's only liberating if you can actually tell different katakana apart :P
22:00:51 <fizzie> Ut-oh. I was just shutting down the server at home (in preparation for the move) when it dawned on me that I haven
22:00:54 <fungot> fizzie: no, it's not. it's more complex than that. read the code.) good stuff that makes me even)) x sort ( filter procedure, but maybe i will when i start fixing it rather than having arbitrary bf, as if it wasn't. holy cow, i never claimed that the victim) subject:re: `which fnord echo
22:01:09 <fizzie> Ok, apparently it's even more complex than that.
22:05:11 <fizzie> fungot: Do you think I should do something to keep you online, or do you want to take a holiday of few weeks?
22:05:11 <fungot> fizzie: ( ( ( a()**)a*:a*)(a()**)a*:a*)((x1)(x2)(x3)) ...out of time! don't let " persons" be added to the actual standard being sane) scheme implementations but guile is my fnord' doggie than a dozen tales, of the whole fnord range of the ' ' ' delete a value of type " airbus is a big fan of avril....but this song " there
22:05:23 -!- hjulle has joined.
22:05:33 <fizzie> I'm not sure how to interpret that.
22:06:46 -!- Phantom_Hoover has joined.
22:08:53 -!- Phantom__Hoover has joined.
22:08:56 -!- Phantom__Hoover has quit (Changing host).
22:08:56 -!- Phantom__Hoover has joined.
22:09:36 -!- sebbu has joined.
22:09:50 <FireFly> J_Arcane: the prototypal object model is pretty straightforward (although JS's in particular is a bit messy)
22:10:12 -!- sebbu has quit (Changing host).
22:10:12 -!- sebbu has joined.
22:11:13 <J_Arcane> FireFly: Yeah, I noticed the syntax gets a little ambiguous when you're iterating over object fields.
22:11:29 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
22:11:55 -!- fungot has quit (Quit: BEEP BOOP TIME TO TAKE A BREAK).
22:13:03 <J_Arcane> FireFly: Well, unclear at least. When doing for (var x in obj), I'm a little unclear what's actually in x. Ie. is it thus a string, and thus you must do obj[x], or can obj.x work safely, that kinda thing.
22:13:06 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
22:13:37 <FireFly> I think that's pretty straightforward. foo.bar is basically just sugar for foo["bar"]
22:14:22 <J_Arcane> In Heresy, you can do (for (x in (Obj 'fields)) ...) and x will contain a valid symbol for calling a field in Obj, such that you can then do (Obj x).
22:17:36 <J_Arcane> It's a similar idea though, Heresy objects are basically just a lambda wrapped round an association list, so you can do fun stuff like that pretty easily. Need to decide what, and if, I'm gonna do with it I think.
22:19:03 <FireFly> Does heresy have the concept of prototypal inheritance, where if you look up a property in an object and the property is missing, it'll try to look it up in the prototype instead?
22:20:01 <b_jonas> `8-ball Does heresy have the concept of prototypal inheritance?
22:21:02 <J_Arcane> FireFly: Depends how it was declared. I'm a little fuzzy on the inheritance feature, because 1) it's new, and 2) I didn't write it.
22:22:35 <J_Arcane> http://pkg-build.racket-lang.org/doc/heresy/index.html#%28form._%28%28lib._heresy%2Fmain..rkt%29._describe%29%29
22:28:12 -!- nisstyre has quit (Changing host).
22:28:12 -!- nisstyre has joined.
22:35:24 -!- oerjan has joined.
22:45:21 <int-e> sigh. echo '#social-share-button { display: none !important }' >> .mozilla/firefox/default/chrome/userChrome.css
22:45:33 <int-e> firefox continues to add useless crap
22:46:01 <oerjan> int-e: i believe we've successfully delayed ghc by a month hth
22:47:58 <int-e> No new comments on the ticket, hmm.
22:48:16 <oerjan> there was a ghc-devs post linked from reddit
22:48:44 <int-e> hmm, I'm not subscribed to ghc-dev, perhaps I should be...
22:49:18 <oerjan> https://www.haskell.org/pipermail/ghc-devs/2015-January/008189.html
22:54:19 -!- ^v has quit (Read error: Connection reset by peer).
22:54:43 -!- ^v has joined.
22:59:10 <int-e> I just hope the BBP discussion does not take advantage of this delay. I mean I don't really care about the BBP as such, but going forth and back on this seems like a big waste of effort (mostly hvr's)
23:02:45 <oerjan> i am somewhat wondering if they manage to implement this in such a way that no type signatures need to be changed to use anything Kindable-like
23:06:03 <int-e> I don't know. To me it seemed that a proper solution would involve tracking Typable instances for polymorphic kinds, much the same way they have to be tracked for polymorphic datatypes. So we'd have things like (Typeable k, Typeable t) => Typeable (Proxy (t :: k))
23:06:47 <int-e> And that would indeed change some type signatures.
23:06:48 <oerjan> yeah i was thinking that too, although that (1) would require changing type signatures (2) cannot be done with current ghc types
23:07:18 <oerjan> but since there is essentially a function dependency from type to kind...
23:07:28 -!- AnotherTest has quit (Ping timeout: 252 seconds).
23:07:34 <J_Arcane> oooh man this Black Mirror ep is weird ...
23:08:00 <elliott> why are they delaying 7.10
23:08:11 <elliott> it's not going to make things any less vulnerable
23:08:27 <int-e> elliott: It would mean getting a fix out sooner
23:08:30 <oerjan> elliott: yes but spj _really_ doesn't like Safe Haskell completely broken, i think
23:08:55 <oerjan> of course it's only theoretically ever sound
23:09:03 <int-e> Besides, yeah, SPJ's opinion carries some wait here.
23:09:48 <int-e> I hate those phonetically correct typos.
23:10:33 <elliott> yeah but you could just release 7.10.1 quickly
23:10:39 <elliott> I guess the point is that nobody wants to upgrade twice in quick succession
23:10:43 <oerjan> int-e: does your typefamily method avoid needing anything for kinds in the signatures?
23:10:52 <b_jonas> but wouldn't it require changing the type signatures to the _correct_ signatures from the wrong ones?
23:11:16 <oerjan> b_jonas: the old signatures aren't wrong per _se_
23:11:25 <oerjan> a type always implicitly includes its kind
23:11:29 <b_jonas> elliott: ah right, because ghc still breaks binary compatibility of all modules you've compiled with it at every point release!
23:11:30 <int-e> elliott: It's easier to explain breaking code (and I'm still not convinced that that won't happen) with a full release than with a point release.
23:11:38 <b_jonas> sn't that the basic problem?
23:11:57 <b_jonas> so people can't just upgrade as lightly as with most other software
23:12:35 <int-e> elliott: So what I'm trying to say is, I'm not sure whether this should be left for 7.10.1 or 7.12.1, but I don't think it can be done in a 7.10.x, x>1, release.
23:13:34 <oerjan> but i fear that if you have a typeable instance which depends on a kind variable, then ghc will do its instance resolution in such a way that it _needs_ an explicit context for the kind as well, which is what seemed to happen for my experiments
23:13:37 <int-e> Of course I may be wrong and this won't break any code at all.
23:13:57 <int-e> ... but as already indicated, I don't see how.
23:14:36 <b_jonas> (seriously, that's what really shows it's a research language)
23:14:42 <oerjan> _if_ they can manage to avoid the kind separating from the type in a sense, then the signatures wouldn't need to change. or so i think.
23:15:25 -!- hjulle has quit (Ping timeout: 264 seconds).
23:15:25 <oerjan> i don't understand int-e's type family version enough to say if that does it
23:15:32 <int-e> And I suggested leaving this for 7.12 mainly because there have already been two RCs, so breaking code now *will* cause some upset.
23:16:24 <int-e> oerjan: What it is supposed to accomplish is that you don't need explicit Typeable contexts for monomorphic kinds.
23:17:17 <oerjan> int-e: oh. i thought my method did that as well, or could, at least.
23:18:56 <oerjan> the fact that you cannot actually write Typeable k for a kind k afaik, except possibly in goldfire's branch, seems to be a problem.
23:18:59 <int-e> oerjan: Hmm, you may be right. But the type family also covers the (Typeable a, Typeable b) => (Typable (a b)) instance, where with MPTCs you run into the open world assumption problem
23:20:15 <oerjan> it does? as i said there is essentially a functional dependency.
23:20:50 <oerjan> hm i was going to test something...
23:21:27 <zzo38> How can you have Typeable contexts for kinds?
23:21:30 <zzo38> What is a "open world assumption problem"? Also what is goldfire's branch?
23:22:15 <oerjan> alas, nope, you cannot define a type synonym with a kind parameter either :(
23:23:06 <zzo38> Are you supposed to?
23:23:10 <oerjan> zzo38: you cannot, currently, but it would seem the most obvious way of getting a reified kind to put in the Typeable instance for a polykind type
23:24:10 <oerjan> zzo38: goldfire's branch is a branch where he is removing the distinction between types and kinds, in order to prepare for a dependent types extension
23:24:33 <oerjan> (am i remembering the nick correctly, hm...)
23:25:25 <oerjan> the "open world assumption" is the rule that instance resolution for a class never assumes anything based on which instances are _not_ in scope
23:25:59 <int-e> oerjan: hmm, you may be right. Perhaps the real trick is that in my code, only *some* Typeable instances have a "Kindable (Proxy :: k -> *)" (= Typable (KindRep (Proxy :: k -> *))) context.
23:26:46 <oerjan> the "problem" then is that it can sometimes be hard to convince ghc to use the one you want
23:27:04 <int-e> So the problem of getting from Kindable (k1 -> k2) to Kindable k1 and Kindable k2 doesn't crop up.
23:27:06 <zzo38> I believe you should need support for defining automatic classes and for defining closed classes. Typeable can then be made into a automatic class; you don't need deriving(Typeable) and can't define an explicit instance but for polymorphic functions you will still need a Typeable context if you want to use its type information.
23:27:44 <int-e> zzo38: yes that's the way SPJ is heading
23:28:56 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
23:29:12 <oerjan> b_jonas: the changes for 7.10 are big enough that several people have suggested that it should be numbered 8.0 instead. but then they don't really affect the _internals_ of ghc as much as the libraries.
23:29:32 <zzo38> I am not sure how the syntax should be for defining automatic classes, but Typeable would be built-in anyways so it doesn't matter in this case.
23:30:00 <int-e> oerjan: not much wrong with bumping base to 5.0 without bumping the ghc version...
23:30:17 <zzo38> But it would help to make up a syntax and capability for these kind of things, as well as to define the new kind of macros so that do-notation and list-syntax can be made into macros that are defined in the Prelude instead of being built-in.
23:30:23 <int-e> but everything is wrong with bumping the base version, I have upper bounds 5 almost everywhere ;0
23:30:49 -!- Phantom_Hoover has joined.
23:31:36 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
23:32:01 -!- J_Arcane has joined.
23:34:04 <oerjan> zzo38: there aren't that many other classes than Typeable that really _can_ be automatic in a user-definable way, because you want to support abstract data types by allowing not exporting constructors and deriving classes that expose internal structure. The information in Typeable is afaict about everything that _cannot_ be hidden this way.
23:36:57 <oerjan> Coercible is also automatic, but it _checks_ whether the constructors are exposed.
23:37:14 <zzo38> I know that; you would somehow need macros if you can have user-definable automatic classes at all, since the macro then needs to use the stuff it is capable of using. This might result in the instances of such classes being different in different modules. But another way might be automatic classes based on instances of other classes. Other details would be names of types as strings.
23:37:39 <oerjan> ...i suppose there could be a mechanism for that, but then you'd have the same weirdness as Coercible in that the instance isn't necessarily inherited
23:39:04 <oerjan> zzo38: aeson has default methods for some its classes based on Generic, not quite automatic but close.
23:40:03 <oerjan> hm there _was_ a suggestion of allowing deriving any class by using its default methods...
23:40:27 <oerjan> maybe it was even in 7.10 RC
23:40:57 <zzo38> Do you mean like: data A = B | C deriving(Eq, default D, default E);
23:41:35 <zzo38> (So that you would have to explcitly specify you are deriving by defaults.)
23:41:46 -!- arjanb has quit (Quit: .).
23:41:52 <zzo38> But can't you just use instance without defining the methods, in such case, instead?
23:42:48 <oerjan> zzo38: hm i don't think there was an explicit keyword, just (Eq, D, E)
23:43:20 <oerjan> however it _would_ be good to be able to at least specify explicitly if you want GND or defaults
23:43:32 <oerjan> if your module has both extensions
23:43:50 <zzo38> Yes for newtype instead of data it would help to explicitly specify "default" in this case at least; for data it isn't needed
23:44:20 <oerjan> you might even want to able to overrule that for base classes, so you could do newtype MyType = MyType Int deriving (newtype Show)
23:44:42 <zzo38> Yes that too I agree
23:44:59 <zzo38> Would be better, and I think more useful than deriving defaults
23:47:49 <zzo38> Why did they add "\case" syntax instead of my "\of" suggestion? (Which I think is probably same except for the words in use; "\of" would probably simplify the parser both for layout and nonlayout)
23:47:52 <oerjan> i think the syntax deriving (newtype Show, default JSON) is pretty much vacant?
23:48:22 <oerjan> both because they're keywords, and because they're lower case
23:48:36 <b_jonas> oerjan: re-using existing language keywords for new meanings? I see you're learning from us C++ers. Very good.
23:48:38 <zzo38> oerjan: Yes that is why I suggested using the keyword "default"
23:49:54 <zzo38> In SQLite although new keywords are sometimes added, they are never reserved words; only a few keywords are reserved words. Therefore it doesn't cause problem if your name of a column or table or whatever is now a keyword.
23:50:40 <oerjan> zzo38: i also liked \of better than \case for logical grounds, although i actually preferred "case of". but someone (spj) vetoed \of on the grounds it was too lightweight
23:51:03 <b_jonas> http://sqlite.org/lang_keywords.html lists more than there are in C++ I think
23:51:16 <zzo38> b_jonas: Yes, although most of those aren't reserved.
23:52:07 <zzo38> I looked again and actually I forgot how many are reserved
23:52:08 <b_jonas> funnily that list doesn't include COVERING
23:52:12 <zzo38> Still, a lot of them aren't reserved.
23:52:32 <zzo38> And any new ones added also won't be reserved.
23:53:01 <b_jonas> that page actually says “SQLite adds new keywords from time to time when it takes on new features.”
23:53:03 <zzo38> I think they do implicitly although it doesn't say so.
23:53:17 <b_jonas> but then, perl says that too but they don't add new keywords anymore
23:53:32 <zzo38> It is true they add new keywords, but from my experience as well as for backward-compatibility reasons, the new keywords won't be reserved.
23:54:11 <b_jonas> perl has used like three different solutions to avoid adding new reserved words
23:54:28 <oerjan> my arguments for "case of" were (1) it doesn't need a new layout keyword (2) it leaves out the expression, so you can think of it as a case section
23:54:45 <b_jonas> namely, (1) putting important core functions to modules rather than builtin functions, (2) adding a weak keyword, (3) adding a keyword that is active only if you specifically allow it with "use feature"
23:55:21 <zzo38> I have made a list of the reserved words. There are 58 reserved words, which is almost half of all of the keywords in SQLite.
23:55:54 <zzo38> All of the new keywords in Objective-C also aren't reserved and can be used as the names of ordinary C stuff without a problem.
23:56:23 <zzo38> (Therefore, any C program is also a valid Objective-C program.)
23:58:07 -!- ProofTechnique has joined.
23:58:42 <zzo38> WITH and WITHOUT aren't reserved words in SQLite; nor is RECURSIVE.
23:59:45 <zzo38> oerjan: Yes those are my reason too. I don't use the layout mode but many people do, and regardless of this it makes the parser more sensible. Either "case of" or "\of" is better to me than "\case".
00:00:30 <oerjan> zzo38: also thanks to multiway-if, | is now sometimes a layout keyword. it wasn't originally but i remember loudly pointing out that was a mistake and some time later they added layout.
00:01:26 <oerjan> (not that my shouting was in the right place to be the direct cause)
00:02:28 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
00:18:08 <zzo38> I made up two Magic: the Gathering cards based on suggestions from the game master for the Dungeons&Dragons game, which are called "Imp of Deception" (opponent's mana is of a different color than they expect) and "Calimshan Advisor" (opponent shows you the cards he intends to use during his turn).
00:18:13 <oerjan> <b_jonas> We don't have many Chinese in European soccer teams yet, but only because they prefer other sports. <-- didn't i mention a while ago that the chinese premier is a soccer fan who wants to make china stop being abysmal at it
00:18:34 <oerjan> so that may change. eventually.
00:19:02 <zzo38> I changed the effects to make them work better with the rules of Magic: the Gathering though. Did you look at it?
00:19:46 <oerjan> (btw the chart for norway would be Football and, bizarrely, Cross Country Skiing)
00:20:48 <oerjan> (norway is dominating the latter to an unhealthily degree - unhealthy because every other country is starting to lose their remaining interest in the sport)
00:23:44 <oerjan> (ok the chart would also have some other winter sports)
00:25:35 <oerjan> decades ago, skating used to be huge in norway. i think the dutch may be doing the "unhealthy dominance" thing on that at present.
00:29:23 <zzo38> I made "sqlircbot" but I haven't tried it yet http://sprunge.us/MNaa please tell me if you notice anything wrong, or that I should need to fix, or other feature suggestion, or complaint, etc
00:33:14 -!- oerjan has set topic: This channel is defunged | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
00:35:03 * int-e waits for zzo38 to rewrite fungot in sqlite3
00:35:39 * oerjan waits for fungot to rewrite zzo38 in scheme
00:36:13 <int-e> oerjan's a little schemer
00:36:38 <zzo38> I don't really have a intention to rewrite fungot in anything; you rewrite fungot if you like to do so. I doubt fungot has any such intention either, although maybe they can fake it.
00:37:40 <int-e> zzo38: sigh. I was merely trying to hint, politely (ok, maybe not), at the fact that you seem to be a bit obsessed with sqlite.
00:38:05 <zzo38> You are allowed to say thing like that if you like to do so.
00:38:20 <oerjan> i was merely trying to hint, politely, at the fact that fungot seems to be a bit obsessed with scheme hth
00:39:07 <int-e> oerjan: it may have to do with hanging around on #scheme
00:40:38 -!- int-e has set topic: This channel got defunged | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
00:41:00 <elliott> what's wrong with being obsessed with something
00:41:38 <int-e> elliott: nothing, but it can be hard to take for people who are not obsessed about the same things.
00:41:47 -!- Tritonio has quit (Remote host closed the connection).
00:44:40 -!- GeekDude has quit (Ping timeout: 255 seconds).
00:45:55 -!- vifino has joined.
00:46:53 -!- GeekDude has joined.
00:50:40 <Taneb> I am listening to my (British) university's radio coverage for the Superbowl
00:50:48 <Taneb> I have no idea what is going on, and neither do they
00:53:30 <zzo38> Then call them on telephone and complain
00:53:32 <Taneb> "The Patriots are up 42 to 7, what does that mean? We don't know"
00:53:41 <Taneb> zzo38, It's amusing
00:53:49 <Taneb> They're now ordering pizza
00:54:53 <Taneb> They've got the person on the student union representing sports clubs
00:56:12 <Taneb> I sent in a message saying "Do any of you have any idea what is going on?"
00:56:33 <Taneb> And they read it out and said "Absolutely not, except for one thing, and that's that pizza is on its way"
00:58:00 <Jafet> Maybe they should interpret the game using British football rules.
00:58:26 <Taneb> Apparently there was a touchdown
00:58:31 <Taneb> Do they work like in Rugby
00:58:36 <Taneb> Do they get to convert the touchdown
00:59:46 <Taneb> "I don't know what that means, I'm just reading things that are on the screen"
01:06:19 <zzo38> I made up two variants of Magic: the Gathering which are using entirely proxies, which is one for Limited (using a Solomon draft) and one for Constructed (using duel decks).
01:07:00 -!- hutin has joined.
01:10:48 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=41787&oldid=41554 * 66.57.93.188 * (+40) /* Nim */
01:11:32 <Taneb> Now the campus satire magazine has came to beat up the radio presenters
01:14:12 <pikhq> Taneb: Yes, in football you can convert a touchdown.
01:14:59 <pikhq> Though you ordinarily kick for a field goal to get an extra point rather than do a two-point conversion.
01:15:17 <zzo38> What are you going to convert it into?
01:15:35 <pikhq> zzo38: The nomenclature is... weird.
01:16:14 <zzo38> Maybe that's why nobody understands?
01:16:15 <pikhq> A "two point conversion" in American football refers to attempting a second run into the in zone immediately after a touchdown in a single play.
01:16:38 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=41788&oldid=41787 * 66.57.93.188 * (+18) /* Changed language name to Nim. Allow multiple commands at once. */
01:17:25 <oren> When did katy perry become an american copy of kyary pamyu pamyu
01:20:24 <oren> Like seriously, googly eyed beachballs and palm trees. clearly copying kyary pamyu pamyu
01:20:34 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
01:20:49 <pikhq> To be perfectly honest, American football is not that complicated a game, particularly if you understand rugby.
01:20:58 <pikhq> (American footbball is "just" a very weird variant of rugby)
01:21:31 <AndoDaan> rugby is a very weird variant of soccer.
01:21:47 <zzo38> You are probably correct but that doesn't make it easily enough to understand by people who don't understand these kind of game!
01:21:59 <Taneb> Association football is a weird variant of Magic: The Gathering
01:22:01 <zzo38> Especially if the nomenclature is... weird.
01:22:34 <AndoDaan> MTG is a reasonable varient of Pocket Monsters.
01:22:55 <pikhq> zzo38: True. It's not *hard*, but it's non-zero knowledge.
01:23:32 <AndoDaan> Wait, was MTG the first card game of it's kind?
01:23:34 <zzo38> Magic: the Gathering is different from football and Pocket Monsters entirely, just as much as poker is different from chess and stuff like that, and more
01:23:40 <zzo38> AndoDaan: I believe so.
01:24:10 <AndoDaan> What a mind the invertor must have.
01:25:02 <zzo38> But there was no Limited play when it was first designed, only Constructed. There also weren't any deck construction rules as far as I know, and many cards were written in ways that are unusual for today, some cards says "destroys a black card as it is being cast", and "target creature is now a flying creature", and "if this reduces creature's toughness below 1, it is dead"
01:26:23 <pikhq> The closest to a predecessor to MTG, which isn't especially similar, is Cosmic Encounter.
01:27:22 <Taneb> They are now ordering pizza LIVE ON AIR
01:27:49 <pikhq> By the way, it is a terrible idea to order pizza in the US during the Superbowl.
01:28:22 <pikhq> I mean, you can, they will take your order, and they will deliver it, but don't be surprised if the game has been over for an hour by the time they actually make the thing.
01:28:22 <Taneb> pikhq, good thing they are in Yorkshire
01:28:33 <pikhq> In Yorkshire I can't imagine it's a big problem.
01:28:54 <pikhq> Well, except that it's 0130.
01:29:18 <Taneb> Eh, I've ordered later successfully
01:29:28 <Taneb> It's a city with two universities
01:29:42 <zzo38> I am supposed to design Aberration Hater Card Game though, instead of being mainly Constructed it can be designed from the start to be mainly for Limited, as well as from the start it says you can use proxies if it is written clearly and don't constitute "marked cards".
01:29:50 <pikhq> You might be limited in options, but still.
01:30:31 <zzo38> And also if I can try to design the rules from the start so that you don't get unclear and ambiguous problems, by inventing the programming language to design the rules with.
01:31:02 <zzo38> I don't know if you believe it is a better, worse, or neither, idea than how other game design.
01:32:14 <zzo38> What is your opinion of such thing anyways?
01:33:43 <Sgeo> At this rate, Chrome is going to assume General Biotics is one of my favorite websites
01:33:57 <zzo38> Can you disable those feature?
01:34:21 <Taneb> They've challenged the satire magazine to strip-watching Superbowl
01:34:32 <Taneb> One item of clothing for each point scored
01:34:48 <zzo38> What happen when they run out of clothing?
01:35:51 <Taneb> Then they lose I guess
01:36:19 <zzo38> Whoever has a lot of clothing is winner.
01:36:34 <Taneb> They've just realised that they're going to have to collect the pizza after a while
01:43:12 -!- hutin has quit (Read error: Connection reset by peer).
01:44:27 <Taneb> Eh, I'm going to bed
01:44:55 <Taneb> When you start hearing owls and radio commentators talking about themselves stripping it's time to sleep
01:48:05 <Taneb> "The last time we called him on air, he was in the middle of something... very personal, that"
02:02:52 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=41789&oldid=41788 * Oerjan * (-61) Undo everything except name change, misunderstood language semantics
02:12:04 <oerjan> deadfish may be a simple esolang, but it's semantics are among the hardest to understand unaided
02:19:52 -!- shikhin_ has joined.
02:22:36 -!- shikhin has quit (Ping timeout: 245 seconds).
02:25:59 <HackEgo> [wiki] [[Joke language list]] M http://esolangs.org/w/index.php?diff=41790&oldid=41785 * Oerjan * (+0) /* General languages */ Totally Accurate Ordering
02:30:45 <HackEgo> [wiki] [[Brainfuck implementations]] M http://esolangs.org/w/index.php?diff=41791&oldid=41730 * Oerjan * (+3) fix some punct.
02:33:37 <HackEgo> [wiki] [[Talk:Brainfork]] M http://esolangs.org/w/index.php?diff=41792&oldid=41774 * Oerjan * (+54) unsigned
02:35:27 <HackEgo> [wiki] [[Talk:Al Dente]] M http://esolangs.org/w/index.php?diff=41793&oldid=41781 * Oerjan * (+52) unsigned
02:37:49 <HackEgo> [wiki] [[Totally Accurate Malbolge]] M http://esolangs.org/w/index.php?diff=41794&oldid=41786 * Oerjan * (+16) fmt, link
02:40:35 <oerjan> TomPN has managed to outrun my patience with adding unsigned templates
02:44:37 <int-e> oerjan: do you have to manually collect the metadata?
02:46:32 <oerjan> well, i don't know if i _have_ to, but i generally cut and paste from the history subpage
02:46:54 <oerjan> adjusting the time zone as well
02:47:52 <oerjan> it's not the chore of it that broke my patience, but the fact that he keeps not signing even as my previous templates are visible on the same page
03:17:13 -!- tromp_ has joined.
03:23:39 -!- scarf has joined.
03:23:46 -!- scarf has changed nick to ais523.
03:27:42 -!- callforjudgement has quit (Ping timeout: 264 seconds).
03:28:57 -!- one has joined.
03:34:37 -!- one has quit (Quit: Page closed).
03:35:54 -!- ProofTechnique has joined.
03:36:15 -!- Qfwfq has quit (Ping timeout: 256 seconds).
03:40:09 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
03:41:35 -!- Qfwfq has joined.
03:45:42 <zzo38> A game called "Cuttle" with some similarities with Magic: the Gathering is said to have been invented much earlier--in 1970s at the latest.
03:49:26 <pikhq> I mostly know of Cosmic Encounter because it's what Garfield actually had *played* that gave him ideas for MTG.
03:49:34 <pikhq> Also because I've played Cosmic Encounter.
04:03:57 <Sgeo> hasgeneralbioticsreleasedtheirstudyyet.example.com: NO
04:16:10 -!- ProofTechnique has joined.
04:21:37 -!- copumpkin has joined.
04:26:24 -!- nys has quit (Quit: quit).
04:39:33 -!- tromp_ has quit (Read error: Connection reset by peer).
04:40:08 -!- tromp_ has joined.
04:40:50 -!- Sprocklem has joined.
04:50:06 * oerjan wonders if he's playing too much devil's advocate https://ghc.haskell.org/trac/ghc/ticket/9858#comment:43
04:55:53 -!- adu has joined.
04:56:26 -!- oerjan has quit (Quit: Nite).
05:07:44 -!- idris-bot has quit (Quit: Terminated).
05:08:01 -!- idris-bot has joined.
05:20:12 -!- atehwa has joined.
05:32:10 -!- AndoDaan has quit (Quit: Off to find the mythical clitoris.).
06:15:03 -!- callforjudgement has joined.
06:17:22 -!- not^v has joined.
06:18:42 -!- ais523 has quit (Ping timeout: 264 seconds).
06:18:59 -!- callforjudgement has changed nick to ais523.
06:22:37 -!- shikhin_ has quit (Ping timeout: 264 seconds).
06:28:58 -!- adu has quit (Read error: Connection reset by peer).
06:33:22 -!- ais523 has quit.
06:35:54 -!- adu has joined.
06:47:29 -!- MDude has changed nick to MDream.
07:07:28 -!- Sprocklem has quit (Ping timeout: 245 seconds).
07:11:36 -!- Sgeo_ has joined.
07:13:05 -!- Sgeo_ has quit (Read error: Connection reset by peer).
07:15:05 -!- Sgeo has quit (Ping timeout: 244 seconds).
07:15:55 -!- Sgeo has joined.
07:27:57 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
07:30:44 -!- sqlircbot1 has joined.
07:30:57 -!- sqlircbot1 has quit (Read error: Connection reset by peer).
07:31:09 -!- Patashu has joined.
07:35:11 <zzo38> I got SQLIRCBOT working now. You can try sending VERSION, PING, and TIME requests to it at "sqlircbot1".
07:44:36 <zzo38> I will terminate it for now.
07:53:31 <zzo38> Yes; I only needed it on temporarily for testing
07:53:51 <zzo38> I can put back on if you want and I can also show you the program and schema if you like it too.
07:54:11 <zzo38> The VERSION, TIME, and PING requests are responded by triggers.
07:54:27 <b_jonas> yep, you said you'll do everything by triggers
07:54:36 <zzo38> (This isn't a built-in feature of SQLIRCBOT)
07:55:30 <b_jonas> does it respond to server PING requests, or else at least send a message every five minutes, so that the server doesn't kick it for being idle?
07:56:05 <zzo38> Responding to server PING requests is built-in to SQLIRCBOT; it is one of the few things that doesn't use triggers.
07:56:50 <zzo38> So, yes it does do that (and currently there is no way to turn that off).
07:58:03 <zzo38> You also don't need triggers to log the date/time; to do that you can use a DEFAULT clause in the CREATE TABLE statement.
07:59:42 <zzo38> The responding to client pings looks like this: CREATE TRIGGER ping_trigger before insert on irc_log when new.command = 'PRIVMSG' collate nocase and new.arg2 like (x'01'||'PING%') begin select ircsend('notice',new.nick,new.arg2); end;
07:59:53 <b_jonas> right. you really need to respond to PING messages because some non-freenode servers absolutely won't talk to you unless you do
08:00:06 <b_jonas> zzo38: there's one specific thing I'd like to ask you about though
08:00:21 <zzo38> Yes, the host program automatically responds to server pings regardless of the database schema.
08:00:56 <zzo38> What specific thing do you like to ask me about?
08:01:27 <b_jonas> you know how irc networks use one of two casefolding methods to fold the case of nicknames and channel names. the server tells you which one it uses in a 005 message early.
08:01:43 <zzo38> I know about IRC casefolding.
08:01:59 <b_jonas> technically, it tells you early enough that you could depend on that message, but it's very difficult to organize code in a way that guarantees you don't need to know about casefolding before the server tells you.
08:02:00 <zzo38> SQLIRCBOT implements a collation called IRCNOCASE which does that.
08:02:45 <b_jonas> so my take is that when I just tell the casefolding to the program before I set up the connection, and then verify it, and if the server tells it's wrong then I make the program die, because it's just easier to implement it that way.
08:03:26 <zzo38> Your database schema will need to know which kind of casefolding to use.
08:03:59 <zzo38> If you want you can add a trigger that checks that it is the correct one, but normally you probably don't need to.
08:04:59 <zzo38> If you are only logging, it doesn't normally matter which one you use anyways (unless you want to add an index by name), but if you want to do other stuff too then you would figure this out and do this.
08:06:10 <zzo38> That's how I handle it. If you want the non-English casefolding then you just will use the IRCNOCASE collation; for English casefolding use NOCASE collation.
08:06:37 <zzo38> Does this answer your question?
08:08:35 <b_jonas> I definitely need code in my bot that follows the nicks my bot sees. For that, I need to follow JOIN, QUIT, PART, KICK, NICK, 353, 366 messages, plus if I want to follow nickserv accounts too then I have to issue CAP and WHOx commands and follow ACCOUNT, 354, 315 messages.
08:09:41 <b_jonas> (Freenode has a set of three extensions that together let you track which nicks on channels are logged in to what nickserv accounts. I will need this for my bot ideally.)
08:12:59 <b_jonas> I have proof of concept code for this, but I'll have to make sane code.
08:15:23 <b_jonas> The other difficult part of irc handling I encountered is making sure you don't send too many messages so the server doesn't kick you. I have the throttling code working so I know exactly how much I can send, but the hard part is making the bot behave sanely when its queue fills up too much and it can't empty it because it keeps getting incoming requests. I don't have a good solution for that yet.
08:17:35 <b_jonas> zzo38: Does your bot attempt to handle that?
08:23:52 <zzo38> I currently have no such code although maybe it should have.
08:24:12 <zzo38> It contains no timing code at all for now because I cannot figure out how to get it to work.
08:25:21 <zzo38> However I assume that it wouldn't receive incoming requests too fast either.
08:25:34 <zzo38> Because the other client is also limited to the same speed.
08:28:02 <b_jonas> zzo38: you don't actually have to use timing code for this
08:30:28 <b_jonas> you only have to count bytes
08:30:59 -!- mitchs_ has quit (Ping timeout: 265 seconds).
08:40:07 <b_jonas> Basically, the irc server gives each connection a buffer of 3000something bytes (3072 I think, but I'm not sure). It removes a command from that buffer only after it's processed the previous command from that connection completely. If you send more input than fits in the buffer, it disconnects you. If you send a line longer than 512 bytes (counting the terminating LF) it also disconnects you.
08:40:16 -!- mitchs has joined.
08:40:52 <b_jonas> The easy way to know how much you can send is to reserve the last 7 bytes of that buffer, send a PING command before the buffer gets full, and continue sending only after the server has replied to that PING command.
08:41:05 <b_jonas> You could do more elaborate tracking, but this is the easiest to implement.
08:41:27 <b_jonas> (There's also another throttling on the server which is much more difficult to handle.)
08:41:56 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41795&oldid=41782 * Taktentus * (+136) new version and some other t
08:44:01 <b_jonas> Lots of this stupid specific information about IRC servers is not documented well and I have to acquire it from various pieces of partial documentation, from talking to people who know the servers on #freenode, from experimenting, and sometimes even from the source code.
08:46:20 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41796&oldid=41746 * Taktentus * (+16) add taktentus
08:53:25 <J_Arcane> I swear sometimes there's nothing worse than waking up later than someone who's already been awake long enough to get chatty ...
08:59:40 <zzo38> I will implement your ideas OK thank you for telling me how it is working.
09:02:03 <zzo38> Did you see my newest Magic: the Gathering cards and puzzle.3? (The solution is available too if you want it, although I didn't write the solution but I did make up the puzzle by myself.)
09:05:56 <J_Arcane> woo! http://www.theregister.co.uk/2015/02/02/raspberry_pi_model_2/
09:28:02 <zzo38> Later if you did then you can tell me.
09:52:08 <elliott> fizzie: is BF Joust scoring just the same as PageRank
09:59:10 -!- AndoDaan has joined.
09:59:55 <fizzie> It's at least pretty close.
10:09:34 -!- AnotherTest has joined.
10:22:19 -!- AndoDaan_ has joined.
10:24:23 -!- AndoDaan has quit (Ping timeout: 240 seconds).
10:27:16 -!- adu has quit (Quit: adu).
10:28:33 -!- _AndoDaan_ has joined.
10:30:23 -!- AndoDaan_ has quit (Ping timeout: 244 seconds).
10:34:43 -!- _AndoDaan_ has quit (Ping timeout: 250 seconds).
10:42:54 <Jafet> But you're ranking the jousters, not the pages.
11:16:33 -!- boily has joined.
11:29:02 <boily> int-e: int-ello. you set the topic to something very serious. what happened to dear Sir Fungellot?
11:39:39 -!- Patashu has quit (Ping timeout: 264 seconds).
11:48:53 -!- AndoDaan has joined.
11:52:41 <fizzie> boily: 22:11 -!- fungot [fis@selene.zem.fi] has quit [Quit: BEEP BOOP TIME TO TAKE A BREAK]
11:52:56 -!- PinealGlandOptic has left.
11:53:15 <fizzie> It's having a vacation.
11:54:29 -!- PinealGlandOptic has joined.
12:07:23 -!- AnotherTest has quit (Ping timeout: 256 seconds).
12:15:42 -!- hjulle has joined.
12:19:48 <boily> even bots have right to their own two paid vacation weeks.
12:19:53 <lambdabot> CYUL 021210Z 02020KT 1SM R06L/P6000FT/D R06R/P6000FT/D -SN BLSN SCT009 OVC022 M22/M26 A3000 RMK SN1SF2SC5 SLP163
12:20:20 -!- boily has quit (Quit: ACCLIMATISED CHICKEN).
12:58:59 <fizzie> It might be a bit more than two weeks.
13:47:36 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
14:01:49 <HackEgo> olist 974: shachaf oerjan Sgeo FireFly boily nortti
14:09:54 -!- oerjan has joined.
14:14:24 <Sgeo> oerjan: olist 974
14:16:30 -!- ProofTechnique has joined.
14:45:09 -!- TieSoul has quit (Quit: http://quassel-irc.org - Chat comfortably. Anywhere.).
14:45:26 -!- TieSoul has joined.
15:34:31 -!- SopaXorzTaker has joined.
15:36:54 -!- Koen_ has joined.
15:39:55 -!- PinealGlandOptic has quit (Quit: leaving).
15:41:43 -!- shikhin has joined.
15:47:06 <J_Arcane> Well this is perfectly barking: http://cj-johnson.github.io/Single-Tag_Website/
15:48:03 -!- Lymia has quit (Ping timeout: 264 seconds).
16:15:45 -!- mihow has joined.
16:15:47 -!- ^v^v has joined.
16:18:43 -!- ^v has quit (Ping timeout: 245 seconds).
16:40:26 -!- skj3gg has joined.
16:46:24 -!- Sprocklem has joined.
16:58:16 -!- vanila has joined.
17:00:12 <vanila> https://github.com/pigworker/PolyTest/blob/master/TLCAPoly.pdf?raw=true
17:02:37 -!- skj3gg has quit (Quit: ZZZzzz…).
17:05:48 -!- skj3gg has joined.
17:20:18 -!- Sprocklem has quit (Quit: [).
17:27:09 -!- adu has joined.
17:37:04 -!- FreeFull has quit.
17:44:07 -!- Phantom_Hoover has joined.
17:44:11 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
17:57:58 -!- oerjan has quit (Quit: Death to pdf urls that don't open in the browser!).
18:01:46 -!- ^v^v has quit (Read error: Connection reset by peer).
18:02:10 -!- ^v^v has joined.
18:06:03 -!- SopaXorzTaker has quit (Ping timeout: 264 seconds).
18:06:39 -!- skj3gg has quit (Quit: ZZZzzz…).
18:08:04 -!- bb010g has quit (Quit: Connection closed for inactivity).
18:15:41 -!- MDream has changed nick to MDude.
18:19:08 -!- Lymia has joined.
18:20:50 -!- S1 has joined.
18:23:39 -!- skj3gg has joined.
18:26:28 -!- arjanb has joined.
18:40:38 -!- mitchs has quit (Quit: mitchs).
18:47:11 <oren> What kind of math is required to take matrices of derivatives without disassembling them
18:50:58 <oren> for example d/dB A x B
18:52:07 <oren> I've been doing it by turning it into a summation and then turning the final formula back into a set of matrix operations
18:53:19 -!- AnotherTest has joined.
19:04:52 -!- shikhin has quit (Read error: Connection reset by peer).
19:06:04 -!- shikhin has joined.
19:16:48 -!- MoALTz_ has joined.
19:19:58 -!- MoALTz has quit (Ping timeout: 244 seconds).
19:21:42 <Sgeo> General Biotics study still not released
19:22:21 -!- MoALTz_ has quit (Quit: Leaving).
19:25:01 -!- S1 has quit (Quit: S1).
19:32:11 -!- ProofTechnique has joined.
19:47:30 -!- oren has quit (Ping timeout: 264 seconds).
19:57:12 -!- skj3gg has quit (Quit: ZZZzzz…).
20:01:06 -!- skj3gg has joined.
20:03:33 -!- FreeFull has joined.
20:06:49 -!- Patashu has joined.
20:13:12 -!- shikhin_ has joined.
20:15:15 -!- shikhin has quit (Ping timeout: 252 seconds).
20:15:45 -!- shikhin_ has changed nick to shikhin.
20:25:04 -!- Patashu has quit (Ping timeout: 244 seconds).
20:37:20 -!- oren has joined.
20:41:31 <myname> how comes bf2d is not on the wiki?
21:01:07 -!- FreeFull has quit (Ping timeout: 265 seconds).
21:05:26 -!- skj3gg has quit (Quit: ZZZzzz…).
21:06:32 -!- nys has joined.
21:12:55 -!- FreeFull has joined.
21:13:13 -!- skj3gg has joined.
21:58:26 -!- Koen_ has left.
22:08:33 -!- TieSoul_ has joined.
22:12:22 -!- TieSoul has quit (Ping timeout: 245 seconds).
22:20:04 -!- Tritonio has joined.
22:20:13 -!- dtscode has quit (Quit: (dtscode.io)).
22:21:22 -!- dts|pokeball has joined.
22:26:29 -!- MDream has joined.
22:27:35 -!- skj3gg has quit (Quit: ZZZzzz…).
22:29:30 -!- AnotherTest has quit (Ping timeout: 264 seconds).
22:30:07 -!- MDude has quit (Ping timeout: 255 seconds).
22:36:48 <zzo38> How should I work the send buffering into sqlircbot? I did already fix it not to send lines that are too long in case some IRC server disconnects you when that happens
22:37:47 <zzo38> (The IRCSEND function returns 1 if it could not send for any reason (line too long, parameters before the last one having spaces, any one having carriage returns and line feeds) or 0 if it can send, but that doesn't seem to fix the send buffer size too)
22:47:27 -!- adu has quit (Quit: adu).
22:50:37 <zzo38> I know I should PING the server and wait for the PONG response to know they have processed the message but I cannot seem to see where in this program such a thing can go without blocking everything else the program is doing.
22:52:59 -!- boily has joined.
22:54:06 <b_jonas> zzo38: you can store the messages you want to send in a table (you are probably already doing that), and add triggers to try to send some of the messages from that table both when (1) a new message is added and the table was empty, and (2) when you get the PONG response so you know the output buffer is cleared.
22:54:35 <b_jonas> The problem is when that table gets too long so you can never clear it and are sending very old messages.
22:57:01 <lambdabot> KSFO 022156Z 00000KT 8SM FEW002 BKN200 17/11 A3010 RMK AO2 SLP194 T01670106
23:01:44 <olsner> iirc it's possible to make tables that have C callbacks for some operations (like adding or deleting a row)
23:02:14 <zzo38> Yes you can do those things
23:02:49 <zzo38> However I have the sending messages done by the IRCSEND function exposed to the SQL program and want the C code in that function to handle it somehow
23:03:02 <olsner> (https://sqlite.org/vtab.html)
23:04:04 <zzo38> Yes, virtual tables, although I don't expect virtual tables to really help with what I am trying to do here at all
23:04:58 -!- oerjan has joined.
23:05:21 <b_jonas> zzo38: you don't need virtual tables for thsi
23:05:31 <b_jonas> I don't think they help either
23:08:06 <int-e> oerjan: GG updated.
23:09:17 <int-e> But hmm, it's still working up to one of Agatha's outbreaks.
23:11:20 <fizzie> A sudden violent spontaneous occurrence (usually of some undesirable condition) hth
23:11:39 <oerjan> well int-e has predicted one kind of that
23:11:40 <int-e> oerjan: oh you know when she starts to shout and make a stand
23:12:05 <oerjan> i don't think the word means that in english.
23:12:26 <int-e> I can't have that. The language is there to bend to my will.
23:13:06 <oerjan> although on the bright side, its cognate does so in norwegian, so i assume german is similar.
23:13:29 <oerjan> or well, sort of cognate.
23:13:59 -!- oren has quit (Ping timeout: 245 seconds).
23:14:39 <oerjan> i suspect both break and burst are cognates of it
23:15:23 <int-e> Ok, fine, outburst it is.
23:18:09 <oerjan> hm they're supposedly from different, but eerily similar PIE roots
23:18:21 <oerjan> probably just going back a bit further, then
23:20:00 <int-e> . o O ( /topic This channel got defunged | Breaking bubbles and ursting barriers | ... )
23:20:06 <zzo38> For now I just put in sleep for 1 millisecond per character sent, but probably I should change it later
23:20:19 <zzo38> Since the way I put now is not very good
23:20:22 <int-e> zzo38: that sounds unhealthy
23:22:07 <int-e> . o O ( All these typos are seriously denting my prefectionism. )
23:22:21 -!- oerjan has set topic: This channel got defunged | reaking ubbles and ursting arriers | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
23:22:41 <zzo38> I just now changed it to twice as fast, which probably still not so good but might work, I don't know
23:22:50 <boily> oerjan: usually spelled correctly?
23:23:15 <oerjan> boily: i think we had that yes
23:23:15 <int-e> t's ow sually pelled orrectly
23:23:18 -!- mitchs has joined.
23:24:22 <boily> int-e: sotp hruntig my bairn.
23:24:54 <oerjan> boily: some of those words are real tdnh
23:25:06 <int-e> I'm just sharing some pain here, hoping to alleviate it.
23:27:21 <boily> int-e: I only accept pain in capsaicin form.
23:27:22 <int-e> Well, there is a desensitizing effect at least.
23:27:39 <int-e> boily: Well then your brain shouldn't be hurting now.
23:27:58 <int-e> (Which it probably isn't, not literally at least, but never mind that.)
23:29:05 -!- adu has joined.
23:30:05 -!- oren has joined.
23:30:21 <boily> helloren. do you reak ubbles oo?
23:31:11 <int-e> boily: I see you're adopting my strategy.
23:31:42 <boily> adapt with the imes, I say.
23:33:08 <int-e> Hmm, that's a tricky one. Should we adopt adaptation or adapt adoptation...
23:34:49 <boily> that's exactly the kind of conundrum I'd be asking Sir Fungellot, but it seems to have been excised from the chännel...
23:36:52 * int-e may opt for adept adaptation.
23:37:06 -!- mihow has quit (Quit: mihow).
23:38:56 <zzo38> Maybe this way better: - Keep track of how many characters are send so far. - If it would exceed 3000, instead send a PING and insert the message to send into a temporary table. - If the PING has been sent and not responded yet, also insert into temporary table.
23:39:07 <zzo38> - Once the server responds by PONG then delete records from the temporary table. - This temporary table can have triggers to resend the message when records are deleted. - Once it runs out then reset the counter to zero and you can send messages normally again.
23:40:39 <zzo38> Do you expect this can work then?
23:49:02 -!- Lymia has quit (Ping timeout: 245 seconds).
23:54:18 -!- Tritonio has quit (Ping timeout: 252 seconds).
23:55:45 <oerjan> zzo38: you need to subtract the size of a PING from the 3000
23:56:06 <zzo38> Yes I forgot to mention that
23:56:22 <zzo38> That would be 8 bytes though
23:58:31 <zzo38> (Since you can write "PING 1" followed by a carriage return and a line feed, which will be 8 bytes in total)
00:02:44 -!- boily has quit (Quit: STYLISH CHICKEN).
00:11:10 -!- Lymia has joined.
00:12:17 -!- Lymia has quit (Client Quit).
00:12:31 -!- Lymia has joined.
00:12:37 -!- MDream has quit (Quit: later chat).
00:12:51 -!- MDude has joined.
00:19:17 -!- vanila has quit (Quit: Leaving).
00:26:51 <oren> http://nanoha.wikia.com/wiki/Barrier_Burst
00:28:31 <oren> Is that the reference?
00:29:38 <oerjan> or well, i guess int-e should answer that.
00:31:38 -!- hjulle has quit (Ping timeout: 245 seconds).
00:42:57 -!- Sprocklem has joined.
00:59:52 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
01:10:24 -!- ocharles_ has quit (Ping timeout: 272 seconds).
01:12:28 -!- supay has quit (Read error: Connection reset by peer).
01:21:19 -!- supay has joined.
01:21:40 -!- ocharles_ has joined.
01:29:58 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:44:31 -!- dts|pokeball has quit (Ping timeout: 256 seconds).
01:54:21 -!- dts|pokeball has joined.
02:05:50 -!- Phantom_Hoover has joined.
02:12:09 -!- shikhin_ has joined.
02:15:21 -!- shikhin has quit (Ping timeout: 250 seconds).
02:47:28 -!- Lymia has quit (Ping timeout: 245 seconds).
02:58:37 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
03:09:48 -!- ^v has joined.
03:16:51 -!- Phantom_Hoover has joined.
03:32:53 -!- ^v has quit (Ping timeout: 245 seconds).
03:46:04 -!- Lymia has joined.
04:01:56 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
04:04:55 -!- bb010g has joined.
04:25:22 -!- ProofTechnique has joined.
04:32:37 -!- MDude has changed nick to MDream.
04:33:51 -!- oerjan has quit (Quit: Nite).
04:57:05 -!- shikhin_ has quit (Ping timeout: 244 seconds).
05:18:59 <oren> yay i finished my little clock app
05:21:40 <oren> http://snag.gy/ZWoOa.jpg
05:23:32 <oren> now how to make it turing complete?
05:24:03 <oren> there are some who say "not everything has to be turing complete"
05:24:14 -!- nys has quit (Quit: quit).
05:24:40 <zzo38> Of course not everything has to be turing complete, and anyways I don't know. But you are certainly free to try to figure out how, please!
05:25:26 <oren> since I wrote all this date-handling code, the only data type should be dates
05:26:58 <oren> AHA: the loop mechanism is by scheduling things to be done at another tiem
05:29:27 <oren> and conditions are simply comparisons of times
05:29:29 -!- Sprocklem has quit (Ping timeout: 256 seconds).
05:47:21 <oren> actually, a better set of conditions would be "is the program scheduled to run at time t" and "has time t passed yet"
05:47:48 <oren> and then you can tell the program to run itself at a later time
05:52:23 <oren> Yeh. So the basic commands are T(...) where .. runs only if T has passed, T?(...) where ... runs only if T is on the schedule, and T. which puts T on the schedule. T must be replaced with a relative orabsolute timestamp.
05:53:12 <oren> The program then runs once upon open, and then once at each time that is on the schedule.
05:54:17 <oren> perhaps there should also be T/ which crosses T off the schedule
05:54:56 <Jafet> Or, things that should remain on the schedule must put themselves back each time.
05:55:28 <oren> Jafet: yeah, that could work too.
05:55:49 <oren> in other words, each run is a "revising" of the schedule
05:56:48 <Jafet> Well, it becomes a to-do list instead, such as http://www.dangermouse.net/esoteric/whenever.html
06:07:56 <Sgeo> oren: of course I need to go listen to that video
06:08:02 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
06:09:15 <Sgeo> I hear sounds that remind me of Das Boot
06:09:24 <Sgeo> (Which I've only listened to because of Activeworldsa)
06:11:36 -!- dts|pokeball has quit (Quit: Leaving).
06:17:44 <zzo38> {1}, {T}, Sacrifice a permanent: You lose the game.
06:55:34 -!- TieSoul_ has changed nick to TieSoul.
07:16:20 <FreeFull> oren: Make your clock app do elliptic curve encryption
07:19:24 -!- technomad has joined.
07:21:33 -!- dianne_ has quit (Quit: Lost terminal).
07:23:36 -!- dianne has joined.
07:29:02 <HackEgo> technomad: 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.)
07:32:47 -!- Patashu has joined.
07:35:50 -!- shikhin has joined.
07:38:17 -!- technomad has left ("dftba").
07:38:18 -!- arjanb has quit (Quit: bbl).
08:12:42 -!- shikhin_ has joined.
08:15:31 -!- shikhin has quit (Ping timeout: 245 seconds).
08:22:53 -!- adu has quit (Quit: adu).
08:26:05 -!- AndoDaan_ has joined.
08:28:33 -!- AndoDaan has quit (Ping timeout: 256 seconds).
09:13:34 -!- zzo38 has quit (Ping timeout: 245 seconds).
09:31:34 -!- AnotherTest has joined.
09:36:19 -!- shikhin_ has changed nick to shikhin.
09:48:15 <oren> an extension on the assignment I pulled an all-nighter to finish. why am i angry
09:50:05 <oren> probably because i'm tired and cranky. going to sleep now
10:00:24 -!- Tritonio has joined.
10:00:43 -!- Phantom_Hoover has joined.
10:32:17 -!- ^v^v has quit (Read error: Connection reset by peer).
10:32:40 -!- ^v^v has joined.
10:37:57 -!- Tritonio_ has joined.
10:41:06 -!- Tritonio has quit (Ping timeout: 252 seconds).
10:44:35 -!- Tritonio_ has changed nick to Tritonio.
10:52:57 -!- hjulle has joined.
11:10:37 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41797&oldid=41795 * Taktentus * (+117) /* Syntax */
11:11:39 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41798&oldid=41797 * Taktentus * (+23) /* Syntax */
11:12:09 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41799&oldid=41798 * Taktentus * (-4) /* suma */
11:12:38 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41800&oldid=41799 * Taktentus * (+9) /* External resources */
11:22:15 -!- boily has joined.
11:47:31 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
12:05:33 -!- AnotherTest has quit (Ping timeout: 250 seconds).
12:21:16 -!- boily has quit (Quit: PROTIST CHICKEN).
12:21:40 -!- oerjan has joined.
12:25:15 -!- hjulle has quit (Ping timeout: 265 seconds).
12:32:34 -!- PinealGlandOptic has joined.
12:43:19 -!- Patashu has quit (Ping timeout: 264 seconds).
12:47:59 -!- hjulle has joined.
12:49:24 -!- _AndoDaan_ has joined.
12:54:13 -!- Eolus has joined.
12:57:24 -!- AndoDaan_ has quit (Ping timeout: 250 seconds).
12:57:38 -!- Eolus has quit (Changing host).
12:57:38 -!- Eolus has joined.
13:00:37 <oren> Are the computable numbers identical to the rationals?
13:01:03 <oerjan> e.g. pi and e are computable
13:01:28 <elliott> also, well, lots of things. most things :p
13:01:38 <oerjan> most continuous functions you've heard of are computable
13:01:51 <oerjan> discontinuous functions cannot be
13:02:03 <oren> I suppose if they weren't computable it wouldn't be very useful
13:02:25 <elliott> Chaitin's constant isn't computable, though
13:03:27 <oren> elliott: oh god, why would anyone even construct programs randomly
13:03:37 <b_jonas> oerjan: you mean continuous in which topology?
13:03:45 <b_jonas> is this about functions on the reals?
13:03:51 <elliott> oren: you can use chaitin's constant to decide the halting problem
13:04:07 <Eolus> http://youtu.be/MuOvqeABHvQ
13:04:44 <b_jonas> meh, pi is just square root 10 minus some correction offset
13:05:05 <oerjan> of course complex numbers also work
13:08:11 <oren> what is the probability that a random program willdo something useful?
13:08:32 <b_jonas> oerjan: but in that case, aren't there still a continuum many continuous functions from reals to reals, whereas only like countably many computable functions?
13:09:12 <b_jonas> but I guess I've probably only seen a countably many
13:11:44 <oerjan> b_jonas: the "you've heard of" was important
13:13:15 <oerjan> basically, you won't get a non-computable continuous function by accident
13:15:38 -!- hjulle has quit (Ping timeout: 246 seconds).
13:16:11 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
13:16:33 -!- ais523 has joined.
13:53:49 -!- ProofTechnique has joined.
13:53:58 -!- Tritonio has quit (Ping timeout: 252 seconds).
13:54:46 -!- Niedaw has joined.
13:55:40 <Eolus> did Tennessee the heaven hurt when you fell from the it
13:56:44 <Niedaw> Can You look taktentus?
13:56:45 <HackEgo> Niedaw: 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.)
13:57:53 <Niedaw> What is the best interpreter? Binary native , jscript or script lang for ex. python
13:57:54 <Eolus> so oerjan niedaw needs your help since you are of the smart and I'm terrible at helping persons of such nature
13:58:20 <Eolus> for ex? give us an exact language you want those for
13:58:47 <oerjan> as a rule i never help people when pushed to it hth
13:59:13 <Eolus> oerjan you want some lemon bread
13:59:27 <Eolus> I made like seven loafs
13:59:31 <oerjan> i don't think so. my stomach is queasy today.
13:59:55 <Eolus> oerjan hopes to much
14:01:23 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
14:01:28 <Niedaw> Is necessqry to write compilator? Anybody use rodacy any compilator of esolang?
14:01:32 <oerjan> i do a rare visit of reddit.com/r/physics and learn that the gravitational wave discovery from last year is now officially dead http://www.nature.com/news/gravitational-waves-discovery-now-officially-dead-1.16830
14:02:43 <Eolus> gravity is a theory
14:02:53 <oerjan> earth to earth, dust to dust
14:03:37 <oerjan> Eolus: theory means something more in science than in ordinary language
14:04:05 <Eolus> Nuclear fire to death
14:05:00 <Eolus> Alas let it be the knowns of the stuff that the gravities lives in the water cake of the stuff when to do the things we like do
14:05:13 <Eolus> I can't grammar some the times : (
14:05:49 <Eolus> Or well I am of the randoms because I am most unstable of the bunch lol
14:06:38 <Eolus> Ipecac is good for the soul
14:06:54 -!- skj3gg has joined.
14:07:16 -!- shikhin has changed nick to minicat.
14:07:43 -!- minicat has changed nick to shikhin.
14:08:32 <lambdabot> <hint>:1:1: parse error on input ‘{’
14:08:36 <Niedaw> can You Check interpreter taktentus ?
14:08:44 <Eolus> thank you lambdabot
14:09:09 <Eolus> I don't know Niedaw
14:09:11 <oerjan> { in haskell always requires something before it
14:09:16 -!- ProofTechnique has joined.
14:09:29 <lambdabot> Just *Exception: <interactive>:3:1-7: Missing field in record construction
14:09:46 <Eolus> oerjan I didn't know that
14:09:54 <Eolus> probably why I got so many parse errors
14:10:04 <oerjan> > let { x = 1 } in x+1
14:10:15 <oerjan> those last brackets are redundant though
14:11:31 -!- ProofTechnique has quit (Client Quit).
14:11:35 <Eolus> this > let { x = 1 in x+1 is what you can do, or does it have to be { x = 1 } in x+1
14:12:06 <Eolus> two brackets to seperate the definition from the equation given?
14:12:09 -!- shikhin_ has joined.
14:12:36 <Eolus> or one bracket to signify a new line to split from the last one?
14:12:48 -!- ProofTechnique has joined.
14:12:52 -!- Niedaw has quit (Ping timeout: 246 seconds).
14:13:17 <oerjan> Eolus: if you have one bracket, you must have both.
14:13:46 <oerjan> but if you leave them out, they'll be automatically inserted by the parser in that case
14:14:09 <lambdabot> parse error (possibly incorrect indentation or mismatched brackets)
14:14:16 <oerjan> haskell's indentation blocks are syntactic sugar for { ; }
14:14:32 <Eolus> 1 minute till school bus
14:15:03 -!- shikhin has quit (Ping timeout: 264 seconds).
14:16:35 -!- skj3gg has quit (Quit: ZZZzzz…).
14:20:16 <J_Arcane> I must say, JS syntax has its flaws, but jQuery is downright unsightly.
14:21:52 -!- oren has quit (Ping timeout: 240 seconds).
14:25:44 -!- shikhin_ has changed nick to shikhin.
14:26:56 -!- skj3gg has joined.
14:27:29 -!- GeekDude has joined.
14:27:40 -!- GeekDude has quit (Remote host closed the connection).
14:27:52 -!- GeekDude has joined.
14:28:10 -!- GeekDude has changed nick to Guest83288.
14:29:05 -!- Guest83288 has quit (Changing host).
14:29:06 -!- Guest83288 has joined.
14:29:19 -!- Guest83288 has changed nick to GeekDude.
14:34:59 -!- nys has joined.
14:38:17 -!- oerjan has quit (Quit: Later).
14:44:18 -!- oren has joined.
14:59:39 -!- skj3gg has quit (Quit: ZZZzzz…).
15:04:48 -!- skj3gg has joined.
15:27:41 -!- spiette has joined.
15:32:14 -!- ais523 has quit (Quit: be back in a bit).
15:32:59 -!- SopaXorzTaker has joined.
15:43:18 -!- Sprocklem has joined.
15:48:19 -!- AnotherTest has joined.
15:48:42 -!- ^v^v has quit (Read error: Connection reset by peer).
15:48:43 -!- Sprocklem has quit (Ping timeout: 255 seconds).
15:49:06 -!- ^v^v has joined.
15:50:47 -!- ais523 has joined.
15:52:33 -!- Tritonio has joined.
15:53:14 -!- skj3gg has quit (Quit: ZZZzzz…).
16:02:19 -!- skj3gg has joined.
16:17:21 -!- MDream has changed nick to MDude.
16:17:41 -!- ais523 has quit (Quit: almost out of battery).
16:17:44 -!- Eolus has quit (Quit: Connection closed for inactivity).
16:17:48 -!- adu has joined.
16:40:39 -!- mihow has joined.
16:58:39 -!- skj3gg has quit (Quit: ZZZzzz…).
17:06:57 -!- skj3gg has joined.
17:07:25 -!- Tritonio has quit (Remote host closed the connection).
17:08:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:08:21 -!- Tritonio has joined.
17:17:21 -!- Tritonio has quit (Remote host closed the connection).
17:17:51 -!- Tritonio has joined.
17:21:37 -!- Phantom__Hoover has joined.
17:21:38 -!- Phantom_Hoover has joined.
17:25:24 -!- Phantom__Hoover has quit (Client Quit).
17:53:22 <J_Arcane> https://www.reddit.com/r/nethack/comments/2tluxv/yaap_fullauto_bot_ascension_bothack
17:54:13 -!- skj3gg has quit (Quit: ZZZzzz…).
17:59:52 -!- Lymia has quit (Ping timeout: 240 seconds).
18:00:10 -!- Koen_ has joined.
18:01:32 -!- mihow has quit (Ping timeout: 245 seconds).
18:06:07 -!- SopaXorzTaker has quit (Ping timeout: 264 seconds).
18:09:20 -!- mihow has joined.
18:10:13 -!- Tritonio has quit (Remote host closed the connection).
18:13:59 -!- FreeFull has quit (Ping timeout: 245 seconds).
18:18:13 -!- SopaXorzTaker has joined.
18:29:06 -!- arjanb has joined.
18:30:22 -!- TieSoul has changed nick to TieWorking.
18:40:44 -!- FreeFull has joined.
18:45:05 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:47:09 -!- Koen_ has quit (Quit: Koen_).
19:05:56 -!- skj3gg has joined.
19:08:54 -!- mihow has quit (Quit: mihow).
19:10:49 -!- Raven has joined.
19:12:20 <HackEgo> Raven: 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.)
19:18:48 -!- bb010g has joined.
19:18:50 -!- Raven has quit (Quit: Saliendo).
19:22:28 -!- MoALTz has joined.
19:26:47 -!- `^_^v has joined.
19:40:40 -!- mihow has joined.
19:42:12 -!- ^v has joined.
19:43:07 -!- MoALTz has quit (Quit: Leaving).
19:45:15 -!- Tritonio has joined.
19:46:56 -!- MoALTz has joined.
19:56:49 -!- Lymia has joined.
20:02:29 -!- supay has changed nick to supay|zzZZ.
20:03:38 -!- Patashu has joined.
20:08:49 -!- ^v has quit (Read error: Connection reset by peer).
20:12:21 -!- shikhin_ has joined.
20:12:33 -!- S1 has joined.
20:12:33 -!- S1 has changed nick to puritania.
20:15:23 -!- shikhin has quit (Ping timeout: 240 seconds).
20:15:38 -!- skj3gg has quit (Quit: ZZZzzz…).
20:19:32 -!- skj3gg has joined.
20:25:56 -!- Patashu has quit (Ping timeout: 245 seconds).
20:43:19 -!- lifthrasiir has quit (Ping timeout: 272 seconds).
20:57:51 -!- lifthrasiir has joined.
20:59:01 -!- SirCmpwn has quit (Read error: Connection reset by peer).
20:59:18 -!- ^v^v has quit (Read error: Connection reset by peer).
20:59:45 -!- ^v^v has joined.
21:01:52 -!- AnotherTest has quit (Remote host closed the connection).
21:02:28 -!- SirCmpwn has joined.
21:11:46 -!- ais523 has joined.
21:13:17 -!- Koen_ has joined.
21:14:19 -!- Koen__ has joined.
21:14:20 -!- Koen_ has quit (Read error: Connection reset by peer).
21:15:23 -!- ais523 has quit (Excess Flood).
21:15:40 <Koen__> well, good ol' connection reset bug is back. hello to you all
21:16:36 -!- ais523 has joined.
21:18:46 -!- augur has quit (Read error: Connection reset by peer).
21:18:52 -!- oren has quit (Ping timeout: 240 seconds).
21:18:57 -!- puritania has changed nick to S1.
21:20:35 -!- augur has joined.
21:32:04 -!- Frooxius has quit (Ping timeout: 255 seconds).
21:35:59 -!- oren has joined.
21:42:37 -!- skj3gg has quit (Quit: ZZZzzz…).
21:45:07 -!- ais523 has quit (Read error: Connection reset by peer).
21:45:24 -!- ais523 has joined.
21:47:38 <myname> if you want to write a paper about twodimensional esolangs, what the hell would you cite?
21:50:01 <myname> are there _any_ serous sources?
21:52:22 <HackEgo> [wiki] [[Special:Log/newusers]] create * CodeNMore * New user account
22:04:08 -!- S1 has quit (Quit: S1).
22:19:21 -!- esowiki has joined.
22:19:25 -!- esowiki has joined.
22:19:26 -!- esowiki has joined.
22:20:37 -!- esowiki has joined.
22:20:38 -!- glogbot has joined.
22:20:41 -!- esowiki has joined.
22:20:42 -!- esowiki has joined.
22:21:00 -!- FireFly has quit (Excess Flood).
22:22:26 -!- FireFly has joined.
22:25:09 -!- Frooxius has joined.
22:26:31 -!- 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?").
22:27:43 -!- Eolus has joined.
22:29:11 <Eolus> aww jquery is good ;-;
22:29:30 <Eolus> I made a jquery validation engine once J_Arcane
22:30:23 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
22:31:56 <Phantom_Hoover> myname, not directly, but his name's ville salo and if you find his website it'll be there somewhere
22:34:25 <J_Arcane> I'm now at the point of debating whether I want to soldier on into the jQuery course, or backtrack and do the full HTML/CSS tutorial first.
22:34:43 <J_Arcane> also I'm having some kind of nervous fit about resumes for some reason, so that's fun.
22:34:47 <Eolus> http://twapa.deviantart.com/art/Bucket-of-Tits-323028841
22:37:56 <J_Arcane> Sorta the trouble with .js, innit, depending on what you're doing anyway. It's all the mucking about with the other parts of the web you have to deal with ...
22:41:16 -!- adu has quit (Quit: adu).
22:52:10 <Taneb> A lot of my maths lectures now-adays make me think "Wow, Category Theory is a really good idea"
22:54:04 <b_jonas> Taneb: do you also think that about general topology too?
22:54:06 -!- hjulle has joined.
22:54:11 <b_jonas> or other crazy topics like that
22:54:57 <Taneb> b_jonas, I haven't done any topology
22:58:18 -!- Lymia has quit (Ping timeout: 245 seconds).
23:00:07 -!- Lymia has joined.
23:02:38 <oren> I am reading a marvellous book: A child's history of England, by Charles Dickens
23:03:14 <oren> I was previously unaware that Dickens wrote any nonfiction
23:03:35 -!- oerjan has joined.
23:08:01 -!- bb010g has quit (Ping timeout: 245 seconds).
23:08:55 -!- tswett has joined.
23:09:06 -!- ocharles_ has quit (Ping timeout: 252 seconds).
23:09:16 -!- supay|zzZZ has quit (Ping timeout: 245 seconds).
23:09:31 <tswett> Arright, let's see if I can make the spec for Al Dente better.
23:11:52 -!- `^_^v has quit (Ping timeout: 240 seconds).
23:12:36 -!- hjulle has quit (Ping timeout: 245 seconds).
23:13:18 -!- Eolus has quit (Ping timeout: 245 seconds).
23:14:55 -!- vanila has joined.
23:17:59 <oerjan> tswett: i find the syntax insufficiently pasta-inspired hth
23:18:24 <tswett> Sorry, but the syntax and semantics of the language are now immutable.
23:18:35 -!- supay|zzZZ has joined.
23:19:50 <oerjan> taktentus looks like a language with polish
23:20:41 -!- supay|zzZZ has quit (Changing host).
23:20:41 -!- supay|zzZZ has joined.
23:20:43 -!- ProofTechnique has joined.
23:21:14 <tswett> Sven said, Ted, send ten tents. Ted said, Sven, send ten cents. When Sven sent Ted ten cents, then Ted sent Sven ten tents.
23:22:27 <oerjan> those were some cheap tents
23:23:20 -!- ocharles_ has joined.
23:23:29 <tswett> Maybe they were some valuable cents.
23:23:57 <tswett> Or maybe Ted didn't really want the money and was just being a jerk.
23:31:28 -!- bb010g has joined.
23:32:10 -!- Eolus has joined.
23:32:19 <oren> If Ted and Sven live in England, then they need to send pence
23:33:41 -!- mitchs has quit (Ping timeout: 250 seconds).
23:33:45 <int-e> Penn hedged a plan to end the tent renting trend by sending ten tanks to tend to Ted and Sven.
23:34:22 -!- mitchs_ has joined.
23:35:11 <int-e> Clearly Ted should be called Trent.
23:35:38 <Taneb> It's stuff like "This is a group homomorphism." "This is a ring homomorphism" "This is a linear transformation" and like they are all the same shape of things
23:36:49 <Taneb> And my mind is going "Yes, these are all subcategories of eachother, of course they are the same thing"
23:36:51 <oerjan> Taneb: a linear transformation is of course a vector space homomorphism
23:37:03 <oerjan> it's just called something else for hysterical raisins
23:37:09 <Taneb> oerjan, yes, that was pointed out
23:37:31 <tswett> An arrow is just a natural transformation between two functors on 1.
23:37:31 <oerjan> and all of those fit in the same universal algebra framework
23:37:44 <Taneb> It doesn't really help matters much that my ring theory lecturer is the same person as my linear algebra lecturer
23:38:01 <HackEgo> Arrows are just strong monads in the category of profunctors.
23:38:13 <HackEgo> Morphisms are just elements of the Hom-set of a pair of objects.
23:38:21 <Taneb> How do profunctors form a category?
23:38:31 <oerjan> tswett: you mean arrows = morphisms, right?
23:38:56 <oerjan> `learn A morphism is just a natural transformation between two functors on 1.
23:38:59 <HackEgo> Learned 'morphism': A morphism is just a natural transformation between two functors on 1.
23:40:22 <vanila> `learn Zygohistomorphic-prepromorphism Used when you really need both semi-mutual recursion and history and to repeatedly apply a natural transformation as you get deeper into the functor
23:40:24 <HackEgo> Learned 'zygohistomorphic-prepromorphism': Zygohistomorphic-prepromorphism Used when you really need both semi-mutual recursion and history and to repeatedly apply a natural transformation as you get deeper into the functor
23:40:47 <oerjan> vanila: `learn doesn't work that way
23:41:05 <Taneb> I am right in thinking that the category of linear transformations and the category of ring homomorphisms are both subcategories of the category of group homomorphisms?
23:41:20 <HackEgo> ls: cannot access wisdom/zy*: No such file or directory
23:41:38 <tswett> Linear transformations and ring homomorphisms are objects of categories?
23:41:54 -!- vanila has left ("Leaving").
23:41:57 <tswett> `? something HackEgo doesn't know anything about
23:41:58 <HackEgo> something HackEgo doesn't know anything about? ¯\(°_o)/¯
23:42:27 <Taneb> tswett, morphisms of categories
23:42:41 <int-e> . o O ( `learn learn `learn does not work this way. )
23:42:56 -!- adu has joined.
23:43:22 <Taneb> tswett, which I guess makes them objects of another category? Category theory hurts my head sometimes
23:43:24 <HackEgo> ¯\(°_o)/¯ is a misspelling of ¯\(°_o)/¯
23:44:30 <tswett> Lemme see. A ring homomorphism could be seen as a group homomorphism, I guess.
23:44:40 -!- CakeMeat has joined.
23:44:46 <tswett> But going from the ring homomorphism to the group homomorphism forgets information.
23:45:13 <CakeMeat> my irc cloud account doesn't work
23:45:30 <Taneb> tswett, isn't the homomorphism just a function with a few restrictions?
23:45:53 -!- CakeMeat has quit (Client Quit).
23:46:13 <tswett> But turning the domain and codomain from rings into groups forgets information.
23:46:45 -!- CakeMeat has joined.
23:46:50 <Taneb> Is it possible for there to be two rings with the same set and addition?
23:47:24 <oerjan> there's clearly a forgetful functor from rings to groups, but i don't know that those are thought of as subcategories?
23:47:31 -!- adu has quit (Ping timeout: 255 seconds).
23:47:37 <Taneb> Hmm, I may be wrong then
23:47:46 <tswett> I think the integers with x added have the same addition group as the integers with sqrt(2) added.
23:48:09 <tswett> But the integers with sqrt(2) and the integers with sqrt(3).
23:48:26 <tswett> The addition group is Z^2 either way.
23:48:44 <int-e> tswett: but those are isomorphic; they don't have the same carrier.
23:49:00 <int-e> But for example, GF(2^2) has the same additive structure as (Z/2Z)^2.
23:49:03 <tswett> Well then, make them have the same carrier.
23:49:37 <tswett> As the homotopy type theorists say, if x is isomorphic to y, then x is y.
23:50:02 <int-e> (the latter dontes pairs of elements of Z/2Z with operations performed pointwise: (a,b)*(c,d) = (a*c,b*d))
23:50:50 <int-e> tswett: Sorry, you're right of course.
23:51:23 * int-e got distracted from the point (which is that Z[x]/(x^2-3) is a different ring from Z[x]/(x^2-2).)
23:52:04 <int-e> and I'm using these representations because they have the same carrier if one chooses polynomials of degree less than 2 as representatives.
23:52:26 <oerjan> CakeMeat: right now you don't sound like the kind of person elliott would want to respond to hth
23:52:28 <int-e> CakeMeat: It's "loosens", hth.
23:52:57 <CakeMeat> And this stupid client wonr let me log on
23:53:19 <CakeMeat> I just wanna contact him so I can leave this stupid client
23:54:16 <oerjan> CakeMeat: you can log on by sending private messages to nickserv
23:54:23 <int-e> Sorry, I just happen to think that irccloud is a really stupid idea.
23:54:44 <int-e> oerjan: that would require a registered nick :P
23:54:56 <oerjan> int-e: i think Lilax is registered...
23:55:15 <CakeMeat> there is NO nick serv system message on this
23:55:32 <CakeMeat> I can do /msg nickserv identify password
23:55:42 <CakeMeat> because /msg isn't a thing on this clienr
23:56:09 <int-e> "android irc client", but even so...
23:56:17 <oerjan> CakeMeat: that sounds very implausible
23:56:23 -!- Eolus has quit.
23:56:25 <CakeMeat> Nope won't let me log into lilax
23:56:34 <int-e> no "private message" or "direct message" feature?
23:56:37 -!- CakeMeat has changed nick to Lilax.
23:56:46 <oerjan> either there is a way to send private messages, or that client should be banned hth
23:57:07 -!- Eolus has joined.
23:58:18 -!- Eolus has changed nick to Guest80873.
23:58:25 <Taneb> I am going to bed now
23:58:57 <int-e> Hi Lilax, Eolus says he isn't you, what's your take on this matter of contention?
23:59:27 <Lilax> I logged out for a second and my account was taken
23:59:44 <Lilax> I know elliotts thing
00:00:53 <int-e> Is it the thing where he suddenly bans you from the channel?
00:01:09 <Lilax> Not that the other thing ;---;
00:01:27 <Lilax> nvm Elliott that eolus is a fake
00:01:36 <oerjan> elliott is so polite these days
00:01:40 <elliott> it's a dead client connecting, from the looks of it
00:01:44 <elliott> it's from irccloud at least
00:02:05 <Lilax> did int-e get a message then?
00:03:01 <int-e> I mean I got messages but nothing private. Err...
00:03:41 <Lilax> it won't let me join from irc cloud ;-;
00:03:54 <Lilax> fresh batch of frownies
00:04:01 <int-e> Sorry, I can't help milking a dead horse for puns.
00:04:06 <int-e> Or mixing metaphors.
00:06:09 -!- SirCmpwn has quit (Remote host closed the connection).
00:06:48 <Lilax> for some reason its faded on irc cloud
00:07:01 <Lilax> then it doesn't register as sent through
00:07:07 -!- SirCmpwn has joined.
00:08:07 <Lilax> :Nick/channel is temporarily unavailable
00:08:35 <Lilax> this is what happens when I Try to log into that account
00:08:37 <int-e> oerjan: Too bad the pronunciation doesn't work out: "When I see a bad pun I just nod and simile."
00:09:50 <elliott> Lilax: you need to send "recover nick password" to nickserv in that case
00:10:23 -!- FireFly has quit (Changing host).
00:10:23 -!- FireFly has joined.
00:10:48 <elliott> it looks like /pv nickserv or /query nickserv
00:10:53 <elliott> (/pv?? what a weird client)
00:11:51 <int-e> also /quote nickserv ... (communication with services often has builtin support in the IRC server, so "nickserv" and "chanserv" work as IRC commands)
00:13:33 -!- Sprocklem has joined.
00:13:58 <int-e> sorry, elliott seems to have read some actual client documentation...
00:14:34 <oerjan> int-e: that's cheating!
00:14:59 <Lilax> dislike everything
00:16:03 -!- Lilax has quit (Read error: Connection reset by peer).
00:16:07 <oerjan> does that include chocolate?
00:18:31 <int-e> oh, "ten cent tents" can be parsed two ways.
00:20:28 -!- Lilax has joined.
00:20:51 -!- Lilax has changed nick to Guest92557.
00:21:39 -!- Tritonio has quit (Remote host closed the connection).
00:23:15 -!- adu has joined.
00:23:38 <int-e> http://www.twogag.com/archives/1887
00:23:45 <HackEgo> [wiki] [[Al Dente]] http://esolangs.org/w/index.php?diff=41801&oldid=41775 * 98.243.16.185 * (+2691) Add some illustrative examples
00:24:49 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:27:10 -!- mihow has quit (Quit: mihow).
00:27:31 <Guest92557> My Lilax account will expire in 30 days if another Lilax comes in here or anyone named after me and my nicks itz not me
00:27:57 -!- Guest92557 has quit (Quit: Guest92557).
00:28:17 -!- Guest92557 has joined.
00:28:45 <int-e> use a hammer or a brick
00:30:49 -!- MoALTz_ has joined.
00:33:23 -!- Guest92557 has quit (Remote host closed the connection).
00:33:34 -!- MoALTz has quit (Ping timeout: 245 seconds).
00:33:35 <int-e> oh the usual, frustration, hatred, and outbreaks of outbursts.
00:38:46 -!- shikhin_ has quit (Read error: Connection reset by peer).
00:50:25 -!- ais523 has quit.
01:05:03 -!- tromp_ has quit (Ping timeout: 244 seconds).
01:07:35 -!- ^v^v has quit (Read error: Connection reset by peer).
01:08:00 -!- ^v^v has joined.
01:10:02 -!- blockzombie has joined.
01:10:51 <blockzombie> I'm looking at Forth and some legit esolangs like False, True and Dup.
01:11:31 <oerjan> might add Underload then
01:11:32 <blockzombie> I'd like to evolve and optimise algorithms using a GA
01:11:50 <oerjan> another concatenative one
01:12:32 <blockzombie> I'm not so much going for absurdity but I would like to enable self-modifying code
01:12:39 -!- tswett2 has joined.
01:13:07 <blockzombie> Do all these have separate program memory from the stack?
01:13:52 <int-e> Hmm, what exactly is self-modifying code? Is the lambda calculus self-modifying?
01:14:02 -!- tromp_ has joined.
01:14:13 <oerjan> well there's the control/return stack too, at least
01:14:22 <oerjan> (don't know about True and Dup)
01:14:39 <oerjan> ok in that case underload is also self-modifying
01:14:53 <blockzombie> I think the practical matter of self-modification is reaching into program data and reading constants and references
01:15:37 <blockzombie> yeah but the stack and the symbol table are disconnected right?
01:15:48 -!- tswett has quit (Ping timeout: 245 seconds).
01:16:01 <oerjan> well underload has no symbol table
01:16:11 <blockzombie> I'd like to have a small instruction set but I'm aware of the turing tarpit quote from perlis
01:18:57 <oerjan> ^ul (Underload! )(~:S:^):^
01:20:07 <oerjan> you can also think of it as rewriting the program
01:24:10 <blockzombie> so awesome there's a compiler written in redcode
01:26:57 <blockzombie> nice... scala underload compiler that compiles scala
01:27:09 <oerjan> i wrote one in emmental, which btw is a self-modifying language where you modify the language _itself_. so my interpreter works by turning it into underload
01:27:24 <oerjan> oh and that's also stacky
01:27:56 -!- tswett3 has joined.
01:29:47 <blockzombie> is the interpreter loaded into the program space?
01:30:29 <oerjan> i recall that you cannot really use the jvm stack directly for a stack language because the type checker won't accept it...
01:30:51 <blockzombie> what I'd love is a language where I can build crossover functions for a GA where the genotype corresponds to a program
01:30:57 -!- shikhin has joined.
01:31:25 <blockzombie> You can't use the stack directly in java but the real problem is there is no tail-call optimisation yet
01:31:33 -!- tswett2 has quit (Ping timeout: 250 seconds).
01:34:06 <int-e> doesn't that give you nightmares though?
01:34:29 -!- heroux has quit (Ping timeout: 246 seconds).
01:35:19 <oerjan> <blockzombie> is the interpreter loaded into the program space? <-- not sure what you mean
01:36:10 <oerjan> the official interpreter has a table from command characters to commands, essentially, which some of the commands update
01:40:23 -!- heroux has joined.
01:42:56 <oerjan> the type of that table is called Interpreter
01:47:03 -!- Lymia has quit (Ping timeout: 245 seconds).
01:55:46 -!- tswett3 has quit (Ping timeout: 255 seconds).
01:58:14 * oerjan is reminded by blockzombie's nick to check up on bitcoin
01:58:26 <oerjan> seems to still be slowly falling
02:07:51 <blockzombie> the price is not much affected by news on fundamentals at the moment
02:08:07 <blockzombie> it is mostly margin traders pushing it around
02:08:22 <blockzombie> they love the volatility... hedge funds are moving in now
02:08:39 <blockzombie> so we're likely to see a major drop before the next bubble
02:10:13 <oerjan> nighmares about dayjobs, i assume
02:10:41 <blockzombie> oerjan: i was asking whether you modify the language itself by having the program loaded in as a kind of #include for the interpreter and then self-modification === modifying the language
02:11:36 <oerjan> well the emmental interpreter is in haskell
02:11:50 <oerjan> rather basic haskell in fact
02:12:09 <oerjan> (if i had written it it would have used a lot more higher order functions and monads)
02:12:17 <blockzombie> I'm convinced haskell is awesome.. I've looked at it just not really got my hands dirty
02:12:56 -!- shikhin_ has joined.
02:13:10 <oerjan> no, chris pressey is the author of both the language and the interpreter
02:13:22 <oerjan> i wrote the underload interpreter in emmental
02:16:09 -!- shikhin has quit (Ping timeout: 256 seconds).
02:16:10 <oerjan> actually i generated it with haskell, here's the program for that http://oerjan.nvg.org/esoteric/emmental/EmmUnl.hs
02:17:45 -!- Guest80873 has quit (Quit: Connection closed for inactivity).
02:18:19 <blockzombie> and this is the output?: http://oerjan.nvg.org/esoteric/emmental/ul.emm
02:19:39 -!- Lymia has joined.
02:21:39 <blockzombie> I guess what I'm trying to figure out is what program representation poses the easiest crossover function. If you're familiar with GA you wan to "breed" two programs and ideally preserve implementation features from each program
02:23:00 <blockzombie> it seems very easy to end up with a situation like disassembling two clocks into a bag, shaking it and tipping out half. What you end up with is not much like a working clock - least one that shares much with either "parent"
02:23:44 <blockzombie> I'm familiar with evolving corewar warriors
02:26:51 <oerjan> i don't have any real experience with GA
02:27:01 -!- PinealGlandOptic has quit (Ping timeout: 250 seconds).
02:27:47 <oerjan> i was just looking at my own haskell program there, i had forgotten a lot of the trickiness. also it was the first time i tried using lens.
02:33:58 <oerjan> blockzombie: maybe you could use something like chromosomes...
02:34:43 <oerjan> where your combined program parts are chosen from corresponding parts of the originals
02:35:50 <oerjan> it works to make living organisms have a good chance of still working, anyhow
02:38:02 <blockzombie> yeah but the mapping of parts has to be chosen
02:38:53 <blockzombie> if there were modules then you could have intra and inter module variations
02:39:38 <blockzombie> I like the idea. Is underload eqipped for this?
02:39:52 <oerjan> presumably a part would be a sequence of commands...
02:40:21 <oerjan> well i assume you would have to keep track of the parts outside underload.
02:41:29 <oerjan> underload doesn't have much in the way of analyzing its own subprograms.
02:41:58 <oerjan> in a safe way, anyway.
02:41:59 <blockzombie> yeah so part boundaries is what we're talking about.
02:42:43 <blockzombie> I expect that something like 95% needs to be junk dna
02:43:00 <blockzombie> I think this is how mutation levels are insulated against
02:43:08 <oerjan> that's a bit troublesome on a stack, actually.
02:43:40 <oerjan> because how does the non-junk find its data if the stack is filled with junk
02:43:58 -!- PinealGlandOptic has joined.
02:44:01 <oerjan> well, you do have nops i guess
02:44:13 <blockzombie> yeah well I'm not saying the stack is filled with junk, but the program is
02:44:45 <blockzombie> the key is it's not clear which is junk and which is useful... that's up to the tree of future generations
02:44:47 <oerjan> well badly constructed junk would tend to seep onto the stack :P
02:45:49 <blockzombie> but if I had a RISC cpu emulator instead of underload would I be any better off?
02:46:27 <oerjan> it might be that a language that keeps most of its data on the stack is unsuited to GA :(
02:46:29 <blockzombie> the first step is what set of producible programs are valid/executable
02:46:50 <blockzombie> if that is the case then I will use something else
02:46:52 <oerjan> because junk then gets in the way
02:47:52 <blockzombie> like pointers to stacks, also potentially a symbol table of sorts
02:48:09 <blockzombie> so there's be a random lookup mechanism to keep parts and their data connected
02:48:35 <blockzombie> but the flip side is you want to enable code to read randomly because that's an essential combining effect
02:49:07 <blockzombie> the good news is I only really need numeric types and I don't need any output
02:49:27 <blockzombie> I can just halt and use the top of the stack as the "result"
02:49:40 <blockzombie> really only need a binary or ternary output
02:51:08 <blockzombie> reconsidering I think output is overkill... just use memory state at halt
03:08:57 <blockzombie> the reason I like the stack is because you can get away from having loads of abitrary operands. maybe the existence of operands is better than the alternative: long chains of stack manipulation code
03:09:15 <blockzombie> I'm in this channel because I can't figure this out
03:11:07 -!- dianne has quit (Ping timeout: 244 seconds).
03:13:16 -!- dianne has joined.
03:36:09 -!- oerjan has quit (Quit: Well, good luck).
04:16:01 -!- Sprocklem has quit (Ping timeout: 264 seconds).
04:44:41 -!- shikhin_ has quit (Ping timeout: 245 seconds).
04:53:28 -!- MDude has changed nick to MDream.
04:57:39 -!- nys has quit (Quit: quit).
04:57:39 -!- blockzombie has quit.
05:00:15 -!- AndoDaan_ has joined.
05:03:12 -!- _AndoDaan_ has quit (Ping timeout: 245 seconds).
05:04:19 -!- GeekDude has quit (Remote host closed the connection).
05:04:50 -!- _AndoDaan_ has joined.
05:08:47 -!- AndoDaan_ has quit (Ping timeout: 250 seconds).
05:49:18 -!- AndoDaan_ has joined.
05:52:07 -!- _AndoDaan_ has quit (Ping timeout: 250 seconds).
05:53:45 -!- AndoDaan_ has quit (Ping timeout: 252 seconds).
05:57:13 -!- adu has quit (Quit: adu).
06:07:52 -!- adu has joined.
06:34:32 -!- AndoDaan_ has joined.
06:34:33 -!- AndoDaan_ has quit (Remote host closed the connection).
06:35:25 -!- AndoDaan has joined.
06:41:27 -!- AndoDaan has quit (Ping timeout: 265 seconds).
07:32:06 -!- Patashu has joined.
07:38:39 -!- AndoDaan has joined.
07:40:11 <AndoDaan> I was thinking of adding (more thinking about thinking of adding) a new catergory to the wiki. Esoteric languages usable on Anarchy Golf.
07:41:06 <AndoDaan> What would you guys think. It's one of the few (only) places you can program in bonafide esolangs where it's of some - competative - use.
07:41:55 <AndoDaan> And I came to esolangs via Anarchy Golf. I might not be the only one.
08:02:45 <Jafet> That doesn't seem useful because it depends on the whim of the anagol administrator; it could have anywhere from ten languages to the entire intersection of TC and Implemented
08:03:31 <Jafet> You could make it a list article instead. Then you can also add content which would not fit in a category page.
08:03:51 <AndoDaan> True. Good input. And that's a great idea.
08:07:12 <AndoDaan> Now I just have get over my natural ability to write stubby wiki articles.
08:39:10 -!- adu has quit (Quit: adu).
09:05:00 -!- AndoDaan has quit (Ping timeout: 265 seconds).
09:05:03 -!- AndoDaan_ has joined.
09:22:57 -!- augur has quit (Quit: Leaving...).
09:23:22 -!- ^v^v has quit (Read error: Connection reset by peer).
09:23:45 -!- ^v^v has joined.
09:24:30 -!- supay|zzZZ has quit.
09:25:04 -!- supay has joined.
09:40:43 -!- augur has joined.
10:14:49 -!- AndoDaan_ has quit (Ping timeout: 245 seconds).
10:15:56 -!- Tritonio has joined.
11:17:27 -!- Patashu has quit (Ping timeout: 264 seconds).
11:23:05 -!- boily has joined.
11:27:23 -!- AndoDaan has joined.
11:29:02 -!- heroux has quit (Ping timeout: 245 seconds).
11:33:52 <HackEgo> [wiki] [[Special:Log/newusers]] create * Elboza * New user account
11:43:08 <HackEgo> [wiki] [[Brainfuck-ng]] N http://esolangs.org/w/index.php?oldid=41802 * Elboza * (+28767) Created page with "{{featured language}} {{infobox proglang |name=brainfuck |paradigms=imperative |author=[[Urban Müller]] |year=[[:Category:1993|1993]] |memsys=tape-based |dimensions=one-dimen..."
11:45:56 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41803&oldid=41802 * Elboza * (+14)
11:58:52 -!- Tritonio has quit (Remote host closed the connection).
12:09:30 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41804&oldid=41803 * Elboza * (-24847)
12:12:02 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41805&oldid=41804 * Elboza * (-42) /* Hello, World! */
12:12:24 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41806&oldid=41805 * Elboza * (+3) /* Language overview */
12:12:25 -!- heroux has joined.
12:13:19 -!- Tefaj has joined.
12:13:49 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41807&oldid=41806 * Elboza * (-586) /* History */
12:14:04 -!- tromp__ has joined.
12:15:04 -!- Vorpal_ has joined.
12:15:50 <fizzie> I'm not seeing the "-ng" part, I think.
12:16:06 -!- PinealGl1ndOptic has joined.
12:17:14 * Taneb has a place to live next year almos
12:19:48 <boily> fizzie: I think it's some kind of wip hth
12:19:55 -!- trnv2 has joined.
12:20:00 <boily> Taneb: Tanelle. moving away from York?
12:20:30 <Taneb> boily, no, but my housemates are dispersing
12:20:34 <Taneb> So I needed somewhere else
12:20:49 -!- contrapumpkin has joined.
12:20:55 -!- PinealGlandOptic has quit (*.net *.split).
12:20:55 -!- copumpkin has quit (*.net *.split).
12:20:55 -!- Vorpal has quit (*.net *.split).
12:20:55 -!- tromp has quit (*.net *.split).
12:20:55 -!- trn has quit (*.net *.split).
12:20:55 -!- variable has quit (*.net *.split).
12:20:55 -!- paul2520 has quit (*.net *.split).
12:20:55 -!- Jafet has quit (*.net *.split).
12:21:02 <Taneb> So I'm moving into private student halls
12:21:08 -!- Tefaj has changed nick to Jafet.
12:21:16 -!- Jafet has left.
12:23:21 <boily> Taneb: so it goes.
12:23:52 -!- boily has quit (Quit: ABRIDGED CHICKEN).
12:24:15 <Taneb> Which means I'm paying what I am now for rent but it includes utilities
12:24:32 -!- AndoDaan has quit (Quit: Off to find the mythical clitoris.).
12:25:45 <fizzie> elliott: Some men in Finland packed up the computers the other day.
12:26:15 <fizzie> elliott: Apparently they had also made disparaging comments about the amount of computers, and the weight of the monitor.
12:26:27 -!- trnv2 has changed nick to trn.
12:28:46 -!- paul2520 has joined.
12:29:41 -!- paul2520 has changed nick to Guest56395.
12:39:22 -!- AnotherTest has joined.
12:40:06 -!- variable has joined.
12:40:06 -!- variable has quit (Changing host).
12:40:06 -!- variable has joined.
12:43:49 <Taneb> So come July probably I will be slightly further east than my current location
12:57:28 <Taneb> Oooh, Conor McBride is doing a seminar on dependent types in half an hour
13:02:29 <HackEgo> [wiki] [[Special:Log/newusers]] create * Mazeman * New user account
13:09:43 -!- GeekDude has joined.
13:13:58 -!- Guest56395 has changed nick to paul2520.
13:14:29 -!- paul2520 has changed nick to Guest22773.
13:14:50 -!- Guest22773 has changed nick to paul2520.
13:15:15 -!- paul2520 has quit (Changing host).
13:15:15 -!- paul2520 has joined.
13:22:04 <HackEgo> [wiki] [[Mice in a maze]] N http://esolangs.org/w/index.php?oldid=41808 * Mazeman * (+2180) Created page with "'''Mice in a maze''' is another brainfuck derivative. It was invented in 2015 by an anonymous user. Mice in a maze was inspired by items called cellular automata, especially C..."
13:22:42 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41809&oldid=41796 * Mazeman * (+21) /* M */
13:23:28 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41810&oldid=41808 * Mazeman * (+6) /* Defining a maze */
13:23:49 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41811&oldid=41810 * Mazeman * (+7) /* Defining a maze */
13:24:15 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41812&oldid=41811 * Mazeman * (-6) /* Defining a maze */
13:24:41 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41813&oldid=41812 * Mazeman * (+0) /* Basics */
13:26:15 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41814&oldid=41813 * Mazeman * (+145) /* Syntax */
13:26:28 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41815&oldid=41814 * Mazeman * (+1) /* = Example maze */
13:27:04 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41816&oldid=41815 * Mazeman * (+0) /* Instructions */
13:29:11 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41817&oldid=41816 * Mazeman * (+104) /* Instructions */
13:29:27 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41818&oldid=41817 * Mazeman * (+0) /* Defining a maze */
13:30:56 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41819&oldid=41818 * Mazeman * (+7) /* Example maze */
13:31:23 -!- ^v^v has quit (Read error: Connection reset by peer).
13:31:55 -!- ^v^v has joined.
13:40:31 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41820&oldid=41819 * TomPN * (+430) /* Example programs */
13:43:08 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41821&oldid=41807 * Elboza * (-76)
13:45:12 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41822&oldid=41821 * Elboza * (+0)
14:01:25 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41823&oldid=41822 * Elboza * (+727)
14:02:48 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41824&oldid=41823 * Elboza * (+12) /* ReverseFuck mode */
14:05:00 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41825&oldid=41824 * Elboza * (+74) /* ReverseFuck mode */
14:06:16 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41826&oldid=41825 * Elboza * (+34) /* ReverseFuck mode */
14:07:34 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41827&oldid=41826 * Elboza * (+0)
14:08:51 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41828&oldid=41827 * Elboza * (+18)
14:13:18 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41829&oldid=41828 * Elboza * (+9)
14:17:22 -!- Lymia has quit (Ping timeout: 240 seconds).
14:23:09 -!- nys has joined.
14:23:59 -!- MDream has changed nick to MDude.
14:39:23 -!- oerjan has joined.
14:46:48 -!- shikhin has joined.
14:49:00 -!- oerjan has set topic: What is the land-speed velocity of a migrating fungot? | reaking ubbles and ursting arriers | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
14:50:21 * oerjan isn't sure whether "unladen" would be better or worse
14:56:03 -!- Tritonio has joined.
14:56:54 -!- skj3gg has joined.
15:01:59 -!- `^_^v has joined.
15:04:17 -!- SopaXorzTaker has joined.
15:07:28 -!- AnotherTest has quit (Ping timeout: 245 seconds).
15:09:48 <oerjan> argh testing if my stomach had got well enough to drink orange juice again was a mistake.
15:12:16 <oerjan> (the test results were "no")
15:16:58 <oerjan> hm the keyboard controls of tatham's Bridges are somewhat annoying, you cannot always easily undo a wrong cursor movement
15:18:01 <oerjan> because it's too easy to jump away from a node that's hard to get back to
15:26:04 <oerjan> which might be fine for a different kind of game, but here navigation isn't supposed to be the real puzzle...
15:26:08 <int-e> hmm, no java plugin here.
15:26:56 <oerjan> int-e: if you're looking at tatham's puzzles, i think there's also js versions? (i'm playing the offline downloaded versions)
15:28:45 <oerjan> (i'm not really assuming you're talking about that, mind you)
15:28:54 <int-e> ah it's Hashiwokakero.
15:29:35 <oerjan> lots of tatham's puzzles are renamed nikoli puzzles, i think
15:29:38 <int-e> oerjan: I googled, and the first hit was the java version.
15:29:46 <oerjan> even sudoku got a different name
15:31:18 -!- skj3gg has quit (Quit: ZZZzzz…).
15:33:34 -!- adu has joined.
15:34:09 -!- Sprocklem has joined.
15:39:40 <int-e> hmm, I seem to be too used to Nikoli's interface (which doesn't have the feature of locking completed nodes, but marks them in gray, and which allows removing bridges by clicking on them.)
15:45:19 -!- Tritonio_ has joined.
15:46:01 <oerjan> right, removing a single bridge is a litle awkward
15:47:28 <oerjan> unless you just added it, then "u"ndo works of course
15:49:22 -!- Tritonio has quit (Ping timeout: 252 seconds).
15:50:41 -!- Tritonio_ has changed nick to Tritonio.
15:57:48 <HackEgo> [wiki] [[Special:Log/newusers]] create * Intgr * New user account
16:00:13 <oerjan> int-e: is that you, but more grammatical?
16:00:54 -!- adu has quit (Quit: adu).
16:01:40 -!- adu has joined.
16:03:15 <int-e> oerjan: seems unlikely
16:04:15 <int-e> wow, the keyboard *navigation* for the bridges thing is awkward...
16:04:33 <oerjan> that's what i was saying duh
16:06:01 <oerjan> you can get used to it, but don't make any typing mistakes...
16:06:07 -!- adu has quit (Ping timeout: 244 seconds).
16:08:12 <oerjan> and there are always the "how the f do i get to there" moments
16:09:05 -!- rsal has joined.
16:09:36 <oerjan> tatham's Bridges puzzle
16:10:05 <oerjan> which int-e has pointed out is a version of nikoli's Hashiwokakero
16:10:58 <int-e> oerjan: I see, but that's not how I understood your complaint at first. (Personally I don't really find myself wanting to undo much; however I do find myself pressing cursor keys randomly to get to a nearby-but-not-adjacent spot.)
16:11:44 <oerjan> yeah that just doesn't work...
16:13:07 <oerjan> undo is _very_ nice when you realize you've made a mistake a while ago
16:14:34 <oerjan> although i sometimes end up carefully undoing each step, checking if it was actually certain, getting back to the beginning of the game, winding forward and discovering my second to last step was fishier than it looked at first recheck
16:16:17 <oerjan> the unlimited undo mechanism is common to all of tatham's puzzles, of course.
16:17:32 <oerjan> what did i do wrong _now_
16:20:42 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41830&oldid=41829 * Elboza * (+1765)
16:21:16 -!- adu has joined.
16:32:26 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41831&oldid=41830 * Elboza * (+424)
16:35:55 <int-e> oerjan: hmm, the javascript version gets stuck from time to time for me, refusing to process further events :/
16:37:30 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41832&oldid=41831 * Elboza * (+174)
16:37:52 <int-e> oh. "Cannot enlarge memory arrays." ... apparently 30x30 is too much for the thing.
16:39:05 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41833&oldid=41832 * Elboza * (+0)
16:41:08 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41834&oldid=41833 * Elboza * (+4)
16:43:41 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41835&oldid=41834 * Elboza * (+12)
16:44:07 <oren> my best friend might be getting a job in finland
16:44:35 <oren> how is the economy in finland these days?
16:45:01 -!- mihow has joined.
16:46:28 <fizzie> It's all relative, of course.
16:46:46 <fizzie> But I think Finland is technically still in a "slump".
16:47:22 -!- skj3gg has joined.
16:48:11 <fizzie> http://www.oecd.org/economy/surveys/economic-survey-finland.htm and I don't think things have improved terribly much since that was updated.
16:48:49 <oerjan> int-e: you don't have to use the web interface, there are native compiled versions you can download if you want.
16:49:26 <HackEgo> [wiki] [[Web framework list]] N http://esolangs.org/w/index.php?oldid=41836 * Intgr * (+678) List of esoteric web application frameworks. Most of these are fully functional web frameworks that aren't about making the coder's life easier. Often they are a response to the hype wave surrounding some technologies (such as Ruby on Rails).
16:50:57 <int-e> oerjan: I know, but couldn't be bothered. The generated problems don't look all that interesting.
16:51:04 <HackEgo> [wiki] [[Web framework list]] http://esolangs.org/w/index.php?diff=41837&oldid=41836 * Intgr * (-55) Not a functional framework
16:51:40 -!- Lymia has joined.
16:52:20 <int-e> oerjan: (I'm actually still at work.)
16:53:16 <oerjan> Bridges doesn't seem to generate very hard problems. although i recall it used to be even worse.
16:53:19 <int-e> Otoh I missed the source code in my previous visits to that website
16:54:15 <int-e> oerjan: increasing the size to 30x30 seemed to help a little. But of course then it becomes tedious to get to the few non-trivial conclusions.
16:54:28 <elliott> fizzie: nice (Re: computers)
16:55:59 -!- Phantom_Hoover has joined.
17:02:03 -!- skj3gg has quit (Quit: ZZZzzz…).
17:04:00 -!- Koen_ has joined.
17:04:18 -!- Koen_ has quit (Read error: Connection reset by peer).
17:04:59 -!- Koen_ has joined.
17:07:58 <HackEgo> [wiki] [[Talk:Web framework list]] N http://esolangs.org/w/index.php?oldid=41838 * Intgr * (+870) Background for creating this pagfe
17:08:30 <HackEgo> [wiki] [[Web framework list]] http://esolangs.org/w/index.php?diff=41839&oldid=41837 * Intgr * (-98) Per discussion at [[Talk:Cobol on Cogs]], it's just a joke and not real working software
17:09:34 -!- oerjan has quit (Quit: Later).
17:16:12 -!- Sprocklem has quit (Quit: gtg).
17:18:57 -!- TieWorking has changed nick to TieSoul.
17:28:43 -!- oren has quit (Ping timeout: 245 seconds).
17:30:46 -!- skj3gg has joined.
17:45:46 -!- oren has joined.
17:48:56 -!- SopaXorzTaker has quit (Quit: Leaving).
17:49:18 -!- SopaXorzTaker has joined.
17:52:46 -!- sebbu2 has joined.
17:52:56 -!- sebbu has quit (Ping timeout: 264 seconds).
17:53:23 -!- sebbu2 has quit (Changing host).
17:53:23 -!- sebbu2 has joined.
17:54:15 -!- ^v^v has quit (Quit: Network ban).
17:54:31 -!- ^v has joined.
17:57:52 -!- SopaXorzTaker has quit (Ping timeout: 240 seconds).
17:57:57 -!- MoALTz_ has quit (Quit: Leaving).
17:58:17 -!- MoALTz has joined.
18:01:20 -!- ^v has quit (Read error: Connection reset by peer).
18:01:46 -!- ^v has joined.
18:08:36 -!- shikhin_ has joined.
18:11:22 -!- shikhin has quit (Ping timeout: 240 seconds).
18:13:06 -!- shikhin_ has changed nick to shikhin.
18:18:16 -!- Koen_ has quit (Quit: Koen_).
18:25:26 -!- SopaXorzTaker has joined.
18:29:10 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:42:44 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
18:45:44 -!- idris-bot has quit (Ping timeout: 252 seconds).
18:46:55 -!- Melvar has quit (Ping timeout: 255 seconds).
18:48:57 -!- Melvar has joined.
18:49:59 -!- idris-bot has joined.
18:51:34 -!- mitchs has joined.
18:54:03 -!- mitchs_ has quit (Ping timeout: 256 seconds).
19:07:08 -!- skj3gg has quit (Quit: ZZZzzz…).
19:12:17 -!- nortti has changed nick to lawspeaker.
19:14:06 -!- lawspeaker has changed nick to nortti.
19:31:08 -!- intgr has joined.
20:03:11 -!- Patashu has joined.
20:05:13 -!- oren has quit (Ping timeout: 255 seconds).
20:19:31 -!- perrier has quit (Remote host closed the connection).
20:20:45 -!- perrier has joined.
20:25:52 -!- Patashu has quit (Ping timeout: 240 seconds).
20:30:10 <J_Arcane> whoah: http://www.extremetech.com/extreme/134672-harvard-cracks-dna-storage-crams-700-terabytes-of-data-into-a-single-gram
20:36:23 -!- nycs has joined.
20:38:32 -!- `^_^v has quit (Ping timeout: 264 seconds).
20:40:28 -!- MDude has quit (Ping timeout: 244 seconds).
20:40:58 <TieSoul> but couldn't they use quaternary instead of binary? would make storage more dense, right?
20:42:26 <TieSoul> like, A = 0, T = 1, C = 2, G = 3
20:42:49 <TieSoul> I wonder why they didn't do that
20:59:04 -!- atehwa has quit (Ping timeout: 244 seconds).
20:59:56 -!- atehwa has joined.
21:26:50 -!- hjulle has joined.
21:29:54 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=41840&oldid=41525 * 69.166.47.107 * (+384) Rely on SSRI and say 'hi-ho' in the coffee shop.
21:31:03 <myname> i guess that would be missleading if you start reading the wrong helix
21:34:05 -!- MDude has joined.
21:37:45 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41841&oldid=41835 * Elboza * (+72)
21:47:51 -!- skj3gg has joined.
21:48:13 -!- nycs has quit (Quit: This computer has gone to sleep).
21:48:41 -!- `^_^v has joined.
21:55:48 <quintopia> tiesoul: even stranger that each binary value cknsists of both a purine and pyrimidine. you'd think it would easier to distinguish those from each other than those of the same shape
22:09:52 -!- skj3gg has quit (Quit: ZZZzzz…).
22:10:55 -!- skj3gg has joined.
22:13:56 -!- skj3gg has quit (Client Quit).
22:21:07 -!- adu has quit (Ping timeout: 245 seconds).
22:24:00 -!- skj3gg has joined.
22:27:13 -!- skj3gg has quit (Client Quit).
22:32:10 -!- AndoDaan has joined.
22:50:32 -!- hjulle has quit (Ping timeout: 264 seconds).
22:51:21 -!- monotone has quit (Quit: "I can hear myself... I think I'm a bit afraid.").
22:55:58 -!- tswett has joined.
22:59:00 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:59:44 -!- oerjan has joined.
23:10:17 <J_Arcane> Heh. Staring at a Javascript exercise unsure how to solve it, when some tinkering reveals you can more or less write point-free style in JS too, of a sort: function squareDigits(num){ return parseInt(num.toString().split("").map(function (x) { return x*x; }).join(""));}
23:12:22 -!- Lymia has quit (Ping timeout: 240 seconds).
23:14:12 -!- mihow has quit (Quit: mihow).
23:15:09 -!- Koen_ has joined.
23:16:01 -!- Koen_ has quit (Read error: Connection reset by peer).
23:16:19 -!- Koen_ has joined.
23:29:57 -!- Tritonio has quit (Remote host closed the connection).
23:31:51 -!- olsner has quit (Ping timeout: 264 seconds).
23:32:13 -!- olsner has joined.
23:40:09 -!- Lymia has joined.
23:46:38 -!- 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?").
23:52:14 -!- Phantom_Hoover has joined.
00:05:26 -!- Warrigal has joined.
00:07:25 -!- tswett has quit (Quit: Leaving).
00:07:39 -!- Warrigal has changed nick to tswett.
00:07:59 <oerjan> removing errors by adding one ghc extension at a time...
00:08:58 -!- shikhin_ has joined.
00:08:59 -!- shikhin_ has quit (Changing host).
00:08:59 -!- shikhin_ has joined.
00:10:29 <oerjan> Taneb: i'm trying to show that current ghc (well, 7.8.3) _can_ express the types necessary to implement the new kind-aware Typeable without a builtin solver. but it needs a _lot_ of extensions.
00:10:39 -!- boily has joined.
00:11:48 <oerjan> gah now it accepts everything except the main function
00:12:03 -!- shikhin has quit (Ping timeout: 264 seconds).
00:12:06 <oerjan> and i don't want to change that because this is supposed to be backwards-compatible :(
00:12:51 <oerjan> oh i haven't defined a Kindable instance for ()
00:14:24 <oerjan> now it compiled, but it thinks main isn't in scope
00:14:55 <Melvar> oerjan: Is there any problem about () being the name of both a value and a type?
00:15:19 <oerjan> not in normal haskell, no.
00:15:48 <oerjan> but this is with DataKinds, so in theory you would add a ' in front of the value one when promoting it to a type.
00:16:01 <oerjan> but i'm using the kind so that's not necessary.
00:17:01 <oerjan> oh wait, i forgot to save the file after i uncommented main again :P
00:18:59 -!- spiette has quit (Quit: :qa!).
00:19:11 -!- spiette has joined.
00:20:06 <oerjan> http://oerjan.nvg.org/haskell/TypeableDesign/
00:21:23 <oerjan> the latest epiphany that made this possible is that you can have a type family as a superclass
00:23:04 -!- Jafet has joined.
00:23:45 -!- spiette has quit (Client Quit).
00:29:35 -!- Jafet has set topic: What is the land-speed velocity of a migrating fungot? | acking ubbles and urting arriers | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
00:32:35 -!- adu has joined.
00:35:35 <boily> AndoDaan: ursting as asy, ut 'm aving rouble ith urting.
00:35:44 <boily> Jafet: eah ight, s f.
00:39:15 <boily> elp, 'm ompletely ost ere.
00:40:20 <tswett> O c, j t f l o e w d p e i t r t s.
00:40:42 <tswett> I m, I g t f l c s a a m o s w y w t r t s l.
00:40:50 <boily> AAAAAAAAAAAAAAAAAAAAAAAAAAAAH!
00:41:32 <boily> erjan: ot y ault. our win tarted t.
00:45:12 <oerjan> maybe i should actually join #ghc
00:45:28 <boily> I should have plugged a few stealth diæreses in all that unusual discussion...
00:45:46 -!- contrapumpkin has changed nick to copumpkin.
00:45:58 <oerjan> just claim they were all in the censored letters hth
00:47:23 <boily> that's where'd've put them. very discreet, elegant in their placement. not unlike a zen garden ambush.
00:48:07 <oerjan> is that like plants vs. zombies?
00:48:21 * oerjan hasn't actually played that, but has heard good things
00:52:25 <elliott> oerjan: type family as a superclass @_@
00:53:09 <elliott> oerjan: btw, wasn't implicit Typeable for all types meant to be part of the Typeable redo to start with?
00:53:12 <elliott> it seems like that didn't happen?
00:54:27 <boily> zen zombies. zenbies.
00:55:10 <oerjan> elliott: well i started thinking, if you want to deduce that subparts of kinds are kinds, you need to make that fact a superclass if ghc's inference is to comprehend it properly. but the problem is, different kinds have different number of subparts, so i couldn't put a fixed number of them as superclasses. then i realized the obvious...
00:55:50 -!- lurklurklurk has joined.
00:56:16 <HackEgo> lurklurklurk: 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.)
00:56:32 <tswett> Hacking Hubbles and hurting harriers.
00:56:38 <oerjan> you may lurk, but you won't get slower than HackEgo
00:56:47 <tswett> I guess it's a proper noun.
00:56:52 <tswett> Hacking Hubbles and hurting Harriers.
00:57:31 -!- tswett has set topic: What is the land-speed velocity of a migrating fungot? | acking ubbles and urting arriers | ZFC is a Chu space. | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
00:57:41 <oerjan> by "comprehend it properly", i mean comprehend it without you needing to repeat it at every usage site.
00:57:41 <tswett> I just felt like announcing to the world that ZFC is a Chu space.
00:58:15 <oerjan> (because everything is, right?)
00:58:24 <oerjan> (same with category theory)
00:58:29 <boily> Taneb: Tanelle. have you invented that?
00:58:32 <HackEgo> [wiki] [[StackStacks]] http://esolangs.org/w/index.php?diff=41842&oldid=40793 * Oj742 * (-5) /* Instructions */ Corrected stack effect diagrams
00:58:34 <tswett> Well, I suppose you could say that everything is a Chu space.
00:58:44 <tswett> But ZFC is a Chu space in a particular meaningful way.
00:58:47 <Taneb> boily, I did, but then I forgot
00:58:58 <Taneb> lurklurklurk, you seem to not be lurking particularly well
00:59:07 <tswett> Define the points as being the models of ZFC, and the states as being the statements in the language of ZFC.
00:59:22 <tswett> Then the r function is the truth function. 1 if the statement is true in the model, 0 if it's not.
01:00:04 <tswett> Every theory of a similar sort is a Chu space in the same way.
01:00:49 <oerjan> that sounds related to gödel's second completeness theorem
01:01:03 <tswett> So then a morphism from a theory A to a theory B consists of a mapping of models of A to models of B, and a mapping of statements of B to statements of A, where the two mappings are compatible.
01:02:00 <tswett> (Given a model m of A and a statement s in B, the image of s is true in m if and only if s is true in the image of m.)
01:02:19 <tswett> Pretty sure G&owithanumlaut;del only had one completeness theorem.
01:06:02 <boily> well, he started working on another, but he didn't finish.
01:07:59 <tswett> The second incompleteness theorem, for ZFC: if the statement "ZFC has a model" is true in every model of ZFC, then there exist no models of ZFC.
01:13:51 -!- lurklurklurk has quit (Quit: KVIrc 4.2.0 Equilibrium http://www.kvirc.net/).
01:14:46 <elliott> oerjan: does this handle datakinds
01:15:57 <tswett> So I think this little fact generalizes to other types of theories without insanely much trouble.
01:16:02 <tswett> Like, consider the calculus of constructions.
01:17:25 <tswett> Points are models of the calculus of constructions. States are terms in the calculus of constructions. Then the r function is what value a term denotes in a model.
01:18:34 -!- arjanb has quit (Quit: bbl).
01:28:32 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:33:08 <oerjan> elliott: um nothing about it is automatic, but it's just a matter of making deriving (Typeable) also derive the corresponding Kindable instance for the datakind. i have [] and () as examples in the file.
01:38:49 <tswett> So certain theories seem to have "free models".
01:39:21 <tswett> Like, consider this theory:
01:40:05 <tswett> There exists an object x. For all objects x, there exists an object y.
01:40:27 <tswett> The free model of that theory is the natural numbers.
01:42:05 <tswett> I guess this is a better way of stating that theory. There exists an object 0. For all objects x, there exists an object S(x).
01:43:18 <Taneb> tswett, that is consistent with the natural numbers
01:43:29 <tswett> Indeed. The natural numbers are a model of that theory.
01:43:50 <tswett> Any set, along with a point in that set and a function from the set to itself, is a model of that theory.
01:43:57 <tswett> But the natural numbers are the free model.
01:44:05 <tswett> I think my idea of a "free model" might be the same thing as a term model.
01:44:08 <Taneb> Is the set {{}} a model?
01:45:03 <tswett> Yeah. 0 = {}, and S({}) = {}.
01:45:47 <oerjan> that's also a free algebra
01:46:02 <oerjan> i mean, the natural numbers with the operation S
01:46:35 <tswett> Right. An algebra is pretty much a type of model, right?
01:46:57 <tswett> An algebra is the same thing as a model, a type-of-algebra is the same thing as a theory.
01:47:30 <oerjan> although this type-of-algebra is a variety.
01:48:35 <oerjan> well, with no equations, even
01:49:08 <oerjan> (does that mean it's a free variety?)
01:51:11 <tswett> Now, categories aren't a type-of-algebra, right? Categories are two-sorted, and one of the sorts is parameterized by the other.
01:51:45 <oerjan> you can ignore the objects and use the identity morphisms instead
01:52:07 <oerjan> however the fact composition isn't always defined may be a bigger problem
01:53:20 <tswett> Ooh, ooh. Lemme see if I understand the proof of the model existence theorem.
01:53:39 <tswett> Suppose we have a consistent theory in first-order logic.
01:54:10 <tswett> Given a statement, there are three possibilities: the theory entails that it's true, the theory entails that it's false, or the statement is independent of the theory.
01:54:38 <tswett> So look through all statements that exist. Whenever you find a statement that's independent of the theory, just arbitrarily decide whether it's true or false.
01:55:01 <tswett> Now you have an assignment of a truth value to every possible statement.
01:55:09 <oerjan> um it needs to be independent of the theory and the statements you've already decided
01:56:00 <tswett> Then... I don't know if you can go from this assignment of a truth value to every statement to a model.
01:57:44 <oerjan> i think for every existence theorem that you've decided to be true, you need to choose a witness for it
01:58:18 <tswett> Yeah, we need to have witnesses.
01:58:26 <oerjan> oh and then you get to decide statements involving that witness as a free variable
02:00:17 -!- PinealGl1ndOptic has quit (Ping timeout: 244 seconds).
02:01:21 <oerjan> and then you probably use zorn's lemma to show you've got a maximal element where everything is decided and everything has witnesses
02:01:53 <oerjan> (element of the set of partial assignments)
02:02:39 <oerjan> or maybe you don't actually need choice, i don't know this
02:07:27 <tswett> Well, the set of all statements is countable.
02:08:04 <tswett> You can just enumerate them and say that each nondisprovable one is true, or each nonprovable one is false.
02:08:11 <tswett> Except that doesn't give you witnesses.
02:08:34 <tswett> Anyway, I guess you ultimately get a model just by saying that each term is an element of the model, and you glue two terms together if the model entails that the two terms are equal.
02:08:49 <tswett> Er, if the augmented theory entails that.
02:13:13 -!- PinealGlandOptic has joined.
02:16:21 -!- ^v has quit (Read error: Connection reset by peer).
02:16:48 -!- ^v has joined.
02:22:43 -!- naturalog has joined.
02:29:54 <tswett> Now, my view of things is pretty classical-finitistic.
02:30:19 -!- adu has quit (Quit: adu).
02:31:30 <tswett> Once you start talking about uncountable collections, I start to think that you're not really talking about "real mathematical objects" but rather hypothetical ones.
02:32:51 <tswett> This is why I want to figure out how to do model theory without actually talking about models.
02:39:03 <tswett> I definitely feel like there should be a concept of morphisms between models. There probably is.
02:39:17 <tswett> There pretty much has to be.
02:40:33 <tswett> I guess it depends on the flavor of theory, though.
02:41:01 <tswett> The group axioms are a sort of theory, right? A model of the group axioms is a group.
02:41:33 <tswett> And a morphism between two models of the group axioms is a function such that, what.
02:42:04 <tswett> True statements remain true when you take the image of every point mentioned in the statement.
02:42:28 -!- Lymia has quit (Ping timeout: 245 seconds).
02:44:23 <naturalog> hi. i was wondering lately, why Notation3 isnt used as a programming language per-se
02:47:15 <naturalog> and couldnt come up with anything :)
02:47:41 <tswett> Well, can you write fizzbuzz in it?
02:49:35 <tswett> And is it interpretable?
02:50:12 <naturalog> you dont actually interpret it, you ask it logic questions
02:50:38 <naturalog> on the other hand you could translate it isomorphically to Idris then idris compiler will compile it to C and gcc from there
02:51:00 <naturalog> but you actually query it with tools like cwm
02:52:07 <naturalog> like "given those rules, what should i do now?"
02:52:11 <boily> if it's isomorphic to Idris, then there exists a map from Idris to Notation3.
02:52:25 <boily> so program in Idris, then translate.
02:52:49 <naturalog> well it sounds better to program in n3 and then translate. or not translate at all, but query, or infer
02:53:46 <naturalog> ofc Curry-Howard isomorphism has to be kept in mind wrt this
02:55:11 -!- boily has quit (Quit: EXTRACURICULAR CHICKEN).
02:55:37 <HackEgo> boily is monetizing a broterhood scheme with the Guardian of Lachine. He's also a NaniDispenser, a Trigotillectomic Man Eating Chicken and a METARologist. He is seriously lacking in the f-word department.
02:57:08 -!- PinealGlandOptic has quit (Ping timeout: 264 seconds).
02:58:33 -!- PinealGlandOptic has joined.
03:20:45 -!- PinealGlandOptic has quit (Ping timeout: 252 seconds).
03:21:15 -!- PinealGlandOptic has joined.
03:23:06 -!- oren has joined.
03:25:57 -!- Lymia has joined.
03:29:58 -!- adu has joined.
03:30:02 <oren> I just realized something: Perl and python code is easy to write but herd to read because it lacks redundancy.
03:31:01 <oren> e.g. python variables never state what exactly their type or usage is.
03:31:41 <oren> So why not make an interpreter which, as it executes, inserts redundancy into the surce
03:32:21 <oren> redundant information such as the type of variables
03:36:57 <oren> In the original source it might say "var x = y * z", but after you run it the first time, the source now says "matrix[batch_size,number_of_outputs] x = y * z"
03:44:48 <oren> C++ could also use such thing. E.g. have an auto type, but have it replaced upon compilation with the variable's actual type
03:47:22 <elliott> in lots of editing environments for languages with type inference you can query the inferred type of some expression or variable in the code
04:01:31 <int-e> oerjan: your latest code on #9858 scares me.
04:04:20 <oerjan> well, you were right that type families were a good idea
04:05:01 <oerjan> and i was right that having things be superclasses was a good idea
04:06:22 <oerjan> also, my hands hate you for suggesting 30 x 30 bridges hth
04:08:23 <int-e> oerjan: Putting the constraints directly in the type family is quite clever. Anyway, there's still the question of whether one wants to track the whole kind of type constructors or just the poly-kinded arguments. For the former, you need the Kindable superclass for Typeable; for the latter, perhaps you don't.
04:09:45 <int-e> (I did the latter, which in retrospect is the main reason why the KindRep stuff didn't infect the normal Typeable (s a) instance.)
04:11:38 <oerjan> well my point in having Kindable a superclass is so it doesn't have to mentioned explicitly in type signatures, giving backwards compatibility
04:14:11 <oerjan> also my instance code for Typeable (a b) doesn't mention Kindable now.
04:15:07 <oerjan> and also i don't put the kind in the TypeRep for the monokind types
04:15:42 <oerjan> although it's still in the superclass of course
04:19:39 -!- Eolus has joined.
04:19:53 <Eolus> Pffft I hate phones
04:20:21 <Eolus> They never work >:(
04:20:46 -!- Eolus has quit (Client Quit).
04:21:25 -!- Guest81556 has joined.
04:21:59 -!- Guest81556 has changed nick to Lilax.
04:22:26 <Lilax> ok so just getting used to and chat
04:27:32 <int-e> oerjan: So essentially, you've circumvented the open world assumption, saying "well, whatever the instance is, it *will* contain evidence for the parts, just as if the standard instance had been used."
04:28:32 <int-e> But it's a complication that the compiler doesn't actually face.
04:29:10 <oerjan> have you looked at my kind-polymorphic recursion test cases?
04:29:18 <int-e> oerjan: on the matter of not breaking code, I wonder how many uses that amount to variations on typeRep (Proxy :: Proxy Proxy) are out there.
04:32:34 <oerjan> obviously there are no working uses out there that depend on typeReps actually distinguishing kinds
04:35:54 <int-e> oerjan: Okay, let me split that up into two questions. 1. Are there any users who inadvertently use a Typeable instance whose kind is not fully instantiated at runtime? 2. What will the [user-visible] type of typeRep (Proxy :: Proxy Proxy) be under the proposed solutions? I *hope* that the Kindable (or Typeable) constraint for the kind will show up in that type.
04:37:08 <oerjan> No instance for (Kindable Proxy) arising from a use of ‘typeRep’
04:37:08 <oerjan> The type variable ‘k0’ is ambiguous
04:40:24 <oerjan> istr there's an Any_K or something that's used when a kind isn't known
04:41:29 <oerjan> i deliberately didn't suggest any test cases that pick up a kind from something non-Typeable passed in
04:41:53 <oerjan> because i feel those "morally" shouldn't compile
04:42:25 <oerjan> and making them actually work would essentially require having no kind erasure
04:44:23 <oerjan> i don't know whether anyone has mixed Typeable with code depending on kind polymorphism in an essential way.
04:44:38 * oerjan gives Lilax a lollipop
04:49:52 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
04:50:06 -!- naturalog has quit (Quit: leaving).
04:50:07 <int-e> oerjan: Hmm, I need to think about this some more.
04:50:54 <oerjan> int-e: what i can see happening is some polymorphic code with signature (Typeable a, Typeable b) => ... and then applying some polymorphic type constructor to an (a b) inside
04:51:26 <oerjan> that's the most likely case where the "solver" solution needs to decompose kinds
04:52:02 <int-e> oerjan: If one goes against your stated "moral" principle, just using Any_K will be insufficient, because it cannot distinguish kinds (forall k. k -> k) and (forall k1 k2. k1 -> k2) or ((forall k.k) -> (forall k.k)).
04:52:12 <oerjan> if you cannot actually deduce that a b's kind is Kindable, then you cannot make a Typeable instance for the polymorphic type constructor
04:53:08 <oerjan> um is Any_K a kind or a type again
04:54:24 <Lilax> I'm still a noob :0
04:54:59 -!- nys has quit (Quit: quit).
04:57:00 -!- naturalog has joined.
04:57:40 <oerjan> i cannot remember where i found it
04:58:18 <oerjan> int-e: probably kinds tend to default to * anyway
05:00:15 <oerjan> int-e: anyway, the representation i made up today is meant to work about the way i understood goldfire's explanation of how the solver would work, except written in existing haskell.
05:01:35 <oerjan> and as i've mentioned, i believe the essential need to decompose kind representations comes about already when constructing Typeable (a b)
05:03:21 <int-e> oerjan: There is this interesting sentence on the wiki page: "Although it is impossible to create all necessary Typeable instances for poly-kinded constructors at the definition site (there's an infinite number), it is possible to create Typeable "instances" on demand at use sites."
05:04:30 <oerjan> yes, that's the sentence that made me think they were only constructing kind-monomorphic instances, and led to me making those test examples
05:04:54 <oerjan> i think i've disproved that sentence now :P
05:05:20 <int-e> Yeah, I'll add a comment.
05:13:24 -!- ProofTechnique has joined.
05:24:07 -!- GeekDude has quit (Remote host closed the connection).
05:36:58 <oerjan> int-e: i don't think it's impossible to adjust my representation to be more clever about leaving out redundant kind info in TypeReps
05:46:01 <int-e> hmm, that took longer than expected.
05:48:43 <int-e> but I hope I managed to express the concern that hiding evidence is bad.
05:52:09 <int-e> I should've used that phrase...
05:52:25 <oerjan> hm now i'm worrying about your second point too
05:52:33 <elliott> int-e: I suspect kinds default to *.
05:52:38 <elliott> I have no evidence, though.
05:53:13 <int-e> elliott: I don't think any defaulting happens at all.
05:53:20 <oerjan> elliott: my tests with my implementation indicate that the kind stays ambiguous and the program fails to compile.
05:53:26 <int-e> The kinds are erased after all. Who cares if they're still polymorphic ;-)
05:53:38 <elliott> int-e: that is basically like GHC's "Any" stuff then
05:54:24 <int-e> Except when they aren't erased, and that's what happens with oerjan's code.
05:54:30 <oerjan> int-e: for the first point, my idea was that all Kindable contexts have to come from a Typeable one, which must be explicit if it is now.
05:55:20 <elliott> I think kinds should be able to be instances before anything like this i done
05:55:29 <elliott> so that you can just use Typeable rather than adding a new class.
05:55:33 <int-e> oerjan: Oh, mumble. I wanted to mention that that function currently has type Proxy Proxy -> TypeRep
05:55:56 <int-e> oerjan: So for backward compatibility, it cannot take a Typeable context.
05:56:42 <oerjan> ic. i suspect this will be a problem for _all_ the suggested solutions.
05:59:47 <int-e> Ok, I clarified that.
05:59:49 <oerjan> int-e: if there is an _explicit_ type signature, then i think kinds default to *.
06:00:30 <oerjan> if there is _not_ an explicit type signature, then inferring a Typeable constraint, or defaulting to * if there is a monomorphism restriction involved, might be the best thing.
06:01:29 <oerjan> although i guess with my method the constraint would actually be Kindable. oh well.
06:02:22 <oerjan> i suspect in most cases that appear in practice, * will be what's intended if there is nothing to disambiguate.
06:05:12 <oerjan> <elliott> I think kinds should be able to be instances before anything like this i done <-- that's not _quite_ the same thing as types and kinds being able to be instances of the _same_ class. both would help here, of course.
06:05:49 <int-e> oerjan: Anyway, I never considered burying kindable evidence as a possible solution, so I always assumed that any solution that closes the Typeable hole would break *some* code.
06:05:54 <elliott> oerjan: right, that's what I mean.
06:05:57 <elliott> oerjan: get that done before doing all this.
06:06:20 <elliott> int-e: I think it's fine for code to pick up additional Typeable constraints, honestly
06:06:23 <oerjan> elliott: well this is meant to be a stopgap solution for 7.10, first.
06:06:31 <elliott> like, come on, BBP and everything ish appening
06:06:38 <elliott> oerjan: I guess this way doesn't break compatibility so it would be "okay"
06:06:47 <elliott> but please fix it at some point, thanks :p
06:08:35 <oerjan> int-e: well i always assumed there would be some _possible_ code that could break, but your typeRep (Proxy :: Proxy Proxy) example has convinced me it's more likely than i thought that it's actually out there.
06:09:01 -!- shikhin has joined.
06:10:04 <int-e> well, let's see what Richard (and perhaps SPJ) think about this
06:11:11 <oerjan> if we didn't worry about breaking backwards compatibility at _all_, then i'd go for making the kinds fully explicit instead of extracting things deeply from Typeable.
06:11:43 <int-e> oerjan: And this is why I suggested to push this to 7.12.
06:12:11 -!- shikhin_ has quit (Ping timeout: 245 seconds).
06:14:17 <oerjan> although i think your second issue can be mostly solved by default a bit more aggressively to *
06:14:20 <int-e> (I mean, I had vague ideas in my mind that suggested that any proper solution for plugging the Typeable whole would necessarily break compatibility, and a conviction (which I still have) that doing so after 2 RCs would be bad.)
06:14:49 <elliott> oerjan: that would be weird though
06:14:52 <int-e> oerjan: Yeah, (And elliott: I'm happy with extra Typeable constraints popping up for such code, too.)
06:14:56 <elliott> like stuff randomly gets monokinded
06:15:08 <elliott> and you fix it by adding a typeclass instance(??)
06:15:46 <oerjan> elliott: well it would still be _inferred_ with the typeclass instance. i mean defaulting to * in essentially the same cases type defaulting happens.
06:16:01 <elliott> okay, maybe that would work.
06:17:01 <int-e> Lilax: sorry, this is not supposed to be a Haskell channel. It's just that 3 of the people involved in discovering and exploring the ramifications of this particular bug happen to be here, and a few other Haskell enthusiasts.
06:17:30 <int-e> This particular discussion will probably fade away in a week or three.
06:18:06 <int-e> Lilax: yes, and we're still going on about the same thing.
06:18:26 <elliott> this channel always talks about haskell though
06:19:26 <int-e> Oh sure, but I like to think that most of those discussions are more accessible than this. But perhaps I'm wrong. Lenses are scary, too.
06:23:54 <oren> i have invented a new direction: doup which is sort of down or up depending on context.
06:24:18 <oerjan> it depends on the gravity of the situation
06:24:41 <oerjan> or levity, depending on context
06:26:01 <Lilax> What's the void inbetween dimensions called?
06:26:05 <oren> oerjan: it also allows Y and upside down Y nodes to have the same structure
06:26:05 <int-e> oren: sounds like "up" which means "down" on ${OPPOSITE_CONTINENT}.
06:27:24 <oerjan> Lilax: that's not a scientific concept, so probably varies wildly between religion / crackpot / scifi writer / superhero series
06:27:59 <Lilax> Dimension 1 -> Dimension 2
06:28:11 <Lilax> what is the -> then
06:28:13 <oerjan> in science, that's just not how dimensions work.
06:28:28 <oerjan> and they're _not_ the same thing as dimensions in comics
06:28:35 <oren> dimension can mean all sorts of things
06:29:19 <oren> I like to use it to mean how many real numbers you need in order to specify something
06:29:22 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
06:29:24 <oerjan> int-e: now i'm reminded of Overside
06:29:48 <Lilax> Uh I forget my though
06:32:01 -!- oerjan has quit (Quit: Good night, anyway).
06:32:18 -!- ProofTechnique has joined.
06:34:58 -!- Adrop has joined.
06:36:10 -!- Adrop has left.
06:57:51 <Lilax> androirc gave me admin options so idk maybe its crap
07:30:31 <int-e> operator stuff? kick, ban, etc?
07:30:55 -!- ChanServ has set channel mode: +o elliott.
07:31:01 -!- elliott has set channel mode: -o elliott.
07:31:06 -!- ChanServ has set channel mode: +o Lilax.
07:31:12 <elliott> they're not redundant now, problem solved!
07:31:17 -!- ChanServ has set channel mode: -o Lilax.
07:32:30 -!- Patashu has joined.
08:00:57 <Lilax> why did you OP me lol
08:01:15 <elliott> so you could use admin commands :p
08:01:21 <Lilax> but yes admin options kick ban disband channel
08:01:39 <Lilax> but why would you give them to me
08:01:43 <elliott> those probably just won't do anything if you use them. hopefully.
08:01:51 <Lilax> I mean I am your friend but
08:04:21 -!- ChanServ has set channel mode: +v Lilax.
08:09:24 <Lilax> The people gather in the streets
08:15:56 -!- hjulle has joined.
08:23:35 -!- adu has quit (Quit: adu).
08:24:25 -!- Tritonio has joined.
08:29:08 -!- hjulle has quit (Ping timeout: 246 seconds).
08:35:06 -!- Lilax has quit (Ping timeout: 245 seconds).
08:40:41 <b_jonas> fungot, why does libcurl have to be so type-unsafe?
08:53:36 <int-e> fungot is on vacation because fizzie is moving between servers
08:55:36 <AndoDaan> When fungot is offlin, is it dead?
08:55:53 <int-e> It's not dead, it's resting.
08:55:54 <b_jonas> `8-ball When do you suppose fungot will be back?
08:56:48 <Jafet> If fizzie moves it to the UK, it will be
09:01:42 <Jafet> Hmm https://en.wikipedia.org/wiki/Category:Fjords_of_Finland
09:07:35 <int-e> Does pining have anything to do with pines?
09:09:40 -!- MDude has changed nick to MDream.
09:11:29 -!- FreeFull has quit (Ping timeout: 246 seconds).
09:14:07 <AndoDaan> int-e, it's physically impossible for my brain to think otherwise.
09:21:28 <fizzie> int-e: Technically, I'm not moving between servers, I'm moving the one server to another place.
09:47:01 -!- Patashu_ has joined.
09:47:01 -!- Patashu has quit (Disconnected by services).
09:53:45 -!- Patashu has joined.
09:54:14 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41843&oldid=41841 * Elboza * (+316)
09:54:39 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41844&oldid=41843 * Elboza * (+1)
09:55:12 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41845&oldid=41844 * Elboza * (+1)
09:56:07 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41846&oldid=41845 * Elboza * (+11)
09:56:39 -!- Patashu_ has quit (Ping timeout: 244 seconds).
10:03:36 -!- FreeFull has joined.
10:12:04 -!- AnotherTest has joined.
10:21:19 -!- Phantom_Hoover has joined.
10:24:50 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41847&oldid=41846 * Elboza * (+0)
10:35:23 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41848&oldid=41847 * Elboza * (-5)
10:47:44 -!- TodPunk has quit (Ping timeout: 246 seconds).
11:13:54 -!- Patashu has quit (Ping timeout: 252 seconds).
11:15:03 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
11:24:32 -!- boily has joined.
11:47:44 -!- Taneb has quit (Ping timeout: 265 seconds).
11:49:54 -!- jameseb has quit (Ping timeout: 276 seconds).
11:56:42 -!- jameseb has joined.
11:56:42 -!- Taneb has joined.
11:59:33 <int-e> fizzie: fair enough
12:02:05 <boily> @ask Lilax back to Lilax, eh?
12:02:14 -!- Tritonio has quit (Remote host closed the connection).
12:02:33 -!- Tritonio has joined.
12:12:03 -!- shikhin has quit (Ping timeout: 245 seconds).
12:14:17 -!- shikhin has joined.
12:20:32 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41849&oldid=41820 * TomPN * (+0) /* Hello World! */
12:22:49 -!- boily has quit (Quit: LAGOPEDE CHICKEN).
12:33:39 -!- FreeFull has quit (Ping timeout: 265 seconds).
12:37:18 -!- GeekDude has joined.
13:24:58 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
13:25:20 -!- FreeFull has joined.
14:14:08 -!- ProofTechnique has joined.
14:19:07 -!- heroux has quit (Ping timeout: 256 seconds).
14:38:20 -!- ^v has quit (Read error: Connection reset by peer).
14:38:29 -!- Phantom_Hoover has joined.
14:38:47 -!- ^v has joined.
14:42:43 -!- ais523 has joined.
14:43:46 -!- Naprecks has joined.
14:54:17 -!- oerjan has joined.
14:54:47 -!- oren has quit (Ping timeout: 265 seconds).
14:55:32 -!- adu has joined.
15:04:34 -!- `^_^v has joined.
15:11:11 -!- oren has joined.
15:11:42 -!- SopaXorzTaker has joined.
15:14:33 -!- PinealGlandOptic has quit (Ping timeout: 264 seconds).
15:26:20 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41850&oldid=41848 * Ais523 * (-168) remove/adjust some things that were presumably accidentally copied from [[brainfuck]]
15:37:44 -!- shikhin has quit (Quit: leaving).
15:38:03 -!- shikhin has joined.
15:49:28 <mroman> we should un-invent brainfuck
15:49:33 -!- Frooxius has quit (Ping timeout: 245 seconds).
15:50:27 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
15:50:39 -!- SopaXorzTaker has joined.
15:53:38 <oerjan> the current darths & droids is seriously straining my suspension of disbelief.
15:54:11 <int-e> oerjan: unbelievable
15:54:29 <int-e> . o O ( I find your lack of faith disturbing )
15:55:59 <b_jonas> oerjan: I just don't understand it. I hope the explanation will continue in the next strip or the next few.
15:57:11 <oerjan> int-e: i don't think goldfire got your point
15:57:34 <oerjan> alternatively, he envisions the solver as being more magical than i do
15:57:55 -!- SopaXorzTaker has quit (Ping timeout: 252 seconds).
15:59:37 <int-e> oerjan: Hmm, let me see...
16:00:07 <fizzie> b_jonas: It will probably still be maybe two weeks.
16:01:29 <oerjan> (i assume your point is that _currently_, that code gets inferred to a signature not containint Typeable (Proxy ...) at all)
16:01:50 <int-e> oerjan: I think this stuff is actually fairly easy on the type inference level. Any constraint that can't be solved immediately (and an unknown kind means that the Typeable constraint is not solvable) ends up being propagated upwards.
16:02:42 <oerjan> int-e: well i agree wthat it's easy, but also it's not backwards-compatible
16:02:56 <int-e> oerjan: At least my impression was that most of the complications our mock implementations ran into had to do with the open world assumption. When treating Typeable specially (and that is the plan), the compiler isn't bound by it.
16:03:14 <oerjan> um i don't see the difference, really
16:03:32 <oerjan> the type signature still has to change, either way.
16:03:44 <oerjan> otherwise, kinds no longer become subject to type erasure.
16:04:50 <oerjan> because a signature that doesn't mention that the kind needs to be Kindable _somehow_ implies that the function has an ABI where the kind _does_ get erased.
16:06:25 <oerjan> maybe i should make a comment
16:07:16 <b_jonas> "kinds no longer become subject to type erasure" -- I don't know what that means but it sounds scary
16:07:54 <b_jonas> oh, you mean kind parameters inside types when they don't influence the resulting type, right?
16:08:04 <b_jonas> wasn't that what this typable stuff was about?
16:09:00 <oerjan> yes. but the attempt is to make this backwards compatible, and int-e's test case would seem to break that.
16:09:08 -!- adu has quit (Quit: adu).
16:11:44 -!- SopaXorzTaker has joined.
16:18:34 -!- Sprocklem has joined.
16:21:11 -!- Sprocklem has quit (Client Quit).
16:21:20 -!- Sprocklem has joined.
16:23:30 -!- oren has quit (Quit: Lost terminal).
16:28:09 <int-e> oerjan: Right, that was the point (as I just said on the ticket)
16:28:26 -!- MDream has changed nick to MDude.
16:31:26 -!- adu has joined.
16:33:52 <TieSoul> un-inventing brainfuck souds like a good idea
16:33:59 <TieSoul> there's too many damn derivatives
16:34:34 <TieSoul> but I have a feeling people would make derivatives of some other random esolang instead if brainfuck were un-invented
16:34:57 <TieSoul> and then we'd have to un-invent those
16:35:11 <TieSoul> and eventually we'd have no esolangs left
16:35:25 <J_Arcane> I should make another retro language one of these days.
16:35:49 <TieSoul> except maybe eodermdrome because nobody wants to try implementing eodermdrome :P
16:36:27 <b_jonas> TieSoul: why is implementing relevant? people invent languages they don't try to implement.
16:36:35 <b_jonas> J_Arcane: what's a "retro language" like?
16:36:56 <J_Arcane> b_jonas: like VIOLET. Or that COBOL-parody punchcard language.
16:36:58 <TieSoul> but only having unimplemented languages seems pointless
16:37:11 <J_Arcane> Something meant to feel like it could've been developed in the 1970s.
16:39:59 <Jafet> Eodermdrome has been implemented... multiple times, in fact
16:40:53 <TieSoul> yeah, I just learned about that
16:41:01 <TieSoul> and now what I said seems kind of stupi
16:45:11 <Jafet> Look to the future--there is probably yet room for a good satire of ecmascript
16:47:02 <J_Arcane> http://fortytwo-as-a-service.herokuapp.com/
16:47:54 <J_Arcane> Jafet: Much as I'm starting to love it, ecmascript is it's own parody already: https://twitter.com/abt_programming/status/563318058996224000
16:50:09 <int-e> oerjan: Btw, I'm not sure that some sort of Kindable information isn't required in general; I think comment 47 indicates that Richard sort of agrees, but hopes to cover that information in a TypeRep? Hmm :)
16:55:39 <J_Arcane> Enterprise-Grade JavaScript. ;)
16:56:12 <J_Arcane> Ahahahaha: https://github.com/ajlopez/CobolScript
16:56:44 <Jafet> Is that a parody or an enhancement?
16:57:08 <J_Arcane> It is apparently real software, transpiling COBOL to JS ...
16:57:10 <oerjan> int-e: so far, i've seen nothing to indicate my mock implementation will be that different from what they end up with in terms of actual information passed.
16:58:14 <oerjan> um that statement might need some careful interpretation
16:58:45 <oerjan> i'm saying, the might not use superclasses, but if so they'll end up passing the same information in a different way.
16:59:19 <Jafet> Oh, it actually uses COBOL as input, which makes it quite commercially oriented
16:59:30 <oerjan> a solver might be more clever about how it extracts things
16:59:57 <Jafet> (As in, if you do this properly someone would probably buy it.)
17:08:05 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:12:30 <b_jonas> we need a computed come from statement in BANCStar
17:13:41 <int-e> oerjan: and another comment...
17:13:56 <int-e> oerjan: this one should be closer to your concerns about Kindable :)
17:17:37 <oerjan> g :: forall (k :: BOX) (a :: k) (b :: k). Kindable Proxy => Proxy a -> Proxy b -> PolyTypeable2.TypeRep
17:18:01 <oerjan> :t 's printing of kinds is so annoying
17:18:25 <int-e> oerjan: yeah, but simplified that will be what I wrote: g :: Typeable k => Proxy (a :: k) -> Proxy (b :: k) -> TypeRep
17:18:49 <int-e> oerjan: (simplified by getting rid of the Proxy-that-only-serves-to-make-the-class-parameter-have-kind-*)
17:19:23 <oerjan> that's the inferred type anyway
17:20:16 <b_jonas> int-e: what? no, you're getting it backwards
17:20:37 <int-e> b_jonas: are you sure?
17:20:48 <oerjan> oh hm i see what you're saying: it's not necessarily possible to infer a non-kind based type
17:21:00 <b_jonas> int-e: you need the proxy because a method in the cass isn't allowed to have a type that doesn't depend on the class arguments, such as Typerep, it has to depend on them, so you need at least a proxy
17:21:18 <b_jonas> int-e: minValue in enum should use such a proxy too
17:21:18 <oerjan> yeah, Kindable or the like is needed for sensible type inference
17:21:53 <b_jonas> if you wish, you could add a convenience function for the simple case when you already have a value of that type, but you shouldn't need a value, a proxy should be enough
17:22:13 <oerjan> b_jonas: um you need the proxy because classes cannot have arguments that are kinds.
17:22:45 <int-e> b_jonas: That's wrong. The class method could take a proxy, and in fact it does: Data.Typeable.Internal.typeRep# :: GHC.Prim.Proxy# a -> TypeRep
17:22:46 <b_jonas> oerjan: oh, you mean Kindable needs a proxy for that?
17:22:56 <b_jonas> I thoguht you asked why Typable needs a proxy
17:23:08 <int-e> b_jonas: Sorry, but oerjan got this right.
17:23:35 <oerjan> there's a proposal on the Typeable ghc trac wiki page to change Typeable to use a phantom type instead.
17:24:59 <b_jonas> ok. but I mean, how would you use Typeable on a type that isn't of kind * without such a proxy with a phantom type?
17:25:00 <int-e> b_jonas: *personally* I would prefer newtype Tagged a b = Tagged b, and typeRep# :: Tagged a TypeRep. And in fact that's pretty much what the TTypeRep idea accomplishes.
17:25:19 <int-e> b_jonas: So I disagree about the minValue; I want to eliminate the proxies instead.
17:25:39 <int-e> b_jonas: at least from the class methods. They are still useful for convenience functions.
17:25:47 <b_jonas> int-e: a constructor wrapper instead of a functions? sure, that would be better
17:25:48 -!- Koen_ has joined.
17:26:15 -!- Koen_ has quit (Read error: Connection reset by peer).
17:26:24 <b_jonas> (and no, I don't really know what I'm talking about.)
17:26:34 -!- Koen_ has joined.
17:26:59 <int-e> b_jonas: I presume you mean minBound in Bounded?
17:27:15 <b_jonas> int-e: yes, those. whatever Bounded has
17:28:07 <b_jonas> you know, we in C++ have more easy to remember names for important stuff like this, namely numeric_limits<T>::lowest() and numeric_limits<T>::max()
17:28:21 <b_jonas> those don't take a dummy argument
17:28:29 <oerjan> int-e: i'm a little bit miffed that they didn't include Tagged in base when they absorbed Proxy.
17:28:44 <int-e> If so, minBound :: Bounded a => a is perfect. minBound :: Proxy a -> a would carry unnecessary runtime cost. However, there may be a case for defining a small convenience function outside the class, minBoundProxy :: Enum a => Proxy a -> a; minBoundProxy _ = minBound.
17:29:41 -!- gde33 has joined.
17:30:02 <int-e> (I don't see the point though, since I don't see how that would save any type signatures)
17:32:06 -!- oerjan has quit (Quit: Later).
17:33:50 <int-e> @tell oerjan yes, the omission of Tagged is sad, given that one can naturally write taggedToProxy :: Tagged a b -> Proxy a -> b and proxyToTagged :: (Proxy a -> b) -> Tagged a b.
17:37:11 -!- huc has joined.
17:38:10 -!- huc has quit (Client Quit).
17:40:43 -!- nys has joined.
17:50:57 -!- skj3gg has joined.
17:53:12 -!- SopaXorzTaker has quit (Remote host closed the connection).
17:58:40 -!- skj3gg has quit (Quit: ZZZzzz…).
18:06:21 -!- skj3gg has joined.
18:09:20 -!- shikhin_ has joined.
18:09:33 -!- Lymia has quit (Ping timeout: 245 seconds).
18:10:35 <HackEgo> [wiki] [[Special:Log/newusers]] create * Mihip * New user account
18:13:01 -!- shikhin has quit (Ping timeout: 245 seconds).
18:14:38 -!- shikhin_ has changed nick to shikhin.
18:19:23 -!- skj3gg has quit (Quit: ZZZzzz…).
18:21:56 -!- oren has joined.
18:22:36 -!- skj3gg has joined.
18:23:52 <oren> Would it be possible for a language to incorporate neural networks in a central role
18:24:16 -!- AndoDaan has quit (Ping timeout: 245 seconds).
18:25:37 <oren> I am imagining a source file consisting of defining the network and the format of training data, and a "compilation" consisting of training the network.
18:26:13 <oren> But the network can also contain parts that are defined algorithmically, and not trained
18:28:33 <oren> The final executable would incorporate the trained network(s).
18:42:22 <Jafet> Just define the whole network by training data...
18:42:45 <Jafet> Naturally, the program input is the validation data.
18:44:13 <oren> Jafet: but formatting??? the input has to be defined as to which parts are ignored, how to segment it.
18:44:31 <HackEgo> [wiki] [[Prelude]] http://esolangs.org/w/index.php?diff=41851&oldid=13450 * 86.176.120.87 * (+86) /* External resources */
18:50:37 <Jafet> It should be enough just to set the number of layers, number of neurons, and size of each sample.
18:51:15 <Jafet> Then give enough data to reliably train a cat program. Hello world is left as an exercise.
18:52:14 -!- arjanb has joined.
18:52:24 <Jafet> (How would you produce an output without inputs?)
18:52:47 -!- heroux has joined.
18:59:43 -!- idris-bot has quit (Quit: Terminated).
19:00:00 -!- idris-bot has joined.
19:04:44 <oren> Jafet: like this:
19:05:36 <oren> INPUT FORMAT (IGNORE ALL, EOF)
19:06:26 <oren> NET INPUT: (ZEROS(N))
19:06:58 <oren> In other words, ignore all input, and feed the net N zeros
19:07:39 <oren> Then you train it to output 13 characters
19:08:13 <oren> (Assuming feed-forward network architecture)
19:10:44 <oren> Cat could be INPUT FORMAT((CHAR C)*,EOF) NET INPUT(C) NET TARGET(C)
19:11:35 <oren> Or maybe a more terse syntax
19:14:19 <Jafet> Alternatively you can use a recurrent network to get mutable state more easily.
19:15:33 <oren> Jafet: yeah. I haven't been able to implement reccurrent network properly yet tho. I'll have to wait until my NN course gets to them
19:30:49 -!- skj3gg has quit (Quit: ZZZzzz…).
19:35:26 -!- skj3gg has joined.
19:35:43 -!- shikhin has quit (Ping timeout: 250 seconds).
19:37:29 -!- shikhin has joined.
19:40:38 -!- nys has quit (Quit: quit).
20:01:48 -!- Patashu has joined.
20:02:44 -!- TodPunk has joined.
20:04:45 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
20:07:38 -!- TodPunk has quit (Read error: Connection reset by peer).
20:07:57 -!- TodPunk has joined.
20:24:16 -!- Patashu has quit (Ping timeout: 245 seconds).
20:33:28 -!- _AndoDaan has joined.
20:34:54 <_AndoDaan> Okay, so brainfuck-ng isan interpreter, not a new language.
20:36:17 -!- Tod-Autojoined has joined.
20:36:21 -!- bb010g has joined.
20:36:25 -!- TodPunk has quit (Ping timeout: 264 seconds).
20:38:09 <Koen_> I had an computer science theory class today
20:38:17 -!- _AndoDaan has changed nick to AndoDaan.
20:38:19 <Koen_> or whatever fancy name you call those classes in english
20:38:50 <Koen_> and we talked about Post problems, which are basically a string-rewriting thingy
20:39:21 <Koen_> and the first example we had was one where we had a binary string, and it kept increasing
20:40:49 <Koen_> 0000p 0001q 0001p 000p0 0001q etc
20:41:09 <Koen_> it wasn't obvious from the beginning that was what was happening
20:41:57 <HackEgo> [wiki] [[Brainfuck-ng]] http://esolangs.org/w/index.php?diff=41852&oldid=41850 * Rdebath * (-1) CnP error
20:42:14 <Koen_> so we had all those trandformations rules written down, that were actually kinda hard to read
20:42:22 <Koen_> and the teacher asked us the next string at every step
20:42:41 <Koen_> which is sloooow if you have to find the correct rule without knowing what to expect
20:43:17 <Koen_> and at some point I realized no one else knew what to expect so they had all been doing hard work
20:45:59 <Koen_> that class is fun but also somewhat disappointing as sometimes it sounds like we're reading a random page from esolangs wiki
20:46:22 <Koen_> it would be more fulfilling if I felt like we were building something
20:47:11 -!- ^v^v has joined.
20:47:31 -!- skj3gg has quit (Quit: ZZZzzz…).
20:47:49 -!- nycs has joined.
20:49:57 -!- `^_^v has quit (Ping timeout: 250 seconds).
20:49:57 <Koen_> I mean, math classes go like "we want to do fun stuff with probabilities, so let's build a whole measure theory for that"
20:50:23 -!- ^v has quit (Ping timeout: 245 seconds).
20:50:44 <Koen_> but the computerry classes go like "erm okay so this is an automat. and this is an automat hooked to a tape. and this is a string-rewriting thingy."
20:51:13 <b_jonas> Ugh, measure theory is ugly. I still don't understand the basics of the important proofs, despite that they're supposed to be nice.
20:51:35 -!- Tritonio has quit (Remote host closed the connection).
20:51:53 -!- Tritonio has joined.
20:54:33 -!- _AndoDaan has joined.
20:55:13 -!- FreeFull has quit (Ping timeout: 256 seconds).
20:55:18 <MDude> Whu do computer class have to do with restaraunts based on walls of vending machines?
20:55:22 -!- Sprocklem has quit (Ping timeout: 240 seconds).
20:55:23 -!- _AndoDaan_ has joined.
20:56:46 -!- AndChat-234416 has joined.
20:57:19 -!- AndoDaan has quit (Ping timeout: 245 seconds).
20:58:01 -!- AndChat-234416 has quit (Client Quit).
20:58:57 -!- _AndoDaan has quit (Ping timeout: 252 seconds).
20:59:41 -!- _AndoDaan_ has quit (Ping timeout: 252 seconds).
21:07:19 -!- skj3gg has joined.
21:18:18 <J_Arcane> "// false, null, undefined, NaN, 0 and "" are falsy; everything else is truthy. Note that 0 is falsy and "0" is truthy, even though 0 == "0"."
21:18:53 <b_jonas> J_Arcane: is that about ecmascript?
21:19:18 <J_Arcane> Reading the learnxiny for JavaScript yeh.
21:22:15 -!- GeekDude has changed nick to GeekAfk.
21:23:21 -!- AndoDaan has joined.
21:34:09 -!- Lymia has joined.
21:37:49 <HackEgo> [wiki] [[Malbolge]] http://esolangs.org/w/index.php?diff=41853&oldid=41721 * 70.36.190.3 * (+13) /* Virtual machine description */ Specify initial register values
21:39:08 -!- ^v^v has quit (Ping timeout: 245 seconds).
21:43:54 -!- TieSoul_ has joined.
21:46:07 -!- TieSoul has quit (Ping timeout: 245 seconds).
21:47:04 -!- FreeFull has joined.
21:54:44 <J_Arcane> ... .JS dates use 0-based month field ... why?
21:58:46 <FreeFull> The question is why everything else uses 1-based month fields
21:59:34 <Melvar> I would presume that’s because they’re normally written in dates.
22:00:22 <Melvar> If you write down a date, the month is represented as a number 1-12.
22:00:51 <J_Arcane> Not to mention, why only Months?
22:01:07 <J_Arcane> Well, I say that, but days of the week are 0-indexed too I think.
22:09:56 -!- nycs has quit (Quit: This computer has gone to sleep).
22:12:57 -!- GeekAfk has changed nick to GeekDude.
22:15:48 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:27:49 -!- skj3gg has quit (Quit: ZZZzzz…).
22:28:22 -!- `^_^v has joined.
22:32:17 -!- hjulle has joined.
22:41:38 -!- AndoDaan has quit (Quit: Going, going, gone.).
22:42:36 -!- oren has quit (Ping timeout: 245 seconds).
22:45:44 -!- 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?").
22:54:31 -!- oren has joined.
22:59:57 -!- Lilax has joined.
23:00:18 <Lilax> > var foo = new object[]{ 1, 2, 3 }; int bar = foo[1];
23:00:20 <lambdabot> <hint>:1:9: parse error on input ‘=’
23:02:09 -!- ProofTechnique has joined.
23:02:29 <Lilax> "list foo = [1,2,3]; integer bar = llList2Int(list, 1);"
23:05:23 -!- Lymia has quit (Ping timeout: 245 seconds).
23:05:35 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:06:56 -!- AnotherTest has quit (Ping timeout: 246 seconds).
23:08:43 -!- Lymia has joined.
23:14:37 -!- oerjan has joined.
23:21:00 -!- Lilax has changed nick to Lilax|away.
23:21:26 <oerjan> curses, goldfire bypassed int-e's Kindable trap
23:22:42 -!- AndoDaan has joined.
23:26:02 -!- Tritonio has quit (Remote host closed the connection).
23:26:49 -!- Phantom_Hoover has joined.
23:27:45 -!- adu has quit (Ping timeout: 264 seconds).
23:39:39 -!- hjulle has quit (Ping timeout: 264 seconds).
23:44:20 -!- ^v has joined.
23:49:05 -!- ^v^v has joined.
23:51:44 -!- ais523 has quit (Ping timeout: 246 seconds).
23:52:03 -!- ^v has quit (Ping timeout: 245 seconds).
23:57:34 * Sgeo wonders if the trick for monads in dynamically typed languages would work in F3
23:58:29 <oerjan> Lilax|away: trying to convince him that fixing the ghc bug requires creating something like a Kindable class.
23:59:37 -!- boily has joined.
00:05:14 -!- Lilax|away has quit (Read error: Connection reset by peer).
00:09:22 <boily> オォォォォッ！あちらも日本語IMEで書けています!すごい！
00:09:27 -!- shikhin_ has joined.
00:10:43 <boily> 天気はどうですか ここにはもっとも寒い（＞＿＜）
00:12:01 <oren> ここも寒い。冬はもうおわんない
00:12:33 -!- shikhin has quit (Ping timeout: 252 seconds).
00:13:26 <oerjan> i think this channel may have entered the matrix, there are all these strange symbols
00:14:36 <oerjan> unless this is zalgo, see today's sromg (NSFL)
00:15:05 <oerjan> square root of minus garfield
00:16:11 <oerjan> mezzacotta / david morgan mar's collaborative garfield parody comic
00:17:31 <oren> ギャアア！その漫画は怖いよ！
00:17:34 <oerjan> he just added a dinosaur comic collaborative fan comic, so now i'm reading that without reading dinosaur comic itself...
00:18:42 <olsner> how much better is the fan comic than the original?
00:18:55 <oren> そのSROMG漫画を読んでいます
00:18:57 <boily> obscure webcomics are obscure for a reason.
00:19:05 <olsner> I've been trying to find dinosaur comics funny for some time now
00:19:20 <oren> They aren't that funny
00:19:24 <oerjan> olsner: hm, in that case probably a lot
00:19:55 <boily> oren: わかります 僕は読まないんだよ
00:20:24 <boily> olsner: hellolsner. they were supposed to be funny?
00:20:38 <olsner> boily: what else could they be supposed to be?
00:20:56 <oerjan> i thought today's fan comic was funny, anyway
00:21:35 <oren> my favorite webcomic (in English) is "Basic Instructions"
00:21:38 <boily> olsner: philosophical? reflective? introspective?
00:22:29 <boily> I'm still a thorough fan of xkcd.
00:22:46 <boily> olsner: a fortunate incident.
00:24:10 <HackEgo> 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.
00:24:10 <HackEgo> 918) <olsner> boily: the man eating chicken is just a normal man, it's quite common to eat chicken in some parts of the world \ 919) <elliott> ~eval 1+2 <cuttlefish> Error (127): <elliott> this is a great bot boily i love it \ 928) <boily> not only there is no God, but try to find an APL keyboard on Sunday. \ 931) <boily> ais523: I'm not sure my
00:24:35 <HackEgo> The lystrosaurs were an ancient genus of evil reptiles who successfully took over the world in the early Triassic.
00:24:36 <boily> (huh. I thought there were l[iy]strosaurs somewhere in oerjan's `?...)
00:24:40 -!- ais523 has joined.
00:25:00 <oerjan> boily: i guess you just associated on "evil" hth
00:25:15 <boily> oerjan: naturally.
00:25:39 * oerjan denies being a lystrosaur recently awakened from stasis
00:25:52 <olsner> oerjan is an evil overlord, lystrosaurs were evil and took over the world => became overlords, everything matches up
00:26:06 <olsner> denial doesn't make it not so
00:26:11 <oerjan> i hear elizabeth II might be one, though
00:27:31 <oerjan> i suppose lystrosaurs were also antediluvian
00:27:57 <oerjan> and roald dahl wrote books about defeating evil monsters, so they'd naturally hate him.
00:28:10 <oerjan> yeah, a surprising amount of matches there
00:52:14 -!- ais523 has quit.
00:57:46 -!- ais523 has joined.
01:17:34 -!- AndoDaan has quit (Quit: Going, going, gone.).
01:17:36 -!- Tod-Autojoined has changed nick to TodPunk.
01:43:23 -!- oren has quit (Read error: Connection reset by peer).
01:44:18 -!- oren has joined.
01:44:33 -!- Lymia has quit (Ping timeout: 245 seconds).
01:57:51 <quintopia> and you'd already be in bed half an hour from now when i got home
01:59:14 <boily> real life is an illusion. and besides, this chännel entered the matrix a few hours ago.
02:01:02 <boily> so you're back home? have you enjoyed your trip?
02:01:10 <oerjan> i dunno, the strange symbols seem to have disappeared
02:01:50 <oerjan> is mainly in the plane
02:04:55 <ais523> huh, apparently I shouldn't try to send email during a distro upgrade
02:05:09 <ais523> the email editor in Evolution has no send button
02:05:16 <ais523> and when I try to close the compose window
02:06:11 <ais523> it puts up a dialog box with an information icon and no text
02:07:36 <boily> oerjan: don't worry. the next swarm will strike when you least expect it.
02:07:44 <boily> ais523: which distro?
02:30:49 -!- boily has quit (Quit: MOXIBUSTIVE CHICKEN).
02:31:29 <oerjan> HE'S JUST PLAYING WITH US
02:31:38 <ais523> ugh, the distro upgrader seems to have crashed
02:32:23 <lambdabot> http://en.wikipedia.org/wiki/Moxibustion
02:32:24 <lambdabot> Title: Moxibustion - Wikipedia, the free encyclopedia
02:32:41 <lambdabot> *** "word" wn "WordNet (r) 3.0 (2006)"
02:32:41 <lambdabot> n 1: a unit of language that native speakers can identify;
02:32:41 <lambdabot> "words are the blocks from which sentences are made"; "he
02:32:41 <lambdabot> hardly said ten words all morning"
02:32:56 <ais523> my response was to kill dpkg, it seems to be continuing now, at least
02:33:07 -!- AndoDaan has joined.
02:33:18 <ais523> I've restored Ubuntu from a broken distro upgrade before now
02:33:22 <ais523> but prefer it when I don't have to
02:33:43 <ais523> let's hope that whatever package it didn't install isn't essential for the computer to boot
02:39:44 -!- Lymia has joined.
02:47:05 -!- Phantom_Hoover has quit (Remote host closed the connection).
02:57:45 -!- shikhin_ has quit (Ping timeout: 264 seconds).
02:59:05 -!- adu has joined.
03:44:53 <ais523> OK, about to reboot into the new distro
03:45:01 <ais523> I've done the best I can to manually fix things
03:45:07 -!- ais523 has quit (Quit: rebooting).
03:48:13 -!- AndoDaan has quit (Quit: Going, going, gone.).
03:49:56 -!- ais523 has joined.
03:50:21 <ais523> ooh, I think it worked
03:50:48 <ais523> huge number of crash reports, but I think all of them were either caused by a bug in ocaml-doc, or indirectly from my kill -9 dpkg during the upgrade
03:54:02 <ais523> nah, famous last words would be me before the reboot
03:54:48 <oerjan> i cannot help it, i'm reading the tvtropes untwist page
04:02:41 <ais523> oh, hmm, the unity dash still has terrible performance
04:02:51 <ais523> it only takes like 5 seconds to open rather than like 15
04:05:23 -!- rodgort has quit (Ping timeout: 252 seconds).
04:13:04 -!- Sprocklem has joined.
04:15:13 -!- Sprocklem has quit (Client Quit).
04:16:04 -!- rodgort has joined.
04:25:37 <oren> ais523: that's why I switched to Xubuntu
04:26:47 <oren> well, also because I like windows and hate mac, and i hate how everyone wants to be an iphone now
04:30:41 -!- rodgort has quit (Ping timeout: 252 seconds).
04:34:32 <oerjan> i don't want to be an iphone hth
04:35:15 <oerjan> i also don't want to be a lumberjack. (nothing wrong with lumberjacks, they're okay.)
04:35:49 -!- Eolus has joined.
04:36:14 <oerjan> what evil plans dost thou laugh about
04:38:30 <Eolus> I truly don't know
04:39:14 <Eolus> We had a headache earlier and I dun know maybe I'm just wantin' to laugh
04:39:56 <oerjan> well it is good to practice one's evil cackling
04:41:58 <oerjan> still addicted to 30x30 Bridges
04:42:58 <Eolus> Ok, So I made a self modifying encryption key for my bot
04:43:04 <Eolus> and I am proud of me self
04:43:17 <Eolus> Although it breaks every other day ;--;
04:43:48 <int-e> oerjan: I'm soooo sorry.
04:44:12 <oerjan> you have to make it _remember_ that you modified it hth
04:44:27 <oerjan> no, the 30x30 Bridges is int-e's fault
04:45:13 <int-e> oerjan: you did retaliate however, by pointing me to yet another webcomic.
04:45:28 <Eolus> lol webcomics and oerjan
04:45:58 <int-e> (namely, Rice Boy)
04:46:11 <oerjan> well i learned about rice boy on this channel, i think
04:47:07 -!- rodgort has joined.
04:49:09 -!- rodgort has quit (Excess Flood).
04:51:08 <oerjan> kom mai du skjønne milde
04:52:25 <Eolus> http://puu.sh/fxhxd/9833c39b67.gif
04:56:51 <int-e> Eolus: You're so || close to failing the Turing test.
04:58:16 <Eolus> I have no idea who you are ^_^
05:03:28 <oren> neildegrasse_ok_well.gif
05:08:47 <oerjan> int-e: wait are you saying Eolus has been a bot all along
05:13:44 <oren> osaka_oh_mai_gaa.m4a
05:16:00 <int-e> oerjan: no, of course not. stop reading between the lines!
05:17:24 -!- rodgort has joined.
05:17:54 <oerjan> int-e: well i have to do it to keep passing the turing test
05:18:27 <oren> Eolus: the correct format for dates, btw is YYYY-MM-DD
05:18:44 <oren> or maybe YYYY.MM.DD
05:19:50 <int-e> https://xkcd.com/1179/
05:20:33 <oren> Although, there should be a standard for where and how to put the weekday
05:21:26 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:21:33 <oren> One idea is to do 2015-02F06
05:22:06 <oren> With letters MTWRFSU for the weekdays
05:22:29 <oerjan> i agree that it is one idea.
05:23:42 <int-e> 2015-02-06 is 2015-W05-5
05:23:51 -!- rodgort has quit (Ping timeout: 252 seconds).
05:24:17 <oren> Hmm. In japan they do Y年M月D日（W）
05:24:28 <int-e> elliott: thanks, you're right.
05:24:28 <HackEgo> January 2015 \ Su Mo Tu We Th Fr Sa \ 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
05:24:37 <int-e> `` date +%Y-W%V-%u
05:25:01 <int-e> date has a few too many of those week number and day of week format strings.
05:25:43 <oerjan> hm so it includes the short week?
05:26:18 <oerjan> which is officially a week of the previous year
05:26:44 <int-e> yes. note that the ISO week is from Mo to Su, so that's 4 days in 2015.
05:26:48 <oerjan> it starts listing on Su
05:26:55 <Eolus> who said I was doing dates?
05:27:06 <oerjan> Eolus: so you prefer figs?
05:27:08 <int-e> Eolus: this channel isn't about you.
05:27:32 <Eolus> Go to your cupboard
05:29:17 <oerjan> Eolus: please be more polite.
05:29:22 <int-e> oh, %Y is also wrong.
05:29:51 <int-e> `` date +%G-W%V-%u -d2016-01-01
05:36:08 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
05:37:11 <oren> `` LC_TIME=jp_JA.utf8 ; date
05:37:11 <HackEgo> bash: warning: setlocale: LC_TIME: cannot change locale (jp_JA.utf8): No such file or directory \ Fri Feb 6 05:37:09 UTC 2015
05:37:21 <oren> `` LC_TIME=jp_JA ; date
05:37:21 <HackEgo> bash: warning: setlocale: LC_TIME: cannot change locale (jp_JA): No such file or directory \ Fri Feb 6 05:37:19 UTC 2015
05:42:16 <HackEgo> Fri Feb 6 14:42:14 JST 2015
05:42:18 <oren> Anyway the japanese notation has the advantage that each part of the date is clearly labeled, making an order irrelevant
05:45:47 <oren> Effectivley the advantage is the same as assigned arguments for a function call
05:47:47 -!- rodgort has joined.
05:48:38 -!- rodgort has quit (Excess Flood).
05:58:10 -!- ProofTechnique has joined.
06:18:33 -!- rodgort has joined.
06:29:56 -!- FreeFull has quit (Ping timeout: 244 seconds).
06:36:05 -!- rodgort has quit (Ping timeout: 252 seconds).
06:38:58 -!- rodgort has joined.
06:42:59 -!- adu has quit (Quit: adu).
07:01:50 -!- adu has joined.
07:14:22 -!- Eolus has quit (Ping timeout: 240 seconds).
07:21:56 -!- FreeFull has joined.
07:30:48 -!- adu has quit (Quit: adu).
07:33:16 -!- arjanb has quit (Quit: bbl).
07:36:33 -!- oerjan has quit (Quit: ni nite).
07:49:19 -!- Patashu has joined.
08:13:04 -!- MDude has changed nick to MDream.
08:22:09 -!- Tritonio has joined.
08:30:12 -!- shikhin has joined.
08:59:04 -!- ais523 has quit (Quit: breakfast).
09:26:04 -!- ais523 has joined.
09:35:53 -!- shikhin has changed nick to sortie.
09:35:58 -!- sortie has changed nick to shikhin.
09:49:01 -!- augur has quit (Read error: Connection reset by peer).
09:49:11 -!- Patashu has quit (Read error: Connection reset by peer).
09:49:24 -!- augur has joined.
09:49:31 -!- Patashu has joined.
09:51:31 -!- rodgort has quit (Ping timeout: 252 seconds).
09:53:24 -!- AnotherTest has joined.
09:58:25 -!- rodgort has joined.
10:03:43 -!- rodgort has quit (Ping timeout: 245 seconds).
10:13:29 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=41854&oldid=40843 * Elboza * (+213) /* Notable implementations */
10:15:26 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=41855&oldid=41791 * Elboza * (+213) /* Normal implementations */
10:16:42 -!- Phantom_Hoover has joined.
10:21:26 <J_Arcane> writing mutation feels so wrong now ...
10:38:18 -!- Lymia has quit (Ping timeout: 245 seconds).
10:43:29 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=41856&oldid=41854 * Ais523 * (-213) Undo revision 41854 by [[Special:Contributions/Elboza|Elboza]] ([[User talk:Elboza|talk]]) this shouldn't be on both lists, and this one is the wrong one
11:02:26 -!- Patashu has quit (Disconnected by services).
11:02:26 -!- Patashu_ has joined.
11:09:25 -!- hjulle has joined.
11:15:37 -!- ^v^v has quit (Read error: Connection reset by peer).
11:16:05 -!- ^v^v has joined.
11:21:20 -!- boily has joined.
11:55:07 -!- Tritonio_ has joined.
11:56:42 -!- Tod-Autojoined has joined.
11:57:10 -!- TodPunk has quit (Read error: Connection reset by peer).
11:57:26 -!- Tritonio has quit (Ping timeout: 252 seconds).
11:58:26 -!- ocharles_ has quit (Ping timeout: 245 seconds).
11:59:49 -!- perrier has quit (Ping timeout: 250 seconds).
12:00:09 -!- trn has quit (Ping timeout: 265 seconds).
12:00:43 -!- Tritonio_ has changed nick to Tritonio.
12:01:06 -!- perrier has joined.
12:01:20 -!- ocharles_ has joined.
12:01:40 -!- ais523 has quit.
12:01:43 -!- trn has joined.
12:03:54 -!- nyuszika7h has quit (Read error: Connection reset by peer).
12:05:38 -!- nyuszika7h has joined.
12:08:51 -!- Taneb has quit (Ping timeout: 245 seconds).
12:10:53 -!- Taneb has joined.
12:12:07 -!- ski has joined.
12:14:06 -!- Melvar` has joined.
12:19:10 -!- perrier has quit (*.net *.split).
12:19:10 -!- Phantom_Hoover has quit (*.net *.split).
12:19:10 -!- Melvar has quit (*.net *.split).
12:19:10 -!- copumpkin has quit (*.net *.split).
12:19:10 -!- intgr has quit (*.net *.split).
12:19:10 -!- elliott has quit (*.net *.split).
12:19:10 -!- incomprehensibly has quit (*.net *.split).
12:19:10 -!- rsal has quit (*.net *.split).
12:19:11 -!- quintopia has quit (*.net *.split).
12:20:58 -!- perrier has joined.
12:20:58 -!- Phantom_Hoover has joined.
12:20:58 -!- intgr has joined.
12:20:58 -!- rsal has joined.
12:20:58 -!- copumpkin has joined.
12:20:58 -!- elliott has joined.
12:20:58 -!- incomprehensibly has joined.
12:20:58 -!- quintopia has joined.
12:22:45 -!- boily has quit (Quit: THERAPEUTIC CHICKEN).
12:34:33 -!- shikhin_ has joined.
12:37:24 -!- shikhin has quit (Ping timeout: 252 seconds).
12:38:16 -!- shikhin_ has changed nick to shikhin.
12:43:18 -!- SopaXorzTaker has joined.
13:00:14 <Taneb> Officially learnt about the "Fundamental Theorem of Linear Transformations" today
13:00:45 <Taneb> It seems very similar to what I know as the "Fundamental Theorem of Group Homomorphisms"
13:01:08 <Taneb> Both are S/Ker(phi) ~= Im(phi)
13:01:12 <Taneb> Is there something deeper going on?
13:03:34 -!- ais523 has joined.
13:04:28 -!- rodgort has joined.
13:04:29 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
13:05:10 -!- rodgort has quit (Excess Flood).
13:05:30 <b_jonas> Taneb: sure, a vector space is a group, and all vector space homomorphisms are group homomorphisms as well (but not the reverse)
13:05:43 <b_jonas> but that's not really "something deeper" I guess
13:05:52 <Taneb> b_jonas, but a vector space has more conditions than a group
13:06:12 <Taneb> And not all group homomorphisms end up as linear transformations
13:10:37 -!- Frooxius has joined.
13:10:53 -!- Patashu_ has quit (Ping timeout: 250 seconds).
13:17:01 -!- TieSoul_ has changed nick to TieHomework.
13:22:48 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
13:27:33 -!- Koen__ has joined.
13:30:35 -!- GeekDude has joined.
13:47:09 <jameseb> Taneb: I was under the impression that that was what category theory was for, though I don't know enough category theory to verify that
13:49:22 -!- Melvar` has changed nick to Melvar.
13:50:50 -!- Tritonio has quit (Remote host closed the connection).
13:51:25 -!- Tritonio has joined.
13:54:16 -!- ProofTechnique has joined.
14:15:54 -!- spiette has joined.
14:29:35 -!- SopaXorzTaker has quit (Remote host closed the connection).
14:37:30 -!- Lymia has joined.
14:42:00 -!- SopaXorzTaker has joined.
15:00:35 -!- skj3gg has joined.
15:15:59 -!- oerjan has joined.
15:17:03 -!- `^_^v has joined.
15:45:55 -!- skj3gg has quit (Quit: ZZZzzz…).
15:55:26 <Taneb> I've just reread the end of IWC backwards
15:55:39 * oerjan cannot quite stop quibbling about the Typeable bug
15:56:10 -!- skj3gg has joined.
15:56:39 <oerjan> Taneb: so it's about several groups of people falling from prosperity, through great disaster, and into a continued life of trouble and chaos?
15:57:02 <Taneb> oerjan, it made me realise that Choking may in fact be DMM
15:58:26 <Taneb> DMM's body and Hitler's brain
15:59:10 <Taneb> http://irregularwebcomic.net/3147.html http://irregularwebcomic.net/3158.html http://irregularwebcomic.net/3165.html
16:00:46 -!- SopaXorzTaker has quit (Ping timeout: 264 seconds).
16:01:18 -!- ais523 has quit.
16:01:35 <oerjan> that _does_ look deliberate indeed.
16:03:48 -!- adu has joined.
16:04:16 <Taneb> I need to reread IWC
16:10:59 -!- mihow has joined.
16:12:38 -!- SopaXorzTaker has joined.
16:13:42 <b_jonas> DMM is present as a self-insert in IWC and he's not the same as Choking
16:13:55 <b_jonas> he time travels and almost kills himself or something
16:20:46 <oerjan> b_jonas: it's actually hitler who is the same as choking
16:21:04 <oerjan> also, there's not "almost" about it.
16:23:11 <Koen__> are you all regular fans of iwc?
16:23:58 <oerjan> it was the first webcomic i read, and i learned about it on this channel.
16:24:24 <oerjan> Taneb and b_jonas traveled in the opposite direction :P
16:26:26 <Taneb> Yeah, it was my first webcomic, and eventually got me into esolangs and actually CS as a whole
16:26:29 <int-e> I used to like IWC but got bored around the 2700 strips mark.
16:27:09 <oerjan> <Taneb> Is there something deeper going on? <-- yes. there are versions of those theorems for universal algebras.
16:27:18 <b_jonas> the first webcomic I read was StickManStickMan, now at http://stickman.qntm.org/index.php , which was already completed when I first read it
16:27:21 <Taneb> Universal... algebra?
16:28:03 <oerjan> Taneb: think of groups, monoids, rings, vector spaces etc. as all being special cases of operations on a set
16:28:37 <b_jonas> oerjan: do you mean K-vector spaces for a particular fixed field K?
16:28:55 <oerjan> if _some_ of the operations give you a group, then you have kernels, and the theorems have essentially the same form. otherwise you need to use "congruences".
16:29:42 <oerjan> but otherwise it's quite analogous regardless of the type of algebra.
16:30:20 <b_jonas> oerjan: ok, and how much extra do you need for the form on finitely generated vector spaces, where you can also claim that the dimension of of the source space is equal to the dimension of the kernel plus the dimension of the image?
16:30:51 <oerjan> b_jonas: ouch. that doesn't even hold for modules i think, so quite specific.
16:31:05 <oerjan> modules aren't always free and so don't have a basis.
16:31:28 <b_jonas> oerjan: yes, it's specific for vector spaces, but quite important
16:31:47 <b_jonas> I'm not sure what happens in infinite dimensional spaces
16:31:58 <oerjan> i think it may be summarized as "all vector spaces are free"
16:32:07 <oerjan> although i'm not sure if that's enough
16:32:13 -!- S1 has joined.
16:32:45 <oerjan> in fact there's probably a module counterexample about free submodules of free modules behaving nicely
16:33:08 <oerjan> my memory of that stuff is old
16:33:18 <b_jonas> you don't really have a sane dimension in modules
16:33:37 <b_jonas> not even when finitely generated
16:34:27 <b_jonas> Infinite vector spaces supposedly have a basis and so they have a dimension, though I've never tried to understand the proof for this. It's an axiom of choice thing.
16:34:44 -!- skj3gg has quit (Quit: ZZZzzz…).
16:35:04 <oerjan> int-e: you seem to have become bored about when dmm started wrapping things up for the finale...
16:35:51 -!- skj3gg has joined.
16:35:56 -!- Phantom_Hoover has joined.
16:37:03 <oerjan> <b_jonas> I'm not sure what happens in infinite dimensional spaces <-- i think it still holds as long as you sum cardinalities. of course you cannot subtract then.
16:37:12 -!- MDream has changed nick to MDude.
16:37:57 <oerjan> b_jonas: yeah it's basically about using zorn's lemma to increase your independent set until it generates everything.
16:38:12 <oerjan> nothing complicated, actually.
16:38:55 <oerjan> just it needs the big cannon
16:40:21 -!- Phantom__Hoover has joined.
16:40:27 <b_jonas> Meh, the zorn lemma isn't the big cannon.
16:40:30 -!- Phantom__Hoover has quit (Client Quit).
16:40:34 -!- SopaXorzTaker has quit (Remote host closed the connection).
16:40:51 -!- Phantom__Hoover has joined.
16:40:57 <b_jonas> Not when the calculus guys use basic theorems whose proofs are really complicated, unlike that of the zorn lemma.
16:40:58 <oerjan> well then there's nothing complicated at all :P
16:41:09 <int-e> oerjan: yeah maybe he should've done that sooner then *ducks*
16:41:34 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
16:42:41 <b_jonas> well, http://mathoverflow.net/a/99568/5340 states zorn lemma is big guns in the sense I claim it's not
16:46:22 <oerjan> Taneb: anyway, https://en.wikipedia.org/wiki/Isomorphism_theorem#General
16:46:47 <b_jonas> also, aren't there two or three fundamental theorems?
16:47:57 <oerjan> the one discussed here is the first
16:48:27 <b_jonas> ok wait, I don't think I want to do universal algebra directly, so let me look at the group ones, those I'll probably recognize
16:50:00 <b_jonas> Yes, I think I've heared of these for groups.
16:50:49 <b_jonas> And https://en.wikipedia.org/wiki/Rank%E2%80%93nullity_theorem is the one about vector space dimensions
16:51:28 -!- aretecode has quit (Ping timeout: 272 seconds).
16:52:20 -!- oren has quit (Ping timeout: 246 seconds).
16:53:11 <oerjan> i was about to link that
16:55:20 <oerjan> to get an intuition for the general, you need to understand that kernels/normal subgroups/ideals are all specific ways of encoding a congruence
16:55:27 <HackEgo> isomorphism theorem? ¯\(°_o)/¯
16:56:35 <b_jonas> you need that to understand normal subgroups and ideals in rings in first place
16:57:19 <Phantom__Hoover> oerjan, at least in the first case that's just stating the standard definition with slightly different terms
16:57:37 -!- ais523 has joined.
16:57:39 <Phantom__Hoover> i dunno about the second and third because, well, who actually gives a shit about the second and third isomorphism theorems
16:57:49 <b_jonas> Phantom__Hoover: what? they're useful
16:58:39 -!- GeekDude has changed nick to }{FISH}.
16:59:09 <oerjan> also, defining a congruence as a subalgebra of A x A may be elegant, but maybe not the most pedagogic way.
16:59:35 <oerjan> also, i agree with both of you, they're useful but i can only remember the first :P
17:00:21 <oerjan> without straining my brain, anyhow
17:00:43 <b_jonas> I mean, you use them all the time without referring to them explicitly
17:00:44 <Phantom__Hoover> the second and third are useful properties of algebraic quotients; the first fundamentally encapsulates what algebraic quotients are
17:00:57 -!- skj3gg has quit (Quit: ZZZzzz…).
17:01:21 <oerjan> anyway, should be going ->
17:01:28 -!- oerjan has quit (Quit: Later).
17:01:47 <Phantom__Hoover> i remember when i saw the thing about short exact sequences and quotients in hatcher it seemed like witchcraft, even though it's fairly simple
17:01:52 <b_jonas> which is the usual way algebra works
17:02:09 -!- zzo38 has joined.
17:07:33 <Koen__> b_jonas: you can actually do a lot of things with ideals without understanding they have anything to do with congruences
17:08:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:09:50 -!- ais523 has quit (Ping timeout: 252 seconds).
17:13:35 <Koen__> (I know that because I didn't)
17:14:31 -!- oren has joined.
17:14:53 <Koen__> random thought: why are there so many brainfuck derivatives and so few Turing-machine derivatives on the wiki?
17:17:09 <MDude> They're basically the same thing, technically.
17:17:59 <MDude> Brainfuck with an endless tape is just a specific kind of turing machine, as is P''.
17:18:03 <Koen__> well that's my point! but Turing-machines are historically more relevant, and in my opinion, more fun
17:21:07 <zzo38> It is very easy to compile brainfuck or P'' into Turing machines as each instruction would easily correspond to one state, although sometimes you can merge states
17:24:55 -!- rodgort has joined.
17:30:09 <oren> Brainfuck is easier to derive something from
17:30:51 -!- }{FISH} has changed nick to GeekDude.
17:31:12 <MDude> I just mean the reverse is also true.
17:31:38 <MDude> Any turing machine could be described in a way that makes it look like a Brainfuck derivative.
17:31:46 <MDude> People just go with BF b/c rude.
17:32:05 <oren> Also brainfuck is easy to understand for nonmathy people
17:32:52 <oren> because it is the ultimate simplification of the imperative, structured paradigm
17:33:43 <MDude> P" is actually simpler.
17:35:06 <MDude> Though it does require that epople write ?.
17:35:13 <oren> but turing machines involve symbols and states and rules, where BF has numbers and characters in the code
17:35:20 <MDude> Which as you can see isn't even an ASCII character.
17:36:45 <oren> this is a lamda: λ
17:37:57 <zzo38> You can make the P'' version with ASCII though
17:39:23 <oren> Hm... Is it P" or P''
17:40:18 <Koen__> "nonmathy people" know what a decision tree is, and that looks exactly like an automaton
17:40:39 <b_jonas> nonmathy people probably don't care about this stuff
17:40:40 <Koen__> whereas ++++[-] doesn't look like much
17:42:01 <oren> Koen: I mean people who are qualified to take Game Development 101 but not Game Theory 101
17:42:22 <Koen__> (also by decision tree I probably meant flow chart)
17:43:27 <MDude> A flow chart would more complex than a simple automaton.
17:43:32 <oren> Although I annoy the hell out of my dad by incessantly referring to my game development course as "Game Theory"
17:48:39 <oren> With the course naming problems at UofT, the course that should be named "Operations Research" is named Algorithm Design, Analysis, and Complexity
17:48:56 <oren> So I might not have been wrong
17:54:42 <MDude> To be fair, Operations Research sounds like a course where you research military operations.
17:58:05 -!- rodgort has quit (Ping timeout: 252 seconds).
18:01:24 -!- ^v^v has quit (Read error: Connection reset by peer).
18:01:50 -!- ^v^v has joined.
18:12:29 -!- SopaXorzTaker has joined.
18:15:31 -!- skj3gg has joined.
18:17:02 -!- FreeFull has quit.
18:17:10 -!- arjanb has joined.
18:24:20 -!- SopaXorzTaker has quit (Quit: Leaving).
18:32:26 -!- Koen__ has quit (Quit: Koen__).
18:34:43 -!- shikhin_ has joined.
18:37:12 -!- shikhin_ has changed nick to Beself.
18:37:29 -!- shikhin has quit (Disconnected by services).
18:37:36 -!- Beself has changed nick to shikhin.
18:40:00 -!- rodgort has joined.
18:40:04 -!- skj3gg has quit (Quit: ZZZzzz…).
18:41:03 -!- skj3gg has joined.
18:42:08 -!- skj3gg has quit (Client Quit).
18:42:28 -!- bb010g has joined.
18:44:23 -!- S1 has quit (Quit: S1).
18:46:06 -!- rodgort has quit (Excess Flood).
18:52:47 -!- rodgort has joined.
18:54:26 -!- rodgort has quit (Remote host closed the connection).
18:57:34 -!- skj3gg has joined.
19:06:43 -!- oren has quit (Ping timeout: 255 seconds).
19:15:55 <zzo38> Is it possible to make up an orthodox Magic: the Puzzling where player 1 has a way to gain any amount of life, but only once, and they win if they can set their life total to a Collatz counterexample?
19:20:22 <zzo38> (And otherwise they cannot possibly win)
19:22:21 -!- mihow has quit (Quit: mihow).
19:23:35 -!- oren has joined.
19:24:22 -!- `^_^v has quit (Quit: This computer has gone to sleep).
19:25:40 -!- `^_^v has joined.
19:34:02 -!- oren has quit (Ping timeout: 246 seconds).
19:42:17 -!- skj3gg has quit (Quit: welp, see you later.).
19:51:52 -!- rodgort has joined.
19:56:59 <HackEgo> [wiki] [[Wct]] N http://esolangs.org/w/index.php?oldid=41857 * Mihip * (+1672) Created page with "Wct is hex numeric system analog, but fully consists entirely of the letters. WARNING! Writing a program on it will blow your mind. Wct editor - machine code editor for Wct. =..."
19:58:39 <HackEgo> [wiki] [[Wct]] http://esolangs.org/w/index.php?diff=41858&oldid=41857 * Mihip * (+4) /* Notes */
20:12:43 -!- monotone has joined.
20:13:45 -!- rodgort has quit (Ping timeout: 252 seconds).
20:16:25 -!- mihow has joined.
20:18:51 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41859&oldid=41809 * Mihip * (+10) /* W */
20:23:28 -!- rodgort has joined.
20:50:03 -!- rodgort has quit (Ping timeout: 252 seconds).
20:55:36 -!- `^_^v has quit (Quit: This computer has gone to sleep).
20:58:31 -!- `^_^v has joined.
21:24:16 -!- Froox has joined.
21:27:54 -!- Frooxius has quit (Ping timeout: 244 seconds).
21:33:20 -!- TieHomework has changed nick to TieSoul.
21:33:40 -!- oren has joined.
21:40:04 -!- oren has quit (Ping timeout: 252 seconds).
21:51:52 -!- oren has joined.
22:08:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
22:13:57 -!- Patashu has joined.
22:16:13 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:18:09 -!- adu has quit (Ping timeout: 245 seconds).
22:19:02 -!- oren has quit (Ping timeout: 245 seconds).
22:24:46 -!- AnotherTest has quit (Ping timeout: 264 seconds).
22:37:52 -!- ProofTechnique has joined.
22:38:41 -!- nys has joined.
22:45:18 -!- oerjan has joined.
22:47:09 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:50:19 -!- KingOfKarlsruhe has quit (Quit: ZNC - http://znc.in).
22:50:23 -!- adu has joined.
22:51:26 -!- KingOfKarlsruhe has joined.
22:55:55 <newsham> http://bertfreudenberg.github.io/SqueakJS/
23:02:42 <J_Arcane> heh. I was just thinking about writing a library for .js strings and then clicked here and now there's Squeak.
23:09:18 -!- FreeFull has joined.
23:13:11 <J_Arcane> I thought about implementing string specific versions of the usual first-class functions, you know. So you could do like "string".map().filter() or whatever.
23:16:45 -!- mihow has quit (Quit: mihow).
23:17:54 -!- mihow has joined.
23:17:54 -!- Froox has quit (Read error: Connection reset by peer).
23:17:57 -!- Froo has joined.
23:18:02 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
23:19:54 <J_Arcane> I'm sure someone's already written that, but it would be a fun learning project.
23:30:04 -!- Tritonio has quit (Ping timeout: 252 seconds).
23:30:48 -!- sebbu2 has changed nick to sebbu.
23:34:58 -!- Lymia has quit (Ping timeout: 245 seconds).
23:36:22 -!- Froox has joined.
23:36:27 -!- Froo has quit (Read error: Connection reset by peer).
23:37:05 -!- Lymia has joined.
23:38:39 -!- Froo has joined.
23:42:15 -!- Froox has quit (Ping timeout: 250 seconds).
23:42:51 -!- bb010g has joined.
23:47:31 <oerjan> zzo38: if the collatz counterexample can be one which grows indefinitely rather than looping, and if the win condition has to be detected in finite time, then i don't see how you can possibly distinguish that from a number that just takes a very long time to reach 1
23:48:05 <oerjan> (i say this knowing very little about MtG)
23:48:42 <oerjan> @tell zzo38 if the collatz counterexample can be one which grows indefinitely rather than looping, and if the win condition has to be detected in finite time, then i don't see how you can possibly distinguish that from a number that just takes a very long time to reach 1
23:53:29 -!- AndoDaan has joined.
00:09:44 -!- ^v^v has changed nick to ^v.
00:11:03 -!- ^v has quit (Quit: Network ban).
00:11:18 -!- ^v has joined.
00:16:11 -!- mihow has quit (Quit: mihow).
00:22:33 -!- hjulle has quit (Ping timeout: 250 seconds).
00:35:06 -!- shikhin_ has joined.
00:38:09 -!- shikhin has quit (Ping timeout: 245 seconds).
00:59:20 <Sgeo> Is it reasonable or unreasonable to expect alpha software to not crash and die on untrusted input?
01:19:59 <FreeFull> Browsers really should handle untrusted inputs well, because the entirety of the web is an untrusted input..
01:21:07 <Sgeo> The question is, as alpha software?
01:21:17 <Sgeo> Not sure what sort of issue
01:21:27 <Sgeo> https://www.reddit.com/r/janusVR/comments/2v191r/security/
01:22:47 -!- Adrop has joined.
01:24:43 -!- Adrop has left.
01:33:25 <zzo38> Of course any internet client or server needs to untrust the input from the other side please (although they could have configuration options to partially trust them, it should normally be untrusted by default; some internet software might be very special case though so they have other requirements).
01:50:21 -!- FreeFull has quit (Ping timeout: 256 seconds).
01:54:50 -!- FreeFull has joined.
01:56:16 -!- oren has joined.
01:58:34 <Jafet> No more unreasonable than expecting ubiquitous release-version software to get pwnedzord on untrusted input
01:58:42 <Jafet> which it does, every day
02:02:27 -!- mbrcknl has quit (Ping timeout: 276 seconds).
02:02:40 * oerjan is pretty sure Jafet reversed his sense of meaning there
02:05:01 -!- incomprehensibly has quit (Ping timeout: 265 seconds).
02:17:24 <oren> Sgeo: depends what kind of software it is
02:20:36 <oren> Web browsers are effectively interpreters for a messy dialect group of programming languages.
02:21:02 -!- J_Arcane_ has joined.
02:21:04 <oren> So i wouldn't say it's unexpected that they could segfault
02:21:23 -!- adu has quit (Quit: adu).
02:22:06 <zzo38> It isn't unexpected but it still isn't supposed to and it is still way too messy even if it doesn't segfault.
02:22:28 -!- J_Arcane has quit (Ping timeout: 245 seconds).
02:22:42 -!- J_Arcane_ has changed nick to J_Arcane.
02:27:42 <oren> Anyway this JanusVR thing looks like crap. If you're going to reinvent the internet, make it entirely new and better, standardize it, and for the love of god, don't base it on XML.
02:29:06 -!- adu has joined.
02:29:56 <MDude> Web, technically, not internet.
02:33:27 <MDude> And not even neccisarily a full replacement for browsers.
02:33:43 <oren> Right. The main problem is that the web is an application framework that evolved from a document format.
02:34:26 <MDude> It seems more like a VR thing that happens to use web pages as supplimentary source of level design.
02:35:13 <MDude> Which I wouldn't mind, but if something's going to be a web browser it should follow an open specification.
02:35:26 <zzo38> The web is a terrible mess.
02:35:35 <MDude> Not neccesarilly an enforced standard, though.
02:36:01 <zzo38> You call it "an application framework that evolved from a document format", but actually it is a mess.
02:37:03 * MDude scraps javacript and CSS for not being based on SGML.
02:39:11 <oren> zzo38: I agree.
02:41:22 <oren> That's why so many websites now have their own apps
02:41:51 -!- ProofTechnique has joined.
02:42:53 <zzo38> oren: That isn't really quite a solution either
02:43:19 <lambdabot> ENVA 070150Z 26027KT 9999 BKN028 06/02 Q1009 RMK WIND 670FT 26025G39KT
02:43:37 <oerjan> which part of that tells that the weather is getting ugly twh
02:43:38 <Sgeo> MDude: it has a web browser in it.
02:43:47 <Sgeo> If you press esc, you see the web page version of the world you're in
02:43:55 <Sgeo> Also can put web pages on surfaces
02:44:24 <MDude> I don't think there's a VR client that doens't have a web browser of some sort built in.
02:44:44 <MDude> Except for maybe a few that are built into web browser.
02:44:46 <Sgeo> Does Flatland?
02:45:10 <MDude> It's a Netscape plugin, so it's in another browser already.
02:45:16 -!- FreeFull has quit (Ping timeout: 255 seconds).
02:45:20 <Sgeo> I know a "web os" that has a web browser
02:45:33 <zzo38> Actually I think there are some VR clients which don't have a web browser or be a web browser plugin.
02:45:36 <MDude> There's the standalone Flatland rover, but I haven't used it.
02:45:52 <zzo38> There is Gopher VR, for one thing, and a few others I forget.
02:46:15 * Sgeo will soon have an Oculus, hopefully
02:46:56 <oren> I was going to put a web browser in a game i was making, but it turned out to be too hard
02:47:17 <oren> HTML (even a small subset) is too hard to parse
02:48:46 <oren> zzo38: I put TTML it
02:48:48 <zzo38> Hopefully is a bit more easily than HTML.
02:49:24 <zzo38> The format used in Perl
02:49:42 <oren> Pod is a nice format
02:51:30 <MDude> You mean timed text or tagged text?
02:51:53 <oren> I mean the esolang
02:52:11 <MDude> So neither of https://en.wikipedia.org/wiki/TTML
02:52:19 <oren> which uses the C0 control codes for formatting
02:52:52 <oren> http://esolangs.org/wiki/Ttml
02:54:10 -!- incomprehensibly has joined.
02:55:04 <oren> In the version my game implements, the ^[ ^] codes are used for formatting the hyperlinks
02:56:10 <MDude> Sounds similar to ANSI escape codes.
02:56:13 <MDude> https://en.wikipedia.org/wiki/ANSI_escape_code
02:57:19 <oren> Like ^[next/page/path^_Click
02:57:48 <oren> the links would be formatted like that
03:03:06 <oren> Dammit would people please stop writing japanese with Chinese Simplified characters?!
03:04:45 <zzo38> Yes please do and start writing with Japanese characters. (I also don't like Simplified Chinese, but that is a different thing.)
03:05:35 <oren> That's what I mean: http://snag.gy/eVLhS.jpg
03:08:57 <MDude> I'll just go ahead and write things in Sarus.
03:09:27 <oren> The lyrics should say: 君の向かい風 僕が背に受
03:09:53 <pikhq> oren: Aaaagh! Wrong wrong wrong!
03:10:18 <oren> Note the difference in the third and fourth kanji
03:10:50 <oren> pikhq: me or the screenshot's lyrics
03:11:36 <naturalog> haha oren i was sure you're israeli, oren is a hebrew name and means palm (the tree) :)
03:11:54 <oren> naturallog: I'm Canadian
03:12:37 <naturalog> i wish i was canadian too :) haha really :(
03:13:59 <naturalog> btw is anyone here familiar with the lang Maude? i was wondering where it is on the lambda cube
03:15:52 <oerjan> looks like it'd be on a different cube
03:16:08 <oerjan> (whichever prolog is in)
03:16:46 <naturalog> but couldnt be sure about it. im also new to the lambda stuff
03:17:23 <naturalog> afaict prolog is FOL, still Maude is HOL
03:17:35 <oerjan> well i don't actually know maude, just looking at the wikipedia article
03:18:12 <naturalog> i was wondering cause im interested on this formalism http://federwin.sip.ucm.es/sic/investigacion/publicaciones/pdfs/Kademlia%20SpecificationSummary0212.pdf
03:23:21 -!- Tod-Autojoined has changed nick to TodPunk.
03:28:35 -!- AndoDaan has quit (Quit: Going, going, gone.).
03:32:33 <oren> "First we define the sort Bit"... God damn it why are booleans not built in????
03:33:16 <oren> s/why are/why; are/
03:33:38 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
03:36:59 -!- FreeFull has joined.
03:38:02 -!- raptural has joined.
03:38:08 -!- mbrcknl has joined.
03:38:44 <elliott> why build booleans in if you don't have to
03:39:07 -!- raptural has left ("Textual IRC Client: www.textualapp.com").
03:40:42 <elliott> okay yes so it's in some speicifcation language
03:40:49 <elliott> I dunno, I don't get why you're complaining about this
03:40:56 -!- rodgort has joined.
03:42:34 <elliott> it also looks like it does and they defined everything themselves for simplicity or greater control: "NOTE: If you want to test these examples on your own, you should start Maude with the option -no-prelude which lets Maude know that none of its basic modules are included (like Maude's own NAT module which will cause a conflict)."
03:42:51 <elliott> (well, potentially. it's possible that it has naturals but not bits.)
03:42:59 <elliott> anyway, bits and booleans aren't really the same thing
03:43:08 -!- rodgort has quit (Excess Flood).
03:43:09 <elliott> 0 isn't inherently a false-y bit
03:43:23 <elliott> and having to write [false,true,true,false] for 0110 is a pain
03:43:56 <elliott> "And as you can see the state this person ends up in might look a bit strange. (When you're married at the age of one you kind of stick out a bit in kindergarten I guess)." wikipedia's article on maude is a wild ride
03:47:21 -!- augur has quit (Quit: Leaving...).
03:47:51 <oren> Oh god it went back to simplified chinese
03:48:52 <oren> elliott: i'm surprised wikipedia's people didn't "clean it up" by making it all unfun
03:49:59 <oren> Wikipedia is full of killjoys
03:53:13 <MDude> Write [ja,da,da,ja]. Or [da,ja,ja,da].
03:53:37 -!- dianne has quit (Ping timeout: 245 seconds).
03:54:24 -!- augur has joined.
03:55:36 <oren> MDude: what language is that?
03:55:37 -!- dianne has joined.
03:56:08 <MDude> "The Hardest Logic Puzzle Ever" three gods language
04:15:16 -!- FreeFull has quit (Ping timeout: 255 seconds).
04:20:06 -!- shikhin_ has quit (Ping timeout: 245 seconds).
04:27:00 -!- FreeFull has joined.
04:28:51 -!- rodgort has joined.
04:30:10 <oren> Google translate doesn't work well on multilingual text
04:34:20 <int-e> MDude: Addendum: When a God is asked a question that they cannot answer in a logically consistent way, they smite you. Good luck.
04:38:57 <oren> http://postimg.org/image/lf1xao06b/
04:39:32 <oren> It does this when the rest of the page is in Chinese
04:39:55 <zzo38> Do you have to assume that you automatically lose if smited and are not allowed to figure out the answer after that?
04:40:42 <int-e> zzo38: I'm not sure. Usually, when solving a puzzle involves my own death, I look for a new one.
04:41:32 <oren> A setting where gods exist tends to involve an afterlife
04:41:59 <oren> Although if smited you would probably end up living with the liar god
04:43:06 <int-e> MDude: https://xkcd.com/246/ is relevant, too.
04:44:41 -!- FreeFull has quit (Ping timeout: 245 seconds).
04:48:18 <naturalog> ic they do mention calculus of constructions "near" maude, maybe its dtlc http://maude.cs.illinois.edu/w/index.php?title=Other_Tools
04:48:38 <zzo38> oren: Unless you can prove that you would end up living with the liar god, such thing doesn't help.
04:52:57 <MDude> I don't think living with the liar god would be particularly annyoing compared to the others.
04:53:51 -!- Sprocklem has joined.
04:54:14 <MDude> The coin flip god could get tiresome just because you'd have to be mroe vrbose in aksing questions.
04:54:28 -!- Sprocklem has changed nick to Guest61957.
04:54:51 <zzo38> Whether or not it is annoying doesn't seem to be relevant?
04:55:24 <zzo38> Only if you can win or not by figuring out the question, isn't it?
04:56:07 <MDude> I was under the impression oren would sent people to the liar god when smiting them due to presuming that this would be the relatively "bad" afterlife.
04:56:49 <zzo38> If being smited doesn't automatically mean you lose, then being smited is just another way to answer your question isn't it? Therefore you can figure it out from that.
04:56:59 -!- nys has quit (Quit: quit).
04:58:25 <MDude> My aforementioned comment directed towards oren is beyond the scope of the puzzle.
05:00:34 <oren> Hm... I was going off of Christian mythology where Satan is the prince of lies.
05:02:33 <MDude> Makes sense, though he sounds more like a Bizzaro.
05:03:22 <MDude> Worse would be if you had to live with someone who only communicates in yes-no responses as your only source of conversation to begin with.
05:03:28 <pikhq> For extra-bizzaro, Jesus is referred to as "lucifer" in the Vulgate.
05:05:51 -!- chaosagent has joined.
05:06:06 <naturalog> "16:02 < MDude> Worse would be if you had to live with someone who only communicates in yes-no responses as your only" i think the concept of undecidability comes clear when someone pushes you to answer yes/no only
05:06:18 <zzo38> I suppose it might be a title because he is often called light of the world, but that isn't his name, although neither is Jesus; his name is supposed to be Yeshua Ben Josef.
05:06:54 <zzo38> But I don't have a copy of Vulgate anyways.
05:06:55 <naturalog> ^ yes on the hebrew sources he's called Yeshua
05:08:54 <pikhq> zzo38: It was used to describe him as the "light of the world", yes.
05:10:33 <zzo38> pikhq: So, even if it looks like "extra-bizzaro", at least I can see the reason clearly.
05:10:48 <oren> So in English his name would be Jesus Jesephson?
05:11:09 <pikhq> oren: No, "Jesus Ben Josef" or "Yeshua Ben Josef".
05:11:21 <pikhq> Modern English doesn't have a rule of Anglicizing names.
05:11:23 <zzo38> oren: I think so, but I don't study all that history?
05:13:11 <pikhq> naturalog: XD You are right.
05:13:58 -!- Guest61957 has quit (Changing host).
05:13:58 -!- Guest61957 has joined.
05:14:16 -!- Guest61957 has changed nick to Sprocklem.
05:14:18 <oren> What little I know of Christianity is from interactions with the Christian half of my family
05:14:54 <oren> So I dunno if the Devil is supposed to lie all the time, or just sometimes
05:15:45 <zzo38> oren: Some things I know of Christianity from my family but also from studying; sometimes I read various book and learn various stuff, and sometimes I just ask a question, or I just heard/read what someone else has said.
05:15:49 <int-e> in the logic puzzles I've seen He seems to lie constantly.
05:16:20 <int-e> Which is, of course, a stupid strategy for an evil entity.
05:17:27 <MDude> He did invent lies, not neccessarily perfect using them.
05:17:44 <zzo38> int-e: That's just a made up puzzle situation anyways though, so it doesn't matter if other entity's strategy is stupid as long as it is formalized isn't it?
05:26:52 -!- ^v has quit (Read error: Connection reset by peer).
05:27:15 -!- ^v has joined.
05:45:34 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:51:29 -!- skj3gg has joined.
06:00:04 -!- skj3gg has quit (Quit: ZZZzzz…).
06:06:58 -!- FreeFull has joined.
06:07:33 -!- Guest11 has joined.
06:11:22 -!- Sprocklem has quit (Ping timeout: 240 seconds).
06:13:34 <b_jonas> oren: no, I think the trope is that the Devil never lies, but he uses confusing statements and twisting words
06:14:07 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
06:15:08 -!- Guest11 has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
06:27:47 <oren> b_jonas: I see
06:28:15 -!- KingOfKarlsruhe has quit (Ping timeout: 264 seconds).
06:30:11 -!- KingOfKarlsruhe has joined.
06:30:41 <HackEgo> [wiki] [[Ttml]] M http://esolangs.org/w/index.php?diff=41860&oldid=41403 * Orenwatson * (+1) uugh, i must have been drunk
06:43:43 -!- ProofTechnique has joined.
06:44:52 -!- FreeFull has quit (Ping timeout: 245 seconds).
06:56:56 -!- FreeFull has joined.
07:17:23 <zzo38> I tried to think of how to combine mahjong with Magic: the Gathering.
07:18:17 <zzo38> What I came up with is the mahjong hand is played during the oya's precombat main and dobon rule must be used
07:21:13 <zzo38> You can have 1 life point = 1000 mahjong point; fractional life points remain unaffected by Magic: the Gathering except if you have 100-900 you still don't lose.
07:23:34 <zzo38> What would you think is better way?
07:24:56 -!- shikhin has joined.
07:24:58 -!- MDude has changed nick to MDream.
07:26:56 -!- AndoDaan has joined.
07:28:43 -!- Lymia has quit (Ping timeout: 245 seconds).
07:31:08 -!- Lymia has joined.
07:44:52 -!- FreeFull has quit (Ping timeout: 245 seconds).
07:53:35 -!- Qfwfq has changed nick to Qfwfq|zzz.
08:01:50 -!- oerjan has quit (Quit: Nite).
08:37:04 -!- FreeFull has joined.
08:38:31 -!- hjulle has joined.
09:06:42 <HackEgo> [wiki] [[Talk:Wct]] N http://esolangs.org/w/index.php?oldid=41861 * Rdebath * (+479) /* The Greeks already did this. */ new section
09:08:33 -!- adu has quit (Quit: adu).
09:11:21 -!- Qfwfq|zzz has changed nick to Qfwfq.
09:15:07 -!- FreeFull has quit (Ping timeout: 250 seconds).
09:27:01 -!- FreeFull has joined.
09:34:15 -!- ^v has quit (Read error: Connection reset by peer).
09:34:41 -!- ^v has joined.
09:44:41 -!- FreeFull has quit (Ping timeout: 245 seconds).
09:57:16 -!- hjulle has quit (Ping timeout: 255 seconds).
10:02:13 -!- AnotherTest has joined.
10:13:39 -!- CADD has joined.
10:25:01 -!- chaosagent has quit (Ping timeout: 264 seconds).
10:31:46 -!- AndoDaan has quit (Ping timeout: 245 seconds).
10:33:33 -!- AndoDaan has joined.
10:39:03 -!- AndoDaan has quit (Ping timeout: 256 seconds).
10:43:13 -!- Froo has changed nick to Frooxius.
10:43:29 -!- Phantom_Hoover has joined.
10:44:22 -!- AndoDaan has joined.
10:47:48 -!- Frooxius has quit (Read error: Connection reset by peer).
10:47:52 -!- Froox has joined.
10:48:51 -!- AndoDaan has quit (Ping timeout: 250 seconds).
10:52:15 -!- AndoDaan has joined.
10:56:17 -!- Froox has changed nick to Frooxius.
11:03:14 <J_Arcane> I miss tail call optimization. :P
11:07:05 -!- FreeFull has joined.
11:13:39 <oren> J_Arcane: I do tail calls with Goto in C
11:14:50 <oren> But for some reason people frown on me setting all the parameters and 'goto start;'
11:17:52 <oren> You can sometimes convert a goto to a do{}while() loop
11:18:24 <oren> a lot of people forget all about the humble do{}while() loop
11:19:42 <J_Arcane> this is bizarre. My code doesn't terminate unless I use my function as a method instead of a function ...
11:20:22 <J_Arcane> nm, I see what I've done wrong. weird as hell that it works that way at all ...
11:24:06 -!- SopaXorzTaker has joined.
11:28:14 <J_Arcane> neat. a CMS in haskell. https://github.com/lambdacms/lambdacms-core
11:33:58 <Jafet> Basics of web design http://www2.jpl.nasa.gov/basics/index.php
11:34:47 <elliott> http://www2.jpl.nasa.gov/basics/splash3.gif is a fantastic image
11:36:00 <oren> It can. Oberth Manever
11:36:15 <Taneb> elliott, gravity helps me stay on the ground sometimes
11:36:19 <Jafet> Yes, it has a lot of potential.
11:37:36 <Jafet> J_Arcane: http://kangax.github.io/compat-table/es6/
11:38:40 <J_Arcane> Jafet: Yeah, really looking forward to ES6.
11:39:16 <J_Arcane> sadly, looks like fucking no one supports it yet, standard or no. . . :P
11:40:45 <Jafet> I like comparison tables that have single-valued rows
11:47:19 -!- Koen_ has joined.
12:00:50 <J_Arcane> also amusing that IE tech preview rates higher in compliance than anything except 6to5 transpilers ...
12:02:09 <Phantom_Hoover> effect, not manoeuvre, and i think they were probably referring to gravity assists
12:02:58 -!- Tritonio has joined.
12:21:05 -!- 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?").
12:35:21 -!- shikhin_ has joined.
12:36:41 -!- boily has joined.
12:38:26 -!- shikhin has quit (Ping timeout: 245 seconds).
12:40:07 -!- idris-bot has quit (Quit: Terminated).
12:41:34 -!- idris-bot has joined.
12:44:47 -!- Tritonio has quit (Remote host closed the connection).
13:11:07 -!- TieSoul has quit (Ping timeout: 245 seconds).
13:18:03 -!- TieSoul has joined.
13:36:04 * Melvar recently used a foreach-until loop. >ω>
13:37:51 -!- Patashu has quit (Ping timeout: 264 seconds).
13:41:55 -!- ^v has quit (Read error: Connection reset by peer).
13:42:19 -!- ^v has joined.
13:42:55 -!- idris-bot has quit (Quit: Terminated).
13:43:08 -!- Melvar has quit (Quit: rebooting).
13:45:56 -!- Melvar has joined.
13:49:06 -!- idris-bot has joined.
13:49:58 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
13:55:52 -!- Phantom_Hoover has joined.
13:55:53 -!- boily has quit (Quit: TRICKLING CHICKEN).
13:57:21 <FreeFull> Do you mean having a conditional break at the end of the loop?
14:00:12 <Melvar> FreeFull: Well, no, It was actually phrased foreach … until, because in the language in question you can use any loop opener with any loop closer. The effect is the same though.
14:02:19 <FreeFull> Melvar: So, does that language allow a while while loop?
14:03:55 <Melvar> No, while is neither an opener nor a closer, but actually a negative conditional break. It’s a forth variant btw.
14:16:03 <Melvar> Basically you use “begin … repeat” (by itself an infinite loop) and stick “<condition> while” in there. At the beginning it’s like a while loop, at the end it’s like a do-while loop.
14:16:52 -!- S1 has joined.
14:45:20 -!- S1 has quit (*.net *.split).
14:45:20 -!- olsner has quit (*.net *.split).
14:45:20 -!- nortti has quit (*.net *.split).
14:45:20 -!- nisstyre has quit (*.net *.split).
14:45:20 -!- coppro has quit (*.net *.split).
14:45:20 -!- Gregor has quit (*.net *.split).
14:45:29 -!- nortti has joined.
14:45:31 -!- Gregor has joined.
14:45:46 -!- coppro has joined.
14:46:57 -!- S1 has joined.
14:47:30 -!- nisstyre has joined.
14:48:05 -!- Koen_ has joined.
14:50:27 -!- oerjan has joined.
14:54:11 -!- olsner has joined.
15:04:47 -!- shikhin_ has changed nick to shikhin.
15:14:37 <tswett> That reminds me of how Python has while-else and try-else.
15:16:15 -!- S1 has quit (Quit: S1).
15:25:41 <Melvar> elliott: MUF, a forthish variant, a scripting language used in some MU*s, but my only resource on it (the guy who asked for help) says every place that uses it has its own incompatible set of builtins and such.
15:37:03 -!- nys has joined.
15:41:50 -!- rodgort has quit (Quit: Leaving).
15:44:14 -!- GeekDude has joined.
15:45:46 -!- rodgort has joined.
15:50:48 -!- rodgort has quit (Ping timeout: 245 seconds).
16:00:52 -!- SopaXorzTaker has quit (Ping timeout: 255 seconds).
16:05:39 -!- rodgort has joined.
16:14:15 -!- SopaXorzTaker has joined.
16:24:52 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
16:26:26 -!- MoALTz has quit (Quit: Leaving).
16:56:35 -!- oerjan has quit (Quit: Latër).
16:56:35 -!- idris-bot has quit (Quit: Terminated).
16:56:51 -!- idris-bot has joined.
17:08:04 -!- not^v has joined.
17:11:34 <mroman> we should do a #howesolangerslook
17:11:45 <mroman> as an analogy to #howgamerslook
17:14:13 -!- not^v has quit (Ping timeout: 255 seconds).
17:40:01 -!- arjanb has quit (Ping timeout: 246 seconds).
17:50:55 -!- ^v has quit (Read error: Connection reset by peer).
17:51:19 -!- ^v has joined.
17:51:30 <Taneb> Is there a name for the class of languages which are turing complete when their output is pumped back into the program?
17:51:35 <Taneb> eg. C preprocessor?
17:52:56 -!- not^v has joined.
17:54:06 -!- adu has joined.
17:58:42 <FreeFull> Taneb: So, turing complete when stuck in an outer loop?
18:02:51 <elliott> "pretty much anything that can branch"
18:03:11 <mroman> trees are turing complete
18:03:21 -!- skj3gg has joined.
18:05:01 <Koen_> mroman: yes, because they are stuck in the seasons loop
18:05:12 <MDream> Oh, neat http://fll.presidentbeef.com/
18:05:19 -!- MDream has changed nick to MDude.
18:05:44 -!- MoALTz has joined.
18:07:09 -!- adu_ has joined.
18:07:40 <MDude> It's a list of languages that aren't neccessarily esoteric, but aren't widespread either.
18:07:42 <mroman> These creepy lumber jacks are always trying to destroy my turing machines.
18:08:05 <mroman> If fungot were here he would think the same way
18:08:54 <MDude> That's the kind of language the reversible language I want to get to will be.
18:09:27 -!- adu has quit (Ping timeout: 244 seconds).
18:09:27 -!- adu_ has changed nick to adu.
18:09:49 <MDude> It'll only have branchine, but its output is to meant to get pumped back into it, with parts of it optionally replaced by input.
18:10:29 <mroman> http://kittenlang.org/
18:10:44 <mroman> it's statically typed and stack based
18:10:48 <mroman> that's always a plus point
18:12:50 <J_Arcane> heh. I should submit Heresy to that.
18:13:45 -!- SopaXorzTaker has quit (Ping timeout: 250 seconds).
18:14:21 <mroman> stuck in an outer loop is the same as having a recursive function
18:14:53 <mroman> ok not exactly the same
18:15:00 <mroman> but I think same enough :)
18:35:40 -!- shikhin_ has joined.
18:37:44 -!- adu has quit (Quit: adu).
18:38:54 -!- shikhin has quit (Ping timeout: 244 seconds).
18:43:18 <AndoDaan> Is there anything like an Object Oriented Assembly language in existance?
18:47:42 <quintopia> you might consider jvm bytecodes to be essentially that? a lot of the abstraction of objects is removed...
18:52:13 <AndoDaan> I kinda just threw to words together. But that's quite a good interpretation, I think.
18:54:51 <J_Arcane> AndoDaan: Yes. I can't remember what it's called though.
18:55:56 <J_Arcane> there's this for instance: http://en.wikipedia.org/wiki/High_Level_Assembly
18:57:41 <AndoDaan> "object-oriented assembly language programming." Didn't actually think it would exist.
18:58:07 -!- skj3gg has quit (Quit: ZZZzzz…).
18:59:42 <HackEgo> [wiki] [[Wct]] http://esolangs.org/w/index.php?diff=41862&oldid=41858 * Mihip * (+891) /* Examples */
18:59:59 -!- skj3gg has joined.
19:14:24 <mroman> http://codepad.org/NKldiU4a
19:17:35 -!- adu has joined.
19:17:46 <mroman> http://codepad.org/kV0MSf49
19:17:58 <mroman> Burlesque is becoming somewhat shellscripty I guess
19:20:00 <AndoDaan> Cool. When Anagol adopts it, we'll finally be able to do the "123" golf task.
19:20:26 <AndoDaan> hmm, does the time thingie show milliseconds?
19:20:41 <mroman> time /t doesn't show milliseconds
19:21:09 <mroman> time /t is windows though
19:23:37 -!- adu has quit (Quit: adu).
19:23:41 <mroman> it's not backwards compatible
19:23:56 <mroman> because I need some characters to signal "io expression" or "blsq expression"
19:31:23 <mroman> AndoDaan: there's also blsq on the web
19:31:32 <mroman> it's all bullshit of course
19:31:52 <HackEgo> [wiki] [[Wct]] http://esolangs.org/w/index.php?diff=41863&oldid=41862 * Mihip * (+495) /* Examples */
19:32:34 <mroman> because it's useless crap?
19:34:06 -!- adu has joined.
19:35:40 <AndoDaan> Hmm, my view of it is of course narrowed by the code golfing. BUt I've used Burlesque for other stuff occasionally.
19:36:34 <AndoDaan> Counting substring, getting all permutations of a list. Was a lot quicker to just fire uup the shell.
19:36:57 <mroman> That's what I created it for :)
19:37:13 <AndoDaan> Some people use J for serious reason, I thought. Why not your baby too?
19:37:24 <mroman> because my baby is fuckingly slow :)
19:42:29 <HackEgo> [wiki] [[Wct]] http://esolangs.org/w/index.php?diff=41864&oldid=41863 * Mihip * (-31)
19:46:00 -!- shikhin_ has changed nick to shikhin.
19:56:55 -!- skj3gg has quit (Quit: ZZZzzz…).
19:57:24 <FreeFull> J has a built-in verb for getting the nth permutation
19:58:23 <Taneb> There are now two York programming meetup groups both meeting on the last Thursday of the month at 7PM...
19:59:19 -!- chaosagent has joined.
20:09:50 <Taneb> quintopia, they have no overlap
20:09:56 <Taneb> One's for Haskell and one's for JavaScript
20:11:27 -!- skj3gg has joined.
20:12:57 <Koen_> yeah but then there's gonna be a third group about Scala and they'll all want to go
20:13:56 <Taneb> Koen_, JavaScript and Scala have very little in common at all
20:14:01 <Taneb> You may be getting mixed up with Java
20:14:30 <Taneb> Of course, if Elm takes off...
20:14:37 <J_Arcane> Although you can compile Scala to JabaScript.
20:14:41 -!- Lymia has quit (Quit: Hug~♪).
20:15:02 -!- Lymia has joined.
20:15:07 <Taneb> J_Arcane, you can also compile Haskell to JavaScript
20:15:26 <J_Arcane> Taneb: Yup. Really, you can compile damn near anything to JavaScript these days.
20:15:38 <J_Arcane> Thanks to asm.js and Emscripten anyway ...
20:15:53 <Taneb> You can even compile Node to JavaScript!
20:19:46 -!- Lilax has joined.
20:20:04 <mroman> they should've standardized a VM for Browsers rather than Javascript
20:20:31 <Lilax> Make like a book an livre
20:32:37 <zzo38> I think better would be they don't need a script
20:33:48 <mroman> how the fuck do you delete pictures on facebook?
20:34:20 <AndoDaan> Befriend Mark, and ask him nicely.
20:34:36 <AndoDaan> Though they're never really gone.
20:35:06 <zzo38> You can also use JavaScript programs with Synchronet as server-side scripts for HTTP or as door programs for telnet access
20:35:34 <zzo38> (Synchronet can also use DOS programs and native programs as door programs too)
20:36:34 <zzo38> Of course XULrunner stuff is also all in JavaScripts.
20:38:41 <zzo38> Do you like to combine mahjong and other games with Magic: the Gathering?
20:39:51 -!- skj3gg has quit (Quit: ZZZzzz…).
20:41:53 -!- Lilax has quit (Ping timeout: 252 seconds).
20:48:25 -!- not^v has quit (Ping timeout: 264 seconds).
20:51:30 <mroman> why not write the browser itself in javascript
20:51:46 <zzo38> I suppose you could, although it might be slow
20:52:30 <zzo38> You would still need to make the graphics libraries and so on accessible to JavaScripts though
20:53:34 <mroman> just make them part of ECMA Standard
20:53:38 <J_Arcane> mroman: I think Vivaldi is doing the UI in HTML/CSS/JS.
20:54:17 <zzo38> Mozilla has the HTML and CSS implementations in C++ but all of the menus and stuff of the browser are implemented in JavaScript.
20:54:18 <J_Arcane> And there's Breach, which is in fact written in pure JS. http://breach.cc/
20:54:50 <J_Arcane> (though I guess technically it's still on top of the Chromium engine by way of node.js)
21:16:05 <zzo38> All official world cards in Magic: the Gathering are global enchantments, but I also want to make up a world creature, a world land, and a world Aura
21:25:24 <zzo38> Kjugobe's Psychic Control {5UU} Enchantment - Aura :: Enchant spell :: Enchanted spell gains split second. :: You control enchanted spell's controller. :: Flash, Ripple 2
21:36:41 -!- adu has quit (Quit: adu).
21:37:19 <J_Arcane> I always forget about the ternary operator.
21:46:52 -!- ProofTechnique has joined.
21:51:25 -!- ProofTechnique has quit (Ping timeout: 255 seconds).
21:55:23 -!- ^v has quit (Ping timeout: 245 seconds).
21:56:39 -!- Patashu has joined.
22:06:35 -!- AndoDaan has quit (Ping timeout: 265 seconds).
22:21:29 <J_Arcane> (It says “I like to move the behavior of unsophisticated young engineers by making this job seem fun by buying 20 cent cans of soda, saving myself tens of thousands in compensation while simultaneously encouraging them to ruin their health.” And I like soda.)
22:21:30 <J_Arcane> http://www.kalzumeus.com/2011/10/28/dont-call-yourself-a-programmer/
22:27:15 -!- Qfwfq has left.
22:34:58 -!- 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?").
22:38:03 <J_Arcane> I wonder what I should think about the fact that so many of my Codewars solutions are uniques ...
22:46:25 -!- Vorpal_ has changed nick to Vorpal.
22:47:19 <Vorpal> Not often when you select a new package in aptitude and see that it will download over 360 MB... Got it down to 127 MB by removing some recommended dependencies I didn't really need. Still massive.
22:47:31 -!- Froox has joined.
22:49:29 -!- AnotherTest has quit (Remote host closed the connection).
22:50:07 -!- chaosagent_ has joined.
22:50:33 -!- KingOfKarlsruhe has quit (Ping timeout: 245 seconds).
22:50:33 -!- bb010g has quit (Ping timeout: 245 seconds).
22:50:33 -!- incomprehensibly has quit (Ping timeout: 245 seconds).
22:50:33 -!- chaosagent has quit (Ping timeout: 245 seconds).
22:51:16 -!- incomprehensibly has joined.
22:51:31 -!- Frooxius has quit (Ping timeout: 250 seconds).
22:52:44 -!- KingOfKarlsruhe has joined.
22:54:27 -!- oerjan has joined.
22:54:44 <lambdabot> ENVA 072220Z 33018KT 9999 VCSH SCT002 BKN015 M03/M04 Q1012 RMK WIND 670FT 33031G42KT
22:57:11 -!- bb010g has joined.
22:58:40 -!- oren has quit (Quit: Lost terminal).
22:59:22 -!- chaosagent_ has changed nick to chaosagent.
23:00:11 -!- ProofTechnique has joined.
23:00:43 -!- TieSoul has quit (Remote host closed the connection).
23:07:58 -!- AndoDaan has joined.
23:09:37 <zzo38> Do you think this is correct way to make IRC bot (dealing with buffering and whatever else is necessary)? http://sprunge.us/fSeb
23:23:00 -!- EgoBot has quit (Ping timeout: 252 seconds).
23:23:24 -!- EgoBot has joined.
23:23:37 -!- heroux has quit (Ping timeout: 245 seconds).
23:27:34 -!- Tritonio has joined.
23:30:51 -!- heroux has joined.
23:39:31 <Vorpal> Hm a popup saying std::bad_alloc when opening a program is a bit worrying, even though it appears to be working correctly otherwise...
23:40:15 <MDude> And I'm scrolled up.
23:41:43 <J_Arcane> Woo! 6to5 just got TCO: https://github.com/6to5/6to5/pull/714
23:52:18 -!- ^v has joined.
23:53:13 -!- Lymia has quit (Remote host closed the connection).
23:54:07 -!- Lymia has joined.
00:04:31 -!- Tritonio has quit (Remote host closed the connection).
00:04:38 <MDude> Also, I read what I was replying to wrong to begin with.
00:09:07 -!- adu has joined.
00:20:04 <zzo38> Do you know IRC bot writing stuff?
00:35:08 -!- shikhin_ has joined.
00:38:01 -!- shikhin has quit (Ping timeout: 252 seconds).
01:07:47 -!- zzo38 has quit (Remote host closed the connection).
01:17:27 -!- not^v has joined.
01:18:48 -!- hjulle has joined.
01:21:58 -!- not^v has quit (Client Quit).
01:34:01 -!- shikhin_ has quit (Ping timeout: 264 seconds).
01:38:58 -!- Guest11 has joined.
01:41:59 <Sgeo> General Biotics has moved their study end date to mid 2015
01:42:01 <Sgeo> "Our 200 person, placebo-controlled study is slated for completion in mid 2015. "
01:42:54 <Sgeo> http://www.generalbiotics.com/robots.txt
01:43:05 <Sgeo> They're explicitly and specifically blocking the Internet Archive
02:05:21 -!- hjulle has quit (Ping timeout: 265 seconds).
02:12:17 -!- adu has quit (Quit: adu).
02:13:53 <paul2520> it bothers me when sites do that
02:14:12 <paul2520> though sometimes I get it, if the site is really dynamic
02:15:02 -!- adu has joined.
02:15:07 <Sgeo> But it's been blocked since Dec 2014
02:15:07 <Sgeo> http://wayback.archive.org/web/20141217104405/http://www.generalbiotics.com/robots.txt
02:15:19 <Sgeo> I find it funny IA considers itself allowed to show that
02:18:37 -!- adu has quit (Client Quit).
02:20:48 -!- spiette has quit (Ping timeout: 245 seconds).
03:12:57 -!- AndoDaan has quit (Read error: Connection reset by peer).
03:13:02 -!- AndoDaan_ has joined.
03:24:51 -!- Guest11 has quit (Ping timeout: 252 seconds).
03:34:57 -!- Sprocklem has joined.
03:46:59 -!- Sprocklem has quit (Ping timeout: 264 seconds).
03:51:14 <Taneb> When did it get to be almost 4 AM?
03:55:30 <Taneb> I think it is a good time for me to get some sleep
03:57:03 -!- FreeFull has quit (Ping timeout: 245 seconds).
04:10:21 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
04:43:23 -!- zzo38 has joined.
05:02:35 -!- oren has joined.
05:03:29 <oren> coding standard proposal: when using the God Object Antipattern, name the object 'God'
05:06:27 -!- J_Arcane has quit (Read error: Connection reset by peer).
05:06:57 -!- J_Arcane has joined.
05:07:59 <zzo38> In such a case you usually shouldn't even need an object if you can avoid it (although sometimes you cannot avoid it)
05:08:11 <lambdabot> oerjan said 1d 5h 19m 28s ago: if the collatz counterexample can be one which grows indefinitely rather than looping, and if the win condition has to be detected in finite time, then i don't see how you can possibly distinguish that from a number that just takes a very long time to reach 1
05:18:41 -!- nys has quit (Quit: quit).
05:19:37 -!- chaosagent has quit (Ping timeout: 255 seconds).
05:29:02 -!- Patashu has quit (Remote host closed the connection).
05:29:22 -!- Patashu has joined.
05:30:37 <MDude> I just noticed somsone mispelled Javascript as Jabascript earlier a some point.
05:31:17 <MDude> Which made me think there should maybe be a Star Wars themed scripting language called Jabbascript.
05:31:58 <oerjan> MDude: hey stop reading my thoughts
05:32:43 <zzo38> You can try to make it up if you like to
05:33:24 <HackEgo> [wiki] [[Special:Log/newusers]] create * Youknowone * New user account
05:34:10 <MDude> I would want to learn Hutese first so I can make it in that.
05:34:38 <AndoDaan_> Another person fiding Esolangs via Anarchy Golf.
05:35:54 <zzo38> A lot of people seem to like to avoid "everything is a filter" kind of programming, but I don't avoid it and probably most of my programs are acting as filters.
05:36:27 <HackEgo> [wiki] [[Aheui]] http://esolangs.org/w/index.php?diff=41865&oldid=40352 * Youknowone * (-61) /* External resources */
05:40:16 <MDude> Oh neat, Huttese uses base 8.
05:40:54 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:41:29 -!- GeekTest has joined.
05:41:36 <zzo38> Why do a lot of people hate it?
05:42:30 -!- GeekTest has quit (Client Quit).
05:54:38 <HackEgo> [wiki] [[Xihcute]] http://esolangs.org/w/index.php?diff=41866&oldid=39945 * Ds84182 * (+210) Added a couple of new instructions, fixed the definition of an instruction. Changed some code to work with the fixed instruction definition.
05:56:31 -!- Patashu has quit (Ping timeout: 255 seconds).
05:58:51 -!- FreeFull has joined.
06:20:46 -!- oren has quit (Quit: Page closed).
06:24:06 -!- ^v has quit (Read error: Connection reset by peer).
06:54:50 -!- oerjan has quit (Quit: leaving).
06:56:17 -!- adu has joined.
08:08:02 -!- tromp_ has quit (Remote host closed the connection).
08:08:49 -!- FreeFull has quit (Ping timeout: 265 seconds).
08:12:48 -!- mbrcknl has quit (Read error: Connection reset by peer).
08:13:18 -!- supay has quit (Ping timeout: 245 seconds).
08:13:47 -!- mbrcknl has joined.
08:15:08 -!- AndoDaan_ has quit (Quit: Going, going, gone.).
08:17:09 -!- supay has joined.
08:19:18 -!- adu has quit (Quit: adu).
08:37:00 <zzo38> Are there other functions that you think SQLIRCBOT would require to include built-in?
08:42:01 <J_Arcane> Science! http://electronics.stackexchange.com/questions/152090/measuring-feline-capacitance
08:49:33 <mroman> How long does it take to become a pro soldat player again
09:01:39 -!- MDude has changed nick to MDream.
09:06:30 -!- Patashu has joined.
09:08:34 -!- tromp has joined.
09:13:10 -!- tromp has quit (Ping timeout: 255 seconds).
09:14:48 -!- SopaXorzTaker has joined.
09:48:23 -!- Tritonio has joined.
09:51:41 -!- AnotherTest has joined.
10:08:25 -!- TieSoul has joined.
10:09:38 -!- FreeFull has joined.
10:13:13 <mroman> http://codepad.org/Y3sUFPbG
10:13:54 <mroman> the io builtin prepares an IO command to execute
10:22:59 <J_Arcane> this is a Windows computer in a device the size of 4 thumb drives. http://www.eurogamer.net/articles/digitalfoundry-2015-hannspree-micro-pc-review
10:23:33 <Jafet> Uh, what kind of machine has `time /t`
10:25:55 -!- AndoDaan has joined.
10:26:06 <mroman> Jafet: ah windows machine
10:28:14 <Jafet> The Windows shell doesn't have backquotes...
10:28:44 -!- Neolink5 has joined.
10:29:30 <mroman> a dialect of Burlesque with IO
10:34:36 <mroman> http://codepad.org/PK5mSHfG <- see
10:35:35 -!- Tritonio has quit (Remote host closed the connection).
10:37:35 <mroman> ok maybe not that cool but still
11:08:46 -!- tromp has joined.
11:10:48 -!- Phantom_Hoover has joined.
11:13:05 -!- tromp has quit (Ping timeout: 252 seconds).
11:18:08 -!- AnotherTest has quit (Read error: Connection reset by peer).
11:18:47 -!- AnotherTest has joined.
11:25:27 <mroman> but let's try something new
11:25:39 <mroman> I'm gonna design an actual useful good-looking language for once
11:35:15 <int-e> b_jonas: it's be perfectly esoteric ;)
11:36:18 <int-e> An esoteric programming language that is unfit for its primary purpose, namely being an esoteric programming language.
11:42:47 -!- Patashu has quit (Ping timeout: 264 seconds).
11:46:16 -!- AnotherTest has quit (Remote host closed the connection).
11:46:55 <mroman> parsec runs out of memory o_O
11:50:22 -!- Neolink5 has quit (Ping timeout: 240 seconds).
11:50:51 <mroman> it runs out of mem for parsing 5+5
11:51:25 <mroman> and even for parsing just 5
11:51:26 <int-e> did you write a left-recursive grammar?
11:52:21 <Jafet> It's ok, your mistake is non-terminal.
11:53:07 <mroman> expression = expression bin_op expression
11:54:07 <mroman> I see parsec can't handle that
11:54:51 <b_jonas> don't use recursive descent parsers
11:55:12 <b_jonas> not only because they run out of memory, but because they are hard to debug when you make mistakes, they don't tell you about ambiguities
11:55:20 <b_jonas> use a proper LR parser generator
11:56:04 <mroman> expression bin_op expression is always recursive
11:56:06 <int-e> or do your own factorization, expression = term bin_op expression | term; term = literal | variable | "(" expression ")
11:56:31 <int-e> it gets more tedious with precedences
11:56:52 <mroman> You can fix it by doing expression = '(' expression bin_op expression ')'
11:57:01 <Jafet> @hoogle buildExpressionParser
11:57:03 <lambdabot> Text.ParserCombinators.Parsec.Expr buildExpressionParser :: OperatorTable tok st a -> GenParser tok st a -> GenParser tok st a
11:57:03 <lambdabot> Text.Parsec.Expr buildExpressionParser :: Stream s m t => OperatorTable s u m a -> ParsecT s u m a -> ParsecT s u m a
11:57:19 <int-e> Jafet: have you used that thing?
11:57:54 <mroman> i can make a non-terminal <> terminal distinction
11:58:41 <Jafet> I've never needed to parse expressions
12:09:52 -!- tromp has joined.
12:10:06 -!- nortti has changed nick to bender|_|.
12:10:24 -!- bender|_| has changed nick to nortti.
12:14:27 -!- tromp has quit (Ping timeout: 245 seconds).
12:22:55 -!- sebbu has quit (Quit: reboot).
12:24:13 -!- hjulle has joined.
12:29:23 -!- Koen__ has joined.
12:33:55 -!- ElizaMarmot has joined.
12:35:02 -!- ElizaMarmot has left ("Leaving").
12:45:05 -!- sebbu has joined.
12:45:05 -!- sebbu has quit (Changing host).
12:45:05 -!- sebbu has joined.
12:47:00 <mroman> *Main> runString "iMain(){return(5+5)}"
12:52:10 -!- AndoDaan has quit (Ping timeout: 244 seconds).
12:57:06 <Jafet> It's all lazy IO, I assume
13:03:39 -!- AndoDaan has joined.
13:04:06 <mroman> http://codepad.org/OnXQ9sME
13:04:15 <mroman> type is encoded in the identifier
13:17:27 <int-e> mroman: There's some precedent for that. (god is real, unless declared as integer...)
13:24:14 <int-e> b_jonas: "<mroman> I'm gonna design an actual useful good-looking language for once" <-- this one, I suppose
13:37:38 -!- boily has joined.
13:54:33 <mroman> the above wouldn't typecheck though
13:54:56 <mroman> but typechecking not implemented yet
13:59:00 -!- tromp has joined.
14:03:28 -!- tromp has quit (Ping timeout: 244 seconds).
14:33:00 -!- GeekDude has joined.
15:08:05 -!- tromp has joined.
15:10:58 -!- tromp has quit (Read error: Connection reset by peer).
15:11:24 <tswett> So the thing about programming languages is that a programming language usually has some sort of model of computation associated with it.
15:11:54 -!- tromp has joined.
15:12:03 <Taneb> So the challenge is abstracting over the computation model?
15:12:22 <tswett> C and C++ have very minimalistic models. Data consists of bytes. Code consists of instructions. That's it.
15:12:51 <tswett> Well, my point is that creating a "perfect programming language" would have to entail creating a perfect computation model, too.
15:13:26 <tswett> Languages like Haskell and Python have "maximalistic" models, which are much easier to use and much harder to implement.
15:13:30 <Jafet> Yes, so minimalistic that it only takes dozens of pages to define them
15:14:37 <tswett> And the thing about linking two pieces of software, as everyone knows, is that it's easy as long as both pieces of software are written in the same language or one of them is written in C.
15:14:39 <Jafet> Let's be fair and only use the pages that talk about the basic memory semantics
15:15:42 <coppro> Jafet: what about the concurrency model in C++? that's a vital part of the underlying computational
15:19:20 <Jafet> Hmm, the memory model had better be defined in less than a hundred pages or I will seriously consider switching to erlang
15:19:21 <tswett> Can you write a Python program that uses a Haskell library? Sure, as long as the Haskell library has a C-shaped interface, or you're calling it via IPC, or something.
15:20:21 <mroman> the real question is why you would ever attempt to do that
15:20:28 <Jafet> Linking with C is pretty hard unless you happen to already have a bunch of C linkers
15:22:40 -!- skj3gg has joined.
15:23:20 <tswett> I guess I should work on coming up with that perfect computation model.
15:23:40 <Jafet> You can invent a new calling convention and force everyone around you to use it, there is nothing special about C in this sense.
15:25:35 -!- Froox has quit (Ping timeout: 250 seconds).
15:26:08 -!- Froox has joined.
15:32:53 -!- Lymia has quit (Ping timeout: 245 seconds).
15:34:32 <Jafet> Uh, the latest 14882 public draft is from 2013
15:53:55 <mroman> but don't forget to patent your calling convention
16:00:49 -!- SopaXorzTaker has quit (Ping timeout: 256 seconds).
16:02:18 -!- Lymia has joined.
16:06:08 -!- SopaXorzTaker has joined.
16:06:15 * J_Arcane is suddenly reconsidering his dismissal of TypeScript ...
16:15:03 <boily> J_Arcanello. what do you not like about undefined?
16:26:25 <J_Arcane> boily: The tendency for JavaScript to return it instead of an error. ditto 'NaN'.
16:28:39 <Jafet> It just means that the result was undefined.
16:29:11 * boily want to completely annihilate NaN into some parallel Universe.
16:29:21 -!- ais523 has joined.
16:29:25 <boily> J_Arcane: I understand the sentiment.
16:29:36 <J_Arcane> Jafet: yes, but it returns that rather than an error in cases where even dynamic languages would just return an error.
16:31:27 -!- 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?").
16:31:44 <J_Arcane> Oh lord, and now I've hit a floating point bug. Yup, this exercise can fuck right the hell off ...
16:33:30 <Jafet> Huh, javascript has exceptions? Why don't they just return null.
16:34:55 <Jafet> boily: a perfectly denormal sentiment.
16:38:26 <b_jonas> Jafet: yes, javascript has exception
16:47:59 -!- nys has joined.
17:02:51 <J_Arcane> JavaScript in generally does do some insane implicit behaviors; it seems as if it was designed with 'keep calm and carry on' as a language policy.
17:03:22 <J_Arcane> For example, guess what the following returns: 5 + function (x) { return; }
17:03:55 <tswett> Hm, lemme try to guess.
17:05:15 <tswett> A pet peeve of mine is when a language has a value called "undefined".
17:06:01 <tswett> With one or two exceptions.
17:06:33 <tswett> "Nil" and "null" are fine. Decent ways of saying "no ordinary value".
17:08:09 <tswett> But "undefined" is an adjective meaning "not having a definition".
17:08:30 <J_Arcane> tswett: I actually kinda like the Maybe type for that. Or just Scheme/Racket's use of the empty list for nil. Because it has a practical use.
17:09:35 <tswett> I guess what I don't like is when there's a difference between a variable having a value called "undefined" and the variable *actually not being defined*.
17:09:38 <J_Arcane> But yeah, JS' case it's more the interpreter going 'well, I don't know what to do here' (which happens a lot) and just returning 'undefined' and carrying on. That to me is the behavior of a crazy person.
17:10:07 <tswett> If those are the *same* thing, that's fine. If they're different things, then the guys who created the programming language really need to think about what the word "defined" means.
17:16:04 -!- boily has quit (Quit: EXTREME CHICKEN).
17:16:48 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
17:17:35 -!- SopaXorzTaker has joined.
17:31:30 -!- AnotherTest has joined.
17:31:37 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
17:31:37 -!- TieSoul has quit (Quit: http://quassel-irc.org - Chat comfortably. Anywhere.).
17:32:02 -!- TieSoul has joined.
17:36:40 -!- MDream has changed nick to MDude.
17:42:19 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:12:24 -!- rxs1 has joined.
18:17:16 -!- rxs1 has left.
18:20:36 -!- AndoDaan has quit (Ping timeout: 264 seconds).
18:37:24 -!- kallisti has joined.
18:45:56 <MDude> I would think undefined would make sense as a vaue. If it can be the result of an operation on paper, a comptuer should be able to represent it.
18:46:35 <kallisti> what kind of "undefined" are we talking about?
18:48:22 <tswett> MDude: if you ask me, it can't be the result of an operation on paper.
18:48:55 <tswett> 1/0 isn't an operation whose result is a value called "undefined". It's a sequence of symbols that has the property of being undefined.
18:49:02 <kallisti> for instance, a certain kind of undefined can be the result of a computation which never halts.
18:49:36 <kallisti> "undefined behavior" where the specification or implementation of something doesn't handle a certain case.
18:52:25 <elliott> tswett: that view kinda clashes with denotational semantics
18:52:32 <kallisti> but if you're talking about, say, the value of "undefined" in javascript, you could say that this is "defined" in some sense, since it is a definition representing things that are deterministically without a specific meaning.
18:52:35 <elliott> we say that [[ 1 / 0 ]] = _|_
18:54:13 <tswett> elliott: *nod* Yeah, you're right.
18:56:00 -!- Koen__ has joined.
18:56:24 <elliott> kallisti: what's up. you can't just reappear every N months without telling everyone your life story since
18:57:59 <kallisti> are denotations technically computations though?
18:58:20 <tswett> kallisti: so, how about that operating system we're collaborating on making?
19:02:24 <tswett> Let's use the Linux kernel but write everything else from scratch.
19:03:13 <kallisti> I'm not very interested in starting a project with that kind of scope until I get other things sorted out.
19:03:22 <FireFly> tswett: undefined in JS is more messy than you might think.. there's a well-defined value called "undefined", a global variable "undefined" holding said value, and also the typeof operator sometimes returns the string 'undefined'
19:03:26 <kallisti> like "not being homeless or starving to death"
19:03:46 <kallisti> I don't think tswett ever mentioned JS. That was my contribution. Coincidentally, I've been writing a lot of JS code.
19:04:11 <FireFly> specifically, typeof foo results in the string 'undefined' both if foo is defined and holds the value undefined, and if it is /not defined/
19:04:31 <FireFly> oh, I just read parts of the backlog, might've missed the context
19:05:52 <elliott> how old are you now even kallisti
19:05:53 <FireFly> So in other words, in JS it both means "not defined" and "holds the `undefined` value" (and is the name of a global variable)
19:06:58 <kallisti> yikes? now I feel I should be concerned about something.
19:08:47 <kallisti> it's not too crazy. It just means that the value undefined doesn't actually mean 'an undefined variable'. It just means that undefined variables result in an undefined value, but not the other way around.
19:09:49 <kallisti> I believe you'd use hasOwnProperty to actually determine if a specific name has never been assigned to.
19:10:31 <kallisti> elliott: I think when you hit 20 or so you start feeling old and then as you get closer to 25 you start feeling young again briefly, and then probably old again after that point, but I haven't gotten there yet.
19:10:47 <kallisti> that's just my experience anyway
19:12:01 <kallisti> I shall now confirmation bias this piece of information. Thank you for your input.
19:13:01 <tswett> FireFly: so there's actually a difference between an unassigned variable and a variable containing "undefined"?
19:13:46 <FireFly> Trying to access the former is an error
19:14:48 <kallisti> only if you have 'use strict' enabled
19:15:34 <FireFly> No, I'm pretty sure that's the case either way. As in, if you open a repl and type foo you get a ReferenceError
19:15:54 -!- ProofTechnique has joined.
19:17:17 <FireFly> What strict mode changes wrt globals is that you need to explicitly declare variables before assigning to them
19:18:11 <kallisti> ah okay. I guess I never use strict mode then.
19:19:35 <kallisti> I wish I had started writing my current node.js project in livescript, actually.
19:20:09 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
19:20:47 <kallisti> I don't really feel like rewriting everything in livescript, and only writing SOME of it in livescript seems a little awkward.
19:20:58 <FireFly> What kind of project is it?
19:22:57 <kallisti> millions of nested callbacks becomes second nature at some point, but if I were using livescript I could use "backcalls" to flatten everything.
19:23:20 <kallisti> looks nearly identical to do notation.
19:24:20 <HackEgo> [wiki] [[Xihcute]] http://esolangs.org/w/index.php?diff=41867&oldid=41866 * Ds84182 * (+0) Fix 99 bottles of beer with the new instruction fixes.
19:24:48 <kallisti> oh, huh, this is an IRC channel for esoteric programming languages isn't it?
19:25:52 <elliott> kallisti: remember the good all days when we argued all the time
19:29:23 <kallisti> any interesting new esolangs since I was last here?
19:29:32 <kallisti> or languages in general that I may be unaware of?
19:34:47 -!- Patashu has joined.
19:35:02 <elliott> you were last here semi-recently
19:36:12 <kallisti> yes but I haven't really been following language design closely for several years.
19:36:38 <elliott> yeah but you said since you were last here :p
19:36:39 <kallisti> so, maybe not exactly when I was last present on the channel
19:36:49 <elliott> we implemented deadfish in even more languages!
19:37:25 <elliott> https://esolangs.org/wiki/Deadfish 71 now
19:37:54 <kallisti> deadfish in deadfish. that's all I need.
19:38:43 <kallisti> hm, the perl implementation isn't a one-liner though
19:40:33 <kallisti> "The language defined by the Revised Revised Revised Revised Revised Report on the Algorithmic Language Scheme"
19:40:52 <b_jonas> kallisti: that's old. they ahve R7RS now I think
19:41:07 <elliott> the interpreter is broken but whatever
19:41:14 <elliott> I mainly did it for the ridiculously full language name
19:41:20 <elliott> kallisti: haha it's just R5RS Scheme
19:41:26 <elliott> the 5 in R5RS is for Revised^5
19:41:39 <elliott> originally it was like, the Revised Report on the Algorithmic Language Scheme
19:41:43 <elliott> then the Revised Revised Report
19:41:52 <elliott> then they started using power superscripts pretty quickly
19:41:56 <b_jonas> they call it "Revised^7 Report on the Algorithmic Language Scheem"
19:43:24 <kallisti> it's unfortunate that the number of revisions will probably not exceed the threshold beyond which up-arrow notation is reasonable.
19:43:39 <kallisti> or if it does, I won't be alive for it.
19:46:38 -!- adu has joined.
19:46:49 <kallisti> why does Protocol Buffers have such an awful name.
19:46:51 -!- skj3gg has quit (Quit: ZZZzzz…).
19:52:13 -!- AnotherTest has quit (Ping timeout: 244 seconds).
19:55:11 -!- copumpkin has quit.
19:55:26 -!- skj3gg has joined.
20:03:42 -!- copumpkin has joined.
20:08:38 -!- ProofTechnique has joined.
20:13:25 <HackEgo> [wiki] [[EsoAPI]] M http://esolangs.org/w/index.php?diff=41868&oldid=39468 * Smjg * (+26) wayback
20:13:34 -!- Patashu has quit (Ping timeout: 245 seconds).
20:14:52 <elliott> kallisti: are you still in uh. the same physicall ocation you were. god I forget where that even was but it seemed like half the channel lived there
20:16:35 -!- Patashu has joined.
20:16:54 <kallisti> I live in Georgia (the US state not the nation)
20:21:40 <HackEgo> [wiki] [[PESOIX]] http://esolangs.org/w/index.php?diff=41869&oldid=30600 * Smjg * (-13) found something on wayback
20:21:48 -!- AndoDaan has joined.
20:44:43 -!- Patashu_ has joined.
20:44:43 -!- Patashu has quit (Disconnected by services).
20:51:47 -!- boily has joined.
20:58:26 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
21:26:56 <Jafet> Hmm, Orbiter is perfectly happy to let you turn the ISS into a meteorite
21:37:40 <zzo38> Why does the Deadfish article render the last few sections incorrectly for a few seconds?
21:39:03 <zzo38> Which Deadfish implementation is longest? Is it the one for Famicom?
21:41:14 -!- HMC_A has joined.
21:41:17 -!- skj3gg has quit (Quit: ZZZzzz…).
21:42:46 -!- copumpkin has joined.
21:44:07 -!- copumpkin has quit (Remote host closed the connection).
21:50:38 <zzo38> Or is the Chicken one longer?
21:54:50 <zzo38> The shortest one seems to be AWK, followed by Staq, and then dc.
21:57:41 -!- vifino has quit (Ping timeout: 246 seconds).
21:58:37 -!- TieSoul has changed nick to TieSleep.
22:07:31 -!- adu has quit (Quit: adu).
22:14:12 -!- skj3gg has joined.
22:16:01 -!- vifino has joined.
22:26:53 -!- Tritonio has joined.
22:34:41 -!- ais523 has quit.
22:43:52 -!- 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?").
22:51:47 <zzo38> Why is COBOL program using the C library for I/O?
22:58:20 -!- Tritonio has quit (Ping timeout: 252 seconds).
23:00:42 -!- AndoDaan has quit (Read error: Connection reset by peer).
23:00:57 -!- AndoDaan has joined.
23:03:26 -!- skj3gg has quit (Quit: ZZZzzz…).
23:05:23 -!- oerjan has joined.
23:06:17 -!- skj3gg has joined.
23:17:00 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=41870&oldid=41789 * AndoDaan * (+388) Added Kipple version.
23:22:38 <naturalog> here's a q i've been wondering about today: assume you have an array A of bools. at t=0, A[0]=true and all the rest are false. assume the working memory can contain only one bool (bit), and you have a pointer to A which you can either inc or dec by 1, and it goes back cyclically when out of range. which computations can't this machine do?
23:23:25 <naturalog> its like tape turing machine with redundant state machines
23:23:43 -!- Sprocklem has joined.
23:23:45 <elliott> what operations can you do
23:24:05 <naturalog> ah i forgot: you can either read, or set to 0, 1, or to the mem bit
23:25:19 <naturalog> and it begins with its head marked
23:25:30 <elliott> tbh it sounds like you can't do much at all with this
23:25:37 <elliott> it's a very limited state machine
23:25:44 <elliott> it's barely even computation
23:26:07 <elliott> I don't know exactly what class it'd be in, though
23:28:19 <naturalog> sorry, complete squares. 1,4,9,16,25..
23:29:03 -!- adu has joined.
23:29:32 <elliott> okay maybe it's more interesting than I thought
23:31:50 <HackEgo> [U+0020 SPACE] [U+0488 COMBINING CYRILLIC HUNDRED THOUSANDS SIGN]
23:41:41 <boily> there shouldn't have been a space having had left there...
23:44:00 <boily> sorry, I'm more or less coherent today. I was complaining that a space shouldn't have been left there.
23:44:04 <HackEgo> [U+0488 COMBINING CYRILLIC HUNDRED THOUSANDS SIGN]
23:44:32 <HackEgo> [U+00F8 LATIN SMALL LETTER O WITH STROKE] [U+0020 SPACE] [U+0488 COMBINING CYRILLIC HUNDRED THOUSANDS SIGN] [U+0072 LATIN SMALL LETTER R]
23:46:02 <boily> I know. and please don't shout too much. I'm finally enjoying a lack of headache.
23:48:50 <boily> sorry, was it a sample of your suave OKAY voice?
23:50:11 <oerjan> i mean i am not enjoying a lack of headache.
23:51:33 <boily> sickness? hangover? alien invasion? meteorite?
23:52:32 <oerjan> most likely no. 3, i think.
23:53:38 <oerjan> although come to think of it, i am coughing a bit as well
23:53:51 -!- adu has quit (Ping timeout: 246 seconds).
23:56:19 -!- adu has joined.
23:56:44 -!- skj3gg has quit (Quit: ZZZzzz…).
00:04:30 <naturalog> q2: we have an array of bools with 1 bit memory. we can do all bit operations, 1- and 2-ary, with the current tape's head and the mem bit. now this machine can do 2-cnf and 2-dnf, right?
00:04:42 <naturalog> how would you characterize *everything* it can do?
00:05:02 <naturalog> boily: i hope bold keeps your head fine
00:05:48 <naturalog> this machine obviously cannot do everything. can it do 3cnf?
00:06:34 <boily> naturalog: bold is correct.
00:13:17 -!- adu has quit (Quit: adu).
00:22:15 -!- skj3gg has joined.
00:22:43 -!- Lilax has joined.
00:24:31 <Lilax> landspeed of a migrating fungot is 78mp/s
00:26:52 * boily mapoles Lilax “no stabbing in the channel!”
00:27:19 * Lilax gasps and dies to death
00:27:43 <boily> if you die, please don't leave hard to wash stains hth
00:29:07 * Lilax sprays blood and calcium oxide on the carpets
00:32:44 <Lilax> channel created Sun Nov 26 2006 1:42:50
00:32:53 <elliott> this place was actually created in 202
00:33:25 <Lilax> just seeing why the channel time is off for the client
00:35:15 * pikhq beats Windows with a large stick
00:36:47 <Lilax> what does +C mean?
00:39:46 <oerjan> naturalog: i think your definition is very vague on this machine's flow control hth
00:40:03 <elliott> it strips ctcps or something I think
00:40:09 <elliott> oerjan: it has none, afaict
00:40:28 <naturalog> it has tape over the array, and head
00:40:39 <naturalog> can more left or right, but cyclically
00:41:06 <Lilax> Reaaaaaaaaallllllllllllyyyyyyyyyyyy small
00:44:01 <oerjan> naturalog: i don't think you are understanding the question.
00:44:16 <oerjan> i'm not asking what it can do in a single instruction
00:44:32 <oerjan> i'm asking how it decides what instruction to do next
00:45:06 <elliott> oerjan: you just get a list of fixed instructions to execute
00:45:23 <oerjan> hm i guess with a finite array...
00:45:26 <naturalog> like the machine in q1 can create all complete squares indices to be true
00:45:43 <Lilax> lets get together and make a humanoid AI named Glad0s
00:45:52 <oerjan> sounds a bit like those circuit complexity models
00:46:36 <naturalog> i dont know what you speak about. im pretty new on this stuff
00:46:57 <oerjan> hm i wonder if the barrington theorem applies
00:47:18 <oerjan> in which case the answer is: anything, as long as you are allowed a few spare bits
00:47:51 <oerjan> in fact i think that's the case.
00:48:01 <boily> Lilax: not sure it's a good idea.
00:49:08 <oerjan> i guess that's not quite the same.
00:49:22 <oerjan> although i think it's pretty unknown exactly how much that allows.
00:49:41 <oerjan> (e.g. does it contain all of NP)
00:50:21 <oerjan> the thing here is that the length of the program could be _much_ larger than the array itself
00:50:35 <naturalog> how does this depend on p=np? i.e. assume p=np then what? and assume p neq np then what?
00:51:17 <oerjan> naturalog: actually if we assume an extremely large program, i don't think it depends. i think you can calculate any boolean function on the array minus those few spare bits.
00:51:53 -!- adu has joined.
00:51:57 <naturalog> well for some problems you'll run out of mem even if you use the array as mem
00:51:57 <oerjan> (you need enough to encode 5 different states of the machine)
00:53:31 <oerjan> naturalog: no, you actually don't. the barrington theorem works by visiting all cells a _lot_ of times, but it has to remember nothing other than its place in the program and which of the 5 states it's in
00:54:22 <naturalog> ok so if its turing complete, then we can built a turing equivalent machine by simple matrix multiplications
00:54:44 <oerjan> the word "turing complete" does not apply to anything with a finite array as input.
00:54:48 <naturalog> i.e. vector is the state, we mul it by a matrix on each step, very simple one
00:55:27 <naturalog> yes ofc turing completeness i.e. equivalent to some finite turing machine of order of magnitude of this machines
00:55:36 <Lilax> you kiddos are so smart
00:56:08 <oerjan> a given program only has time to visit finitely many cells, so if you want to calculate anything for arbitrary large arrays, you need to have the program dependent on the size of the array
00:56:20 -!- Patashu has joined.
00:56:48 <oerjan> and then the actual turing-completeness question gets passed on to whatever you use to prepare the program
00:57:21 -!- Patashu_ has quit (Ping timeout: 252 seconds).
00:57:34 <naturalog> ok ic i'll try to understand barrington theorem welel
00:57:38 <oerjan> (this is exactly how circuit complexity tends to work, except if you are careful with balancing the powers)
00:58:01 -!- AndoDaan_ has joined.
00:59:01 -!- AndoDaan has quit (Ping timeout: 250 seconds).
00:59:48 -!- AndoDaan_ has changed nick to AndoDaan.
01:02:42 <boily> elliott: heh. I didn't know that mimics in 0.15 changed character when you hit them.
01:02:51 <oerjan> btw the NC(1) restriction is if the program has polynomial size in the array size, i think
01:02:51 <boily> oerjan: it's Quake hth.
01:03:13 <oerjan> oh and P = NP need not apply, because it's not even known if NC(1) contains P
01:03:46 <naturalog> think we have a key-value hashtable storage. our machine can query for key and retrieve a value from the storage. it cannot query by value. and it can store in memory 1 key, 1 value, 1 auxiliary var. all same length
01:04:03 <oerjan> but if the program has unlimited size then things get simpler.
01:05:03 <oerjan> sounds like a pointer machine
01:05:05 <naturalog> it begins with a single key in the memory
01:06:54 <naturalog> i thought about it while wondering what computation can a dht network do with dht only
01:07:06 <naturalog> without syncronization ofc, otherwise its noninteresting
01:09:29 <naturalog> ofc they can be sync with e.g. blockchain algo, but its not purely mathematicaly true. crypto is practical science at this case
01:10:12 <naturalog> with blockchain its kinda nondeterministic machine
01:12:49 <naturalog> btw on #zennet we sometimes have discussions about such problems, sometimes we like going deep on p=np and such
01:16:07 * oerjan thinks he may actually be sick
01:16:45 <lambdabot> Local time for oerjan is Mon Feb 9 02:16:44 2015
01:17:37 <boily> oerjan: go rest! you're being unreasonable!
01:17:51 <boily> what's your address, so I can send you a can of chicken soup?
01:18:13 <oerjan> i think you are somehow assuming i actually woke _up_ at a reasonable time tdnh
01:18:49 <oerjan> i might have to go rest anyway, though.
01:18:58 -!- AndoDaan_ has joined.
01:19:08 <oerjan> right now, however, i am eating.
01:20:36 -!- AndoDaan has quit (Ping timeout: 264 seconds).
01:21:06 <Lilax> oerjan is in the future
01:21:12 <Lilax> its the 8th for me
01:21:21 <Sgeo> How do I tell between a broken LCD cable and just it not being seated properly, if I only want to open computer once to fix it
01:22:57 <Lilax> actually let me see something :00
01:23:48 <lambdabot> <hint>:1:1: parse error on input ‘:’
01:23:51 -!- _AndoDaan_ has joined.
01:24:01 <lambdabot> Local time for lifthrasiir is Mon Feb 9 10:23:58 2015
01:26:06 -!- AndoDaan_ has quit (Ping timeout: 252 seconds).
01:27:29 <lifthrasiir> it won't work if your client doesn't support CTCP TIME
01:28:26 <boily> I'm guessing the Lilaxtime is either 5:28pm or 8:28pm.
01:31:16 <boily> your watch/clock/radio is running fast.
01:31:35 <Lilax> Uses sattalite time
01:31:43 <Lilax> can't spell sattalite
01:31:47 <oerjan> it was definitely :28 when i saw boily's message
01:32:23 <oerjan> in that case your clock is off by 2 minutes or so
01:35:40 <oerjan> if it's window's then there's a menu choice to ask it to contact a time server, if it's for some reason not doing that already
01:36:32 <Lilax> http://okuria.co.vu/post/110494876443/delusionalkieren-happy-valentines-day
01:36:54 <Lilax> since I'm poor and unreliable
01:37:00 <oerjan> you'd think a phone would know what time it is
01:37:39 * Lilax uses the brick to irc
01:38:36 <zzo38> Once you receive a telephone call, if you have call display then a phone should know what time it is, at least, even if it doesn't ordinarily know.
01:38:45 -!- bb010g has quit (Ping timeout: 250 seconds).
01:38:45 -!- ocharles_ has quit (Ping timeout: 250 seconds).
01:40:03 -!- supay has quit (Ping timeout: 250 seconds).
01:40:07 <Lilax> I wouldn't even bother
01:43:21 -!- skj3gg has quit (Quit: ZZZzzz…).
01:47:20 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:51:05 -!- supay has joined.
01:51:19 -!- ocharles_ has joined.
01:51:28 -!- bb010g has joined.
02:00:36 <Sgeo> If tilting my monitor changes how broken or not the display is, is it likely a broken LCD cable, loose LCD cable, or something else?
02:03:47 <kallisti> Sgeo: are you getting artifacts?
02:04:05 <Sgeo> I'm getting weird bands of color, usually blue
02:04:14 <Sgeo> That seem to appear when a specific color is shown on my monitor
02:04:50 <Sgeo> I use click2play for plugins, for example, and often the grey of that will be a flickering blue
02:05:28 <Sgeo> It depends on the tilt of my monitor, if I tilt it back far enough, no problem
02:06:33 <kallisti> sounds like a problem with the video cable
02:06:36 <boily> single channel weirdness sounds like an unseated connector, or the cable got pinched somewhere.
02:07:01 <Sgeo> boily: sometimes it's other colors
02:07:22 <Sgeo> kallisti: more accurately, the current tilt affects it. If I move it into one position, the effect can be there even when I stop moving it
02:07:50 <Sgeo> kallisti: is it likely to be the type of problem I'd need to replace the cable itself to fix, or just make it tighter or something
02:08:54 <kallisti> doesn't sound like a problem with the LCD, since that would usually be permanent artifacts. dead pixels and such.
02:10:03 <kallisti> Sgeo: is it just the negative of the original image?
02:14:03 <kallisti> try hooking up an external monitor if you have one
02:14:21 <kallisti> and see if it has the same problem.
02:17:28 <Sgeo> Don't have one at home
02:17:38 <Sgeo> Do have one at work, don't think taking personal computer there good idea
02:31:00 -!- _AndoDaan_ has quit (Ping timeout: 252 seconds).
02:32:48 -!- skj3gg has joined.
02:51:05 -!- skj3gg has quit (Quit: ZZZzzz…).
03:01:29 -!- boily has quit (Quit: MIROBOLANT CHICKEN).
03:09:19 <zzo38> Do you like to play a mahjong game?
03:11:58 <coppro> I've recently learned the rules to riichi
03:12:50 <Lilax> I once made a program that stores your copies of text and links in the scroll and right click of a mouse
03:13:03 <Lilax> Its broken now since firefox updated
03:13:06 <zzo38> I am just curious. Have you ever seen or heard of Washizu mahjong (a variant involving teams and tiles made of glass and a few other things)?
03:13:31 -!- skj3gg has joined.
03:13:37 <zzo38> Also I am writing the rules of a Magic: the Gathering variant for combining it with mahjong.
03:15:17 <zzo38> People have tried before combining Magic: the Gathering with other games such as Monopoly and chess.
03:15:47 -!- adu has quit (Quit: adu).
03:20:05 <coppro> zzo38: I have heard of it, yes
03:23:29 <zzo38> Washizu mahjong is invented by Fukumoto and is played in Akagi manga.
03:25:23 -!- Lilax has quit (Read error: Connection reset by peer).
03:26:08 -!- skj3gg has quit (Quit: ZZZzzz…).
03:27:02 <zzo38> It was invented in the manga at first but now you can actually buy Washizu mahjong tiles (I have a box of them).
03:30:32 <coppro> they were sold by a company in vancouver
03:30:37 <coppro> afaik they went out of business though
03:32:53 <zzo38> You can buy Washizu tiles from Japan; I imported it from Japan, and the company that imported it for me is still in business.
03:35:45 -!- adu has joined.
03:35:55 <zzo38> I have no link it is a physical store
03:49:42 <HackEgo> [wiki] [[Talk:Wct]] M http://esolangs.org/w/index.php?diff=41871&oldid=41861 * Oerjan * (+47) The date is not optional
03:53:57 <HackEgo> [wiki] [[Prelude]] http://esolangs.org/w/index.php?diff=41872&oldid=41851 * Oerjan * (-36) /* External resources */ Template
03:57:07 -!- Zefpher has joined.
03:59:57 -!- skj3gg has joined.
04:00:05 * oerjan digs a hole and buries Zefpher in it
04:00:31 * oerjan is a very disturbed doggie
04:08:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
04:08:37 -!- FreeFull has quit (Ping timeout: 245 seconds).
04:13:05 <zzo38> Now I made up the file in my computer that I wrote how to play Magic: the Gathering with mahjong combined together.
04:17:41 -!- Zefpher has quit (Remote host closed the connection).
04:28:52 -!- skj3gg has quit (Quit: ZZZzzz…).
04:45:39 -!- bb010g has joined.
04:55:35 -!- nys has quit (Quit: quit).
05:15:23 -!- augur has quit (Quit: Leaving...).
05:16:59 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:22:14 -!- augur has joined.
06:10:40 -!- FreeFull has joined.
06:17:13 <Sgeo> People who have heard me sing: Do I really sound feminine enough that I would be called "ma'am" by everyone who hears me on the phone?
06:27:43 <zzo38> I don't know because I didn't hear you sing, and even if I did I probably wouldn't know that answer anyways.
06:30:05 -!- Sprocklem has quit (Ping timeout: 250 seconds).
06:33:57 -!- oerjan has quit (Quit: Nite).
06:49:32 -!- CADD has quit (Quit: Lost terminal).
06:55:39 -!- hjulle has quit (Ping timeout: 250 seconds).
07:01:09 <zzo38> Do you have any *indexed* Latin-suited tarot decks?
07:06:11 <zzo38> I also don't like the Fool/Excuse labeled as zero; while I understand why this is (someone told me why, it is because the trumps represent a journey and the fool is the beginning of the journey), but its value is never zero (it is either the highest trump, or it has another purpose). I would like to leave off the index of that card and only that one.
07:08:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
07:36:57 <b_jonas> "Magic: the Gathering with mahjong combined together" heh
07:37:45 <zzo38> http://zzo38computer.org/textfile/miscellaneous/mahjong.var This is the rules I wrote for this game
07:37:54 <zzo38> Oops sorry that is the wrong URL
07:38:05 <zzo38> http://zzo38computer.org/textfile/miscellaneous/magic_card/mahjong.var
07:40:16 <zzo38> b_jonas: Do you like this?
07:40:48 <b_jonas> I don't know, I'm not a mahjong player, so I probably won't appreciate it
07:41:22 <zzo38> Do you know how to play mahjong at all?
07:41:32 <b_jonas> I don't know all the scoring
07:42:25 <zzo38> Then you can learn.
07:47:15 <zzo38> Is there anything like Hackage/CTAN/CPAN/whatever but for SQLite?
07:47:58 <b_jonas> zzo38: I dunno, but you can abuse CPAN to advertise any software if you just put a half-assed perl interface to it.
07:49:28 <zzo38> Advertising the software where it doesn't belong is not the point though
07:51:25 <b_jonas> "Whichever player is the active player in Magic: the Gathering is east
07:51:37 <b_jonas> - is this all the time, or only at the start of the game?
07:52:02 <zzo38> b_jonas: All the time.
07:57:07 <b_jonas> so you deal mahjong in each M:tG turn?
07:57:22 <b_jonas> that seems like it's a much slower game than M:tG then
07:57:29 <zzo38> Yes. It would slow down the game.
07:57:32 <b_jonas> but yes, it might make sense
07:58:03 <b_jonas> people invent so many hybrid sports like chess-boxing and kayak polo
08:00:14 <zzo38> I even read once someone they play chess several times, winning at chess is worth a certain value in poker chips; afterward you play poker, but instead of starting an equal number of chips you have whatever chips you won from the chess game, so whoever is better at chess game starts with an advantage in the poker game.
08:00:42 <zzo38> The games don't interfere with each other much in this case though, but it is one thing to do if it is what you like to do.
08:01:22 -!- Patashu_ has joined.
08:01:22 -!- Patashu has quit (Disconnected by services).
08:01:52 <b_jonas> sure, the "mahjong tiles are permanents" thing is scary
08:02:19 <b_jonas> it makes them interact a lot
08:04:10 <int-e> zzo38: so is this for a four player version of MtG?
08:04:51 <zzo38> int-e: Yes you need to play four players
08:10:24 -!- tromp has quit (Read error: Connection reset by peer).
08:11:00 -!- tromp has joined.
08:14:03 -!- Melvar has quit (Ping timeout: 252 seconds).
08:19:10 <zzo38> Once on Monty Python they asked "Which great opponent of Cartesian dualism resists the reduction of psychological phenomena to a physical state and insists there is no point of contact between the extended and the unextended?" What does "there is no point of contact between the extended and the unextended" mean here?
08:19:56 <b_jonas> does it have to mean somethign?
08:20:21 <zzo38> I don't know; I expected it to mean something.
08:20:44 <b_jonas> dunno, some philosophers or something might know what it means
08:21:27 <zzo38> It seems to be legitimate as Henri Bergson is mentioned and looking at Wikipedia, he is actually a philosopher.
08:21:38 <b_jonas> (unless you want a generalized zygomorphism)
08:22:02 <zzo38> The stuff in Wikipedia though is just as confusing.
08:27:31 -!- Melvar has joined.
08:34:06 -!- MDude has quit (Read error: Connection reset by peer).
09:04:23 <zzo38> If there isn't the one for SQLite then maybe I have to learn how to invent such thing.
09:29:33 -!- adu has quit (Quit: adu).
09:36:55 -!- Tritonio has joined.
10:28:08 -!- Tritonio has quit (Remote host closed the connection).
10:32:35 -!- Tritonio has joined.
10:49:41 -!- FreeFull has quit (Quit: Later).
10:55:59 -!- jix_ has quit (Quit: Lost terminal).
10:56:47 -!- shikhin has joined.
10:57:03 -!- Gracenotes_ has quit (Ping timeout: 245 seconds).
10:57:41 -!- jix has joined.
10:57:58 -!- Gracenotes has joined.
10:58:22 -!- AndoDaan has joined.
11:01:14 -!- skarn has quit (Ping timeout: 245 seconds).
11:02:04 -!- supay has quit (Ping timeout: 245 seconds).
11:02:39 -!- skarn has joined.
11:03:38 -!- supay has joined.
11:05:18 -!- ais523 has joined.
11:20:16 -!- boily has joined.
11:37:47 -!- Patashu_ has quit (Ping timeout: 256 seconds).
11:58:30 <Jafet> http://arcsynthesis.org looks like it got sprayed by a drive-by
12:00:11 <Jafet> Maybe I should be more careful when using the gltut example code
12:06:28 <boily> Jafet: http://www.carpathos.com/ ?
12:06:52 <boily> http://treasurevalleytax.com/ ???
12:07:08 <boily> what in fungot is that?
12:07:46 <Jafet> http://www.truckbacker.com/ brings a new meaning to drive-by backdoors
12:16:52 -!- ais523 has quit (Ping timeout: 240 seconds).
12:23:03 -!- boily has quit (Quit: OMNIDIRECTIONAL CHICKEN).
12:25:01 -!- Froo has joined.
12:28:45 -!- Froox has quit (Ping timeout: 250 seconds).
12:31:58 -!- Tritonio has quit (Ping timeout: 252 seconds).
12:36:40 -!- shikhin_ has joined.
12:39:49 -!- shikhin has quit (Ping timeout: 265 seconds).
12:40:30 -!- ais523 has joined.
12:41:25 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41873&oldid=41589 * 193.69.211.10 * (+2) /* External resources */
13:00:15 -!- GeekDude has joined.
13:03:13 -!- hjulle has joined.
13:08:20 -!- Tritonio has joined.
13:29:56 -!- AndoDaan has quit (Quit: Going, going, gone.).
13:40:06 <naturalog> https://bitcointalk.org/index.php?topic=950309
13:43:09 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
13:50:47 -!- hjulle has quit (Ping timeout: 250 seconds).
13:53:53 <Jafet> That is a very fractured ceramic container
14:13:27 -!- Zefpher has joined.
14:14:25 <Zefpher> Ok ill just leave our nick like this
14:14:58 -!- Tritonio has quit (Remote host closed the connection).
14:20:42 -!- Zefpher has quit (Ping timeout: 245 seconds).
14:26:14 -!- ProofTechnique has joined.
14:30:47 <HackEgo> [wiki] [[Talk:Al Dente]] M http://esolangs.org/w/index.php?diff=41874&oldid=41793 * Doesthiswork * (+391) nitpicking
14:34:52 <quintopia> why has no one been triggering pbflist for me :/
14:35:17 -!- shikhin_ has changed nick to shikhin.
14:35:56 <HackEgo> pbflist: shachaf Sgeo quintopia ion
15:00:33 -!- AnotherTest has joined.
15:02:08 <mroman> can neural networks be trained to do calculations?
15:02:47 <quintopia> they can be wired into logic circuits
15:03:13 <quintopia> no training required...just create the network anually
15:03:56 <naturalog> mroman: cf universal approximation theorem
15:04:37 -!- `^_^v has joined.
15:11:08 -!- TieSleep has changed nick to TieSoul.
15:13:45 -!- mihow has joined.
15:15:17 -!- adu has joined.
15:39:54 -!- Sprocklem has joined.
15:40:28 -!- adu has quit (Quit: adu).
15:43:16 -!- SopaXorzTaker has joined.
15:43:22 -!- oerjan has joined.
15:45:24 -!- Koen__ has joined.
15:51:16 -!- ais523 has quit.
15:59:44 -!- SopaXT has joined.
16:00:48 -!- SopaXorzTaker has quit (Ping timeout: 245 seconds).
16:15:23 -!- Froo has quit (Ping timeout: 250 seconds).
16:42:12 -!- oerjan has quit (Quit: leaving).
16:49:43 -!- adu has joined.
16:50:22 -!- choochter has joined.
16:54:01 -!- spiette has joined.
17:13:58 <mroman> Wasn't there some site that let's you enable comment functionality in static webpages
17:28:38 -!- supay has changed nick to supay_zZZ.
17:37:00 -!- supay_zZZ has changed nick to supay.
17:41:59 <fizzie> There was also at least one thing where you can scribble over arbitrary websites, and other people registered on the service can see those scribblings.
17:42:51 -!- mihow has quit (Quit: mihow).
17:44:26 <kallisti> nice, I've always wanted to enhance my web surfing experience with crudely drawn dicks.
17:57:39 <zzo38> I have invented a ASCII based file format for deck lists for Magic: the Gathering and can be used with other card games too. It is designed to be: * Easy to read it manually. * Easy to write it manually. * Easy to program the computer to parse it (ignoring things it doesn't need to understand).
18:21:12 -!- FreeFull has joined.
18:22:22 -!- `^_^v has quit (Read error: Connection reset by peer).
18:23:03 -!- `^_^v has joined.
18:23:30 -!- arjanb has joined.
18:35:27 -!- mihow has joined.
18:37:02 -!- shikhin_ has joined.
18:37:19 -!- Sprocklem has quit (Ping timeout: 245 seconds).
18:38:22 -!- SopaXT has quit (Ping timeout: 250 seconds).
18:38:55 <zzo38> Is it your opinion that SQLite virtual table should allow the virtual table implementation to read the LIMIT and OFFSET clauses of a query in case that virtual table is accessing data over the internet it would help to have these things?
18:39:19 <zzo38> (In order to avoid wasting bandwidth by accessing all of the data even if it isn't used)
18:39:50 -!- shikhin has quit (Ping timeout: 246 seconds).
18:43:45 -!- shikhin_ has changed nick to shikhin.
19:02:07 -!- Sprocklem has joined.
19:06:28 -!- Sprocklem_ has joined.
19:07:18 -!- Sprocklem has quit (Read error: Connection reset by peer).
19:07:52 -!- Sprocklem_ has changed nick to Sprocklem.
19:18:54 -!- idris-bot has quit (Quit: Terminated).
19:19:11 -!- idris-bot has joined.
19:33:13 <zzo38> Now I have made up a few scheme cards for Magic: the Gathering, which are called "Ice Scheme", "The Ultimate Sacrifice", and "You Have To Study Too Much".
19:33:25 -!- Sprocklem has quit (Ping timeout: 250 seconds).
19:35:23 -!- spiette has quit (Ping timeout: 245 seconds).
19:35:47 -!- spiette has joined.
19:51:22 -!- adu has quit (Quit: adu).
19:54:29 -!- Tritonio has joined.
19:55:28 -!- nys has joined.
20:00:14 -!- skj3gg has joined.
20:02:42 -!- Patashu has joined.
20:16:40 -!- Tritonio has quit (Remote host closed the connection).
20:16:56 -!- Tritonio has joined.
20:18:06 -!- zzo38 has quit (Remote host closed the connection).
20:25:45 -!- Patashu has quit (Ping timeout: 265 seconds).
20:38:29 -!- AnotherTest has quit (Remote host closed the connection).
20:39:33 <mroman> PLEASE ACCEPT MY STANDARD FONT SIZE SETTINGS YOU FUCKING MORON
20:42:18 <mroman> I set default font size to 12pt
20:42:26 <mroman> but if a website does not specify any font size
21:16:08 -!- nycs has joined.
21:18:18 -!- `^_^v has quit (Ping timeout: 245 seconds).
21:19:18 -!- Sprocklem has joined.
21:33:25 <mitchs> int-e, in case you didn't notice, henkma struck back on sin curve
21:49:05 <mroman> this february in your local cinema :(
21:49:16 <mroman> (also in your local cinema of course)
22:06:42 -!- Tritonio_ has joined.
22:08:25 <mitchs> good movies this month
22:08:37 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:08:44 -!- Tritonio has quit (Ping timeout: 252 seconds).
22:09:29 -!- Tritonio has joined.
22:11:18 -!- Tritonio_ has quit (Ping timeout: 252 seconds).
22:20:02 <mroman> do you have some food to spare?
22:20:20 <Taneb> If you're in York, want half a pizza?
22:21:52 -!- Sprocklem has quit (Ping timeout: 240 seconds).
22:22:19 <mroman> Wasn't it time for an #esoteric meet-up?
22:22:50 <Taneb> We're all quite geographically disparate
22:23:01 <Taneb> Unless it's in like Turku or the West Midlands
22:23:54 <mroman> we just have to make it an educational conference
22:24:01 -!- 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?").
22:24:27 <mroman> so I can write it off as educational expences
22:24:44 <mroman> then my employer might pay for the trip ;)
22:25:07 <Taneb> Unfortunately I am not in that situation
22:25:26 <mroman> I guess that could work as well
22:25:38 -!- skj3gg has quit (Quit: welp, see you later.).
22:45:25 -!- oerjan has joined.
22:47:10 -!- ProofTechnique has joined.
23:04:45 -!- boily has joined.
23:06:37 -!- mihow has quit (Quit: mihow).
23:12:49 -!- diginet has quit (Ping timeout: 264 seconds).
23:13:25 -!- diginet has joined.
23:24:22 -!- Phantom_Hoover has joined.
23:29:08 -!- Lymia has quit (Ping timeout: 245 seconds).
23:29:21 -!- oren has joined.
23:31:41 -!- Lymia has joined.
23:36:43 -!- ProofTechnique has quit (Ping timeout: 255 seconds).
23:57:47 <HackEgo> [wiki] [[Glass]] http://esolangs.org/w/index.php?diff=41875&oldid=32008 * 70.36.190.3 * (-36) /* 99 bottles of beer */ Fix bug by removing P.n, which referred to the nonexistent variable s, resulting in returning from P.n with 3 junk values pushed onto the stack when running the 0.12 interpreter.
23:59:48 <HackEgo> [wiki] [[Glass]] http://esolangs.org/w/index.php?diff=41876&oldid=41875 * 70.36.190.3 * (+8) /* 99 bottles of beer */ Formatting
00:02:38 -!- ProofTechnique has joined.
00:06:19 -!- skj3gg has joined.
00:07:18 -!- boily has quit (Quit: IMPRINTED CHICKEN).
00:07:54 -!- nycs has quit (Quit: This computer has gone to sleep).
00:10:14 -!- variable has quit (Quit: I found 1 in /dev/zero).
00:32:37 -!- kallisti has quit (Ping timeout: 264 seconds).
00:36:44 -!- shikhin_ has joined.
00:39:24 -!- shikhin has quit (Ping timeout: 245 seconds).
00:47:57 -!- skj3gg has quit (Quit: ZZZzzz…).
00:59:46 -!- oren has quit (Ping timeout: 246 seconds).
01:12:15 <Sgeo> pikhq: did I make a mistake in buying Urbanite XL?
01:25:29 -!- adu has joined.
01:44:09 <Sgeo> It's very bass-y
01:44:23 <Sgeo> Also choppy sound in one ear, but maybe that's a bad headphone port
01:45:26 <oerjan> it sounds like you have done a fine acquirement of a torture instrument hth
01:46:25 <Phantom_Hoover> are usb headphones really bad enough that it's worth dealing with the incredible unreliability of headphone jacks instead?
01:47:38 <Sgeo> I did not realize USB headphones existed until just now.
01:53:05 <Sgeo> Also, I was under the impression that my old headphones were just dead. Now I blame the headphone port
01:53:43 <Sgeo> At least the new headphone smell is addictive
01:55:47 -!- variable has joined.
01:55:47 -!- variable has quit (Changing host).
01:55:47 -!- variable has joined.
02:24:30 <HackEgo> [wiki] [[Talk:Al Dente]] M http://esolangs.org/w/index.php?diff=41877&oldid=41874 * Doesthiswork * (+225) more nitpicking
02:25:17 -!- TieSoul has quit (Ping timeout: 245 seconds).
02:27:12 <Sgeo> I spent way too much money on these
02:32:21 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
03:07:00 -!- ^v has joined.
03:13:01 -!- zzo38 has joined.
03:20:48 -!- ^v has quit (Ping timeout: 245 seconds).
03:22:37 -!- ^v has joined.
03:24:37 -!- mitchs has quit (Quit: mitchs).
03:28:18 -!- ^v has quit (Ping timeout: 245 seconds).
03:36:07 -!- mitchs has joined.
03:40:53 -!- ^v has joined.
03:52:53 -!- ^v has quit (Ping timeout: 245 seconds).
03:59:02 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
04:00:59 -!- ^v has joined.
04:01:00 -!- ^v has quit (Client Quit).
04:07:10 -!- ^v has joined.
04:11:52 -!- bb010g has joined.
04:25:23 -!- ^v has quit (Ping timeout: 245 seconds).
04:27:40 -!- ^v has joined.
04:49:33 -!- ^v has quit (Ping timeout: 245 seconds).
04:50:26 -!- ^v has joined.
04:57:10 -!- Sprocklem has joined.
05:01:38 -!- ^v has quit (Ping timeout: 245 seconds).
05:02:40 -!- ^v has joined.
05:10:22 -!- arjanb has quit (Ping timeout: 246 seconds).
05:10:48 -!- ^v has quit (Ping timeout: 245 seconds).
05:14:28 -!- nys has quit (Quit: quit).
05:14:59 -!- ^v has joined.
05:22:28 -!- ^v has quit (Ping timeout: 245 seconds).
05:26:06 -!- Tritonio has quit (Remote host closed the connection).
05:31:12 -!- Zefpher has joined.
05:31:40 * pikhq grabs some popcorn for watching Alabama
05:32:24 <pikhq> No, no. The hilarity of watching a judge in a high position actively defy a higher court's explicit orders.
05:36:36 <elliott> higher court? is that some football thing
05:37:16 <oerjan> Zefpher: i think you may shake elliott too hth
05:38:49 <oerjan> THAT'S NOT WHAT I MEANT
05:41:33 -!- MDude has joined.
05:43:17 <HMC_A> i followed naturalog in
05:43:24 <HMC_A> thought maybe we could talk about esolang stuff
05:43:44 <HMC_A> can we consider the empty dictionary as an esolang?
05:45:17 -!- oerjan has quit (Quit: Perchance to sleep).
05:46:19 <Zefpher> Never heard of it but let me captcha log it
05:46:55 <HMC_A> just a language with no terms. matches nothing. Is it a language? Is it esoteric? :-)
05:49:07 <HMC_A> an implementation of a machine for such an empty language could only do one function, its own existence proof, I think
05:50:13 -!- Sprocklem has quit (Quit: [).
05:50:18 <MDude> Well there's http://esolangs.org/wiki/Compute
05:50:31 -!- Sprocklem has joined.
05:50:35 -!- mitchs has quit (Ping timeout: 252 seconds).
05:51:22 <HMC_A> that has no required syntax but still has syntax
05:51:33 <HMC_A> just no (meaningful) semantics
05:51:40 <HMC_A> this would be a language with neither :-)
05:52:22 -!- Sprocklem has quit (Client Quit).
05:52:38 -!- Sprocklem has joined.
05:53:09 <MDude> I tohught there was one, but I can't find it.
05:53:21 <HMC_A> I'd say someone should implement it, but...
05:53:34 <MDude> http://esolangs.org/wiki/Text
05:54:12 <HMC_A> that still matches anything
05:54:13 <zzo38> Nobody else seem to answer this question: An invisible character puts a gold coin on the ground (the coin is made visible though) so that the guard will come and open the gate to pick up the gold coin. What is the correct trope page of it? (on All The Tropes, not on TV Tropes)
05:55:30 <MDude> I haven't read All the Tropes at all.
05:57:07 <MDude> You enter a program, and get the reponse "Done."
05:58:30 <Zefpher> I should make a language that makes people fall into the pits of inferno
05:58:42 -!- Sprocklem has quit (Quit: [).
06:02:32 -!- mitchs has joined.
06:15:27 <Zefpher> It takes a lot to make a stew, A dash of crime; Some arson too~ Add some theives for the spice, Serial killers to make it nice.
06:19:36 <HMC_A> cannibalism isn't cool
06:19:55 <HMC_A> even if they are criminals
06:36:17 -!- shikhin_ has quit (Read error: Connection reset by peer).
06:36:59 -!- shikhin has joined.
06:38:17 <Sgeo> I think [S] Caliborn: Enter is muddled
06:42:56 <Sgeo> Compared to in the HD 201s
06:43:15 <Sgeo> Maybe it's placebo effect, I keep seeing less than positive reviews of the thing I just spent hundreds of dollars on
06:44:13 <coppro> dude, it's audio equipment
06:44:43 <coppro> if you don't have a 3500$ headphone cable, you're doing it wrong
06:45:17 * HMC_A stares back at Zefpher
07:03:11 -!- TieSoul has joined.
07:05:04 -!- TieSoul has changed nick to TieSchool.
07:05:37 -!- Zefpher has quit (Ping timeout: 264 seconds).
07:47:50 -!- Patashu has joined.
08:00:08 <mroman> Closures are working \o/
08:00:29 <mroman> addls -> (map (atom (add $0 &1)) $0)
08:00:30 <mroman> main -> (putstrln (show (addls #(1 2 3) 10)))
08:14:57 <int-e> oh, I have not seen that from myndzi before...
08:16:21 <int-e> it seems to trigger twice. note that the | body is also duplicated
08:16:30 <int-e> does anybody remember the snowflake trigger?
08:18:01 <int-e> see, it gets triggered twice.
08:18:37 <lifthrasiir> int-e: let's pretend that it generates some futuristic species of human
08:19:25 <int-e> I thought the |\ /| one looks a bit like a plant. Either upside down, or a sort of root.
08:22:09 -!- ineiros has joined.
08:28:54 <lambdabot> Control.Concurrent forkIO :: IO () -> IO ThreadId
08:28:54 <lambdabot> GHC.Conc.Sync forkIO :: IO () -> IO ThreadId
08:28:54 <lambdabot> GHC.Conc forkIO :: IO () -> IO ThreadId
08:34:32 <mroman> I'm a supposed to use read/write MVar or Take/Put MVar?
08:35:41 <int-e> mroman: if you want a mutex, you usually should use withMVar.
08:36:31 -!- MDude has changed nick to MDream.
08:37:30 <int-e> mroman: or modifyMVar[_] if you also want to modify a value inside the MVar. In contrast to take/put, this ensures proper cleanup when exceptions are received.
08:38:46 <int-e> mroman: readMVar is currently changing; it used to be a takeMVar followed by putMVar, but it's becoming properly atomic with ghc 7.10. It's a slightly strange operation.
08:39:27 <mroman> "However, it is only atomic if there are no other producers for this MVar."
08:39:42 <mroman> I want: read and write which will LOCK the mvar
08:39:47 <int-e> mroman: that part is being changed :P
08:39:53 <mroman> If two threads are doing a write
08:40:00 <mroman> one should succeed and the other should be blocked
08:40:53 <int-e> okay, putMVar will do that. readMVar, however, will unblock the other thread.
08:41:14 <mroman> but takeMVar is single-wakeup
08:41:42 <mroman> http://codepad.org/NEArKvwB
08:42:20 <mroman> (put does putMVar, take does takeMVar)
08:44:15 <int-e> mroman: Right, that should work. You're using MVar as a single slot mailbox, which is precisely what putMVar/takeMVar implement. (putMVar blocks when the mailbox is full, waiting for it to become empty; takeMVar blocks if the mailbox is empty, waiting for it to be filled)
08:44:39 <mroman> K. Then I can move on to implement chans :D
08:56:14 <mroman> http://codepad.org/5SOeQQi0
09:08:03 <mroman> "on windows this function behaves differentely
09:47:26 -!- Phantom_Hoover has joined.
10:07:24 -!- furiusbutcake has joined.
10:10:42 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41878&oldid=41849 * Mazeman * (+36) /* Example programs */
10:11:17 <HackEgo> [wiki] [[Mice in a maze]] http://esolangs.org/w/index.php?diff=41879&oldid=41878 * Mazeman * (+39) /* Example programs */
10:16:21 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41880&oldid=41741 * TomPN * (-5) /* Setup */
10:17:05 <HackEgo> [wiki] [[Quantum Dimensions]] http://esolangs.org/w/index.php?diff=41881&oldid=41880 * TomPN * (-10) /* Output */
10:24:24 -!- adu has quit (Quit: adu).
10:30:17 -!- furiusbutcake has left.
10:37:34 -!- adu has joined.
11:07:28 <HackEgo> [wiki] [[Aheui]] http://esolangs.org/w/index.php?diff=41882&oldid=41865 * Puzzlet Chung * (+26) revert to original Hello, world!
11:11:54 <Jafet> How about "on non-Windows systems this function behaves differently"
11:12:23 <Jafet> Also is it a function
11:20:02 <b_jonas> which esolangs have important builtin rules that don't work on particular days of weeks? eg. something like "the 'my' builtin declares a lexical variable, except on Tuesdays"
11:25:49 -!- boily has joined.
11:30:30 <MDream> http://esolangs.org/wiki/TMMLPTEALPAITAFNFAL
11:30:49 <MDream> It's not specific to weeks, but different every day.
11:30:54 -!- MDream has changed nick to MDude.
11:31:23 <mroman> hm. I guess "lazy" would be next
11:39:18 <mroman> #((lazy (add $0 $0)) (lazy (add $0 $0)) (lazy (add $0 $0)))
11:39:23 <mroman> that didn't work out well
11:40:10 <Taneb> Damn, TMMLPTEALPAITAFNFAL's full name is longer than Real Fast Nora's Hair Salon 3: Shear Disaster Download
11:40:28 <Taneb> otoh, Real Fast Nora's Hair Salon 3: Shear Disaster Download can't be shortened
11:43:03 -!- hjulle has joined.
11:48:50 -!- Patashu has quit (Ping timeout: 250 seconds).
11:49:11 <fizzie> I'm still disappointed it wasn't about a character called Real Fast Nora.
11:50:33 <fizzie> I always used to parse it ((Real Fast Nora)'s Hair Salon 3: Shear Disaster) Download, but apparently it's "really" Real Fast (Nora's Hair Salon 3: Shear Disaster) Download.
11:52:33 <MDude> I parsed it as ((Real Fast Nora)'s Hair Salon 3: Shear) (Disaster Download).
11:53:25 <MDude> Or I guess Just ((Real Fast Nora)'s Hair Salon 3:) Shear Disaster Download.
11:59:22 <mroman> there's a lazy in there :(
12:01:38 -!- zzo38 has quit (Ping timeout: 245 seconds).
12:02:34 <mroman> "not lazy: [$0,(lazy $0)]"
12:02:35 <mroman> *** Exception: (add 1 (lazy $0))
12:02:41 <mroman> why is this not lazy when it is
12:06:46 <mroman> my isLazy function must be broken
12:16:39 <boily> does isLazy rely on having solved the halting problem?
12:20:53 <Taneb> fizzie, it parses however you want it to parse
12:21:34 <Taneb> I parse it (((Real Fast Nora)'s (Hair Salon 3)) (Shear (Disaster Download)))
12:21:46 <Taneb> Got results from exams in January
12:21:52 <Taneb> 96% in my group theory exam
12:23:15 -!- boily has quit (Quit: LEGERDEMAIN CHICKEN).
12:25:59 -!- intgr has left.
12:33:17 <Jafet> https://en.wikipedia.org/wiki/Earth_in_science_fiction
12:33:51 <HackEgo> [wiki] [[Semi-quantum]] N http://esolangs.org/w/index.php?oldid=41883 * Mazeman * (+1165) Created page with "Semi-quantum is an esoteric programming language invented in 2015 by an anonymous user. It allows the user to chose between "classical" programming, in a similar manner to b..."
12:37:14 -!- shikhin_ has joined.
12:40:35 -!- shikhin has quit (Ping timeout: 256 seconds).
12:41:22 <mroman> #({(add 1 {(add 1 1)})} {(add 1 {(add 2 2)})} {(add 1 {(add 3 3)})})
12:43:42 <mroman> main -> (putstrln (show (map (atom (add $0 $0)) (map (atom (add 1(add $0 (lazy $0)))) #(1 2 3)))))
12:43:55 <mroman> => #({(add {(add 1 (add 1 1))} {(add 1 (add 1 1))})} {(add {(add 1 (add 2 2))} {(add 1 (add 2 2))})} {(add {(add 1 (add 3 3))} {(add 1 (add 3 3))})})
12:44:33 <mroman> I'm trying to implement a thing called "lazy"
12:44:47 <mroman> which rather than evaluating the stuff returns the expression "unfolded" that would evaluate to that stuff
12:45:04 <mroman> It doesn't actually execute the "add"
12:47:30 <mroman> it's really broken though :(
12:48:22 <mroman> main -> (putstrln (show (map (atom (add $0 (putstrln (show 0)))) (map (atom (add 1(add $0 (lazy $0)))) #(1 2 3)))))
12:48:26 <mroman> this prints three times the 0
12:48:38 <mroman> #({(add {(add 1 (add 1 1))} NIL)} {(add {(add 1 (add 2 2))} NIL)} {(add {(add 1 (add 3 3))} NIL)})
12:48:45 <mroman> (putstrln returns NIL)
12:48:56 <mroman> so at least the putstrln is actually executed :)
12:49:17 <mroman> or mabye that's actually correct behaviour
12:49:31 <mroman> technically (putstrln (show 0)) isn't wrapped into lazy
12:49:56 <mroman> if I wrap into into lazy it returns
12:49:59 <mroman> #({(add {(add 1 (add 1 1))} {(putstrln (show 0))})} {(add {(add 1 (add 2 2))} {(putstrln (show 0))})} {(add {(add 1 (add 3 3))} {(putstrln (show 0))})})
13:07:22 -!- adu has quit (Quit: adu).
13:14:22 <HackEgo> [wiki] [[Semi-quantum]] http://esolangs.org/w/index.php?diff=41884&oldid=41883 * Mazeman * (+2875)
13:15:00 <HackEgo> [wiki] [[Semi-quantum]] http://esolangs.org/w/index.php?diff=41885&oldid=41884 * Mazeman * (+1) /* Input */
13:15:17 <HackEgo> [wiki] [[Semi-quantum]] http://esolangs.org/w/index.php?diff=41886&oldid=41885 * Mazeman * (+1) /* Output */
13:17:05 <mroman> http://mroman.ch/private/100215.html
13:17:14 -!- shikhin_ has changed nick to shikhin.
13:25:44 <Taneb> Today is a good day
13:28:04 <Taneb> I got exam results back that were better than I expected, and I signed the contract for the place I'm going to be living next year
13:28:22 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
13:30:40 -!- ais523 has joined.
13:32:37 <mroman> are you moving to finnland?
13:33:10 <b_jonas> yeah, now I want to know, which country gets even more esoteric people
13:34:05 <mroman> Not too many swiss in here
13:34:22 <mroman> I could use another swiss in here
13:34:41 <mroman> abr nur wänn er au richtigs dütsch chan rede logischerwiis suscht dätschts
13:36:53 <Taneb> I am just moving about 200m east
13:37:24 <mroman> You'll be closer to Mekka then
13:40:42 <Taneb> That wasn't really part of my decision making process, mroman
13:45:45 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
13:51:51 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41887&oldid=41859 * Mazeman * (+19) /* S */
13:53:11 -!- Frooxius has joined.
14:00:44 -!- dulla has joined.
14:04:06 <Taneb> I've thought of a novel approach to solving the dining philosopher's problem
14:04:16 <Taneb> Or at least of illustrating it
14:04:44 <Taneb> Jafet, my plan is to host a bunch of philosophers
14:04:52 <Taneb> Establishing the conditions of the problem
14:06:33 <Taneb> And then seeing what happens
14:10:46 -!- ProofTechnique has joined.
14:11:29 <mroman> http://codepad.org/4VuqbvyD
14:11:38 <mroman> my tcp relaying thing ported to my lisp dialect
14:13:27 -!- Tritonio has joined.
14:42:59 <HackEgo> dulla: 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.)
14:44:59 <dulla> I came from a roughly categorical channel
14:45:31 -!- Tritonio has quit (Remote host closed the connection).
14:45:44 -!- Tritonio has joined.
14:50:11 -!- idris-bot has quit (Quit: Terminated).
14:50:27 -!- idris-bot has joined.
14:51:00 -!- Tritonio has quit (Remote host closed the connection).
14:51:14 <mroman> I can't call a FunPtr, now can I?
14:51:35 -!- Tritonio has joined.
14:52:01 -!- Tritonio has quit (Remote host closed the connection).
14:52:16 -!- Tritonio has joined.
14:53:37 <elliott> you use some weird foreign import directive to do it
14:54:04 <elliott> that's probably not what you want
14:54:19 <elliott> https://stackoverflow.com/questions/997738/haskell-ffi-calling-funptrs first result for "call funptr haskell"
14:55:47 <mroman> https://hackage.haskell.org/package/libffi-0.1/docs/Foreign-LibFFI.html
14:55:49 -!- Tritonio_ has joined.
14:55:51 <mroman> ^- this looks nice as well
14:55:59 <mroman> it has callFFI which takes a FunPtr
14:56:31 -!- Tritonio_ has quit (Remote host closed the connection).
14:56:42 -!- Tritonio has quit (Ping timeout: 252 seconds).
15:03:48 -!- AnotherTest has joined.
15:08:25 -!- GeekDude has joined.
15:16:49 -!- nycs has joined.
15:31:12 -!- SopaXT has joined.
15:34:37 -!- Sprocklem has joined.
15:47:01 -!- Sprocklem has quit (Ping timeout: 256 seconds).
15:53:00 -!- SopaXT has quit (Remote host closed the connection).
15:56:39 -!- SopaXorzTaker has joined.
16:01:14 -!- Froox has joined.
16:01:28 -!- SopaXorzTaker has quit (Ping timeout: 250 seconds).
16:04:59 -!- Frooxius has quit (Ping timeout: 246 seconds).
16:05:57 -!- SopaXorzTaker has joined.
16:11:27 -!- mihow has joined.
16:30:42 -!- TieSchool has changed nick to TieSoul.
16:39:05 -!- Frooxius has joined.
16:39:35 -!- oren has joined.
16:42:26 -!- Froox has quit (Ping timeout: 246 seconds).
16:45:44 <oren> Taneb: 96% nice!
16:46:36 <oren> But why haven't you recieved your results already?
16:47:09 <oren> semesters in <Taneb's country> must be on a different schedule
16:55:12 -!- nycs has quit (Quit: This computer has gone to sleep).
16:58:25 -!- `^_^v has joined.
17:12:44 -!- hjulle has quit (Ping timeout: 245 seconds).
17:14:28 -!- `^_^v has quit (Quit: This computer has gone to sleep).
17:14:47 -!- `^_^v has joined.
17:18:07 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:20:21 -!- oren has quit (Read error: Connection reset by peer).
17:40:47 -!- Lymia has quit (Ping timeout: 265 seconds).
17:46:54 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41888&oldid=41800 * 109.243.193.241 * (-17)
17:48:43 -!- Ebola-C has joined.
17:51:41 <Ebola-C> hmm I thought that esoteric means something else.. Wrong defined chan name :(
17:51:45 -!- Ebola-C has left.
18:06:13 -!- nycs has joined.
18:07:08 -!- `^_^v has quit (Ping timeout: 250 seconds).
18:09:34 -!- TieSoul has changed nick to TieStudying.
18:10:17 -!- PinealGlandOptic has joined.
18:10:37 -!- mihow has quit (Quit: mihow).
18:12:58 -!- adu has joined.
18:14:49 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:15:44 -!- SopaXorzTaker has joined.
18:19:20 -!- TieStudying has changed nick to TieProcrastinati.
18:19:25 -!- TieProcrastinati has changed nick to TieProcrastinate.
18:19:55 <int-e> TieProcrastinate: I like the procrastinati variant
18:20:08 <HackEgo> 1202) <int-e> The people of Procrasti hereby resolve to lodge a formal complaint with Taneb and nortti about their ridicule of Procasti's glorious nation... later.
18:20:39 -!- PinealGlandOptic has quit (Quit: Lost terminal).
18:20:48 -!- FreeFull has quit (Ping timeout: 246 seconds).
18:22:07 <int-e> TieProcrastinate: have you seen this great essay, http://structuredprocrastination.com/ ?
18:24:14 <TieProcrastinate> I sometimes go and learn some programming stuff to procrastinate on studying for a test
18:24:56 -!- FreeFull has joined.
18:31:53 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:32:22 -!- dorei has joined.
18:32:33 <dorei> do you cast spells?
18:36:10 -!- adu has quit (Quit: adu).
18:37:43 -!- shikhin_ has joined.
18:40:49 -!- shikhin has quit (Ping timeout: 244 seconds).
18:54:21 -!- hjulle has joined.
19:02:03 <mroman> everything is more exciting than school
19:04:30 <dorei> I used to count my arm's hair when I was at school xD
19:07:34 <dorei> it was more exciting than school
19:11:13 <TieProcrastinate> I once wrote a pretty cool turn-based RPG on my graph calculator in school
19:11:29 <TieProcrastinate> because programming in TI-BASIC is still more exciting than school
19:17:53 <mroman> when I'm bored I do stuff like http://mroman.ch/private/100215.html
19:18:15 <mroman> and this time it's actually a sane language
19:18:37 <mroman> next version will have named arguments though
19:19:09 <mroman> instead of foo -> (add $0 $0) foo x -> (add $x $x)
19:19:38 <mroman> or something like that
19:21:06 <mroman> or maybe def foo(x) := (add $x $x)
19:21:51 <mroman> still... most likely foo x -> (add $x $x)
19:23:19 -!- shikhin_ has changed nick to shikhin.
19:24:27 -!- arjanb has joined.
19:25:40 -!- oren has joined.
19:26:30 <oren> So i was wondering if anyone has tried using a neural network to guide a genetic algorithm...
19:29:22 -!- kallisti has joined.
19:32:07 -!- Lymia has joined.
19:53:33 -!- TieProcrastinate has changed nick to TieSoul.
19:54:27 <TieSoul> mroman: I also made a sane language
19:54:37 <TieSoul> though it's a scripting language that can't do a whole lot
19:56:12 <TieSoul> (no file system implemented yet, mostly due to me being too lazy to make a way to make builtin functions and classes that relay actions to the interpreting language)
19:56:35 <TieSoul> (except I special cased println() and print())
19:59:57 <TieSoul> which makes it very very very very slow
20:00:11 <TieSoul> especially recursion. Dunno what's up with that to be honest
20:00:34 <TieSoul> it's just very slow, probably due to the way I handle functions
20:02:26 -!- Patashu has joined.
20:03:48 -!- mihow has joined.
20:09:28 -!- heroux has quit (Ping timeout: 252 seconds).
20:10:19 -!- Koen__ has joined.
20:14:20 -!- Tritonio has joined.
20:17:19 -!- Tritonio has quit (Remote host closed the connection).
20:19:58 -!- oren has quit (Ping timeout: 245 seconds).
20:25:05 -!- Patashu has quit (Ping timeout: 250 seconds).
20:31:50 -!- oren has joined.
20:32:42 -!- `^_^ has joined.
20:34:53 -!- nycs has quit (Ping timeout: 246 seconds).
20:40:34 <dulla> > let foo x = (+) x x in foo 3
20:41:02 <dulla> > let foo x = x + x in foo 3
20:50:45 -!- AnotherTest has quit (Ping timeout: 256 seconds).
20:54:48 -!- FreeFull has quit (Ping timeout: 246 seconds).
20:56:41 -!- FreeFull has joined.
21:00:06 -!- TieSoul has changed nick to TieSleep.
21:12:50 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
21:29:27 -!- adu has joined.
21:36:34 -!- heroux has joined.
21:37:05 -!- ais523 has quit.
21:40:19 <kallisti> > let f = 0 : 1 : zipWith (+) f (tail f) in f
21:40:21 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
21:48:20 <oren> dorei: ponos is a memetic word for "penis" arising from the use of the circle character 〇 to censor part of a word in Japanese.
21:52:28 <oren> also apparently a greek god of toil.
21:57:22 -!- ProofTechnique has joined.
22:09:53 -!- adu has quit (Quit: adu).
22:14:07 -!- zzo38 has joined.
22:19:04 -!- Phantom_Hoover has joined.
22:21:09 <b_jonas> this is the first time I see the word "fivegon" meaning pentagon
22:26:48 -!- oerjan has joined.
22:28:43 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:32:29 -!- hjulle has quit (Ping timeout: 250 seconds).
22:33:53 -!- olsner has quit (Ping timeout: 256 seconds).
22:34:51 -!- olsner has joined.
22:38:43 -!- GeekDude has changed nick to GeekDudesBot.
22:38:54 -!- GeekDudesBot has quit (Changing host).
22:38:55 -!- GeekDudesBot has joined.
22:42:30 -!- Astrologos_ has joined.
22:43:07 -!- GeekDudesBot has changed nick to GeekDude.
22:43:09 -!- GeekDude has quit (Changing host).
22:43:09 -!- GeekDude has joined.
22:45:22 -!- dorei has quit (Ping timeout: 240 seconds).
22:45:26 -!- Astrologos_ has quit (Client Quit).
22:45:47 -!- dorei has joined.
22:48:08 -!- Tritonio has joined.
22:49:10 -!- 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?").
22:50:52 <b_jonas> http://math.ucr.edu/home/baez/octonions/integers/integers_6.html "So, there's not as much arbitrary baloney to remember as you might think! Anyone can remember how to multiply octonions, and I'm surprised they're not taught in elementary school right after category theory."
22:55:08 -!- adu has joined.
23:06:38 -!- Lymia has quit (Ping timeout: 245 seconds).
23:06:52 <Jafet> Speaking of elementary school
23:06:54 <Jafet> "it doesn't matter whether all your little arrows go counterclockwise or clockwise, as long as your consistent."
23:10:39 -!- Lymia has joined.
23:34:28 -!- `^_^ has quit (Quit: This computer has gone to sleep).
23:43:00 -!- dorei has quit.
23:46:49 -!- Lymee has joined.
23:47:27 -!- Lymia has quit (Read error: Connection reset by peer).
23:47:33 -!- Lymee has changed nick to Lymia.
00:01:27 -!- ^v has joined.
00:06:03 -!- Tritonio_ has joined.
00:07:26 -!- Tritonio has quit (Ping timeout: 252 seconds).
00:07:58 -!- Tritonio_ has changed nick to Tritonio.
00:09:08 -!- Lymia has quit (Ping timeout: 245 seconds).
00:31:41 -!- Lymia has joined.
00:37:58 -!- shikhin_ has joined.
00:40:56 -!- shikhin has quit (Ping timeout: 244 seconds).
00:50:19 -!- mihow has quit (Quit: mihow).
01:03:44 <Taneb> I am looking forward to Australia's entry to Eurovision this year
01:18:42 -!- olsner has quit (Ping timeout: 246 seconds).
01:18:49 * oerjan assumes Taneb is being serious
01:19:10 <Taneb> http://www.eurovision.tv/page/news?id=australia_to_participate_in_the_2015_eurovision_song_contest
01:21:20 -!- adu has quit (Quit: adu).
01:21:26 <oerjan> can we hope for some confused votes if both australia and austria reach the final
01:22:03 <oerjan> or is austria one of those countries who've stopped participating
01:22:38 <oerjan> hm nope, the final is actually _in_ austria
01:22:54 <oerjan> definitely some joke potential here
01:24:47 -!- olsner has joined.
01:27:15 <oerjan> ah, they already thought of "what if they win"
01:30:28 -!- adu has joined.
01:34:33 <Taneb> oerjan, if they hadn't I'd vote for Australia just to see them panic
01:34:49 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:38:13 -!- pallokolmio has quit (Ping timeout: 255 seconds).
01:40:23 -!- Lymia has quit (Ping timeout: 245 seconds).
01:51:08 -!- newline1 has joined.
01:51:19 -!- newline1 has left.
02:17:58 <dulla> > let the = 0:11: zipWith (\a b -> a+b+1) (tail the) ((init . tail) $ the) in the
02:18:14 <dulla> > let the = 0:11: zipWith (\a b -> a+b+1) (tail the) ((init . tail) $ the) in take 7 the
02:19:27 <oerjan> please don't use offensive words like that in here
02:19:44 -!- ^v has quit (Read error: Connection reset by peer).
02:20:07 -!- ^v has joined.
02:20:58 <oerjan> i think the (init . tail) $ the is not lazy enough to work with just two elements known
02:21:05 <pikhq> Except in the context of discussion of, say, the works of Mark Twain.
02:21:18 <pikhq> (I guarantee that wasn't in such a context)
02:21:49 <elliott> even then, preferably, at least not in here
02:22:10 <oerjan> are you saying mark twain isn't esoteric
02:22:34 -!- Froox has joined.
02:22:48 <elliott> never the twain shall meet
02:24:50 <oerjan> dulla: if you are going to create an infinite list, then init is redundant anyhow
02:25:12 <dulla> leonardo numbers, yo
02:25:54 -!- Frooxius has quit (Ping timeout: 250 seconds).
02:26:00 <dulla> > let durr 1:1: zipWith (\a b -> a+b+1) durr tail durr in durr
02:26:02 <lambdabot> <hint>:1:54: parse error on input ‘in’
02:26:24 <dulla> > let durr 1:1: zipWith (\a b -> a+b+1) durr (tail durr) in durr
02:26:25 <lambdabot> <hint>:1:56: parse error on input ‘in’
02:26:34 <oerjan> needs work on the punctuation
02:27:00 <dulla> > let durr = 1:1: zipWith (\a b -> a+b+1) durr (tail durr) in durr
02:27:02 <lambdabot> [1,1,3,5,9,15,25,41,67,109,177,287,465,753,1219,1973,3193,5167,8361,13529,21...
02:27:30 <dulla> Meanwhile I disconnect everwhere else
02:28:08 <dulla> If I recall leonardo numbers are okay for heaps
02:29:58 -!- Lymia has joined.
02:31:20 -!- CADD has joined.
02:33:05 <dulla> okay, for smooth sort
02:37:33 <oerjan> game idea: mark twain clones running around in 19th century san francisco, your goal is to keep them from meeting.
02:37:45 <oerjan> emperor norton will be included.
02:39:33 <lambdabot> <hint>:1:1: parse error on input ‘:’
02:39:37 <oerjan> wait, it's not a clone, it's mark twain from a parallel universe where norton _actually_ rules.
02:39:57 <oerjan> dulla: lambdabot is not GHCi
02:40:23 <oerjan> it has :t and :k commands, but not much else
02:40:41 <oerjan> (from GHCi that is. it has many other commands.)
02:40:59 <lambdabot> <hint>:1:1: parse error on input ‘:’
02:41:02 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
02:41:31 <lambdabot> What module? Try @listmodules for some ideas.
02:42:15 <dulla> We need more shadow of the Colossus
02:54:19 <Sgeo> "Because the Academy could not plan ahead, buildings were placed wherever they fit; they were attached to other buildings by a network of tunnels, bridges, and walkways that were rumored to have been the inspiration for a frustrated Professor Dijkstra’s famous pathfinding charm."
03:18:21 <dulla> anyone know about them zippers
03:20:55 -!- nisstyre has quit (Changing host).
03:20:55 -!- nisstyre has joined.
03:43:59 -!- fractal has quit (Ping timeout: 272 seconds).
03:50:56 -!- pallokolmio has joined.
03:51:04 <Sgeo> I found a really.. weird spammer on reddit
03:51:27 <Sgeo> Posts images on a weird domain. Viewed from a desktop UA string, it's legitimate content, viewed from a mobile UA, it's a creepy porn ad
03:56:01 -!- adu has quit (Quit: adu).
03:56:19 <oerjan> huh i guess that was inevitable
03:57:43 -!- ProofTechnique has joined.
04:00:17 -!- nyuszika7h has quit (Read error: Connection reset by peer).
04:01:37 -!- nyuszika7h_ has joined.
04:17:17 -!- bb010g has joined.
04:29:23 -!- Zefpher has joined.
04:32:59 <Zefpher> ?!?! should make lambdabot flip out
04:33:47 <lambdabot> What module? Try @listmodules for some ideas.
04:33:54 <lambdabot> activity base bf check compose dice dict djinn dummy elite eval filter free fresh haddock help hoogle instances irc karma localtime metar more oeis offlineRC pl pointful poll pretty quote search slap source spell system tell ticker todo topic type undo unlambda unmtl version where
04:34:02 <lambdabot> @dice <expr>. Throw random dice. <expr> is of the form 3d6+2.
04:34:12 <lambdabot> activity base bf check compose dice dict djinn dummy elite eval filter free fresh haddock help hoogle instances irc karma localtime metar more oeis offlineRC pl pointful poll pretty quote search slap source spell system tell ticker todo topic type undo unlambda unmtl version where
04:37:27 <Zefpher> Monad structures make me confuse
04:37:44 -!- fractal has joined.
04:39:15 <dulla> something something encapsulating computations
04:39:30 <dulla> each of them has some kind of effect
04:39:54 <dulla> Maybe is the case of failure, Just a | Nothing, the latter being the failure
04:40:02 <Zefpher> ill just go back to making librarys for people
04:40:09 <dulla> Either can be more verbose, but can be used for choice
04:40:22 <dulla> Then there is List for multiple answers
04:40:30 <dulla> State for Mutable or Global States
04:40:31 -!- KingOfKarlsruhe has quit (Ping timeout: 245 seconds).
04:40:59 <dulla> No idea what Reader or Writer do
04:41:17 <dulla> Error throws an exception, which usually fucks a lot of things
04:41:54 -!- jix has quit (Ping timeout: 245 seconds).
04:42:01 <dulla> Perhaps does range data, which is good for probablity
04:42:19 <dulla> And then there's there's the Monte Carlo
04:42:28 <Sgeo> Reader allows for pervasive read-only state. It's the same as passing the same thing into every function
04:42:56 <Sgeo> Writer is for write-only state, such as logging
04:43:19 -!- KingOfKarlsruhe has joined.
04:43:25 -!- naturalog has quit (Ping timeout: 250 seconds).
04:43:35 <dulla> > Monte Carlo is so that people can do arithmetic operations on probablistic distributions
04:43:36 <lambdabot> <hint>:1:35: parse error on input ‘do’
04:43:50 <dulla> or distribution curves
04:43:50 <Sgeo> Either and Error are... kind of the same
04:43:52 -!- jix has joined.
04:43:56 <oerjan> a monad is just an endomorphism in the category of bad analogies hth
04:43:58 <Sgeo> At least when used as a monad
04:44:12 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
04:44:15 <Zefpher> Idk whats going on with my ban times but they exceed any actual universal date
04:44:22 <HackEgo> hth is help received from a hairy toe. It is not at all hambiguitous.
04:44:50 -!- naturalog has joined.
04:45:05 <dulla> curious, irc clients somehow manage multiple network connections
04:45:23 <oerjan> oh wait s/endomorphism/monoid/
04:45:26 <Zefpher> how long is 78e+8000000000000000000 years?
04:45:27 <dulla> Not sure how to deal with that in a functional purview
04:45:58 <dulla> namely because of a very primitive, if any, understanding of juggling state or data
04:46:26 <dulla> the issue of multiple handles comes up again in writing to multiple log files at once
04:46:40 <Zefpher> Hmmm I find any language that requires a drag and drop variable type to very useful
04:46:53 <zzo38> Either x = CodensityAsk (Traced x) and I hoped they would add the corresponding MonadPlus Either instance. Shoudln't it be?
04:46:55 -!- MDude has changed nick to MDream.
04:47:16 <Zefpher> I forgot what is was called
04:47:39 <dulla> makes me think of a visual IDE, Zefpher
04:48:00 <lambdabot> <http://hackage.haskell.org/package/>, also see `revdeps'
04:48:48 <Zefpher> No but they were little tabs on a free white space and you just pulled variable strings to eachother and it made a nice big spider web of variables
04:49:09 <Zefpher> doesn't work anymore though
04:49:26 <dulla> Even Ethereum has that kind of thing already
04:50:29 <oerjan> > Left "hm" `mplus` Left "..." `mplus` Right 42
04:50:56 <oerjan> zzo38: isn't that the MonadPlus?
04:51:16 <lambdabot> ‘infinity’ (imported from Data.Number.Natural),
04:52:02 <Zefpher> Lets make a bot that can list out really big numbers
04:52:40 <Zefpher> who said we would join it here oerjan
04:53:10 <zzo38> > Left "hm" <|> Left "..."
04:53:34 <Zefpher> no but idk I'm just getting really big numbers
04:53:40 <zzo38> It isn't quite the one I wanted although it might do I suppose
04:54:04 <zzo38> It isn't the one achieved from CodensityAsk (Traced x) anyways
04:54:15 <oerjan> zzo38: if you mean the thing that does mappend on the Lefts, i thought that was only Applicative?
04:54:38 <zzo38> > Left "hm" `mplus` Left "..."
04:54:59 <dulla> > Right "a" `mplus` Left "b"
04:55:07 <zzo38> oerjan: Applicative? How is that?
04:55:15 <dulla> > Left "a" `mplus` Right "b"
04:55:24 <dulla> > Left "a" `mplus` Left "b"
04:55:29 <zzo38> I don't see how Applicative would do it.
04:55:34 <dulla> > Right "a" `mplus` Right "b"
04:55:36 <lambdabot> No instance for (GHC.Show.Show a0)
04:55:36 <lambdabot> arising from a use of ‘M211300074112954360827231.show_M2113000741129543608...
04:55:36 <lambdabot> The type variable ‘a0’ is ambiguous
04:55:58 <Zefpher> two rights make a wrong dulla
04:56:01 <dulla> I can't add two Rights
04:56:22 <zzo38> The one that lambdabot seems to use is wrong
04:56:32 <zzo38> It doesn't follow the laws
04:56:40 <dulla> IT DOESN"T FOLLOW THE RULES
04:56:44 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
04:56:51 <oerjan> zzo38: i meant Alternative i guess
04:57:08 <Zefpher> > Right "a" `mplus` left "a"
04:57:09 <lambdabot> Couldn't match type ‘Data.Either.Either GHC.Types.Char d’
04:57:13 <zzo38> The <|> is Alternative and it doesn't do it either
04:57:19 <lambdabot> ["hora","hora","hora","hora","hora","hora","hora","hora","hora","hora","hora...
04:57:27 <zzo38> > empty :: Either String String
04:57:32 <dulla> > concat . repeat $ "hora"
04:57:34 <lambdabot> "horahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahor...
04:57:35 <Zefpher> Why doesn't it follow the laws?!
04:57:51 <zzo38> > empty :: Either [Int] [Int]
04:57:52 <lambdabot> No instance for (Control.Monad.Trans.Error.ErrorList GHC.Types.Int)
04:57:52 <lambdabot> arising from a use of ‘Control.Applicative.empty’
04:57:54 <dulla> > concat . repeat $ "hora"
04:57:56 <lambdabot> "horahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahorahor...
04:58:09 <zzo38> > Left "hm" <|> Left ""
04:58:21 <dulla> It seems right-biased
04:58:22 <zzo38> That violates the laws it is wrong
04:58:30 <dulla> What is associativity
04:58:43 <zzo38> Now I proved it is wrong.
04:58:47 <lambdabot> Couldn't match type ‘Data.Either.Either d b0’
04:59:10 <zzo38> Zefpher: You have to capitalize both "Left" and "Right"
04:59:19 <dulla> > concat . repeat $ "shoah"
04:59:21 <lambdabot> "shoahshoahshoahshoahshoahshoahshoahshoahshoahshoahshoahshoahshoahshoahshoah...
04:59:33 <zzo38> oerjan: Now can you see it is all wrong?
04:59:56 <lambdabot> "ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz"
05:00:21 <dulla> > [minBound..maxBound] :: [Char]
05:00:22 <lambdabot> "\NUL\SOH\STX\ETX\EOT\ENQ\ACK\a\b\t\n\v\f\r\SO\SI\DLE\DC1\DC2\DC3\DC4\NAK\SY...
05:00:40 <lambdabot> Couldn't match type ‘GHC.Types.Char’
05:00:40 <lambdabot> Expected type: Control.Lens.Type.LensLike f s t c0 c0
05:00:40 <dulla> When I put that in ghci it spams me with \n
05:01:00 <dulla> not control characters
05:01:13 <Zefpher> lambdabot is having a dumb
05:01:26 <dulla> it freaks out in the middle of dumping ASCII 256 when I do it in ghci
05:01:31 <dulla> why does it do that
05:01:52 <dulla> why can't it putChar something int he Prelude's Char class
05:02:23 <oerjan> zzo38: i don't know which law you claim it violates
05:02:28 <Zefpher> It just strings random variables out
05:02:58 <zzo38> oerjan: Monoid law
05:03:34 <dulla> fuck the MonadPlus Laws
05:04:01 <dulla> Fuck the MonadZero Laws
05:04:06 <dulla> Fuck the Monad Laws
05:04:12 <dulla> Fuck the Arrow "Laws"
05:04:24 <Zefpher> why can't I just have fun ;--;
05:05:02 <zzo38> I want the Alternative (Either x) and MonadPlus (Either x) instances which are the same one that you would achieve for free as if it was CodensityAsk (Traced x)
05:05:20 <zzo38> Which do follow the monoid laws properly
05:05:27 <Zefpher> raw :: empty should just output empty
05:05:28 <elliott> what are the implementations?
05:05:36 <Zefpher> or maybe I'm just a weirdo
05:06:21 <zzo38> I also made up a proper MonadPlus IO instance but people don't use it and use the wrong one instead.
05:06:59 <zzo38> (and the corresponding Alternative IO)
05:08:41 <oerjan> dulla: GHCi uses your locale settings as default for stdout's allowed characters
05:09:26 <dulla> so if I write to a txt I could see it all
05:10:40 <zzo38> My proper instance used the rightmost nonempty error if all of them are errors, but the wrong one failed to pay attention to whether or not it is empty.
05:11:08 <oerjan> zzo38: there is no requirement that mplus be a monoid operation.
05:11:40 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:12:08 <zzo38> There is the requirement actually.
05:12:51 <zzo38> However the documentation is wrong anyways; it also gives the left zero law and right zero law. Actually the right zero law is wrong (it is true of some instances, but isn't actually a general law) while the left zero law is implied by the monad laws and is therefore redundant.
05:13:11 <zzo38> A lot of people don't believe me that it is implied by the monad laws and is therefore redundant.
05:14:31 -!- FreeFull has quit (Ping timeout: 256 seconds).
05:16:34 <oerjan> dulla: well it also uses it as default for files. you can use hSetEncoding if you want.
05:19:11 <oerjan> i mean that by default ghc uses locale settings for opened text files
05:19:31 <oerjan> but you can set them explicitly
05:21:21 <lambdabot> No instance for (Control.Monad.MonadPlus
05:21:21 <lambdabot> ((->) (a0 -> Data.Maybe.Maybe a0)))
05:21:21 <lambdabot> arising from a use of ‘Control.Monad.mzero’
05:21:38 <lambdabot> No instance for (Control.Monad.MonadPlus ((->) [t0]))
05:21:38 <lambdabot> arising from a use of ‘Control.Monad.mzero’
05:21:45 -!- ProofTechnique has joined.
05:22:36 -!- not^v has joined.
05:23:10 <oerjan> zzo38: i believe you, although i'm a bit fishy on the details, but in mzero >>= f (1) mzero cannot produce an argument for f, so it is probably irrelevant what f is (2) mzero >>= return = mzero is a monad law. i expect you can use the third law to make it more precise?
05:24:22 -!- ProofTechnique has quit (Read error: Connection reset by peer).
05:24:38 <oerjan> dulla: you seem to have some problems with the syntax...
05:25:29 <dulla> I don't know the syntax
05:25:48 -!- fractal has quit (Ping timeout: 245 seconds).
05:26:11 <dulla> There is a concept of willingness
05:26:16 <oerjan> i had the vague impression you knew some haskell but ok
05:26:19 -!- ProofTechnique has joined.
05:26:26 <dulla> But no concept in efficacy towards
05:26:55 <dulla> You can say I would like to dabble
05:27:42 <oerjan> i can say you are making no sense.
05:29:24 <dulla> I get that a lot, also
05:29:51 <dulla> But I manage to eventually understand something?
05:30:04 <dulla> I just need some kind of asshole to lecture me
05:30:42 <dulla> Something about someone else saying something makes me understand
05:32:21 <Zefpher> he's an asshole sometimes and likes to lecture I think
05:33:27 <dulla> Hey, Big Brother oerjan
05:33:52 <dulla> Also what is it with all these fucking germans saying sig heil today
05:34:14 <dulla> So you are saying oerjan is a loli
05:34:19 <dulla> I can get behind that
05:34:21 <Zefpher> It means something about victory
05:34:31 <Zefpher> Dulla don't spam unless you are a bot
05:34:40 <dulla> They call those kinds of women Sea Lions because they like to suck clam?
05:37:02 <oerjan> dulla: i am starting to get tempted to ban you. just so you know.
05:37:15 <elliott> dulla: this is your last warning btw
05:38:19 -!- fractal has joined.
05:40:19 <Zefpher> does the wiki have a clear rule set
05:40:33 <zzo38> You have to post only public domain files to esolang wiki is one thing
05:40:39 <Zefpher> or are people just happening to do #esoteric into their clients
05:41:10 <Zefpher> such grammar /I think that was correct/
05:41:12 <elliott> I think the wiki has rules? maybe?
05:41:24 <oerjan> we have Esolang:Policy
05:41:26 <elliott> thankfully people aren't generally jerks or gross to people on a wiki about esolangs
05:41:37 <elliott> so doing things case-by-case has worked fine so far
05:41:49 <int-e> It's probably one of those hard "common sense" things.
05:42:28 -!- not^v has quit (Ping timeout: 245 seconds).
05:42:34 <elliott> I don't really believe in common sense
05:42:58 <zzo38> No posting any file to esolang wiki which is not public domain; regardless if it is BSD, GPL, ordinary copyright, or otherwise, those aren't public domain, therefore they are all banned. Only public domain is allowed.
05:43:35 <zzo38> CC0 is public domain, so that is OK. SQLite is also public domain.
05:45:29 <zzo38> Those are the rules for posting files on esolang wiki.
05:45:50 <zzo38> (Also you shouldn't post wrong and irrelevant and spam stuff)
05:48:11 <zzo38> Do you like to make up any Magic: the Gathering cards or Pokemon cards?
05:53:31 -!- shikhin_ has quit (Ping timeout: 265 seconds).
05:55:17 <Zefpher> can't I bypass that by making a private domain public for users coming directly from the esolangs wiki
05:55:41 <Zefpher> Which in all sense is very easy
06:00:08 <zzo38> If it is external you could do that
06:00:36 <zzo38> But for files posted on the wiki, no, it has to be public domain for everyone
06:01:19 <elliott> public domain means free of copyright
06:01:33 <int-e> to be clear "public domain" is a term from copyright; it means that everybody is free to use the contents on the wiki for whatever purpose they want.
06:05:09 <int-e> (It's also an oversimplification because most works cannot actually be put in the public domain anymore. So instead CC0 is a perpetual, transferrable, free license, without any strings attached.)
06:23:38 -!- nyuszika7h_ has changed nick to nyuszika7h.
06:42:42 -!- Zefpher has quit (Ping timeout: 252 seconds).
06:47:40 <int-e> Sigh, information density 3.0... http://int-e.eu/~bf3/tmp/density.png
06:50:25 -!- TieSleep has changed nick to TieSoul.
06:50:42 <int-e> bye sleep, hi soul
06:59:10 -!- nyuszika7h has quit (Remote host closed the connection).
06:59:15 -!- MoALTz has quit (Quit: Leaving).
07:00:55 -!- nyuszika7h has joined.
07:08:28 -!- not^v has joined.
07:16:10 -!- FreeFull has joined.
07:18:55 -!- MoALTz has joined.
07:25:39 -!- not^v has quit (Read error: Connection reset by peer).
07:32:21 -!- oerjan has quit (Quit: Zzzoul).
07:45:26 -!- Patashu has joined.
07:50:02 -!- Patashu_ has joined.
07:50:03 -!- Patashu has quit (Disconnected by services).
07:57:43 -!- lambdabot has quit (Remote host closed the connection).
08:02:08 -!- lambdabot has joined.
08:21:36 -!- kallisti has quit (Read error: Connection reset by peer).
08:27:30 -!- arjanb has quit (Quit: bbl).
09:39:32 -!- shikhin has joined.
09:47:03 -!- FreeFull has quit (Ping timeout: 244 seconds).
09:47:26 -!- AnotherTest has joined.
09:51:27 <elliott> int-e: btw, I'm not sure I believe that "most". you're german, right? that's the country typically known for having a bad time with PD
09:51:39 <elliott> at least in the US/UK I think PD is relatively simple/easy
09:51:50 <elliott> CC0 is a PD declaration whenever it can be, i.e. it tries to release all the rights it can
09:51:55 <elliott> (but failing that it gives a license)
09:51:59 <elliott> at least, that's my memory
09:52:16 <int-e> elliott: AFAIU the US has gotten rid of PD recently.
09:52:33 <elliott> that... sounds really unlikely?
09:52:34 <int-e> except for publicly fundet research and publications
09:52:44 <elliott> they like stopping things automatically falling into the PD
09:52:50 <elliott> but that's different from explicitly releasing it
09:53:13 <elliott> I would be *extremely* surprised if they got rid of that
09:53:18 <elliott> especially from not hearing about it
09:53:48 <int-e> I meant, specifically, donating works to the public domain.
09:54:07 <int-e> Not the automatic stuff, and not the expiry of copyright.
09:54:22 <elliott> I'd be very interested in a source, and a recommendation for sources to follow if I want to not miss news like that again, because right now I'm still extremely sceptical :)
09:54:31 <int-e> None of which is really applicable to the wiki (yet?)
09:54:38 <elliott> and googling doesn't turn anything up
09:55:56 <int-e> If I remember I'll do some research tonight. For now, I'll leave you with "The Problem" at http://creativecommons.org/about/cc0
09:56:17 <elliott> right, I know it's tricky in many jurisdictions
09:56:28 <elliott> (I'm the one who switched the wiki over to using CC0)
09:57:24 <int-e> Anyway I recall reading something about this being difficult in the US nowadays, but I'll try finding a source; my memory isn't the most reliable.
09:58:27 <elliott> I'm curious, but no obligation, heh
10:01:36 <int-e> Ultimately I believe it comes down to Article 14 of the Berne Convention, "The author, or after his death the persons or institutions authorized by national legislation, shall, with respect to original works of art and original manuscripts of writers and composers, enjoy the inalienable right to an interest in any sale of the work subsequent to the first transfer by the author of the work."
10:02:21 <int-e> Anyway, back to work...
10:02:35 -!- Phantom_Hoover has joined.
10:03:53 <int-e> (And no, that's not the reference I'm looking for.)
10:43:07 -!- Tritonio has quit (Remote host closed the connection).
10:44:15 -!- Tritonio has joined.
10:53:40 -!- ^v has quit (Read error: Connection reset by peer).
10:54:06 -!- ^v has joined.
11:20:57 -!- boily has joined.
11:48:56 -!- FreeFull has joined.
11:50:50 -!- Patashu_ has quit (Ping timeout: 246 seconds).
12:20:17 -!- boily has quit (Quit: INFORMATIVE CHICKEN).
12:48:48 -!- Tritonio has quit (Remote host closed the connection).
12:49:01 -!- Tritonio has joined.
12:51:14 -!- Tritonio has quit (Remote host closed the connection).
12:52:44 -!- Tritonio has joined.
13:01:02 -!- Tritonio has quit (Remote host closed the connection).
13:11:47 -!- lambdabot has quit (Remote host closed the connection).
13:15:33 -!- shikhin_ has joined.
13:17:13 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
13:18:11 -!- lambdabot has joined.
13:18:50 -!- shikhin has quit (Ping timeout: 264 seconds).
13:22:01 -!- FreeFull has quit (Ping timeout: 255 seconds).
13:36:36 -!- mihow has joined.
13:48:53 -!- FreeFull has joined.
14:14:57 -!- Tritonio has joined.
14:27:38 -!- FreeFull has quit (Ping timeout: 246 seconds).
14:33:18 -!- shikhin_ has changed nick to shikhin.
14:44:38 -!- GeekDude has joined.
14:48:26 -!- Tritonio has quit (Remote host closed the connection).
14:49:28 -!- adu has joined.
14:51:07 -!- ProofTechnique has quit (Ping timeout: 255 seconds).
15:07:08 -!- `^_^v has joined.
15:08:25 -!- ^v has quit (Read error: Connection reset by peer).
15:08:51 -!- ^v has joined.
15:17:26 -!- adu has quit (Quit: adu).
15:21:52 -!- ProofTechnique has joined.
15:28:21 -!- FreeFull has joined.
15:41:03 <int-e> that doesn't look like a valid Fortran to C conversion to me.
15:57:30 -!- Lymia has quit (Remote host closed the connection).
15:58:01 -!- Lymia has joined.
15:59:46 <HackEgo> [wiki] [[AlPhAbEt]] http://esolangs.org/w/index.php?diff=41889&oldid=39837 * 94.176.102.31 * (+0) /* Combined operations */ Simple correction to inaccuracy
16:00:49 -!- nortti has changed nick to minidog.
16:01:00 -!- minidog has changed nick to nortti.
16:07:00 -!- SopaXorzTaker has joined.
16:07:34 -!- SopaXorzTaker has quit (Remote host closed the connection).
16:07:52 -!- SopaXorzTaker has joined.
16:10:02 -!- ^v^v has joined.
16:13:18 -!- ^v has quit (Ping timeout: 245 seconds).
16:17:33 -!- diginet has quit (Quit: diginet has quit!).
16:18:08 -!- diginet has joined.
16:49:32 -!- shikhin has quit (Ping timeout: 250 seconds).
16:56:20 -!- shikhin has joined.
17:08:07 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:15:35 -!- oren has quit (Ping timeout: 246 seconds).
17:23:12 -!- monotone has quit (Ping timeout: 245 seconds).
17:24:43 -!- monotone has joined.
17:35:29 -!- Phantom_Hoover has joined.
17:43:02 -!- mihow has quit (Quit: mihow).
17:54:16 -!- sebbu has quit (Ping timeout: 255 seconds).
17:58:35 -!- ^v^v has changed nick to ^v.
17:59:10 -!- arjanb has joined.
18:04:22 -!- sebbu has joined.
18:04:58 -!- sebbu has quit (Changing host).
18:04:59 -!- sebbu has joined.
18:13:58 -!- MDream has changed nick to MDude.
18:14:07 -!- adu has joined.
18:32:31 -!- Froox has quit (Ping timeout: 255 seconds).
18:40:52 -!- ais523 has joined.
18:43:14 -!- hjulle has joined.
18:47:29 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:56:47 -!- Frooxius has joined.
19:12:36 -!- ais523 has quit (Read error: Connection reset by peer).
19:12:50 -!- ais523 has joined.
19:13:33 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
19:15:59 -!- shikhin_ has joined.
19:18:50 -!- shikhin has quit (Ping timeout: 246 seconds).
19:20:22 -!- ais523 has quit.
19:21:42 -!- shikhin_ has changed nick to shikhin.
19:29:53 -!- mihow has joined.
19:34:17 -!- ^v has quit (Read error: Connection reset by peer).
19:34:43 -!- ^v has joined.
20:02:10 -!- Patashu has joined.
20:14:03 -!- AnotherTest has quit (Ping timeout: 264 seconds).
20:23:31 -!- shift_k3y has joined.
20:24:59 -!- Patashu has quit (Ping timeout: 252 seconds).
20:33:37 -!- shift_k3y has left.
20:40:30 -!- nycs has joined.
20:42:29 -!- `^_^v has quit (Ping timeout: 246 seconds).
20:56:45 -!- bb010g has joined.
21:32:49 -!- Frooxius has quit (Quit: *bubbles away*).
21:49:10 -!- Frooxius has joined.
21:58:43 -!- MDude has quit (Ping timeout: 245 seconds).
22:03:12 -!- naturalog has quit (Ping timeout: 245 seconds).
22:04:09 -!- ais523 has joined.
22:05:00 -!- naturalog has joined.
22:11:03 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
22:30:52 -!- MDude has joined.
22:56:02 -!- ais523 has quit.
22:56:02 -!- callforjudgement has joined.
22:56:08 -!- callforjudgement has changed nick to ais523.
23:09:47 -!- nycs has quit (Quit: This computer has gone to sleep).
23:15:50 -!- mihow has quit (Quit: mihow).
23:21:19 -!- Phantom_Hoover has joined.
23:21:25 -!- oerjan has joined.
23:22:18 -!- spiette has quit (Quit: :qa!).
23:35:38 -!- adu has quit (Quit: adu).
23:41:40 -!- ^v has quit (Read error: Connection reset by peer).
23:42:05 -!- ^v has joined.
23:50:29 -!- Frooxius has quit (Quit: *bubbles away*).
23:54:28 -!- Frooxius has joined.
00:00:38 -!- Froox has joined.
00:00:54 -!- adu has joined.
00:01:38 -!- Froo has joined.
00:03:41 -!- boily has joined.
00:04:36 -!- Frooxius has quit (Ping timeout: 250 seconds).
00:05:25 -!- Tritonio has joined.
00:05:26 -!- Froox has quit (Ping timeout: 246 seconds).
00:17:29 -!- MDude has quit (Read error: Connection reset by peer).
00:20:18 <oerjan> wednesday's at mezzacotta are starting to get crowded
00:22:20 <oerjan> also, the two new comics haven't been added to the sidebar yet
00:24:43 * boily has trouble with weekdays...
00:24:47 <zzo38> I found a public domain JSON implemention in C called PDJSON, therefore I am making the SQLite interface for PDJSON so that you can import data from JSON into SQLite. (Currently is no export functions but is it could be added later on if someone wants to export JSON in this way.)
00:24:58 <oerjan> the *- means what's following should be removed hth
00:26:35 <oerjan> apparently høily is an existing norwegian place name
00:27:00 <pikhq> If PDJSON is the one I'm thinking of, that's quite a good library.;
00:27:40 <oerjan> if it isn't, it's a good mimicry
00:28:06 <zzo38> pikhq: Have you used that one?
00:29:55 -!- Sprocklem has joined.
00:32:47 <boily> oerjan: there's at least http://www.yelp.com/biz/industriteam-%C3%B8st-tomter . not only is it a mimicry, but an authentic mimicry!
00:34:11 <oerjan> boily: i was actually responding to pikhq but all's well that ends well
00:35:08 <boily> pikhq: pikhelloq. sorry for diverting oerjan.
00:36:39 <pikhq> zzo38: No, but I've read it. :)
00:37:18 <zzo38> Have you used other JSON libraries?
00:41:13 -!- Lymia has quit (Ping timeout: 245 seconds).
00:52:48 -!- MDude has joined.
01:15:48 -!- shikhin_ has joined.
01:17:27 -!- ProofTechnique has joined.
01:18:43 -!- shikhin has quit (Ping timeout: 245 seconds).
01:23:28 -!- dianne has quit (Ping timeout: 250 seconds).
01:25:26 -!- dianne has joined.
01:36:18 -!- tswett has quit (Quit: tswett).
01:36:28 -!- Warrigal has joined.
01:36:35 -!- Warrigal has changed nick to tswett.
01:39:30 -!- oren has joined.
01:57:04 -!- boily has quit (Quit: ENDOMORPHIC CHICKEN).
02:09:57 -!- skj3gg has joined.
02:11:05 -!- skj3gg has quit (Client Quit).
02:11:59 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
02:13:14 -!- skj3gg has joined.
02:17:58 -!- arjanb has quit (Ping timeout: 246 seconds).
02:32:17 <zzo38> I found a bug in PDJSON that empty arrays and empty objects don't work. I will fix that now.
02:34:15 -!- Sprocklem has quit (Ping timeout: 250 seconds).
02:42:49 -!- teuchter has joined.
02:44:35 -!- skj3gg has quit (Quit: ZZZzzz…).
02:44:57 -!- ocharles__ has joined.
02:47:13 -!- zzo38 has quit (Disconnected by services).
02:47:18 -!- zzo38 has joined.
02:47:57 -!- ski_ has joined.
02:48:04 <zzo38> After fixing that bug, now the SQL interface to PDJSON is working OK
02:51:31 -!- trnv2 has joined.
02:52:10 <Taneb> The clash that the York JavaScript meetup group has with the York Haskell meetup group is getting annoying...
02:52:17 -!- lambdabot has quit (*.net *.split).
02:52:17 -!- choochter has quit (*.net *.split).
02:52:17 -!- ocharles_ has quit (*.net *.split).
02:52:17 -!- trn has quit (*.net *.split).
02:52:17 -!- ski has quit (*.net *.split).
02:52:59 -!- ocharles__ has changed nick to ocharles_.
02:53:36 -!- Zefpher has joined.
02:57:20 <oerjan> Taneb: you found someone who wants to go to both?
02:57:41 <Taneb> oerjan, yes, also we want to use the same venue at the same time
02:57:56 <Taneb> Which does have a natural solution
02:58:03 -!- trnv2 has changed nick to trn.
02:58:14 <oerjan> ah that seems to be a problem
02:58:22 -!- lambdabot has joined.
02:59:41 <Taneb> oerjan, somehow we both decided on "Last Thursday of the month"
03:00:02 <Taneb> Zefpher, York Haskell meetup group and York JavaScript meetup group
03:00:23 <oerjan> it's a small town on mars
03:00:31 <oerjan> near the capital of O'Wobble
03:00:48 <Taneb> York is a city in the north of England
03:00:49 <Zefpher> I don't have time for geography
03:00:54 <Taneb> It's where New York is named for
03:01:04 <Zefpher> I live in Washington state
03:01:32 <Zefpher> Ill just call my aunt who lives in London for like $2000
03:01:52 <oerjan> i thought phone calls had got cheaper than that
03:02:41 <Zefpher> I will call my aunt For a $2000 Plane ticket
03:03:28 <oerjan> you can have my alarm clock, i changed the battery and the ticking got so annoying i had to take it out again
03:04:35 <Zefpher> I can't be in in heavily polluted areas my sensory issues will make my chromesthesia flip out
03:04:44 <Taneb> It's quite a small city
03:04:52 <Taneb> Sometimes there is a smell of burnt sugar
03:05:14 <oerjan> <Zefpher> Be serious <-- just testing y'all for obscure references hth
03:05:14 <Taneb> There is a chocolate and sweets factory
03:06:35 <pikhq> Is anything new in York?
03:06:43 <pikhq> Or did they export it all to New York?
03:07:04 <Taneb> pikhq, we're making a New York Haskell Compiler
03:09:28 <Zefpher> Ill just be in the background
03:09:51 <pikhq> I'll just keep drinkin' my coffee stout.
03:10:08 <Zefpher> If there are any fires /it wasn't me/
03:11:33 <Zefpher> Alas I try my best to be weird
03:11:50 <Zefpher> and you are all old So I would very much stick out
03:14:55 <pikhq> Meh, age is an illusion.
03:15:12 <pikhq> Though the beards, probably not.
03:17:00 <Taneb> Zefpher, I am not old
03:18:50 <pikhq> On a scale from 1 to oerjan how old are you Taneb?
03:19:53 <pikhq> It's an oatmeal stout with coffee.
03:20:03 <pikhq> And it is delicious.
03:20:39 <pikhq> oerjan is older than the stars.
03:20:49 <pikhq> oerjan: Not really.
03:20:51 <Taneb> Zefpher, that was a typo, I'm 20
03:20:55 <pikhq> Just profoundly tasty.
03:21:06 <Zefpher> Sometimes I can trick adults into thinking I'm an adult
03:21:40 <oerjan> pikhq: i mean, it's two potential addictions in one
03:22:24 <Zefpher> I was once addicted to meth
03:22:41 <Zefpher> Or well I was none of the others were |_|
03:22:55 <oerjan> are you trying to trick us into thinking you're adult again
03:23:18 <oerjan> just general trickery, check
03:24:08 <pikhq> I advise against meth.
03:24:23 <pikhq> Even if you have medical cause for amphetamines there's better ones.
03:25:00 <Zefpher> To late pikhq that era is over for me
03:25:11 <Zefpher> unless your advising my grandma
03:25:28 <oerjan> i can quit caffeine any time i want, just give me a couple weeks
03:25:57 <pikhq> IRC on the other hand.
03:27:31 <Taneb> I seem to have misplaced my tie
03:28:39 <Taneb> I have had a good track record for not burning my house down this year
03:28:43 <Zefpher> I need to go give 30 moneys to my mothwr
03:28:44 <Taneb> And I don't want to lose it
03:29:11 <Zefpher> Mr Ink: http://youtu.be/K2WazFk2Cwg
03:32:32 <Zefpher> In America its technically required to go to college if you want supreme mastery over that subject
03:37:03 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
03:37:37 <oerjan> girl genius: ah the bears have arrived
03:51:36 -!- chaosagent has joined.
03:52:21 -!- Lymia has joined.
04:17:43 <oren> York is also the university in Toronto that my dad worksfor
04:18:58 -!- ProofTechnique has joined.
04:31:37 -!- Eolus has joined.
04:32:00 -!- Eolus has changed nick to Guest85091.
04:33:03 -!- Zefpher has quit (Ping timeout: 256 seconds).
04:41:27 -!- hjulle has quit (Ping timeout: 252 seconds).
04:46:01 -!- Guest85091 has changed nick to Zefpher.
04:52:14 <Zefpher> > Right "hm" <|> Left "..."
04:53:29 -!- shikhin_ has quit (Ping timeout: 246 seconds).
04:59:37 <lambdabot> <hint>:1:1: parse error on input ‘|’
04:59:59 <Zefpher> Now tell me what does | stand for in haskell
05:00:14 <Zefpher> and why is it bordered by greater than and less than signs
05:03:07 <oren> @bf ++++++++++++++++++++++++++++++++++.+.+.+.
05:03:15 <oren> That is what it does
05:03:28 <oren> it interpretsbrainfuck
05:09:06 <oerjan> Zefpher: | has several different uses, but <|> is a completely different operator - haskell doesn't have a fixed set of operators so any sequence of operator characters doesn't get split up into smaller ones.
05:09:43 <lambdabot> Alternative f => f a -> f a -> f a
05:09:52 <Zefpher> so what does [| ] do for stuff
05:10:06 <Zefpher> it breaks all of me program
05:10:20 <oerjan> Zefpher: you probably mean a list comprehension
05:10:34 <oerjan> > [ x*x | x <- [1..10] ]
05:11:01 <Zefpher> and does -> point towards different variables¿
05:11:29 <Zefpher> Oerjan teach me the haskells
05:11:44 <oerjan> > case Just "testing" of Nothing -> "nope" ; Just something -> something
05:12:04 * Zefpher finds money and offers it to oerjan
05:13:22 <oerjan> actually, i don't think -> usually points to variables, but away from them (or away from a pattern)
05:14:29 <oerjan> <- and -> are essentially keywords
05:15:01 <oerjan> and there's usually a pattern to the left of them
05:15:11 <oerjan> (a variable is the simplest kind of pattern)
05:15:38 <oerjan> but other than that, they're used in several different contexts
05:15:58 <oerjan> coppro: shocking, isn't it?
05:16:12 <coppro> xdg-open determined that the best way to open a text file was to start x-terminal-emulator and run vim inside it?
05:16:52 <oerjan> curiously, i have long since resigned to setting IE to open haskell files in vim
05:17:08 <oerjan> it's the least annoying thing that works when it won't display in-browser
05:17:16 <lambdabot> data Bool = False | True deriving (Eq, Ord)
05:17:29 <dulla> > [ x | x <- "jeys hush", elem x "suej"]
05:20:11 <oerjan> | is also a keyword btw
05:20:14 <dulla> All I hear is that one should use filters, and maps instead of list comprehensions
05:20:44 <oerjan> dulla: nah sometimes one is better, sometimes the other
05:21:09 <dulla> Sometimes you feel lazy
05:21:26 <oerjan> > filter (`elem` "suej") "jeys hush"
05:21:58 <HMC_A> in haskell is list comprehension primitive or just syntactic sugar?
05:22:23 <oerjan> @undo [ x | x <- "jeys hush", elem x "suej"]
05:22:23 <lambdabot> concatMap (\ x -> if elem x "suej" then [x] else []) "jeys hush"
05:23:10 <HMC_A> so you can't really use filters/maps "instead" :-)
05:23:26 <dulla> Also, do you get angry about the "special syntax" [] ?
05:23:57 <oerjan> well the idea is you can get a better point-free definition without comprehensions, when that works nicely.
05:24:12 <HMC_A> well that is an idea.
05:24:50 <coppro> oerjan: yeah I'm surprised it actually started a terminal emulator though
05:24:53 <coppro> rather than running gvim
05:25:27 <dulla> > let fil as = filter (`elem` as) in fil "suej" "jeys hush"
05:26:06 <oerjan> > let fil = filter . flip elem in fil "suej" "jeys hush"
05:26:36 <HMC_A> now i want to go implement a pointless topology using just list comprehensions simply to rile people. XD
05:27:09 <dulla> ah, I see what the flip does
05:27:27 <oerjan> > intersection "jeys hush" "suej"
05:27:28 <lambdabot> ‘IM.intersection’ (imported from Data.IntMap),
05:27:48 <oerjan> > Data.List.intersection "jeys hush" "suej"
05:27:49 <lambdabot> Not in scope: ‘Data.List.intersection’
05:27:49 <lambdabot> ‘Data.List.intersect’ (imported from Data.List),
05:27:56 <dulla> Isn't there a list difference operation?
05:28:00 <oerjan> > intersect "jeys hush" "suej"
05:28:14 <dulla> one that's a symbol
05:29:01 <dulla> > "jeys hush" \\ "y hh"
05:29:35 <oerjan> i think using them on non-sets is not originally intended
05:30:28 <dulla> They could be used for a very crappy cipher
05:31:34 <oerjan> hm actually the report seems to define \\ on non-sets well enough
05:35:51 <dulla> > intersect "test" "t"
05:43:44 <zzo38> I get angry about the "special syntax" because I believe it ought to be made as macros instead
05:46:35 <Sgeo> Remind me never to use cloud to butt
05:46:36 <Sgeo> https://www.reddit.com/r/TagPro/comments/2vlkzp/note_have_the_cloud_to_butt_extension_disabled/
05:46:57 <Sgeo> Why doesn't it search/replace just text nodes in HTML?
05:47:10 <Sgeo> And... hmm, impossible to tell whether strings in Javascript need to be replaced
05:55:25 <oren> Sgeo: Javascript itself needs to be replaced hth
06:00:09 <Zefpher> javascript type tables are complete shit
06:00:22 <Zefpher> deletes javascript off the internet
06:09:57 <oren> Does haskell have a type for unordered sets? Most languages don't.
06:11:42 <oerjan> there's an unordered-containers library
06:12:30 <oerjan> that's actually in the usual containers library
06:12:48 <oren> See I realized that an unordered set can be implemented to be faster than using a vector like thing
06:13:28 <oren> And in my use case (bullets in a 2d game) I don't care what order they are processed in
06:13:30 <elliott> tbf those aren't unordered so much as very ordered
06:14:29 * oerjan hasn't really looked at unordered-containers, but things he heard it was getting more official
06:14:42 <elliott> well unordered-containers isn't that ordered
06:14:45 <int-e> . o O ( ricocheting bullets )
06:14:58 <elliott> but my joke works for Data.Set.Set
06:15:47 <oren> Anyway, the problem is C++ has no real unordered set type. std::unordered_set is actually a hash table
06:16:00 <oerjan> int-e: THE BEARS HAVE ARRIVED
06:16:04 <elliott> what do you want from this type anyway
06:16:09 <oren> I want a type with three operations
06:16:44 <oren> add(set, thing), remove(set, current_index), iterate(set,function)
06:17:05 <oren> So add doesn't add the thing in any particular place
06:17:25 <oren> and iterate doesn't iterate over in any particular order
06:17:51 <oren> but during iteration, i need to be able to remove the current bullet from the set
06:19:14 <oerjan> oren: the problem is, without a known place to find it, remove() is going to be horribly slow
06:19:26 <int-e> elliott: https://en.wikipedia.org/wiki/Wikipedia:Granting_work_into_the_public_domain#Legal_basis_of_copyright_in_the_United_States seems a better source of the situation of donating works to the public domain in the US... the conclusion seems to be that it *ought* to be possible but it's hard to make an unequivocal statement to that effect. So there's a cloud of uncertainty and doubt around the topic.
06:20:00 <oren> oerjan: right, but ideally remove would only be callable from within an iteration
06:20:32 <oren> And only callable on the current bullet
06:20:42 <oren> I think that can make it fast
06:21:13 <int-e> oerjan: uh-oh. do they eat metal? *risks a look at the comic*
06:21:15 <oerjan> plausible. you could even use a list then.
06:21:51 <int-e> Oh, it seems friendly. Ominous.
06:22:30 <oerjan> i expect zeeta and violetta to freak out first next panel
06:23:18 <int-e> Oerjan made a typo!
06:23:30 <Zefpher> [ y | y <- "whomykissrobfistersfightpowertopick", elem y "mspiss"]
06:23:30 <j-bot> Zefpher: 'y' | 'y' < -"_ _ _"_ _ _ elem 'y'"_ _ _"_ _ _
06:23:31 <oerjan> there should be an h there, right?
06:23:45 <oerjan> i'm just not sure _where_...
06:24:23 <Zefpher> I look forward to seeing you oerjan
06:24:59 <Zefpher> > [ y | y <- "whomykissrobfistersfightpowertopick", elem y "mspiss"]
06:25:12 * int-e still doesn't know what Zefpher and friends (like the one with L who shall not be named) are doing here.
06:25:36 <Zefpher> I could be rude and tell you to die in a fire
06:25:44 <int-e> You could do that.
06:25:53 <dulla> I'm here to pillage, and relish the lamentation of your women
06:26:13 <Zefpher> And I wont do that to int he's a funny
06:26:22 <int-e> You could try living up to that claim. Perhaps I'd not be so nasty either?
06:27:04 <dulla> needs more DanMachi
06:27:34 <int-e> "I used to be indecisive, but now I'm not so sure."
06:27:41 <Zefpher> Meh I'm only a 16 year old with DID and ptsd and aspds
06:27:57 <Zefpher> Int e must have children by now
06:28:24 <int-e> Fortunately for my children, I don't have any :P
06:29:02 <Zefpher> Ill try to be Nicer than my current level
06:29:13 <Zefpher> I'm not good an socializing with older folks
06:29:39 <oren> Hey oerjan, what did the scouter say about his nice level?
06:29:40 <Zefpher> if you say something bad about me I'm not afraid to hit a senior citizen
06:30:47 <Zefpher> I usually spew out a full front of hate and anger during febuary because its the only time I'm reminded of the incident that ruined my entire life
06:31:20 <Zefpher> also Sorry if I sound like I like to burn houses down
06:31:38 <Zefpher> I also don't have enough money to do that
06:31:45 <oren> OR maybe I just like cooking bacon at way to high a heat
06:32:03 <oerjan> oren: i'm too tired to reverse engineer puns hth
06:33:11 <Zefpher> Sorry for implying you should die in a nuclear blast cloud int-e
06:33:13 <int-e> oerjan: s/to/too/; no pun.
06:33:52 <int-e> (I think. Maybe it's a pun submarine)
06:34:37 <int-e> Or perhaps I missed something that oren wrote.
06:35:51 <oerjan> int-e: perhaps you were looking at the wrong line.
06:36:30 <int-e> oerjan: still it's not a pun; google suggests a quote from Dragon Ball Z
06:38:09 <oerjan> Zefpher: that _still_ means we can ban you until march 1 without feeling bad about it hth
06:39:09 <Zefpher> You don't talk to me for awhile and I will work on my skills of friendly Ness
06:39:58 -!- oerjan has quit (Quit: Let's try that ZZZZZZZ).
06:40:59 <Zefpher> What's the cmd that turns msgs off for some users
06:41:01 <oren> 光る雲を突き抜けフライアウェイ
06:41:30 <Zefpher> That third one looks like a tower
06:41:42 <oren> it means claud
06:42:00 <lifthrasiir> (a loan version of "flying away" is not a common word, I guess)
06:42:45 <oren> Japanese songs have lots of english in them, usually bad english
06:44:24 <oren> but it usually makes sense with a back-translation
06:47:35 <oren> Anyway the song i quoted is the original opening for dragon ball
06:50:36 <oren> Interestingly the fact they don't focus on correct grammar allows the lyrics to more easily fit the tune than in western music
06:55:14 -!- quintopia has quit (Ping timeout: 265 seconds).
06:56:03 -!- quintopia has joined.
06:58:08 <oren> this pronounciation is basically inexcusable tho: https://www.youtube.com/watch?v=8u0EEjNJNQE
07:06:46 -!- kapil__ has joined.
07:12:28 -!- weissschloss has quit (Remote host closed the connection).
07:15:58 -!- weissschloss has joined.
07:24:24 <zzo38> I looked at the "Empty Room Psych" in All The Tropes, and remind me of some computer game I once made (I don't entirely remember and don't have it now), where there is one room that contains only text that says "THERE IS NOTHING IN THIS ROOM" (I suppose it is a bit like pages of a book that says this page is intentionally left blank). However, the text blocks the door from opening.
07:24:33 <zzo38> So you can't actually enter the room.
07:31:12 -!- MDude has changed nick to MDream.
07:35:53 -!- Patashu has joined.
07:40:42 <zzo38> This is the SQL extension of PDJSON: http://sprunge.us/DXie Do you think the documentation is OK to you?
07:41:11 -!- Patashu has quit (Remote host closed the connection).
07:41:23 -!- Patashu has joined.
07:44:41 <zzo38> Esolang wiki says that Taktentus is "an simple language with equal". Well, just in general, it doesn't get described very well.
07:45:04 -!- adu has quit (Quit: adu).
07:45:05 <zzo38> (Also seems to lack flow-controls)
07:48:02 <MDream> I think it means all operations use the equals sign for assignment.
07:48:19 -!- teuchter has quit (Changing host).
07:48:19 -!- teuchter has joined.
07:48:21 -!- ocharles_ has quit (Changing host).
07:48:21 -!- ocharles_ has joined.
07:48:45 <oren> there should be a language where = is move notcopy
07:48:47 <MDream> And it looks like _ is the instruction pointe.
07:49:32 <zzo38> O, if _ is the instruction pointers then that can be use for flow-controls I suppose. It doesn't make it very clear (at least in English isn't clear).
07:51:53 <MDream> I agree on the English.
07:53:37 <MDream> Putting the source page through an auto-translator confirms my suspicion.
07:54:36 -!- adu has joined.
08:19:11 <b_jonas> zzo38: yes, I think there's such a language where _ is the instr pointer and can be used for flow control
08:21:02 <b_jonas> in the W language here http://www.vttoth.com/CMS/index.php/projects/49
08:21:09 <b_jonas> $ is the instruction pointer and can be used for flow control
08:41:05 -!- Zefpher has quit (Ping timeout: 265 seconds).
09:13:15 -!- skarn has quit (Killed (orwell.freenode.net (Nickname regained by services))).
09:13:31 -!- skarn_ has joined.
09:37:02 -!- chaosagent has quit (Ping timeout: 250 seconds).
09:42:50 -!- adu has quit (Quit: adu).
09:43:26 -!- J_Arcane has quit (Read error: Connection reset by peer).
10:09:22 -!- J_Arcane has joined.
10:31:46 -!- Tritonio has quit (Ping timeout: 252 seconds).
10:47:39 <mroman> foo -> (bind #(0 1) #(T:function T:argument) (eval S:function S:argument))
10:47:40 <mroman> main -> (putstrln (show (foo (atom (add $0 1)) 9)))
10:47:58 <mroman> bind is a special function that rewrites the expression
10:48:20 <mroman> so bind takes a list of numbers (the arguments) and a list of symbol names and an expression
10:48:37 <mroman> and then rewrites all symbols in the expression to the corresponding param
10:48:43 <mroman> so it rewrites to (eval $0 $1)
10:51:48 -!- Tritonio has joined.
10:52:37 -!- Phantom_Hoover has joined.
10:54:24 <mroman> http://codepad.org/cY4nDxU7
11:12:22 -!- Tritonio has quit (Remote host closed the connection).
11:13:56 -!- Tritonio has joined.
11:23:18 -!- boily has joined.
11:23:55 -!- ais523 has quit.
11:23:58 -!- callforjudgement has joined.
11:27:25 -!- rodgort has quit (Read error: Connection reset by peer).
11:35:16 -!- rodgort has joined.
11:59:59 -!- callforjudgement has quit (Read error: Connection reset by peer).
12:00:14 -!- callforjudgement has joined.
12:05:31 -!- ^v has quit (Read error: Connection reset by peer).
12:05:58 -!- ^v has joined.
12:06:57 -!- Tritonio has quit (Remote host closed the connection).
12:07:11 -!- Tritonio has joined.
12:09:29 -!- Tritonio has quit (Remote host closed the connection).
12:10:13 -!- callforjudgement has quit.
12:11:57 -!- Tritonio has joined.
12:14:48 -!- Patashu has quit (Ping timeout: 252 seconds).
12:17:52 -!- Tritonio has quit (Remote host closed the connection).
12:18:54 -!- Tritonio has joined.
12:20:36 -!- boily has quit (Quit: POPULATED CHICKEN).
12:21:21 <mroman> although this bind is inefficient for recursion
12:21:30 <mroman> because the rewriting is done each time
12:21:47 <mroman> but you can make a static run over binds one time so...
12:21:51 <mroman> unless it's a dynamic bind
12:22:02 <mroman> but I could write a checker that rewrites static binds at start-up
12:25:44 -!- Tritonio has quit (Remote host closed the connection).
12:26:02 -!- Tritonio has joined.
12:32:05 -!- Tritonio has quit (Remote host closed the connection).
12:32:23 -!- Tritonio has joined.
12:37:02 -!- Tritonio has quit (Remote host closed the connection).
12:37:20 -!- Tritonio has joined.
12:40:37 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
12:46:00 -!- Tritonio has quit (Remote host closed the connection).
12:46:18 -!- Tritonio has joined.
12:51:43 -!- Tritonio has quit (Remote host closed the connection).
12:51:52 -!- Tritonio has joined.
12:54:20 -!- Tritonio has quit (Remote host closed the connection).
12:54:31 -!- Tritonio has joined.
12:55:03 -!- Tritonio has quit (Remote host closed the connection).
12:55:17 -!- Tritonio has joined.
12:55:55 -!- Tritonio has quit (Remote host closed the connection).
12:56:07 -!- Tritonio has joined.
12:56:51 -!- Tritonio has quit (Remote host closed the connection).
12:57:04 -!- Tritonio has joined.
12:57:53 -!- Tritonio has quit (Remote host closed the connection).
12:58:04 -!- Tritonio has joined.
13:06:48 -!- Tritonio has quit (Remote host closed the connection).
13:06:58 -!- Tritonio has joined.
13:09:05 -!- Tritonio has quit (Remote host closed the connection).
13:09:16 -!- Tritonio has joined.
13:10:28 -!- Tritonio has quit (Remote host closed the connection).
13:10:39 -!- Tritonio has joined.
13:19:31 -!- CADD has quit (Read error: Connection reset by peer).
13:48:09 -!- Tritonio has quit (Remote host closed the connection).
13:59:52 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=41890&oldid=41888 * 46.113.205.53 * (+31) /* External resources */
14:07:42 -!- ski_ has quit (Remote host closed the connection).
14:18:24 <mroman> how do I catch every exception?
14:22:06 <quintopia> wrap the enter program in a giant try
14:22:50 <mroman> handle (\_ -> print 0) (dostuff)
14:22:51 <b_jonas> mroman: fork-exec, do the cleanup in the parent process
14:22:59 <mroman> also catch doesn't work
14:23:02 <mroman> and try doesn't as well
14:23:34 <mroman> it works with (\(e :: IOException) -> print 0)
14:23:38 <mroman> but not with (\_ -> print 0)
14:23:57 <mroman> No instance for (Exception e0)
14:24:17 <mroman> (in other words: The code from real world haskell results in a type error for me)
14:25:16 -!- ProofTechnique has joined.
14:26:02 <mroman> There's no "Exception"
14:26:05 <mroman> Expecting one more argument to ‘Exception’ Expected a type, but ‘Exception’ has kind ‘* -> Constraint’
14:26:56 <mroman> SomeException might do it
14:29:36 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
14:38:11 -!- hjulle has joined.
14:39:55 <dulla> I recall a blog post talking about three, four methods to do errors
14:40:04 <dulla> I have about 9000 submerged tabs though
14:40:57 <mroman> SomeException works fine for now
14:41:05 <mroman> main -> (try (putstrln (show (error))) (putstrln :(Nooooo!)))
14:53:56 -!- oren has quit (Ping timeout: 252 seconds).
14:54:52 -!- adu has joined.
15:04:15 -!- nycs has joined.
15:05:56 -!- SopaXorzTaker has joined.
15:10:54 -!- oren has joined.
15:11:38 -!- nycs has changed nick to `^_^v.
15:21:28 -!- adu has quit (Quit: adu).
15:22:05 -!- Tritonio has joined.
15:25:42 <J_Arcane> https://twitter.com/HaskellCEO/status/565891621406138369
15:40:36 -!- skj3gg has joined.
15:41:06 <HackEgo> [wiki] [[Redstone]] N http://esolangs.org/w/index.php?oldid=41891 * 206.15.236.252 * (+375) Created page with " Redstone is used for electronics in the game Minecraft. (see http://minecraft.gamepedia.com/Redstone) Although not intended to be a programming language, a compiler is techni..."
15:41:30 <oren> And what the FUCK is with this constant talk of "purity"? I suppose "impurity" means ACTUALLY hitting our quarterly targets?!?! #FML
15:41:55 -!- skj3gg has quit (Client Quit).
15:43:05 <oren> this guy is hilarious in a totally unfair way
15:50:20 -!- perrier has quit (Read error: Connection reset by peer).
15:51:32 -!- perrier has joined.
15:55:36 -!- perrier has quit (Remote host closed the connection).
15:56:00 -!- skj3gg has joined.
15:56:23 -!- adu has joined.
15:56:48 -!- perrier has joined.
16:01:33 -!- SopaXorzTaker has quit (Ping timeout: 250 seconds).
16:07:13 -!- hjulle has quit (Ping timeout: 256 seconds).
16:09:14 <J_Arcane> mroman: oren: I think its a parody account, but I've often mused on that very sentiment. XD Wondering if FP/Lisps never took off because to clueless managers it doesn't 'look like work'.
16:14:11 -!- SopaXorzTaker has joined.
16:30:13 -!- perrier has quit (Remote host closed the connection).
16:31:26 -!- perrier has joined.
16:33:28 -!- perrier has quit (Read error: Connection reset by peer).
16:34:40 -!- perrier has joined.
16:37:00 -!- perrier has quit (Remote host closed the connection).
16:38:13 -!- perrier has joined.
16:38:55 -!- MDream has changed nick to MDude.
16:44:28 -!- perrier has quit (Remote host closed the connection).
16:45:40 -!- perrier has joined.
16:47:28 -!- Lymia has quit (Ping timeout: 245 seconds).
16:48:50 -!- AnotherTest has joined.
16:49:11 -!- Lymia has joined.
16:51:29 -!- heroux has quit (Ping timeout: 245 seconds).
17:00:31 -!- skj3gg has quit (Quit: ZZZzzz…).
17:01:38 -!- skj3gg has joined.
17:01:39 <HackEgo> [wiki] [[Ook!]] http://esolangs.org/w/index.php?diff=41892&oldid=41107 * 74.73.232.36 * (+98) /* External resources */ Add link for Terry Pratchett wiki
17:16:17 -!- skj3gg has quit (Quit: ZZZzzz…).
17:18:11 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:18:22 <HackEgo> [wiki] [[Esme]] http://esolangs.org/w/index.php?diff=41893&oldid=13230 * 24.104.140.55 * (+0) /* Examples */
17:24:34 -!- skj3gg has joined.
17:27:54 -!- mrohman has joined.
17:29:09 <mrohman> This android client is weird
17:29:35 <int-e> fungot's still on the move
17:31:07 <int-e> And, unfortunately, nontrivial to get running. (At least I couldn't get the version from https://github.com/fis/fungot to do much more than loop forever. But I don't know Funge.)
17:31:26 <mrohman> Oh. Portraitmode is better
17:32:24 <mrohman> Landscape the keyboard needs the whole screen
17:33:36 <fizzie> int-e: Other people have succeeded in running it.
17:33:56 <fizzie> int-e: But you do need to start it with the loader.
17:34:05 <fizzie> (The main "fungot.b98" is not a standalone program.)
17:34:23 <fizzie> At any rate, it's probably not worth it unless you had the models.
17:34:24 <int-e> fizzie: I did, but it hangs trying to parse the non-existent fungot.dat file.
17:34:43 <fizzie> That's right there in the instructions.
17:34:48 <fizzie> "It might be necessary to create the file data/fungot.dat and put ten empty lines there."
17:35:16 <fizzie> (I believe in robust code.)
17:35:51 <mrohman> I could write an irc client in my lisp dialect. Hm...
17:36:33 <fizzie> As for fungot, its estimated time of arrival is next week, but I don't have internet in the new place yet, so it won't be getting online.
17:36:46 <fizzie> I think I was quoted "10-12 business days" for that.
17:37:51 <int-e> fizzie: I actually tried that (fungot.dat containing 10 newlines) but it still hung.
17:38:27 <int-e> Anyway, it's not important. I was bored.
17:41:02 -!- mrohman has quit (Ping timeout: 246 seconds).
17:41:03 <int-e> usage ./testlm-disk.pl tokens.bin.foo model.bin.fii <-- actually that's a nice typo (typi?).
17:42:47 <int-e> (I do have a working language model, producing stuff like "what are you supposed to be looking for is here, i don't care to take a quick change of magnification brought them into close focus on it properly or tell how near vicinity of betelgeuse? ... guess the source...)
17:42:53 -!- Lymia has quit (Ping timeout: 245 seconds).
17:42:59 -!- oren has quit (Ping timeout: 256 seconds).
17:48:18 <fizzie> int-e: I think I fixed that typi.
17:48:35 <fizzie> But it probably didn't end up in the githubbed version.
17:49:10 <Jafet> Instead of guessing, I consulted Google's language model.
17:50:17 -!- SopaXorzTaker has quit (Quit: gtg).
17:50:34 <int-e> Jafet: yeah, "vicinity of betelgeuse" finds the right source.
17:56:04 -!- arjanb has joined.
17:57:48 <fizzie> int-e: Hmm. Might be things have changed since that was written. Although I thought it was correct.
18:03:30 -!- ProofTechnique has joined.
18:08:07 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
18:16:48 -!- shikhin has joined.
18:16:54 -!- shikhin has quit (Read error: Connection reset by peer).
18:20:16 -!- shikhin has joined.
18:20:18 -!- shikhin has quit (Read error: Connection reset by peer).
18:33:20 -!- zzo38 has quit (Remote host closed the connection).
18:39:32 -!- ProofTechnique has joined.
18:41:23 -!- shikhin has joined.
18:41:59 -!- shikhin has quit (Read error: Connection reset by peer).
18:46:23 -!- shikhin has joined.
18:47:04 -!- Sprocklem has joined.
18:47:56 -!- shikhin has quit (Read error: Connection reset by peer).
18:56:42 -!- shikhin has joined.
18:57:29 -!- oren has joined.
18:58:50 -!- shikhin has quit (Read error: Connection reset by peer).
19:00:37 -!- Tritonio has quit (Remote host closed the connection).
19:01:42 -!- shikhin has joined.
19:04:51 -!- zzo38 has joined.
19:07:12 -!- shikhin has quit (Read error: Connection reset by peer).
19:08:01 -!- shikhin has joined.
19:08:47 <Taneb> Today I made paper boats then unleashed them on my uni's lake
19:08:49 -!- shikhin has quit (Read error: Connection reset by peer).
19:13:00 -!- shikhin has joined.
19:14:34 -!- shikhin has quit (Read error: Connection reset by peer).
19:17:49 <oren> Taneb: then it was a good day!
19:17:57 -!- skj3gg has quit (Quit: ZZZzzz…).
19:18:04 -!- shikhin has joined.
19:18:30 -!- shikhin has quit (Read error: Connection reset by peer).
19:19:23 <Taneb> Also I have written a program which says "Socrates is eating" repeatedly!
19:21:00 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41894&oldid=32474 * Rottytooth * (+516) /* Language Overview */
19:21:18 <int-e> Taneb: you may have missed the point of the Dining Philosopher's probem...
19:21:34 <Taneb> int-e, I think I in fact have a buggy implementation
19:21:43 <Taneb> What with not actually knowing the language I'm implementing it in
19:22:04 -!- oren has quit (Ping timeout: 246 seconds).
19:23:04 -!- shikhin has joined.
19:23:47 -!- shikhin has quit (Read error: Connection reset by peer).
19:24:20 <Taneb> Hmm, I really do not know Java
19:28:08 -!- shikhin has joined.
19:28:49 -!- shikhin has quit (Read error: Connection reset by peer).
19:31:03 <int-e> . o O ( I've never been there either. )
19:31:08 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41895&oldid=41894 * Rottytooth * (+42) /* Examples */ added Hello, World
19:32:45 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41896&oldid=41895 * Rottytooth * (-5) /* Language Overview */
19:33:05 -!- shikhin has joined.
19:35:41 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41897&oldid=41896 * Rottytooth * (+210) /* Hello World */
19:36:36 <HackEgo> [wiki] [[User:Rottytooth]] http://esolangs.org/w/index.php?diff=41898&oldid=41572 * Rottytooth * (-35)
19:36:44 -!- shikhin has quit (Read error: Connection reset by peer).
19:38:07 -!- shikhin has joined.
19:38:45 -!- shikhin has quit (Read error: Connection reset by peer).
19:40:30 -!- shikhin has joined.
19:40:40 -!- shikhin has quit (Read error: Connection reset by peer).
19:48:21 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41899&oldid=41897 * Rottytooth * (+30) /* Hello World */ added default Hello World
19:49:41 <HackEgo> [wiki] [[Stasis]] http://esolangs.org/w/index.php?diff=41900&oldid=41899 * Rottytooth * (-34) /* Hello World */ changed order of examples, clarified
19:49:46 -!- skj3gg has joined.
19:50:52 -!- shikhin has joined.
19:53:45 -!- shikhin has quit (Read error: Connection reset by peer).
20:00:49 -!- shikhin has joined.
20:00:59 -!- Patashu has joined.
20:01:38 -!- shikhin has quit (Read error: Connection reset by peer).
20:02:06 -!- nys has joined.
20:04:06 -!- zzo38 has quit (Remote host closed the connection).
20:11:06 -!- ocharles_ has quit (Ping timeout: 252 seconds).
20:11:13 -!- shikhin has joined.
20:14:06 -!- shikhin has quit (Read error: Connection reset by peer).
20:16:20 -!- shikhin has joined.
20:18:15 -!- ocharles_ has joined.
20:18:49 -!- shikhin has quit (Read error: Connection reset by peer).
20:19:11 -!- skj3gg has quit (Quit: ZZZzzz…).
20:21:23 -!- shikhin has joined.
20:22:02 -!- skj3gg has joined.
20:25:13 -!- shikhin has quit (Read error: Connection reset by peer).
20:26:28 -!- shikhin has joined.
20:30:13 -!- shikhin has quit (Read error: Connection reset by peer).
20:31:26 -!- shikhin has joined.
20:31:34 -!- shikhin has quit (Read error: Connection reset by peer).
20:36:26 -!- shikhin has joined.
20:39:24 -!- shikhin has quit (Read error: Connection reset by peer).
20:41:31 -!- shikhin has joined.
20:41:57 -!- shikhin has quit (Read error: Connection reset by peer).
20:42:13 -!- Patashu has quit (Ping timeout: 265 seconds).
20:43:32 -!- mrohman has joined.
20:44:24 <mrohman> Can you do typechecking for ifs that have differenz return types?
20:45:14 <mrohman> This has two possible return types
20:46:16 <mrohman> (Foo (if p 5 5.0)) is ok if foo accepts ints and doubles
20:46:32 -!- shikhin has joined.
20:49:34 -!- shikhin has quit (Read error: Connection reset by peer).
20:51:25 <mrohman> Of course nested ifs can have 2^n possible return types
20:53:14 <mrohman> I think this can be statically typechecked
20:54:05 <mrohman> (Head (List (if p 5.0 6))) hm...
20:54:56 <mrohman> The type of a list is the union of all element types
20:56:27 <mrohman> This way you can have hetero lists that typecheck statically
20:56:51 -!- shikhin has joined.
20:59:33 -!- shikhin has quit (Read error: Connection reset by peer).
20:59:39 -!- skj3gg has quit (Quit: ZZZzzz…).
21:00:18 <mrohman> You can keep much of dynamic typing style but still have guarantees that no runtime type error can occur
21:07:14 -!- adu has quit (Quit: adu).
21:07:35 -!- shikhin has joined.
21:08:28 -!- shikhin has quit (Read error: Connection reset by peer).
21:09:49 -!- skj3gg has joined.
21:15:46 <mrohman> Is there already a name for such typesystems?
21:32:33 -!- mrohman has quit (Remote host closed the connection).
21:32:35 -!- Lymia has joined.
21:46:17 -!- TieSoul has quit (Read error: Connection reset by peer).
21:52:28 -!- AnotherTest has quit (Remote host closed the connection).
21:56:54 -!- shikhin has joined.
22:07:38 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:11:32 -!- shikhin has quit (Quit: leaving).
22:20:56 -!- myndzi has quit (Excess Flood).
22:21:15 -!- myndzi has joined.
22:22:41 -!- skj3gg has quit (Quit: ZZZzzz…).
22:28:05 -!- skj3gg has joined.
22:33:29 -!- `^_^v has joined.
22:33:57 -!- Sprocklem has quit (Ping timeout: 252 seconds).
22:37:15 -!- hjulle has joined.
23:09:51 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:12:02 -!- skj3gg has quit (Quit: ZZZzzz…).
23:14:39 -!- Tritonio has joined.
23:24:47 -!- oerjan has joined.
23:27:33 <tswett> So I want to make a dependently typed functional programming language that compiles to LLVM IR.
23:27:54 <tswett> It would have proofs and whatnot, of course.
23:28:32 <tswett> But a problem I'm planning to encounter is the "C Turing-completeness problem".
23:28:57 <tswett> In ordinary programming practice, we usually assume that all of the following are true:
23:29:19 <tswett> (1) By calling malloc() sufficiently many times, it is possible to create an arbitrary number of distinct pointers.
23:29:29 <tswett> (2) A pointer can be faithfully converted into an "int".
23:29:35 <tswett> (3) There are only finitely many possible "int"s.
23:36:19 -!- skj3gg has joined.
23:44:57 -!- not^v has joined.
23:47:59 -!- blockzombie has joined.
23:58:43 -!- contrapumpkin has joined.
00:02:59 -!- contrapumpkin has changed nick to copumpkin.
00:12:42 <Taneb> Today- well, yesterday- I made some paper boats then went to the cinema
00:15:41 <Taneb> I was making the best out of a printing error
00:16:57 <Taneb> Which led me to have about 30 sheets of paper with 4 black squares on each side
00:17:19 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
00:25:02 -!- ProofTechnique has joined.
00:35:48 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
00:38:12 <Taneb> I was trying to print of some slides, 4 per page
00:38:19 <Taneb> So I guess 8 per sheet
00:39:59 -!- Adrop has joined.
00:41:22 -!- Adrop has left.
00:41:24 -!- hjulle has quit (Ping timeout: 250 seconds).
00:41:31 -!- not^v has quit (Ping timeout: 255 seconds).
00:56:45 -!- skj3gg has quit (Quit: ZZZzzz…).
01:02:38 -!- chaosagent has joined.
01:15:18 -!- boily has joined.
01:20:33 <lambdabot> CYUL 130100Z 27012KT 8SM -SN SCT035 OVC060 M12/M16 A2989 RMK SC3SC5 SLP123
01:33:19 -!- Froo has quit (Quit: *bubbles away*).
01:35:08 -!- skj3gg has joined.
01:39:00 <lambdabot> ENVA 130120Z 13008KT CAVOK M04/M06 Q1014 RMK WIND 670FT 14008KT
01:42:24 <boily> hellørjan. still enjoying tropical weather?
01:42:39 <lambdabot> shachaf said 23h 45m 7s ago: not much of a hello when you quit within a few seconds!
01:43:07 <boily> @tell shachaf sorry. I had to disappear toward a pre-work shower.
01:44:14 <oerjan> still enjoying the flu, possibly
01:45:07 <boily> oh. the sickness disproved?
01:45:22 <boily> (what's the opposite of improved? I'm seriously drawing a blank here...)
01:45:51 <oerjan> i'm pretty sure disproved means something completely different
01:46:43 <boily> yes, but I had a long day, and my mental hamster is sprawled besides its wheel, lightly twitching.
01:47:05 <oerjan> is it epileptic spasms
01:47:13 -!- skj3gg has quit (Quit: ZZZzzz…).
01:47:28 <boily> perhaps. I'm drinking diet coke.
01:48:00 * oerjan is drinking orange juice, might change to coke zero later
01:49:20 <oerjan> i suppose not having nausea is good
01:49:44 * dulla gets oerjan a Coke Orange
01:49:53 <dulla> Welcome to Americlap
01:49:58 -!- Lymia has quit (Ping timeout: 245 seconds).
01:50:24 <oerjan> we don't generally mix coke and orange in norway afaik
01:50:28 * boily glares at dulla “no corrupting Scandinavians!”
01:50:52 <dulla> Hey, you can put your own god damn oj in your own god damn cocaine cola
01:51:06 <oerjan> unless you mean coke in the "americans have a different word for fizzy drinks dependent on region and time of day" sense
01:51:37 <oerjan> i believe i've read there's no trace of cocaine in coke since the 1930s or thereabouts
01:51:46 <dulla> it's become the coca cola company versus pepsi co
01:51:58 <dulla> you have root beer, or dr pepper
01:52:27 <dulla> regardless, the automated drink machines are really weird, they allow you to make your own cola flavors
01:52:38 <dulla> > orange vanilla coke
01:52:40 <lambdabot> Perhaps you meant ‘range’ (imported from Data.Ix)Not in scope: ‘vanilla’Not ...
01:54:11 <oerjan> i do not believe lambdabot yet has a vending machine attached
01:54:50 <dulla> Well, now I have a goal
01:55:31 <oerjan> obviously what we truly want is launchMissiles :: IO ()
01:59:13 <boily> I'd be more worried about a launchMissiles :: ().
01:59:33 <dulla> This is going to be the start of a strategy game, oerjan
01:59:39 <dulla> Are you realy willing?
02:00:16 <oerjan> the answer to that should be obvious to anyone who has been here in the channel for a while
02:00:25 <oerjan> ("heck no, far too much work")
02:00:56 <oerjan> boily: no, that would be unsafeLaunchMissiles, which you have to construct yourself hth
02:01:41 <oerjan> i think intuitively the type should be Void rather than ()
02:01:50 <oerjan> because, there won't be anything left to return.
02:03:05 <dulla> I would not be opposed to a proc chance of the missiles simply exploding on you for being so unsafe
02:03:26 <boily> dulla: those are missiles we are talking about. missiles are reliable.
02:04:41 <dulla> Not when they are from kazahkstan
02:05:02 <dulla> or is uzbekistan more apropos
02:09:48 <Taneb> Missiles of this size, apocalypstrophestan
02:11:52 -!- adu has joined.
02:17:28 -!- Frooxius has joined.
02:17:48 -!- ^v has quit (Read error: Connection reset by peer).
02:18:15 -!- ^v has joined.
02:20:30 -!- dianne has quit (Quit: Lost terminal).
02:21:22 -!- dianne has joined.
02:23:49 -!- boily has quit (Quit: TEXTURED CHICKEN).
02:24:38 -!- Sprocklem has joined.
02:25:04 -!- Lymia has joined.
02:25:31 -!- arjanb has quit (Quit: .).
02:27:17 -!- skj3gg has joined.
02:30:18 -!- AndoDaan has joined.
02:36:10 -!- oren has joined.
02:40:15 -!- skj3gg has quit (Quit: ZZZzzz…).
03:14:26 <oren> That is a problem with the definition of "turing complete", not with C, tswett...
03:15:12 <oren> That is, no real computer can ever be "turing complete", thus some algorithms that theoretically "work" don't actually
03:16:54 -!- skj3gg has joined.
03:17:01 <oren> elliott, are there models of computability that take the limits of physics into account?
03:19:14 <nys> linear bounded automaton with tape fixed to 10^90 bits
03:20:16 <oren> nys: I think there are more restrictions than that. Consider the maximum speed of information propagation, and the energy supply, for example.
03:21:32 <oren> Personally, I think there is in theory a tradeoff between the size of memory and the speed of the computer.
03:21:40 <nys> oren: http://arxiv.org/abs/quant-ph/0110141
03:24:16 <oren> nys: cool. So there will never, even in theory, be a need for pointers longer than 90 bits. We can saefly assume that
03:26:40 -!- skj3gg has quit (Quit: ZZZzzz…).
03:39:00 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
04:35:25 <dulla> this is why we have a hierarchical cache structure, and coproccessing, oren
04:36:33 -!- skj3gg has joined.
04:49:01 -!- skj3gg has quit (Quit: ZZZzzz…).
04:52:26 -!- skj3gg has joined.
04:52:41 -!- Sketra has joined.
04:53:06 -!- nys has quit (Quit: quit).
04:59:53 <HackEgo> olist 975: shachaf oerjan Sgeo FireFly boily nortti
05:00:30 <Sgeo> I saw it but forgot to olist
05:01:36 <oerjan> order of the stick announcements
05:01:56 <HackEgo> Update notification for the webcomic Order of the Stick.
05:02:18 <oerjan> HackEgo: you're, like, slow, tdnh
05:02:31 <oerjan> no, he sent me a lambdabot message
05:02:45 <Sketra> I've heard of lambdabot
05:02:57 <lambdabot> Always remember that others may hate you but those who hate you don't win unless you hate them. And then you destroy yourself.
05:03:29 <Sketra> That makes Not a lick o' sense
05:04:38 -!- Sprocklem has quit (Ping timeout: 246 seconds).
05:04:39 <oerjan> nixon often didn't hth
05:05:27 <lambdabot> activity base bf check compose dice dict djinn dummy elite eval filter free fresh haddock help hoogle instances irc karma localtime metar more oeis offlineRC pl pointful poll pretty quote search slap source spell system tell ticker todo topic type undo unlambda unmtl version where
05:05:32 <lambdabot> quote provides: quote remember forget ghc fortune yow arr yarr keal b52s pinky brain palomer girl19 v yhjulwwiefzojcbxybbruweejw protontorpedo nixon farber
05:05:45 <lambdabot> I think so, Brain, but me and Pippi Longstocking -- I mean, what would the children look like?
05:06:13 <lambdabot> Vote for ME -- I'm well-tapered, half-cocked, ill-conceived and TAX-DEFERRED!
05:06:32 <Sketra> Vile creature of the internet begone from this sacred land of code and drama
05:07:10 <Sketra> Sorry, I spout often words of wimsical use
05:07:36 <lambdabot> Occurs check: cannot construct the infinite kind
05:09:49 <Sketra> By the hymen of Olivia newton John that is a big bot lib for lambdabot
05:11:16 <oerjan> what do you expect of a bot more than a decade old
05:13:13 <Sketra> Who are you btw & what do you do for program wise
05:13:41 <lambdabot> It could refer to either ‘L.y’, defined at L.hs:153:16
05:13:52 <Sketra> I haven't haskelled in years
05:13:54 <dulla> you need an input set, Sketra
05:14:12 <Sketra> Its ok I gave up in fifth grade
05:14:14 <oerjan> > is just an abbreviation for @run it doesn't have access to the other commands
05:14:16 <lambdabot> ‘id’ (imported from Data.Function),
05:14:18 <dulla> > [y|y <- "aeiou"]
05:14:49 <Sketra> Remember ten years from now oerjan you make lambdabot into an artificial intelligance
05:18:36 <Sketra> is it bad if I had a bot use lambdabot to do nefarious deeds
05:19:06 <elliott> that's pretty traditional actually >_>
05:19:26 -!- skj3gg has quit (Quit: ZZZzzz…).
05:19:36 <Sketra> Doesn't have a good security system?
05:20:53 <elliott> its security system is really terrible
05:20:58 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:21:07 <oerjan> @@ @run text @show @nixon
05:21:08 <lambdabot> I brought myself down. I impeached myself by resigning.
05:21:10 <elliott> there are some very bad exploits that I doubt got fixed that I'm not going to tell anyone about
05:21:21 <elliott> @@ @ run text . reverse $ @show @nixon
05:21:21 <lambdabot> Plugin `compose' failed with: Unknown command: ""
05:21:24 <elliott> @@ @run text . reverse $ @show @nixon
05:21:25 <lambdabot> .era yeht ,ti ecaf s'tel ,woN .seert eht fo tuo tsuj era ,yllacisab , meht ...
05:22:24 <Sketra> them basically are just out of the trees Now lets face they are
05:22:40 <oerjan> Sketra: lambdabot only got a proper sandbox last month after we found that security bug
05:23:20 <oerjan> before that it tried to trust haskell's type system
05:24:17 <oerjan> Sketra: um you don't know what sandbox means for a bot?
05:24:36 <oerjan> it means putting it in a more secure environment
05:25:41 <Sketra> yeah well you may have could said that
05:26:04 <Sketra> My friend did that to our currency bot
05:29:21 <oerjan> you're sounding seriously crazy today.
05:30:27 <Sketra> I'm just asking a question
05:30:45 <oerjan> i'm a norwegian who does pretty much nothing.
05:30:51 <Sketra> I wish to know what you've done in your life As a programming
05:31:15 <Sketra> How come Germany took over Norway but Sweden?!
05:32:04 <oerjan> sweden didn't have a long atlantic coastline or a stupid policy of downsizing the military (not sure about the latter)
05:34:17 <Sketra> Geometery confuses me oerjan
05:36:01 <oerjan> you just have to look at it from the right angle
05:37:18 <oerjan> nordics are people living in northern europe. some of their ancestors were vikings.
05:37:26 <Sketra> ouo" I heard from a friend that..
05:38:03 <oerjan> you're Eolus. you should have noticed by now.
05:38:11 <Sketra> Ofc in some fields you may not be as smart
05:38:42 <oerjan> i don't actually believe that but whatever.
05:39:15 <oerjan> that you're not the exact same person as Eolus.
05:40:55 <Sketra> Second split of third tri quarter of the Median system Sketra Split from Zetsu Female alter Mental age 17
05:41:55 <Sketra> Should I have everyone introduce themselves like that? I assume it would be easier
05:42:56 <oerjan> we aren't going to distinguish you into personae anyhow.
05:42:58 <Sketra> 4000 newtons psi to shatter bones
05:43:45 <Sketra> Its ok just call us by the nick that is displayed and you should be spared any type of discontent and murderous anger from sprouting
05:44:28 <Sketra> Like int-e always calling us By lilax
05:45:31 <Sketra> you never do that anyways
05:45:41 <Sketra> You are good friend I guess
05:46:23 <Sketra> Probably would forgive since you only did it once
05:46:50 -!- MDude has quit (Read error: Connection reset by peer).
05:46:58 <Sketra> Its just hhhh titles matter cuz ugh idk we just hate being called by eachothers names
05:47:11 <Sketra> Albiet confusing just call us by our nicks
05:48:07 <oerjan> i'll do that, but only because i'd be doing that anyway. if you start making me want to follow rules i consider pointless, i might run out of patience myself.
05:48:39 <oerjan> *start making me follow
05:48:47 <Sketra> well no oerjan you don't have to follow the rules you are nice and funny
05:49:15 <Sketra> Also you remind of us our grandpa so its ok
05:49:15 <oerjan> ...that kind of talk doesn't help, either.
05:50:12 <Sketra> As long as you don't say anything rash in anger lol Cuz lots of us are emotionally unstable and you might never hear from me again or us for that matter
05:50:38 -!- bb010g has joined.
05:50:53 -!- pikhq has quit (Remote host closed the connection).
05:51:34 <oren> HaskellCEO: TOO MUCH! Just found out that these dickwads belong to some Christian denomination known as the Alonzo Church of God in Christ or some shit.
05:52:24 <oren> It's a joke about the famous mathematician Alonzo Church
05:52:57 <oren> what's RGB for pink?
05:55:10 <oerjan> (/usr/share/X11/rgb.txt)
05:56:00 <oerjan> Sketra: Red Green Blue
05:56:20 <Sketra> I'm colour blind to Blue and Green
05:56:26 <oerjan> color numbers for a monitor
05:56:58 <oerjan> probably somewhat randomly assigned
05:57:04 <Sketra> Thas cool I haven't coded since 10th grade
05:57:28 <oren> I'm gonna go with "deep pink" 255 20 147, for the color of bad links, and "Purple" 160 32 240 for the good links
05:57:50 <Sketra> Oh I see what you are doing
05:58:18 <oerjan> this all probably depends on monitor calibration and stuff, something i only know the vaguest part about
05:58:38 -!- ProofTechnique has joined.
05:58:44 <oren> Sketra: writing a primitive hypertext browser for my game
06:05:17 -!- pikhq has joined.
06:13:44 <oerjan> hm iirc today's freefall seems to miss the direct order the mayor's assistant gave...
06:16:20 <oerjan> http://freefall.purrsia.com/ff2200/fc02155.htm
07:28:27 <J_Arcane> http://www.noulakaz.net/weblog/2007/03/18/a-regular-expression-to-check-for-prime-numbers/
07:31:59 -!- Patashu has joined.
07:32:44 -!- blockzombie has quit (Remote host closed the connection).
07:35:48 -!- oerjan has quit (Quit: leaving).
07:44:55 <J_Arcane> http://webcache.googleusercontent.com/search?q=cache%3Awww.monohaskell.com&oq=cache%3Awww.monohaskell.com&aqs=chrome..69i57j69i58.1240j0j4&sourceid=chrome&es_sm=122&ie=UTF-8
07:47:48 -!- Sketra has quit (Ping timeout: 250 seconds).
07:54:43 -!- int-e has set topic: What is the land-speed velocity of a migrating fungot? | The many faces of Lilax | ZFC is a ChuChu rocket. | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
07:57:55 <int-e> Oh, early GG comic today.
08:03:30 <int-e> Ah I guess collateral damage is no fun if you're it. http://www.schlockmercenary.com/2015-02-13
08:13:07 -!- spupuser has joined.
08:15:44 <oren> woohoo it't working
08:23:41 <oren> http://postimg.org/image/8upxjp4rz/
08:27:41 <oren> See, it detected that the "element" link's file exists and made that link blue
08:30:29 <oren> Now to reinvent web forms
08:33:08 <HackEgo> [wiki] [[Ttml]] http://esolangs.org/w/index.php?diff=41901&oldid=41860 * Orenwatson * (+24) update spec to include hyperlinks
08:38:08 -!- bb010g has quit (Quit: Connection closed for inactivity).
08:51:50 -!- shikhin has joined.
08:53:00 -!- elliott has set topic: What is the land-speed velocity of a migrating fungot? | ZFC is a ChuChu rocket. | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
08:53:15 <elliott> int-e: can you stop being a dick to 16 year olds, it's getting really old
08:55:35 <elliott> it's the most ridiculous feud in this place since whenever I cared enough to feud with people
09:09:18 <elliott> oren: do you pick a new terminal font for every sreenshot
09:09:26 <elliott> that one is actually cute though
09:15:40 -!- adu has quit (Quit: adu).
09:26:29 <oren> elliott: well, not every screenshot, but I do acquire new terminal fonts every week or so
09:26:56 <int-e> elliott: He strokes (pets? pats?) me the wrong way, it's hard not to bite.
09:28:47 -!- shikhin_ has joined.
09:31:32 -!- shikhin has quit (Ping timeout: 245 seconds).
09:47:24 -!- ais523 has joined.
09:49:10 -!- ais523 has quit (Read error: Connection reset by peer).
09:49:28 -!- ais523 has joined.
10:02:20 -!- chaosagent has quit (Ping timeout: 252 seconds).
10:23:47 <J_Arcane> Wife made me new jewelry: https://twitter.com/J_Arcane/status/566173919770869760
10:40:29 -!- Phantom_Hoover has joined.
10:57:32 -!- ^v has quit (Read error: Connection reset by peer).
10:57:59 -!- ^v has joined.
11:18:27 -!- shikhin_ has changed nick to shikhin.
11:25:35 -!- boily has joined.
11:33:04 -!- ais523 has quit (Quit: computer is malfunctioning).
11:46:59 -!- ais523 has joined.
11:47:03 -!- AndoDaan has quit (Ping timeout: 252 seconds).
11:59:33 -!- ais523 has quit (Read error: Connection reset by peer).
11:59:47 -!- ais523 has joined.
11:59:56 -!- AnotherTest has joined.
12:11:39 -!- Lymia has quit (Remote host closed the connection).
12:15:04 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
12:15:10 -!- boily has quit (Quit: CARBONATED CHICKEN).
12:16:02 <mroman> where can you find law texts of us laws?
12:16:14 <mroman> apparentely some cities have some weird laws
12:16:23 <mroman> but nobody seems to have an actual source
12:18:05 -!- Lymia has joined.
12:18:06 <Jafet> The libraries of those cities, perhaps.
12:18:17 <J_Arcane> So weird question: does immutability simplify the prospect of building a compiler for a dynamically typed language?
12:19:10 <Jafet> Well, you no longer need to convert the program to SSA.
12:23:14 <Jafet> (Compilers for imperative languages like gcc already use immutable IRs, so the passes after that wouldn't really change.)
12:25:49 <tswett> So I'm trying to figure out what kind of hypercomputer you'd need to do the Henkin construction.
12:26:56 <tswett> Define a level-1 hypercomputer as a Turing machine attached to a halting oracle for Turing machines.
12:27:11 <J_Arcane> Jafet: Yeah, that was my thought; the risk of a name changing in type gets smaller if it can't change (local override notwithstanding, and potentially workaroundable). Polymorphic functions seem like they could still be stickier, but maybe not so much?
12:27:22 <mroman> Jafet: so... no online :(
12:27:39 <J_Arcane> I should really do SICP, and look into the source code of Bones.
12:28:45 <tswett> So our L1H starts with a consistent theory, such as ZFC (assuming ZFC is consistent). It then enumerates every statement in the language; whenever it gets to a statement consistent with the theory so far, it adds it to the theory.
12:29:00 <tswett> It can check if a statement is consistent with the theory or not by seeing if a Turing machine halts.
12:30:07 <tswett> Now, the way I just said it, stage 1 will go on forever, meaning we'll never start on stage 2. Aye?
12:30:14 <Jafet> There are a hundred counties in Kansas, which is probably about as regressive as america gets, and each of them can enact strange ordinances. I don't think there's a good chance you will find them all online (especially any recently-passed ones).
12:31:02 <Jafet> State-wide laws should be available though (google suggests http://www.usa.gov/Topics/Reference-Shelf/Laws.shtml)
12:32:53 -!- Patashu has quit (Ping timeout: 245 seconds).
12:32:59 <Jafet> I could be wrong... https://library.municode.com/index.aspx?clientId=14166
12:33:17 <tswett> Anyhoo, stage 2 begins by adding a constant to the language for every "there exists" statement we added in stage 1.
12:33:37 <tswett> Then we add a statement saying that the constant is an example of the "there exists" statement.
12:34:02 <tswett> Then we do the same thing we did in stage 1, enumerating all the statements and adding the consistent ones.
12:34:37 <tswett> But now how do you check if a statement is consistent with all the previously added statements?
12:34:39 <Jafet> J_Arcane: in a unityped language, all functions (or perhaps no functions?) can essentially be polymorphic
12:35:43 <Jafet> Anyway, whether "local variables" (if your language has them) are immutable is mostly immaterial because of SSA transform.
12:35:45 <J_Arcane> Jafet: Hmm. That makes me think of the Write Yourself a Scheme implementation; where there's a union type of 'LispValue' that can be either of number, symbol, etc.
12:36:14 <Jafet> If your compiler goes to the trouble of SSA transform for performance, that is
12:38:47 <tswett> I think that involves checking if an L1H halts, meaning you need an L2H. And stage 3 will require an L3H, and so on.
12:39:43 <J_Arcane> "In functional language compilers, such as those for Scheme, ML and Haskell, continuation-passing style (CPS) is generally used where one might expect to find SSA in a compiler for Fortran or C. SSA is formally equivalent to a well-behaved subset of CPS (excluding non-local control flow, which does not occur when CPS is used as intermediate representation), so optimizations and transformations for
12:39:45 <J_Arcane> mulated in terms of one immediately apply to the other." Hm.
12:40:10 <tswett> After you've done all the infinitely many stages, your model is just the set of all constants.
12:40:14 <tswett> Great discussion, everyone.
12:41:20 <Jafet> Is that a countable model?
12:54:11 <Jafet> Why do you need an oracle for that construction, though
12:54:29 <Jafet> Just test all statements in parallel in stage 1, and accumulate the ones proven to be consistent
12:54:45 <Jafet> When you find any existentially quantified ones, thread them through stage 2, etc.
12:56:25 <Jafet> This will eventually give you every (finitely provably) consistent finite statement
13:17:32 -!- GeekDude has joined.
13:22:36 -!- graSP has joined.
13:27:29 -!- graSP has quit (Quit: ChatZilla 0.9.91.1 [Firefox 35.0.1/20150122214805]).
13:28:00 -!- graSP has joined.
13:28:03 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
13:28:31 -!- SopaXorzTaker has joined.
13:42:27 -!- sorch has joined.
13:45:43 -!- skj3gg has joined.
13:47:24 -!- sorch has quit (Quit: Leaving).
13:49:34 -!- ais523 has quit (Read error: Connection reset by peer).
13:49:48 -!- ais523 has joined.
13:52:53 -!- graSP has quit (Ping timeout: 244 seconds).
14:06:29 -!- TieSoul has joined.
14:19:49 -!- skj3gg has quit (Quit: ZZZzzz…).
14:31:06 -!- Tritonio has quit (Ping timeout: 252 seconds).
14:40:06 -!- Guest50274 has joined.
14:54:27 -!- skj3gg has joined.
14:57:16 -!- skj3gg has quit (Client Quit).
15:11:27 -!- adu has joined.
15:14:15 -!- `^_^v has joined.
15:19:25 -!- adu has quit (Quit: adu).
15:21:17 -!- callforjudgement has joined.
15:22:48 -!- ais523 has quit (Ping timeout: 252 seconds).
15:23:03 -!- callforjudgement has changed nick to ais523.
15:28:55 -!- spupuser has quit (Ping timeout: 255 seconds).
15:32:44 -!- shikhin has quit (Ping timeout: 265 seconds).
15:49:44 -!- adu has joined.
15:58:37 <dulla> Jafet J_Arcane What is SSA if it's a "well-behaved" CPS?
15:59:59 <dulla> Also what is an oracle?
16:00:02 <elliott> is anyone here capable of getting paywalled papers and doesn't have the morals to prevent sharing it afterwards
16:00:18 <elliott> yes, thanks ais523, I thought of you too
16:01:57 -!- SopaXorzTaker has quit (Ping timeout: 250 seconds).
16:14:07 <oren> UofT library has a lot
16:14:31 <elliott> uh I just mean like online ACM paywall kinda things
16:14:34 <elliott> unless you mean a digital library
16:15:59 -!- mihow has joined.
16:17:10 <Jafet> Morals? Perhaps "legals" is a better term.
16:17:40 <Jafet> Hmm, this spell checker agrees
16:18:20 -!- bb010g has joined.
16:18:27 <elliott> I meant more "doesn't have a moral system s.t. ..."
16:19:31 <oren> Chaotic Good FTW
16:19:50 <elliott> it's "Natural Deduction and Weak Normalization for Full Linear Logic", anyway.
16:20:29 <elliott> http://jigpal.oxfordjournals.org/content/12/6/601.abstract
16:21:58 <Taneb> elliott, I find often googling the title works
16:23:42 <Taneb> Are there any interesting concurrency esolangs?
16:24:07 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
16:25:48 * elliott waits anxiously in the get-away car
16:29:47 <Jafet> How would you rate π-calculus as 1) interesting 2) esolang
16:31:58 -!- ProofTechnique has joined.
16:34:13 -!- Guest50274 has quit (Remote host closed the connection).
16:36:18 <Taneb> I am not familiar with it, Jafet
16:36:58 * dulla brings elliott to the combination sex dungeon and creamery
16:37:57 <elliott> um... what kind of cream are we talking here
16:38:08 -!- shikhin has joined.
16:40:10 <Jafet> A number of researchers are, but it's fairly safe to rate them as esoteric
16:41:59 -!- oerjan has joined.
16:43:20 <Jafet> https://esolangs.org/wiki/Ziim looks interesting
16:51:57 -!- oren has quit (Ping timeout: 245 seconds).
17:04:10 -!- oren has joined.
17:21:30 -!- GeekDude has changed nick to GeekDudesBopt.
17:21:31 -!- GeekDudesBopt has changed nick to GeekDudesBot.
17:21:49 -!- GeekDudesBot has changed nick to GeekDude.
17:23:06 -!- GeekDude has quit (Changing host).
17:23:06 -!- GeekDude has joined.
17:23:31 -!- GeekDude has changed nick to GeekDudesBot.
17:32:27 -!- GeekDudesBot has changed nick to GeekDude.
17:32:39 -!- GeekDude has quit (Changing host).
17:32:39 -!- GeekDude has joined.
17:50:28 -!- perrier has quit (Remote host closed the connection).
17:51:40 -!- perrier has joined.
17:53:36 -!- Phantom_Hoover has joined.
17:56:17 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
17:56:34 -!- J_Arcane has joined.
17:58:18 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
17:59:25 -!- callforjudgement has joined.
18:02:22 -!- ais523 has quit (Ping timeout: 245 seconds).
18:02:36 -!- callforjudgement has changed nick to ais523.
18:18:08 -!- bb010g has quit (Quit: Connection closed for inactivity).
18:58:36 -!- arjanb has joined.
19:05:23 -!- oren has quit (Ping timeout: 245 seconds).
19:06:03 -!- Phantom_Hoover has joined.
19:10:23 -!- nortti has changed nick to lawspeaker.
19:12:06 -!- lawspeaker has changed nick to nortti.
19:15:25 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in herpes
19:15:26 <lambdabot> [1,1,3,5,9,15,25,41,67,109,177,287,465,753,1219,1973,3193,5167,8361,13529,21...
19:15:44 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in take 8 herpes
19:16:40 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in intersperse ' ' . (take 8) $ herpes
19:16:41 <lambdabot> No instance for (GHC.Num.Num GHC.Types.Char)
19:17:01 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in intersperse ' ' . map show . (take 8) $ herpes
19:17:03 <lambdabot> Couldn't match type ‘[GHC.Types.Char]’ with ‘GHC.Types.Char’
19:17:03 <lambdabot> Expected type: a0 -> GHC.Types.Char
19:17:03 <lambdabot> Actual type: a0 -> GHC.Base.String
19:17:16 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in intersperse " " . map show . (take 8) $ herpes
19:17:17 <lambdabot> ["1"," ","1"," ","3"," ","5"," ","9"," ","15"," ","25"," ","41"]
19:17:20 -!- oren has joined.
19:17:27 <dulla> > let herpes = 1:1: zipWith (\a b -> a + b + 1) herpes (tail herpes) in unwords . intersperse " " . map show . (take 8) $ herpes
19:19:10 -!- ais523 has quit.
19:19:21 -!- ais523 has joined.
19:21:50 -!- ais523 has quit (Read error: Connection reset by peer).
19:22:03 -!- ais523 has joined.
19:24:26 <int-e> quintopia: of course they do. it's just 2*F_n - 1 [with n counting from 1]
19:25:34 <int-e> (uhm and using F_n to denote Fibonacci numbers)
19:26:32 <dulla> quintopia they are leonardo numbers
19:26:48 <dulla> they can be described in terms of that, afaik
19:27:30 <dulla> besides, you can compile it yourself on compile online, quintopia
19:29:29 <dulla> also it's L(n)=2F(n+1)-1, /wikipedia int-e
19:31:05 <dulla> J_Arcane what is an orcale in that talk you have about SSA and CPS?
19:31:11 -!- zzo38 has joined.
19:33:28 <quintopia> i figured it would but wasnt sure if the +1 would throw it off somehow
19:33:49 <J_Arcane> Nice. Rust 1.0 by May, and beta end of next month.
19:33:55 <oerjan> did you know fibonacci's first name is actually leonardo, confusing that
19:34:10 <quintopia> how do you prove the ratio approaches phi in the limit
19:34:21 <int-e> dulla: so what. the code doesn't really indicate whether the first index is 0 or 1.
19:35:15 <dulla> You can have a zero in it, but to reuse the lazy list construction of the fibb numbers, I had to start at 1:1
19:35:52 -!- oren has quit (Ping timeout: 240 seconds).
19:35:55 <dulla> by the looks of it L(0)=1
19:36:31 <dulla> er, Oracle* J_Arcane
19:37:06 <J_Arcane> Dunno what you mean. There were a couple convos going at once though, perhaps there's some confusion there?
19:38:15 <oerjan> quintopia: you can absorb the +1 into the terms instead.
19:38:34 <dulla> Um, something about hypercomputers, and oracles resolving or optimising SSA's or halting problems
19:39:11 <oerjan> (a + b + 1) + 1 = (a + 1) + (b + 1)
19:40:04 <oerjan> and then you have the usual fibonacci recursion
19:41:15 <J_Arcane> dulla: ahh, yeah, no someone was working on a proof of ... something. I was just talking about immutability and compiling.
19:41:23 <oerjan> basically, take your sequence fulfilling a_n = a_(n-1) + a_(n-2) + 1 and define b_n = a_n + 1
19:42:58 <oerjan> dulla: an oracle is an extra instruction you add to your turing machine / whatever which does something arbitrary you decide on.
19:43:16 <oerjan> in this case, testing whether an ordinary turing machine halts
19:43:16 <dulla> So more or less external or side influence
19:43:42 <oerjan> the thing is, a lot of the theory works the same if you add an oracle to things
19:43:50 <dulla> So Buterin wasn't pulling Oracle out his ass when talking about news tickers
19:44:16 <oerjan> just, instead of not being able to decide halting problem for ordinary TMs, you're now unable to decide it for a TM with your oracle
19:45:57 <zzo38> I also thought of adding a oracle operation into a sequent calculus, where |- Oracle X is an axiom if and only if |- X is not a theorem of the system (even if it cannot be proven that it isn't a theorem).
19:45:59 <dulla> So you can exit a loop?
19:47:21 <oerjan> well you can detect an infinite loop
19:47:45 <int-e> dulla: Well, the oracles are often hypothetical. The one that solves the halting problem cannot, as far as we know, exist. (It would require computing power that goes beyond Turing machines, which goes against the Church-Turing thesis)
19:48:49 <oerjan> see e.g. https://esolangs.org/wiki/Banana_Scheme which is an esolang applying this to scheme
19:49:21 <int-e> (Not all oracles are hypothetical. It's interesting to think of polynomial time algorithms that can query oracles that solve (at least conjecturally) harder problems like satisfiability of boolean formulas)
19:49:52 <int-e> (just as an example)
19:50:04 <oerjan> a big part of why the P = NP problem is so hard is that the answer to it can change if you add an oracle.
19:50:06 -!- Sprocklem has joined.
19:50:38 <oerjan> which means that many of the easy methods for proving complexity results simply cannot work for it
19:51:17 <int-e> zzo38: is that oracle circular?
19:51:29 <zzo38> int-e: How does that mean?
19:52:17 <int-e> zzo38: does the system in "not a theorem of the system" refer to the system with those axioms?
19:52:26 <int-e> zzo38: (produced by the oracle)
19:52:56 <zzo38> int-e: I would think so. Maybe there might be some systems where this doesn't work although I expect it to work in most cases.
19:54:25 <int-e> Hmm, actually, what good is such an axiom schema? Knowing Oracle X doesn't tell you much.
19:55:17 <zzo38> I don't actually know the answer of that question.
19:57:56 <dulla> so an oracle of x?
19:59:28 <zzo38> Although |- Oracle Oracle X would indicate that |- X is a theorem, I think.
20:00:06 <dulla> go intuintionistic on it
20:00:11 <dulla> x is better than not not x
20:06:39 -!- oren has joined.
20:08:05 <int-e> zzo38: tricky. it almost fails if the theory is inconsistent, but then X is a theorem anyway...
20:08:32 <int-e> classically, at least.
20:14:09 -!- dorei has joined.
20:17:28 -!- hjulle has joined.
20:21:27 <J_Arcane> Man, I've been on board with this for years: http://www.stopusinglinkedin.com/
20:25:22 <dorei> stop using web 2.0 xD
20:25:28 <int-e> "With these changes in place, developers can no longer build tools that allow you to better leverage your own professional connections." ... err, right, sure.
20:26:02 <int-e> "Linkedin prevents *US* from earning money with your data." ... cry me a river, baby.
20:27:11 <int-e> (I agree with the idea of not using LinkedIn, but these are the wrong reasons.)
20:27:14 <J_Arcane> well true, the latest complaint is not the most compelling.
20:27:30 <J_Arcane> the part where it's little more than a spam pyramid is the bigger one for me.
20:31:17 -!- nycs has joined.
20:32:53 -!- `^_^v has quit (Ping timeout: 256 seconds).
20:35:16 -!- ais523 has quit (Read error: Connection reset by peer).
20:35:30 -!- ais523 has joined.
20:37:54 -!- drdanmaku has joined.
20:38:25 -!- drdanmaku has quit (Client Quit).
20:44:29 <int-e> the dream machine: yea :-P
20:47:22 <zzo38> Tell the people that made PDJSON that I fixed the bug in it.
20:51:44 -!- AnotherTest has quit (Ping timeout: 246 seconds).
20:51:59 -!- GeekDude has quit (Changing host).
20:52:00 -!- GeekDude has joined.
20:52:45 -!- GeekDude has quit (Changing host).
20:52:45 -!- GeekDude has joined.
20:58:27 -!- Tritonio has joined.
20:59:01 -!- callforjudgement has joined.
21:03:29 -!- ais523 has quit (Ping timeout: 256 seconds).
21:04:12 -!- callforjudgement has changed nick to ais523.
21:11:29 -!- mihow has quit (Quit: mihow).
21:22:58 -!- mihow has joined.
21:23:41 -!- Patashu has joined.
21:24:35 -!- ais523 has quit.
21:24:47 -!- ais523 has joined.
21:27:30 <oren> J_Arcane: I'm aheadof the game, I never started using Linkedin.
21:28:10 -!- ais523 has quit (Client Quit).
21:28:17 -!- callforjudgement has joined.
21:29:07 -!- callforjudgement has changed nick to ais523.
22:13:46 -!- nycs has quit (Quit: This computer has gone to sleep).
22:14:04 -!- nycs has joined.
22:18:26 -!- callforjudgement has joined.
22:18:28 -!- ais523 has quit (Read error: Connection reset by peer).
22:18:30 -!- callforjudgement has quit (Changing host).
22:18:30 -!- callforjudgement has joined.
22:30:51 -!- nys has joined.
22:36:02 -!- shikhin_ has joined.
22:39:07 -!- shikhin has quit (Ping timeout: 255 seconds).
22:47:05 <zzo38> I made up a format that can be used in a HTML comment inside of a HTML form, which can be used to make the form to work with interactive command-line interfaces; for example this can be used to login to OpenID servers which support it. An example can be: <!-- [HTML-FORM-COMMAND-INTERFACE] "Login: " ?username "Password: " *concealed ?password *send -->
22:48:04 <zzo38> (The client would need to parse the form method and action too, as well as any hidden fields in the form)
22:49:00 <zzo38> It might be used for example now you can login to stuff other than webpages using OpenID too.
22:49:37 -!- mihow has quit (Quit: mihow).
22:49:52 <zzo38> (Assuming there is a reason you still want to use OpenID for this)
23:01:52 -!- nycs has quit (Quit: This computer has gone to sleep).
23:02:05 <callforjudgement> dulla: one of the tricks with this channel is, there doesn't really have to be a reason
23:02:59 <callforjudgement> oh, everyone, eso question that came up in another channel: what's the minimum number of transistors needed to have a functioning CPU, assuming you don't care about performance?
23:03:30 <callforjudgement> we have to assume that there's some sort of external memory for this to work, but presumably we can rig the details as appropriate (e.g. by use of a magnetic tape drive)
23:03:31 <zzo38> I want to know too the answer. Perhaps might TOGA computer do it?
23:04:20 <callforjudgement> it's got to be some sort of simple Turing machine, hasn't it? you don't want to waste transistors storing addresses
23:04:22 <tswett> Jafet: you want *all* the consistent statements, not just the provably consistent ones.
23:04:32 <callforjudgement> the (2,3) machine doesn't count because it requires an infinite initialization
23:05:21 <tswett> Taneb: also, Al Dente is totally an interesting concurrency esolang.
23:05:43 <zzo38> I like "Al Dente" esolang too
23:05:54 <tswett> There's no flow control. Stuff just spontaneously happens.
23:05:55 <callforjudgement> what about My Unreliable Past? that's a concurrency esolang really, even though it doesn't look like one
23:06:12 <callforjudgement> (I don't think anyone's guessed the original inspiration for that one yet)
23:07:09 <tswett> As for the CPU, bitwise cyclic tag might be the winner.
23:07:30 <zzo38> Now write out all of the transistors of it please
23:08:33 <tswett> Mmm I don't feel like it.
23:10:29 -!- oren has quit (Ping timeout: 264 seconds).
23:12:34 -!- Lymia has quit (Remote host closed the connection).
23:13:09 -!- Lymia has joined.
23:13:38 <tswett> People don't sell unlimited-size RAM, either.
23:14:19 <tswett> Say each queue has four pins. Input, output, enqueue, dequeue.
23:14:26 <callforjudgement> so you can add more tape when you run out, without needing an infinite number of address bits
23:15:02 <callforjudgement> even if we assume our infinite queues are self-powering, they still need power pins to know what logic levels to use
23:15:03 <tswett> Does the clock count towards transistor count?
23:15:23 <callforjudgement> well it's very hard to make a clock with nothing but transistors
23:15:34 <callforjudgement> I think you can make a clock with one transistor plus a bunch of extra components
23:15:56 <callforjudgement> although I think that might give you a sine wave rather than a square wave? probably good enough, anyway
23:16:21 <tswett> So lemme think how this ultra-tiny CPU would work.
23:17:24 <tswett> I think the state could just be stored in a single flip-flop or whatever.
23:18:16 <oerjan> i hear this guy named babbage had an idea to make a computer with no transistors at all
23:18:20 <tswett> Mm, maybe two. Execute one command per two clock cycles.
23:19:12 <callforjudgement> oerjan: yes, but the implication is that we're making one with /only/ transistors
23:19:49 <tswett> Okay, so you have a one-bit register S, where zero means we're about to read the first bit of a command and one means we're about to read the second bit of a 1 command.
23:20:18 <tswett> As well as, I dunno, T, where zero means we're about to read a bit and one means we're about to write one.
23:21:32 <tswett> Even if the queue supports that, I'm not sure if the CPU logic could handle that.
23:21:56 <tswett> Well, this is what it is.
23:22:10 <tswett> T = 0 means we're about to read a bit. T = 1 means we're about to enqueue or dequeue a bit.
23:22:17 <tswett> You can't dequeue a bit and read a bit in the same clock cycle.
23:24:04 <tswett> So, upon clock positive edge, if T = 0 and S = 0, then we dequeue the data queue, enqueue the program queue, and subsequently dequeue the program queue.
23:24:19 <tswett> Except can you enqueue and dequeue in the same clock cycle?
23:24:34 <tswett> Maybe we can make it so that you enqueue on positive edge and dequeue on negative edge.
23:25:31 <tswett> The program queue's input and output pins can just always be shorted together. The enqueue and dequeue pins can be controlled by a single wire, but one of the pins needs to have a not gate before it.
23:28:25 <tswett> Which logic style (or whatever you call it) are we using?
23:29:05 <dulla> so an infinite without infinite addressing is more or less tape + some instruction storage?
23:29:10 <callforjudgement> I think RTL is going to be cheapest in most cases? or randomly changing between NMOS and PMOS?
23:29:13 <dulla> infinite tape without*
23:29:38 <callforjudgement> you don't want a logic style that drives both up and down because that needs twice as many transistors, even if it is more efficient
23:32:54 -!- scarf has joined.
23:33:32 <tswett> And are these real transistors governed by calculus, or idealized ones which act kinda like relays?
23:34:52 -!- callforjudgement has quit (Ping timeout: 245 seconds).
23:35:19 <scarf> tswett: real analog transistors, but I don't see why we can't use them in the digital range
23:35:26 -!- scarf has changed nick to ais523.
23:36:05 <ais523> (for people who don't know, there are a range of ways to use transistors, but some make them act quite like amplifiers, and others make them act very digitally)
23:39:26 <oerjan> dulla: an infinite tape + a controlling finite state automaton, that's what a turing machine is.
23:42:07 -!- Sprocklem has quit (Ping timeout: 255 seconds).
23:53:53 -!- chaosagent has joined.
23:54:25 <tswett> You know what my favorite analog electronic component is?
23:54:31 <tswett> The Fourier transformer.
23:59:30 <ais523> how complex is one of those?
00:02:01 <tswett> Unless, of course, its preimage is an even function.
00:04:20 -!- adu has quit (Quit: adu).
00:15:55 -!- kcm1700_ has joined.
00:19:59 -!- kcm1700 has quit (Ping timeout: 246 seconds).
00:27:36 -!- adu has joined.
00:30:36 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:35:49 -!- adu has quit (Quit: adu).
00:42:48 -!- adu has joined.
00:44:21 -!- Sprocklem has joined.
01:11:01 -!- boily has joined.
01:11:17 -!- dorei has quit.
01:11:46 <lambdabot> CYUL 140100Z 25007KT 15SM SKC M22/M30 A3012 RMK SLP204
01:12:21 <oerjan> for once, the outside weather is immaterial.
01:12:22 <boily> the sickness disprovement worsened again?
01:12:26 <lambdabot> ENVA 140050Z 13002KT 1000 R09/P2000N R27/P2000N SN VV003 M01/M01 Q1012 RMK WIND 670FT 17001KT
01:12:41 <boily> the outside weather is the kind where your eyelids try to freeze together.
01:12:48 <boily> (seriously. no joke.)
01:13:26 <boily> oerjan: are you still mainly oerjan, or has the flu made a coup and installed a new government in you body?
01:13:33 <oerjan> well the _flu_ isn't getting that much worse now, but my back is really longing for an outside walk. and then there had to pop up a canker sore just for completeness.
01:15:46 <quintopia> cold as in temperature or illness?
01:15:59 <boily> temperature. re the previous @metar.
01:16:34 <boily> > (-21) * 9/5 + 32
01:17:08 <boily> quintopia: it's -21 °C (-6 °F) outside. much fun.
01:17:25 <oerjan> the last one sort of interfers with plans to gorge on comfort pizza and chocolate
01:17:45 <oerjan> (that's generally the right thing to do with a flu, right?)
01:18:05 <quintopia> feed a flu, starve an eating disorder?
01:18:10 <boily> for me it's large doses of chicken noodle soup and OJ.
01:18:16 * oerjan fetches some chocolate anyway
01:18:28 <quintopia> thank goodness they invented kanka eh
01:18:41 <quintopia> i always buy some and can never find it when i need it next
01:18:55 <boily> speaking of pizza, today we ordered a special gigantic oversized poutine, with sausage, ham, mushrooms and bell peppers in it.
01:19:03 <boily> quintopia: what's a kanka?
01:19:05 <oerjan> well i _have_ had OJ, although i only drink half a cup per day as my stomach doesn't hold well with too much sour
01:19:08 <quintopia> that sounds like a good approach to cold weather
01:19:16 <quintopia> boily: medication for canker sores
01:19:54 <quintopia> i probably wouldn't need it if i brushed more regularly eh
01:20:06 <quintopia> so what you gotta do tonight boilyface
01:20:08 <boily> ah! something like anbesol!
01:20:17 <oerjan> my understanding is that chicken soup for healing is an american thing, possibly jewish in origin.
01:20:26 <boily> don't care; has chicken.
01:21:08 <boily> hm... I'll have to investigate that mysterious product.
01:21:28 <boily> meanwhile, tonight is the night where nothing happens much.
01:23:22 <boily> uhm... <_<'... mainly reddit browsing hth
01:23:59 <quintopia> so hard to find people who want to game with me
01:24:25 <boily> sorry, completely exhausted. I don't know how many hours I worked this week.
01:27:28 -!- Patashu has quit (Remote host closed the connection).
01:28:43 -!- Patashu has joined.
01:29:27 -!- Sprocklem has quit (Ping timeout: 245 seconds).
01:30:11 <tswett> Depends on the game and how you play it.
01:30:34 <tswett> When I play Starcraft, if I'm trying hard to win, it's pretty stressful.
01:31:21 <quintopia> just fucking around and messing with stuff
01:34:20 <zzo38> If you don't like Starcraft then play game "I don't know"craft
01:35:39 <quintopia> i don't know if i like starcraft, but i'll play "I don't know"craft when you finish writing it.
01:37:03 <zzo38> Or, try to play Washizu mahjong by internet if you have any software to do so.
01:37:31 <quintopia> I already beat and 100%ed that game
01:53:39 -!- boily has quit (Quit: SPLIT CHICKEN).
02:02:14 -!- skj3gg has joined.
02:11:48 -!- Tritonio has quit (Ping timeout: 252 seconds).
02:12:37 -!- skj3gg has quit (Quit: ZZZzzz…).
02:24:07 -!- ais523 has quit.
03:21:07 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
03:44:48 -!- doesthiswork has joined.
03:47:18 -!- bb010g has joined.
03:58:02 <zzo38> Why is it permitted for names of elements and attributes in XML to contain non-ASCII characters? My opinion is this is stupid and it shoudln't be. Non-ASCII characters should only be allowed in text (both normal and CDATA), values of attributes, and comments.
03:58:51 <pikhq> XML is overly complex as a rule.
04:00:48 <zzo38> Yes it is too complex, although it presumably is doing what it needs to do. Still a few things are a bit stupid.
04:01:17 <pikhq> Take a quick look at the processing instructions. :)
04:05:14 <zzo38> While it does have a lot of extensions, most of them are optional (and does not affect the syntax of the document) so it is not a problem. If you can ignore unknown processing instructions then it might work in some cases.
04:07:06 <zzo38> It does have a few good ideas such as namespaces, although the method of doing this might be a bit more complicated than it should be.
04:09:07 <zzo38> It does have far more complexity than it should have, although some files/services are using XML so a XML parser would be needed.
04:12:48 -!- Sprocklem has joined.
04:19:25 -!- dulla_ has joined.
04:19:29 -!- dulla has quit (Ping timeout: 264 seconds).
04:19:36 -!- dulla_ has changed nick to dulla.
04:20:48 -!- shikhin_ has quit (Ping timeout: 245 seconds).
04:21:00 <coppro> pikhq: wasn't "overly complex" a design goal?
04:22:47 <coppro> also related: oh my god I cannot wait for HHTP/2
04:23:54 <oerjan> hyperhyped transfer protocol
04:25:11 <pikhq> coppro: Not really.
04:25:21 <pikhq> It was supposed to be a simplified subset of SGML.
04:26:02 <oerjan> then they forgot to shoot the enterprise people before they started designing.
04:43:16 -!- nys has quit (Quit: quit).
04:48:49 <pikhq> oerjan: Common problem.
05:01:18 <pikhq> Clearly the proper answer is to murder enterprises.
05:25:56 <zzo38> I want to read XML files in SQLite. I don't need DTD and encryption and fancy stuff like that, although I do want namespaces, and it would also help to support queries.
05:30:51 <zzo38> Is there suitable C library to do it with? With simple one file and don't need a configure script and so on
05:31:50 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
05:48:08 -!- bb010g has quit (Quit: Connection closed for inactivity).
05:50:19 -!- MDude has joined.
06:09:22 -!- chaosagent has quit (Remote host closed the connection).
06:18:57 -!- copumpkin has joined.
06:32:24 -!- vanila has joined.
06:37:41 <MDude> I keep getting distracted from writing things, and need to go to bed.
06:38:30 <MDude> Also, I got a microSD card but immediatley forgot the adapter to plug it into normal sized SD slots.
06:39:23 <MDude> Maybe I left that downstars actually.
06:41:13 <MDude> But yeah, I should write about ideas on chatbots and AI and stuff already instead of waiting until I implement stuff to write about it.
06:41:42 <MDude> Since getting my idea down somewhere probably helps get to work actually following through with it.
06:42:53 -!- adu has quit (Quit: adu).
06:47:32 -!- ProofTechnique has joined.
06:57:55 <zzo38> What is your idea about it?
07:06:01 -!- doesthiswork has quit (Quit: Leaving.).
07:07:17 -!- doesthiswork has joined.
07:08:25 -!- doesthiswork has quit (Client Quit).
07:08:40 -!- bb010g has joined.
07:14:13 -!- Sprocklem has quit (Ping timeout: 264 seconds).
07:17:22 <MDude> I don't want to distract myself from sleeping currently.
07:18:03 <MDude> I'll try to get some stuff written down tomorrow, I'll try to do that first and then link the posts to talk about them.
07:18:19 -!- MDude has changed nick to MDream.
07:19:36 <MDream> It's all very simple stuff.
07:19:57 <dulla> I'm still interested
07:20:20 -!- Tod-Autojoined has joined.
07:22:19 <MDream> I think I mentioned some of it before, about making variants of chatbots.
07:22:41 <MDream> But yeah, I need to make sure I'm not up too late.
07:23:37 -!- NihilistDandy has joined.
07:23:49 <MDream> Of the general idea of how they work.
07:24:19 <dulla> or they have more general functionality
07:24:41 <dulla> but that'd require run-time reloading/factoring, or a dynamic structure which is a pain nin the cock
07:24:48 <MDream> The first idea I had on it was when thinking about how chatbots left in public tend to pick up rude behavior.
07:25:44 <MDream> If you string two chatbots together, the first one can do the learning, but isntead of speaking directly to the user it can pass it message through a more hardcoded chatbot that paraphrases it.
07:26:15 <MDream> And from there I came up with other ideas in which a chatbot is considered a node in a larger network.
07:26:59 <dulla> so more or less a multi-layer ANN for information representation
07:27:05 <dulla> So that shit stays pg
07:27:16 <dulla> and that they can't teach your dog to respond to a retarded name
07:27:40 <dulla> With multiple inputs, it can gather more data in the long run
07:27:58 <dulla> Though you'd need to enforce some kind of channel-locality to some of the endpoints
07:28:06 -!- ProofTechnique has quit (*.net *.split).
07:28:07 -!- TodPunk has quit (*.net *.split).
07:28:07 -!- paul2520 has quit (*.net *.split).
07:34:04 <MDream> This seems like a good place to leave it for now, rather than stringing things along further.
07:35:56 -!- paul2520 has joined.
07:46:42 -!- vanila has quit (Quit: Leaving).
07:55:48 -!- Lymia has quit (Ping timeout: 245 seconds).
07:59:59 -!- Lymia has joined.
09:20:04 -!- Taneb has quit (Ping timeout: 250 seconds).
09:22:19 -!- Taneb has joined.
09:30:10 -!- Patashu has quit (Disconnected by services).
09:30:10 -!- Patashu_ has joined.
09:33:06 -!- Patashu_ has quit (Remote host closed the connection).
09:33:18 -!- Patashu has joined.
09:36:44 -!- Patashu has quit (Disconnected by services).
09:36:44 -!- Patashu_ has joined.
09:47:29 -!- mihow has joined.
10:01:19 -!- Phantom_Hoover has joined.
10:23:23 -!- augur has quit (Ping timeout: 246 seconds).
10:35:12 -!- heroux has joined.
10:38:06 -!- augur has joined.
10:51:17 -!- mihow has quit (Quit: mihow).
10:59:23 -!- augur has quit (Ping timeout: 246 seconds).
11:14:02 -!- SopaXorzTaker has joined.
11:14:31 -!- augur has joined.
11:16:33 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
11:22:33 -!- augur has quit (Ping timeout: 256 seconds).
11:29:13 -!- Patashu_ has quit (Ping timeout: 264 seconds).
11:29:13 -!- augur has joined.
11:55:17 -!- ^v has quit (Read error: Connection reset by peer).
11:55:44 -!- ^v has joined.
12:03:14 -!- AndoDaan has joined.
12:17:13 -!- SopaXorzTaker has quit (Ping timeout: 255 seconds).
12:55:15 -!- Tritonio has joined.
13:13:35 -!- boily has joined.
14:12:12 -!- SopaXorzTaker has joined.
14:21:08 -!- Phantom_Hoover has joined.
14:32:27 -!- GeekDude has joined.
15:17:21 -!- shikhin has joined.
15:35:42 -!- Tritonio has quit (Remote host closed the connection).
15:36:16 -!- Tritonio has joined.
15:41:18 -!- skj3gg has joined.
15:41:26 -!- AndoDaan has quit (Read error: Connection reset by peer).
15:41:54 -!- AndoDaan has joined.
15:45:38 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
16:02:33 -!- SopaXorzTaker has quit (Ping timeout: 265 seconds).
16:04:08 -!- Tritonio has quit (Ping timeout: 252 seconds).
16:14:44 -!- SopaXorzTaker has joined.
16:31:33 -!- hjulle has quit (Ping timeout: 246 seconds).
16:47:51 -!- boily has quit (Ping timeout: 250 seconds).
16:50:43 -!- boily has joined.
16:51:21 -!- ais523 has joined.
16:56:24 -!- Tritonio has joined.
17:01:40 -!- oren has joined.
17:03:11 -!- MDream has quit (Read error: Connection reset by peer).
17:06:31 -!- conehead has quit (Quit: ZNC - http://znc.in).
17:15:56 -!- oren has quit (Quit: Lost terminal).
17:28:54 -!- adu has joined.
17:33:29 -!- adu has quit (Read error: Connection reset by peer).
17:34:15 -!- adu has joined.
17:41:54 -!- skj3gg has quit (Quit: ZZZzzz…).
17:55:46 -!- conehead has joined.
17:57:54 -!- skj3gg has joined.
18:00:40 -!- mrohman has joined.
18:01:06 <mrohman> This irc client eats 20% cpu
18:02:21 <mrohman> Most cpu consuming client ever
18:04:21 <mrohman> Is there yet an or-typesystem?
18:05:48 <mrohman> (List (if p 5 5.0) "hi") has the type 《int or double or string》
18:08:37 <oerjan> mrohman: i've seen such a system for lambda calculus but damn if i can manage to google it
18:09:27 <ais523> mrohman: I was working on this in my thesis
18:09:29 <elliott> there are type systems like that. i forget the name. gradual typing systems often have it. typed racket is like that i think
18:09:32 <ais523> the normal search term is "intersection types"
18:09:47 <oerjan> i tried "disjunctive" or "conjunctive" :P
18:10:13 <ais523> my favourite prior work on the subject was by Kfoury
18:10:21 <ais523> let me see if there's a publicly available link
18:10:46 <oerjan> it seems rather obscure to find regardless
18:11:30 <oerjan> actually i'm not sure this is the same thing
18:11:40 <oerjan> what i remember was _untagged_ types
18:12:05 <ais523> here we go: http://hdl.handle.net/2144/1597
18:12:18 <ais523> it's a technical report, so should be available even if you don't have subscriptions to every journal in existence
18:12:23 <ais523> (I like technical reports for that reason)
18:12:35 <ais523> that's very close to the stuff I was doing in my thesis, btw
18:12:38 <oerjan> e.g. \f x -> f (f x) had a type like ((x -> y) /\ (y -> z)) -> x -> z
18:13:16 <ais523> oerjan: that's exactly the type it gets in my bounded intersection types
18:13:23 <ais523> and regular intersection types also give it the same type
18:13:41 <oerjan> also, if you added an omega type that everything belonged to, you could characterize terminating terms in untyped LC as those that could be typed with the omega in only negative positions
18:14:48 <oerjan> (where negative position corresponds roughly to "you can take this as an argument but not return it")
18:15:08 <oerjan> and also to contravariance in functor terms
18:15:13 -!- skj3gg has quit (Quit: ZZZzzz…).
18:15:27 <oerjan> note also that there was no quantification in this type system
18:15:28 -!- skj3gg has joined.
18:16:22 <oerjan> oh and you didn't need omega for strongly normalizing terms
18:16:48 -!- ^v has quit (Read error: Connection reset by peer).
18:17:14 -!- ^v has joined.
18:17:28 <oerjan> come to think of it, this was precisely the subject which got me to make my first SO post, way back
18:21:58 <oerjan> i guess "top" type mentioned in that report abstract is the same as omega
18:38:15 <mrohman> I thought intersection types had something to do with value ranges
18:38:56 <mrohman> Certain expressions in my type system would bind a type
18:39:01 <oerjan> that's probably interval types
18:40:04 <mrohman> (If (isint q) (add 1 q) (strreverse q))
18:40:40 <mrohman> This would imply that q is (int ot str)
18:40:42 <oerjan> pattern matching is so much more elegant
18:40:58 <mrohman> So the add wouldnt typecheck
18:41:50 <mrohman> However you can add a rule that the if check binds q in subexpressions to a specific type
18:42:31 <mrohman> Which allows that add there typechecks statically as well
18:54:27 <mrohman> So in an essence the only reason for dynamic typed languages is being too lazy to write a typechecker
19:02:45 -!- Sprocklem has joined.
19:02:45 -!- Sprocklem has quit (Changing host).
19:02:45 -!- Sprocklem has joined.
19:02:50 -!- Sprocklem has quit (Read error: Connection reset by peer).
19:04:08 <boily> mrhello.. mrohello? mrohmhellon??? hmm... hellohman, perhaps?
19:05:38 <boily> mrhelloman. I guess dynamic typed languages are "it works until it doesn't and you hit some runtime error", and static are "it doesn't compile until it does".
19:06:26 <ais523> I think you can write programs in dynamic languages that can't be decidably type-checked (without rewording them)
19:08:30 -!- shikhin_ has joined.
19:08:36 <oerjan> f(n) = if n == 1 then "hi" / 0 else if odd n then f(3*n+1) else f(n `div` 2)
19:09:46 <boily> I'm not sure ghc will accept a blatant use of ‘"hi" / 0’.
19:11:14 <ais523> > f(n) = if n == 1 then "hi" / 0 else if odd n then f(3*n+1) else f(n `div` 2)
19:11:15 <lambdabot> <hint>:1:6: parse error on input ‘=’
19:11:27 <ais523> > let f(n) = if n == 1 then "hi" / 0 else if odd n then f(3*n+1) else f(n `div` 2)
19:11:28 <lambdabot> not an expression: ‘let f(n) = if n == 1 then "hi" / 0 else if odd n then f(...
19:11:31 <oerjan> boily: this is supposed to be a dynamical language hth
19:11:32 -!- shikhin has quit (Ping timeout: 246 seconds).
19:11:38 <ais523> > let f(n) = if n == 1 then "hi" / 0 else if odd n then f(3*n+1) else f(n `div` 2) in 0
19:11:39 <lambdabot> Could not deduce (GHC.Real.Fractional [GHC.Types.Char])
19:11:39 <lambdabot> arising from a use of ‘GHC.Real./’
19:11:43 -!- shikhin_ has changed nick to shikhin.
19:12:04 <ais523> I think that would work in a hypothetical dynamically typed Haskell
19:12:18 <oerjan> yes, but it cannot be typechecked then
19:12:18 <ais523> although it has to end in either type mismatch error, or an infinite loop
19:12:54 <oerjan> i assume the point is to have a typechecking that is equivalent to "only err if the program would dynamically do so"
19:13:20 <oerjan> because otherwise, what's the question really.
19:13:59 <ais523> in which case it's obviously undecidable due to TCness
19:14:14 <ais523> err, due to halting problem
19:17:28 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
19:24:25 <dulla> > let f n = if n == 1 then "hi" 0 else if odd n then f (3*n+1) else f (n `div` 2) in 0
19:24:26 <lambdabot> Couldn't match expected type ‘a0 -> t’
19:24:26 <lambdabot> with actual type ‘[GHC.Types.Char]’
19:24:26 <lambdabot> Relevant bindings include f :: a1 -> t (bound at <interactive>:1:5)
19:24:44 <dulla> > let f n = if n == 1 then 1337 else if odd n then f (3*n+1) else f (n `div` 2) in 0
19:24:54 <dulla> > let f n = if n == 1 then 1337 else if odd n then f (3*n+1) else f (n `div` 2) in f 0
19:25:04 <dulla> > let f n = if n == 1 then 1337 else if odd n then f (3*n+1) else f (n `div` 2) in f 1
19:25:10 -!- Tod-Autojoined has changed nick to TodPunk.
19:25:33 <dulla> > let f n = if n == 1 then 1337 else if odd n then f (3*n+1) else f (n `div` 2) in f 3
19:25:42 <dulla> > let f n = if n == 1 then 1337 else if odd n then f (3*n+1) else f (n `div` 2) in f 9
19:30:25 -!- boily has quit (Quit: ACORN CHICKEN).
19:37:58 -!- skj3gg has quit (Quit: ZZZzzz…).
19:52:27 -!- mitchs has quit (Quit: mitchs).
20:04:48 -!- mitchs has joined.
20:16:53 -!- mrohman has quit (Read error: Connection reset by peer).
20:18:30 -!- skj3gg has joined.
20:19:12 -!- SopaXorzTaker has quit (Remote host closed the connection).
20:28:44 -!- skj3gg has quit (Quit: ZZZzzz…).
20:29:55 -!- skj3gg has joined.
20:39:55 -!- Tritonio has quit (Remote host closed the connection).
20:44:25 -!- Tritonio has joined.
20:45:39 -!- adu has quit (Quit: adu).
20:47:41 -!- GeekDude has joined.
20:47:43 -!- GeekDude has changed nick to Guest87001.
20:48:44 -!- Guest87001 has quit (Changing host).
20:48:44 -!- Guest87001 has joined.
20:48:52 -!- Guest87001 has changed nick to GeekDude.
21:02:04 -!- skj3gg has quit (Quit: ZZZzzz…).
21:09:26 -!- oren has joined.
21:14:41 -!- shikhin has quit (Quit: leaving).
21:20:46 -!- Patashu has joined.
21:23:15 -!- mrohman has joined.
21:24:01 <mrohman> Of course i can typecheck it even if its tc
21:25:10 <oerjan> not in such a way that exactly the non-erring programs fail to typecheck
21:25:43 <oerjan> PLEASE ADD/REMOVE A NEGATION AS APPROPRIATE
21:26:39 <oerjan> mrohman: you cannot make a typechecker that accepts all programs that wouldn't give a dynamic error and none that would, and does so before running the program
21:27:46 <mrohman> You mean (if p a b ) where b produces a runtime type error
21:28:31 <mrohman> But thats not what i'm aiming for
21:29:30 <mrohman> It's just that i want the style of such languages with static typechecking
21:29:58 <oerjan> i think the word "hybrid" belongs in there somewhere then hth
21:30:56 <mrohman> Which means that you have to account for ifs not always returning the same type
21:31:25 <oerjan> did you know that "hybrid types" gives you a lot of information on cars tdnh unless that's what you're looking for i guess
21:31:57 <mrohman> You wont need runtime typechecks then
21:33:41 -!- mrohman has quit (Remote host closed the connection).
21:39:32 -!- skj3gg has joined.
21:47:26 <zzo38> You could make the compiler to defer the error until runtime, although this doesn't seems like very good in most cases (although maybe in some cases it might help, if it is possible at all in such case).
21:49:52 -!- skj3gg has quit (Quit: ZZZzzz…).
21:53:05 -!- adu has joined.
21:58:22 -!- skj3gg has joined.
22:09:01 -!- oren has quit (Quit: Lost terminal).
22:22:05 -!- skj3gg has quit (Quit: ZZZzzz…).
22:39:34 -!- skj3gg has joined.
22:40:08 -!- ais523 has quit (Ping timeout: 246 seconds).
22:45:44 -!- Phantom_Hoover has joined.
23:02:33 <Sgeo> I can't tell if this soundfont has piano keys that last too long or if this music is just bad
23:19:48 -!- skj3gg has quit (Quit: ZZZzzz…).
23:26:10 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
23:27:22 -!- ais523 has joined.
23:27:46 -!- copumpkin has joined.
23:36:48 <Vorpal> Sgeo, you could say that is a key question
23:39:34 * Sgeo goes to buy all Ray Lynch music on Amazon
23:46:03 -!- augur has quit (Quit: Leaving...).
23:52:14 -!- yorick has quit (Remote host closed the connection).
00:09:45 -!- yorick has joined.
00:10:08 -!- yorick has changed nick to Guest20901.
00:13:56 -!- Guest20901 has quit (Client Quit).
00:14:22 -!- augur has joined.
00:14:48 -!- yorick_ has joined.
00:15:11 -!- yorick_ has changed nick to Guest64625.
00:16:22 -!- Guest64625 has quit (Client Quit).
00:16:52 -!- yorick__ has joined.
00:20:20 -!- yorick__ has quit (Changing host).
00:20:21 -!- yorick__ has joined.
00:21:33 -!- yorick__ has changed nick to yorick.
00:29:21 <Taneb> I seem to be going to Edinburgh the weekend after next
00:29:39 <Taneb> Phantom_Hoover, why are train tickets to Edinburgh like twice as expensive as train tickets to Hexham?
00:29:50 <Taneb> Is it because Edinburgh is, in fact, twice as far away from here as Hexham?
00:30:16 <Phantom_Hoover> of course there's also the customs duty on importing englishness
00:30:59 <Taneb> Am I allowed to protest that I am in fact only 50% English?
00:31:30 <zzo38> I suppose you can ask
00:32:34 <Vorpal> Taneb, price is generally roughly correlated with the length of travel yes. In most parts of the world at least.
00:33:34 <oerjan> god, google map's ui has got annoying
00:33:38 <Phantom_Hoover> the trains tend to be so empty after newcastle it wouldn't be unexpected if they charged less, though
00:33:54 <Taneb> Vorpal, I was mostly surprised at the price because I've ended up with an instinct for train ticket prices entirely based on the York <-> Hexham route
00:34:04 <oerjan> all i want to do is pan in such a way that i can see edinburgh, hexham and york simultaneously :(
00:34:25 <Taneb> oerjan, Hexham is precisely the midpoint of the two cities
00:36:06 <oerjan> no GM, when i double click on the map i _don't_ want you to zoom out to the whole UK
00:38:24 <oerjan> what is the point of showing a smooth zooming if i cannot _stop_ it at an intermediate point
00:38:50 <Phantom_Hoover> which, if you've been very good this year and said the appropriate prayers, might be slightly under £60
00:44:32 <lambdabot> quote <nick>: Quote <nick> or a random person if no nick is given
00:44:48 <Taneb> Bah, I think the quote I am after is on lambdabot and I do not know how to search
00:48:32 <lambdabot> No quotes match. And you call yourself a Rocket Surgeon!
00:49:01 <lambdabot> thermoplyae says: <thermoplyae> someone finally pointed out to me that a monad is an monoid-object in an endofunctor category <thermoplyae> i have no idea how i've never seen that before
00:49:07 <oerjan> definitely not just nicks
00:51:14 <Taneb> Actually, no, it was on HackEgo
00:51:27 <Taneb> Something about a cage with a lambda underneath used as a trap
00:51:34 <HackEgo> 225) <Gregor> !bfjoust furry_furry_strapon_pegging_girls http://sprunge.us/eKWa * Sgeo had no idea that Gregor was hetero
00:52:35 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:59:33 <HackEgo> 103) <Mathnerd314> Gregor-P: I don't think lambda calculus is powerful enough \ 332) [after a long string of Lymia getting lambdabot to spit out huge, meaningless type signatures] <Lymia> I need to learn more Haskell... <CakeProphet> ..I need to get op privs. \ 410) <monqy> rest in peace lambdabot???? <ais523> monqy: it'll probably be back later
00:59:50 <oerjan> `` quote lambda | tail -10
00:59:51 <HackEgo> 103) <Mathnerd314> Gregor-P: I don't think lambda calculus is powerful enough \ 332) [after a long string of Lymia getting lambdabot to spit out huge, meaningless type signatures] <Lymia> I need to learn more Haskell... <CakeProphet> ..I need to get op privs. \ 410) <monqy> rest in peace lambdabot???? <ais523> monqy: it'll probably be back later
01:00:04 <ais523> `` quote lambda | tail -1
01:00:05 <HackEgo> 1203) <Bike> scheme doesn't have any control structures, you can make them yourself out of call/cc, lambdas, and arrogance
01:00:07 <oerjan> `` quote lambda | tail -5
01:00:08 <HackEgo> 410) <monqy> rest in peace lambdabot???? <ais523> monqy: it'll probably be back later <monqy> nap in peace \ 497) <CakeProphet> monqy: help how do I use lambdabot to send messages to people. [...around half an hour later...] <CakeProphet> @messages <lambdabot> quicksilver said 1y 2m 18d 19h 54m 29s ago: you use @tell \ 525) <Taneb> I think this
01:00:29 <oerjan> `` quote lambda | tail -2
01:00:29 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.9373
01:00:30 <HackEgo> 892) <shachaf> FOUR SIMULTANEOUS TYPE SYSTEMS IN A SINGLE ROTATION OF THE LAMBDA CUBE \ 1203) <Bike> scheme doesn't have any control structures, you can make them yourself out of call/cc, lambdas, and arrogance
01:00:41 <oerjan> `` quote lambda | tail -3
01:00:55 <HackEgo> 525) <Taneb> I think this has taught us one thing. We can't teach itidus20 lambda calculus by comittee \ 892) <shachaf> FOUR SIMULTANEOUS TYPE SYSTEMS IN A SINGLE ROTATION OF THE LAMBDA CUBE \ 1203) <Bike> scheme doesn't have any control structures, you can make them yourself out of call/cc, lambdas, and arrogance
01:00:58 <Taneb> Whatever happened to itidus
01:01:06 <Taneb> Like, after he left the channel
01:01:43 <ais523> 497 is still one of the best quotes ever
01:01:47 <oerjan> he probably transcended to a higher plane of confusion
01:02:37 <Vorpal> <oerjan> god, google map's ui has got annoying <-- website? app?
01:03:20 <Vorpal> oerjan, you could also try openstreetmap maybe?
01:03:57 <Vorpal> oerjan, Hm yeah it doesn't do smooth scrolling fully afaik
01:04:06 <oerjan> well it was like, linked from the google result page for "york"
01:04:12 <zzo38> Is it possible to import openstreetmap data into SQLite?
01:04:54 <Vorpal> zzo38, probably, but oh god the performance?
01:05:32 <Vorpal> iirc they use postgresql + postgis as their backend for vector data
01:06:49 <HackEgo> 497) <CakeProphet> monqy: help how do I use lambdabot to send messages to people. [...around half an hour later...] <CakeProphet> @messages <lambdabot> quicksilver said 1y 2m 18d 19h 54m 29s ago: you use @tell
01:07:09 <zzo38> Write a RVTP server for PostgreSQL so that it can access with RVTP client, and then write a RVTP client for SQLite.
01:07:10 <Vorpal> ais523, yeah that is pretty good
01:07:30 -!- sebbu has quit (Ping timeout: 264 seconds).
01:08:04 <zzo38> Some protocol I made up but isn't implemented yet; it is short for "Remote Virtual Table Protocol"
01:08:21 -!- Patashu has quit (Disconnected by services).
01:08:21 -!- Patashu_ has joined.
01:08:34 <Vorpal> Well whatever, I'm not sure anybody cares about importing gigabytes of map data in sqlite.
01:09:02 <Vorpal> And frankly I don't see the point. OpenStreetMap has some good query tools written for it already
01:09:47 <Vorpal> http://overpass-turbo.eu/ for example
01:10:57 <HackEgo> 951) <Phantom_Hoover> Sgeo_, are you just trying to post kmcbait... * Fiora imagines a cardboard box propped up by a stick with a pile of monads inside. <elliott> Fiora: that is actually what Haskell is.
01:11:46 <zzo38> Still it is using a webpage and then you might want to access by command-line
01:26:49 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
01:43:24 <zzo38> Do you know anything about Turtle RDF formats?
01:43:30 -!- AndoDaan has quit (Ping timeout: 264 seconds).
01:54:20 -!- boily has joined.
02:06:04 -!- boily has quit (Quit: ABOLUTIVE CHICKEN).
02:09:56 -!- copumpkin has joined.
03:04:21 -!- sebbu has joined.
03:04:59 -!- sebbu has quit (Changing host).
03:04:59 -!- sebbu has joined.
03:14:25 -!- Tritonio has quit (Remote host closed the connection).
03:20:18 -!- oren has joined.
03:24:05 -!- Sprocklem has joined.
03:24:49 -!- ^v^v has joined.
03:27:53 -!- ^v has quit (Ping timeout: 245 seconds).
04:00:59 -!- lokita23 has joined.
04:01:36 -!- ^v has joined.
04:01:36 -!- lokita23 has quit (Read error: Connection reset by peer).
04:17:27 <zzo38> A virtual table in SQLite could have read-only fields, write-only fields, and compare-only fields.
04:20:28 -!- not^v has joined.
04:23:18 -!- ^v has quit (Ping timeout: 245 seconds).
04:24:34 -!- not^v has quit (Read error: Connection reset by peer).
04:25:23 -!- not^v has joined.
04:27:53 -!- bb010g has quit (Ping timeout: 245 seconds).
04:29:08 -!- nyuszika7h has quit (Ping timeout: 245 seconds).
04:30:16 -!- not^v has quit (Ping timeout: 265 seconds).
04:30:42 -!- nyuszika7h has joined.
04:38:29 -!- bb010g has joined.
04:54:19 -!- nyuszika7h has quit (Read error: Connection reset by peer).
04:55:48 -!- skarn_ has quit (Ping timeout: 245 seconds).
04:56:02 -!- nyuszika7h has joined.
04:56:13 -!- pikhq has quit (Ping timeout: 245 seconds).
04:56:13 -!- fractal has quit (Ping timeout: 245 seconds).
04:56:21 -!- pikhq has joined.
04:56:29 -!- arjanb has quit (Quit: .).
04:57:39 -!- skarn has joined.
05:01:48 -!- fractal has joined.
05:04:19 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:46:10 -!- not^v has joined.
05:46:20 -!- ^v has joined.
05:46:24 -!- ^v has quit (Client Quit).
05:47:48 -!- not^v has quit (Read error: Connection reset by peer).
05:57:23 -!- ^v has joined.
06:10:04 -!- oren_ has joined.
06:10:25 -!- oren has quit (Ping timeout: 246 seconds).
06:11:28 <oren_> I recieved an awesome book today. Nelson's Japanese-English Character Dictionary. It is a bit outdated, but beautiful and easy to look kanji up in.
06:16:14 <ais523> some of the art contributed to NetHack 4 contains what are apparently Chinese characters
06:16:21 <ais523> and I want to make sure that they don't say anything rude or out-of-place
06:16:37 <zzo38> You should try to learn what it does mean anyways
06:17:46 <oren_> Isn't nethack a text-based game?
06:18:28 <zzo38> I think you can do icon-mode too though?
06:18:41 -!- not^v has joined.
06:19:19 <oren_> zzo38: googled it, yeah apparently there is a mode with actual graphics
06:20:19 <ais523> oren_: I'm implementing both multiple graphical modes, and multiple text modes
06:20:36 <ais523> anyway, here it is: http://nethack4.org/pastebin/unknown-chinese.png
06:20:53 <ais523> I'd put it into Google Translate or the like, but I don't know how to translate the image into ideograms
06:21:27 <ais523> especially given how small the image is
06:21:30 -!- ^v has quit (Ping timeout: 250 seconds).
06:21:40 <zzo38> I suppose multiple text mode can be ASCII mode, PC mode, VT100 mode, and Unicode xterm mode, and also colors or monochrome, and there are some other kind of details too I think; would that be it?
06:21:44 <ais523> anyone have ideas for an OCR that works on Chinese?
06:22:20 <zzo38> I don't have any OCR, but I know there is servers to look up by radicals and other methods that you can pick from the form
06:22:28 <ais523> zzo38: well, currently the user specifies what characters they want; there are two implemented modes for this, one selection uses only characters that exist in ASCII, the other uses only characters that exist in codepage 437
06:22:36 <ais523> and then the game engine works out how to render it
06:22:39 <oren_> last character is 少 meaning "small" not sure about the other two
06:22:52 <ais523> no I don't think it is
06:23:00 <ais523> the top-left stroke is sloping top left to bottom right
06:23:05 <ais523> not bottom left to top right
06:23:20 <ais523> (also flavour implies that this is Chinese rather than Japanese)
06:23:24 <zzo38> You also have to look if it is Simplified Chinese or if it is Traditional Chinese
06:23:31 <ais523> I don't know, is the answer
06:23:35 <ais523> it may well be meaningless
06:23:41 <ais523> I just don't want it to be meaningful in an offensive way
06:24:21 <zzo38> (My opinion is that Traditional Chinese is better; however, inside of China it is usually Simplified is used)
06:24:52 <zzo38> What are those Chinese icons used for anyways?
06:24:57 <ais523> zzo38: I think the majority use is different between mainland China and Taiwan, isn't it?
06:25:00 <ais523> and they decorate a wall
06:25:04 <ais523> in the tileset called "Chinese wall"
06:25:10 <ais523> which is why I think it's meant to be Chinese
06:26:38 <zzo38> ais523: As far as I understand, Simplified is used in China, and Traditional is for everywhere else in the world
06:27:08 <oren_> Japan has its own less simple simplifications
06:27:24 -!- v^ has joined.
06:27:42 <oren_> they are called 新字体 (shinjitai)
06:28:06 <zzo38> oren_: Yes I know that too, and theirs aren't as difficult understanding as Simplified Chinese, I think.
06:28:50 <oren_> zzo38: I can see that. In my new book the traditional version is listed beside each character and they are usually barely different
06:29:44 -!- ^v^v has quit (Ping timeout: 250 seconds).
06:30:03 <oren_> one of the bigger chages is 竜 from 龍
06:31:30 <oren_> but most of the time it is just changing whether strokes are connected or not, or whether they cross another stroke or not
06:32:19 -!- ^v has joined.
06:35:22 -!- not^v has quit (Ping timeout: 250 seconds).
06:37:17 <ais523> hmm, now I'm halfway though character map looking for them
06:37:19 <oren_> I tried linedict.com but I can't find anything that looks like the first two characters
06:39:07 <ais523> I guess the first one could be 牜?
06:39:17 <HackEgo> U+725C CJK UNIFIED IDEOGRAPH-725C \ UTF-8: e7 89 9c UTF-16BE: 725c Decimal: 牜 \ 牜 (牜) \ Uppercase: U+725C \ Category: Lo (Letter, Other) \ Bidi: L (Left-to-Right)
06:40:30 <oren_> That's like a halfwidth version of 牛 which means cow
06:41:05 <ais523> the second one is pretty hopeless, I agree
06:42:01 <oren_> but it doesn't really work
06:42:03 <ais523> I don't think there's a great match for the third one either
06:42:24 <HackEgo> U+5936 CJK UNIFIED IDEOGRAPH-5936 \ UTF-8: e5 a4 b6 UTF-16BE: 5936 Decimal: 夶 \ 夶 (夶) \ Uppercase: U+5936 \ Category: Lo (Letter, Other) \ Bidi: L (Left-to-Right)
06:42:34 <oren_> in general chinese characters don't often have a shape like < in them
06:42:52 <ais523> yep, many of the shapes there are quite different from anything I'm seeing in the Unicode list
06:43:18 <ais523> if we go by slope directions of the lines (which are very clear in the third shape), the only option is 氵
06:43:29 <ais523> but I have a feeling that would have been drawn differently
06:43:32 <oren_> If those are chinese characters then they are pixelated out of recognition
06:43:49 <ais523> in that case, I'm probably OK with them, although perhaps we should actually spell something appropriate
06:44:31 <ais523> and 氵 is crazily common, at least, and not particularly awkward
06:44:41 <ais523> (it was nice of Unicode to give definitions)
06:44:43 <oren_> that is the water radical
06:45:35 <ais523> in retrospect, this doesn't actually look very much like a CJK language at all
06:45:41 <ais523> and perhaps is failing to perform its function due to that?
06:47:29 <oren_> most recognizable characters would become orange blocks at that scale...
06:51:18 <oren_> take 街道 which means street for example...
06:54:06 <ais523> isn't that two ideograms?
06:56:45 <oren_> yes two. In chinese Jiēdào. In japanese it is pronounced kaidou and means highway
06:58:11 <ais523> hmm, how cross-intelligable are written chinese and japanese?
06:59:18 <ais523> like french and italian?
07:00:14 <oren_> the japanese-chinese words are mostly ones from the middle ages, so their meanings have shifted, and Mandarin has evolved in the meantime. Japanese and Classical Chinese are much closer
07:00:31 <ais523> so yes, pretty much exactly like french and italian then
07:00:52 <oren_> More like italian and english
07:01:20 <oren_> because japanese has a superstrate of chinese over a japanese substrate
07:01:22 <ais523> sometimes I play computer games set to a foreign language, for fun
07:01:56 <oren_> like english has a latinate superstrate over a germanic substrate
07:03:57 <oren_> ais523: yeah that can be fun
07:07:03 <oren_> The most annoying thing my parents used to do is speak in italian french or spanish, depending on their mood, in order so I couldn't tell what they were saying.
07:08:20 <oren_> it was really annoying to 8 year old me
07:10:14 <oerjan> is that why you learned japanese twh
07:10:54 <oren_> oerjan: It may be why I practice it with my best friend in my dad's office
07:11:53 <oren_> きゃははは、お父さん、分からないか？
07:13:59 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
07:15:20 <ais523> wait, you follow random links in people's quit messages?
07:15:26 <ais523> that's almost like clicking on spam
07:15:47 <oren_> ais523: I do that too
07:16:38 <oren_> I have noscript, adblocker, and this computer is total crap anyway
07:18:05 -!- Patashu_ has quit (Ping timeout: 252 seconds).
07:18:29 <oren_> It's like my dad agressively driving in a 15 yearold ford focus
07:27:40 <oren_> Why can't I smelt cobalt from cobaltite
07:56:06 -!- Sprocklem has quit (Ping timeout: 264 seconds).
08:18:05 -!- oerjan has quit (Quit: Because of the kobolds hth).
08:35:21 -!- shikhin has joined.
09:19:30 -!- naturalog has quit (Ping timeout: 264 seconds).
09:20:06 -!- aloril has quit (Ping timeout: 264 seconds).
09:21:26 -!- tromp__ has quit (Ping timeout: 264 seconds).
09:21:26 -!- jameseb has quit (Ping timeout: 264 seconds).
09:26:06 -!- glogbot has quit (Ping timeout: 264 seconds).
09:26:13 -!- esowiki has joined.
09:26:17 -!- esowiki has joined.
09:26:17 -!- esowiki has joined.
09:27:16 -!- esowiki has joined.
09:27:20 -!- esowiki has joined.
09:27:21 -!- esowiki has joined.
09:27:53 -!- esowiki has joined.
09:27:57 -!- esowiki has joined.
09:27:58 -!- esowiki has joined.
09:28:43 -!- esowiki has joined.
09:28:47 -!- esowiki has joined.
09:28:48 -!- esowiki has joined.
09:29:47 -!- esowiki has joined.
09:29:51 -!- esowiki has joined.
09:29:51 -!- esowiki has joined.
09:30:23 -!- esowiki has joined.
09:30:27 -!- esowiki has joined.
09:30:28 -!- esowiki has joined.
09:31:13 -!- esowiki has joined.
09:31:17 -!- esowiki has joined.
09:31:18 -!- esowiki has joined.
09:32:03 -!- esowiki has joined.
09:32:04 -!- glogbot has joined.
09:32:07 -!- esowiki has joined.
09:32:08 -!- esowiki has joined.
09:33:35 -!- aloril has joined.
09:38:19 <zzo38> I found some papers on which I have written several kind of chess variants. One is a complex dimensional chess variant.
09:39:09 <zzo38> There is also one where the bishops are now beavers and the king can use a shotgun but only if he has a license.
09:40:02 <b_jonas> you can find lots of chess variants on the internet.
09:42:07 <zzo38> I know and many I have put in too.
09:44:31 <zzo38> There is also "Bland Chess" from my brother; no diagonal moves are allowed (although knights can still move normally).
09:45:21 <zzo38> This means that pawns cannot capture, queens are same as rooks, bishops cannot move at all, and the king moves only one space orthogonally.
09:48:10 <zzo38> There is also a game "Chess With Checkers Added" that both me and my brother have simultaneously invented independently; we both invented the same game. At first he just put the checkers in front of the pawns as a joke but then we both made up the same rules for the game that is set up like that.
09:51:43 <zzo38> Do you make up chess variant too?
09:59:08 <b_jonas> zzo38: hehe, "bland chess" reminds me to two variants Smullyan mentions: one where every piece can move only in a way that it stays on the same colored square that it starts from, so pawns can only move double or (non en-passant) capture,
09:59:23 <ais523> and knights are just stuck?
09:59:26 <b_jonas> and the less restricted version where knights can't move but other figures aren't restricte.
10:00:20 <ais523> clearly we need Evil Chess where the pieces sometimes explode when you move them, and arbitrary time limits are placed on you every now and then, and the rules aren't what you think they are, and there are cutscenes
10:01:17 <zzo38> Another idea if something I wanted to learn how to make up is the chess variant where the commands of INTERCAL are included.
10:01:38 <b_jonas> chess with intercal commands
10:08:12 -!- CrazyM4n has joined.
10:09:27 -!- naturalo1 has changed nick to naturalog.
10:09:30 <zzo38> Is it possible to make a C header file with macros having mangled names so that it can interface with C++ programming?
10:10:29 <ais523> zzo38: not macros, but you can do wrapper functions by using a separate C++ object file
10:10:47 <ais523> which basically has a bunch of C++ functions that call counterparts declared with extern "C"
10:11:33 <b_jonas> zzo38: it depends on the architecture
10:11:51 <zzo38> I wanted to do it without wrapper functions so that the function pointer is the same as the C function
10:11:54 <b_jonas> zzo38: on some compilers or systems, C++ symbols mangle to names that aren't valid in C because they contain weird characters
10:12:26 <b_jonas> wait, let me look up the specifics
10:12:32 <zzo38> On which systems are they? Is it possible with GNU C?
10:12:58 <b_jonas> a moment, I don't know off the top of my head, I just let the compiler and debugger deal with this stuff
10:13:42 <CrazyM4n> So I've been messing around with trying to reverse engineer /dev/input/mice for fun
10:13:47 <CrazyM4n> Did I miss anything? https://gist.github.com/CrazyM4n/553379cf3fa93721664f lol
10:13:51 <b_jonas> the MS compiler use @ signs in mangled names
10:14:26 <b_jonas> all C++-mangled names start with a ? sign
10:14:45 -!- adu has quit (Quit: adu).
10:15:23 <b_jonas> on GNU C, it might be possible because it uses only alphanumeric and underscore characters in mangled names
10:15:47 <zzo38> But the C++ code might be compiled with a different compiler even though I am using GNU
10:16:21 <b_jonas> but of course such a thing might be somewhat fragile and dependent on the version of compiler and libstdc++ you're targetting, not because of the name mangling, but because of the other stuff like representation of library stuff and exceptions and other horrible things
10:16:39 -!- Phantom_Hoover has joined.
10:16:58 <zzo38> I don't actually know what compiler and libc++ and stuff they are using
10:17:29 <b_jonas> zzo38: why don't you use the normal solution, that is, write the wrappers in C++?
10:17:38 <b_jonas> oh wait, wrong channel for that
10:17:56 <zzo38> Like I said maybe it is a different compiler, for one thing
10:18:02 <b_jonas> zzo38: anyway, if you wanted for MSVC, you could try writing in assembler directly
10:18:36 <b_jonas> zzo38: sure, if you don't know the compiler then you can't compile C++ interfaces.
10:18:53 <b_jonas> you have to know the compiler type and version and architecture.
10:20:33 <zzo38> I believe their files are Microsoft but my files are GNU and I want to be able to interface them, preferably only the header file needs to change and the main file can be keep the same one even when interfacing with other C++ programs with other compilers and versions and architectures.
10:21:21 <b_jonas> zzo38: could you make C interfaces for your code, compiled with gnu, and a thin C++ wrapper for it, compiled with MSVC, possibly header-only with inline functions?
10:21:56 <b_jonas> zzo38: for MSVC, if you don't do this and you want to generate the mangled stuff yourself, you might also have to depend on which version of MSVC
10:22:12 <b_jonas> zzo38: if this is not esoteric stuff, then don't do that, and just write a wrapper they have to compile or include
10:22:47 <b_jonas> you can probably make the wrapper portable enough C++ and test it by compiling (including) it in a C++ program compiled with gnu C
10:23:10 <b_jonas> but even then, you can be burned by the various idiocies of the MS compiler regarding C++
10:24:27 <zzo38> I don't even know if I have MSVC, and if I do, I don't know what versions and other stuff
10:25:52 <zzo38> Also it is interfacing with a DLL
10:26:21 <b_jonas> zzo38: sure, but the DLL can have a C interface
10:26:43 <b_jonas> if you give them a thin wrapper they include or compile, then it can be mostly portable among compilers
10:26:51 <zzo38> The program expects to load a DLL file with C++ codes
10:27:09 <zzo38> But I want to write the DLL file with C codes
10:27:11 <b_jonas> well, a DLL with C++ interface can almost never be portable among multiple versions of MSVC, or among gcc and msvc
10:27:26 <b_jonas> so if you want to do that, then you'll have to ask what compiler they're using
10:28:04 <b_jonas> you also have to know the operating system type (windows or linux etc) and the CPU (x86 or x86_64)
10:32:53 -!- skarn has quit (Ping timeout: 245 seconds).
10:33:09 -!- skarn has joined.
10:40:23 -!- Lymia has quit (Ping timeout: 245 seconds).
10:44:56 <ais523> oh no, I just realised
10:45:08 <ais523> the current realtime-viable glitch to the credits in Super Mario World
10:45:13 <ais523> spells out shellcode /using shells/
10:45:25 <ais523> why is this not an observation that I've seen elsewhere
10:49:31 -!- Lymia has joined.
10:54:30 <HackEgo> [wiki] [[Special:Log/newusers]] create * MuEncy12345 * New user account
10:54:42 <ais523> ooh, those digits are in sequence
10:54:45 <ais523> probably not a spambot
10:58:45 <HackEgo> [wiki] [[User:MuEncy12345/Island]] N http://esolangs.org/w/index.php?oldid=41902 * MuEncy12345 * (+785) Created page with "[[User:MuEncy12345/Colloquial|Colloquial]] abbr|eviation of [[User:MuEncy12345/island mu-molecule|Island mu-molecule]], or of User:MuEncy12345/island mu-unit|island mu-un..."
10:59:55 <ais523> and it looks like a copyright-infringing one, too
11:00:21 <HackEgo> [wiki] [[Special:Log/delete]] delete * Ais523 * deleted "[[User:MuEncy12345/Island]]": copyright-infringing spam
11:00:54 <HackEgo> [wiki] [[Special:Log/block]] block * Ais523 * blocked [[User:MuEncy12345]] with an expiry time of 2 decades, 4 years, 4 hours, 19 minutes and 12 seconds (account creation disabled): copyright-infringing spambot
11:00:55 <ais523> I have a feeling that it was planning to make a bunch of pages, all cross-linked
11:01:56 <ais523> "11:00, 15 February 2039"
11:02:03 <ais523> yay, they fixed the Y2038 bug
11:02:04 <vanila> http://mrob.com/pub/muency.html
11:02:14 <ais523> vanila: isn't that the link that was being spammed?
11:02:40 <ais523> why did you post it to the channel
11:04:20 <ais523> definitely copyright infringement
11:04:27 <ais523> less sure on the spam, though, because it links to source
11:04:51 <HackEgo> [wiki] [[Special:Log/block]] unblock * Ais523 * unblocked User:MuEncy12345: maybe not a spambot
11:05:07 -!- CrazyM4n has quit (Remote host closed the connection).
11:06:28 <HackEgo> [wiki] [[User talk:MuEncy12345]] N http://esolangs.org/w/index.php?oldid=41903 * Ais523 * (+568) warning
11:07:37 <vanila> http://mrob.com/cc-license.html
11:07:42 <vanila> you are free to copy and reuse any of this work as long as you tell people where it is from
11:08:23 <ais523> vanila: and it's noncommercial
11:08:35 <ais523> and you preserve copyright notices
11:08:50 <ais523> the wiki's copyright status outright claims a different copyright on everything posted there
11:09:00 <ais523> that is, that anything there can be reused for any purpose, no attribution required
11:09:13 <int-e> almost. "Content is available under CC0 public domain dedication unless otherwise noted."
11:10:06 <int-e> at least the way I'm reading that I could post an article under some other CC license (for example) if I explicitely state that in the article.
11:10:26 <ais523> that's just boilerplate that a wiki upgrade put on there
11:10:41 <ais523> the edit prompt requires a CC0 license
11:11:24 <int-e> ah. it's been a while.
11:11:42 <ais523> yep, bad MediaWiki default
11:11:51 <ais523> you can't go around changing the wiki's copyright status like that!
11:12:23 <HackEgo> [wiki] [[MediaWiki:Copyright]] N http://esolangs.org/w/index.php?oldid=41904 * Ais523 * (+30) a MediaWiki apparently put a bad (lack of) copyright notice on here; fixing that
11:12:56 <vanila> is solar power enough to keep a drone in the air
11:13:20 <ais523> vanila: I believe so, but it has to have a very weird form factor to make enough room for the solar panels
11:13:57 <b_jonas> probably no. if it was, birds would just eat the plants (moss, lichens) grown on their backs and wings rather than actively seeking out food
11:16:29 <b_jonas> this shellcode with shells is a good enough joke that maybe you should ask the tasvideos guys to edit it into the description
11:16:41 <ais523> most people don't know what "shellcode" means
11:16:49 <ais523> and the TASvideos route doesn't use that method of setup
11:16:54 <ais523> rather, it uses the controller ports
11:17:16 <b_jonas> do "most people" watch tases?
11:17:32 <vanila> Did you see a guy perform the exploit by hand?
11:17:35 <ais523> I think speedruns are more popular
11:17:40 <ais523> vanila: yep, it's been done by hand
11:17:45 <ais523> different setup, though
11:17:53 <ais523> there's actually a video explaining all the steps on YouTube
11:18:14 <vanila> I wonder how to find similar code exec type things in NES and gameb oy games
11:18:26 <b_jonas> oh, you said realtime-viable glitch
11:19:16 <b_jonas> I mean, it's not like GB pokémon where you can just edit memory in real time
11:19:36 <b_jonas> or Zelda OOT where they do memory corruption with items in real time
11:20:15 <b_jonas> apparently the GB Super Mario Land 2 memory corruption has been performed in real time too
11:20:25 <b_jonas> so I shouldn't be surprised by any of this anymore
11:22:43 <b_jonas> these real time speedrunners are crazy
11:23:07 <b_jonas> they find their way to perform glitches in real time
11:23:14 <b_jonas> develop very crazy techniques
11:23:23 <ais523> b_jonas: I do realtime speedrunning too
11:23:41 <b_jonas> ais523: ok, but how glitched?
11:24:10 <ais523> wall clips and item duping and exploiting broken scripts, mostly
11:24:12 <b_jonas> mind you, a not very glitched real time speedrun can be also amazing when the player demonstrates good technique
11:24:28 <vanila> do you pull the scripts out of the game and study them?
11:24:40 <ais523> yes, there's a level editor that can read them
11:24:48 <ais523> although you can only use it on levels you've already completed
11:25:05 <ais523> (unless you just rename the files to make them think they're custom)
11:25:39 <b_jonas> on what console or operating system do you speedrun that?
11:25:52 <b_jonas> (I think you mentioned this once already when I asked about silence spells)
11:26:05 <b_jonas> (but it could have been a different game)
11:37:16 -!- Tritonio has joined.
11:37:25 <J_Arcane> I think curly brace syntax might be ergonomically bad for me, at least on a Finnish keyboard. AltGr in general is a problematic key.
11:38:00 -!- TieSoul has changed nick to TieSchool.
11:38:10 -!- TieSchool has changed nick to TieSoul.
11:39:50 <vanila> ive made it so the [/{ and ]/} keys input ( and ) for me
11:39:52 <vanila> that makes lisp easier
11:39:57 -!- Patashu has quit (Ping timeout: 265 seconds).
11:41:19 <J_Arcane> vanila: Yeah, in DrRacket I have Å mapped to automatically output the () or [] pair I need for the context; but right now I'm doing JavaScript tutorials on codecademy; which doesn't even do auto-pairs.
11:52:14 <oren_> I think keyboards in general need more keys. I would put a few more rows above the number row
11:54:09 <oren_> although maybe that wouldn't help if you're a touch-typist
11:54:44 <oren_> I type with two fingers
11:56:18 <ais523> J_Arcane: () or [] are a little easier to type than Å (capslock shift-a a for me)
11:57:00 <J_Arcane> ais523: å, rather, which is a plain key on a Finnish keyboard.
11:57:25 <ais523> that's where [ is already on a UK keyboard
11:57:55 <ais523> also UK keyboards have exactly two altgr keys, it used to be one
11:58:11 <ais523> one of them is a second |; on some OSes, it looks different from the original |
11:58:20 <ais523> and the other, added quite recently, is €
12:01:19 <ais523> I don't like my compose key to be a key that's otherwise useful
12:01:31 <ais523> caps lock's intended function is the least useful on the keyboard
12:01:34 <ais523> even pause is useful more often
12:02:11 <int-e> I use caps-lock for WM interaction.
12:03:26 <oren_> Caps lock is useful if you use it for IME switching
12:04:22 <int-e> (slightly perversely, I use the left windows key for äöüÄÖÜß...)
12:05:51 <ais523> super is a generally useful key, though
12:06:01 <ais523> also I use alt+super for WM interaction
12:06:03 <ais523> a single key tended to get typoed too often
12:06:18 <b_jonas> I use alt for WM interaction,
12:06:28 <b_jonas> but not all alt+key and alt+mouse combos are that, only some of curse
12:06:30 <oren_> That's what happens when you look at the screen instead of you keyboard
12:07:46 <b_jonas> alt plus any of (the function keys, escape, space) (possibly with other modifiers at the same times); alt plus right or middle drag; and alt plus control plus arrows and edit keys and numpad keys
12:08:36 <b_jonas> but I should refine the specific, in particular, I should make a system where shift isn't used for any WM function so I can reserve it as a modifier to act on a WM nested inside a VNC session
12:09:12 <int-e> b_jonas: no, I've run into that nesting problem myself
12:09:39 <oren_> I've never found a need to interact with a window manager with my keyboard... What would the point be?
12:09:51 <int-e> oren_: the mouse is so far away
12:10:10 <b_jonas> int-e: sure, but is the particular desire to have two full sets of shortcuts (rather than either a limited set of shortcuts in the nested WM, or switch with numlock, or act on the nested stuff only when it's full screen) normal?
12:10:13 <oren_> It is in the centre of my kyboeard
12:10:17 -!- skj3gg has joined.
12:10:29 <b_jonas> hmm, actually switching with numlock might be an option
12:10:29 <int-e> oren_: well, mine isn't. I hate those knobs or touchpads.
12:12:10 <oren_> touch typists tend to hit the touchpad with their wrists but my typing style never has that problem
12:12:11 <int-e> (they don't have the same accurace and speed as a proper mouse, for me)
12:13:01 <oren_> well yeah for games I use an actual mouse
12:14:27 <oren_> i type in a position resting my fingers on the cdwq and mkop keys
12:14:41 <b_jonas> oren_: I interact with a mouse too sometimes, or with a combination of the keyboard modifiers and mouse
12:14:54 <oren_> well sort hovering over that area anyway
12:14:56 <b_jonas> oren_: I have set it up so I can do almost any function with either the keyboard or the mouse,
12:15:14 <b_jonas> (well, not really, the window managers are like that by default, I've just modified the settings a bit)
12:15:19 <Phantom_Hoover> all this time i'd thought the david mitchell who wrote cloud atlass was the comedian
12:15:35 <b_jonas> except of course restoring a full screen window, which you have to do with the keyboard because there's no WM area left on
12:16:02 <b_jonas> but I rarely full screen windows, only for games or watching movies, when I don't want to interact with the WM for a while
12:16:42 <b_jonas> I have, however, spent some time to be able to make the WM are very small so it doesn't waste vertical screen estate
12:21:08 -!- oren_ has changed nick to oren.
12:22:57 <oren> Phantom_Hoover: whatver. I only recently found out that "led zeppelin" is not the name of a guitarist
12:24:46 -!- SopaXorzTaker has joined.
12:25:01 -!- skj3gg has quit (Quit: ZZZzzz…).
12:30:50 -!- AnotherTest has joined.
12:33:43 -!- ais523 has quit (Quit: buying lunch).
13:07:20 -!- ais523 has joined.
13:08:17 -!- shikhin_ has joined.
13:11:00 -!- shikhin has quit (Ping timeout: 250 seconds).
13:16:28 -!- Tritonio has quit (Ping timeout: 252 seconds).
13:18:35 <ais523> so, I started working on azip again
13:19:04 <ais523> and found a really elegant algorithm for "find all substrings that appear more than once in a given string" that runs in O(n log n log n) time
13:20:22 <ais523> now I'm wondering where to start looking to see if it's already known
13:23:28 <vanila> that sounds really interesting!!
13:24:49 <ais523> I'm planning to use it to make the new version of azip
13:24:55 <ais523> or maybe just a better zlib encoder
13:26:07 <ais523> azip is a compression algo Iwas working on a while back
13:26:25 <ais523> it's about comparable with bzip2 (and much better than gzip)
13:28:50 -!- AnotherTest_ has joined.
13:28:57 <ais523> oh, it assumes that the input string can be indexed in O(1), which might or might not be true in practice
13:29:27 -!- AnotherTest has quit (Ping timeout: 245 seconds).
13:29:27 -!- AnotherTest_ has changed nick to AnotherTest.
13:29:32 <ais523> otherwise, you'd have to build a binary tree out of the input string for indexing it, and get O(n log³ n) performance
13:30:37 -!- ais523 has quit (Quit: rebooting).
13:34:22 -!- ais523 has joined.
13:40:50 <int-e> Karp, Miller, Rosenberg ""
13:40:51 <int-e> Rapid identification of repeated patterns in strings, trees and arrays
13:41:03 <int-e> 1972, looks relevant
13:41:29 <int-e> Though old. https://en.wikipedia.org/wiki/Suffix_array#Construction_Algorithms has a couple more references.
13:42:47 <int-e> (The Karp, Miller, Rosenberg one is based on the idea of first identifying equal letters, and then doubling the match lengths iteratively, in O(n) steps per doubling. So it'll actually be O(n log n) total for what you need, I think.)
13:44:30 <ais523> int-e: my algorithm is basically that, with some extra tricks to also figure out the lengths
13:47:02 <ais523> oh, hmm, the algo there is a) not the same as mine, b) solves a subset of the problem
13:47:22 <ais523> theirs looks for matches at length n, mine finds all lengths n for which there are matches (together with the matches themselves)
13:48:58 <int-e> if you have "aaaaaa", how what does the output of the algorithm look like? Do you only look for longest matches?
13:50:21 <int-e> (with a^n as input, listing all occurrences of a^k for k<n is clearly not doable in sub-quadratic time)
13:50:36 <ais523> it finds a single match at each of the lengths 1, 2, 3, 4, and 5, because it doesn't directly find matches that are prefixes of other matches (but those are trivial to add to the output if you need them, but that obviously gives you O(n²) performance worst-case)
13:51:23 <ais523> also the output's hierarchical in a sense
13:52:23 <ais523> ah no, right, that paper is basically the same algo as mine
13:52:34 <ais523> just with less information retained between iterations
13:52:47 <ais523> I thought it would be unlikely to be new
13:53:59 <ais523> anyway, 1972 is over 25 years ago
13:54:04 <int-e> Mainly I was trying to suggest suffix arrays and trees as starting points for finding related work.
13:54:06 <ais523> meaning no patent concerns even if you're American
13:54:28 <int-e> Then I looked at the Karp paper and wondered how close it was to what you actually did.
13:54:36 <ais523> a suffix array is the form which my output takes
13:55:04 <ais523> except that it also knows the longest common prefix of any two consecutive lines
13:55:41 <int-e> (I should write Karp et al.)
13:56:16 <ais523> aha: https://en.wikipedia.org/wiki/LCP_array
13:56:20 <ais523> this is what I was looking for
13:57:15 <ais523> apparently it was done in O(n) (!) in 2003
13:58:26 <ais523> also there's an O(n²) algo that's faster in practice, asymptotic performance can be weird sometimes
13:59:32 <int-e> linear time suffix tree construction has been known since 1973.
14:00:45 <Taneb> ꙮ_ꙮ is my favourite emoticon
14:01:05 <int-e> (That's not an LCP yet, of course.)
14:01:42 <Taneb> Mostly because my housemate's terminal can't render it
14:01:47 <int-e> (20 in some fonts)
14:02:18 <int-e> my terminal doesn't render it either
14:02:42 <ais523> int-e: yes, linear time LCP is what I was surprised at
14:02:43 <int-e> but cut&paste work
14:02:59 <ais523> it's even been done with only enough memory to hold the inputs plus the outputs
14:03:40 -!- GeekDude has joined.
14:04:22 -!- AnotherTest has quit (Ping timeout: 240 seconds).
14:04:45 <ais523> wow, Springer are trying to sell the paper about the fastest known LCP algorithm for £20
14:05:23 -!- AnotherTest has joined.
14:06:22 <int-e> Fun. Do you need a copy?
14:06:59 <ais523> it's not in this University's subscriptions, directly
14:07:06 <ais523> I'm going to check for preprints and the like
14:07:44 <ais523> yay for preprints: http://arxiv.org/pdf/1101.3448.pdf
14:17:39 -!- boily has joined.
14:42:28 -!- shikhin_ has changed nick to shikhin.
14:53:56 <ais523> "All programs were compiled using the same compiler options (-ffast-math -O9 -funroll- loops -DNDEBUG)."
14:54:04 <ais523> wow, those are some compiler options
14:55:25 <ais523> I don't think -O normally goes up to 9
15:03:55 <boily> I thought you had -Os, -O0, -O1 and -O2?
15:05:27 <boily> perhaps. for me -O2 is already dangerous, and can cause many miscast effects...
15:06:25 <boily> (that is to say: nothing above 0 when programming µC. also, I may be playing DCSS at the moment >_>'...)
15:07:24 <ais523> yay, I am currently first on an anagolf problem: http://golf.shinh.org/p.rb?utf8+to+unicode
15:07:40 <ais523> -O3, also -Ofast exists for some reason
15:08:15 <ais523> ah, apparently -Ofast is -O3, plus optimizations that violate the relevant standards
15:08:43 <ais523> (in the case of C, it's equivalent to "-O3 -ffast-math" in the gcc I have installed)
15:21:08 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
15:22:28 -!- kapil__ has quit (Quit: Connection closed for inactivity).
15:32:13 -!- boily has quit (Quit: EQUIVALENT CHICKEN).
15:59:55 -!- Tritonio has joined.
16:02:23 -!- SopaXorzTaker has quit (Ping timeout: 256 seconds).
16:38:08 -!- Tritonio has quit (Ping timeout: 252 seconds).
16:41:02 -!- ^v has joined.
16:51:34 -!- not^v has joined.
16:53:18 -!- ^v has quit (Ping timeout: 250 seconds).
17:01:18 -!- skj3gg has joined.
17:11:25 <HackEgo> [wiki] [[Special:Log/newusers]] create * NeilK * New user account
17:13:12 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41905&oldid=41887 * NeilK * (+17) HeartForth added
17:14:23 <int-e> clever bot. or perhaps, a human ;)
17:24:26 <HackEgo> [wiki] [[Special:Log/upload]] upload * NeilK * uploaded "[[File:HeartForth Factorial.png]]": A screenshot of HeartForth, an Emoji stack language.
17:28:58 -!- PinealGlandOptic has joined.
17:31:07 -!- ais523 has quit.
17:31:17 -!- ais523 has joined.
17:31:56 <HackEgo> [wiki] [[HeartForth]] N http://esolangs.org/w/index.php?oldid=41907 * NeilK * (+782) Initial page for HeartForth
17:32:50 <vanila> :grinning::boom:0:revolving_hearts::point_right::two_hearts:1:heavy_minus_sign::two_hearts:1:pray::+1::point_right::couple_with_heart:0:pray::+1::revolving_hearts::broken_heart::wink:
17:34:10 <HackEgo> [wiki] [[HeartForth]] http://esolangs.org/w/index.php?diff=41908&oldid=41907 * NeilK * (-2) /* Examples */
17:35:13 <HackEgo> [wiki] [[HeartForth]] http://esolangs.org/w/index.php?diff=41909&oldid=41908 * NeilK * (+0) /* Examples */
17:36:01 <int-e> "Clean visual separation between program and data."
17:37:09 <HackEgo> [wiki] [[User:NeilK]] N http://esolangs.org/w/index.php?oldid=41910 * NeilK * (+45) contact info
17:38:02 <HackEgo> [wiki] [[HeartForth]] http://esolangs.org/w/index.php?diff=41911&oldid=41909 * NeilK * (+2) /* Disadvantages */ bulleted to match
17:41:07 -!- Sprocklem has joined.
17:51:16 * int-e idly wonders whether the use of those emoji constitutes fair use
17:52:15 -!- skj3gg has quit (Read error: Connection reset by peer).
17:55:42 -!- skj3gg has joined.
18:01:49 <elliott> unicode is public domain, right
18:02:14 <elliott> why don't we just inline the actual emoji
18:02:25 <elliott> we can't do fair use anyway
18:02:27 <elliott> since the wiki is meant to be pd
18:02:45 -!- skj3gg has quit (Quit: ZZZzzz…).
18:03:26 <fizzie> pgcc had up to -O6, I think.
18:04:01 <fizzie> Or egcs or whatever. Some GCC fork anyway.
18:12:40 <int-e> elliott: AFAIUI, fair use allows incorporation of copyrighted work into other works, which can then be relicensed as a whole.
18:13:33 <int-e> (IANAL, etc.; also I'm not actually operating the wiki, so it's not my call to make anyway.)
18:16:48 <fizzie> This mobile network is strange. SSH works nice and fast, and web browsing was okay for an hour there, but then suddenly stopped. With the exception of Google searches.
18:16:55 -!- oerjan has joined.
18:17:40 <fizzie> Perhaps I should set up some sort of a VPN thing, in case it's some traffic shaping stuff.
18:17:42 <int-e> fizzie: so use ssh -D to set up a socks proxy and use that?
18:18:19 <fizzie> int-e: I'm on Android. I don't know how to do that here.
18:18:57 <fizzie> But I know this has some VPN settings in the network stuff.
18:21:42 -!- not^v has quit (Ping timeout: 250 seconds).
18:21:57 <fizzie> Apparently port forwarding in general is also a "pro" (aka paid) feature in this SSH client (JuiceSSH).
18:22:01 -!- FreeFull has quit (Ping timeout: 264 seconds).
18:26:24 * int-e feels like an expert ;-)
18:27:17 -!- FreeFull has joined.
18:38:08 <dulla> Join the 10$ Crew, int-e
19:03:42 -!- Tritonio has joined.
19:08:31 -!- shikhin_ has joined.
19:11:32 -!- shikhin has quit (Ping timeout: 245 seconds).
19:18:00 -!- ais523 has quit.
19:27:20 <int-e> oerjan: Are you a knight or is that a lower-case "not invented here"?
19:37:38 -!- KingOfKarlsruhe has quit (Quit: ZNC - http://znc.in).
19:37:40 -!- shikhin_ has changed nick to shikhin.
19:38:28 -!- KingOfKarlsruhe has joined.
19:42:48 <int-e> oerjan: ?¿;՞؟፧᥅⁇⁈⁉⍰❓❔⳺⳻⸮꘏꛷︖﹖
19:44:59 <oerjan> are those all question marks
19:45:15 <int-e> yes. no, I don't think so.
19:45:24 <int-e> (they all are; but I doubt that the list is complete)
19:45:44 <oerjan> oh and bidirectional text that causes irssi/putty to show the time in reverse
19:45:50 <int-e> (and the ?! and !? ones are cheating.)
19:46:13 <int-e> (it doesn't do that for me)
19:46:33 <oerjan> i saw 24:02 int-e> ...
19:47:10 <oerjan> it's happened before as i recall
19:47:21 <oerjan> oh tmux is also included
19:47:58 <int-e> Hmm, the stack here is xterm/ssh/screen/irssi... so that's a bit different.
19:48:58 <oren> here i don't have reversed anything. gnome terminal/irssi
19:49:15 <int-e> oerjan must be special.
19:50:26 <HackEgo> [U+00D8 LATIN CAPITAL LETTER O WITH STROKE]
19:51:19 <oren> `unidecode 〇◯○●◎
19:51:20 <HackEgo> [U+3007 IDEOGRAPHIC NUMBER ZERO] [U+25EF LARGE CIRCLE] [U+25CB WHITE CIRCLE] [U+25CF BLACK CIRCLE] [U+25CE BULLSEYE]
19:51:23 <oerjan> suddenly i'm getting an "Ørjan, is that really my name" experience
19:51:46 <int-e> oerjan: I don't find mixing up that letter with symbols for the empty set funny anymore.
19:52:01 <oerjan> that's called mathematical maturity hth
19:52:12 <oren> That's how I write my zeros
19:52:30 <oren> yeah, on paper
19:52:46 <oerjan> you norteamericanos are weird
19:53:32 <oerjan> (we fight back with 1 and 7)
19:54:00 <oren> I write 1 like | and 7 like an unclosed 9
19:54:39 <oerjan> so they don't look too similar to the 1's
19:55:17 * oerjan has been reading the language construction kit
19:55:31 <HackEgo> [U+0C78 TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR]
19:55:40 <int-e> sounds quite specific :)
19:57:32 <oren> I like base 60
19:59:06 <HackEgo> [U+A620 VAI DIGIT ZERO] [U+2189 VULGAR FRACTION ZERO THIRDS]
19:59:24 <int-e> there are 60+ zero digits in unicode...
19:59:47 <lambdabot> <hint>:1:1: lexical error at character '\42528'
20:00:06 <oerjan> disappoint, i thought haskell did unicode
20:00:51 <oren> maybe it only supports some characters. I know perl allows $か as a variable name
20:01:00 <int-e> > generalCategory '꘠'
20:01:13 <int-e> > generalCategory '↉'
20:01:33 <oren> `perl $か = 3; print $か
20:01:36 <HackEgo> Can't open perl script "$か = 3; print $か": No such file or directory
20:01:40 <oerjan> variable names are fine
20:01:54 <oerjan> but that should, of course, be a number
20:01:56 <oren> `perl -e '$か = "foo"; print $か;'
20:01:56 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: runperl: not found
20:01:57 -!- Patashu has joined.
20:02:20 <int-e> ``perl -e '$か = "foo"; print $か;'
20:02:20 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `perl: not found
20:02:28 <oerjan> by coincidence, you don't need `` for it
20:02:29 <int-e> `` perl -e '$か = "foo"; print $か;'
20:02:30 <HackEgo> Unrecognized character \x81; marked by <-- HERE after $<-- HERE near column 3 at -e line 1.
20:02:46 <oerjan> int-e: use `perl -e without ``
20:03:06 <int-e> oerjan: why does that work?
20:03:22 <oerjan> i leave that as an exercise hth
20:04:15 <int-e> `perl -e$か = "foo"; print $か;
20:04:17 <HackEgo> Unrecognized character \x81; marked by <-- HERE after $<-- HERE near column 3 at -e line 1.
20:04:46 <oren> `` perl -e 'use utf8; $か = "foo"; print $か;'
20:05:10 <int-e> `perl -e use utf8; $か = "foo"; print $か;
20:05:26 <int-e> that's what oerjan meant.
20:06:08 <oerjan> that also exists if you're too confused :)
20:06:16 <oren> `` perl -e 'use utf8; $夢 = "foo"; print $夢;'
20:06:27 <int-e> fiendish, as oerjan would say.
20:08:01 <oerjan> `interp perl use utf8; $か = "foo"; print $か;
20:08:45 <oerjan> `! perl use utf8; $か = "foo"; print $か;
20:09:14 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: pl: not found
20:09:32 <oren> `` perl -e 'use utf8; $∀ = "foo"; print $∀;'
20:09:34 <HackEgo> Malformed UTF-8 character (unexpected end of string) at -e line 1. \ Unrecognized character \x88; marked by <-- HERE after e utf8; $<-- HERE near column 12 at -e line 1.
20:10:26 <oerjan> the telugu number pages i checked don't seem to mention that character.
20:13:45 -!- ^v has joined.
20:14:12 -!- AndoDaan has joined.
20:20:43 -!- skj3gg has joined.
20:21:44 -!- ^v has quit (Ping timeout: 250 seconds).
20:24:21 -!- MDude has joined.
20:24:22 -!- Patashu has quit (Ping timeout: 240 seconds).
20:30:45 -!- SignX has joined.
20:40:17 -!- Sprocklem has quit (Ping timeout: 245 seconds).
20:40:48 -!- AndoDaan has quit (Ping timeout: 265 seconds).
20:47:54 -!- skj3gg has quit (Quit: ZZZzzz…).
20:51:12 -!- Lymia has quit (Ping timeout: 250 seconds).
20:53:10 -!- TieSoul has changed nick to TieSleep.
21:06:56 -!- idris-bot has quit (Quit: Terminated).
21:07:54 -!- idris-bot has joined.
21:08:56 -!- vanila has quit (Quit: Leaving).
21:18:40 -!- skj3gg has joined.
21:32:51 -!- Sprocklem has joined.
21:34:51 -!- skj3gg has quit (Quit: ZZZzzz…).
21:35:07 -!- AnotherTest has quit (Remote host closed the connection).
21:42:28 -!- contrapumpkin has joined.
21:42:29 -!- copumpkin has quit (Ping timeout: 250 seconds).
21:55:13 <zzo38> Strange Item {2} Artifact :: Cumulative upkeep--{1} or discard a card :: {T}: Put a token copy of ~ into play tapped and phased out.
21:56:15 <b_jonas> zzo38: phased out and cumulative upkeep? are you trying to do an Old Fogey?
21:56:26 <zzo38> No, I just like those abilities
21:56:58 <zzo38> I suppose a token phased out won't work anyways
21:57:27 <zzo38> The rules say it doesn't for some reason
21:57:49 <zzo38> {T}: Put a token copy of ~ into play tapped. If ~ is a card, it phases out.
21:59:31 -!- qlkzy has quit (Ping timeout: 255 seconds).
21:59:45 <zzo38> Steal Summoning {3UU} Instant :: Manifest target spell. Do you like that one?
22:00:29 -!- SignX has quit (Quit: Page closed).
22:00:46 <b_jonas> zzo38: hmm... how does that work? does the manifested object come into play under your control? and what happens if you target a copy of a spell?
22:01:28 <zzo38> I think it does come into play under your control. If it is a copy of a spell then it doesn't.
22:02:33 <b_jonas> zzo38: yes, but what happens if it's a copy of a spell? nothing? or does the spell disappear? or moved to another zone and then disappear?
22:03:43 -!- adu has joined.
22:04:02 <zzo38> Actually I fixed my alternative rules now and now the copy can come into play as a token (previously I wrote it not to work with objects that come into play face-down, but I changed that)
22:04:40 -!- qlkzy has joined.
22:05:34 <zzo38> This rule doesn't affect any official cards as far as I am aware.
22:06:02 <b_jonas> I'm still not sure I know how manifest works
22:06:03 <zzo38> (Also this alternative rule doesn't affect non-card objects that come into play from a zone other than the stack)
22:06:19 <b_jonas> and this might confuse it further
22:07:18 <zzo38> I believe manifesting an object means you put the object into play face-down under your control, and then it becomes allowed to be turned face-up for its mana cost if the front face is a creature.
22:07:45 <zzo38> If a instant or sorcery tries to turn face up for any reason, it is revealed but then remains face down.
22:07:54 <b_jonas> zzo38: yes, and there's some extra rules, like on what happens when you try to bounce a manifested non-permanent (it remains exiled)
22:08:14 <zzo38> That's implied by other rules and has nothing to do with manifest.
22:08:32 <zzo38> Any instant or sorcery that tries to come into play for any reason whatsoever instead remains where it is.
22:08:55 <b_jonas> so what if I try to target a face down spell with Steal Summoning? does it get revealed as it is put onto the battlefield, or only when it leaves the battlefield?
22:09:28 <zzo38> Only when it leaves the battlefield, although you can look at it right away.
22:10:14 <zzo38> (Well, not until Steal Summoning resolves; you can't look at it before then if it isn't your spell.)
22:11:19 <b_jonas> “Steal Summoning” sounds like the name of that nonexistant instant that gets you to control a spell, which is why I find this a bit disappointing
22:11:44 <zzo38> I think if a face-down permanent turns face-up and the front face is a Aura, that it would be discarded right away, but that if it is exiled and comes back, then a target for the Aura can be chosen.
22:12:10 <b_jonas> zzo38: yes, that sounds about right
22:13:02 <b_jonas> I think the face down spell should probably be revealed when Steal Summoning resolves though
22:13:22 <zzo38> Why? I don't see any reason why it should have to?
22:13:42 <b_jonas> Because it leaves the stack in a way other than the normal way.
22:13:45 <zzo38> Does the rule about revealing them apply to spells too?
22:13:53 <zzo38> If it does, then yes it does get revealed.
22:14:18 <b_jonas> it has to, to make sure you can't cheat by casting a non-morph spell face down
22:14:32 <b_jonas> this is so that M:tG in principle doesn't require an independent judge to play
22:14:40 <b_jonas> as long as you know the rules perfectly
22:15:50 <b_jonas> I'll check the rules, but that is definitely a goal the rules are trying to keep
22:17:24 <zzo38> Probably it is then
22:17:44 <b_jonas> “707.9. If a face-down permanent moves from the battlefield to any other zone, its owner must reveal it to all players as he or she moves it. If a face-down spell moves from the stack to any zone other than the battlefield, its owner must reveal it to all players as he or she moves it.
22:17:52 <b_jonas> If a player leaves the game, etc”
22:18:05 <b_jonas> So that means it wouldn't be revealed, because it's moved to the battlefield.
22:18:40 <b_jonas> This means if you Scroll of Cryptic Runes a face down spell, it's also not revealed.
22:18:42 <zzo38> O, OK then it isn't revealed, and in fact doesn't need to anyways
22:19:23 <b_jonas> though as this situation doesn't exist in official M:tG, you could change that rule for this
22:19:58 <zzo38> I don't want to change rules that I don't believe should be changed
22:21:10 <b_jonas> I wonder if putting a copy of a spell into play as a face down token could lead to any strange situations, but it's probably fine
22:21:48 <b_jonas> it's face down, can't be turned face up in any way because its face is a sorcery or instant, and it disappears after it leaves the battlefield
22:22:57 <zzo38> One other rule I made up is that an effect is allowed to prohibit conceding in a subgame, but the outer game can always be conceded regardless of any effects, including during the subgame
22:24:22 <b_jonas> that might work rules-wise, but I think it might be a bad idea
22:24:44 <b_jonas> because it could make subgames take too much real time
22:25:09 <zzo38> For example the effect that creates the subgame might say that conceding is not allowed. In such case the outer game can still be conceded, and subsubgames still can be conceded if those aren't prohibited too. If a continuous effect says "Conceding is not allowed" then it has no effect if this effect isn't played inside of the subgame.
22:25:33 <b_jonas> would you also make the rules about infinite loops not apply to the subgame directly as well?
22:26:01 <zzo38> So far I didn't and am not sure about that one yet
22:27:27 <zzo38> An effect that only says you can't lose doesn't prohibit you from conceding though.
22:27:53 <b_jonas> zzo38: what if it says you can't lose and your opponents can't win?
22:28:42 <zzo38> Still doesn't prohibit conceding.
22:28:50 <b_jonas> and aren't subgames basically deprecated anyway, with all cards creating subgames currently banned in all formats, even Vintage?
22:29:22 <b_jonas> sort of like Ante, only newer
22:29:51 <int-e> . o O ( "unban target card" )
22:30:49 <zzo38> Maybe although I made up one new card that creates a subgame. Also I wrote a few new rules for ante and sideboard; one effect is that all effects that cross games begin no earlier than the beginning of a match and end no later than the end of a match. Therefore anted cards are always returned at the end of a match.
22:31:10 <b_jonas> int-e: like a backwards Look at Me, I'm the DCI?
22:32:12 <int-e> Oh, nice flavour text on that one.
22:33:24 <zzo38> As far as I know "unban target card" should only work if the card was already unbanned at the beginning of the current game; even if it said "name a card" it still is
22:33:53 <b_jonas> zzo38: or at least at the beginning of the match
22:34:47 <zzo38> I would think that banned cards cease existing even in a sideboard though?
22:35:12 <zzo38> And you wouldn't be allowed to name a banned card.
22:35:55 <b_jonas> zzo38: yes, they definitely cease existing in the sideboard. the remainder text of Look at Me is clear in that
22:36:11 <b_jonas> zzo38: I think it probably moves the banned cards to the same zone as AWOL
22:39:18 <zzo38> I would also make the assumption that cards with no valid RULECARD representation are automatically banned regardless of anything
22:40:09 <zzo38> Some programming language I partially made up but not much yet
22:40:54 <b_jonas> um, then maybe the card doesn't have a representation because you just haven't implemented it yet?
22:41:18 <zzo38> It is hypothetical for now of course.
22:42:20 <b_jonas> anyway, the relevant rule is “100.2. To play, each player needs his or her own deck of traditional Magic cards,” and “108.2. When a rule or text on a card refers to a “card,” it means only a Magic card.”
22:42:54 <b_jonas> and the tourn't rules I guess
22:43:21 -!- adu has quit (Quit: adu).
22:54:41 -!- skj3gg has joined.
23:04:59 -!- skj3gg has quit (Quit: ZZZzzz…).
23:07:54 <zzo38> I got the Famicom working now.
23:08:35 <zzo38> After cleaning up the cartridge
23:19:11 <zzo38> Tell people who made PDJSON that I fixed the bug and interfaced it with SQLite.
23:19:56 -!- hjulle has joined.
23:21:06 -!- adu has joined.
23:23:20 <zzo38> (I don't know how to tell them by myself)
23:23:20 -!- oren has quit (Quit: Lost terminal).
23:23:34 -!- zzo38 has quit (Remote host closed the connection).
23:24:59 -!- adu has quit (Client Quit).
23:37:09 -!- Sprocklem has quit (Remote host closed the connection).
23:45:19 -!- PinealGlandOptic has quit (Quit: leaving).
23:50:05 -!- AndoDaan has joined.
23:58:05 -!- skj3gg has joined.
00:02:46 -!- contrapumpkin has changed nick to copumpkin.
00:09:08 -!- skj3gg has quit (Quit: ZZZzzz…).
00:10:14 -!- Tritonio has quit (Ping timeout: 252 seconds).
00:21:02 -!- Sprocklem has joined.
00:24:58 -!- adu has joined.
00:44:38 <oerjan> @tell ais523 <ais523> anyway, 1972 is over 25 years ago <-- 40 hth
00:45:20 <Taneb> oerjan, that makes no sense
00:45:29 <Taneb> 40 years is, like, 2 of my lifetimes
00:46:10 <oerjan> did you know jesus was born more than 100 of your lifetimes ago hth
00:47:31 <Taneb> Wasn't he born in, like, 6 BC
00:48:21 <oerjan> are you saying it's only 99?
00:49:00 <Taneb> I'm saying it's 101
00:49:34 <oerjan> well the date is a bit approximate so...
00:52:15 <oerjan> did you know the great pyramid was finished more than 227 of your lifetimes ago hth
00:54:00 <AndoDaan> So, that's 111 of your life times ago then, oerjan?
00:55:03 <AndoDaan> Looks good... wow I can't remember when the great pyramids were built.
00:55:53 <AndoDaan> Wait. I know Chleopatra lived closer in time to the moon landings than the building of those pyramids.
00:56:07 <AndoDaan> I can figure this out without google.
00:56:18 <oerjan> hm i resolved the other day to look up the date for the fall of constantinople, only so i could give a cheeky in case someone asked me when the roman empire fell.
00:56:50 <oerjan> cleopatra was only about 50 years before jesus
00:57:30 <AndoDaan> It's funny how Western Civilisation gradual moved eastward over the centuries.
00:57:57 <oerjan> hm actually just 30, she survived caesar by some years
00:58:05 <AndoDaan> I always mistake 50 BCE with 50CE.
00:58:25 <oerjan> AndoDaan: well it first moved westward from greece hth
00:58:38 <oerjan> in fact it probably never left greece, which included turkey
00:58:57 <oerjan> (see: fall of constantinople)
01:00:17 <AndoDaan> I know there's some different views about the exact date.
01:01:50 <AndoDaan> You're right. I must be confusing the confusion with something else.
01:02:17 -!- gde33|2 has joined.
01:02:47 -!- gde33 has quit (Ping timeout: 245 seconds).
01:05:50 -!- gde33 has joined.
01:07:26 -!- gde33|2 has quit (Ping timeout: 252 seconds).
01:08:38 -!- shikhin_ has joined.
01:09:26 <Taneb> I am really enjoying Linear Algebra
01:09:41 <Taneb> So I ought to go to sleep now so I can get to my LA lecture in 9 hours
01:11:28 -!- shikhin has quit (Ping timeout: 252 seconds).
01:16:05 -!- Lymia has joined.
01:19:09 -!- Sprocklem has quit (Ping timeout: 250 seconds).
01:19:38 -!- boily has joined.
01:53:22 -!- adu has quit (Quit: adu).
02:13:59 -!- v^ has quit (Read error: Connection reset by peer).
02:16:16 -!- ^v has joined.
02:43:21 -!- boily has quit (Quit: SEMILATTICE CHICKEN).
03:01:20 -!- skj3gg has joined.
03:15:57 -!- AndoDaan has quit (Quit: Going, going, gone.).
03:20:20 -!- hjulle has quit (Ping timeout: 246 seconds).
03:32:51 -!- skj3gg has quit (Quit: ZZZzzz…).
03:41:35 -!- skj3gg has joined.
03:52:51 <HackEgo> [wiki] [[Special:Log/move]] move * Rottytooth * moved [[A programming language is an artificial language designed to communicate instructions to a machine, particularly a computer.]] to [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]]: Updating to reflect new first sentence of Wik
03:55:44 <HackEgo> [wiki] [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]] http://esolangs.org/w/index.php?diff=41914&oldid=41912 * Rottytooth * (+122) changed name of language, to match Wikipedia entry
03:56:51 <oerjan> brb prepending a paragraph saying just "brainfuck" to the wikipedia page
03:57:32 <HackEgo> [wiki] [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]] http://esolangs.org/w/index.php?diff=41915&oldid=41914 * Rottytooth * (+149) /* Overview */
04:12:39 <oerjan> hm freefall mystery solved
04:14:46 -!- skj3gg has quit (Quit: ZZZzzz…).
04:16:34 <oerjan> hm i think he may have retconned the previous one
04:17:13 <oerjan> i distinctly thought it implied more clearly that there was just one order
04:18:08 <oerjan> maybe the last bubble in today's is lampshading it.
04:25:38 -!- zzo38 has joined.
04:25:38 <oerjan> the forum unfortunately links directly to the same image url
04:34:48 -!- adu has joined.
04:39:22 -!- shikhin_ has changed nick to shikhin.
04:39:36 -!- skj3gg has joined.
05:04:08 -!- MDude has changed nick to MDream.
05:05:14 <oerjan> ah mark stanley admits to having forgotten it
05:22:30 -!- skj3gg has quit (Quit: ZZZzzz…).
05:39:29 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:57:24 -!- doesthiswork has joined.
06:27:13 -!- kapil__ has joined.
06:40:43 -!- shikhin has quit (Ping timeout: 256 seconds).
06:57:47 -!- doesthiswork has quit (Quit: Leaving.).
07:06:36 -!- AndoDaan has joined.
07:06:38 -!- AndoDaan_ has joined.
07:07:54 -!- AndoDaan has quit (Client Quit).
07:08:13 -!- AndoDaan_ has changed nick to AndoDaan.
07:08:48 -!- adu has quit (Quit: adu).
07:41:41 -!- Patashu has joined.
08:15:02 -!- tswett has quit (Quit: No Ping reply in 180 seconds.).
08:16:38 -!- Warrigal has joined.
08:36:08 -!- AndoDaan_ has joined.
08:36:28 -!- AndoDaan has quit (Read error: Connection reset by peer).
08:53:51 -!- AndoDaan_ has changed nick to AndoDaan.
08:54:19 -!- oerjan has quit (Quit: leaving).
09:14:09 <zzo38> HAKMEM says "The myth that any given programming language is machine independent is easily exploded by computing the sum of powers of 2. [...] If arithmetic overflow is a fatal error, some fascist pig [...] is trying to enforce machine independence. But the very ability to trap overflow is machine dependent."
09:14:15 -!- Sgeo has quit (Ping timeout: 244 seconds).
09:14:34 <zzo38> I think that it could be implemented in a machine independent way actually, although that might slow down the program.
09:15:42 <zzo38> (Also most computer in use today is twos complement, and if it isn't you can still imitate such things)
09:18:10 <zzo38> Also item 149 is algorithm to draw circle. With arithmetic bit shifting it would be: for(;;) { x-=y>>n; y+=x>>n; plot(x,y); } where n is a parameter, and the initial value of x and y are parameters.
09:18:46 <zzo38> I think you could set n=8 to do it with 8-bit computers.
09:20:11 <zzo38> So you could do it with only addition and subtraction (and carrying)!
09:21:33 <int-e> > sqrt (1 + 1/256^2)
09:29:58 -!- ais523 has joined.
09:44:03 -!- shikhin has joined.
09:45:44 -!- jameseb- has changed nick to jameseb.
09:51:54 -!- ais523 has quit (Quit: meeting).
10:17:47 <J_Arcane> "I can't come up with a real world use for the .map function" " it's a treatment for a symptom from anonymous functions, that you shouldn't even use in the first place." ... these kids today.
10:24:40 <myname> lap is like the best thing ever
10:26:11 <b_jonas> no! it should be called "collect" or "transform"
10:28:50 <myname> collect is just plain wrong
10:33:05 <b_jonas> why? collect is what smalltalk uses, it can't be wrong.
10:33:33 -!- AnotherTest has joined.
10:34:54 <b_jonas> (together with select, inject, detect)
10:34:56 -!- ais523 has joined.
10:42:22 -!- AnotherTest has quit (Ping timeout: 252 seconds).
10:43:45 <myname> collect sounds more like reduce/fold but nothing like map
10:44:11 -!- oren has joined.
10:50:16 <oren> real world use of map function: activation function over weighted sum output, in neural network.
10:50:24 <b_jonas> myname: it's computer jargon, fixed once smalltalk got popular enough. just like how "||" now means logical or even if you think it seems more like string concatenation.
10:50:44 <b_jonas> and it's better than "map" which means two different things
10:51:00 <b_jonas> reduce is called "inject" in smalltalk
10:51:28 <oren> I'm only familiar with the map from perl
10:52:17 <b_jonas> oren: sure, "map" means collect/transform in perl, but means dictionary or associative array in C++ or haskell
10:53:16 <oren> oh. well those meaning are related through the math meaning of it.
10:53:28 <b_jonas> but "select" is _much_ worse
10:53:36 <b_jonas> it means like ten different things in computers
10:53:57 <b_jonas> so for that, I recommend "filter" instead, which is what haskell calls it
10:54:01 <oren> I still picture the select button from my gameboy when I read the word select
10:54:05 <b_jonas> or "find_all" if you prefer
10:54:24 <b_jonas> http://www.perlmonks.com/?node_id=295576 has the list on how many things "select" means
10:54:33 <b_jonas> and the game boy button isn't listed
11:00:25 -!- Patashu has quit (Remote host closed the connection).
11:00:47 -!- Patashu has joined.
11:02:08 -!- AnotherTest has joined.
11:20:02 -!- shikhin has quit (Ping timeout: 250 seconds).
11:20:35 -!- AndoDaan has quit (Ping timeout: 246 seconds).
11:24:36 -!- boily has joined.
11:29:41 -!- AnotherTest has quit (Ping timeout: 246 seconds).
11:38:13 -!- AndoDaan has joined.
11:41:53 -!- Patashu has quit (Ping timeout: 246 seconds).
11:48:00 -!- AnotherTest has joined.
12:11:16 <elliott> b_jonas: map is collect in Haskell...
12:11:27 <elliott> (there's also Data.Map though, yeah)
12:11:57 <b_jonas> elliott: ah, right, in Haskell it means _both_
12:22:08 -!- boily has quit (Quit: TRIMETHYLXANTHINE CHICKEN).
12:37:28 -!- AnotherTest has quit (Ping timeout: 255 seconds).
12:56:55 -!- ais523 has quit (Read error: Connection reset by peer).
13:26:01 -!- vanila has joined.
13:32:35 -!- shikhin has joined.
13:36:07 -!- ais523 has joined.
13:41:52 -!- NihilistDandy has quit (Ping timeout: 240 seconds).
13:51:42 -!- Taneb has quit (Ping timeout: 250 seconds).
13:53:34 -!- SopaXorzTaker has joined.
13:54:13 -!- Taneb has joined.
14:01:22 -!- SopaXorzTaker has quit (Ping timeout: 240 seconds).
14:04:41 <J_Arcane> "A trick here is to use keyboard macros to do the boilerplate." Oh the horror.
14:07:43 -!- SopaXorzTaker has joined.
14:11:45 <vanila> http://rosettacode.org/wiki/Quine
14:12:17 <ais523> I'm not sure a quine collection does that well at comparing languages
14:12:49 -!- Tritonio has joined.
14:13:23 <vanila> that burlesque quine sucks D:
14:15:12 <vanila> im tnot good at burleque
14:15:58 <vanila> #1=(write '#1# :circle t) this common lisp one is very funny
14:16:56 <vanila> canwe please disallow self evaluating forms as "quines" :|
14:16:57 <ais523> @tell oerjan I picked 25 because that's when patents expire
14:18:54 <ais523> hmm, I think you could do better for Befunge
14:18:57 <J_Arcane> ((λ (x) `(,x ',x)) '(λ (x) `(,x ',x))) ; <3
14:19:19 <ais523> you can use a mismatched double quote character to put the entire program both inside and outside itself
14:20:07 <b_jonas> ais523: like, a string but you enter from orthogonally (or through a trampoline) so it's also not a string?
14:20:22 <b_jonas> I do something similar in perl and lua, when I both eval a string a use its value
14:20:23 <ais523> oh, we have one that works like that on the wiki: http://esolangs.org/wiki/Befunge#Quine
14:20:27 <ais523> I think it's possible to do better though
14:20:36 <b_jonas> (and there's such an obfuscation for dc too)
14:20:53 <vanila> R is a room. To quit: (- quit; -). When play begins: say entry 1 in Q; say Q in brace notation; quit. Q is a list of text variable. Q is {"R is a room. To quit: (- quit; -). When play begins: say entry 1 in Q; say Q in brace notation; quit. Q is a list of text variable. Q is "}
14:21:20 <b_jonas> but my favourite style of quine is one that's easy to translate to any language,
14:21:28 <b_jonas> namely one where you index an array of strings with an array of numbers
14:21:32 <vanila> I like seeing the different categories of quine
14:21:33 <J_Arcane> BASIC's is my favorite: 10 LIST
14:21:36 <b_jonas> `perl -eprint+("print+(","\"",",","\\",")[g1012131121212133121414=~/./g]")[g1012131121212133121414=~/./g]
14:21:37 <HackEgo> print+("print+(","\"",",","\\",")[g1012131121212133121414=~/./g]")[g1012131121212133121414=~/./g]
14:21:41 <J_Arcane> I actually used that one as a kid for something IIRC.
14:22:30 <b_jonas> [ ;@(2 0 0 0 0 1 0 1 0 1 0 2 0&{)'''';';';';@(2 0 0 0 0 1 0 1 0 1 0 2 0&{)'
14:22:31 <j-bot> b_jonas: ;@(2 0 0 0 0 1 0 1 0 1 0 2 0&{)'''';';';';@(2 0 0 0 0 1 0 1 0 1 0 2 0&{)'
14:22:35 <vanila> `perl -eprint+("print+(","\"",",","\\",")[h=~/./g]")[h=~/./g]
14:22:42 <b_jonas> [ ;2 0 0 0 0 1 0 1 0 1 0 2 0{'''';';';';2 0 0 0 0 1 0 1 0 1 0 2 0{'
14:22:42 <j-bot> b_jonas: ;2 0 0 0 0 1 0 1 0 1 0 2 0{'''';';';';2 0 0 0 0 1 0 1 0 1 0 2 0{'
14:22:50 <vanila> what is g1012131121212133121414 ?
14:23:10 <b_jonas> vanila: it's a bareword, a string literal
14:23:35 <ais523> `! befunge "0<>,#:_@#-2*66
14:23:39 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ 0<>,#:_@#-2*66 .
14:23:58 <ais523> you can't put the EOF onto the playfield
14:24:16 <ais523> `! befunge "0<>,#:_@#,-2*66
14:24:17 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ "<>,#:_@#,-2*66 .
14:24:18 -!- ProofTechnique has joined.
14:24:47 <ais523> also I'm handling the end of the string wrong
14:24:49 <vanila> `perl -eprint+("print+(","\"",",","\\",")[g1017131121212133121414=~/./g]")[g1017131121212133121414=~/./g]
14:24:50 <HackEgo> print+("print+(""\"",",","\\",")[g1017131121212133121414=~/./g]")[g1017131121212133121414=~/./g]
14:24:53 <ais523> `! befunge "0<>:#,_@#,-2*66
14:24:54 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ "<>:#,_@#,-2*66
14:25:33 <vanila> it seems to matter, what the name of g is.. why?
14:26:55 <b_jonas> vanila: any letter instead of g works
14:27:13 <vanila> can you expplain what it does
14:27:19 <ais523> anagolf is also putting an EOF on the playfield
14:27:26 <b_jonas> vanila: you need a letter, because if you wrote 01017131121212133121414 it would stringify as exponential
14:27:40 <b_jonas> `perl -eprint 1017131121212133121414
14:27:45 <b_jonas> `perl -eprint 01017131121212133121414
14:27:53 <b_jonas> `perl -eprint g1017131121212133121414
14:28:00 <vanila> im asking about the number
14:29:12 <vanila> `perl -eprint+("print+(","\"",",","\\",")[g8888=~/./g]")[g8888=~/./g]
14:29:27 <vanila> `perl -eprint+("print+(","\"",",","\\",")[g1118888=~/./g]")[g1118888=~/./g]
14:29:53 <b_jonas> `perl -eprint+("zero ","one ","two ","three ")[3,1,0,0,1]
14:30:02 <b_jonas> `perl -eprint+("zero ","one ","two ","three ")[31001=~/./g]
14:30:15 <b_jonas> the digits are indexes to a list of strings
14:30:39 -!- SopaXorzTaker has quit (Ping timeout: 245 seconds).
14:30:41 <b_jonas> this is why it works in almost any language, because you can create a list of strings in almost any language, and a list of integers too, and index one by the other
14:30:56 <vanila> but it will not be so short, probably
14:31:06 <b_jonas> sure, it's not as short as other quines, not even in perl
14:31:19 <b_jonas> but it's also not very long
14:31:22 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41916&oldid=41873 * Ais523 * (+1) /* External resources */ site has moved
14:31:32 <b_jonas> I've written a kilobyte long quine in C long ago
14:31:32 <vanila> The one you wrote in J uses the same idea
14:31:55 <b_jonas> http://www.perlmonks.com/?node_id=661934 has shorter quines in perl
14:32:17 -!- SopaXorzTaker has joined.
14:32:25 <vanila> I've written a new quine today which im proud of
14:32:28 <ais523> this online IDE crashed when I divided by zero
14:32:42 <ais523> vanila: this is befunge, though
14:32:46 <ais523> it has defined behaviour on dividing by zero
14:33:55 <b_jonas> ais523: online befunge IDE?
14:34:05 <ais523> b_jonas: http://www.tutorialspoint.com/compile_befunge_online.php
14:34:08 <ais523> it's not that good, though
14:34:10 <ais523> can't even divide by zero
14:34:20 <ais523> I was looking for an online debugger though
14:34:20 <vanila> someone wrote a quine on perl whichs loads up the perlmonks thread and prints that post out
14:34:29 <vanila> the post containing his own quine haha
14:34:54 <ais523> at least it's not putting an EOF on the playfield
14:35:11 <b_jonas> I don't know of any online befunge interpreter
14:35:29 <ais523> oh, here it is: http://www.quirkster.com/iano/js/befunge.html
14:36:24 <vanila> Save the following line to a file named "/tmp/p" and run as: perl /tmp/p
14:36:24 <vanila> Illegal division by zero at /tmp/p line 1.
14:38:37 <ais523> I'm surprised that that gives a divide-by-zero, though
14:38:44 <ais523> I thought it'd fail to parse after three barewords
14:38:51 <ais523> `! perl one two three four five siz
14:38:52 <HackEgo> Can't locate object method "five" via package "siz" (perhaps you forgot to load "siz"?) at /tmp/input.290 line 1.
14:38:54 -!- TieSleep has changed nick to TieSoul.
14:38:56 <ais523> `! perl one two three four five six
14:38:57 <HackEgo> Can't locate object method "five" via package "six" (perhaps you forgot to load "six"?) at /tmp/input.290 line 1.
14:39:04 <HackEgo> Can't locate object method "one" via package "two" (perhaps you forgot to load "two"?) at /tmp/input.291 line 1.
14:39:26 <ais523> `! perl Illegal division by zero at /tmp/input.292 line 1.
14:39:32 <HackEgo> Bareword found where operator expected at /tmp/input.290 line 1, near "292 line" \ (Missing operator before line?) \ Number found where operator expected at /tmp/input.290 line 1, near "line 1." \ (Do you need to predeclare line?) \ syntax error at /tmp/input.290 line 1, near "292 line " \ Execution of /tmp/input.290 aborted due to compilation er
14:39:53 <ais523> oh, it seems that the chained barewords can be interpreted as one big chain of method calls
14:42:18 <HackEgo> /hackenv/bin/!: 4: exec: ibin/error: not found
14:42:28 -!- kapil__ has quit (Quit: Connection closed for inactivity).
14:42:28 <vanila> `! /hackenv/bin/!: 4: exec: ibin/error: not found
14:42:29 <HackEgo> /hackenv/bin/!: 4: exec: ibin//hackenv/bin/!:: not found
14:42:35 <vanila> `! /hackenv/bin/!: 4: exec: ibin//hackenv/bin/!:: not found
14:42:36 <HackEgo> /hackenv/bin/!: 4: exec: ibin//hackenv/bin/!:: not found
14:43:58 <ais523> is this a hackego quine?
14:44:41 <HackEgo> /hackenv/bin/quine: 2: cd: can't cd to /var/irclogs/_esoteric \ ls: cannot access ????-??-??.txt: No such file or directory
14:45:32 <ais523> `quine worked by grepping the logs for the most recent `quine command
14:46:05 <HackEgo> /hackenv/bin/quine: 2: cd: can't cd to /var/irclogs/_esoteric \ ls: cannot access ????-??-??.txt: No such file or directory
14:47:06 <b_jonas> ah, befunge calls it "bridge", not "trampoline"
14:47:26 <ais523> `! befunge "0<>:#,_@#0,-2*66
14:47:29 <b_jonas> I guess it was developped by hardware guys who know how wires work
14:47:38 <ais523> `! befunge "0<>:#,_@#1,-2*66
14:47:59 <b_jonas> in befunge, could you use the g command to read the program?
14:47:59 <ais523> I had to add a bunch of trailing spaces because this Befunge interp puts EOF on the playfield for some reason
14:48:07 <ais523> b_jonas: yes, you could
14:48:10 <ais523> I think this way's more elegant though
14:48:21 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: x: not found
14:49:02 <ais523> b_jonas: the shortest befunge quine on anagolf works like you suggest
14:49:13 <ais523> :0g:,%1+ and a NUL character, by flagitious
14:49:56 <b_jonas> ok wait, how does your quine work? doesn't befunge start at the top left corner going right? if so, the double quote puts it to string mode but how does it exit that?
14:49:59 <ais523> by the look of it, that relies on the program exiting upon mod-0, which probably counts as cheating
14:50:05 <ais523> b_jonas: the program wraps around
14:50:13 <ais523> that quote is both the start and end of the string
14:50:18 <ais523> this is what I think is so elegant
14:50:19 <vanila> its the best type of cheating :D
14:50:46 <ais523> `! befunge "<>:#,_@#1,-2*66
14:50:47 <HackEgo> "<>:#,_@#1,-2*66 66*2-,1#@_,#:><
14:50:52 <ais523> oh right, that's why I needed the 0
14:50:59 <ais523> `! befunge "0<>:#,_@#1,-2*66
14:51:46 <ais523> `! befunge98 "0<>:#,_@#1,-2*66
14:52:05 <ais523> `! befunge98 '"r:#,_@#1,-2*66
14:52:31 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: befunge: not found
14:52:32 <ais523> `! befunge98 '"r:#,_@#
14:52:41 <vanila> im disappointed with hte prolog quine
14:52:53 <vanila> it hink this shoudn't count
14:52:59 <ais523> I reckon we can do better
14:53:09 <ais523> let me think about this
14:53:13 <ais523> do we have prolog in HackEgo?
14:53:23 <ais523> `! prolog :- write("test").
14:53:24 <HackEgo> /hackenv/bin/!: 4: exec: ibin/prolog: not found
14:53:29 <ais523> let me try this local then
14:53:35 <b_jonas> I'm still trying to understand this befunge stuff
14:53:42 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: befunge: not found
14:53:44 <vanila> http://swish.swi-prolog.org/ this is a prolog
14:53:46 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?)
14:53:55 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?)
14:54:10 <ais523> oh wow, the stack isn't even starting full of zeroes?
14:54:50 <b_jonas> ais523: quick, code a better one in two lines of perl or C or something and teach it to HackEgo
14:59:20 <b_jonas> right, you have to add that
14:59:54 <b_jonas> that's why ais has that 66*2- thing in his
15:00:17 -!- skj3gg has joined.
15:00:23 <ais523> vanila: << is a heredoc
15:00:47 <ais523> oh good, I just trying to figure out how to explain what a heredoc was
15:00:53 <ais523> if you know already that makes things easier
15:01:15 <vanila> "There are a number of excellent quines in the Tcl wiki[2], the most useful for real-world programming probably the one that uses [info] to read the source of the currently running script"
15:01:25 <vanila> what real-world programming??
15:02:11 <vanila> join { {} \{ \} } { join { {} \{ \} } } this is cool
15:02:19 <vanila> very similar to the lis p one
15:04:26 <vanila> ais523, your befubnge quine reminds me of a mobius strip
15:04:54 <ais523> hmm, that's a good thing to be reminded of, really
15:07:17 <b_jonas> member(D,"200001010102010303"),I is D-47,nth(I,['''',',','member(D,"200001010102010303"),I is D-47,nth(I,[','],W),write(W),fail.'],W),write(W),fail.
15:07:23 <b_jonas> ^ that should work in prolog, modulo typos
15:07:48 <vanila> youve ported the quineto J and prlog
15:07:54 <b_jonas> you might need to modify it so it starts and ends how you want (like, add a main predicate or something)
15:08:04 <b_jonas> vanila: actually, I'm quite sure the J quine was before the perl version
15:08:08 <ais523> b_jonas: that's very different from my approach
15:08:13 <ais523> I'm trying to do the data-structure approach
15:08:15 <ais523> rather than the literal approach
15:08:56 <b_jonas> vanila: if you wanted to be sure, you'd hvae to check the date in the edit history here: http://www.jsoftware.com/jwiki/Puzzles/Quine
15:22:17 <dulla> what is the join crap, vanila
15:27:46 -!- skj3gg has quit (Quit: ZZZzzz…).
15:35:03 -!- skj3gg has joined.
15:36:30 -!- adu has joined.
15:55:09 -!- skj3gg has quit (Quit: ZZZzzz…).
16:00:39 <ais523> quine:-asserta(a((quine:-asserta(a(A,B)),a(C,[D|E]),a(D,E),numbervars(C),write(C),write(.)),[A|B])),a(F,[G|H]),a(G,H),numbervars(F),write(F),write(.).
16:01:08 -!- adu has quit (Quit: adu).
16:01:10 <ais523> the hard part was to make it work both as a data-structure quine /and/ as a literal quine
16:01:52 <ais523> it constructs a data structure equivalent to its own definition, then outputs it and a full stop
16:02:13 -!- SopaXorzTaker has quit (Ping timeout: 255 seconds).
16:02:20 <ais523> actually I think I can golf this slightly
16:02:27 <int-e> sigh, footnotes in the middle of formulas should be forbidden.
16:02:33 <vanila> that is interesting! why does iy use asserta
16:02:52 <ais523> quine:-asserta(a((quine:-asserta(a(A,B)),a(C,D+E),a(D,E),numbervars(C),write(C),write(.)),A+B)),a(F,G+H),a(G,H),numbervars(F),write(F),write(.).
16:03:02 <ais523> the reason for asserta is that I needed to write it all as one predicate
16:03:14 <ais523> basically it's to make a local definition
16:03:28 <ais523> it's basically just "let a(A,B) = … in"
16:03:38 <b_jonas> ais523: what's numbervars?
16:03:40 <ais523> I should probably retract it at the end to clean up
16:03:59 <ais523> and numbervars(),write() is GNU prolog for writing out a predicate with all its free variables named with letters in alphabetical order
16:04:10 <ais523> it ensure that the variable names used on the output are the same as on the input
16:04:20 <ais523> without it, the quine still works but the variable names might be different
16:06:14 -!- KingOfKarlsruhe has left.
16:09:46 <b_jonas> ais523: I'm still trying to understand this
16:10:08 <vanila> i think thats the key bit
16:10:30 <ais523> yeah, that took me ages to figure out
16:12:17 <b_jonas> how does + even come into this?
16:12:27 <ais523> it's basically just cons
16:12:35 <ais523> /all/ Prolog operators are basically just cons
16:12:39 <ais523> until you try to pattern match on them
16:12:56 <ais523> I could have picked any binary operator, but + has a good precedence for making it readable
16:13:30 <b_jonas> ah right, that's why you ad [D|E] before
16:13:48 <ais523> yep, but | has an awful precedence for the purpose
16:15:14 <b_jonas> ah, tricky! you call a twice, and the second time unifies H with G+H
16:15:44 <ais523> Prolog is really hard to think about because the variable names change meanings all the time
16:16:08 -!- SopaXorzTaker has joined.
16:17:08 -!- Tritonio has quit (Ping timeout: 252 seconds).
16:28:33 <b_jonas> ais523: that's a crazy quine. I think it's possible to write it without assert, but it would be much uglier and longer.
16:28:53 <ais523> I'd be interested in a non-asserting version
16:28:58 <ais523> the hard part is to get it all as a single predicate
16:29:13 <ais523> ooh, maybe you could do it with copy_term
16:29:25 <b_jonas> ais523: yes, you can emulate lambdas with copy_term
16:30:18 -!- sebbu has quit (Ping timeout: 250 seconds).
16:30:44 <b_jonas> basically you create an anonymous function like F=fun(body here,Param0,Param1), and then invoke it like (copy_term(F,fun(F0,argument here,other argument here)),F0),
16:31:08 <b_jonas> but I still don't really understand how you got this particular structure of this quine
16:35:29 <b_jonas> actually, you need a slightly more general representation if you want to allow bound variables in the anonymous functions
16:39:16 <b_jonas> ais523: http://dpaste.com/13KEQM6
16:39:32 <b_jonas> ^ that shows how to represent anonymous functions that can be closed over variables
16:39:46 <b_jonas> so if it's closed on variables, those variables must not be copied, but the free variables are copied
16:39:57 <coppro> C++ is a pretty amazing esoteric language
16:40:43 <ais523> oh, I see, the reason we can't directly translate the original into copy_term
16:40:49 <ais523> is because the name 'a' is no longer an atom
16:41:08 <b_jonas> what? it's anonymous, there's no name for it
16:42:22 <b_jonas> re-reading this stuff sure shows why I dislike prolog
16:42:43 <vanila> this isnt normal prolog
16:42:54 <b_jonas> why do you need such a crazy helper function to just be able to use anonymous functinos?
16:43:02 <vanila> you are programming haksell
16:43:11 <vanila> but running it in prolog interpreter
16:43:46 <b_jonas> vanila: it's more like standard ML in a prolog interpreter, but yes
16:45:09 <b_jonas> well, I use prolog lazyness, but haskell lazyness
16:45:42 <vanila> minikanren embedded in scheme works really great
16:45:52 <vanila> because you can easily pass relations around as values and things
16:46:47 <b_jonas> but yeah, given that I wrote iota(N, L) :- unfoldr(lambda(arg(H, H, F), (H < N, F is H + 1)), 0, L). I can see why you think it's like haskell
16:47:06 <b_jonas> it would be easier to write iota directly, without anonymous functions and unfoldr, but this is more fun
16:50:04 <ais523> I think the world could do with a modern update to Prolog
16:50:17 <ais523> that has things like scope, better functional features, and the like
16:50:26 <ais523> Prolog doesn't even ship with map and fold
16:50:31 <b_jonas> ais523: isn't there such a thing called Mozart?
16:51:01 <b_jonas> which even has functional syntax so you don't need to assign every intermediate results to named variables when you don't want to
16:51:50 -!- sebbu has joined.
16:52:06 <b_jonas> ais523: I think it's this one: http://mozart.github.io/
16:52:24 <vanila> minikanren you should see minikanre
16:52:32 -!- sebbu has quit (Changing host).
16:52:32 -!- sebbu has joined.
16:53:40 <b_jonas> ais523: but anyway, yes, that's why I wrote that library
16:53:45 <b_jonas> because prolog doesn't even have a map builtin
16:55:57 <vanila> id ont have a good link for it
16:56:12 <vanila> i leaerned it from the book
16:56:49 <b_jonas> if I'm writing arrays of four floats in a binary file and I'm using arrays where the first two floats have certain nan values (represented as 0xffc0c708, 0xffcf9846) as sentry records, does that mean I'm strange?
16:57:11 <b_jonas> I mean, I could store lengths instead of sentries, I don't know why I did it this way
16:57:55 <vanila> i think thats a great way to do it :D
16:58:03 <b_jonas> vanila: oh, is it another of those languages like standard ML where you have to buy the language standard to be able to prorgam?
16:58:16 <b_jonas> because it's not available freely
16:58:30 <b_jonas> is it now? where do I get the standard for free?
16:58:33 <vanila> https://github.com/SMLFamily/The-Definition-of-Standard-ML
16:58:36 <b_jonas> there are free interpreters for sure
16:58:45 <b_jonas> oh great, since when is that?
16:59:08 <b_jonas> thanks for telling me that
16:59:41 <b_jonas> are they releasing this because there's a more recent standard (possibly in the future, under preparatoin) that they want us to buy?
17:00:44 <ais523> possibly because they're being outcompeted by ocaml
17:02:02 <vanila> maybe they realized the historical importance of preserving it
17:02:17 -!- MDream has changed nick to MDude.
17:02:21 <vanila> MIT Press has graciously allowed us to release this work in PDF form and continue to extend it again
17:05:41 -!- koo7 has joined.
17:08:09 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:25:10 -!- AndoDaan has quit (*.net *.split).
17:25:10 -!- augur has quit (*.net *.split).
17:25:10 -!- TodPunk has quit (*.net *.split).
17:25:10 -!- J_Arcane has quit (*.net *.split).
17:25:10 -!- myndzi has quit (*.net *.split).
17:25:11 -!- tromp has quit (*.net *.split).
17:25:11 -!- Gregor has quit (*.net *.split).
17:25:11 -!- Vorpal has quit (*.net *.split).
17:25:12 -!- b_jonas has quit (*.net *.split).
17:25:12 -!- mroman has quit (*.net *.split).
17:25:12 -!- clog has quit (*.net *.split).
17:26:37 -!- GeekDude has joined.
17:31:41 -!- augur has joined.
17:31:41 -!- TodPunk has joined.
17:31:41 -!- J_Arcane has joined.
17:31:41 -!- myndzi has joined.
17:31:41 -!- tromp has joined.
17:31:41 -!- Gregor has joined.
17:31:41 -!- Vorpal has joined.
17:31:41 -!- b_jonas has joined.
17:31:41 -!- mroman has joined.
17:31:41 -!- clog has joined.
17:32:10 -!- ais523 has quit.
17:32:18 -!- callforjudgement has joined.
17:50:20 -!- adu has joined.
18:00:56 -!- adu has quit (Quit: adu).
18:03:22 -!- Warrigal has changed nick to tswett.
18:04:19 <tswett> It seems like there are a lot of things that everything is.
18:04:29 -!- vanila has left ("Leaving").
18:04:33 <tswett> Everything is a topological space. Everything is a Chu space. Everything is a category. Everything is a topos.
18:07:25 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:21:23 -!- shikhin_ has joined.
18:24:50 -!- shikhin has quit (Ping timeout: 265 seconds).
18:26:47 -!- shikhin_ has changed nick to shikhin.
18:27:58 <HackEgo> [wiki] [[Iexp]] M http://esolangs.org/w/index.php?diff=41917&oldid=41648 * GermanyBoy * (+0)
18:38:04 -!- skj3gg has joined.
18:41:21 -!- arjanb has joined.
18:42:54 -!- bb010g has joined.
18:43:01 -!- AnotherTest has joined.
18:55:21 -!- GeekDude has quit (Changing host).
18:55:21 -!- GeekDude has joined.
18:55:43 -!- GeekDude has quit (Changing host).
18:55:43 -!- GeekDude has joined.
19:08:10 -!- skj3gg has quit (Quit: ZZZzzz…).
19:27:25 -!- hjulle has joined.
19:30:48 -!- skj3gg has joined.
19:37:00 -!- Koen_ has joined.
19:37:13 -!- skj3gg has quit (Quit: ZZZzzz…).
19:38:19 -!- PinealGlandOptic has joined.
19:41:50 -!- skj3gg has joined.
19:55:44 -!- Sgeo has joined.
20:01:54 -!- Patashu has joined.
20:03:43 -!- Sprocklem has joined.
20:22:18 -!- Patashu has quit (Ping timeout: 244 seconds).
20:24:23 <oren> tswett: You forgot, everything is an object, everything is a file, everything is a sequence of bytes
20:27:27 <oren> Also, in graphics everyhting is a bunch of triangles
20:28:58 <oren> The desire to reduce everything to one thing is similar to the desire to find the simplest turing complete language
20:29:24 <b_jonas> ah yes, everything is also a function, and everything is a set
20:30:15 <oren> and everything is a list (of lists)
20:31:25 <b_jonas> oh yes, everything is a list, as well as a List
20:32:27 <koo7> everything is nothing, without her
20:42:24 -!- spiette has joined.
20:49:12 -!- skj3gg has quit (Quit: ZZZzzz…).
20:54:32 -!- SignX has joined.
21:07:10 <b_jonas> .i ro sazri se karce cu na kakne lo nu pu za jdice lo ve klama
21:09:06 <Koen_> you shouldn't have said, no one would have noticed
21:09:50 <Koen_> in fact someone might have been about to answer
21:10:35 <b_jonas> I think I typed the context that explains it in the right channel
21:11:50 <Koen_> is the language part of the context?
21:12:18 <b_jonas> the language can be guessed. the context might be hard.
21:19:20 <oren> looks like esperanto
21:19:42 <oren> no wait lojban
21:20:07 <oren> yes. it's def. lojban
21:21:31 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
21:23:20 <b_jonas> oren: yes, it's lojban. you can sometimes recognize lojban from the way it has apostrophe between two vowels not following "q", but that doesn't occur in this text
21:23:44 <oren> I recognized the . at the beginninh
21:23:45 <b_jonas> still, ".i" is a give-away
21:25:25 <newsham> does it read backwards? why does it "start" with dot?
21:25:42 <oren> th dot is a glottal stop iirc
21:28:01 <oren> so .i would be sort of like a catch in your throat followed by English "ee".
21:29:58 <newsham> bossy language. what if i want to catch my breath later? :)
21:30:09 -!- skj3gg has joined.
21:30:37 <b_jonas> newsham: dot means a pause, it doesn't matter whether it's attached to after a word or before the next, but it's usually written next to the word that requires the pause
21:38:24 -!- Sprocklem has quit (Ping timeout: 250 seconds).
21:40:22 -!- callforjudgement has quit.
21:46:23 -!- skj3gg has quit (Quit: ZZZzzz…).
21:53:17 -!- Sprocklem has joined.
22:02:22 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:04:42 -!- SignX has quit (Quit: Page closed).
22:15:14 -!- villasukka has joined.
22:18:35 -!- skj3gg has joined.
22:29:08 -!- 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?").
22:33:03 -!- skj3gg has quit (Quit: ZZZzzz…).
22:35:25 -!- AnotherTest has quit (Remote host closed the connection).
22:42:12 -!- skj3gg has joined.
22:43:16 -!- oerjan has joined.
22:46:21 <dulla> > let iter a b = a+b +1 in let again = 1:1: zipWith iter again (tail again) in take 8 again
22:46:47 <dulla> > let iter a b = a+b +1 in let again = 1:1: zipWith iter again (tail again) in unwords . map show . take 8 $ again
22:48:06 <lambdabot> ais523 said 8h 31m 8s ago: I picked 25 because that's when patents expire
22:55:35 <HackEgo> 457) <itidus20> software patents strike again <ais523_> that's got to be at least three times, now <ais523_> are they out yet? \ 1059) <kmc> patents do seem to encourage innovation, but much of it is innovation on how to make things slightly worse to avoid patents
22:59:38 <int-e> patents are devices that allow lawyers to profit from other people's inventions.
23:00:21 <dulla> I know a patent lawyer that knows that feel
23:00:47 <dulla> I tihnk a really long paper was written about the entirety of the patent system
23:00:55 <dulla> I should ask them for it
23:01:10 <dulla> Though it'd send them right out of a job, they are retiring age anyways
23:01:25 <tswett> oren: ah, but in mathematics, almost nothing is a sequence of bytes!
23:02:05 <tswett> Unless you're the kind of mathematician who believes that the only objects which "really exist" are computer programs.
23:02:14 <tswett> And things representable as computer programs.
23:02:31 <oren> the only objects that really exist are, um, actual objects
23:02:49 <oren> like laptops, or coffee beans
23:02:50 <dulla> We need more stallman in this channel
23:02:51 <MDude> Um ins't an object.
23:03:05 <tswett> The "antimathematician", who believes that no abstract mathematical objects exist at all.
23:03:26 <dulla> What isn't a category
23:03:36 <tswett> Addition is commutative? Well, it depends on which sorts of objects you're moving around.
23:04:16 <tswett> What if they're, say, water and sulfuric acid? Any chemistry student knows that water plus sulfuric acid is not the same thing as sulfuric acid plus water.
23:05:12 <MDude> But adding acid to watta is how you oughtta.
23:05:12 <oren> in one case, an accident waiting to happen (the acid will sploosh) in the other way it is safe
23:05:36 <oren> I know that from grade 12 chem
23:06:18 <MDude> I can't beleive Nethack supposedly thinks of everything, but makes water the only clear potion.
23:06:56 <oren> IRL most liquids are clear
23:07:01 <tswett> Actually, Nethack characters perceive the world entirely through scent. Water is the only unscented potion.
23:07:34 * oerjan hands oren some tea water with hardly any polonium in it
23:07:47 <MDude> Johnny was a Chemist's Son would make a great special death screen, though.
23:07:49 <tswett> How can they make out detailed images, you ask?
23:07:58 <olsner> I remember the reason for the rule, but then I learnt the rule both backwards and forwards, so I don't know what you're supposed to do to avoid the acid splashing accident
23:08:27 <oren> add acid to water, and use a stirring stick to guide the stream
23:08:36 <MDude> Acid to watta, just like you outta.
23:08:37 <olsner> luckily I haven't had a reason to mix acid and water
23:08:56 <MDude> Not water to acid, that's stupid and placid.
23:09:13 <tswett> Simple. They have special organs which smell photons. The photons are focused by refractive elements.
23:09:26 <tswett> Of course, "placid" means "peaceful". (Right?)
23:09:27 <olsner> Water In Acid spells "wise" in swedish, so it sounds like that would be the rule :)
23:11:41 <oren> technically, making mixed drinks usually involves mixing acids with water
23:11:52 <oren> just not strong ones
23:11:58 <oerjan> olsner: syre og vann går an, men vann og syre er uhyre hth
23:12:00 <pikhq> Though *typically* you don't make mixed drinks with particularly dangerous acids.
23:12:44 <pikhq> I guess unless you consider Coke. It's dilute, but Coke has phosphoric acid in it.
23:12:49 <pikhq> Which can be crazy dangerous.
23:13:08 <oren> Coca cola is a common part of mixed drink
23:13:33 <oren> so you should add coca cola to rum, not the other way round
23:13:50 -!- spiette has quit (Quit: :qa!).
23:14:11 <tswett> But the rule applies specifically to sulfuric acid, doesn't it?
23:14:26 <pikhq> It's true of most possibly-dangerous acids.
23:14:35 <pikhq> I think just more so of sulfuric.
23:14:46 -!- copumpkin has joined.
23:14:47 <oren> when i learned it we were using hydrochloric acid
23:15:37 <tswett> Now, suppose you dilute sulfuric acid to the point where it just has a mildly sour taste.
23:15:47 <tswett> How dangerous would it be to drink?
23:16:35 <tswett> Arright, I'm going to see if the definition of a topos allows you to define a topos in a topos.
23:17:00 <pikhq> I can't imagine it would be very good to drink. Sulfur is not particularly good in biology.
23:18:22 <oren> I imagine hydrochloric acid would be safer
23:18:47 <oren> where does the chlorine in salt you eat go?
23:19:17 <tswett> Does it go into urine?
23:19:53 <tswett> I've read tiny bits about the medical significance of positive ions like sodium and potassium, but I don't know anything about the significance of chloride.
23:20:04 <tswett> Except that it's in stomach acid.
23:20:25 <pikhq> Chloride ions are apparently used in the kidneys.
23:20:51 <pikhq> And a few other random weird places.
23:21:16 <tswett> Yeah, but how do they exit the body?
23:21:33 <pikhq> Oh, huh. For instance it's used to balance the acidity of the blood.
23:22:28 <pikhq> Actually definitely.
23:22:45 <tswett> Lessee. A topos is a category with all equalizers, all finite products, and all power objects?
23:23:23 <pikhq> So there you go. It's used in the body and excess is excreted in urine.
23:23:54 <int-e> tswett: apparently, sodium sulfate is not toxic, so the main danger of sulfuric acid should be its corrosiveness
23:24:04 <pikhq> Ah. Well then, there you go.
23:24:04 <oren> oh, duh silly me. stomach acid -is- HCl, so of course HCl would be safe to eat as long as it's not strong enough to burn
23:24:11 <zzo38> I am also believing patent is bad things. Maybe it may have been a bit useful much in the past, but these days it is very bad.
23:25:26 -!- Lymia has quit (Ping timeout: 250 seconds).
23:25:59 <tswett> Now, how would you define a "topos in a topos"...
23:26:57 <tswett> There'd have to be an object Ob which is the object of objects.
23:27:31 <tswett> Then what you want is a family Ar of objects indexed by Ob * Ob.
23:27:40 <tswett> Of course, Ob * Ob need not be a set.
23:28:33 <oerjan> i vaguely recall that sweat also contains salt
23:30:19 <oerjan> oh hm seems to be sodium but not chlorine
23:30:51 <olsner> hm, so sweating a lot will leave you with excess chlorine?
23:33:37 -!- contrapumpkin has joined.
23:36:42 -!- copumpkin has quit (Ping timeout: 250 seconds).
23:39:32 <zzo38> Is Unlicensed files OK on esolang wiki? Is WTFPL licensed files OK on esolang wiki? Unlicense is public domain too like CC0 is; I believe WTFPL is also effectively public domain, but I don't know what wiki administration would have you believe about such thing.
23:40:38 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
23:41:07 <zzo38> (The WTFPL license text itself though requires only that modified versions of the license aren't called the same as the original.)
23:42:12 -!- skj3gg has quit (Quit: ZZZzzz…).
23:43:15 -!- skj3gg has joined.
23:43:34 <tswett> You certainly can't put copyrighted stuff there without a license.
23:43:52 -!- teuchter has quit (Read error: Connection reset by peer).
23:43:56 <oerjan> zzo38: i'm guessing the problem might be that simple licenses like WTFPL won't successfully release as many rights as CC0 in all jurisdictions?
23:45:27 <oerjan> the secondary problem is that even if it does, it would take significant work from lawyers to clarify that it does
23:45:34 <zzo38> I believe it does allow you to relicense it under CC0 and treat it as if it is always CC0.
23:46:07 <oerjan> well if it says so explicitly it should be ok?
23:46:48 <tswett> That would be an interesting copyright license: "You are permitted to release this work under any license."
23:46:48 <zzo38> Well, it just says that you "DO WHAT THE FUCK YOU WANT TO"; they say that implies anything can be done, so that would include relicensing under CC0 like that
23:47:07 <zzo38> Or making it just public domain if that is legal in your jurisdiction
23:47:09 <tswett> It doesn't actually let you do much directly, but you could just give yourself a license to do whatever.
23:47:24 <tswett> Unfortunately, making things public domain is a felony in my jurisdiction.
23:47:53 <zzo38> The only restriction is that modified version of the license itself cannot be called WTFPL.
23:48:40 <olsner> is there a discordian license?
23:48:56 <zzo38> Nevertheless it seems unlikely that any program licensed by WTFPL is one you would likely need to post on esolang wiki, but it is something that might happen.
23:49:17 <zzo38> olsner: I don't know. I think it is just public domain isn't it?
23:49:39 <MDude> You may use software under this license only if you disregard the terms of this license.
23:51:07 <olsner> You may release this work under any license except this license or any other license the work has previously been released under.
23:51:30 -!- Tritonio has joined.
23:52:14 <olsner> needs more work, it should require that the new license includes that clause or something sufficiently like it
23:52:44 <MDude> Step 1: Sells software usnder a closed source license with a "this licesne may be changed at time without notice" clause.
23:52:58 <MDude> Step 2: Wait for it to be sued widely among software developers.
23:53:09 <tswett> You may release this work under any license L as long as you can give a proof that L does not allow anyone to release the work under this license.
23:53:31 <MDude> Step 3: Without notice, change your license to make it so anyone using it needs to relase any software developed on the same comptuer to the public domain.
23:54:12 <olsner> tswett: only "this license"? not L too?
23:55:13 <MDude> This license isn't indicate dto be L, though.
23:55:33 <tswett> "This license" is the license I just stated, not L.
23:56:09 -!- skj3gg has quit (Quit: ZZZzzz…).
00:00:51 -!- Phantom_Hoover has joined.
00:04:47 <tswett> Man, I really like how you can define stuff in the language of categories.
00:04:59 <tswett> From now on, I want everything to be defined in the language of categories.
00:05:08 <tswett> Right now I'm working on defining "category" in the language of categories.
00:06:05 <Phantom_Hoover> i've already mentioned that godawful topology book i once read, i think
00:06:26 <tswett> Hm, what's a topological space in the language of categories...
00:11:14 -!- Sketra has joined.
00:21:39 -!- skj3gg has joined.
00:21:51 -!- shikhin_ has joined.
00:23:44 <oren> and barfing a lot will leave you with excess sodium
00:25:24 -!- shikhin has quit (Ping timeout: 265 seconds).
00:34:25 -!- skj3gg has quit (Quit: ZZZzzz…).
00:35:33 -!- skj3gg has joined.
00:47:00 -!- skj3gg has quit (Quit: ZZZzzz…).
00:49:14 -!- skj3gg has joined.
01:03:53 -!- FreeFull has quit (Ping timeout: 244 seconds).
01:04:31 -!- skj3gg has quit (Quit: ZZZzzz…).
01:13:02 <oerjan> and the bear has been noticed
01:13:33 -!- Phantom__Hoover has joined.
01:13:37 -!- skj3gg has joined.
01:13:46 <oerjan> looks like it's the king
01:16:17 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
01:18:33 <zzo38> Apparently there are at least three different IRC clients called PHIRC.
01:22:23 <tswett> I hope none of them are written in PHP.
01:22:43 -!- skj3gg has quit (Quit: ZZZzzz…).
01:27:45 -!- adu has joined.
01:32:02 <zzo38> One of them is the one I wrote. I wrote it because I don't like any other IRC clients. I wrote in PHP but would want to eventually rewrite it in C, however I don't quite understand making internet connection with a C code.
01:36:21 -!- AndoDaan has joined.
01:40:42 -!- Tritonio has quit (Ping timeout: 252 seconds).
01:42:22 -!- Tritonio has joined.
01:47:13 -!- Sketra has quit (Ping timeout: 264 seconds).
01:50:39 -!- AndoDaan has quit (Ping timeout: 245 seconds).
01:54:37 -!- AndoDaan has joined.
01:55:53 <tswett> I'm trying to write out the definition of a topos in a topos.
01:55:59 <tswett> This thing's complicated.
01:59:39 <dulla> there may be a problem with that
01:59:49 <dulla> how about using ZFC+
02:07:20 <oerjan> what would grothendieck do
02:07:40 <oerjan> (apart from running away into the forest)
02:10:22 <oerjan> i think my brain just vetoed me trying to read about topoi again
02:12:02 -!- dulla has quit (Ping timeout: 246 seconds).
02:15:36 -!- dulla has joined.
02:15:49 <tswett> Most of it is pretty straightforward.
02:16:09 <tswett> A topos in a topos consists of these objects, and these arrows with these commutative diagrams...
02:16:31 <oerjan> and then the universe explodes.
02:16:56 <tswett> And then all of a sudden one of the things you need isn't an object, or an arrow, or a commutative diagram.
02:17:18 <tswett> It's a frickin' mapping from this collection of arrows to that collection of arrows.
02:17:42 <tswett> Nope. It's just a topos.
02:18:09 <oerjan> well also that sounds like a functor.
02:22:37 <tswett> Well, it's this: "An arrow EQ with certain properties. For all arrows M with the same properties, an arrow U with these other properties in relation to EQ and M."
02:24:25 -!- Lymia has joined.
02:29:11 -!- Sprocklem has quit (Ping timeout: 246 seconds).
02:30:57 <tswett> Ah, but topoi are cartesian closed.
02:31:46 <tswett> So that last thing is really just an arrow again. I think.
02:32:54 <tswett> M is an arrow A -> B and U is also an arrow A -> B, so this "for all arrows M with these properties, an arrow U with those properties" is really just a single arrow (A -> B) -> (A -> B).
02:34:36 <tswett> Because having A -> B as a codomain doesn't express the restrictions which M has.
02:49:09 -!- AndoDaan has quit (Quit: Going, going, gone.).
02:49:10 -!- Tritonio_ has joined.
02:50:44 -!- Tritonio has quit (Ping timeout: 252 seconds).
02:51:20 -!- Tritonio_ has changed nick to Tritonio.
02:56:17 -!- skj3gg has joined.
02:57:53 -!- arjanb has quit (Quit: .).
03:18:30 -!- skj3gg has quit (Quit: ZZZzzz…).
03:20:17 -!- shikhin_ has quit (Ping timeout: 244 seconds).
03:22:09 -!- Sprocklem has joined.
03:28:35 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
03:33:30 -!- skj3gg has joined.
03:44:18 -!- skj3gg has quit (Quit: ZZZzzz…).
03:46:20 -!- skj3gg has joined.
03:49:38 -!- Tritonio has quit (Remote host closed the connection).
03:50:02 -!- Sprocklem has quit (Ping timeout: 246 seconds).
03:54:04 <oren> wait. the plural of topos is topoi?
03:56:53 -!- copumpkin has joined.
04:02:38 -!- kapil___ has joined.
04:02:59 -!- hjulle has quit (Ping timeout: 246 seconds).
04:09:51 -!- skj3gg has quit (Quit: ZZZzzz…).
04:16:58 <oerjan> oren: it's a greek plurla
04:17:52 <oerjan> i think -os/-oi is about as common in greek as -us/-i in latin
04:20:33 <oerjan> and essentially derive from the same suffixes in indoeuropean
04:44:50 -!- ProofTechnique has joined.
05:00:45 -!- MDude has changed nick to MDream.
05:35:36 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:35:57 <zzo38> There is still one kind of question I have not received a satisfactory answer which has to do with automatically filling in the frequent words table for a Z-machine story file.
06:27:49 -!- aloril has quit (Read error: Connection reset by peer).
06:28:20 -!- aloril has joined.
07:07:39 -!- bluckbot has joined.
07:08:01 <dulla> oerjan kick bluckbot
07:08:55 -!- merdach has joined.
07:09:35 <dulla> this ithe the channel that shares an abstract kind of feels, through the magic of math, and esotera
07:10:13 <dulla> this is the channel of esolang wiki
07:10:29 <HackEgo> merdach: 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.)
07:11:26 <dulla> > let cock a b = a+b +1 in butt = 1:1: zipWith cock butt (tail butt) in unwords . map show . take 8 $ butt
07:11:28 <lambdabot> <hint>:1:31: parse error on input ‘=’
07:14:11 <dulla> > butt = 1:1: zipWith (\a b -> a+b+1) butt (tail butt) in unwords . map show . take 8 $ butt
07:14:12 <lambdabot> <hint>:1:6: parse error on input ‘=’
07:14:26 <dulla> > let butt = 1:1: zipWith (\a b -> a+b+1) butt (tail butt) in unwords . map show . take 8 $ butt
07:15:12 <HackEgo> [wiki] [[EsoInterpreters]] http://esolangs.org/w/index.php?diff=41918&oldid=41703 * AndoDaan * (+15) noted Kipple's Deadfish.
07:18:02 -!- gelos_ has joined.
07:18:04 <zzo38> I'm not sure what "this ithe the channel that shares an abstract kind of feels, through the magic of math, and esotera" is meaning, although it doesn't seem to be spelled correctly anyways, and possibly the grammar is also unclear.
07:27:45 <elliott> is dulla inviting people here ors omething
07:33:28 -!- Patashu has joined.
07:56:16 <oerjan> dulla: your variable naming scheme needs work hth
08:05:47 -!- AndoDaan has joined.
08:35:27 <dulla> what would you prefer, oerjan
08:37:14 <oerjan> something with less shock words
08:41:04 <dulla> > let tingle = repeat 1 in take 5 tingle
08:45:21 <dulla> > let gently = sum . map 1 in gently [3,6,9]
08:45:23 <lambdabot> Could not deduce (GHC.Num.Num (a0 -> c))
08:45:23 <lambdabot> arising from the ambiguity check for ‘e_11369’
08:45:23 <lambdabot> from the context (GHC.Num.Num (a -> c),
08:45:49 <dulla> > let gently = sum . map (\a -> 1) in gently [3,6,9]
08:46:07 -!- vanila has joined.
08:46:22 <dulla> > let tenderly a = 1 in let gently = sum . map tenderly in gently [3,6,9]
08:58:42 -!- dulla has quit (Ping timeout: 244 seconds).
09:06:17 -!- FreeFull has joined.
09:07:15 -!- oerjan has quit (Quit: Good luck).
09:15:06 -!- adu has quit (Quit: adu).
09:25:51 -!- AndoDaan has quit (Ping timeout: 252 seconds).
09:30:47 -!- AndoDaan has joined.
09:40:55 -!- gelos_ has quit (Ping timeout: 246 seconds).
09:45:33 -!- hjulle has joined.
09:58:45 <HackEgo> [wiki] [[Pig]] N http://esolangs.org/w/index.php?oldid=41919 * 122.37.11.94 * (+279) A esolang with only one keyword: PIG.
09:59:08 <HackEgo> [wiki] [[Pig]] http://esolangs.org/w/index.php?diff=41920&oldid=41919 * 122.37.11.94 * (+1) /* Usage */
10:01:04 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41921&oldid=41905 * 122.37.11.94 * (+10)
10:02:55 <HackEgo> [wiki] [[Pig]] http://esolangs.org/w/index.php?diff=41922&oldid=41920 * 122.37.11.94 * (+95) /* Hello, World in Pig */
10:03:35 <HackEgo> [wiki] [[Pig]] http://esolangs.org/w/index.php?diff=41923&oldid=41922 * 122.37.11.94 * (+1) /* Hello, World in Pig */
10:05:15 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41924&oldid=41790 * 122.37.11.94 * (+67)
10:08:47 -!- dulla has joined.
10:20:58 <HackEgo> [wiki] [[Pig]] http://esolangs.org/w/index.php?diff=41925&oldid=41923 * 122.37.11.94 * (+1) /* Hello, World in Pig */
10:32:36 -!- Phantom_Hoover has joined.
10:56:21 <lambdabot> Control.Monad join :: Monad m => m (m a) -> m a
10:56:21 <lambdabot> System.FilePath.Windows joinDrive :: FilePath -> FilePath -> FilePath
10:56:37 <mroman> why's there no join in Control.Concurrent?
10:59:12 <mroman> also Chan has no chanSize function :(
10:59:23 <mroman> (i.e. return how many items there are in the chan right now)
11:12:36 <mroman> http://codepad.org/QZcPNtQ9
11:12:39 <mroman> oh well. This is working :)
11:15:30 <zzo38> Now I invented many new Sliver cards for Magic: the Gathering
11:24:17 -!- boily has joined.
11:46:32 -!- Patashu has quit (Ping timeout: 264 seconds).
11:53:04 -!- Koen_ has joined.
11:58:11 <b_jonas> they're there in the list http://zzo38computer.org/textfile/miscellaneous/magic_card/cards.txt
11:59:48 <zzo38> Make up the kind of "Babson-task" with Magic: the Gathering; you have same cards as opponent's cards in their hand, and whatever card they play, the only winning move(s) involves the first card you play from your own hand being the matching card of they just played. (For example if they played Aether Snap then you have to play Aether Snap, if they played Artificial Evolution you have to play Artificial Evolution, if they played Ancestral Recall you
12:05:30 <b_jonas> zzo38: I was thinking a bit about that, and I think it might be possible, at least for about three or four cards
12:05:47 <b_jonas> though I haven't found a working construction yet
12:10:03 <zzo38> I wanted to do it with at least five cards though; preferably at least seven; however, even just three or four would do too, almost
12:10:17 -!- vanila has quit (Quit: Leaving).
12:14:34 <b_jonas> zzo38: I might think about this a bit more later
12:22:42 -!- boily has quit (Quit: CORRUGATED CHICKEN).
12:32:28 -!- kapil___ has quit (Quit: Connection closed for inactivity).
12:54:53 -!- Gracenotes has quit (Remote host closed the connection).
12:57:49 -!- kapil___ has joined.
12:58:43 -!- AnotherTest has joined.
13:07:28 -!- AnotherTest has quit (Ping timeout: 252 seconds).
13:33:08 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
14:03:03 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41926&oldid=41921 * Rottytooth * (+20) /* L */ added light pattern
14:04:55 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41927&oldid=41926 * Rottytooth * (+131) /* A */ a programming language...
14:09:45 -!- AnotherTest has joined.
14:15:04 -!- skj3gg has joined.
14:15:16 -!- skj3gg has quit (Client Quit).
14:18:36 -!- AnotherTest has quit (Ping timeout: 252 seconds).
14:21:47 -!- AnotherTest has joined.
14:23:05 -!- SopaXorzTaker has joined.
14:26:18 -!- AnotherTest has quit (Ping timeout: 252 seconds).
14:30:13 -!- nortti has changed nick to lawspeaker.
14:30:35 -!- lawspeaker has changed nick to nortti.
14:34:23 -!- GeekDude has joined.
14:37:43 -!- adu has joined.
14:48:30 -!- skj3gg has joined.
14:48:55 -!- not^v has joined.
15:02:35 -!- `^_^v has joined.
15:10:02 -!- not^v has quit (Ping timeout: 246 seconds).
15:10:23 -!- not^v has joined.
15:20:10 -!- 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?").
15:27:10 -!- not^v has quit (Ping timeout: 252 seconds).
15:27:48 -!- not^v has joined.
15:35:58 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
15:43:54 -!- Sprocklem has joined.
15:44:37 -!- not^v has quit (Ping timeout: 252 seconds).
15:48:50 -!- mihow has joined.
15:52:19 -!- Sprocklem has quit (Ping timeout: 245 seconds).
16:02:22 -!- SopaXorzTaker has quit (Ping timeout: 252 seconds).
16:02:30 <AndoDaan> For the Hello transposable world task "Your code must be transposable. In other words, your code must not be changed by this program: http://golf.shinh.org/p.rb?transpose+lines" No change means no change to what your code outputs, right?
16:06:03 <elliott> sounds like it's a textural property
16:07:13 <AndoDaan> Hmm. The example C code given https://ideone.com/uEyGtr is alright?
16:16:09 -!- SopaXorzTaker has joined.
16:23:00 -!- AndoDaan has quit (Read error: Connection reset by peer).
16:23:15 -!- AndoDaan has joined.
16:27:16 -!- ProofTechnique has joined.
16:33:01 -!- GeekDude has left ("{{{}}{{{}}{{}}}{{}}}").
16:40:54 <int-e> it's an interesting task, but I dislike the coarse granularity for the program sizes...
16:41:55 <int-e> (since the program text must be a square. It'd be more fun if some triangular shapes were allowed)
16:44:22 <int-e> Hmm "triangular" isn't the right term...
16:49:57 -!- AndoDaan has quit (Ping timeout: 265 seconds).
16:53:46 -!- ais523 has joined.
16:53:48 -!- skj3gg has quit (Quit: ZZZzzz…).
16:56:20 -!- callforjudgement has joined.
16:56:34 -!- ais523 has quit (Client Quit).
17:01:17 -!- pallokolmio has quit (Remote host closed the connection).
17:02:24 <int-e> Well, the lines of the lengths would have to be monotonely decreasing.
17:06:42 -!- mihow has quit (Quit: mihow).
17:09:41 <int-e> anyway the risk in doing that is that one could get a ton of L-shaped solutions. So maybe restricting to squares is a good thing after all.
17:12:51 -!- skj3gg has joined.
17:18:09 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:21:56 <Melvar> In one channel, I confused someone by talking about an L-shaped enter key, because he thought I meant a reverse-L, whereas I had never seen that type before.
17:27:54 -!- Lymia has quit (Ping timeout: 250 seconds).
17:30:49 <elliott> wait, L-shaped enter keys are a thing?
17:36:29 <Taneb> elliott, I think I've seen some
17:37:46 -!- callforjudgement has changed nick to ais523.
17:47:36 -!- not^v has joined.
17:51:49 -!- Tritonio has joined.
17:56:29 <mroman> is there an MP library for haskell?
17:58:09 <mroman> like Chan or MVar but over the web?
18:00:36 <mroman> sure I could just use read/show and tcp sockets
18:05:20 -!- FreeFull has quit (Ping timeout: 244 seconds).
18:06:45 -!- arjanb has joined.
18:15:36 -!- vanila has joined.
18:17:21 -!- vanila has quit (Remote host closed the connection).
18:26:08 -!- not^v has quit (Ping timeout: 265 seconds).
18:35:21 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:35:26 -!- vanila has joined.
18:42:07 -!- TieSoul has changed nick to TieHomework.
18:53:36 -!- skj3gg has quit (Quit: ZZZzzz…).
18:54:19 -!- shikhin has joined.
19:13:55 -!- mihow has joined.
19:20:31 -!- MDream has changed nick to MDude.
19:20:52 <MDude> What's up, vanila bean?
19:24:06 <MDude> I should go write things.
19:25:09 <MDude> Maybe about chat bots.
19:25:17 <MDude> Mostly sitting around too.
19:29:23 -!- skj3gg has joined.
19:31:06 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
19:33:08 -!- Vorpal has joined.
19:33:30 -!- Vorpal has quit (Changing host).
19:33:30 -!- Vorpal has joined.
19:52:00 -!- kcm1700_ has quit (Remote host closed the connection).
19:57:13 -!- skj3gg has quit (Quit: ZZZzzz…).
19:57:14 -!- kcm1700 has joined.
20:00:22 -!- Tritonio has quit (Remote host closed the connection).
20:00:31 -!- skj3gg has joined.
20:01:09 -!- Tritonio has joined.
20:01:25 -!- Patashu has joined.
20:05:16 -!- nycs has joined.
20:07:32 -!- `^_^v has quit (Ping timeout: 246 seconds).
20:08:12 -!- vanila has quit (Quit: Leaving).
20:09:14 -!- skj3gg has quit (Quit: ZZZzzz…).
20:09:39 -!- AndoDaan has joined.
20:12:05 -!- TieHomework has changed nick to TieSleep.
20:18:43 -!- bb010g has joined.
20:22:22 -!- Tritonio has quit (Remote host closed the connection).
20:22:35 -!- Tritonio has joined.
20:22:57 -!- Lymia has joined.
20:25:20 -!- AnotherTest has joined.
20:28:11 -!- Patashu has quit (Ping timeout: 246 seconds).
20:37:04 -!- mihow has quit (Quit: mihow).
20:39:24 -!- AnotherTest has quit (Remote host closed the connection).
20:56:07 -!- TieSoul has joined.
20:56:21 -!- Tritonio has quit (Remote host closed the connection).
20:58:37 -!- TieSleep has quit (Ping timeout: 245 seconds).
20:59:07 -!- Tritonio has joined.
21:00:18 -!- Tritonio has quit (Remote host closed the connection).
21:01:42 -!- mihow has joined.
21:29:14 <fizzie> Just so you know, fungot has arrived. But I still don't have any Internet here.
21:31:25 <ais523> so fungot is trying to connect to #esoteric but failing due to lack of internet?
21:31:44 <ais523> or, hmm, I think I misinterpreted you
21:33:18 <AndoDaan> fizzie, the innie and outie of your stament contradict each other.
21:34:43 <AndoDaan> Though, I read somewhere that a couple of guys developed an internet protocol for use with carriere pigeons.
21:35:11 <fizzie> ais523: It's not trying to connect, I just meant that the physical hardware arrived.
21:35:38 <ais523> I take it you're now in UKland?
21:35:45 <fizzie> Although I haven't even booted the box up, been too busy.
21:35:53 <ais523> AndoDaan: IP over Avian Carrier is an RFC
21:36:09 <ais523> I further assume you're doing an ais523 and have borrowed Internet off someone, due to not having your own
21:36:16 <fizzie> IP over bongo drums is a thing too.
21:36:40 -!- skj3gg_ has joined.
21:36:42 -!- skj3gg has joined.
21:37:04 <fizzie> I'm using a mobile thing. But it officially disallows tethering, so it's not suitable for fungotting.
21:37:49 <fizzie> I've ordered something more DSLy, but it might take a week or two more.
21:39:56 <fizzie> (This is Three's pay-as-you-go offering, because funnily enough you can't order a pay-monthly thing online without filling three years of address history, and the online form only accepts UK post codes.)
21:41:20 <fizzie> Still, they have a £15 "add-on" for 30 days of unlimited data, that's not too bad.
21:42:03 <ais523> 50p per day seem reasonable if you don't have another source of Internet access
21:42:17 <AndoDaan> Unlimited meaning limited, of course.
21:42:40 <fizzie> Plus they have this "feel at home" thing, which allegedly means I'll be able to use (25G/month or something) that data on my US visit, and also in Finland.
21:43:11 <fizzie> They have some traffic shaping thing, don't know about other limits.
21:43:19 -!- skj3gg_ has quit (Quit: ZZZzzz…).
21:45:03 <fizzie> I still have a Finnish SIM too, but it's too big to fit in this phone.
21:45:25 <AndoDaan> I guess I could have access to unlimited funds, if I was only allowed to spend 15p a day.
21:46:56 -!- skj3gg_ has joined.
21:47:40 <fizzie> Back in Finland I used to use maybe 100-150M of mobile data per month, so the £10 "add-on" with 1G of data for 30 days might be plenty, after the home internet gets here.
21:52:31 -!- AndoDaan has quit (Ping timeout: 265 seconds).
21:53:37 -!- skj3gg_ has quit (Quit: ZZZzzz…).
21:54:22 -!- skj3gg_ has joined.
21:56:58 <fizzie> It's against the "Terms & Conditions"; I don't know if they've tried (or managed) to actually prevent it. (I remember reading one paper about guessing at the number of hosts behind a NAT based on TCP sequence numbers or source ports or whatnot, but that's probably a bit too fancy for real use.)
21:57:02 -!- skj3gg_ has quit (Client Quit).
21:57:10 <fizzie> (This is not a Three phone.)
22:02:13 -!- skj3gg_ has joined.
22:03:01 -!- AndoDaan has joined.
22:04:32 -!- skj3gg_ has quit (Client Quit).
22:05:36 -!- skj3gg has quit (Quit: welp, see you later.).
22:07:57 <b_jonas> AndoDaan: sadly, IO over Acian Carrier can't be used directly, you'd need some sort of IRC proxy. The latency of IO over avian carriers is too high to use TCP, but luckily I think (I'm not sure) an IRC client connection could be implemented without TCP.
22:08:41 <fizzie> dulla: Sharing a phone's network connection to other devices.
22:09:10 <dulla> So abuse of the sim card and services?
22:09:45 -!- FreeFull has joined.
22:09:52 <ais523> dulla: not necessarily abuse, some providers allow it
22:10:20 <Vorpal> fizzie, hm? I didn't know they could limit you from tethering
22:10:32 <Vorpal> Thought that was a US ting only
22:10:47 <AndoDaan> Does irc make unique, idk, queries to people that are connected. Or could you fake a realtime connection?
22:10:47 <b_jonas> yes, some providers actually encourage it, as in, they're advertizing they allow sharing with multiple mobile devices in a more expansive package, to get more customers
22:11:10 <Vorpal> tethering is allowed by default in Sweden
22:11:22 <Vorpal> At least that was how it worked a couple of years ago
22:11:23 <dulla> So more or less they are allowing Multi-Sim phones
22:11:35 <dulla> Non-phone sim usage
22:11:59 <b_jonas> AndoDaan: you could get away with a connection with a very high lag, you'd just need some slight changes.
22:12:46 <Vorpal> Hm this is a stupidly short USB cable to use for this
22:12:58 <fizzie> Vorpal: Three allows it for pay-monthly plans but not for pay-as-you-go.
22:13:01 <Vorpal> Was the only one I had on hand though
22:13:08 <b_jonas> AndoDaan: basically, due to how IRC is planned to resolve conflicts after a netsplit (conflicts like nick collisions or different channel modes on different sides), it's something that could be modified to work between Earth and Mars
22:13:20 -!- ais523 has quit (Quit: buying food).
22:13:54 <b_jonas> which does require flow control so you can't just flood the server on the other side by requesting lots of pages with a huge response (say large videos)
22:14:01 <dulla> All I know is that Nick Collisions end in n-lateral kicking
22:14:06 <b_jonas> it works even better if the servers are local to the clients
22:14:28 <b_jonas> so the server can kick your connection rightaway if you're flooding,
22:14:34 <dulla> how does it resolve chan modes, b_jonas
22:14:45 <b_jonas> it's just that commands that go from the earth server to mars server or back will have lots of delays
22:14:54 <b_jonas> I'm not saying the softwares would work as is, but they could be modified
22:14:55 -!- Tritonio has joined.
22:15:11 <b_jonas> dulla: I'm not really sure, you'd have to ask on #freenode, but I think they compare timestamps and the earlier wins, or something like that
22:15:12 <dulla> high latency ain't bad
22:16:05 <b_jonas> dulla: it sure ain't bad, it's just that our current infrastructure (if you count the web or facebook, all encrypted and uncachable by proxies) doesn't work at all with high latencies
22:16:43 <dulla> Hmmm, at the very least, continuations could be helpful in high latency
22:16:46 <b_jonas> so basically you can't recruit laypeople for a Mars settlement mission because they won't be able to access websites unless the company who runs the particular website runs a server on Mars and manages the synchronization themselves
22:16:51 <dulla> But I know jack crap
22:17:51 <b_jonas> but maybe Facebook would put a server there and manage it somehow
22:17:55 <dulla> as far as synchronisation goes, let's get referential transparency as the norm for relational networks, yo
22:18:12 <b_jonas> and Youtube and whatever else
22:18:41 <dulla> For Youtube, segemented downloads
22:19:07 <b_jonas> (there might be also problems with bandwidth throughput too in the first few decades, but at least that doesn't come from a fundamental physical limitation that can't be overcome with slightly better infrastructure)
22:19:33 <b_jonas> dulla: no, for Youtube I think you really need a caching server on Mars
22:19:42 <b_jonas> which google could probably put there
22:19:48 <AndoDaan> Nah, FB and the like will be replaced by a company that treats the high latency as a feature, not a obsticle.
22:19:50 <dulla> Hum, I see what you mean
22:20:07 <fizzie> Oh, here's their definition of "unlimited": "All you can eat data gives you worry free internet use. Even if you used your phone for every minute of every day you could only use, subject to TrafficSense™, around 1000GB each month. We may use this cap to identify inappropriate use of the service, such as commercial use, which isn't permitted under our terms and conditions."
22:20:17 -!- skj3gg has joined.
22:20:19 <dulla> Curious about the diferences between low-medium-high latency programs
22:20:53 <AndoDaan> Wow. That's a high cap and it's cool that they defined their unlimited limit.
22:21:41 <b_jonas> fizzie: so it's like the other unlimited services: it's unlimited but they terminate your subscription after the first month you use it too much
22:21:44 <dulla> A caching server to cache the requested videos
22:21:57 <dulla> at least you know the terms of service, b_jonas
22:22:08 <dulla> still, high latency
22:22:11 <b_jonas> dulla: yes, or simply all videos as soon as they're uploaded, even before they're requested
22:22:37 -!- skj3gg has quit (Client Quit).
22:23:05 <dulla> That high latency, though
22:23:16 <b_jonas> and obviously it has to work backwards too, so all uploads from Mars are cached on Earth too
22:23:21 <dulla> I know medium latency is about 12 seconds, high is around at least a minute
22:23:37 <dulla> could use bitswap for caching
22:23:38 <b_jonas> dulla: but Mars is farther than that, right?
22:24:36 <AndoDaan> The Martian is an excellent book for such info btw. Just read it.
22:24:50 <dulla> well shit I have to come back later,
22:25:06 <dulla> mars stuff with b_jonas and AndoDaan, right?
22:26:36 <b_jonas> mailing lists (or usenet) should probably work too, as long as the mail servers filter spam locally
22:26:50 <b_jonas> it's just all the fancy modern stuff that wouldn't work
22:26:51 -!- Phantom_Hoover has joined.
22:27:01 <dulla> no resilience in modern things
22:27:05 <Vorpal> <AndoDaan> Wow. That's a high cap and it's cool that they defined their unlimited limit. <-- 1 TB / month isn't that big
22:27:05 <Vorpal> Unless you have an additional connection
22:27:06 <Vorpal> I hit 150 GB / month on my tablet alone (wifi only)
22:27:07 <Vorpal> Mostly on 1080p youtube
22:27:08 <Vorpal> Oh wait, in november I hit 172 GB
22:27:09 <Vorpal> According to the stats in Android
22:27:11 <Vorpal> And so far this month I hit 130 GB
22:27:12 <Vorpal> 118 GB of that on the youtube app
22:27:15 <Vorpal> AndoDaan, In a household where more than one person watches a lot of youtube you could easily hit a lot more than 1 TB / month
22:27:21 <b_jonas> I mean, I don't want to go to Mars, but if enough people go, the effect might be good here on Earth too
22:27:24 <Vorpal> What the fuck was that..
22:27:44 <dulla> start with the moon
22:27:47 <dulla> seriously, the fuck
22:27:56 <dulla> Shit's an 80's problem
22:28:14 <dulla> Don't need no McDonalds on mars
22:28:18 <b_jonas> dulla: Moon is easy, there's not much latency between the Earth and the Moon, current technology would just work
22:28:37 <b_jonas> satellite internet users can already handle that much latency
22:28:44 <Vorpal> b_jonas, well, you couldn't play CS GO from the moon
22:29:11 <dulla> No I mean sustainablity, b_jonas
22:29:33 <dulla> also, didn't old stuff run on medium latency
22:29:56 <Vorpal> dulla, what do you mean with "stuff" and with "medium latency"
22:30:06 <b_jonas> oh, you mean the problem is the other fundamental limitations like thermodynamics?
22:30:14 <dulla> more than a few seconds, less than a minute
22:30:23 <dulla> and stuff as in tech
22:31:29 <dulla> s far as anything goes
22:31:38 <dulla> just needs erasure codes out the ass
22:32:01 <dulla> generalised torrent
22:32:12 <dulla> none of this perfile crap
22:32:19 <Vorpal> Oh I thought you were talking about endianess
22:32:31 <Vorpal> Never heard of bitswap in the torrent sense
22:33:04 <dulla> more or less because it'd be stupid to tie block dictionaries, blocks, etc per file header
22:33:16 <Vorpal> I get hits about ADSL?
22:33:28 <dulla> I'm being dragged out the door
22:33:42 <dulla> ipfs.io is the site, it has the whitepaper, if you are interested, Vorpal
22:33:43 <Vorpal> If the pattern of noise versus frequencies heard in the bins changes, the DSL modem can alter the bits-per-bin allocations, in a process called "bitswap", where bins that have become more noisy are only required to carry fewer bits and other channels will be chosen to be given a higher burden.
22:34:05 <Vorpal> dulla, so yet another one
22:34:25 <Vorpal> What was the one I saw a while ago... Freenet? What happend to that
22:34:49 -!- skj3gg has joined.
22:36:34 -!- skj3gg has quit (Client Quit).
22:38:17 -!- oerjan has joined.
22:50:22 -!- skj3gg has joined.
22:50:28 -!- skj3gg has quit (Client Quit).
22:51:53 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
22:53:01 -!- ProofTechnique has joined.
22:57:00 -!- ais523 has joined.
22:58:52 <oerjan> fizzie: you now should have all the necessary information to calculate the answer to the topic question hth
22:59:24 <oerjan> i expect you already know whether fungot is african or european.
23:00:57 -!- FreeFull has quit (Ping timeout: 252 seconds).
23:03:50 -!- FreeFull has joined.
23:09:30 -!- nycs has quit (Quit: This computer has gone to sleep).
23:30:27 -!- mihow has quit (Quit: mihow).
23:34:16 <HackEgo> [wiki] [[Pig]] http://esolangs.org/w/index.php?diff=41928&oldid=41925 * 122.37.11.94 * (+106)
23:47:21 -!- zzo38 has quit (Remote host closed the connection).
23:49:08 <dulla> yet another what Vorpal
23:49:54 <dulla> It more or less compacts the issue of trackers into the unit client
23:54:07 <AndoDaan> Tourette's SyndromePIGMight be an interesting theme for an esoteric language.
23:56:27 <ais523> hmm, I am finding this page surprisingly amusing: http://www.minesweeper.info/wiki/Famous_Cheaters
00:07:42 <AndoDaan> Kinda want toplay minesweeper now.
00:13:27 <ais523> the most infamous is the Dreamboard
00:13:52 <ais523> Windows 3.1 Minesweeper has only a limited number of possible boards
00:14:00 <ais523> that one is the easiest, and many players memorized it
00:14:14 <ais523> and there's huge debate about whether Dreamboard records count
00:14:30 <ais523> the problem being a) did they just reset until they got the Dreamboard; b) did they recognise it after a couple of moves
00:18:23 <AndoDaan> Hmm. Seems like arguing that trying to go forthe record invalidates the attempt.
00:18:25 <ais523> and which of those count
00:18:50 <ais523> here it is, btw: http://www.minesweeper.info/wiki/images/b/b3/Dreamboard-10-MattMcGinley-270601.jpg
00:20:05 <AndoDaan> The dreams of it is not immediately obvious to me.
00:21:00 <ais523> basically it's that all the mines are concentrated together, and you have islands of wide open areas, and islands of miens
00:21:09 <ais523> meaning that solving the level requires fewer clicks than normal
00:21:21 <ais523> which is obviously desirable for a world record, especially if you have the layout memorized
00:22:32 <AndoDaan> Ah. They're looking to just clear the negative space as quickly as possible, ratherthan pinpointing bombms.
00:22:42 <ais523> because that's the win condition
00:23:23 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
00:23:29 <AndoDaan> I see it now. Near three vast expances.
00:24:02 <AndoDaan> nope, Idk how to expand on my spelling of 'expand'.
00:25:04 <ais523> "expanses" is the correct spelling, I think
00:25:14 <ais523> at least, my spellchecker likes it
00:30:48 <AndoDaan> Thanks. The spellcheck underline things is near invisible in HexChat.
00:30:52 <ais523> Minesweeper is np-complete, right? or was it pspace-complete?
00:32:01 <AndoDaan> I was just thinking if I was misremembering if it was turing complete or np complete.
00:32:10 <ais523> it can't be TC, it's only finitely large
00:32:24 <ais523> ah right, it can't be above NP because all moves are irreversible
00:32:49 <AndoDaan> Instantly evident to those who are not me. :)
00:32:49 <ais523> meaning that the number of moves is polynomial-time
00:33:56 <ais523> if you have a potential solution to a Minesweeper board
00:34:13 <ais523> you can check whether it's genuine simply by counting the number of mines around each number
00:34:29 <ais523> that means that minesweeper is at most NP
00:34:48 <ais523> proving that it's actually NP-complete is harder, ofc
00:35:29 <ais523> dulla: "NP-complete" is a little awkward to define, but intuitively, it means that given any puzzle for which a solution can be checked for correctness in polynomial time, there's some Minesweeper board that's equivalent to that puzzle
00:35:33 <AndoDaan> I think it was proof by equating it to an already established np complete problem.
00:35:54 <ais523> NP-completeness and PSPACE-completeness are two common ways to translate the notion of Turing-completeness down to finite programs
00:36:02 <AndoDaan> That's even more vaguely remembered. I'm gonna look it up.
00:39:44 <AndoDaan> Reduced from 3SAT, apparently.
00:40:22 -!- boily has joined.
00:40:24 -!- shikhin_ has joined.
00:42:58 <ais523> people always use 3SAT, or nearly so
00:43:24 -!- shikhin has quit (Ping timeout: 250 seconds).
00:43:27 <ais523> although when I proved the generalized RNG-reversing problem NP-complete, I used the subset sum problem
00:44:32 <oerjan> they should use planar 3-coloring more
00:44:41 -!- adu has quit (Quit: adu).
00:46:04 <ais523> it doesn't translate too well to different genres of problem, I guess
00:46:26 <ais523> same reason that we show languages TC by implementing BCT or Brainfuck or Fractran, rather than INTERCAL
00:47:48 <AndoDaan> I'm working on lengthening the esointerpreter chain a bit, and that fact is really annoying.
00:48:13 <ais523> maybe I should work more on underlambda
00:48:27 <ais523> which might make esointerpreters obsolete, at least for the TC languages
00:48:42 <AndoDaan> Nearly got a kipple to MNNBFSL interpreter, but behind kipple it's OOP ork.
00:56:43 <ais523> is it just me, or is Pig a really awful language?
00:58:42 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41929&oldid=41916 * 203.99.128.1 * (+43) /* Instructions */
00:59:48 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41930&oldid=41929 * 203.99.128.1 * (+16) /* Instructions */
01:01:46 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41931&oldid=41930 * 203.99.128.1 * (+122) /* Instructions */
01:02:12 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41932&oldid=41931 * Ais523 * (-5) /* Instructions */ fix typo
01:04:33 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=41933&oldid=41932 * 203.99.128.1 * (+71) /* Instructions */
01:08:56 -!- Lymia has quit (Remote host closed the connection).
01:09:23 -!- Lymia has joined.
01:19:48 -!- PinealGlandOptic has quit (Ping timeout: 250 seconds).
01:20:34 -!- AndoDaan has quit (Quit: Going, going, gone.).
01:26:07 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:50:20 -!- ProofTechnique has joined.
02:08:58 -!- adu has joined.
02:25:07 -!- dianne has quit (Ping timeout: 265 seconds).
02:26:51 -!- dianne has joined.
02:33:46 -!- boily has quit (Quit: ACROBATIC CHICKEN).
02:46:47 -!- Tritonio_ has joined.
02:48:33 <ais523> b_jonas: now I'm curious as to what your solution to "utf8 to unicode" on anagolf was
02:48:43 <ais523> it ran faster than mine, so maybe it's not loading libraries?
02:49:10 -!- Tritonio has quit (Ping timeout: 252 seconds).
02:49:45 -!- Tritonio_ has changed nick to Tritonio.
02:50:41 <ais523> the annoying thing there is that it would be trivial to write if only we could set command-line options, but we can't (the #!perl trick doesn't work for Unicodiness)
02:55:34 -!- Zefphex has joined.
03:16:07 <tswett> Ooh, I should create an "esoteric programming language" that's just an NP-complete problem.
03:16:40 <Zefphex> I should delete the internet
03:19:06 <ais523> that might be difficult, and a huge amount of valuable information would be lost
03:19:09 <ais523> I'd recommend against it
03:21:03 <Zefphex> DDOS the internets biggest servers
03:21:15 <Zefphex> And saturate them so they can't defend?
03:21:27 <ais523> DDOSing works less well on large servers than small servers
03:21:36 <ais523> for reasons that should be obvious if you think about it
03:21:52 <pikhq> And the owners of some of them tend to have huge budgets.
03:22:18 <ais523> have you any idea how little bandwidth there is on the Moon?
03:22:31 <pikhq> For instance, I imagine if your DDOS was enough of a threat Google could actually afford a gun DOS on your DDOS operation.
03:23:01 <ais523> (there is a communications satellite network around Mars, though; I don't know how much bandwidth it has for connecting with Earth)
03:23:04 <pikhq> That's where they shoot you.
03:23:43 <ais523> I don't think Google would need assassinations to stop a DDOS
03:23:48 <Zefphex> now to haunt Google servers with large ammounts of lag
03:23:48 <ais523> but the right way to think about it is
03:24:04 <pikhq> No, but if that's what it would take *they probably could*.
03:24:08 <ais523> Google gets a huge number of Internet connections /anyway/
03:24:19 <Jafet> Google would just reroute the internet around your attack
03:24:24 <pikhq> But yes, Google is practically running under a massive DDOS anyways.
03:24:38 <ais523> it's getting hammered by a large proportion of human Internet users at any given time
03:24:38 <Zefphex> Can't I just burn the buildings holding Google servers down
03:24:40 <pikhq> What most sites call "a DDOS" Google calls "Tuesday".
03:24:48 <Jafet> They do own a killer robot company now, so they could plausibly assassinate you if they wanted to
03:25:13 <Zefphex> How would you go about ddosing the internet
03:26:04 <pikhq> I don't think there's enough electrons for that.
03:26:56 <ais523> technically you could use the same electrons for each packet
03:27:00 <Sgeo> The root zone servers don't actually see much traffic due to caching, right?
03:27:04 <ais523> and just shove them through the wires really fast
03:27:17 <ais523> Sgeo: yep, pretty much everyone knows where, say, the .com servers are anyway
03:27:22 <ais523> so they don't have to ask
03:27:38 <ais523> they're probably seeing a bit more traffic now with all the weird suffixes ICANN opened up in their recent cash grab
03:27:39 <Sgeo> But on the other hand, DDOSing them might not be helpful for the same exact reason
03:27:41 <ais523> but probably not that much
03:27:51 <Sgeo> DDOS .com nses?
03:27:53 <pikhq> And the root zone servers are actually done pretty bizarrely as well...
03:28:09 <pikhq> Several hosts that share IP addresses, relying on how DNS is stateless.
03:28:51 <tswett> There's gotta be a theoretical maximum to how much information you can send through a wire.
03:29:12 <pikhq> There's nominally only, like, 6 root zone servers, but there's a few dozen servers that actually host the root zone.
03:30:02 <ais523> they're named after letters of the alphabet, so it has to be 26 or less
03:30:09 <ais523> but I'm pretty sure there's more than 6
03:30:12 <Zefphex> China is apparently ddosing Canada atm
03:30:23 <ais523> no, the Internet doesn't work like that
03:30:41 <ais523> what you mean is that some people in China are attempting to DDOS various targets within Canada, presumably with varying levels of success
03:30:46 <Sgeo> It may be possible for a country to totally disconnect another country
03:30:50 <pikhq> And all but 3 of them are nominally located in the US.
03:30:53 -!- skj3gg has joined.
03:30:54 <coppro> Google could possibly DDOS an entire country
03:30:58 <Sgeo> I think China could pull the plug on NK?
03:31:02 <Sgeo> But that's not DDOS
03:31:32 <Zefphex> Internet warfare would be scary
03:31:53 <Sgeo> Zefphex: some country accidentally blocked YouTube for much of the Internet
03:31:57 <ais523> Sgeo: I assume there are internet connections directly between north korea and south korea
03:31:57 <Sgeo> Again not a DDOS
03:32:02 <ais523> Sgeo: that was a DNS blackholing
03:32:22 <ais523> you claim to offer a shorter path to the site people are looking for, then discard the traffic
03:32:22 <Sgeo> Conclusion: The best way to attack the Internet is probably not DDOS
03:32:43 <ais523> that only works because of other ASes trusting your routes, though
03:32:45 <pikhq> ais523: Probably, but it's also probably a pretty lightweight link.
03:32:54 <ais523> if you do that sort of thing too often, they stop trusting them
03:32:59 <Sgeo> Nuke the underwater cables!
03:33:14 <ais523> also, I'd like to point out that the entire original purpose of the Internet was to survive nuclear attack
03:33:35 <Sgeo> Does splitting in two temporarily count as surviving?
03:34:10 <ais523> but even then it's connected enough that splitting it in two is unlikely
03:34:49 <Zefphex> If a big country internet usage wise say Europe would take on US servers who would win?
03:35:17 <Zefphex> Also who wants to buy a copy of cs6
03:35:42 <ais523> it's not like a country magically owns all the internet connections inside it
03:35:56 <ais523> also europe isn't a country
03:36:01 <pikhq> Hard to say. It's not entirely meaningful to even speak of "a country's servers" really... Things are sufficiently international these days that damage to most any country, hurts most all countries.
03:36:43 <pikhq> For instance, if China goes down the US is *hosed*.
03:37:12 <Zefphex> Its a big fuck up for nature to have made humans
03:37:40 <Sgeo> http://www.vhemt.org/ ?
03:37:41 <Zefphex> All humans have a large potential to be evil and destroy
03:38:07 <Sgeo> (Note: My linking does not imply that I endorse the views expressed therein)
03:38:17 <Zefphex> Some painless way of vaporising every human on earth
03:39:55 <pikhq> Like... antimater?
03:41:50 <Zefphex> lets all mate with our anti-selves
03:45:00 <ais523> this is getting increasingly offtopic
03:45:03 <ais523> also really depressing
03:45:19 <ais523> it'd be completely out of line for me to kick you, as you haven't really done anything wrong
03:45:24 <ais523> but I'm tired and irritable right now
03:47:34 -!- skj3gg has quit (Quit: ZZZzzz…).
03:49:15 -!- arjanb has quit (Quit: .).
03:50:31 -!- skj3gg has joined.
03:52:38 -!- Tritonio has quit (Remote host closed the connection).
03:52:50 -!- skj3gg has quit (Client Quit).
03:57:40 -!- zemhill__ has joined.
03:58:54 -!- skj3gg has joined.
04:00:26 <HackEgo> [wiki] [[SickPig]] N http://esolangs.org/w/index.php?oldid=41934 * 122.37.11.94 * (+490) Created page with "SickPig is similar to the language [[Pig]], but it simulates a pig that is sick. ==Usage== SickPig follows the same syntax rules as [[Pig]]. You write the name of the text fil..."
04:00:36 -!- zemhill_ has quit (Ping timeout: 276 seconds).
04:01:12 <HackEgo> [wiki] [[SickPig]] http://esolangs.org/w/index.php?diff=41935&oldid=41934 * 122.37.11.94 * (+7)
04:01:23 -!- skj3gg has quit (Client Quit).
04:02:21 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=41936&oldid=41927 * 122.37.11.94 * (-10)
04:03:38 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41937&oldid=41924 * 122.37.11.94 * (+59)
04:05:55 -!- zemhill___ has joined.
04:10:21 -!- zemhill__ has quit (Ping timeout: 276 seconds).
04:11:20 <Jafet> "For example, imagine that a north-south–oriented ice skater, in orbit over the equator of a black hole and rotationally at rest with respect to the stars, extends her arms."
04:12:44 -!- skj3gg has joined.
04:13:11 <ais523> this is north and south with respect to the poles of the black hole?
04:13:16 <ais523> how does she figure out where they are?
04:13:59 <oren> Zefphex: "ddos's from the moon" is almost literally the plot of a book i'm trying to write
04:15:18 <oerjan> i hear the moon is a harsh mistress has already been written hth
04:16:53 <oren> ais523: maybe it's a kerr newman black hole and she has a magnemometer?
04:19:42 -!- skj3gg has quit (Quit: ZZZzzz…).
04:19:44 <oren> oerjan: i thought they just threw rocks in that book
04:20:08 <oerjan> yes, and how could _your_ version not be lame in comparison, i'm saying
04:20:34 <pikhq> Huh, black holes can possess angular momentum.
04:22:00 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41938&oldid=41937 * 122.37.11.94 * (+0)
04:22:15 <oren> is there a real word for a magnemometer?
04:23:19 <oren> something that measures strength and direction of th magnetic field
04:24:01 <oerjan> in that case merely replace the second m by a t hth
04:24:03 -!- skj3gg has joined.
04:24:48 <oerjan> greek: fiendish, logical, or both?
04:25:13 <oren> lately i;ve been having a problem with my laptop screen where it starts going white, until I hit it.
04:25:58 <oerjan> you need to respect that your laptop has a different color identity.
04:26:37 -!- skj3gg has quit (Client Quit).
04:28:21 <oren> I think there's a connector loose inside, otherwise how would hitting it help?
04:30:32 <HackEgo> [wiki] [[DeadPig]] N http://esolangs.org/w/index.php?oldid=41939 * 122.37.11.94 * (+394) Created page with "DeadPig is a version of the language [[Pig]], where the pig has obviously died. ==Usage== DeadPig uses the same syntax rules as [[Pig]], where you write the title of the text ..."
04:30:54 -!- skj3gg has joined.
04:31:53 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=41940&oldid=41938 * 122.37.11.94 * (+58)
04:35:31 -!- Zefphex has quit (Ping timeout: 255 seconds).
04:36:14 <oren> Zefphex: Not that I know of. It's not worth fixing, given that the machine cost CA$200. I'll just buy a new one if this happens too often.
04:39:25 -!- skj3gg has quit (Quit: ZZZzzz…).
04:39:59 -!- skj3gg has joined.
04:40:19 <oerjan> at this rate we're going to need Category:حَرَام
04:44:35 -!- skj3gg has quit (Client Quit).
04:45:59 -!- skj3gg has joined.
04:48:19 <Sgeo> 11 hours of thirst coming up :(
04:49:05 <Sgeo> And a medical procedure
04:49:39 -!- skj3gg has quit (Client Quit).
04:52:31 <Sgeo> Can I just sleep through thirst?
04:52:53 <oerjan> depends how tired you are
04:53:09 <Sgeo> Not tired at all, I slept through do-not-need-to-deprive-myself-of-food-and-water time
04:53:46 <oerjan> did you wake up just when it was too late to eat and drink tdnh
04:53:54 <ais523> I manage 11 hours without water frequently, even when awake
04:54:11 <ais523> the only place to get bottles of water at 4:54 AM charges £1.40 for them, which is really excessive
04:54:15 <Sgeo> No, and drinking water right now during the 6 minutes I have left
04:54:47 <oerjan> if i don't drink before going to bed i tend to have chaffed lips when i awake
04:54:58 <Sgeo> I'm scared of sedation
04:55:50 <oerjan> ais523: birmingham doesn't have drinkable tap water?
04:55:57 <Sgeo> And of having a tube stuck down my throat
04:56:01 -!- MDude has changed nick to MDream.
04:56:17 <ais523> oerjan: it has excellent tap water, but the problem is finding a mains-connected tap and a container to drink from
04:56:36 <oerjan> dammit spilled coke on my sweater
04:56:52 * Sgeo tends to buy bottles of water just for the container
04:57:01 <Sgeo> At work I buy one a week, not sure if that''s particularly unsanitary
04:57:06 <oerjan> also t-shirt but that was going into the laundry soon anyway
04:57:07 <MDream> Is it an invasive prodecure?
04:57:18 <Sgeo> Then again, I may not be the best person to ask for advice on sane behavior
04:57:26 <Sgeo> MDream: are endoscopys considered invasive?
04:57:34 <Sgeo> It's a tube down my throat but I'm not being cut open
04:58:31 <MDream> I got an MRI once, though, and it turns out I didn't actually need to be sedated since I was good at laying still on my own anyway.
04:58:50 <oerjan> ais523: so birmingham has a tap shortage?
04:58:55 <MDream> I of course found this out after going several hours without eating.
04:59:08 <Sgeo> Wait, not eating is for sedation?
04:59:17 <ais523> oerjan: well taps tend to be confined to residential houses and food preparation areas
04:59:19 <Sgeo> I thought it was to not vomit while there's a tube in my throat
04:59:22 <oerjan> i simply cannot imagine anywhere in norway where it's further to a tap than to a shop
04:59:25 <MDream> But I would imagine they don't want to risk you gagging on the endoscoping camera.
04:59:33 <ais523> and toilets, which are plentiful, but which I don't really want to drink from
05:00:32 <MDream> Possibly that too, but also so the sedatives don't make you release an absolutely gigantic bowel movement as easily.
05:01:49 <oerjan> ok i guess _inside_ a shopping center.
05:01:52 -!- Sgeo|web has joined.
05:02:14 -!- Sgeo|web has quit (Client Quit).
05:02:22 <Sgeo> Quassel seriously hits a nerve sometimes
05:02:27 * oerjan guesses he has no idea where ais523 spends his days
05:02:53 <MDream> I would like to carry cleaning equipment with me to areas with water fountains.
05:03:26 <ais523> oerjan: oh, the shops aren't open at 5am
05:03:40 <ais523> the massively overpriced water comes from a small vending machine about 10m from here
05:03:43 <MDream> Because there is one gym I'd visit every few years for some reason or another.
05:04:08 <ais523> when the shops are open, I can by a 2 litre bottle of sparkling or still water for 50p, which is much better value
05:04:11 <MDream> And there was a water fountain that has a single distinctive booger hanging on it for most of those several years.
05:04:18 <ais523> (again, the price is mostly for the container, I think)
05:04:18 <MDream> No once thouching it, no one cleaning.
05:04:36 <ais523> actually, it's a pity that the ASDA isn't near here: they literally sell bottles of tap water for like 15p
05:06:15 <oerjan> also i distinctly recalling having a cup when i was at university.
05:06:53 <oerjan> the one with the nice math on it broke when i was washing it ):
05:06:54 <ais523> part of my problem is I have nowhere to store things, really
05:08:14 <Sgeo> I would buy bottles of tap water
05:08:17 <Sgeo> Or empty plastic bottles
05:08:28 -!- Frooxius has quit (Quit: *bubbles away*).
05:09:14 <ais523> the thing is, I can't exactly carry empty bottles around with me all day
05:09:40 <ais523> my current solution is to buy a lot of water during daytime, and drink it
05:09:43 <ais523> then not drink water overnight
05:11:32 <ais523> I do much the same with food, actually
05:11:36 <ais523> because I'm not sure how long it'll keep
05:19:23 <Sgeo> "Polaris and Omnipotence both require level 5 to be trained in order to even start training level 1. Even if a drunken Dev/GM threw an Omnipotence book at you, you'd never be able to start training it. Same with Polaris."
05:27:09 -!- Oolicile has joined.
05:29:37 -!- Frooxius has joined.
05:33:27 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
05:37:42 -!- skj3gg has joined.
05:46:01 -!- skj3gg has quit (Quit: ZZZzzz…).
05:49:35 -!- skj3gg has joined.
05:54:00 <HackEgo> [wiki] [[Talk:DeadPig]] N http://esolangs.org/w/index.php?oldid=41941 * AndoDaan * (+487) PIGFARMER idea.
05:57:43 <HackEgo> [wiki] [[Talk:DeadPig]] M http://esolangs.org/w/index.php?diff=41942&oldid=41941 * AndoDaan * (+16) Noticed SICKPIG....
06:05:25 -!- ProofTechnique has joined.
06:06:47 -!- skj3gg has quit (Quit: ZZZzzz…).
06:08:34 <HackEgo> Oolicile: 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.)
06:16:17 -!- skj3gg has joined.
06:17:47 -!- skj3gg has quit (Client Quit).
06:18:01 <oren> doesn't even look like a rainbow
06:18:49 <oren> rainbows are Red, orange, yellow, green, blue, indigo, violet
06:19:28 -!- oren has quit (Quit: Lost terminal).
06:26:09 <ais523> Oolicile: IRC color codes don't send exact colors
06:26:12 <ais523> they just send suggestions
06:26:19 <ais523> so your client is presumably using dark interpretations of the color codes in it
06:27:51 -!- skj3gg has joined.
06:40:43 -!- shikhin has joined.
06:41:03 -!- adu has quit (Remote host closed the connection).
06:41:43 -!- adu has joined.
06:43:41 -!- shikhin_ has quit (Ping timeout: 252 seconds).
06:43:46 <b_jonas> ais523: ah! now I've reproduced the 27 character solution at http://golf.shinh.org/p.rb?utf8+to+unicode
06:44:01 <b_jonas> ais523: the 30 character solution simply hard-codes the three output numbers in decimal
06:44:12 <ais523> the 27-char solution is not cheating
06:44:45 <ais523> it even checks that the input is valid UTF-8
06:45:06 <ais523> because the function that doesn't check for that and simply sets the "this is UTF-8" flag has a name that's very slightly longe
06:47:49 <b_jonas> the short ruby solution is also non-cheating
06:49:06 -!- skj3gg has quit (Quit: ZZZzzz…).
07:01:57 -!- Oolicile has quit (Remote host closed the connection).
07:30:52 -!- Patashu has joined.
07:38:53 -!- oren has joined.
07:44:09 <Sgeo> nortti: you're an Evillious Chronicles person, right?
07:44:22 <Sgeo> Why is the new song Clockwork Lullaby 7 if there's no lu li la la la?
07:45:17 <Sgeo> Oh, it's there
07:46:36 <b_jonas> four hands and an axe, that elephant guy probably has double strike => http://www.pbfcomics.com/271/
08:07:26 <elliott> dulla: this is your second warning (re: "gay")
08:08:47 <oren> b_jonas: I think that is Ganesh
08:09:36 <elliott> dulla: I get the impression you don't much care
08:09:52 <dulla> I'm a race to the bottom and it's my first week here
08:11:15 <HackEgo> [wiki] [[Talk:DeadPig]] http://esolangs.org/w/index.php?diff=41943&oldid=41942 * AndoDaan * (-16) Undo revision 41942 by [[Special:Contributions/AndoDaan|AndoDaan]] ([[User talk:AndoDaan|talk]])
08:12:02 <oren> I think future historians might be baffled as to how in the span of one century, "gay" changed meanings three times
08:12:11 <elliott> I mean slurs on day 1 already gave me pretty low patience. please don't make the channel shittier
08:14:23 <oren> Ok, maybe not historians. students of history perhaps. In the same way that I am baffled with the causes of the Crimean War
08:14:44 <HackEgo> [wiki] [[Talk:DeadPig]] http://esolangs.org/w/index.php?diff=41944&oldid=41943 * AndoDaan * (-487) Removing unasked for, and hastily given idea.
08:14:47 <elliott> it's right there in the name
08:15:10 <elliott> deadpig should be pig + deadfish imo
08:15:56 <oren> wikipedia: "The immediate cause involved the rights of Christian minorities in the Holy Land, which was controlled by the Ottoman Empire." Me: "So they fought about in Crimea? Lolwut."
08:17:03 <oren> It may have made sense at the time, but it doesn't now.
08:20:22 <ais523> oren: I'm only aware of one outdated meaning ("happy", which is pretty innocuous)
08:21:57 -!- ais523 has quit.
08:24:51 <oren> ais523: the sequence was: bright,happy -> homosexual (slang) -> homosexual (official) -> general pejorative
08:25:58 -!- oerjan has quit (Quit: leaving).
08:26:09 -!- ais523 has joined.
08:27:52 <oren> The associated press now calls for "gay" over "homosexual" when once the reverse was preferred in proper writing
08:31:57 <dulla> is now a slang for the chinese
08:32:21 <dulla> haven't heard of that colloquialism since what?
08:35:58 <oren> dulla: Well, racists use that word all the time. LAst time I recall hearing it was some hobo in a McDonalds yelling at a Korean family who were conversing in Korean.
08:38:17 <dulla> Well, at least I know 98% of people are straight
08:38:23 <dulla> I'm not deluded in that respect
08:39:59 <oren> Toronto has a big problem with homeless and crazy people.
08:39:59 <oren> Lol that's off by a lot, dude
08:42:01 <oren> why that year? It wasn't that bad a year...
08:43:01 <dulla> Anyways, must be all this "Queering Agriculture" and "Queering Geology and Environmentalism"
08:43:08 <dulla> You can thank Maryland for that
08:45:00 <oren> The way people bring politics into science is a problem, but not a new one. In my father's day there was "Lysenkoism" and "communist science"
08:45:46 <dulla> Well, this is the information age
08:46:06 <dulla> There is too much opinion, and not enough fact to dissuade all these new age peddlers
08:47:17 <oren> dulla: That has always been the case. Those who print the textbooks and newspapers have the power to mold the perception of reality.
08:47:44 <dulla> And business weekly came out with unsurprising figures about the most generous donors to media
08:48:06 <dulla> not sure about academia, but the liberalism there is far from classical, neo-, rather
08:48:37 <oren> dulla: but for the first time in history, it is practically free to post your opinion to the entire world.
08:49:18 <dulla> bit late, but at zero marginal cost it's a terrible supply side
08:52:58 <oren> This level of marginal cost means that opinions are in heavy competition, and it is possible for someone to read news exclusively tailored to their views.
08:53:56 -!- ski has joined.
08:55:59 <oren> Because of this, people can exist within their own "reality" where within reason, what they want to be true, is true.
08:56:38 <int-e> those problems will only get worse as long as countries pay more attention to their GDP than to minimum and median incomes as a measure of economic performance and wealth.
08:58:07 <oren> int-e: the problems with people being able to select their own reality, or the problems with poverty?
08:58:53 -!- AndoDaan has joined.
08:59:09 <dulla> It would be great if they realised the tax only screws everyone but the plutocrats
08:59:50 <int-e> The former isn't a problem per se, though it probably has some undesirable real world implications.
09:01:28 <int-e> (Hmm, has anybody ever blamed Google for contributing to catching people in a bubble of radical ideas that are internally consistent?)
09:02:29 <ais523> I know people blame Reddit for that a lot, and DuckDuckGo claims not doing that as one of its marketing points
09:02:56 <int-e> dulla: I think they do; it's intentionally designed that way. Politicians get their share in the form of thinly disguised bribes.
09:03:29 <int-e> ...thinly veiled...
09:03:38 <dulla> Eh, why are public services such good laundering grounds
09:03:52 <int-e> ais523: thanks, interesting.
09:04:23 <dulla> Well, at least we can make cracks about how the Pentagon used USA Today as a credible source on Putin's neurotype
09:04:44 <dulla> Poor show, and even then, it only means you are getting slapped around by an atypical
09:05:11 <oren> I just bubble-hop when reading the news: RT, Fox, Xinhuanet, Asahi Shinbun, BBC.
09:06:24 <dulla> I simply don't use google to find things
09:06:31 -!- adu has quit (Quit: adu).
09:06:41 <oren> I google things with Bing
09:08:42 <oren> baidu is a good portal to a different bubble
09:12:36 <HackEgo> [wiki] [[DeadPig]] http://esolangs.org/w/index.php?diff=41945&oldid=41939 * 122.37.11.94 * (+144)
09:12:56 <oren> Deadpig. Mxlnt!
09:27:44 <oren> http://dilbert.com/strip/2005-08-21
09:28:14 -!- Phantom_Hoover has joined.
09:33:11 -!- adu has joined.
09:59:43 <oren> did youknow you can make popcorn in bacon fat?
10:16:00 -!- AndoDaan has quit (Read error: Connection reset by peer).
10:18:09 -!- bb010g has quit (Quit: Connection closed for inactivity).
10:28:33 -!- AndoDaan has joined.
10:48:54 -!- AndoDaan_ has joined.
10:50:49 -!- AndoDaan has quit (Ping timeout: 252 seconds).
11:08:34 -!- adu has quit (Quit: adu).
11:23:59 -!- boily has joined.
11:30:51 <AndoDaan_> Boily. What's with you and chicken?
11:35:04 -!- AndoDaan_ has changed nick to AndoDaan.
11:38:38 <int-e> HYPERCRITICAL CHICKEN
11:39:24 -!- augur has quit (Quit: Leaving...).
11:40:53 <AndoDaan> That's your answer? It's good?
11:42:53 <boily> see, int-e understands the chicken.
11:43:07 <boily> (also, int-hello!)
11:43:26 <boily> it's very zen to qualify chickens. therefore it's good.
11:44:06 <int-e> it's a transcendential thing
11:44:25 <b_jonas> (1044) DO REINSTATE CHICKENS
11:44:47 <int-e> PLEASE CHICKEN OUT
11:45:57 -!- Patashu has quit (Ping timeout: 264 seconds).
11:49:41 -!- Tritonio has joined.
11:52:13 <mroman> Chickens are just a co-monad in the category of birds.
11:52:55 <Taneb> mroman, I am not sure that that makes sense
11:53:05 <Taneb> What is composition in the category of birds?
11:54:12 <Taneb> That makes more sense
11:54:28 -!- augur has joined.
11:56:37 <boily> mrhelloman. Tanelle.
11:56:56 <boily> mroman: if monads are monoids in the category of endofunctors, what are comonads?
11:57:51 <Taneb> comonoids in the dual category of endofunctors I think
11:58:40 <Taneb> Although I am not convinced that comonoids are a thing that is different from monoids
11:58:58 * AndoDaan wonders if we're still talking about chicken
11:59:31 * boily brains suffered an out of memory error.
12:01:30 -!- PinealGlandOptic has joined.
12:02:38 <boily> int-e: do you know enough CT to assert that comonoids are a thing, and if so how they relate to comonads?
12:03:01 <elliott> comonads are comonoids in the category of endofunctors, like you'd expect
12:03:08 <elliott> however comonoids in Hask or such are boring
12:03:28 <elliott> you get blah :: a -> () and bleh :: a -> (a,a) with laws that make it so that bleh x must be (x,x)
12:03:47 <elliott> (as opposed to mempty :: () -> a and mappend :: (a,a) -> a)
12:05:06 <elliott> sorry, it disappointed me too
12:05:13 <elliott> if it helps there's some kinda relationship to linear logic.
12:05:22 <elliott> like !A is a comonoid, I think.
12:06:18 <boily> what is linear logic?
12:06:40 <elliott> uhhhh, that's a whole 'nother story
12:07:14 -!- ais523 has quit (Ping timeout: 252 seconds).
12:08:44 <boily> I'll be wikipédiaing later. too much blood in my coffeestream now.
12:08:56 <mroman> isn't blah and bleh the same thing?
12:09:37 <mroman> a -> a and a -> (a,a) should be pretty much the same thing
12:10:02 <mroman> it's an isomorphism after all?
12:14:14 -!- boily has quit (Quit: MYRIAD CHICKEN).
12:15:03 <AndoDaan> It's like ten thousand Chickens when all you need is some rice.
12:18:53 <mroman> All you need is a thread pool full of chickens laying eggs.
12:19:10 <mroman> Just make sure they put their eggs into an MVar.
12:19:36 <mroman> Maybe Chicken: Just Hen | Cock
12:26:19 -!- PinealGlandOptic has quit (Quit: leaving).
12:27:16 <mroman> You should learn Haskell ;)
12:27:43 <AndoDaan> I forgot how I was going to make the eggs in one baskett(?) joke.
12:29:10 <AndoDaan> I probably should. I'm getting adept with JS at the moment. A vast improvement over Lua. But I feel like it doesn't contribute much to any deeper understanding of programming.
12:30:08 <AndoDaan> It's all "Developers! Developers! Developers!"
12:31:16 <AndoDaan> I've started that Haskell online book twice now. But lost focus.
12:37:59 <mroman> but that's no excuse to not learn haskell
12:38:57 <AndoDaan> How would learning haskell help me better understand esoteric languages?
12:40:34 -!- shikhin_ has joined.
12:43:45 -!- shikhin has quit (Ping timeout: 250 seconds).
12:44:49 <mroman> Haskell *is* an esoteric language
12:45:38 <mroman> @pl let f x y z = (x && y) && (z || y || x) in f
12:45:38 <lambdabot> ap (ap . (((.) . (&&)) .) . (&&)) ((flip (||) .) . flip (||))
12:45:55 <mroman> "ap (ap . (((.) . (&&)) .) . (&&)) ((flip (||) .) . flip (||))" looks pretty esoteric too me
12:49:21 <mroman> f(g(h(x)) = f .g . h $ x
12:50:04 <lambdabot> ‘>>’ (imported from Control.Monad.Writer),
12:50:13 <mroman> @define let ($>) = flip ($)
12:50:17 <mroman> @define ($>) = flip ($)
12:50:54 <mroman> > 4 $> (*3) $> (+1) $> ([])
12:50:55 <lambdabot> Couldn't match expected type ‘b0 -> c’ with actual type ‘[t0]’
12:51:01 <mroman> > 4 $> (*3) $> (+1) $> (\c -> [c])
12:51:11 <mroman> > 4 $> (*3) $> (+1) $> (\c -> [c,c]) $> map (*2)
12:51:28 <AndoDaan> Yep, definitely looks esoteric to me. Well made point.
12:52:33 <mroman> > 5 $> (Just) $> fmap (+1)
12:52:48 <mroman> > 5 $> (Just) $> fmap (+1) `mappend` (Just 6)
12:52:49 <lambdabot> No instance for (GHC.Show.Show b0)
12:52:49 <lambdabot> arising from a use of ‘M42903801347602899049054.show_M42903801347602899049...
12:52:49 <lambdabot> The type variable ‘b0’ is ambiguous
12:53:08 <mroman> > (5 $> (Just) $> fmap (+1)) `mappend` (Just 6)
12:53:10 <lambdabot> No instance for (GHC.Show.Show b0)
12:53:10 <lambdabot> arising from a use of ‘M31568903824889092139084.show_M31568903824889092139...
12:53:10 <lambdabot> The type variable ‘b0’ is ambiguous
12:53:24 <mroman> > Nothing `mappend` Nothing
12:53:31 <AndoDaan> Monoids are one input variable functions?
12:53:33 <mroman> > (Just 5) `mappend` (Just 6)
12:53:34 <lambdabot> No instance for (GHC.Show.Show a0)
12:53:34 <lambdabot> arising from a use of ‘M44189842421378468049108.show_M44189842421378468049...
12:53:34 <lambdabot> The type variable ‘a0’ is ambiguous
12:53:48 <mroman> > ((Just 5) `mappend` (Just 6)) :: Just Int
12:53:50 <lambdabot> but ‘Data.Maybe.Just GHC.Types.Int’ has kind ‘Data.Maybe.Maybe *’
12:53:58 <mroman> > ((Just 5) `mappend` (Just 6)) :: Maybe Int
12:53:59 <lambdabot> No instance for (Data.Monoid.Monoid GHC.Types.Int)
12:53:59 <lambdabot> arising from a use of ‘Data.Monoid.mappend’
12:54:33 <mroman> > ((Just 5) `mappend` (Just 6)) :: Maybe ()
12:54:34 <lambdabot> No instance for (GHC.Num.Num ()) arising from the literal ‘5’
12:54:41 <mroman> > ((Just ()) `mappend` (Just ())) :: Maybe ()
12:55:02 <mroman> > foldl1 mappend [Just (), Just (), Nothing]
12:55:07 <mroman> > foldl1 mappend [Just (), Just (), Nothing, Just ()]
12:55:46 <AndoDaan> I feel like I've just witnessed a fascinated argument in Esperanto.
12:55:50 <lambdabot> Data.Monoid First :: Maybe a -> First a
12:55:50 <lambdabot> Control.Arrow first :: Arrow a => a b c -> a (b, d) (c, d)
12:55:58 -!- ais523 has joined.
12:56:06 <lambdabot> Prelude all :: (a -> Bool) -> [a] -> Bool
12:56:07 <lambdabot> Data.List all :: (a -> Bool) -> [a] -> Bool
12:56:24 <mroman> foldl1 mappend [All True, All False]
12:56:29 <mroman> > foldl1 mappend [All True, All False]
12:56:40 <mroman> what's foldl1 mappend again?
12:56:56 <mroman> I thought there was a shortcut for that
12:57:12 <mroman> @hoogle foldl1 mappend
12:57:26 <lambdabot> Data.Foldable fold :: (Foldable t, Monoid m) => t m -> m
12:57:26 <lambdabot> Data.IntSet fold :: (Key -> b -> b) -> b -> IntSet -> b
12:57:26 <lambdabot> Data.IntMap fold :: (a -> b -> b) -> b -> IntMap a -> b
12:57:37 <mroman> > foldl [All True, All False]
12:57:38 <lambdabot> Couldn't match expected type ‘b -> a -> b’
12:57:38 <lambdabot> with actual type ‘[Data.Monoid.All]’
12:57:41 <mroman> > fold [All True, All False]
12:59:29 <mroman> AndoDaan: [] is a Foldable and All is a Monoid
13:01:22 <AndoDaan> Folding is like Burlesque's reduction?
13:02:10 -!- blsqbot has joined.
13:04:08 <mroman> if you know haskell you can extend burlesque!
13:06:28 <AndoDaan> I don't think I'd ever be adept enough to mess with anybody their well crafted work.
13:06:43 -!- ais523 has quit (Ping timeout: 250 seconds).
13:08:05 <mroman> as if Burlesque were well crafted
13:08:40 <mroman> http://mroman.ch/lisp/spec.html
13:08:43 <mroman> this is much more well crafted
13:09:01 <AndoDaan> It's the first esolang I learned to program in. It holds a special place in my esteem.
13:09:42 <mroman> (http://codepad.org/kZPDim0y)
13:10:02 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
13:10:05 <mroman> (^- you can use this program to circumvent firewalls)
13:18:27 <mroman> If you'd like to help go ahead :D
13:18:57 <mroman> There's lots of things that need doing that can be done in the language itself
13:19:02 <mroman> so no haskell knowledge is required
13:19:19 <mroman> (for example a lib to read/write PPM images or stuff like that)
13:19:27 -!- AndoDaan_ has joined.
13:21:46 <mroman> or you could write an interpreter in Java/Python for it
13:21:53 -!- AndoDaan has quit (Ping timeout: 250 seconds).
13:23:16 <fizzie> @tell oerjan I do not have information of fungot's migration route. Although I could compute a lower bound.
13:23:30 <AndoDaan_> I think I'm still a ways away from implenting something as complex as Burlesque.
13:24:06 -!- AndoDaan_ has changed nick to AndoDaan.
13:24:11 <mroman> I meant implementing my Lisp Dialect
13:24:22 <mroman> It's always good to have multiple implementations available
13:24:51 <mroman> reimplementing Burlesque is WAAAAAAY TOOOOO MUCH effort
13:25:06 <blsqbot> | "I have 358 non-special builtins!"
13:25:13 <AndoDaan> Hmm, I'll look into that. Do you have a more informal description of P~.
13:25:26 <mroman> but the newest dev version is around 380 :)
13:26:46 <mroman> P~ is more or less just a LISP dialect
13:27:01 <mroman> I can give you lots of example code
13:28:10 <mroman> http://codepad.org/tUx6pq4G
13:30:35 <mroman> that's probably what sets it apart the most.
13:32:03 <int-e> TIL that proving the Knaster-Tarski fixed point theorem becomes really hard if you mix up the definitions of least and post fixed points :P [for some reason, the least element of a complete lattics is not a fixed point of most monotone functions...]
13:32:31 <mroman> It has good multithreading built-in
13:32:42 <mroman> don't know what LISP has to offer there but I'm sure LISP has multithreading too
13:33:06 <mroman> just think of it as yet another LISP dialect
13:33:42 <mroman> I like experimenting with stuff I guess
13:33:52 <AndoDaan> I haven't done anything with Lisp since I've read Godel, Escher, Bach years ago.
13:34:09 -!- MDream has changed nick to MDude.
13:34:14 <AndoDaan> Or mathemagical themas... one of those two.
13:35:03 <AndoDaan> Me too, but I don't seem to have your knack of producing viable offspring out of experimentation.
13:35:04 <mroman> you can always just add Burlesque to it :)
13:36:04 <mroman> digitsum -> (`XX++` $0)
13:43:15 <AndoDaan> Over the past few months, I've workend on maybe half a dosen ideas for my own language, but I never seem to be able to output anything.
13:44:19 <AndoDaan> I'm doing that wrong, I think.
13:46:59 <AndoDaan> Anyways. I know I'm nowhere near as skilled as any of the group here, but I was hoping enthousiasm would help me to add something of myself.
13:54:35 <mroman> How do you think I feel around here?
13:54:58 <int-e> it's nice to see some activity even without fungot here :P
14:00:41 <AndoDaan> Wait. Befunge was the first esoteric language I coded in, Burlesque second. Sorry.
14:04:59 <b_jonas> try some really esoteric languages
14:06:01 <AndoDaan> If haskell is esoteric than burlesque true enough esoteric.
14:09:30 <mroman> but compared to 99% of the people in here I know shit about anything
14:15:12 -!- skj3gg has joined.
14:41:33 -!- skj3gg has quit (Quit: ZZZzzz…).
14:44:05 -!- AnotherTest has joined.
14:47:07 -!- skj3gg has joined.
14:54:02 -!- GeekDude has joined.
15:00:22 -!- AndoDaan has quit (Quit: Going, going, gone.).
15:01:38 -!- SopaXorzTaker has joined.
15:04:36 -!- nycs has joined.
15:19:33 -!- skj3gg has quit (Quit: ZZZzzz…).
15:20:15 -!- nycs has changed nick to `^_^v.
15:21:38 -!- shikhin_ has changed nick to shikhin.
15:36:24 -!- Phantom_Hoover has joined.
15:40:11 -!- skj3gg has joined.
15:45:59 -!- PinealGlandOptic has joined.
15:46:29 -!- PinealGlandOptic has quit (Client Quit).
16:00:44 -!- perrier has quit (Remote host closed the connection).
16:02:22 -!- SopaXorzTaker has quit (Ping timeout: 240 seconds).
16:15:14 -!- HackEgo has quit (Ping timeout: 244 seconds).
16:15:23 -!- SopaXorzTaker has joined.
16:16:33 -!- mihow has joined.
16:16:55 <Taneb> I've had a ridiculous idea on how to implement Eodermdrome
16:17:54 <fizzie> Does it involve living things?
16:17:55 -!- augur has quit (Read error: Connection reset by peer).
16:18:22 <Taneb> fizzie, only incidentally
16:18:22 -!- augur has joined.
16:19:16 -!- perrier has joined.
16:19:38 -!- augur_ has joined.
16:21:55 <Taneb> Phantom_Hoover, transpiling it into a research language one of my lecturers made that has similar semantics
16:22:01 <Taneb> And is already implemented
16:22:44 -!- augur has quit (Ping timeout: 245 seconds).
16:23:15 <Phantom_Hoover> i mean the subgraph search is the main barrier to implementation, right?
16:23:32 <Phantom_Hoover> if the implementation does that then you could just reuse it
16:23:54 -!- augur_ has quit (Ping timeout: 252 seconds).
16:26:10 <Taneb> That is a fair point
16:26:34 <Taneb> However I do not know the license on this code
16:28:30 <Phantom_Hoover> does it not say? and if not you can always ask the lecturer
16:29:05 <int-e> (could it be down?)
16:30:27 -!- vanila has joined.
16:36:15 -!- TieSoul has quit (Read error: Connection reset by peer).
16:39:11 <Taneb> Phantom_Hoover, I could do
16:46:37 -!- skj3gg has quit (Quit: ZZZzzz…).
16:47:22 -!- augur has joined.
17:01:03 <J_Arcane> Hmm. Do I write my next Lisp in JavaScript or F# ... XD
17:01:52 <vanila> a guy in #scheme is writing a nice js one which runs in a abrowser
17:02:49 <coppro> vanila: HTTP/2 has a lot of cool things. Most importantly, it allows all content needed from a server to be served over a single connection
17:03:12 <coppro> so for instance, if you visit a page with lots of images, all the images would be sent as requested, rather that negotiating separate connections for each one
17:03:13 <vanila> that's definitely an improvement
17:04:08 <coppro> and unlike existing pipelining, it doesn't rely on a specific order of content
17:04:18 <coppro> so the server can respond to the requests in whatever order it wants
17:04:29 <vanila> coppro, the web make me sad though
17:04:51 <J_Arcane> Right now though I think I want to write a basic string-format function for Heresy.
17:06:15 <J_Arcane> I kinda wish Heresy had a Haskell style 'show'. It would be a lot easier to write said string-formatter.
17:06:36 <vanila> well why dont you add it
17:06:54 <pikhq> I look forward to the end of sharding.
17:06:59 <vanila> i guess its tricky to copy typeclasses
17:07:07 <vanila> but you can dynamically dispatch to show
17:07:43 <J_Arcane> Yeah, I probably won't go that far. But a simple (show ...) or (str ...) function that turns most arguments into their string representation should be good.
17:09:50 -!- TieSoul has joined.
17:10:02 <J_Arcane> I could just extend str$ to accept lists really; or even just to (print ...) to an open string value, which would be quite easy.
17:12:39 -!- TieSoul has quit (Read error: Connection reset by peer).
17:13:10 -!- TieSoul has joined.
17:14:23 -!- augur has quit (Remote host closed the connection).
17:15:58 -!- augur has joined.
17:17:14 -!- augur_ has joined.
17:17:28 -!- augur_ has quit (Remote host closed the connection).
17:20:57 -!- augur has quit (Ping timeout: 252 seconds).
17:24:22 <vanila> do you have an new ideas
17:27:21 <coppro> all my ideas are recycled
17:27:42 <vanila> im bored help me out :)
17:27:49 <vanila> has anyone veen looking into anything cool
17:27:52 <MDude> New ideas for languages, presumably?
17:29:21 <MDude> I dunno about new, but there's stuff I haven't seen implemented or talked about much.
17:32:03 <J_Arcane> Hmm. what char to use for the templat value signal.
17:34:58 <J_Arcane> Lisp tradition tends to use ~, C tradition is %, and the BASIC standard (seldom implemented) is #.
17:35:24 <J_Arcane> I also thought of using _, just because it seemed like a value less likely to be needed as a regular character.
17:35:33 <MDude> Hmm, I thought I had something bookmarked.
17:35:57 -!- TieSoul has quit (Remote host closed the connection).
17:36:48 <fizzie> And theen usee thee usual trick of doubling thee eescapee characteer to seelf-inseert.
17:37:57 <J_Arcane> Racket supports Unicode. A shame there's not a Unicode value for the Elder Sign.
17:39:16 -!- skj3gg has joined.
17:39:30 -!- TieSoul has joined.
17:39:49 <MDude> Various kinds of non-classical logic can be interesting.
17:40:34 <MDude> I don't really see much being done with those.
17:40:48 -!- koo7 has quit (Ping timeout: 245 seconds).
17:41:51 <MDude> Well, fuzzy logic actually is pretty well known for AI stuff.
17:42:28 <MDude> I don't remember reading about modal logic being used for computation, but a quick search turned up a pdf on it.
17:43:38 <MDude> I'm trying to find the article on Gsome reek logic of discussion system or whatever.
17:46:15 <dulla> as long as it doesn't completely go to pseudoprobablity on that fuzzy logic
17:46:38 <dulla> I like my chances in [0,1]
17:49:38 -!- mihow has quit (Quit: mihow).
17:52:59 -!- augur has joined.
17:54:29 <MDude> Anyway, another idea I'll try to write about some later is on chatbots.
17:55:22 <MDude> Basically taking a regular chat bot, and using it as a node in a network that passes messages to each other.
17:56:09 <MDude> So, to start with you'd have a learning bot that tries to mimmic visitors, but it'd pick up dumb stuff from people messing with it.
17:57:18 <MDude> But if you had a non-learning chatbot trained to just paraphrase anything said to it politely, you could use it to filte anything said to the first bot.
17:57:56 <dulla> That'd put heavy weight on the filter
17:58:05 <MDude> So the pair of bots as a network would appear as one bot that sort of mimmics people, but tries to sound polite.
17:58:50 <dulla> If you find that Gsome reek logic thing
17:59:47 <J_Arcane> Wee! That was as easy as I expected.
18:00:17 <MDude> That's just whatever it is where categories of thigns are descriped as "all x are y", "some x are y", "not all x are y", and "no x are y".
18:00:44 <MDude> And I think is used in the type of argument that involves two postulates and one conclusion?
18:00:59 <J_Arcane> Wrote my first version of a string formatter.
18:05:01 -!- TieSoul_ has joined.
18:08:12 -!- TieSoul has quit (Ping timeout: 245 seconds).
18:08:25 <MDude> I can't remember any of the terms I want to sue here.
18:08:49 <MDude> I should just eat and take a nap.
18:15:42 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
18:26:08 -!- spiette has joined.
18:37:49 -!- TieSoul_ has changed nick to TieSoul.
18:41:05 -!- shikhin_ has joined.
18:43:19 -!- TieSoul_ has joined.
18:44:21 -!- shikhin has quit (Ping timeout: 265 seconds).
18:45:02 <vanila> I talked a bit about reversible computation in #haskell
18:45:04 <vanila> you can read it if you like
18:45:44 -!- NotSoul has joined.
18:46:07 -!- TieSoul has quit (Ping timeout: 245 seconds).
18:46:20 -!- NotSoul has changed nick to TieSoul.
18:46:29 -!- TieSoul_ has quit (Disconnected by services).
18:49:22 -!- shikhin_ has changed nick to shikhin.
18:53:28 -!- SopaXorzTaker has quit (Remote host closed the connection).
19:01:31 <MDude> Reversible computation sounds nice.
19:01:38 <vanila> it's a fascinating subject!
19:01:47 <vanila> but you can see the logs
19:03:01 <MDude> Here we go, he thing I was thinking of.
19:03:13 <MDude> https://en.wikipedia.org/wiki/Categorical_proposition
19:04:55 <vanila> <dulla> you lied to me vanila , you are strawberry
19:04:58 <vanila> <geekosaur> surely that'd be "strawbery"?
19:09:19 <MDude> So anyway, what about a programming language with classes, in which classes are described in terms of categorical propositions?
19:09:48 -!- augur has quit (Remote host closed the connection).
19:10:32 <vanila> I guess logic programming is a basic example of this
19:10:41 -!- augur has joined.
19:10:49 -!- augur has quit (Remote host closed the connection).
19:10:49 <vanila> where you write out assertions of facts
19:11:05 -!- augur has joined.
19:12:00 <vanila> https://github.com/jeffreycwitt/catlogic this was linked from the wiki page
19:12:14 <dulla> why are you peddling LogicT, by the way, vanila
19:12:29 <vanila> i never talked about it
19:13:34 <vanila> i feel like it's a different type of reversible, not sure..
19:15:20 -!- augur has quit (Ping timeout: 246 seconds).
19:18:00 <vanila> oh darn, im having a problem with xz
19:27:20 -!- skj3gg has quit (Quit: ZZZzzz…).
19:31:56 <J_Arcane> This is what I did for fun this evening: https://github.com/jarcane/heresy/blob/master/lib/string.rkt#L78
19:33:32 -!- skj3gg has joined.
19:36:54 -!- mihow has joined.
19:56:52 <MDude> I've been working on http://orteil.dashnet.org/randomgen/?gen=http://mdude1350.webs.com/generators/random-code/IBNIZ-basic-generator.txt
20:00:53 <MDude> It produces random texts which, most of the time, are syntactically valid IBNIZ programs.
20:01:56 -!- perrier has quit (Remote host closed the connection).
20:02:07 <MDude> Mostly I'm trying to reduce the probability of boring programs without making the results too predetermined.
20:02:26 <dulla> So you are making completely random ones?
20:02:42 <dulla> also, I have 1.7e21 heavenly chips
20:02:45 <MDude> That's what I'm trying to do.
20:03:31 <MDude> http://orteil.dashnet.org/randomgen/?gen=http://mdude1350.webs.com/generators/random-code/IBNIZ-simple-generator.txt
20:03:46 <MDude> This is a earlier version of it.
20:04:07 <MDude> The thing is, I want to avoid stuff like adding a number only to immediately pop it.
20:04:41 <MDude> Or putting two constants in and doing an operation that just makes a third constant.
20:04:43 -!- Patashu has joined.
20:05:04 <MDude> Since that just uses up space.
20:05:11 <MDude> So I want them to be random, but terse.
20:05:36 <MDude> The other is that adding commands completely randomly causes stack over and underflows.
20:06:12 <MDude> So at first, I was just trying to string together commands that added up to a net change of zero to the number of items in the stack.
20:06:50 <MDude> But that can still cause underflows early in the program depending on what order things end up in.
20:07:31 -!- skj3gg has quit (Quit: ZZZzzz…).
20:08:42 <MDude> It'd be easier to made random programs in a language that groups with parentheses, I think.
20:08:56 <MDude> Or at least has a BNF definition written up.
20:10:11 -!- skj3gg has joined.
20:12:58 -!- augur has joined.
20:13:22 -!- MDude has quit (Ping timeout: 240 seconds).
20:21:54 -!- MDude has joined.
20:22:43 <MDude> As I was saying before my computer turned off, most languages don't do A/V as simply as IBNIZ does.
20:23:24 <MDude> But I could try making something for http://wurstcaptures.untergrund.net/music/ which is audio-only.
20:29:49 -!- Patashu has quit (Ping timeout: 245 seconds).
20:32:44 -!- vanila has quit (Quit: Leaving).
21:03:35 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:06:09 -!- `^_^v has joined.
21:08:43 <oren> MDude: BY A/V you mean audio and video?
21:12:05 <elliott> architecture/ventriloquism
21:15:49 -!- bb010g has joined.
21:23:41 -!- skj3gg has quit (Quit: ZZZzzz…).
21:25:17 -!- aretecode has joined.
21:25:32 -!- oren has quit (Quit: Lost terminal).
21:33:30 -!- FreeFull has quit (Ping timeout: 244 seconds).
21:34:25 <MDude> Yeah, audeio/video. That's what IBNIZ does with whatever's on the stack after each cycle the programs runs.
21:37:02 -!- FreeFull has joined.
21:39:07 <J_Arcane> MDude: IBNIZ is a pretty great thing.
21:42:34 <MDude> I would think it'd be simple to generate arbitrary programs in this text generator, but it seems to really not like recursion.
21:54:29 -!- koo7 has joined.
22:00:01 -!- AnotherTest has quit (Remote host closed the connection).
22:03:28 <MDude> Or, I forgot to define what operators are.
22:42:11 -!- spiette has quit (Ping timeout: 250 seconds).
23:02:44 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:17:28 -!- _AndoDaan has joined.
23:18:43 -!- _AndoDaan has changed nick to AndoDaan.
23:26:44 -!- oerjan has joined.
23:27:12 <dulla> some guy asked about the wiki, "it down?"
23:27:13 <lambdabot> fizzie said 10h 3m 56s ago: I do not have information of fungot's migration route. Although I could compute a lower bound.
23:28:08 <oerjan> i am not someone who can fix it.
23:28:22 <oerjan> also, may i recommend downforeveryoneorjustme
23:28:24 <dulla> Should we call in Stallman?
23:28:58 <oerjan> sadly they both look idle
23:29:17 <dulla> fizzie are terrorists attacking your servers? You may need to do something about it
23:29:42 <oerjan> dulla: the server is known to be crap, it's free hosting.
23:29:55 <oerjan> so outages are to be expected.
23:30:08 <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"
23:30:30 <oerjan> oh HackEgo isn't even here
23:30:42 <oerjan> it's likely the server is physically down, then.
23:30:49 <dulla> fizzie rescind that previous statment, did a stiff breeze cause the servers to reformat?
23:31:18 <oerjan> dulla: fizzie is likely to be asleep, he's in britain and has a job...
23:31:27 <oerjan> and has been idle for 5 hours
23:31:45 <oerjan> Gregor has also been idle for 5 hours, but is normally in canada these days
23:32:20 <dulla> site admins that sleep
23:32:36 <dulla> scratch that, site admins that are awake
23:32:52 <AndoDaan> Okay. Thanks for the downforeveryone... tip. Didn't know about that. Handy.
23:33:06 <oerjan> unfortunately there are only those two that can access the server as opposed to just the wiki.
23:33:14 <oerjan> and for _some_ things, only Gregor can.
23:34:02 -!- Lymia has quit (Ping timeout: 250 seconds).
23:34:12 <dulla> does it send multiple requests from different locations?
23:34:31 <dulla> I know a free proxy view site
23:34:58 -!- Phantom_Hoover has joined.
23:35:01 <dulla> it's a great way to get around robot.txt
23:35:11 <oerjan> anyway, i consider the tests conclusive enough for the moment.
23:36:12 <oerjan> also, Gregor while nominally more likely to be awake, also has a history of being much less active here than fizzie.
23:37:41 <dulla> sounds like having an invisible pink unicorn in a world that only has unicorns, and no invisibility capabilities
23:48:33 -!- Tritonio_ has joined.
23:51:14 -!- Tritonio has quit (Ping timeout: 252 seconds).
23:54:45 -!- Tritonio_ has changed nick to Tritonio.
23:55:36 -!- dianne has quit (Quit: byeannes).
23:56:34 <Phantom_Hoover> is the best way to do that not to just... ignore robots.txt?
23:56:55 <dulla> this is what you need to do with third-parties that respect robot.txt
00:03:05 <MDude> http://orteil.dashnet.org/randomgen/?gen=http://mdude1350.webs.com/generators/random-code/one-liner.txt
00:07:05 -!- wool has joined.
00:09:13 <MDude> http://wurstcaptures.untergrund.net/music/?oneliner=(Math.log(sin(215%26t)))-(Math.sqrt(124%7Ct))%2Bcos((tan(t))%26201%7Ct)%20&oneliner2=(Math.log(sin(215%26t)))-(Math.sqrt(124%7Ct))%2Bsin(sin(cos(117%7Ct)))&t0=0&tmod=0&duration=30&separation=100&rate=8000
00:11:39 <dulla> fucking byte bytes
00:14:29 <MDude> Random number generator is not always the best composer.
00:14:47 <MDude> But it did come up with this as I was typing that: http://wurstcaptures.untergrund.net/music/?oneliner=t%3E%3E(sin(t*28))%7Ct%20&oneliner2=t%3E%3E(198-t*(Math.log(t%7C62)))%2F(cos(cos(233%3E%3Et)))&t0=0&tmod=0&duration=30&separation=100&rate=8000
00:23:34 <MDude> http://wurstcaptures.untergrund.net/music/?oneliner=Math.sqrt(81*t)%3E%3Et%25121%20&oneliner2=Math.sqrt(81*t)%3E%3Et&t0=0&tmod=0&duration=30&separation=100&rate=8000
00:31:33 -!- adu has joined.
00:32:29 -!- kcm1700 has quit (Read error: Connection reset by peer).
00:32:34 -!- kcm1700_ has joined.
00:38:21 <Gregor> oerjan: I see my name highlighted multiple times.
00:38:40 <oerjan> Gregor: the wiki server is/was down
00:40:50 -!- shikhin_ has joined.
00:41:25 <Sgeo> Why do resolution changes permanently resize windows?
00:41:41 <Gregor> Wow, it's very down. Weird.
00:41:56 * Sgeo has his oculus rift
00:42:03 -!- Lymia has joined.
00:43:22 -!- shikhin has quit (Ping timeout: 240 seconds).
00:44:08 * Gregor has his occultus rift.
00:44:10 -!- Sgeo has quit (Read error: Connection reset by peer).
00:44:31 <oerjan> Gregor: is this the portal-to-another-dimension kind
00:44:51 <Gregor> It's a portal to the esolangs server panel, anyway.
00:47:20 -!- mitchs has quit (Quit: mitchs).
00:49:16 <MDude> http://wurstcaptures.untergrund.net/music/?oneliner=Math.sqrt(t*253)%2Btan(Math.sqrt(166%7Ct))%20&oneliner2=Math.sqrt(t*253)%2BMath.log(tan(cos(57-t)))&t0=1000&tmod=0&duration=30&separation=100&rate=8000
00:52:57 -!- mihow has quit (Quit: mihow).
00:53:55 -!- hjulle has quit (Ping timeout: 250 seconds).
00:59:41 -!- mitchs has joined.
01:00:34 <oerjan> 't rejoined the channel
01:09:51 <MDude> Oh right, that's the other thing I was thinking of.
01:12:04 <MDude> Anyway, what I was thinking with categorical propositions was to have it used in OOP to make inheritence better/worse.
01:13:39 -!- Lymee has joined.
01:14:08 <oerjan> All JavaBeanVisitorFactories are Factories
01:14:11 <MDude> I'm pretty sure that's what I was thinking.
01:14:52 <oerjan> also forgetting the script bug
01:15:04 <MDude> I just meant you entered that right before me,,.
01:16:20 -!- Lymia has quit (Ping timeout: 265 seconds).
01:16:53 <MDude> But yeah, the idea was mostly that if you has "some" or "not all" of a class as something, you could more easily have exceptions to things.
01:17:31 <MDude> And other parts would know that such exceptions are possible, as oppossed to if it was "all" or "none".
01:18:23 <MDude> And then you could have conditionals like "if (instance) might be a (class)".
01:19:08 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:19:50 <MDude> And that is the fine joke.
01:25:19 -!- Sgeo|phone has joined.
01:26:12 -!- Tritonio has quit (Ping timeout: 252 seconds).
01:29:08 <mitchs> not a burnt out backlight on a laptop is it?
01:31:32 <mitchs> you could tell by shining a flashlight on the screen or hooking up an external monitor
01:33:24 -!- Thedarkb has joined.
01:34:20 <Sgeo|phone> Rift counts as external monitor i think
01:34:39 <Sgeo|phone> Buy it didn't receive video info when i do that
01:35:59 <Sgeo|phone> Last time this happen ed, one of my name restarts was black as usual but eventually showed windows login screen
01:36:30 <Sgeo|phone> I may have been pressing F8 or something
01:36:54 -!- Thedarkb has left ("Konversation terminated!").
01:40:46 -!- oren has joined.
01:41:48 <oren> So I dissasembledmy laptop to see if I could fix the screen problems. Now the screen seems to have stopped acting up... but the touchpad doesn't work.
01:42:51 <Sgeo|phone> Most recent restart seems to be working
01:43:02 <Sgeo|phone> In the sense of getting the Lenovo logo
01:44:04 <oren> I've decided I can live with using an external mouse all the time
01:47:29 <MDude> http://wurstcaptures.untergrund.net/music/?oneliner=((t%3E%3E88*(Math.log(6%2Ft)))%2B(t%7C(cos(sin(242%25t)))))%25(t%7C78)%26(83%25t)%20&oneliner2=%20((t%3E%3E88*(Math.log(6%2Ft)))%2B(t%7C(cos(sin(242%25t)))))%25(234%3E%3Et-227%7Ct)*(sin(sin(t)))&t0=1000&tmod=0&duration=30&separation=100&rate=8000
01:49:36 -!- AndoDaan has quit (Quit: Bye).
01:49:43 -!- AndoDaan_ has joined.
01:49:52 <tswett> MDude: well... that's interesting.
01:50:00 -!- AndoDaan_ has changed nick to AndoDaan.
01:51:17 <MDude> I'm trying to figure out how to have it put parens.
01:52:37 -!- FreeFull has quit (Ping timeout: 255 seconds).
01:54:22 -!- FreeFull has joined.
01:55:06 -!- wool has quit (Quit: Page closed).
01:55:50 -!- Sgeo has joined.
01:57:54 -!- Lymee has quit (Ping timeout: 265 seconds).
01:59:31 <tswett> http://mrob.com/pub/ries/zeta.html - this is one of the best-sounding simple mathematical things I know of.
02:00:06 -!- Sgeo has quit (Ping timeout: 244 seconds).
02:02:27 -!- Lymia has joined.
02:15:48 -!- Sgeo has joined.
02:27:52 <Sgeo> I am currently typing this from in a nebula of some sort
02:28:08 <Sgeo> But the resolution is crap, I can barely make out the words I am typing
02:28:21 <oerjan> Sgeo: is it omg full of stars?
02:28:36 <Sgeo> Did you say "omg full of stars"?
02:28:48 <Sgeo> There's a starfield option, but it's crap, it looks like a posterboard near me
02:30:20 <oerjan> so not a real nebula then
02:45:46 <Sgeo> Apparently I should put my glasses on
02:45:51 <Sgeo> Closed right eye, everything got fuzzy
02:45:56 <Sgeo> Which is what reality does too
02:51:11 -!- Lymia has quit (Ping timeout: 250 seconds).
03:07:02 -!- Tritonio has joined.
03:31:28 -!- MDude has quit (Quit: later chat).
03:31:51 -!- MDude has joined.
03:42:11 -!- Lymia has joined.
03:42:38 -!- oren has quit (Quit: Lost terminal).
03:48:15 -!- Sgeo|phone has quit (Quit: AndroIRC - Android IRC Client ( http://www.androirc.com )).
04:48:11 -!- bb010g has quit (Quit: Connection closed for inactivity).
05:06:09 -!- Oolicile has joined.
05:13:11 -!- heroux has quit (Remote host closed the connection).
05:14:15 -!- MDude has changed nick to MDream.
05:16:57 -!- Sgeo has quit (Ping timeout: 244 seconds).
05:17:41 <Oolicile> I literally am Complete shit at coding I have no idea how I got here
05:17:56 <Oolicile> Ill just go practice and whateverrr
05:18:38 <MDream> That sounds cool. I'd stay to talk about stuff, but I'm probably better off getting to bed earlier.
05:18:48 <MDream> In terms of being more alert to get things done.
05:19:57 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
05:21:19 <Oolicile> Go sleep Mdream ya need it for the stuff we gonna do tommorow
05:34:47 -!- zzo38 has joined.
05:39:44 -!- Oolicile has quit (Ping timeout: 246 seconds).
05:40:00 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
05:43:01 -!- Sgeo has joined.
06:01:00 -!- bb010g has joined.
06:09:50 -!- ProofTechnique has joined.
06:10:19 -!- contrapumpkin has joined.
06:11:49 -!- copumpkin has quit (Ping timeout: 250 seconds).
06:23:45 -!- copumpkin has joined.
06:25:24 -!- contrapumpkin has quit (Ping timeout: 252 seconds).
06:41:15 -!- shikhin has joined.
06:44:31 -!- shikhin_ has quit (Ping timeout: 265 seconds).
07:10:41 -!- contrapumpkin has joined.
07:13:55 -!- copumpkin has quit (Ping timeout: 255 seconds).
07:14:19 -!- contrapumpkin has changed nick to copumpkin.
07:21:11 -!- shikhin has quit (Ping timeout: 246 seconds).
07:34:58 -!- Patashu has joined.
08:14:13 -!- heroux has joined.
08:37:21 -!- AndoDaan has quit (Quit: Going, going, gone.).
08:39:47 -!- vanila has joined.
09:07:46 -!- oerjan has quit (Quit: leaving).
09:35:44 -!- adu has quit (Quit: adu).
10:13:18 -!- TieSoul_ has joined.
10:13:56 -!- TieSoul has quit (Disconnected by services).
10:14:01 -!- TieSoul_ has changed nick to TieSoul.
10:14:23 -!- hjulle has joined.
10:18:18 -!- Tritonio has quit (Remote host closed the connection).
10:23:57 -!- MoALTz has quit (Ping timeout: 246 seconds).
10:36:04 -!- vanila has quit (Quit: Leaving).
10:39:16 -!- TieSoul_ has joined.
10:39:40 -!- AnotherTest has joined.
10:39:52 -!- TieSoul has quit (Ping timeout: 245 seconds).
10:40:07 -!- TieSoul_ has changed nick to TieSoul.
10:42:10 <b_jonas> zzo38: You have 6 life, opponent has 20. Opponent has Arcane Laboratory and Asceticism in play, you have a Soltari Foot Soldier. It's the start of the opponent's turn, both of you have no lands, but have some suspended Lotus Blooms so that the opponent can play a spell his turn, you can play a spell your turn, and a spell in your next turn, but that's all.
10:43:32 <b_jonas> this might not work, I need some more cards
10:46:06 -!- AnotherTest has quit (Ping timeout: 252 seconds).
10:46:18 <b_jonas> Right, let you also have a Bedlam in play. Both of you hvae some mathcing 1/1 creatures that are vanilla or have no relevant abilities (flying or first strike are ok), and you also have an Echoing Decay.
10:46:51 <b_jonas> Opponent will play a creature, and the only way you can win is by playing the same creature then playing Echoing Decay on your own creature next turn, then beating him with the Soltari.
10:47:10 <b_jonas> zzo38: I think that works for your Babson thing, though it's not very elegant.
10:56:09 -!- AnotherTest has joined.
11:00:24 -!- AnotherTest has quit (Ping timeout: 252 seconds).
11:00:39 -!- shikhin has joined.
11:20:46 -!- boily has joined.
11:27:26 -!- MoALTz has joined.
11:30:44 <mroman> @tell AndoDaan https://github.com/FMNSSun/P/tree/master/psrc/std
11:32:19 -!- MoALTz_ has joined.
11:33:47 -!- mhi^ has joined.
11:34:02 -!- MoALTz has quit (Ping timeout: 245 seconds).
11:34:22 -!- MoALTz__ has joined.
11:37:17 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
11:37:56 -!- shikhin has changed nick to shikhout.
11:39:18 -!- shikhout has changed nick to shikhin.
11:40:00 <mroman> My lisp dialect has a module system now
11:40:55 <b_jonas> mroman: is it just the scheme r7rs module system?
11:42:43 <mroman> No there are *.pm files
11:42:54 <mroman> which contains a list of files to load
11:43:02 <mroman> i.e. other *.pm files or *.p files
11:43:06 <mroman> *.p files contain actually code
11:43:13 <mroman> *.pm just is a list of includes
11:43:27 <mroman> map_par.pm includes prelude.pm and map_par.p
11:43:34 <mroman> and prelude.pm includes prelude.p
11:43:49 <mroman> so including map_par.pm results in loading map_par.p and prelude.p
11:47:37 <b_jonas> wait what? why do you call them *.pm ? that's the extension we use for perl
11:47:49 -!- Patashu has quit (Ping timeout: 264 seconds).
11:49:31 -!- Frooxius has quit (Read error: Connection reset by peer).
11:49:49 -!- Frooxius has joined.
12:00:42 <boily> it's been a long time I've had a massage. I'm overdue to have my feet lightly marinated, then forcefully reflexed by strong thumbs.
12:00:51 <mroman> with one to three letter extensions it's hard to take anything that hasn't been used yet
12:04:14 <b_jonas> mroman: sure, but still, perl is already complicated because *.pl is used for two things
12:16:39 <mroman> @tell boily I can massage you over TCP.
12:17:28 <elliott> I only over UDP-based massages.
12:21:39 <boily> ah, the feeling of a lower ACK massage...
12:21:47 <lambdabot> Maybe you meant: clear-auto-reply clear-messages clear-topic learn
12:22:17 -!- boily has quit (Quit: ANATOMIC CHICKEN).
12:35:45 -!- int-e has left ("ERUDITE POULTRY").
12:35:48 -!- int-e has joined.
12:41:10 -!- shikhin_ has joined.
12:44:11 -!- shikhin has quit (Ping timeout: 264 seconds).
12:44:11 -!- Koen_ has joined.
12:49:59 <b_jonas> these fast convolution algorithms (various kinds of fast fourier transforms on various types of elements, plus the Nussbaumer convolution algorithm) are magical, and I think I should try to understand them at least a little.
12:50:10 <b_jonas> I probably won't fully understand them, but I should try to understand them partially.
12:55:35 <int-e> b_jonas: are you familiar with polynomial rings?
12:59:57 <int-e> If so, http://cr.yp.to/papers.html#m3 is a very terse but uniform description of various tricks surrounding fast multiplication (including FFT).
13:02:32 <b_jonas> int-e: there's also the Cormen-Leiserson-Rivest-Stein book which gives a nice description
13:07:38 <b_jonas> in particular, I'd like to understand whether fourier transforms on real or complex numbers (whether approximated with fixed point or floating point) are really always more useful for convolution than ones on finite fields (called "number theoretic transforms" for some reason), or just more popular.
13:07:49 <b_jonas> But I might not be able to answer this.
13:09:26 -!- shikhin_ has changed nick to shikhin.
13:12:17 -!- MDude has joined.
13:15:59 -!- MDream has quit (Ping timeout: 264 seconds).
13:19:47 <int-e> b_jonas: as a data point, https://gmplib.org/repo/gmp-6.0/file/2ff56d3c5dfe/mpn/generic/mul_fft.c does FFT modulo various 2^N+1 (note that for normal FFT's, you need 2 to be invertible, and a suitable root of unity; you don't actually need a field.)
13:21:38 <int-e> The existence of the root is ensured by making N divisible by a large enough power of 2. (If N = 2^k l, then 2^l is a 2^(k+1)-th root of unity modulo 2^N+1)
13:23:38 <b_jonas> int-e: I think I can see the basic problem, namely that for many practical applications, you'd have to use a 32-bit integer to represent an element of the field, but then to do four multiplication in that field, you need not one instructions, but like ten: you need two separate 32-bit-to-64-bit multiplications, some rearrangements, then two 32-bit-to-32-bit multiplications and lots of extra instructions to do the modulus by a constant.
13:25:02 <int-e> Yes, finite fields are a bit awkward. :)
13:26:17 <int-e> Intel is doing something about that for small GF(2^k) at least: http://en.wikipedia.org/wiki/CLMUL_instruction_set
13:26:24 <b_jonas> with real numbers, these smart modern algorithms avoid _most_ of the penalty of having to use complexes rather than reals, and you just have to use single multiplications with reals, or a few instructions with reals.
13:27:17 <b_jonas> int-e: that's for cryptography, but is GF(2^k) relevant for convolutions? I thought you need a field with characteristic at least as large as the size of data in my input and output,
13:27:30 <int-e> b_jonas: the modulo 2^N+1 thing is really quite clever: Multiplying by the root of unity is a shift (or perhaps just an offset for addresses) and reduction moduloy 2^N+1 is basically one subtraction.
13:27:43 <b_jonas> eg. if I want to convolve image data with 8-bit deep pixels, I need at least 16 bit deep data, in fact more because you have to add logarithm of the array size.
13:27:56 <int-e> b_jonas: probably not :)
13:28:49 <b_jonas> I know you said you don't really need a field, but still, I don't see how GF(2^k) would work here
13:30:40 <int-e> b_jonas: I'm a victim of free association :P
13:32:19 <int-e> b_jonas: Perhaps one can implement multiplication over fields of order 2^(kn).
13:32:40 <int-e> But mostly it just doesn't work. (You can't even use the base 2 FFTs, because 2 = 0)
13:45:39 <Jafet> A cute use for FFT is string searching with single-letter wildcards.
13:47:27 <Jafet> Some people (such as GMP developers) prefer finite fields because they don't want to deal with floating point rounding.
13:50:00 -!- MoALTz__ has quit (Ping timeout: 244 seconds).
13:50:12 -!- MoALTz has joined.
13:52:46 <Jafet> (or finite-field-like-rings)
13:53:20 <b_jonas> Jafet: it needn't be floating point. you can represent the complexes with fixed point numbers. the Knuth book explains how that's supposed to be enough to work for Schonhage-Strassen integer multiplication.
13:53:31 <int-e> Jafet: they're only using that for really large numbers; the smallest N for i386 is 464, which has to be multiplied be approximately 32, I guess.
13:54:03 <int-e> (to get a number of bits)
13:54:04 <Jafet> You still need to consider rounding for fixed-point numbers.
13:54:10 <b_jonas> int-e: yes, because there's other algorithms to multiply integers
13:54:18 <int-e> Hmm. "sufficiently field-like rings".
13:54:57 <b_jonas> are there also simple algorithms to convolve polynomials that aren't O(n*polylog(n)) operations like FFT-based ones, but instead just O(n**p) where p is between 1 and 2?
13:55:20 <b_jonas> probably there are, analogous to integer multiplication
13:55:49 <int-e> b_jonas: But you're probably right that there's no floating point FFT in libgmp. At least I don't recall seeing one.
13:56:16 <b_jonas> the question is whether these can be faster than FFT stuff in reality
13:56:28 <b_jonas> maybe they can, I should try to read up on that
13:59:11 <int-e> b_jonas: sure; the integer multiplications are implemented as polynomial multiplications after all. So the Karatsuba trick is: (ax + b)(cx + d) = ac x^2 + ((a+b)(c+d) - ac - bd) x + bd
13:59:48 <b_jonas> int-e: right, the question is how fast that could be for the kind of operations I'm interested in
14:00:22 <b_jonas> most likely, you still can't get away with only 16-bit multiplications, even if the input is only 8 bits in size
14:00:43 <b_jonas> so you need 32 bits for all intermediate results
14:00:54 <int-e> b_jonas: what kind of platform are you targeting?
14:01:22 <int-e> (32 bit arithmetic doesn't scare me)
14:01:40 <b_jonas> int-e: let's say modern x86_64 cpus with SSE4_1 instructions and a decent cache, so 32 bit arithmetic is available, it's just more expensive than 16 bit one
14:01:47 <b_jonas> because you need twice the memory
14:02:28 <b_jonas> but of course I'd like to know a bit in general, not just answers for this
14:03:00 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
14:04:00 <b_jonas> it may matter a lot about the speed how the intermediate results fit in the caches
14:05:10 <b_jonas> and of course it matters whether I'm doing merely 1D convolution or 2D
14:05:13 <int-e> have you mentioned the degree of the involved polynomials?
14:05:13 <Jafet> Since the convolution algorithms don't use division, it doesn't matter what the register size is, you should still get the remainder of the correct result (for integer polynomials)
14:05:46 <int-e> I gathered that the coefficients are 8 bit numbers (unsigned? signed? it probably doesn't matter much.)
14:06:27 <b_jonas> Jafet: yes, but even then, the final results in each digit is the sum of n multiplications of two 8-bit resutls, where n is oyur array size, whcih is still more than 16 bits
14:07:01 <b_jonas> int-e: 8 bit unsigned, but I'm also interested in cases where you want more precision than that
14:07:29 <int-e> b_jonas: I don't know how you're hoping to fit the final result into 16 bits in the first place.
14:07:30 <b_jonas> and I'm thinking mostly of degrees up to 2048
14:07:33 <Jafet> In that case, you need more than 16 bits to store the result no matter what algorithm is used.
14:07:46 <b_jonas> int-e: yes, even the final result doesn't fit
14:09:08 <int-e> 28 bits, hmm. that's tight.
14:09:32 <Jafet> Another cute thing about the FFT mod 2^N+1 is that it always gives you the correct result mod 2^N+1, which is useful for people playing with Fermat numbers.
14:09:48 <Jafet> s/FFT/FFT multiplication/
14:12:18 -!- 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?").
14:19:02 <int-e> Ah, the CHICKEN! have a history of Poulet! which appeared out of nowhere on 2012-08-08.
14:19:54 <mroman> A sufficiently round chicken in space is just a dwarf-planet.
14:20:25 <mroman> That can spawn asteroids.
14:22:04 <int-e> http://int-e.eu/~bf3/tmp/eboilution.txt
14:36:55 -!- ProofTechnique has joined.
14:42:59 <b_jonas> you're right, using 16 bit arithmetic would be totally unrealistic
14:43:39 <b_jonas> I should try to imagine how the Karatsuba-based convolution would really work, as in, how much temporary space it uses and then what operations it does on what arrays in what order
14:53:55 -!- Frooxius has quit (Quit: *bubbles away*).
14:58:17 -!- AnotherTest has joined.
15:00:39 -!- Frooxius has joined.
15:01:00 -!- `^_^v has joined.
15:05:20 -!- GeekDude has joined.
15:05:20 -!- GeekDude has quit (Changing host).
15:05:20 -!- GeekDude has joined.
15:20:12 -!- skj3gg has joined.
15:28:28 -!- skj3gg has quit (Quit: ZZZzzz…).
15:29:49 -!- skj3gg has joined.
15:35:46 -!- AnotherTest has quit (Ping timeout: 252 seconds).
15:39:45 -!- skj3gg has quit (Quit: welp, see you later.).
15:52:57 -!- newsham has quit (Read error: Connection reset by peer).
15:53:14 -!- newsham has joined.
16:05:52 -!- koo7 has quit (Ping timeout: 240 seconds).
16:07:38 -!- koo7 has joined.
16:16:18 -!- trn has quit (Remote host closed the connection).
16:20:35 -!- trn has joined.
16:29:40 -!- shikhin has quit (Ping timeout: 255 seconds).
16:29:42 -!- Koen_ has joined.
16:37:30 -!- cpressey has joined.
16:38:42 * cpressey is beating his head over what exactly is "total" about total functional programming that uses corecursion and codata to work on "infinite" data structures
16:39:25 <cpressey> they do realize that on a finitary computer, those "infinite" data structures aren't actually infinite, and when you try to realize them, it... doesn't terminate. don't they?
16:44:46 -!- mihow has joined.
16:44:54 -!- Phantom_Hoover has joined.
16:45:15 <Koen_> I witnessed a Master 2 class (Master 2 meaning fifth year of college) where the students were asked the complexity of an algorithm about inversing n x n matrices
16:45:24 <Koen_> apparently they agreed the complexity was n
16:45:28 <int-e> cpressey: they produce böhm trees without bottoms. that's nice.
16:45:52 <int-e> (in the limit, of course)
16:46:12 <elliott> cpressey: well, the distinguishing property of codata is productivity; you don't consider the fully unrolled trees, but only what you get after "one step"
16:46:28 <int-e> > [1..] -- and initial segments can be computed in finite time
16:46:30 <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,...
16:46:43 <int-e> (that is productivity)
16:46:47 <elliott> "looking further" is considered an explicit operation rather than something you can ascribe to the result in the abstract
16:47:23 <Koen_> so if you try to "observe" it you're disturbing it? sounds quantic
16:47:32 <int-e> elliott: that's pretty lazy :)
16:47:36 <elliott> if you have "f : A -> Colist B", you know that (f x) is always something, you can look at as much of it as you want
16:47:42 <elliott> (whereas in Haskell it could bomb out)
16:48:22 <int-e> > filter odd [2,4..]
16:48:25 <cpressey> elliott: that grates against my idea of "total". w.r.t. how "total" is used in computability, anyway. *how do you know how much of it you want*
16:48:27 <elliott> cpressey: an alternative way of thinking about it is that functions are codata too. (Nat -> A) is exactly the same as (Colist A), and it's still "total" because we can look at as many "elements" as we want, even if the tree of them is infinitely deep
16:49:00 <b_jonas> cpressey: it's funny how people still try to invent total turing complete languages
16:49:37 <cpressey> b_jonas: https://github.com/wouter-swierstra/
16:49:59 <int-e> codata allows that. the non-termination comes from trying to write a codata structure (like a stream) out completely.
16:50:02 <elliott> Colist A would be, like, {f : Nat -> Maybe A | forall i, isNothing (f i) -> forall j, j >= i -> isNothing (f j)}.
16:50:31 <elliott> you can probably come up with a function type for, like, potentially infinite binary trees too, it'll just be annoying. this gets kinda domain theory-ish
16:50:33 <cpressey> https://github.com/wouter-swierstra/Brainfuck/ and my inquiry https://github.com/wouter-swierstra/Brainfuck/issues/1
16:51:06 <elliott> like, you can do Partial A as {f : Nat -> Maybe A | forall i j, i >= j -> f i >= f j}, where Just >= Just, Just >= Nothing, Nothing >= Nothing
16:51:19 <cpressey> afaict the author wrote this to demonstrate that you can have something which is both total and Turing-complete
16:51:55 <cpressey> which may be true, for his definition of total -- but it's hard to fit it into my idea of total.
16:51:57 <int-e> "A system is total iff it always produces a final result." <-- but the totality refers to functions whose codomain can be codata.
16:52:01 <elliott> my definition of "total functional programming" is just that every function is total
16:52:05 <elliott> not considering it as a global property
16:52:18 <cpressey> int-e: right. and to me, an infinite list is not a final result
16:52:28 <elliott> cpressey: let's put it this way -- it's the same argument as haskell being pure
16:52:37 <elliott> from the point of view of running a haskell program, obviously it's not
16:52:42 <elliott> the trick is you have an RTS to walk the pure results
16:52:55 <elliott> er, *the pure descriptions of effects
16:52:58 <elliott> here, you have [something] to walk the brainfuck execution trail
16:53:10 <int-e> (This is closing a circle. In math, it's perfectly clear what a total function is. If you consider functions on natural numbers, then that notion happens to conicide with terminating functions on a Turing machine. But *defining* totality through termination is wrong once infinite data is involved.)
16:53:15 <elliott> (Agda's IO is actually codata, so you can write a full Agda brainfuck interpreter and have the RTS chase the codata for you, potentially forever.)
16:53:26 <int-e> (I'm *very* sloppy)
16:54:19 <int-e> (what I mean is that total, partial recursive functions on naturals are terminating)
16:54:29 <elliott> https://personal.cis.strath.ac.uk/conor.mcbride/pub/Totality.pdf this is about this exact topic, and might help.
16:54:41 -!- hjulle has quit (Ping timeout: 256 seconds).
16:55:00 <elliott> McBride is probably the strongest advocate of totality =/= turing-incompleteness. he even told me off about it once even though I agree :(
16:55:22 <int-e> (Oh I see that Wouter is attacking the same point.)
16:55:40 <cpressey> I will probably just stop using the term "total", honestly.
16:56:40 <elliott> I mean, totality in this sense is still a good guarantee.
16:56:49 <int-e> As I wrote, it's a perfectly sensible term for saying that a partial function, is, in fact, nowhere undefined.
16:56:51 <elliott> you know your programs won't get "stuck"
16:57:05 <cpressey> i can't talk to both of you at once
16:57:13 <cpressey> i can barely talk to one of you at once
16:57:15 <elliott> (though of course if you just go back and model general recursion again you don't gain anything from the internal POV)x
16:57:57 <int-e> I'm afk for a bit anyway.
16:58:10 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:58:13 <MDude> Often the limit as to how many computation steps a computer can afford to take invloves factors beyond the architecture of the computer itself.
16:59:11 <Koen_> heat comes to mind
16:59:51 <cpressey> I'm going to at least stop using "total" to describe Turing machines that always halt (sorry Kozen), because if you want to look at it as *each transition* of the TM, with the *option* to GET the next transition, well then of COURSE each transition terminates.
17:00:09 <cpressey> (to look at it that way. at least, not to me.)
17:00:13 <MDude> Until zeno machines exist, I'm not too worried about the contradictions that might happen if my turing machines runs an infinite amount of time.
17:00:39 <elliott> I guess this use of "total" to describe languages comes from Turner's Total Functional Programming, as the obvious generalisation of talking about writing total functions.
17:01:03 <cpressey> elliott: yes. linked to in that github issue. i read it (mostly). some parts i like. others, not so much
17:01:51 <cpressey> like... you can't write a self-interpreter in this... but you are thinking you might write an operating system in it? really?
17:02:01 <MDude> Well, it is distinct from a machine that could get stuck infinitely trying to proccess one command.
17:03:39 <cpressey> MDude: I'm a bit "worried" about such contradictions, but they don't keep me up at night.
17:03:45 <elliott> I mean, you can write a self-interpreter in a way.
17:03:53 <elliott> you can't write ProgramWithType A -> A.
17:03:54 -!- oren has joined.
17:03:55 <MDude> I guess you could call such mcachines micricode-total.
17:04:01 <elliott> but you can write ProgramWithType -> Partial A, with the codata partiality monad.
17:04:11 <MDude> Or just micro-total.
17:04:30 <elliott> you can write the computation internally (like you can model IO in Haskell), you just can't prove that it actually always finishes, because Goedel.
17:04:52 <elliott> I think that paper defines 0 / 0 = 0 instead of doing something reasonable though. and probably doesn't cover codata or dependent types? I wouldn't want to program in "Haskell with a termination checker"
17:04:56 <cpressey> elliott: partiality monad in a total functional language, is that right?
17:05:08 <elliott> cpressey: like IO monad in a pure functional language, sure
17:05:31 <cpressey> entirely black horse with white legs
17:05:33 -!- ais523 has joined.
17:05:34 <elliott> you can define it easily with a normal codata mechanism, even prove things terminate and so on
17:05:50 <elliott> if you haven RTS that will chase it forever, you can use it to write any potentially non-terminating program you want, like that brainfuck interpreter does
17:06:35 <ais523> ooh, cpressey is here?
17:06:42 <ais523> that might be enough to make me pay attention to the channle
17:06:46 <elliott> cpressey: you can define the partiality monad regardless of language support for doing things for it. it's like saying the ability to define "data MyIO = GetChar (Char -> MyIO) | PutChar Char MyIO | Halt" makes Haskell an impure language *shrug*
17:11:43 <cpressey> having a total function from partial objects to partial objects is nice. i'm not contesting that. i'm trying to say that it doesn't tell you much about the properties of the program that uses them. and that's really the important part, isn't it
17:12:18 <elliott> I don't personally see, e.g. (Colist Nat) as a partial object
17:12:23 <elliott> this is really deep into definition-arguing though
17:12:52 <elliott> like, I can't see any way to claim (f : Colist A -> Colist B) can't be total without claiming (f : (Nat -> A) -> (Nat -> B)) can't be total, since the two are exactly isomorphic.
17:13:35 <elliott> erm. *Stream for Colist there (sigh)
17:14:37 <elliott> how do you still have the ability to program computers without burning out
17:14:37 <cpressey> in other news, no one here will care, but Cat's Eye Technologies has a Twitter account now. https://twitter.com/catseye_tc
17:15:02 <elliott> this is a lot of fancy unicode quotes
17:15:20 -!- Froox has joined.
17:15:30 -!- Frooxius has quit (Read error: No route to host).
17:15:30 <cpressey> not as many as some of the weirdos I'm following
17:15:51 <cpressey> they're much better at it than I
17:19:12 <cpressey> elliott: would learning about corecursion help me with my consternation here, or should I just give up? keep in mind that my understanding of monads is, after all these years, still fuzzy, at best
17:20:07 <elliott> cpressey: it might, yes, but you might still just come down to not liking how the terminology is used
17:20:20 <elliott> I don't know of a good introduction to codata though
17:20:32 <elliott> http://homepages.inf.ed.ac.uk/wadler/papers/free-rectypes/free-rectypes.txt is classic, at least
17:20:38 <cpressey> isn't codata just the subject of corecursion?
17:21:22 <cpressey> i confess, there's another angle i'm interesting in corecursion for
17:21:39 <elliott> the two-sentence explanation is "data is easy to produce but you have to consume it carefully (i.e., structural recursion)", "codata is easy to consume but you have to produce it carefully (i.e., "guarded" corecursion; making sure you're "productive")"
17:21:45 <elliott> corresponding to folds and unfolds specifically. blah blah blah F-coalgebras
17:22:41 <elliott> I'm sorry for getting into a terminology argument, anyway. I really don't care about it, heh
17:23:24 <elliott> I do think "languages where every function is total and your data recursion is structural and your only infinite data is properly guarded codata are useless for doing actual things, because they're not TC" is too prevalent an attitude but people should stop equating general usefulness with TCness anyway
17:23:44 <cpressey> I agree wholeheartedly with that
17:24:55 -!- shikhin has joined.
17:25:04 <cpressey> btw, I think I saw an article on HN about HTML+CSS3 being TC -- it came back from an unrelated search & I did not click on it but ISTR there was some discussion on that at one point in here
17:25:20 <elliott> yeah it was one of those "by TC I mean FSA" type things
17:25:37 <cpressey> there's a reason i don't get my news from HN
17:26:11 <ais523> cpressey: that article made me sign up to Reddit to debunk it
17:26:18 <ais523> it's not TC due to not having infinite memory
17:26:30 <ais523> assuming it's the one I'm thinking of
17:26:45 <cpressey> i really *don't* read HN, so I don't know, but it probably was
17:26:49 <ais523> it's possible you could salvage it using WebForms, but nobody's figured out how yet
17:27:22 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
17:27:28 -!- Phantom__Hoover has joined.
17:27:42 <Phantom__Hoover> i've had some really frustrating conversations with people who can't accept that the human brain isn't TC
17:28:19 <ais523> I think you need to talk about things like quantum uncertainty to prove it isn't, though
17:28:30 <ais523> human brain is analog in time, and you can store an infinite amount in a single real number
17:28:33 <cpressey> I think we need about 8 more words that are variations on TC
17:28:37 <ais523> but you can prove that it can't measure a time delay accurately enough
17:29:00 <cpressey> even then, maybe it's just pointless
17:29:03 <ais523> cpressey: well I've been thinking a lot about how to define TCness because of the 2,3 Turing machine thing
17:29:31 <cpressey> ais523: I have a something too, based on thinking about Wang tiles
17:29:52 <cpressey> actually's it's just an old thing
17:30:10 <ais523> my latest approach has been along the lines of "a language is TC if you can compile any TC-language program to it, via a function that can output the 'nth' byte of the resulting program in finite time"
17:30:14 <ais523> err, O(1) time, that is
17:30:28 <ais523> but I'm getting bogged down in details of what operations you're allowed
17:30:44 <cpressey> ais523: ah, so I give the "compiler" the source program, and n, and it outputs "byte" number n ?
17:31:06 <elliott> ais523: so you mean, the program that produces the output program has to give a productive colist of bytes back, huh
17:31:09 <ais523> well, symbol, not byte
17:31:15 <cpressey> or maybe O(x) where x is the length of the source program, no?
17:31:28 <ais523> cpressey: oh, I'm treating the source program as fixed here
17:31:47 <ais523> as in, for any given source program, we can produce the nth symbol of the target-language program in finite time
17:31:49 <cpressey> but the "compiler" is invariant of the choice of source program?
17:32:10 <ais523> oh, ooh, yeah we have to be careful here
17:32:30 <ais523> definitions get really complex when you're trying to avoid exploits while still allowing as much as possible
17:32:30 <cpressey> i assume we can't just OPTOMIZE it for each program we want to compil
17:32:55 * cpressey should really be "optomizing" a database query right now
17:33:16 <Phantom__Hoover> ais523, so are you saying that the compiler has to be 'local' when emitting a byte, basically?
17:33:30 <ais523> I guess the compiler has to be a fixed program, which can scale with the size of the source program, but not the target program
17:34:11 <ais523> Phantom__Hoover: I'm not quite sure what you mean
17:34:25 <cpressey> well, in comparison, my insight was simple: Wang tiling ~= Conway's GoL ~= CA-complete ~= can simulate any Turing machine which *never* halts
17:34:53 <Phantom__Hoover> well, that the time it takes to emit the nth byte can't increase without bound
17:34:56 <ais523> aha, we define it like this: a compiler is a single program, which, for any given source program, there is some finite bound within which it can produce any given byte of the target program
17:35:00 <cpressey> ~= meaning "computationally equivalent" because I don't do fancy unicode in IRC (yet)
17:35:23 <ais523> I do fancy Unicode in IRC all the time, but that one isn't on my compose key
17:35:54 <Phantom__Hoover> i.e. what you're trying to prevent is situations where the compilation process is introducing an unbounded amount of computational 'strenght'
17:37:08 <ais523> so for example, imagine a programming language which takes an infinitely long program as input, and only has two commands, "halt" and "nop"
17:37:30 <ais523> you can compile into that language by running your input program for n steps, then outputting "halt" or "nop" based on whether it halted within those n steps
17:37:32 <ais523> to output the nth command
17:37:49 <Phantom__Hoover> presumably because the trouble with the 2,3 turing machine was that, in some sense, most of the computation was done in that way?
17:37:53 <ais523> the problem I'm having is that, to define O(1), you need to define which operations you're allowed
17:37:59 <ais523> Phantom__Hoover: actually it wasn't
17:38:04 <ais523> my problem is proving that it wasn't thouhg
17:38:13 <ais523> which means defining what it means to do that
17:39:27 -!- vanila has joined.
17:42:03 <cpressey> ais523: this sounds reminiscent of one part of Minsky's old book where he frets about mappings between languages wrt TC-ness. He's not conclusive. I think he says the mapping function should not be more than primitive-recursive
17:42:31 <ais523> that's close to the argument I made in the first submission of the 2,3 Turing machine proof
17:42:32 <cpressey> if you allow any PR function, that still gives you an awful lot of leeway
17:42:55 <ais523> however, primitive recursive programs can't run for infinite time
17:42:59 <ais523> so they can't produce infinite output
17:43:00 <cpressey> and if we're trying to find the "smallest" TC things, it seems likely we're going to get into the territory of these "powerfulish" mappings
17:43:12 <cpressey> ais523: yeah, but a mapping doesn't need to
17:43:20 <cpressey> you're just mapping one finite program to another
17:43:27 <ais523> no, the problem with the 2,3 proof is
17:43:30 <ais523> the input program is infinitely long
17:43:56 <cpressey> no lambdabot, I meant an interrobang, but as I said, no fancy unicode yet
17:43:59 <ais523> because it has to initialize the whole tape of the Turing machine
17:44:09 <ais523> and the pattern it initializes it with isn't finite or repeating
17:44:39 <cpressey> in my view, it needs to lazily create that pattern as it uses thar part of the tape
17:44:46 <cpressey> and the complexity of doing so needs to be factored in
17:45:08 <ais523> so you would consider the 2,3 machine to be sub-TC, then
17:45:29 <ais523> I still haven't found the simplest pattern that works
17:45:31 <cpressey> ("needs to" ... er... simpler to consider systems that only do that, rather than ones that need a "prepared tape")
17:45:31 <vanila> An operating system made in common lisp - https://dl.dropboxusercontent.com/u/46753018/Screen%20Shot%202015-01-19%20at%2001.29.31.png
17:45:39 <cpressey> (is that like a perpared piano, John Cage...?)
17:46:01 <ais523> but suspect it's along the lines of "infinitely repeating pattern, except that all cells with index 2^n are replaced with the same specific value as an exception to the pattern"
17:46:15 <cpressey> ais523: I guess I... not exactly; I would consider it to be an abbreviated description of a TC system which, if not abbreviated, would be >2,3
17:46:55 <ais523> have you heard of the language "sequential tag"? it's something that #esoteric sometimes discusses
17:47:19 <cpressey> vanila: nice! (is the nethack written in lisp too?)
17:47:22 -!- arjanb has joined.
17:47:23 <ais523> basically, it has infinitely long programs; each command in the program is a sequence of subcommands, either "run" or "skip"
17:47:39 <cpressey> ais523: I... don't think I have
17:47:49 <ais523> all data is stored in one queue, which is initialized as "run"
17:47:50 <cpressey> oh, infinitely long THIS, infinitely long THAT, what madness is this
17:48:07 <cpressey> (might make more sense if you saw my rant about "total" earlier)
17:48:33 <vanila> it's just telnet talking to nethack server, but the mandelbrot and stuff is in lisp :)
17:48:40 <ais523> then repeatedly, you pop the start of the queue, if it's "run" you append the current command of the program to the end of the queue and move to the next command, if it's "skip" you move to the next command of the program without appending anything to the queue
17:48:47 <ais523> and it halts if the queue ever becomes empty
17:49:19 <ais523> it's one of the easiest languages to implement, if you have the ability to read an infinitely long program
17:49:25 <ais523> because it's so simple
17:49:41 <ais523> and it's TC if you allow an infinitely repeating input prorgam
17:51:01 <ais523> (because with an infinitely repeating input program, it becomes cyclic tag)
17:51:34 <cpressey> wait, i totally do not follow. the queue is not a queue of... maybe i should look this up on the wiki
17:51:55 <vanila> I still find it hard to accept that cyclic tag machines can be TC, I get how they are but.. they shouldn't be..
17:52:04 <ais523> I'm not sure it's on the wiki
17:52:07 <ais523> but the queue is of "run" and "skip"
17:52:29 <ais523> vanila: they "feel" sub-TC?
17:52:37 <cpressey> ok, so you pop "run", and the "current command" is -- the next thing on the queue?
17:53:13 <cpressey> does not appear to be on the wiki, btw
17:53:46 <vanila> yes - but just because my intuition is wrong I guess
17:54:12 <ais523> cpressey: the next command in the program
17:54:18 <ais523> the queue tells you whether to run or skip each command in the program
17:54:34 <ais523> and when you run a command, it shifts a specific sequence onto the end of the queue
17:54:49 <cpressey> ok, so the queue is not infinite, and the program is not on the queue
17:55:13 <cpressey> replace "infinite but repeating" with a "goto" and I'm fine with it
17:55:32 <cpressey> infinitely long programs, though... no.
17:55:55 <vanila> an infinitely long program could contain something very dangerous... unless you know that it was generated by a simple program
17:56:42 <ais523> now, the problem with things like cellular automata and turing machines
17:56:51 <ais523> is that the programs are inherently infinitely long
17:57:12 <cpressey> ais523: i disagree. unbounded, yes. infinite, no.
17:57:12 <ais523> so the conventional wisdom is that you have to initialize them with a repeating pattern
17:57:37 <ais523> for a Turing machine, you can have an unbounded tape, plus a rule for initializing it
17:57:53 <ais523> and I assume you'd treat that initialization rule as part of the Turing machine, rather than part of the input to it?
17:57:54 <cpressey> ais523: yes. and yes, it's a bit more difficult to work that into a CA, but
17:58:33 <cpressey> i consider a tape cell of a TM to essentially not exist until the head gets to it
17:58:44 <cpressey> but the head can always get to a new tape cell and make it exist
17:58:48 <elliott> "This is a little surprising: greatest fixpoints allow infinite objects, such as streams, yet the strong normalisation property is preserved." I guess wadler sums up the totality thing pretty well
17:58:50 <ais523> hmm, this viewpoint is quite at odds to mine
17:59:35 <ais523> elliott: I find it a little hard to define strong normalization if you have infinite input
17:59:54 <ais523> about the strongest concept I can manage to define on that is weak confluence
17:59:57 <elliott> cpressey: that's sort of like how the next cell of an infinite codata stream doesn't exist until you observe it, but you can always observe a new one and make it exist in finite time :)
18:00:18 <vanila> I hope wadler is ok, he was ill
18:01:04 <cpressey> elliott: yes, but this is happening *inside a Turing machine*, not *in my program*
18:01:27 <cpressey> it's only to avoid questions about infinite tapes
18:02:07 <cpressey> and a way to collect the complexity of "prepared tape" into one place, where you were already caring about complexity -- the running of the TM itself
18:02:44 -!- Phantom_Hoover has joined.
18:03:11 <elliott> with codata, semantically, the observation is explicit
18:03:21 <elliott> that can get hidden in sugar and bad implementation of it, though.
18:03:37 -!- Phantom__Hoover has quit (Ping timeout: 245 seconds).
18:04:31 <cpressey> elliott: question: could you formulate codata that represents a Wang tiling?
18:05:53 <elliott> cpressey: I guess I don't see why not. "current tile" and four neighbours, say.
18:06:09 <elliott> that gets annoying because of overlapping ways to observe the same square
18:06:13 <cpressey> http://catseye.tc/installation/Backtracking_Wang_Tiler fwiw
18:06:21 <elliott> cpressey: okay, alternate answer: sure, it's just (Nat,Nat) -> Tile
18:06:22 <cpressey> fun to watch for about 50 seconds
18:06:38 <elliott> functions are one type of codata (the best-supported, usually) and codata can be implemented as functions, so
18:07:19 <elliott> cpressey: uh, or do you mean something that ensures you're tiling properly
18:07:31 <elliott> that sounds like you'd end up with proof objects and stuff and this is out of my pay grade
18:07:32 <cpressey> no elliott, I want an invalid Wang tiling!
18:07:49 <elliott> I'm an invalid Wang tiling :(
18:09:03 <cpressey> I'm trying very hard not to lol
18:10:03 <cpressey> #esoteric: the channel where everyone can disagree about infinite
18:13:27 <cpressey> corecursion looks interesting, because i've been hanging out with people in generative art circles, and they're interested in grammars, but they're more interested in *generating* things from than, than *parsing* things with them
18:13:48 <cpressey> which is easy, programming-wise, in an RDP: replace scan("x") with emit("x") {more or less}
18:15:32 <vanila> also logic programming to run recognizers backwards to generate things
18:17:27 <cpressey> vanila: yes, I'm reading the wikipedia article on it now, and it's looking a bit like that
18:18:41 <cpressey> elliott: maybe I'm a finitist? would that be terrible? istr that might be terrible
18:18:58 <cpressey> an infinite list is REALLY a finite list plus a continuation!
18:19:11 <elliott> that's more or less the codata perspective though
18:19:22 <elliott> thinking of Colist A as an infinite list is up to you
18:20:16 <cpressey> ok, maybe that will help me think about what i don't like about this "TC and total too!" thing
18:20:29 <vanila> oh that's funny, I just learned about TC & total
18:20:35 <elliott> a Colist A is just something you can construct from an X and (X -> Maybe (A, X)) (for any X) (e.g. nats = unfold 0 (\n -> Just (n, n+1))) and that gives you Colist A -> Maybe (A, Colist A)
18:20:43 <vanila> I got my own view on it
18:21:07 <elliott> or more simply, Stream A from X and (X -> (A, X)), yielding head : Stream A -> A and tail : Stream A -> Stream A
18:21:13 <elliott> (eliding the possibility of stopping)
18:22:47 <elliott> depends on your type system :p
18:22:54 <elliott> Agda and Coq rely on a termination checker separate to their type system
18:22:55 <vanila> Here's what I came to understand:
18:23:01 <elliott> I prefer type systems that ensure termination by construction.
18:23:25 <elliott> fwiw: map f stream = unfold stream (\strm -> (f (head strm), tail strm))
18:23:49 <elliott> map f colist = unfold colist (\cl -> case observe cl of Nothing -> Nothing; Just (hd,tl) -> (f hd, tl))
18:24:00 <elliott> (of course your function has to be, um, total.)
18:24:11 <vanila> My idea of 'turing complete' was you could write any nat -> nat function that you can with 'recursive functions' (primitive rec + mu-minimization)
18:25:03 <vanila> agda isn't turing complete in that sense, but if you the notion to allow functions like: nat -> partial nat then it is turing complete
18:25:09 -!- mihow has quit (Quit: mihow).
18:26:22 <cpressey> elliott: I... almost see what you're saying
18:26:27 <cpressey> it's like a negative photograph
18:26:33 -!- mihow has joined.
18:28:12 <cpressey> that was why I was thinking total = well-typed; if the function maps every value in X to any value in Y, it is total, and you can type it X->Y
18:28:33 <cpressey> if for some values in X it doesn't, well, no Y for it then
18:28:42 <vanila> you can have well types programs that infinite loop, e.g. omega = omega
18:28:46 <elliott> then the question is what type in Haskell corresponds to the naturals
18:28:52 <cpressey> YEAH BARRING BOTTOM AND ALL THAT
18:28:53 <elliott> data Nat = Z | S !Nat is so close, but it has _|_
18:28:59 <elliott> but bottom is exactly what makes things non-total >_>
18:29:17 <elliott> since it means you don't have total mathematical \mathbb{N} -> \mathBB{N} functions
18:29:45 <cpressey> well, but f : Nat -> {0, _|_} is total right?
18:30:03 <elliott> also the functions have to be monotone/continuous/whatever blah blah blah
18:30:08 * elliott transforms into dana scott
18:31:42 <cpressey> unfortunately I need to leave no
18:31:55 <elliott> unfortunately, I'm sure :p
18:33:26 <cpressey> my AMAZINGLY ORIGINAL AND NOVEL AND EARTH-SHATTERING THEORY about how IRC destroys productivity has been proven
18:33:38 -!- cpressey has quit (Quit: leaving).
18:35:12 <vanila> i dont like to think of agda as TC, it just seems misleading and flame-war-inviting to me
18:35:41 <ais523> now I'm wondering what goes wrong if you try to get Agda to prove itself consistent
18:35:59 <elliott> the termination checker won't buy it
18:36:02 -!- mihow has quit (Quit: mihow).
18:36:47 <vanila> you can't get conAgda :: Proof (Consistent Agda)
18:37:00 <vanila> but you can produce conAgda' :: partiality (Proof (Consistent Agda))
18:37:14 <elliott> won't that just be fix later
18:37:38 <elliott> I don't believe that can ever work if it's not (clasically), eventually you have to produce a now (p : Proof (Consistent Agda))
18:37:49 <vanila> its just the same as a lisp program that tries fitting together axioms randomly to prove agda consistent
18:37:52 <elliott> *ever work since if it's not fix later (classically),
18:38:03 <elliott> well, it'll never find such a proof though
18:38:12 <elliott> the simpler way to write that value is fix later :p
18:38:42 <vanila> sometimes you can construct a value of type partiality Foo
18:38:43 <int-e> well, it might terminate after all
18:38:52 <vanila> and then actually provide a proof that it terminates, to get a Foo out
18:39:01 <int-e> unless you are, for some reason, convinced that Agda is in fact consistent.
18:39:04 <vanila> in the caes of this Proof, you will not be able to proof that it terminates inside agda
18:39:17 <elliott> int-e: I am convinced that Agda will never find an internal proof of its own consistency...
18:39:35 <elliott> okay, I guess this is pointless without defining Proof here
18:39:38 <vanila> but you can make it to do arbitrary computation
18:40:03 <elliott> okay, here's what I mean: meta-theoretically, we can prove that conAgda' ~~ fix later
18:40:13 <elliott> but that might not be true depending on what Proof is.
18:40:51 <elliott> if we can prove meta-theoretically that conAgda' ~~ later^n (now p) for some n and p, though, then there is an Agda term conAgda : Proof (Consistent Agda)
18:41:09 <elliott> if our metatheory is classical we can prove one of those.
18:41:18 <elliott> okay, it might not give us an n and p
18:41:24 <elliott> arguing about constructivism is too hard
18:42:43 <elliott> okay: there is no expression e : Partial A such that not not (e = later e, or there is an expression e' : A). I hope that's double-negated enough
18:43:25 <elliott> so if you say, there is no e : A, but I have e' : partial A, then I don't believe that e' can be anything other than later e', with enough "not not"s in there
18:43:31 <elliott> so it will not not not halt :p
18:57:21 <int-e> @djinn (((a -> r) -> r) -> r) -> (a -> r)
19:08:57 <int-e> elliott: I still think your assumption that A is empty is a tad optimistic.
19:09:29 <int-e> if the logic is inconsistent then it might well "prove" its own consistency
19:09:41 <elliott> Agda has had proofs of _|_ before.
19:09:57 <elliott> what I said applies regardless of A, though
19:10:03 <int-e> (and djinn just showed that not not not foo is the same as not foo, even intuitionistically)
19:10:21 <elliott> yes, that was what we call a joke >_>
19:10:39 <int-e> it was not not funny
19:18:19 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
19:19:41 -!- Phantom_Hoover has joined.
19:20:38 -!- dianne has joined.
19:22:45 -!- mihow has joined.
19:26:34 -!- ais523 has quit.
19:26:41 -!- shikhin_ has joined.
19:26:41 -!- ais523 has joined.
19:26:51 -!- shikhin_ has quit (Read error: Connection reset by peer).
19:28:25 -!- shikhin has quit (Ping timeout: 244 seconds).
19:28:26 -!- shikhin_ has joined.
19:35:21 -!- shikhin_ has quit (Read error: Connection reset by peer).
19:36:39 -!- shikhin has joined.
19:40:07 -!- shikhin has quit (Read error: Connection reset by peer).
19:41:42 -!- shikhin has joined.
19:45:59 -!- `^_^v has quit (Quit: This computer has gone to sleep).
19:49:25 -!- `^_^v has joined.
19:50:54 -!- shikhin has quit (Read error: Connection reset by peer).
19:51:29 -!- shikhin has joined.
20:01:46 -!- Phantom__Hoover has joined.
20:01:54 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
20:03:17 <b_jonas> ok, so I'm not sure in this, but I believe for polynomial convolution Karatsuba multiplication needs about as much space as twice the outplut plus once the input, but it might still be a bit too slow, and FFT multiplication needs twice the space of the output. so luckily, neither needs too much extra space, which is very useful.
20:04:51 -!- Patashu has joined.
20:05:54 -!- shikhin has quit (Read error: Connection reset by peer).
20:07:05 -!- shikhin has joined.
20:10:04 -!- shikhin has quit (Read error: Connection reset by peer).
20:11:37 -!- Phantom__Hoover has quit (Ping timeout: 250 seconds).
20:12:05 -!- shikhin has joined.
20:21:48 -!- shikhin has quit (Read error: Connection reset by peer).
20:22:31 -!- shikhin has joined.
20:25:02 -!- shikhin has quit (Read error: Connection reset by peer).
20:27:33 -!- shikhin has joined.
20:29:15 -!- shikhin has quit (Read error: Connection reset by peer).
20:32:37 -!- shikhin has joined.
20:32:38 -!- J_Arcane_ has joined.
20:32:56 -!- MoALTz_ has joined.
20:35:22 -!- J_Arcane has quit (Ping timeout: 255 seconds).
20:35:32 -!- J_Arcane_ has changed nick to J_Arcane.
20:35:49 -!- shikhin has quit (Read error: Connection reset by peer).
20:35:49 -!- MoALTz has quit (Ping timeout: 255 seconds).
20:36:37 -!- Patashu has quit (Ping timeout: 244 seconds).
20:41:08 -!- shikhin has joined.
20:50:50 -!- shikhin has quit (Read error: Connection reset by peer).
20:51:43 -!- shikhin has joined.
20:53:46 -!- shikhin has quit (Read error: Connection reset by peer).
20:54:58 -!- bb010g has joined.
20:56:41 -!- shikhin has joined.
20:59:56 -!- shikhin has quit (Read error: Connection reset by peer).
21:01:44 -!- shikhin has joined.
21:05:32 -!- shikhin has quit (Read error: Connection reset by peer).
21:06:57 -!- shikhin has joined.
21:08:21 -!- shikhin has quit (Read error: Connection reset by peer).
21:11:55 -!- shikhin has joined.
21:12:38 -!- shikhin has quit (Read error: Connection reset by peer).
21:16:57 -!- shikhin has joined.
21:20:58 -!- shikhin has quit (Read error: Connection reset by peer).
21:25:35 -!- ChanServ has set channel mode: +o elliott.
21:25:43 -!- elliott has set channel mode: +b shikhin!*@*$##fixyourconnection.
21:25:45 -!- elliott has set channel mode: -o elliott.
21:28:53 -!- PinealGlandOptic has joined.
21:36:33 -!- aretecode has quit (Read error: Connection reset by peer).
21:39:50 -!- aretecode has joined.
21:41:18 <oren> what does _|_ mean?
21:41:36 <oren> Is is the upside down T?
21:41:45 <b_jonas> oren: yes, it's called "bottom"
21:43:48 <oren> I suppose it is smaller on the page than the word "false".
21:44:17 <`^_^v> it's a middle finger to logic
21:44:17 <vanila> http://en.wikipedia.org/wiki/False_%28logic%29
21:44:20 <vanila> its an ascii picture of this
21:44:40 <oren> Maybe the easiest logical literals for me to type are "0=0" and "0=1"
21:45:56 <oren> Idea: an algolike language which lacks literals other than 0 and 1.
21:46:28 <oren> Wait... That would be the peano axioms...
21:46:30 <ais523> PCF? although that doesn't even have 1 really
21:46:36 <vanila> (1+1)*(1+(1+1)*(1+(1+1))) I can do binary like this
21:47:36 <oren> assignment should be <- . It should always have been <- .
21:47:46 <MDude> I think those +s and *s might need switched around?
21:48:38 <MDude> ChucK knows how to assign properly.
21:49:25 <MDude> Though I would also accept "set [var] to [value]" if allowing the language to be more verbose.
21:50:37 <oren> I made a calculator once that did exactly what ChucK does.
21:50:50 <oren> (in assignment, not in anything else)
21:52:42 <MDude> Oh, ChucK actually uses =>
21:53:04 <oren> In math, assignment is "let x be [value]"
21:53:53 <oren> But in math, the evaluation is explicitly controlled, like "now subsitutute in the value of x"...
21:54:18 <oren> God damn it how do you spell subsitute?
21:54:31 <MDude> I was imagining let would be for lazy evaluation statements, while set would be for eager evaluation.
21:54:33 <vanila> you just treat all equal values as identical
21:54:46 <MDude> Because obviously having both in a language makes sense.
21:55:47 <oren> MDude: that is a cool idea.
21:57:59 <oren> vanila: A math paper is a syntax-tree-rewriting program with verification, which a mathematician's brain runs and checks.
22:00:11 <MDude> Oh, good then. I wasn't sure if that was a good idea or not.
22:01:13 <oren> Eager evaluation is a good idea for time-critical parts of a program
22:02:13 <oren> E.g. we don't want to go out of the polygon drawing loop to lazy-evaluate the enemies' positions.
22:05:29 <oren> But in other parts of a program, being lazy can help performance. So having both is a good idea
22:07:44 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:08:15 -!- ais523 has quit (Quit: dinner).
22:08:24 <elliott> 22:02:13 <oren> E.g. we don't want to go out of the polygon drawing loop to lazy-evaluate the enemies' positions.
22:08:29 <elliott> this isn't what lazy evaluation is.
22:08:36 <elliott> I mean that is one possible non-strict evaluation strategy.
22:08:47 <elliott> but that is just not something that really happens when you write in Haskell or whatever.
22:09:00 <elliott> unless you're writing your polygon drawing loop extremely weirdly
22:09:13 <elliott> ok I can see how that would happen with certain kinds of data flow, I misread what you meant
22:09:18 <oren> Why not? You don't need to evaluate anything until it would have visible effects, right?
22:09:29 <elliott> there are tools for solving that within a lazy evaluation discipline though
22:09:34 <elliott> like, the thing is that making the polygon drawing loop eager wouldn't solve that
22:09:39 <elliott> because it's a non-local property you're talking about here
22:09:47 <elliott> it would be the position evaluation prior to that that would need to be strict
22:11:53 <oren> Why not have an evaluate operator that forces the value to be stored?
22:15:03 <vanila> i guess it just doesn't seem aesthetic to me
22:15:04 <elliott> oren: well, you can't quite have a -> a
22:15:08 <elliott> but you can have a -> b -> b
22:15:30 <elliott> in haskell (a `seq` b) is b, but where a must be evaluated (to WHNF)
22:15:34 <elliott> note: no guarantees as to the ordering of the two
22:15:42 <elliott> and (f $! x) is (x `seq` f x) which is useful
22:15:49 <elliott> it can be annoying to juggle though.
22:15:57 <elliott> but you can use it to enforce invariants about evaluation.
22:16:49 <vanila> It's cool how you can do strictness analysis on code and automatically use strict evaluation instead of lazy
22:17:06 <elliott> except when it doesn't work :(
22:17:21 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
22:17:35 <vanila> yeah its undecidable but you can hopefully get a good result a lot of times by abstract interpretation
22:20:19 -!- Lymia has quit (Ping timeout: 250 seconds).
22:22:29 -!- Lymia has joined.
22:24:05 -!- `^_^v has joined.
22:44:17 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:47:50 <oren> I find it intensely annoying that I can get all the ingredients for gunpowder in Dwarf Fortress, but can't make cannon or shot.
22:51:19 <oren> And brimstone (e.g. sulphur), and charcoal.
22:51:51 <Taneb> I am not sure that DF does have saltpetre
22:52:21 <oren> it has "saltpeter"
22:52:40 <pikhq> That's the US spelling.
22:57:00 <oren> Currently I am building my fortress hovering over a freshwater lake.
23:00:54 -!- vanila has quit (Quit: Leaving).
23:18:02 -!- ais523 has joined.
23:18:37 -!- adu has joined.
23:19:40 -!- PinealGlandOptic has quit (Quit: leaving).
23:25:11 -!- Froox has quit (Quit: *bubbles away*).
23:32:02 -!- Phantom_Hoover has joined.
23:40:30 -!- Tritonio has joined.
23:42:57 -!- PinealGlandOptic has joined.
00:09:23 <oren> Also you can get slate and chalk, but you can't make chalkboards!!
00:20:12 -!- tru23 has joined.
00:20:59 -!- tru23 has quit (Client Quit).
00:26:04 -!- Phantom__Hoover has joined.
00:26:47 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
00:28:11 -!- adu has quit (Quit: adu).
00:31:41 -!- PinealGlandOptic has quit (Quit: leaving).
00:35:09 -!- mihow has quit (Quit: mihow).
00:47:44 -!- oerjan has joined.
00:59:56 <zzo38> Then you should tell them to fix it so that it is possible to make chalkboards
01:04:16 <zzo38> The specification for a Hamster archive format can fit on the back of your business card.
01:17:52 -!- Phantom__Hoover has quit (Ping timeout: 240 seconds).
01:24:56 -!- not^v has joined.
01:54:25 -!- ProofTechnique has joined.
02:06:05 -!- not^v has quit (Ping timeout: 250 seconds).
02:16:44 -!- adu has joined.
02:40:35 -!- hjulle has joined.
02:52:27 <oerjan> @tell int-e <int-e> Ah, the CHICKEN! have a history of Poulet! which appeared out of nowhere on 2012-08-08. <-- there are stray poulets even up to last october! also he took a _long_ time to get regular.
03:05:26 -!- Koen_ has quit (Quit: Koen_).
03:23:13 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
03:56:02 -!- Lymia has quit (Remote host closed the connection).
03:56:36 -!- Lymia has joined.
03:58:16 -!- merdach has quit (Quit: WeeChat 1.0.1).
04:26:02 -!- Lymia has quit (Remote host closed the connection).
04:26:36 -!- Lymia has joined.
04:29:13 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
04:45:19 -!- ProofTechnique has joined.
04:54:13 -!- Lymia has quit (Ping timeout: 250 seconds).
04:54:45 -!- Lymia has joined.
04:56:02 -!- MDude has changed nick to MDream.
05:09:52 -!- Lymia has quit (Remote host closed the connection).
05:10:17 -!- Lymia has joined.
06:02:26 -!- Lymia has quit (Remote host closed the connection).
06:04:21 -!- Lymia has joined.
06:31:48 -!- adu has quit (Quit: adu).
06:42:46 -!- merdach has joined.
06:46:31 <b_jonas> zzo38: there's an easy solution for constructing a Babson task like you asked
06:46:57 <zzo38> What is it then? I didn't try to figure it out much so I don't know
06:47:43 <b_jonas> The key is to use one of the dozens of cards that use "with the same name" in their rules.
06:49:57 <b_jonas> You have 6 life, opponent has 20. Opponent has Arcane Laboratory and Asceticism and Bedlam in play, you have a Squire. None of you have lands, but there's some suspended Lotus Blooms so that opponent gets 6 mana in his turn, then you get 6 mana in your turn, then you get 6 mana in your turn after that. It's the start of the opponent's turn.
06:50:18 <b_jonas> Both of you have some mathcing 1/1 creatures that are vanilla or have no relevant abilities (flying or first strike are ok), and you also have an Echoing Decay.
06:50:42 <b_jonas> Opponent may play a creature, and the only way you can win is by playing the same creature then playing Echoing Decay on your own creature next turn, then beat him with the Squire.
06:52:41 <b_jonas> This already allows tens of creatures (you may need Spellbooks to set it up), and can be extended to much more if you increase the life total of the opponent and replace Echoing Decay with Bile Blight so you can use creatures of size up to 3/3.
06:53:52 <zzo38> OK, although I was thinking of stuff that doesn't say "with the same name"; I have thought of a few other examples but not the way to combine them.
06:53:55 <ais523> construct something complicated involving a bounce-to-top-of-library card and Search the City
06:54:04 <ais523> just so that Search the City gets some use ;-)
06:54:25 <ais523> when I first saw it, I thought it'd be an interesting card at U
06:55:18 <b_jonas> zzo38: I'd still like to see a construction that doesn't use "same name", but instead relies on creature cards with different power-toughness.
06:55:27 <b_jonas> I think it's possible, but I haven't found one.
06:55:56 <zzo38> Something I thought of for example is Dark Depths and Aether Snap.
06:56:13 <b_jonas> I'd like to note though that there's lot more cards with "same name" then I thought, and I think half a dozen can be used for this construction
06:56:56 <b_jonas> (as in, they may need extra cards for the set up, but the basic idea is the same)
06:57:12 <b_jonas> besides Echoing Decay and Bile Blight, Detention Sphere also works,
06:58:03 <b_jonas> ais523: hmm, that might work
06:58:28 <b_jonas> Sever the Bloodline also works
06:59:01 <b_jonas> I think there are two cards that destroy enchantments with the same name, those can probably be made to work
06:59:09 <ais523> b_jonas: for power/toughness total, there's brainstorm + wild pair + whatever that card is that steals all creature spells when they're cast
07:01:06 <b_jonas> um, I don't really understand
07:03:16 <ais523> you don't even need brainstorm if the matching card is allowed to start in your library rather than your hand, that was just to put a card in hand back into your library
07:04:04 <b_jonas> I think it might be possible to set up something where it's the actual combat that matters, something with 4/1, 2/3, 0/5 creature cards, switching P/T of your creature, blocking, and making sure you get ahead in combat if you play the exact same creature.
07:04:12 <b_jonas> I'll have to think about whether there's such a construction.
07:14:53 -!- arjanb has quit (Quit: bbl).
07:21:06 -!- fractal has quit (Ping timeout: 265 seconds).
07:23:43 <b_jonas> also, some of what I said and more of what I thought about FFT yesterday was wrong
07:24:01 <b_jonas> I'll have to think more about that stuff
07:29:24 -!- fractal has joined.
07:41:09 -!- Patashu has joined.
07:58:12 <zzo38> The other one might be Airdrop Condor and Artificial Evolution.
07:59:24 <b_jonas> zzo38: hmm... something like that could work
07:59:53 <b_jonas> but then I don't see how you make sure I can't just play a higher power creature
08:01:52 <zzo38> Perhaps there isn't a higher power creatures
08:02:13 <b_jonas> but you have to make a Babson task with multiple creatures to choose from
08:02:41 <zzo38> I mean multiple cards to play; each one may be a different kind of effect
08:02:43 <b_jonas> that's why I want combat, so if you choose a creature with too low power, it can't kill the opponent's creature, but if you choose one with too low toughness, yours doesn't survive
08:05:21 <zzo38> Note also that Artificial Evolution says "The new creature type can't be Wall"; if it didn't say that then you couldn't stop them from activating Airdrop Condor before you are able to change it back, I think?
08:06:08 -!- ais523 has quit (Ping timeout: 252 seconds).
08:07:45 <zzo38> Maybe they want to change "Goblin" into "Dragon" but if you target the other Artificial Evolution to change "Wall" into "Dragon" then they can't. But otherwise once one spell resolves they can activate it before your spell resolves, because that is the cost of the activated ability
08:07:46 <b_jonas> Would it be very inelegant if I used multiple instants previously suspended with Delay?
08:08:53 <b_jonas> Hmm wait, you might not need that...
08:09:01 <zzo38> I don't really know
08:10:07 <b_jonas> Is there something like Otherworldly Journey that works on auras? I know you could use Otherworldly Journey too, but it would require heavy machinery, worse than Delay.
08:12:46 <b_jonas> hmm no, it'd be ugly to make those act through turns
08:14:33 <b_jonas> then Delay might be the easiest
08:20:50 -!- ais523 has joined.
08:21:42 <b_jonas> Is there an easy way to give someone only _one_ colored mana (and possibly multiple colorless mana) in a particular turn, the way Lotus Bloom gives three colored mana?
08:22:04 <b_jonas> Because that could let you get rid of Arcane Laboratory.
08:23:09 <b_jonas> You could give one mana the next turn, that's easier, but how do you give one mana the turn after that?
08:25:46 <b_jonas> Though for this simple construction with Echoing Decay, it's enough to give one colored mana next turn so you can only play one creature, and three colored mana with Lotus Blood the turn after that and make sure there's no black creatures so you're forced to play only Bile Blight
08:28:34 <b_jonas> I'll try to think of a combat-based solution.
08:31:57 <b_jonas> what if you just have much fewer life than your opponent, and multiple creatures, each of which is the only one that can block the same type of creature: a creature with flying, black creature with fear, a creature with shadow, a creature with horsemanship, and a red creature with intimidate?
08:32:16 <b_jonas> plus make sure you can cast only one creature, and you're done
08:32:20 <b_jonas> no need for any fancy p/t magic
08:32:34 <b_jonas> oh, and you'll need an extra vanilla creature
08:33:13 <b_jonas> plus maybe some toughness increasing effects to make sure your blocker survives
08:36:03 <b_jonas> that's not scalable to more than five to ten creatures, but still
08:42:45 <b_jonas> (I'll have to think whether that evasion-based method can be combined with a P/T-based method)
08:44:11 <zzo38> That is one idea too, yes
08:44:41 <zzo38> But, it is possible that your blocker might not need to survive
08:46:50 <b_jonas> zzo38: yes, it needn't survive actually
08:47:07 <b_jonas> zzo38: if you have 1 life, then you die next turn if you don't block
08:47:42 <b_jonas> and suppose you have a large creature that doesn't untap next turn, so you win your second next turn otherwise
08:48:00 <b_jonas> but making your blocker survive is easy enough
08:48:19 <b_jonas> you just need ten Veteran Armorers with Pacifism
08:49:48 <b_jonas> is there an instant that adds just _one_ mana to your mana pool?
08:50:36 <b_jonas> oh, there is, suspended Divergent Growth works if you have ten Reliquary Towers
08:51:07 <b_jonas> then you don't need Arcane Laboratory
08:51:37 <b_jonas> (or Rule of Law or Eidolon of Rhetoric)
08:53:44 <b_jonas> though if there are really three of these cards, all uncommon in accessible sets, then I might not need to avoid it
08:54:40 <b_jonas> there's also Curse of Exhaustion
08:59:50 <zzo38> Or you can win in another way, such as opponent has no card to draw
09:21:32 -!- FreeFull has quit (Ping timeout: 245 seconds).
09:24:51 -!- cpressey has joined.
09:25:28 <cpressey> "produce byte #n in O(1) time" <-> "compile the whole thing in O(n) time"
09:25:42 <cpressey> and it fails hard on C++, with its templates
09:26:08 <cpressey> (obviously, that's a bit out of scope for what you're interested in, but still)
09:26:59 <cpressey> oh -- also, I have no problem per se with "prepared tapes" or infinite CA playfields -- the problem I have is with comparing apples to oranges
09:27:59 <cpressey> the only way I see to fairly compare them is to convert the one to the other
09:29:52 <cpressey> as for "total"... most of my confusion has abated
09:30:34 <cpressey> I do not contest that Woulter Swierstra has written a total function which takes Brainfuck programs to possibly-infinite execution traces
09:30:56 <cpressey> I do not contest that Brainfuck is Turing-complete
09:31:14 <cpressey> (the turing-complete version of brainfuck, that is :))
09:32:31 <cpressey> I might not even contest calling Wouter's function "Turing-complete", but that term is sort of a rubbish bin at this point anyway
09:33:19 <cpressey> I'll try to give an example that illustrates my remaining reservations/nonplussedness
09:34:00 -!- jetpack333 has joined.
09:34:10 <cpressey> Person A writes a function which takes brainfuck programs to possibly-infinite execution traces, represented as lazy lists (a finite list + a continuation)
09:34:14 -!- jetpack333 has left.
09:34:38 <cpressey> Person B writes a function which takes brainfuck programs to possibly-infinite execution traces, represented as brainfuck programs
09:34:50 <cpressey> also known as, er, the identity function.
09:36:08 <cpressey> elliott or int-e or anyone else ^^^
09:37:25 <ais523> what's the non-Turing-complete version of brainfuck?
09:37:35 <ais523> (I assume you aren't referring to one of the many awful BF derivatives)
09:38:00 <oerjan> 30 Kb should be enough for everyone
09:38:11 <ais523> that's an awful BF derivative that predates BF
09:38:13 <cpressey> ais523: well, the version where you take the original implementation in C as god, and... yeah
09:38:27 <ais523> besides, writing off the end of an array is UB
09:38:35 <ais523> I can imagine a C implementation that reacts by extending the array
09:38:50 <ais523> also increasing the size of an int so that it can continue to index the array indefinitely
09:39:33 <ais523> actually I guess you have to increase the size of a char
09:39:40 <ais523> but then defining char_bit would be difficult
09:39:42 <cpressey> ais523: tantamount to throwing much of C out the window, but, ok
09:40:05 <ais523> the world needs more C impls that don't act anything like C
09:40:41 <cpressey> store the tape on a real tape and issue I/O commands by mapping a volatile variable to an I/O port
09:40:47 <cpressey> then you're only limited by the size of your tape reel
09:41:10 <ais523> or by using the stdio FILE * API
09:41:15 <ais523> that's even blessed by the standard
09:41:29 <ais523> and you can move around using relative seeks
09:41:50 <cpressey> ok, but I worry that it still might have some unfortunate verbiage in the spec that imposes a maximum somewhere
09:42:19 <ais523> I'm remembering from last time this subject came up
09:42:55 <cpressey> anyway, on that other note, it seems most "reasonable" languages do admit a "dumb" compiler to Turing-machines in O(n) time
09:43:04 <cpressey> dumb = non-optimizing, of course
09:43:19 <cpressey> maybe a little more than O(n) if you don't accept that hash tables are O(1)
09:43:40 * oerjan wonders if cpressey ever noticed his underload interpreter in emmental
09:44:09 <cpressey> oerjan: I must be going crazy, I swear I can hear your thoughts
09:44:12 <oerjan> dulla: both are esolangs
09:44:31 <oerjan> i made it around the time the wiki featured emmental
09:44:42 <dulla> So, I guess my hint is to look at all the concurrency esols
09:44:48 <ais523> dulla: http://esolangs.org/wiki/Underload
09:44:51 <ais523> if you haven't seen it, you should
09:44:54 <ais523> it's one of the Big Five
09:45:11 <int-e> cpressey: you can prefix an interpreter with a sequence of states that initialises the tape with the source code, which would be really stupid but O(n), no extras.
09:45:16 <ais523> (Befunge, Brainfuck, INTERCAL, Underload, Unlambda)
09:45:54 <oerjan> cpressey: http://oerjan.nvg.org/esoteric/emmental/ul.emm or slightly less evilly, the haskell generator http://oerjan.nvg.org/esoteric/emmental/EmmUnl.hs
09:47:31 <cpressey> "It uses Emmental's metacircular evaluation principles to _turn_ the Emmental interpreter into an Underload one" -- exactly the sort of thing I was hoping for
09:49:14 <ais523> oerjan: the Haskell generator uses lens
09:49:18 <ais523> and you're calling it less evil?
09:50:40 <oerjan> it was in fact the first haskell program where i used lens in earnest
09:50:50 <int-e> Hmm, is there a way to get Firefox use syntax highlighting if it sees Content-Type: text/x-haskell ?
09:51:08 <oerjan> ais523: it's less evil in so far as it is _plausible_ for humans to read
09:51:10 <ais523> it normally delegates to your editor, which will know how, IME
09:51:55 <int-e> (I have the "open in browser" plugin, so at least I can display the file in the browser rather than having to save it to disk)
09:51:58 <oerjan> fizzie: HackEgo didn't get back properly after Gregor restarted the server
09:52:06 <lambdabot> Taneb says: lens has got to be the only library with more contributors than people who know how it works
09:52:22 <ais523> oerjan: did you just call me "fizzie"? :-)
09:52:52 <ais523> also, aimake has more contributors than people who know how it works, but it's not technically a library
09:52:59 <int-e> ais523: he was alerting fizzie to a problem
09:55:04 <ais523> oerjan: technically you'd only need to impl (), : and ^ to prove fancy-L-completeness
09:56:26 <cpressey> if fancy-L is what I think it is, <3 this channel, doing all the computability dirty work that everyone else refuses to touch
09:56:55 <ais523> cpressey: it means "it's possible to write at least one interpreter for a TC language in this program"
09:57:16 <ais523> which may have been your definition?
09:57:37 <oerjan> ais523: i am addressing fizzie as the person most likely to be able to fix it, although he seems frightfully evil
09:57:51 <ais523> he can't be worse than lens, surely
09:58:00 <oerjan> worst brain typo this year so far, i think
09:59:38 <lambdabot> https://dibels.uoregon.edu/market/assessment/idel
10:01:05 <oerjan> <ais523> oerjan: technically you'd only need to impl (), : and ^ to prove fancy-L-completeness <-- it was of course more fun to try to cram (almost) everything in
10:01:18 <ais523> does the ():^ TCness proof use nested parens?
10:01:30 <ais523> if not, minimal-Underload might actually work quite well as a source language for TCness proofs
10:01:32 <zzo38> The other way to open the text file in the browser is if you write "view-source:" before the URL; not all browsers will accept this though
10:02:00 <ais523> oh wow, I remember learning about that when I was in school and Geocities was really popular and I didn't know what CGI was yet
10:02:29 <zzo38> O, do you like to ask too many questions/complaints to me please?
10:02:51 <oerjan> ais523: definitely needs some nesting, although it should be limited by O(states*symbols) of a universal minsky machine
10:03:10 <int-e> (FWIW, on my own webservers I tend to hack mime.types to produce text/plain for .hs files.)
10:03:29 <ais523> how do you measure states and symbols for a minsky machine?
10:03:46 <oerjan> i guess only states then
10:05:02 <b_jonas> "(Befunge, Brainfuck, INTERCAL, Underload, Unlambda)" is the big five? I haven't heared of that yet, but it sounds reasonable.
10:05:17 <oerjan> ais523: also you only need to add ~ to get a TM instead
10:05:18 <ais523> b_jonas: it was sort-of informally agreed here a while ago
10:05:30 <zzo38> On my own computer I have put a .htaccess in /dnd/recording/ in order to make it set the MIME type of the TeX source files to text/plain too
10:05:43 <ais523> oerjan: ~ is one of the hardest commands to impl, although I guess it's not much harder than : and might even be a little easier
10:06:17 <b_jonas> ais523: ok, then I'll propose a category on the wiki
10:06:28 <cpressey> <ais523> so you would consider the 2,3 machine to be sub-TC, then <-- iirc, it's not capable of halting, so no, I don't consider it TC
10:06:35 <ais523> cpressey: my version, it is
10:06:39 <ais523> I use a right-infinite tape
10:06:44 <ais523> halting is falling off the left end
10:07:00 <int-e> Perhaps one could use 2^k as the number of symbols of a Minsky machine with k counters.
10:07:02 <ais523> however, I'm considering simpler tape initializations that have more complex halt states
10:07:15 <cpressey> ais523: beh, i almost want to count that as an extra symbol
10:07:29 <cpressey> at any rate, you can't fairly compare it to a bi-infinite tape
10:07:33 <ais523> cpressey: I have an explicit extra-symbol representation too
10:07:52 <cpressey> ais523: fine, but then it's 2,4 (or 3,3 -- i can't remember)
10:07:58 <ais523> however, the mathematicians who looked over this said that Turing Machines weren't well-defined enough that it mattered
10:08:15 <ais523> and in fact, different papers are inconsistent on whether the tape's infinite both ways or just one way
10:08:16 <cpressey> then the whole argument doesn't matter
10:08:27 <cpressey> all we can say is "Sure is small!" Hyuk
10:08:29 <ais523> this happens a lot during research
10:08:47 <b_jonas> cpressey: by the way, thanks for the article you have recommended
10:08:47 <ais523> I discovered that one of my papers refers to a proof in another paper
10:09:05 <ais523> but the two papers are using different definitions, in a way that probably matters
10:09:09 <b_jonas> Bernstein, Multidigit multiplication for mathematicians
10:09:15 <ais523> or at least, it's nontrivial to prove that it doesn't matter
10:09:33 <cpressey> b_jonas: interesting, I'm completely drawing a blank on that. you're sure it wasn't someone else?
10:09:45 <int-e> b_jonas: that was me; you're welcome.
10:10:37 <int-e> and don't worry, I'm happy not to be the only one who mixes up people :)
10:11:04 <oerjan> int-e: my :()^ gets awkward if you have more than 2 counters, anyway. (you'd need to move across the representation of a counter to get to the other side)
10:11:21 <ais523> but you never need more than 2 counters
10:12:36 <b_jonas> you never need more than 2 counters if you're satisifed with double-exponential slowdown
10:13:04 <oerjan> indeed, it might be worth it still then
10:13:16 <ais523> well, the 2,3 machine proof is double-exponential, I think
10:13:21 <ais523> I might have got it down to single-exponential
10:13:28 <cpressey> oerjan: I'm interested in this "System T" thing of Goedel's, which is apparently decidable but > PR. Know anything about it?
10:13:28 <b_jonas> hmm, if Game of Life was invented before Intercal, does that mean Intercal isn't really the first esolang?
10:13:29 <ais523> or it might have been triple-exponential originally
10:13:31 <oerjan> (of course, you still have exponential for using minsky)
10:13:32 <ais523> I don't even really remember
10:13:37 <ais523> b_jonas: INTERCAL wasn't the first esolang
10:13:44 <oerjan> cpressey: not that i recall
10:13:57 <ais523> b_jonas: http://esolangs.org/wiki/Prehistory_of_esoteric_programming_languages
10:14:09 <b_jonas> ais523: no, the _origianl_ 2,3 machine proof is something-exponential, but it's got a new proof that I think only has a polynomial slowdown
10:14:24 <b_jonas> it's plain counter machines where you can't avoid the slowdown
10:14:38 <ais523> b_jonas: really? I would be very surprised at that
10:14:44 <ais523> (a polynomial slowdown)
10:14:49 <ais523> based on the properties of that machine
10:14:56 <ais523> (you are aware that I wrote the original proof, right?)
10:15:11 <cpressey> oerjan: I'm a bit suspicious, mainly because if it really was, I'd think it would be more well-known, and maybe have a complexity class named after it, but. Never heard of it before yesterday.
10:15:21 <b_jonas> I'm mixing it up with another small machine
10:15:40 <cpressey> i don't know how i'm going to get anyway work done if i'm sitting on this channel :)
10:15:46 <ais523> rule 30's harder to prove but believed to be probably also TC
10:15:48 <b_jonas> one of those with 2 states and 3 neighbours on a line
10:16:13 <b_jonas> but those are distinct from the Turing machines
10:16:32 <b_jonas> anyway, for counter machines, you clearly can't get below at least single exponential
10:16:49 <ais523> the 2,3 construction is from sequential tag
10:16:53 <b_jonas> and I suspect that for a two-counter machine the double exponential is necessary
10:17:38 <oerjan> ais523: if you used tag, then the down-to-polynomial construction for rule 110 might apply to yours too, iirc it's simply about proving _tag_systems_ not to need exponential overhead
10:18:30 <oerjan> by a more clever representation of a turing tape
10:18:52 <b_jonas> but isn't it trivial that tag systems don't need exponential overhead if you can use enough symbols and rules?
10:19:18 <oerjan> b_jonas: maybe, but someone got a paper out of applying it to rule 110 anyhow
10:21:36 <ais523> oerjan: I used cyclic tag, which is proved TC by compiling from tag
10:27:06 -!- Phantom_Hoover has joined.
10:27:21 <oerjan> cpressey: assuming this is the same as https://en.wikipedia.org/wiki/Dialectica_interpretation#Induction i would _almost_ interpret that section as saying it is _not_ decidable.
10:28:15 <oerjan> and on quick browsing i don't see anything in the article that says it _is_.
10:34:10 <oerjan> b_jonas: i assume the thing you've heard of is http://www.citeulike.org/user/cook/article/8904389
10:36:17 <oerjan> b_jonas: ais523: http://www.bcri.ucc.ie/FILES/PUBS/BCRI_52.pdf
10:36:39 <oerjan> ais523: it also uses cyclic tag
10:36:43 <ais523> wow, "P-complete" is a weird phrase
10:37:12 <oerjan> yes, usually you then use LOGSPACE-reductions
10:37:29 <oerjan> or sometimes even lower stuff
10:38:12 <oerjan> as in, the part it changes is between the TM and the cyclic tag stuff, so it should apply to your case as well
10:39:12 <Taneb> This channel has given me a great intuition and informal knowledge for my computability module, but almost none of the formalities
10:40:24 <ais523> the trick is to know that the formalities aren't really as precise as mathematicians would want them to be
10:40:45 <b_jonas> Taneb: there's some nice books telling the formalities
10:41:18 <Taneb> b_jonas, I just received an almost completely irrelevant textbook!
10:42:22 <cpressey> oerjan: I'm going on some very vague statements in Turner's "total fp" paper, plus this: http://home.utah.edu/~nahaj/logic/structures/systems/t.html which says "There is a decision procedure for T"
10:42:51 <cpressey> "decision procedure" might not mean what I think/want it to mean, here
10:43:11 <b_jonas> oerjan: yes, that paper is what I've heared of, for it's linked from http://www.scottaaronson.com/blog/?p=2070
10:43:48 <oerjan> cpressey: ic. i think we're definitely over my head.
10:44:13 -!- MDream has quit (Ping timeout: 264 seconds).
10:44:43 <cpressey> oerjan: Turner's paper also referred to https://en.wikipedia.org/wiki/Primitive_recursive_functional which that wp article refers to.
10:45:10 <cpressey> i think, once you allow values to be infinite... oh, such fun.
10:47:41 <cpressey> oerjan: (scroll up to where I give an example with "Person A" and "Person B" earlier this morning)
10:48:14 <oerjan> i'm sure i read that but also that my brain is approaching breaking point right now.
10:49:16 -!- oerjan has quit (Quit: Later).
10:50:10 -!- bluckbot has quit (Quit: bluckbot).
10:52:03 -!- bluckbot has joined.
10:54:13 <cpressey> my stubborn refusal to let things make sense to me is increasing the cognitive burden of the channel
10:55:09 <ais523> I'd better not try to explain Feather then
11:01:41 -!- skarn has quit (Ping timeout: 250 seconds).
11:06:18 -!- skarn has joined.
11:15:15 -!- bluckbot has quit (Remote host closed the connection).
11:17:04 <fizzie> @tell oerjan Uh-oh, I think my esowiki SSH key is only on the laptop and the fungot server, both of which are currently in the house-with-no-internet.
11:17:30 <zzo38> Are you going to copy it onto a disk?
11:19:50 <fizzie> I should probably put it onto this VPS system I'm ircing on, then I could access it from wherever.
11:23:39 -!- FreeFull has joined.
11:27:01 -!- boily has joined.
11:36:36 -!- mbrcknl_ has joined.
11:43:43 -!- mbrcknl has quit (*.net *.split).
11:44:19 -!- mbrcknl_ has changed nick to mbrcknl.
11:46:12 -!- Lymia has quit (Remote host closed the connection).
11:46:47 -!- Lymia has joined.
11:48:30 -!- ais523 has quit.
11:51:57 -!- Lymia has quit (Ping timeout: 250 seconds).
11:53:21 -!- Lymia has joined.
11:55:24 <boily> how are you? have you esölanged recently? boardgaming?
11:56:22 <Taneb> I have been trying to figure out if I can implement Eodermdrome by piggybacking on the implementation of a research language one my lecturers made
11:58:15 <Taneb> However I don't really know either language
11:59:31 <b_jonas> the problem with Eodermdrone is how you choose an arbitrary injective homomorphism if there are multiple possible ones.
12:01:33 <Taneb> Can I get someone cleverer than me to look at http://arxiv.org/abs/1204.5541 and figure this out?
12:04:35 <Phantom_Hoover> b_jonas, the same way as in any ambiguous rewriting language, you pick one arbitrarily
12:05:27 <b_jonas> Phantom_Hoover: sure, but that could make it hard to debug programs
12:05:52 <b_jonas> because then it's easily possible that your program works well in this implementation, but not in other implementations that pick other choices
12:06:10 <boily> is the choice part of a finite set?
12:06:12 <Taneb> I don't think that many esolangs make debugging particularly easy
12:07:22 <boily> then can you score the arbitrary performance of each possibility, and deterministically go with the best?
12:07:55 <boily> Taneb: there's befunge, where tracing the execution is at least as interesting as running the program itself.
12:08:19 <b_jonas> boily: um, by what measurement of performance?
12:08:57 <boily> b_jonas: some arbitrary measurement >_>'...
12:09:13 * boily mumbles mumbles something about optimisation problems
12:11:02 <Phantom_Hoover> b_jonas, if you write ambiguous substitutions then you'll end up with undefined behaviour, the solution is to make your substitutions unambiguous
12:17:50 -!- Tritonio has quit (Remote host closed the connection).
12:21:09 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
12:22:48 -!- Tritonio has joined.
12:23:01 -!- boily has quit (Quit: SHAPED CHICKEN).
12:35:14 -!- Patashu has quit (Ping timeout: 245 seconds).
12:41:15 -!- MDude has joined.
12:44:22 -!- CADD has joined.
12:45:23 -!- SopaXorzTaker has joined.
12:50:45 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
12:50:45 -!- SopaXT has joined.
13:15:52 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
13:22:54 <elliott> cpressey: I forget if the total FP paper covers the fact that ackermann is actually primitive recursive if you have higher-order functions
13:24:31 <Taneb> My AI textbook arrived today and I am using it as a mousemat
13:24:52 <elliott> in a sense the dependently typed languages get a lot of their expressivity from the fact that you can do "fancy" recursion by returning functions or types, and by allowing you to structurally recurse over any structure you want (rather than just naturals on zero and successor)
13:25:15 <elliott> without actually having a fundamentally more complicated criteria for what recursion is allowed
13:33:01 <cpressey> elliott: it does mention that. what the heck complexity class does that correspond to, though? ackermann isn't contained in PR afaik
13:33:27 <elliott> cpressey: well: "The primitive recursive functions are among the number-theoretic functions, which are functions from the natural numbers (nonnegative integers) {0, 1, 2, ...} to the natural numbers."
13:33:51 <elliott> the trick is just to relax that return type criteria. (it already can't exactly be true, anyway, since ackermann sort of has more than one argument...? there's probably some better definition in The Literature.)
13:34:03 <elliott> (well, either that or the input type has to change, of course.)
13:34:16 <elliott> I doubt it has a name; "higher-order primitive recursive" or something
13:34:31 <cpressey> i consider the nat thing kind of incidental... exanoke has lists, for example; doesn't seem to change much
13:34:37 <cpressey> all you need is some well-founded data
13:34:49 <elliott> yeah but it isn't because adding functions gives you more in some sense
13:34:56 <elliott> actually maybe you can do ack by going via some data-type?
13:35:14 <cpressey> well i know there are rewrite systems by which ack can be proved to terminate
13:35:27 <cpressey> i assume there's some way to draw a correspondence between those systems and types
13:36:01 <elliott> I think the main thing is that you can get a lot out by just being able to generate other kinds of inductive data through the induction principles, rather than just the same type
13:36:07 <elliott> and then recurse on those themselves
13:37:12 <elliott> I don't think I've ever seen a "reasonable" function you can't define in Coq or Agda directly due to termination checking (even if it's really awkward to define) that isn't "interpretation-y stuff" (which I expect to be that way).
13:37:13 <cpressey> til eodermdrome is an oilipoian thing. and that eodermdrome the esolang is a lot like thue, except on graphs, and it has a nicer approach to input imo
13:38:13 <b_jonas> cpressey: the fun part is that eodermdrone would actually be easy to program if you had an unlimited number of letters. the programs might not be efficient of course, but easy to write.
13:38:31 <cpressey> elliott: yes. in the "real" world, most people would consider NEXP too inefficient to be practical anyway. and PR >= NEXP. the problem is that some functions are awkward or inefficient when written in PR style
13:38:32 <b_jonas> but the way it is, it's not even turing complete, because there are only finitely many valid eodermdrone programs
13:38:48 <b_jonas> and the limitation that you have only 26 letters is very severe
13:39:13 <elliott> the "real" world of proving things :)
13:39:35 <cpressey> b_jonas: well that would let you make bigger graphs, but... you can chain smaller graph rewrites into a larger one. but yes i can see how that would be a pita
13:39:53 <elliott> but yeah, you can write things a lot nicer than the usual awkward mathematical primitive recursion in dependent type theory, but it can still get ugly.
13:40:35 <b_jonas> alternately, 26 nodes would be enough if we had more than one type of edge distinguished, possibly even directed
13:40:51 <b_jonas> say, with numbers written between the letters
13:41:12 <b_jonas> then it would be almost as easy to use as an ordinary pointer machine
13:41:12 <elliott> especially when you need to go to the level of well-founded recursion (basically defining your own "smaller than" relation and proving that you can recurse a data type in a way that always gets smaller -- this lets you do things like recurse on (x/2) on naturals, rather than just (x-1). you can define it all in type theory though, no need to extend its notion of recursion, it's just fun with induction pr
13:41:18 <cpressey> b_jonas: um... i think it's TC actually
13:41:18 <elliott> inciples and vaguely higher-order stuff)
13:41:38 <cpressey> b_jonas: you do realize the letters only describe how the graph is formed, right?
13:41:54 <b_jonas> cpressey: no it's not, because there's less than about 2**(2**(26**2)) valid programs (give or take a few
13:42:21 <elliott> now that's some practical limitation
13:42:32 <cpressey> b_jonas: that's not how i understood it, but i could be wrong. maybe ais523 can shed light on it
13:42:40 <elliott> my new esolang: brainfuck but you only get, like, G_64 tape cells
13:44:10 <Taneb> elliott, are the cells bounded at TREE(3)?
13:44:59 <cpressey> b_jonas: ok, i see what you're referring to -- I think this puts it in fancy-L territory -- you can't write arbitrary programs in it but you can write an interpreter for a TC language in it
13:46:20 <fizzie> Taneb: Is it the Russell & Norvig one, or something else?
13:46:33 <cpressey> there are 6906900 eodermdromes (the oulipo kind) if I'm not mistaken. which is cool, because that number looks a little like an eoderdrome itself (but it isn't.)
13:46:39 <Taneb> fizzie, yeah, Artificial Intelligence: A Modern Approach
13:47:19 <fizzie> (Okay, the third edition isn't all that old.)
13:47:28 <Taneb> And this is 4th Ed
13:48:07 <fizzie> People here keep numbering floors wrong.
13:48:16 <Taneb> Or rather, was thinking about the computation theory textbook I plan to order soon
13:48:21 <fizzie> (The whole ground floor / first floor thing.)
13:48:26 <Taneb> fizzie, are they forgetting that G is a natural number
13:48:50 <fizzie> Back in Finland we had 1 at street level, and so on.
13:49:25 <Taneb> Where are you now?
13:50:21 <fizzie> It hasn't been all that bad.
13:50:25 -!- ProofTechnique has joined.
13:53:53 <Taneb> Although if you do ever head further north, give me a bell
13:57:13 <fizzie> There was this talk (sometime last year) about meeting up in... Birmingham?
13:59:39 <Taneb> Birmingham is indeed further north than London
13:59:51 <Taneb> Although considerably further south than anywhere in the UK I've lived
14:00:22 -!- GeekDude has joined.
14:01:00 <Taneb> And yes, I think that was mentioned
14:01:05 <Taneb> Nothing was planned, though
14:03:47 <cpressey> Actually I think it's more like 34534500 because there are 5 possible starting positions
14:03:58 <cpressey> Meeting in Brum, what a bizarre yet intriguing idea
14:05:31 <cpressey> (no wait, there are also 5 possible rotations, they should be captured by the permutation right? i keep forgetting i don't like combinatorics)
14:06:34 <cpressey> elliott: the thing is, I *am* burned out, but can't retire yet
14:06:52 <cpressey> deciding to leave irc open during the day will be my downfall
14:07:40 -!- supay has quit (Ping timeout: 252 seconds).
14:07:48 <elliott> are you still doing, uh, web stuff
14:09:05 <cpressey> no wait, no, i am changing the world!!!1!
14:09:20 <cpressey> it will be a better place after our gamble succeeds
14:10:58 -!- bb010g has quit (Ping timeout: 252 seconds).
14:11:49 <oren> I am now at 6:32 mark of a ten hour video
14:14:24 <oren> http://snag.gy/Fd1Sh.jpg whoops, actually 11hours
14:18:22 <oren> I was thinking about explicit control of evaluation.
14:18:52 <oren> Suppose you have two separate syntax elements:
14:19:50 <oren> level 0 statements define, in a declarative style, the values to compute
14:20:41 <oren> level 1 statements would then in an imperative style, tell the program what order to reduce them in
14:20:46 <elliott> http://www.cs.bham.ac.uk/~pbl/cbpv.html
14:21:21 <elliott> but that's sort of what call-by-push-value is except not really.
14:21:28 <elliott> but it does the explicit evaluation control thing.
14:23:12 -!- supay has joined.
14:26:16 <oren> studentt distribution? what is this madness
14:30:25 <oren> Anyway, so what I am struggling to define is a good syntax for referring to a node in a evaluation tree.
14:32:49 <cpressey> I don't know what an evaluation tree is, but: 1.1.2.1
14:34:39 <oren> That could work. An evaluation tree would be a tree representing a set of values whihc depend on values in their children.
14:40:44 <oren> My idea is to isolate state changes to one level, and the entirety of math to zero level.
14:44:07 -!- bb010g has joined.
14:53:02 <cpressey> @tell shachaf I don't understand the question
14:57:11 -!- `^_^v has joined.
15:04:21 -!- Lymia has quit (Ping timeout: 250 seconds).
15:20:20 -!- Lymia has joined.
15:21:51 <fizzie> Taneb: I'll also be going to Oban at some point, but just for touristy things.
15:37:39 -!- CADD has quit (Remote host closed the connection).
15:40:59 <cpressey> elliott: btw, did you see my "Person A", "Person B" example from this morning. apparently it was too much for oerjan (who, in fairness, had just tried to tackle Goedel's System T)
15:42:19 -!- vanila has joined.
15:43:44 -!- CADD has joined.
15:44:23 <elliott> was it the brainfuck thing
15:44:41 <elliott> my brain filed it under the same category as "here's my self-interpreter: eval" and "my /bin/cat quine"
15:47:31 <cpressey> elliott: yes it was probably that thing, it was "here is a total function which maps any program to its infinite execution trace; its infinite execution trace is represented as a finite object like a lazy list; this finite object is the original program" making it the identity function
15:49:24 <vanila> to be honest the codata stuff seems to me like you're syaing.. "here's a game of life interprete" and then providing a function that computes n steps of game of life
15:50:07 <cpressey> and then saying "and you can call it as many times as you like"
15:50:22 <cpressey> which is fine, programming-wise
15:50:29 <cpressey> computability-wise, it's really not useful
15:50:55 <vanila> https://personal.cis.strath.ac.uk/conor.mcbride/pub/Totality.pdf
15:51:15 <cpressey> totality is a red herring imo (today). in fact, halting is a red herring too! (cf. Rice's theorem)
15:51:43 <elliott> vanila: that's even exactly what it is if you use like Stream
15:51:53 <elliott> since life : Board -> Stream Board is exactly life : Board -> Nat -> Board
15:52:22 <elliott> whereby exactly I mean... not in any language that currently exists. but the language everyone is thinking in, anyway
15:52:23 <oren> vanila: that would not be useful to someone unless they learn how to call said function
15:52:29 -!- kapil___ has quit (Quit: Connection closed for inactivity).
15:52:57 <oren> A function /= a fully functional program
15:54:27 <oren> there isn't a standardized encoding for conway gol initial states.
15:57:45 -!- supay has quit (Remote host closed the connection).
15:57:45 -!- bb010g has quit (Remote host closed the connection).
15:57:46 -!- ocharles_ has quit (Remote host closed the connection).
16:00:59 <oren> hm... technically, you could extract a primitive command-line interface from a function's argument types and numbers
16:02:58 <mroman> game of life interpreters could stop once a stable state has been achieved
16:03:01 -!- SopaXT has quit (Ping timeout: 250 seconds).
16:03:05 <mroman> or once a repeating state has been achieved
16:03:41 <oren> but only if every type is given a standard bijection
16:03:46 -!- variable has quit (Quit: I found 1 in /dev/zero).
16:04:04 <b_jonas> mroman: or just have the input mark a particular cell, and make the program stop when that cell is alive
16:04:09 <Taneb> mroman, I think determining if a state is repeating is uncomputable
16:04:42 <b_jonas> I have a crazy game of life program at http://www.perlmonks.com/?node_id=1008395
16:06:01 <cpressey> undecidable is also semi-decidable. glass half full, and all that
16:06:40 <Taneb> Yeah, I think for a finite initial state, it is actually computable, thinking about it
16:06:44 * cpressey forgot what he was going to rant about
16:06:46 <oren> Because of gliders, most states never repeat
16:06:46 <Taneb> As long as you know the time
16:08:03 <Taneb> And the initial state
16:08:28 <Taneb> Because it can only expand at a maximum of 1 cell per tick in any direction, right?
16:09:48 <cpressey> http://catseye.tc/installation/Schr%C3%B6dinger%27s_Game_of_Life fwiw
16:10:56 <b_jonas> yes, that's why it's better to have an end marker cell or something similar rather than watching for repeating states
16:11:01 <cpressey> there might be any number of conditions under which you want to consider a gol config "halted", also fwiw
16:11:06 <b_jonas> just stop the program when the cell (0,0) is live
16:11:12 <cpressey> which brings me back to Rice's theorem
16:13:30 <cpressey> might as well just define all turing machines as not being able to halt, and instead have a "scream state" which, if they ever enter it, they scream, and call it the Screaming Problem
16:14:24 <cpressey> if I have an infinite stream of codata representing the execution trace of a TM, ... that still doesn't help me tell if screams or not
16:14:50 <cpressey> So I'm very wary of Turner starting out with "it's total, which means it terminates" to "it's total, and you get infinite streams"
16:15:44 -!- SopaXT has joined.
16:15:55 <cpressey> besides! even if we had the most kick-ass language that let me prove all the properties I wanted about my program, it still wouldn't help!
16:16:29 <cpressey> because who writes to a spec, anyway? half of all software is written, not to a spec, but to a fuzzy notion of what will make the company money while not pissing off the users *too* badly
16:16:53 <elliott> you're definitely burnt out hehe
16:17:14 <cpressey> and those who do write to a spec -- their spec is like a gigantic legal document. maybe, if they're lucky, they've checked it for consistency
16:17:49 <cpressey> but they probably still don't know if it captures the requirements
16:18:05 -!- not^v has joined.
16:18:43 <cpressey> which will change tomorrow anyway
16:19:12 -!- spiette has joined.
16:19:30 <oren> cpressey: Or the coders interpret the spec differently then the customers
16:20:20 -!- CADD has quit (Remote host closed the connection).
16:22:26 <oren> "I thought by 'heart bar' you meant a line of hearts, not a heart with a red bar beside it!!"
16:24:15 <Gregor> Or a steel bar impaling a human heart.
16:25:34 <vanila> does anyone here write their own OS?
16:25:59 <oren> Vanila: I wrote part of one for a course...
16:28:12 -!- not^v has quit (Ping timeout: 245 seconds).
16:28:28 -!- ocharles_ has joined.
16:28:31 <cpressey> well, you start with a system, then you teach it to operate
16:28:42 <cpressey> actually -- it's mostly about interrupts.
16:28:55 -!- bb010g has joined.
16:30:30 -!- mihow has joined.
16:31:44 <oren> The overall structure was, some machine-specific stuff in assembler, followed by setting up the interrupt vector and resources for syscalls, then set up the file system (we didn't have to write the hard disk driver ourselves thank god) and then basically you pass control to a userland program which is the command interpreter.
16:32:06 -!- spiette has quit (Ping timeout: 265 seconds).
16:32:30 <oren> Overall the project was a half-assed version of UNIX.
16:33:38 <vanila> ill have to pay special attention to interrupts
16:36:45 -!- supay has joined.
16:41:42 -!- not^v has joined.
16:43:48 -!- spiette has joined.
16:53:27 -!- not^v has quit (Ping timeout: 256 seconds).
16:53:47 -!- not^v has joined.
16:55:44 <oren> So unicode might get color modifiers for face characters, for the sake of not being racist, but that didn't stop them from putting in 👱 👲 👳 .
16:56:52 <cpressey> overlapping boxes containing hexadecimal digits are very racist indeed
16:57:45 <oren> `unidecode 👱👲👳
17:02:18 <cpressey> i suspect, whatever that was supposed to do, it didn't work
17:02:30 <cpressey> or perhaps the bot is just really, really lagged
17:02:45 <oren> Hmm... Anyway those characters are "PERSON WITH BLONDE HAIR" "MAN WITH GUA PI MAO" and "MAN WITH TURBAN" respectively.
17:03:20 <oren> that is, Japanese stereotypes of Europeans, Chinese and Indians.
17:03:21 <cpressey> I see. those sounds like emoji imports
17:03:53 <vanila> I hate unicode so much!!!!!!!!
17:04:04 <vanila> 127 characters is already far too many
17:04:10 <cpressey> emoji which github supports. i always wondered why I'd ever need to pur a man with a gua pi mao in a pull request, though
17:05:39 <oren> "Woman with bunny ears" because the Playboy brand must last for all the ages
17:07:07 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
17:14:19 <b_jonas> vanila: do you want 60 characters, in two planes of 30 characters you can switch among with shifts?
17:16:12 <vanila> i dont know what that is sorry
17:16:52 <vanila> I want ride of everything from 01-1F in ascii (except newline)
17:18:13 <oren> What about tab?
17:29:54 -!- CADD has joined.
17:33:52 -!- Phantom_Hoover has joined.
17:33:55 -!- SopaXT has quit (Remote host closed the connection).
17:45:35 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
18:02:25 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
18:02:54 -!- J_Arcane has joined.
18:17:34 -!- vanila has quit (Quit: Leaving).
18:30:04 -!- bb010g has quit (Quit: Connection closed for inactivity).
18:31:50 -!- cpressey has quit (Quit: leaving).
18:40:42 -!- FreeFull has quit.
19:31:48 -!- arjanb has joined.
19:56:18 -!- AnotherTest has joined.
20:09:07 -!- Lymia has quit (Ping timeout: 265 seconds).
20:12:30 -!- PinealGlandOptic has joined.
20:14:22 -!- PinealGlandOptic has quit (Client Quit).
20:22:02 -!- Tritonio has quit (Ping timeout: 252 seconds).
20:22:50 -!- nycs has joined.
20:23:12 -!- TieSoul has quit (Ping timeout: 245 seconds).
20:24:07 -!- Tritonio has joined.
20:26:12 -!- `^_^v has quit (Ping timeout: 264 seconds).
20:29:11 -!- TieSoul has joined.
20:31:12 -!- PinealGlandOptic has joined.
20:44:52 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
20:48:24 -!- bb010g has joined.
20:59:59 <oren> Yay, I'm this close to flooding the nuiverse with magma.
21:00:55 <oren> one level at a time, I'll flood it with water and magma, thus converting everything to obsidian
21:01:08 <b_jonas> oren: the whole universe, or just the surface of the planet?
21:01:19 <b_jonas> it's not so easy to flood a whole universe with magma
21:01:52 <oren> Well I have a pump stack that can bring magma or water to the highest level.
21:02:21 <oren> I need to build a second one for the other fluid
21:03:14 <b_jonas> oren: is this Dwarf Fortress or Minecraft?
21:03:24 <oren> Dwarf Frotress
21:03:47 -!- ais523 has joined.
21:04:29 <oren> Once I make it self powered, I'll lock one dwarf into my life support chamber and wait a few days.
21:05:17 <b_jonas> for how long can the dwarf survive in that chamber?
21:05:32 <b_jonas> and what are the walls for the chamber made of?
21:06:44 <oren> The walls are natural obsidian except the entrance which is a long tunnel which I'll obsidianify as the first step. The dwarf would have to tunnel his way out.
21:11:57 <oren> I'm not sure it will flood the whole map, but if I switch on a waterfall of each substance at the same time, I assume it will come close.
21:14:19 <oren> The only other guess I have as to the effect, is that a wall of obsidian will separate a vast ocean of magma from a similar ocean of water.
21:16:01 <oren> Either way it will be epic
21:16:32 <b_jonas> will you be able to find out which happens?
21:17:16 <oren> Eventually, when the second pumptower is complete.
21:18:04 <oren> First I have to modify the first one to integrate its power.
21:19:30 <b_jonas> oren: but isn't there fog of war in that game?
21:20:53 <oren> There is clouds, but above ground I can see everything.
21:21:48 <oren> I think it's something like 128 by 128 tiles
21:21:54 <oren> I haven't counted
21:22:02 -!- Patashu has joined.
21:22:08 -!- TieSoul has changed nick to TieSoul_.
21:22:14 -!- TieSoul_ has changed nick to TieSoul.
21:22:20 <oren> each tile is the size of a dwarf
21:24:08 -!- Tritonio_ has joined.
21:24:13 <oren> Seems like it is 48*4 x 48*4
21:26:14 <oren> The bigger it is the begger the lag
21:26:56 -!- Tritonio has quit (Ping timeout: 252 seconds).
21:30:22 -!- Tritonio_ has changed nick to Tritonio.
21:36:48 <b_jonas> so how good is the support chamber? how long can the lone dwarf live in it?
21:37:09 <b_jonas> or will you then rebuild civilization starting from that chamber?
21:37:25 -!- Lymia has joined.
21:39:28 <oren> I *think* practically indefinitely.
21:39:57 <b_jonas> what does that chamber have to contain for that?
21:40:07 <oren> It contains a small farm, and a still.
21:41:29 -!- AnotherTest has quit (Remote host closed the connection).
21:42:30 -!- R40UL has joined.
21:42:47 <oren> And i whenI get around to using it, I'll dump everything usable in the fort into the chamber
21:45:53 <oren> Hmm... won't both of the fluids just flow off the edge.
21:46:12 <oren> They have to meet before they do
21:49:25 <oren> I need like 100 enormous iron corkscrews
21:49:45 -!- nycs has quit (Quit: This computer has gone to sleep).
21:50:33 -!- `^_^v has joined.
21:50:45 <oren> To reach to the top of the map
21:51:35 <oren> I need to build a tower almost 100 levels high (easy with obsidian blocks) and then build 100 magma-proof pumps
21:53:03 <b_jonas> you'll need 100 confused scrolls of enchant weapon to magma-proof that many pumps
21:54:42 <oren> For unexplained reasons, ordinary iron is magma-proof
21:56:57 <b_jonas> oren: probably because DF magma is of only 1500 K or colder temperature
21:57:13 <b_jonas> and the iron is old low tech one with a high melting point
22:04:09 -!- oren has quit (Ping timeout: 265 seconds).
22:10:39 -!- oren has joined.
22:13:56 -!- aretecode has quit (Quit: Toodaloo).
22:18:44 -!- CADD has quit (Remote host closed the connection).
22:21:46 -!- CADD has joined.
22:29:48 -!- aretecode has joined.
22:33:46 <oren> The method of a self-powering water pump is due to escher, of course.
22:35:39 <oren> See we pump the water up, where it falls and becomes water pressure for a waterwheel.
22:35:57 <oren> Which then powers the pumps.
22:59:20 -!- zzo38 has quit (Remote host closed the connection).
23:05:28 -!- CADD has quit (Remote host closed the connection).
23:09:34 -!- CADD has joined.
23:13:12 -!- MDude has quit (Ping timeout: 245 seconds).
23:15:13 -!- cpressey has joined.
23:26:11 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:27:28 -!- `^_^v has joined.
23:29:19 <cpressey> It's entirely possible that there's no complexity class corresponding to the primitive recursive functionals simply because no one gives a crap.
23:29:35 <cpressey> I should probably just give up.
23:29:39 -!- cpressey has quit (Quit: leaving).
23:36:22 -!- mihow has quit (Quit: mihow).
23:38:00 <myname> since you people know haskell pretty well: is there something that is purely functional, can store things (like lists do) and support O(1) concatenation? I was thinking about something like a double linked list, but i am quite unsure
23:38:12 -!- mihow has joined.
23:38:23 <elliott> (you pay the O(1) cost in observation, though)
23:39:12 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:39:45 <myname> isn't ++ O(n) with n being the length of the first list?
23:39:52 <elliott> you only use that for literals.
23:39:58 <elliott> you can write \xs -> 'f':'o':'o':xs if you want
23:40:06 <elliott> the point is that if you have dlists f and g you can append with (f . g)
23:40:25 <elliott> > let foo xs = 'f':'o':'o':xs; bar xs = 'b':'a':'r':xs in (foo . bar) []
23:40:38 <elliott> the Show class uses this trick as ShowS (specialised to Strings only)
23:40:44 <elliott> to avoid exponential build-up doing lots of appends
23:41:25 <myname> searching through it works like always, right?
23:42:03 <elliott> you can only observe it by passing a list to it
23:42:09 <elliott> so you pay all the append costs then
23:42:15 <elliott> but it's much better than ((xs ++ ys) ++ zs) type stuff
23:42:26 <elliott> it's good for doing lots of appends and then observing the result once
23:42:51 <myname> i think i'm actually okay with that
23:42:59 -!- oerjan has joined.
23:43:47 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
23:43:49 <lambdabot> fizzie said 12h 26m 45s ago: Uh-oh, I think my esowiki SSH key is only on the laptop and the fungot server, both of which are currently in the house-with-no-internet.
23:47:04 -!- oerjan has set topic: To the finder of this bottle: I'm a fungot trapped in a house with no internet | ZFC is a ChuChu rocket. | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
23:49:37 <oerjan> Gregor: can you tell HackEgo to join the channel? it's on freenode but not here
23:50:01 -!- FreeFull has joined.
23:50:04 <myname> elliott: does this do the clever way of concatenation? i.e. right associative?
23:51:31 <myname> oh, it has to, if i don't ignore something obvious
23:57:14 <oerjan> elliott: did you point out to cpressey that you can do goodstein sequence in system F, and ackermann is much simpler than that.
23:57:46 <oerjan> (someone on this channel did that after we discussed that it should be possible)
23:58:17 <elliott> myname: in particular (f . g) . h and f . (g . h) both do right-associative appends.
23:58:51 <oerjan> which means that the answer to "what complexity class does that correspond to" is something at most System F / second order logic
23:59:20 <elliott> myname: you can use Endo [a], that comes with the right Monoid instance I think
23:59:38 <myname> elliott: mind explaining?
23:59:43 <elliott> or there's, like, http://hackage.haskell.org/package/dlist
23:59:47 <oerjan> (those are equivalent in some sense iirc from the discussion)
23:59:50 <elliott> Endo a is a wrapper for (a -> a)
23:59:55 <ais523> at least it's not like Ursala, where «(f)(g)(h)» means (f g) h and «(f) (g) (h)» means f (g h)
23:59:58 <elliott> which has a Monoid instance that does composition and an mempty that's id
00:00:05 <elliott> which is exactly the [] and (++) analogues here
00:00:13 <elliott> and you can also use like, mconcat
00:00:23 <elliott> you can also just use functions directly though
00:05:15 <oerjan> sometimes it feels like the amount of rep i get for a stackoverflow answer is inversely correlated to the amount of work it was...
00:06:40 <ais523> that doesn't surprise me
00:07:02 -!- Phantom_Hoover has joined.
00:08:10 <oerjan> it doesn't really surprise me either
00:08:47 <oerjan> an answer that's easy to make is also easy to understand
00:10:10 -!- R40UL has quit.
00:11:04 <myname> so... concat xs = foldr (.) [] (map (\x -> (\xs -> x ++ xs))
00:11:23 <myname> n being all list elements
00:11:47 <elliott> well, that's the same as foldr (++) []
00:11:52 <elliott> (you mean foldr (.) id but yeah)
00:12:38 <myname> foldl would be n^2, wouldn't it?
00:12:42 <oerjan> myname: GHC probably fuses that into something simple
00:12:57 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
00:13:48 <oerjan> and yeah foldl is n^2 at least if it doesn't fuse, i'm not sure nowadays...
00:15:43 <myname> so, what is the advantage of using that function composition thingie instead of concat' = concat . reverse
00:16:15 <myname> you could just do foo:bar:[], couldn't you?
00:16:23 <elliott> if you just want concat you can write foldr (++) []
00:16:28 <elliott> i assumed you were doing something more complicated than that
00:17:45 <myname> i am not quite sure, i have to take a look on how often i actually have to look into that list, but as far as i know it shouldn't happen that much
00:18:11 <oerjan> @tell b_jonas <b_jonas> but the way it is, it's not even turing complete, because there are only finitely many valid eodermdrone programs <-- you're jumping straight into our discussion of what TC means, i see
00:26:06 -!- callforjudgement has joined.
00:29:04 -!- ais523 has quit (Ping timeout: 244 seconds).
00:29:18 -!- callforjudgement has changed nick to ais523.
00:42:46 <oerjan> there appears to be a boily shortage
00:44:26 -!- PinealGlandOptic has quit (Quit: leaving).
00:56:09 -!- hjulle has quit (Ping timeout: 252 seconds).
01:00:50 -!- ProofTechnique has joined.
01:05:09 <oerjan> *sigh* hit the power button again
01:05:24 <oerjan> fortunately i restarted fast enough it didn't disconnect
01:05:52 <oerjan> i already changed it from "reboot" to hibernate, i think i shall change it to "do nothing"
01:07:21 <oerjan> after all, i never really use it anyway; whenever i _actually_ reboot it's to restart immediately.
01:10:01 -!- MDude has joined.
01:12:19 -!- Phantom_Hoover has joined.
01:27:38 -!- ais523 has quit (Ping timeout: 265 seconds).
01:38:05 -!- CADD has quit (Remote host closed the connection).
01:38:55 -!- merdach has quit (Quit: WeeChat 1.1.1).
01:40:04 -!- bb010g has quit (Quit: Connection closed for inactivity).
01:43:37 -!- tromp has quit (Ping timeout: 255 seconds).
01:51:44 -!- tromp has joined.
01:53:34 -!- GeekDude has joined.
02:03:46 -!- PinealGlandOptic has joined.
02:18:35 -!- MDude has changed nick to MDream.
02:23:49 -!- devdean1 has joined.
02:33:57 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
02:36:08 -!- MDude has joined.
02:38:07 -!- MDream has quit (Ping timeout: 250 seconds).
02:39:51 <lambdabot> src <id>. Display the implementation of a standard function
02:40:23 <lambdabot> Source not found. Do you think like you type?
02:42:20 -!- arjanb has quit (Quit: zzz).
02:43:28 -!- MDude has changed nick to MDream.
02:44:30 -!- ProofTechnique has joined.
02:47:59 <lambdabot> 112*total 93*private 9*#haskell-blah 5*#esoteric 4*#haskell 1*#scannedinavian
02:52:28 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
02:56:01 <oerjan> ok girl genius, _that_ was unexpected.
02:58:13 <oerjan> so much for time travel being involved.
02:58:24 -!- kapil___ has joined.
02:58:47 <oerjan> (it'll still be involved _elsewhere_, presumably.)
03:01:22 <lambdabot> *** "esoteric" wn "WordNet (r) 3.0 (2006)"
03:01:22 <lambdabot> adj 1: confined to and understandable by only an enlightened
03:01:22 <lambdabot> inner circle; "a compilation of esoteric philosophical
03:10:23 -!- bb010g has joined.
03:59:04 -!- PinealGlandOptic has quit (Quit: leaving).
04:27:11 -!- merdach has joined.
04:41:36 -!- _1_lyndero3 has joined.
04:42:19 -!- _1_lyndero3 has quit (Remote host closed the connection).
04:49:55 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
04:58:40 <Sgeo> What's the worst that could happen if I upload this music to YouTube?
05:05:54 <Sgeo> This one sounds like someone really playing a real piano... and making mistakes :/
05:18:42 -!- Patashu has quit (Remote host closed the connection).
05:19:07 -!- Patashu has joined.
05:23:05 -!- bluckbot has joined.
05:25:46 <Sgeo> http://runt-of-the-web.com/amazingly-unhelpful-fun-facts
05:27:50 <Sgeo> http://horseysurprise.tumblr.com/
05:34:18 <oerjan> Sgeo: that tumblr site not only has too small text, but it neutralizes attempts to zoom it. i suggest killing it with fire.
05:37:09 <oerjan> also, agreeing with me on this is mandatory hth
05:37:34 * oerjan may have waited a bit too long to eat
05:40:10 <Sgeo> *attempts to neutralize attempts to zoom it
05:40:37 <oerjan> well in IE it succeeds.
05:41:47 <Sgeo> You just made me open IE. I shall not forgive you.
05:42:27 <Sgeo> Fails for me in IE too. Where fail is defined as "not as effective as perfect neutralization would be"
05:43:01 <oerjan> i define "neutralization" as "prevents getting it to an actually readable size" hth
05:43:51 <Sgeo> I was able to increase the size, slower than I should have been able to, but it still increased each time
05:44:11 <Sgeo> Besides the images are usually the important part
05:44:34 <Sgeo> And it's the images where zoom isn't working well :/
05:44:37 <oerjan> um ok i actually meant the image hth
05:45:08 <oerjan> stupid geeks taking blathering literally
05:45:12 <Sgeo> CLicking the image then clicking the image works for me
05:45:35 <oerjan> i think you didn't read the part where i said agreeing was mandatory hth
05:46:09 <oerjan> 's ok my blood sugar should return to normal soon. unless it overshoots again.
05:47:46 <pikhq> Diabetes, or just bad regular eating habits?
05:48:24 <oerjan> well i somehow waited for 8 hours before eating
05:49:24 <oerjan> diabetes runs in the family but i didn't have it when tested two years ago.
05:50:07 <pikhq> Some point I might need to get tested for it.
05:50:18 <pikhq> Turns out it runs in the family for me as well.
05:50:29 <oerjan> ("somehow" ~ "started trawling a webcomic archive for an old strip")
05:50:59 <oerjan> never found it. maybe i'm imagining the strip, or have misremembered the character involved
05:52:01 <Sgeo> What comic what strip?
05:52:17 <Sgeo> Not that I'm especially likely to know personally
05:52:20 <oerjan> yet another fantasy gamer comic
05:52:29 -!- kapil___ has quit (Quit: Connection closed for inactivity).
05:53:15 <oerjan> the current act reintroduces some rather old characters that haven't been seen in a while
05:54:26 <oerjan> i thought there was a strip where dewcup met those ranna worshippers in arachne's dungeon
05:54:43 <oerjan> except i'm not sure if they had shown up yet
05:54:59 <oerjan> so i think it may have been someone other than dewcup
05:56:15 * oerjan doesn't expect anyone else here to know, anyway.
05:56:26 <Sgeo> Try /r/tipofmytongue ?
05:56:27 -!- CrazyM4n has joined.
05:56:40 <Sgeo> Or any comic-specific forums
05:57:17 <oerjan> hm i was going to check which arc the worshippers showed up in
05:58:45 <oerjan> it's moved servers so the whole archive has been reorganized
06:09:06 <Sgeo> "The word 'onomatopoeia' is also an onomatopoeia because it's derived from the sound produced when the word is spoken aloud."
06:10:45 <oerjan> ah i was confusing dewcup with jone.
06:31:02 -!- CrazyM4n has quit (Remote host closed the connection).
07:14:54 -!- kapil___ has joined.
07:52:14 <oerjan> int-e: well that was an unexpected girl genius development.
07:53:04 <int-e> was it now, I haven't even read Wednesday's GG yet.
07:55:29 <oerjan> i suppose someone might have predicted it.
07:57:42 <int-e> Well it surprised me.
07:58:00 <int-e> King of all cats... I remembered that.
08:14:36 <int-e> but I don't recall Krosp being explicitly connected to Dr. Vapnoople
08:20:27 <oerjan> i tried looking up some of that earlier
08:21:23 <int-e> ttp://girlgenius.wikia.com/wiki/Krosp_I is helpful, but the story of Krosp's creation didn't reveal the creator
08:22:05 <oerjan> i looked at wikia too and got frustrated because so many references were to the novels
08:24:24 <oerjan> well krosp is seen hiding when she first meets dr. dim
08:25:28 <int-e> but he's been hiding on the airship ever since his creation, so all I read into that is that there was some convenient hiding place nearby
08:27:08 <int-e> anyway it doesn't really matter; even if it has been mentioned before I probably wouldn't have remembered it
08:27:28 <oerjan> http://www.girlgeniusonline.com/comic.php?date=20040319
08:39:49 -!- CrazyM4n has joined.
08:47:42 -!- CrazyM4n has quit (Remote host closed the connection).
08:59:26 -!- CrazyM4n has joined.
09:13:26 -!- CrazyM4n has quit (Quit: sleep).
09:15:14 -!- cpressey has joined.
09:26:26 -!- vanila has joined.
09:34:16 <vanila> 0000000 0583 8000 000b eb01 00f7 0000 b002 1bad
09:34:16 <vanila> 0000010 0003 0001 4ffb e451 000c 0000 0000 0000
09:34:16 <vanila> 0000020 0000 0000 0000 0000 0000 0000
09:34:35 <vanila> http://i.imgur.com/VX4TjY0.png
09:45:19 <cpressey> i assume that's a hexdump of the bootblock?
09:45:50 <vanila> yeah and boot it with GRUB
09:46:20 <vanila> itsj ust a multiboot header + loop that increments some address
09:46:38 -!- TieSoul_ has joined.
09:46:44 <vanila> what I can't figure out how to do is boot it on a real computer :\
09:46:55 <vanila> i tried usb drive but it doesnt work
09:47:32 <cpressey> i don't know anything about multiboot
09:48:20 <cpressey> in fact, i don't think i've ever gone beyond booting from a floppy
09:49:02 -!- TieSoul has quit (Ping timeout: 245 seconds).
09:51:45 <oerjan> cpressey: we had a discussion here at one time about System F / second order logic, you can look at that as a complexity class if you want and it contains ackermann and even the goodstein sequence
09:52:29 <oerjan> (someone here wrote up an implementation of the latter in non-recursive rank-N haskell, which is basically equivalent)
09:53:31 -!- Phantom_Hoover has joined.
09:55:05 <cpressey> oerjan: you don't know how much it freaked me out to see you talking about webcomics and killing webpages with fire, in the logs
09:55:56 <oerjan> no, it was me, but still, huh?
09:56:20 <oerjan> (most webcomics i read i learned about in this channel)
09:56:21 <vanila> i just booted it for real
09:56:34 <oerjan> myndzi: psst your script is running twice or something
09:57:01 <oerjan> it's been noticed before
09:57:46 <oerjan> cpressey: most webcomics i've followed i learned about via this channel
09:58:21 <oerjan> cpressey: my huh is because i don't know why that freaked you out.
09:59:10 <oerjan> as someone who has recently become a lot more dependent on zooming webpages, it irritates me a lot when they make it hard.
10:00:48 -!- Korok has joined.
10:01:05 -!- Korok has left.
10:02:26 <fizzie> Oh, by the way, a fungot status update. Our Internet arrives on March 3, but I'll be out of the country from March 2 to 13, so I have a fungot ETA of maybe mid-March.
10:02:30 <cpressey> oerjan: never mind -- I think there's something wrong with me.
10:03:06 <oerjan> fizzie: you don't happen to have another way of making HackEgo join a channel, do you? it's actually connected...
10:03:25 <fizzie> I have one but it's convoluted.
10:03:39 <oerjan> cpressey: i'd give you the standard lewis carroll quote but HackEgo isn't here...
10:04:08 -!- devdean1 has quit (Quit: Leaving.).
10:05:21 <cpressey> oerjan: Anyway, I have to just conclude that complexity theorists don't care about the upper reaches
10:05:44 <cpressey> I can almost hear them yawn when it gets bigger than NP
10:05:45 <oerjan> cpressey: that seems likely
10:06:14 <oerjan> nah that's not true, PSPACE and EXP get a fair workout don't they
10:06:41 <cpressey> That's true, I've seen them be interested in PSPACE at least
10:08:17 <oerjan> although you could maybe make a case for "only classes not known to be larger than NP"
10:08:45 <cpressey> Not that anyone here would necessarily know offhand, but: like Ackermann is sort of the poster-child for "not in PR", are there any obvious candidates for "not in <these bigger ones defined by 2nd-order-logic ad/or PR-functionals>"?
10:08:51 <cpressey> I mean, even guesses would be fine
10:09:01 <cpressey> I'd just be a little irked if there are no "natural" examples
10:09:13 <cpressey> Not that Ackermann is particularly natural
10:09:19 <cpressey> But compared to some things, it is
10:10:21 <cpressey> I forgot, I don't actually care.
10:10:42 <cpressey> Nihilism is harder than it looks, isn't it
10:12:39 * oerjan whistles 4'33'' innocently
10:12:44 <cpressey> I just get the feeling that there's no point in me trying to understand these things, because I'm sure I never will. This grates against the fact that they fascinate me.
10:14:02 <oerjan> i think that when you look at very small or very large complexity classes things tend to get intertwined with logic questions
10:14:54 <cpressey> It does seem reasonable, once you get above EXP and friends, to stop treating it as complexity and start treating it as computability
10:15:26 <vanila> what is the thing being investigated?
10:15:51 <fizzie> Okay, laptop is up and keyboard is connected to phone.
10:16:02 <fizzie> Next, I need to something something something.
10:16:18 <oerjan> i'm not sure i know any problems between goodstein/hydra things and the halting problem/busy beaver stuff
10:16:35 <fizzie> What, there's no nc on Android shell.
10:16:42 <cpressey> vanila: algorithms that run a long, loooong, loooooooong time, but we still know that they eventually finish <-- very approximate way to describe it
10:17:08 <vanila> that's a really interesting topic
10:17:13 <fizzie> I can push the SSH key from the laptop to the phone (which is the only thing Internetted here), but I'm not sure how to get it to somewhere else.
10:17:21 <cpressey> oerjan: at least I know about the hydra, but I'll have to refresh myself on goodstein
10:17:23 <vanila> it can get a bit philosophical
10:17:37 <oerjan> cpressey: i think they're sort of on the same level
10:18:19 <oerjan> both are about things that can grow a lot in size but always shrink as ordinals
10:18:49 <cpressey> yeah as soon as you get to the point of needing transfinite induction to prove that it terminates... sheesh
10:19:13 <cpressey> ok, i can see why this is not a well-trodden area
10:20:42 <cpressey> I'm probably overthinking things, too
10:22:26 <fizzie> I don't get it. I pushed the files to Download/ but they're not visible there.
10:22:39 <vanila> A cool thing about the dependent type theory as opposed to something like charity is you can write programs that take a very very long time to halt
10:22:44 <fizzie> Maybe the storage indexer thing doesn't refresh from just an adb push.
10:23:26 <fizzie> Or maybe the "Downloads" list and the Download/ folder aren't a 1:1 thing at all.
10:27:14 -!- Koen_ has joined.
10:27:48 <fizzie> I think I might have got it
10:29:49 <fizzie> The server is being really really slow.
10:30:35 <oerjan> but not so slow that HackEgo is pinging out...
10:30:56 -!- HackEgo has joined.
10:31:07 <fizzie> And it was stupidly complicated.
10:31:37 <fizzie> It took maybe 5 seconds to reply to simple shell commands, so I don't expect the umlbox stuff will run very fast.
10:32:13 <oerjan> maybe someone is DOSing the wiki. it could happen.
10:32:57 <fizzie> I could have a look at network traffic, but I need some breakfast first.
10:32:59 <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."
10:34:43 <cpressey> http://catseye.tc/installation/Cheshire_Text <-- but you need to read the whole thing, top to bottom, for it to work
10:38:56 <int-e> well that went rather more quickly than I expected... http://int-e.eu/~bf3/tmp/cheshire.png
10:43:23 <int-e> (Hmm, couldn't the same effect be achieved by a CSS transition?)
10:45:14 <vanila> I thought: a brainfuck OS
10:45:25 <vanila> the kernel is in assembly and has interrupts for each of <, >, +, -, ., ...
10:45:48 <vanila> so you can compile a brainfuck program into syscalls.. but then someone could still use registers and things
10:46:59 -!- TieSoul_ has changed nick to TieSoul.
10:51:46 <Jafet> If you feel overwhelmed, go with minor-closed graph classification, which takes only cubic time.
10:52:02 <cpressey> vanila: I like the idea of one syscall per BF instruction for some reason
10:52:16 <cpressey> it has a certain terrible elegance
10:52:23 <cpressey> i like things with a certain terrible elegance
11:02:40 <cpressey> speaking of which, I should write that recursive-{de,a}scent {parse,generato}r I've been meaning to
11:17:49 -!- bluckbot has quit (Remote host closed the connection).
11:18:42 -!- bluckbot has joined.
11:22:17 <cpressey> oerjan: I am going to steal that term if you don't mind
11:22:27 <cpressey> at least in this implementation
11:23:13 <oerjan> this smells of recognition
11:23:50 -!- hjulle has joined.
11:29:04 -!- Patashu has quit (Ping timeout: 255 seconds).
11:31:11 <cpressey> done. can anyone recommend a pastebin?
11:32:07 <cpressey> because I just know you are all pastebin connoisseurs
11:34:29 <cpressey> https://gist.github.com/cpressey/dd3f63eda91b33e429fa
11:35:03 <cpressey> now you may all tell me that I should have done it with monads, dependent types, and CSS transitions
11:39:14 <int-e> cpressey: are you going to ask for justifications of such claims?
11:39:23 <int-e> if not I'd be happy to oblige.
11:39:44 <FreeFull> cpressey: I sometimes use dpaste
11:44:06 <cpressey> int-e: no, I'll just say "oh, I know, I know" like Mrs. Fawlty on the phone
11:44:52 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
11:49:17 <oerjan> definitely monads yeah
11:54:38 <oerjan> int-e will have to take care of the CSS transitions and elliott the dependent types
11:58:57 -!- SopaXorzTaker has joined.
12:00:58 -!- oerjan has quit (Quit: leaving).
12:04:06 <elliott> what's going on i just woke up
12:04:32 <elliott> for the sake of fantasy i would like you all to believe that i have irc pings hooked up to an alarm
12:08:59 <int-e> or do you mean CTCP pings, hmm
12:09:35 <elliott> every time i am talked to i have to hit the alarm off. please be considerate and leave me alone forever
12:11:40 <int-e> elliott: I think you got the reverse psychology idea wrong.
12:12:18 <int-e> You *can* go around explaining a new toy to children, then forbid them to use it. But you shouldn't be surprised if they end up playing with them anyway.
12:12:57 <elliott> i feel like the utter certainty all of you would spend hours setting off my alarm were it real is why this channel sucks so much
12:13:55 <elliott> cpressey: this is cute. there is work on this kind of thing in The Literature, i think
12:14:03 <elliott> parser combinators that go both ways, etc.
12:16:02 <int-e> hmm, "both ways" http://hackage.haskell.org/package/boomerang
12:17:15 <elliott> right. there's like, an Actual Name for it and Actual Papers. maybe "reversible grammar" or something, I don't know.
12:17:27 <elliott> you get things like, instead of fmap taking a function it takes an isomorphism
12:17:34 <elliott> one function for each direction
12:17:42 <elliott> cpressey: am I academising sufficiently here?
12:29:09 -!- SopaXorzTaker has quit (Ping timeout: 252 seconds).
12:32:47 <vanila> <elliott> for the sake of fantasy i would like you all to believe that i have irc pings hooked up to an alarm
12:32:58 <vanila> I have done this in the past & suspect someone else does this
12:33:30 <elliott> vanila: like a proper alarm or just making your computer make a lot of noise
12:33:35 <elliott> ideally it should be like, clockwork
12:33:59 <vanila> oh just the computer, but t woldnt be too hard with an adruino or something..
12:35:03 <cpressey> elliott: yes, thank you. i realize it is nothing very special, but i think it's cute too
12:37:10 <vanila> reversible parsing is very awkward
12:37:17 <vanila> parsing is not usually a bijection
12:37:27 <vanila> because of things like skipping whitespace, comments
12:37:48 <vanila> iits better to specify a parse as something that if you print it out and parse that you get the same thing
12:38:52 <elliott> on the other hand it's often kinda useful not to drop things like comments in an AST so you can do things like error reporting and code transformations without disturbing things like that (but it is awkward yeah)
12:43:44 <cpressey> maybe "a certain terrible elegance" that i referred to means "it suggests an algebra" because what is interesting me right now is, are there any operation-sets besides "parse" and "generate" that make any sense
12:44:11 <cpressey> i can only think of fairly contrived ones, and minor (relatively) variations on those two
12:44:51 <cpressey> "count terminals in grammar" is not exactly interesting
12:45:06 <elliott> the operations in http://matt.might.net/articles/parsing-with-derivatives/, maybe?
12:45:23 <elliott> (taking the derivative with respect to a token, deciding whether a grammar admits an empty string, etc.)
12:45:33 <elliott> probably not doable with the imperative recursive-descent style though so n/m
12:46:27 <cpressey> well, this code makes it abundantly clear that the RDP could be a passive data structure instead of a set of functions
12:46:30 <vanila> isnt empyness undecidable for CFG?
12:46:56 <vanila> so maybe it admits a notion of derivative too?
12:46:58 <cpressey> intersection of 2 being empty is, i thnk
12:47:12 <vanila> although that might let you determine equality which is undecidable..
12:47:33 <vanila> I guess there's no derivative for CFGs then
12:47:52 <elliott> vanila: that article is about derivative for CFGs
12:50:18 <vanila> i assumed it was about regex
12:50:39 <elliott> it's about using derivatives to parse arbitrary CFGs
12:54:56 <vanila> the trick is that the derivative is an infinite object
12:55:10 <vanila> so that stops you from being able to use it to determine equality
12:59:53 <cpressey> i remember coming across derivative of regular languages a few years ago; you can basically extend it to a kind of linear algebra, which is neat. didn't realize you could extend it to CFL's
13:00:13 <elliott> vanila: well, it's infinite if the original grammar is, I think
13:00:22 <vanila> because of left recursion
13:00:27 <elliott> well, no, not necessarily, sometimes it can be finite
13:10:43 <cpressey> "There's no backtracking in the algorithm." <-- for some reason that made me interrobang
13:16:59 <cpressey> i'm probably not understanding it entirely correctly, but it's like the memoization and fixed-point parts avert any possibility of backtracking, early on
13:17:21 <vanila> have you looked at the regex version of this?
13:17:35 <vanila> you can use derivatives of regexes to build a DFA
13:28:43 <cpressey> vanila: yes, in a book, probably about 8 years ago :/
13:29:04 -!- Tritonio has quit (Ping timeout: 252 seconds).
13:29:05 <cpressey> the linear alg thing was what stuck in my mind
13:34:53 <cpressey> the no-backtracking property might mean it'd be good for parsing streams (e.g. data over a socket) too
13:56:30 <cpressey> at the end it almost sounds like they want to add some "hash-consing" to it too :)
14:19:31 -!- Lymia has quit (Ping timeout: 265 seconds).
14:22:39 -!- SopaXorzTaker has joined.
14:23:36 -!- SopaXorzTaker has quit (Max SendQ exceeded).
14:29:52 -!- cpressey has quit (Remote host closed the connection).
14:33:55 -!- cpressey has joined.
15:01:55 <cpressey> @tell ais523 wait, doesn't it have to be the other way around? You need a mapping (O(n) or otherwise) from TMs to programs in language X, for X to be TC
15:02:55 <cpressey> If you have a mapping from at least 1 universal TM to at least 1 program in language X, X is fancy-L-complete or whatever
15:04:27 <cpressey> I don't see a lot of "naturally occurring" "compiler mappings" like these that exceed O(n log n), but it might be nice to have some contrived examples
15:11:25 <cpressey> maybe some esolang where programs have to be arranged "just so" and a compiler from-TM-to-it has to take that into account when constructing the target program
15:12:04 <vanila> you have to fit the commands into a tesselation or something, so compiling to it requires solving a NP hard puzzle
15:13:14 <cpressey> vanila: exactly, something like that
15:13:27 <cpressey> heh, there are two esolangs called "Numberwang"
15:16:28 -!- SopaXorzTaker has joined.
15:17:27 <cpressey> well, i can't find anything on esolangs.org that fits the bill offhand, but that thing's huge now :)
15:18:15 <cpressey> a lot of them might fit the bill, if we knew more about them :)
15:20:04 -!- ProofTechnique has joined.
15:20:25 <elliott> who needs anything like that when you have masterpieces like https://esolangs.org/wiki/Pig
15:21:07 <elliott> fizzie: is esolangs.org HSTS yet
15:21:53 <FreeFull> Where are the languages based on qubits?
15:24:25 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
15:27:58 <cpressey> NP-hard might still = P, who knows, so I'd prefer something EXPTIME-complete
15:28:45 <cpressey> I should try to remember that I don't really care before I actually try to devise something like this
15:29:52 <cpressey> FreeFull: there are some: https://esolangs.org/w/index.php?search=qubit&title=Special%3ASearch
15:30:22 -!- SopaXorzTaker has quit (Quit: Leaving).
15:30:41 -!- MDream has changed nick to MDude.
15:37:16 -!- SopaXorzTaker has joined.
15:37:31 -!- boily has joined.
15:38:58 <Phantom_Hoover> cf. http://upload.wikimedia.org/wikipedia/commons/a/a0/P_np_np-complete_np-hard.svg
15:39:01 <FreeFull> NP-hard includes everything that is outside P, doesn't it?
15:39:47 <cpressey> An EXPBLARGL program consists of a description of a Turing machine, a number k, and a Befunge program. To run an EXPBLARGL program, first you determine if the given TM halts in k steps. If it does, you run the Befunge program. If it doesn't, you run 99 bottle of beer on the wall, or something.
15:40:15 <cpressey> and, uh, k must exqual the size of teh Befunge program
15:40:35 <cpressey> no, the compiler can always just pick easy TMs
15:40:49 <cpressey> maybe the Befunge program has to double as the TM description
15:41:10 <cpressey> and the only reason I chose Befunge is because I was going to choose brainfuck but then Phantom_Hoover walked in
15:41:31 <cpressey> Phantom_Hoover: I thought NP-hard meant >= NP-complete
15:42:51 <cpressey> so if x is NP-hard it might be NP-complete which might (WHO KNOWS) be in P
15:43:05 <Phantom_Hoover> for a concrete example, the halting problem is NP-hard but not in NP
15:43:28 <cpressey> Phantom_Hoover: yes but "NP-hard but not in NP" is not the same as "NP-hard"
15:43:32 <vanila> http://upload.wikimedia.org/wikipedia/commons/a/a0/P_np_np-complete_np-hard.svg NP complete is a lemon
15:44:18 <elliott> looks more like an american football
15:44:19 <Phantom_Hoover> cpressey, oh, were you talking about individual problems rather than the classes as a whole?
15:44:54 <cpressey> Phantom_Hoover: yes, I'm trying to make a contrived language to which you can't compile a TM in O(n log n) because ais523
15:46:27 <cpressey> I'm not sure that matters, given the diagram vanila linked to, but I don't really care
15:49:19 -!- GeekDude has joined.
15:50:52 -!- SopaXorzTaker has quit (Quit: Leaving).
15:51:10 -!- SopaXorzTaker has joined.
15:51:37 -!- SopaXorzTaker has quit (Remote host closed the connection).
15:51:38 <cpressey> unefunge or blank would be simpler
15:52:02 <cpressey> EXPBLARGL as defined is only P-complete b/c the length is effectively given in unary
15:53:28 <cpressey> and, sorry, I'm going to use brainfuck because it's convenient. besides, it will give Phantom_Hoover something to blog about
15:54:11 -!- SopaXorzTaker has joined.
15:54:13 <cpressey> an EXPLBARGL program is a brainfuck program except first you interpret it as a base-8 number and call than n and then you only run it if you determine it does *not* halt in n steps
15:55:02 <cpressey> ok, EXPLBLARGL was actually a typo there, but that's fine
15:55:09 <int-e> cpressey: regarding the complexity of compiling stuff to Turing machines, how do you represeny Turing machines? If an n state Turing machine requires O(n log n) data then that should also be a lower bound for a compiler.
15:55:37 <FreeFull> cpressey: How about some sort of incremental XOR?
15:58:15 <MDude> A turing machine requires potentially unbounded memory, depending on what is to be compiled.
15:58:57 <MDude> Though I don't know if that's what you're asking.
15:59:09 <cpressey> int-e: well, the "obvious" way to me to describe a TM has length O(nm) where n is # states and m is # symbols. but if ais523 is going to allow some tricky compression, I dunno
15:59:46 <cpressey> MDude: yeah, that's not a problem, I'm only considering compiling TMs to other languages that also have unbounded storage
16:01:34 <int-e> cpressey: Ah I was thinking about a fixed number of symbols. How do you avoid the log n factor?
16:02:30 <vanila> what about that kthing where you write an interpreter for another lagnuage, then provide your code as data
16:03:06 <vanila> the interpreter is a fixed number of characters and the data can probably be at worst a unary encoded number
16:03:15 -!- SopaXorzTaker has quit (Ping timeout: 246 seconds).
16:03:17 <cpressey> int-e: I don't see any need to avoid it myself. I think it's ais523 who's aiming for O(n). I'm just observing there aren't many cases where you need a compiler that is more than O(n log n)
16:03:24 <cpressey> the log n is for the symbol table
16:04:46 <MDude> Wait, what were you asking about the impossibility of?
16:04:59 <MDude> Compiling things to turing machines, or compiling turing machines to other things?
16:05:23 <cpressey> MDude: compiling TMs to other things and needing more than O(n log n) time to do it
16:05:28 <int-e> vanila: Which shows that you need to be precise with the rules. Is providing extra data on the tape allowed? Of course you can prefix the interpreter by code that initialises the tape but then you /may/ run into issues with encoding the state numbers in O(1) symbols.
16:06:55 <int-e> though it's easy to devise encodings for TMs where this works (for example you can encode references to the "next" state by a fixed string)
16:07:07 <cpressey> as a (bad) example, compiling a TM to a Perl program shouldn't require more than O(n) time, where n is the length of the TM description (and yes, I'm assuming things like, the TM description is given as a table, and it starts with a blank tape)
16:09:33 <cpressey> emit prelude; for each transition in table { emit a bit of Perl with if statements and goto statements }; emit postlude /* probably not even needed here */
16:09:37 -!- TieSoul_ has joined.
16:10:07 <cpressey> prelude defines a global variable for the tape and whatnot
16:10:31 <int-e> I'd emit a TM interpreter followed by the TM description
16:10:47 <int-e> cheating? maybe, but where exactly do you draw the line?
16:10:50 <vanila> maybe the program oculd be encrypted, so to compile to something eslseyou have to decrypt it
16:10:55 <vanila> and that could require brute force
16:11:07 -!- TieSoul has quit (Ping timeout: 245 seconds).
16:11:18 -!- TieSoul_ has changed nick to TieSoul.
16:11:29 <vanila> the interpreter for the program would have to do the same decryption work of course, so it wouldnt' be a efficient programming language
16:12:17 <cpressey> int-e: not cheating at all; in fact that's O(n) too. question is, is there any target language where you can't do it in O(n log n), even given tricks like that
16:12:42 <cpressey> s/where/into which/ maybe for clarity or maybe that makes it even less clear
16:14:00 <int-e> cpressey: Sure, take some enumeration of Brainfuck programs; encode the n-th program by the n-th fibonacci number in unary.
16:15:21 <int-e> But that's very artificial. I don't know of any natural restriction on a programming language with such an effect.
16:15:39 <int-e> Maybe compiling to a 2-counter Minsky machine would do the trick
16:16:36 <int-e> but probably that won't help either (modulo the encoding-dependent log(n) factor that I already mentioned for Turing machines)
16:17:03 <cpressey> int-e: artifical or not, that does seem to do the trick
16:20:09 <cpressey> here's to pathological, conjecture-defeating constructions!
16:22:05 <elliott> cpressey: have you considered "Eightebed II" as a name for whatever this is
16:22:39 <cpressey> elliott: er well no, as it seems so, y'know, different
16:22:49 <cpressey> not really a scion of the House of Eightebed, as it were
16:23:18 <cpressey> not that that matters much, I grant
16:23:53 <elliott> I was just reacting to "pathological, conjecture-defeating constructions"
16:24:51 <cpressey> You've read "Counterexamples in Analysis" and "Counterexamples in Topology", now comes "Counterexamples in Computability"!
16:25:33 <int-e> hum. "Beginning May 1, 2015, new Mac apps and app updates submitted to the Mac App Store may no longer use garbage collection, which was deprecated in OS X Mountain Lion. Instead, migrate your apps to Automatic Reference Counting"
16:26:23 <cpressey> first they tell you what programming language you must use. then they tell you what algorithms you must use.
16:27:18 <cpressey> "Beginning May 30, 2015, new Mac apps must not use Bubble Sort"
16:27:27 -!- SopaXorzTaker has joined.
16:28:11 <elliott> pretty sure that only means the objective-c garbage collector >_>
16:28:13 <int-e> Let's mandata Fibonacci heaps for all implementations of Dijkstra's algorithm...
16:28:19 <elliott> I'd be kind of surprised if they rejected, like, boehm
16:29:14 -!- boily has quit (Quit: IMPLODING CHICKEN).
16:40:55 <cpressey> A brainfuck-like language that only runs the program if it cannot find a shorter program that outputs the same result in less than 2^n steps
16:43:20 <cpressey> but, hey, Kolmogorov. can't beat Kolmogorov
16:46:42 <int-e> and it becomes trickier if the program gets inputs
16:47:10 <elliott> one time I looked at a book about kolmogorov complexity and it cited a person in this channel all over the place
16:48:25 <cpressey> elliott: did it cite them by nick?
16:48:46 <elliott> cpressey: insofar as their nick is -- well, let's not speak too loudly
16:50:38 -!- adu has joined.
16:51:06 <elliott> yes, of course, it was you
16:53:44 <int-e> oh well, this was fun. http://int-e.eu/~bf3/v6/
16:54:16 <vanila> you assembled it scrambed??
16:54:38 <int-e> mostly. only the corners need to be correct.
16:54:56 <vanila> how do you know it would be a solvable state
16:55:14 <int-e> The corners are the only thing that mattes at even sizes.
16:55:27 -!- not^v has joined.
16:55:43 <int-e> For odd sizes, you need to be careful with the center pieces of the edges as well.
16:55:52 <b_jonas> I'm still thinking on this Fast Fourier stuff. it's very interesting.
16:55:57 <elliott> int-e: oh ~bf3 probably isn't a reference to brainfuck...
16:56:01 <vanila> what about it b_jonas?
16:56:06 <int-e> elliott: nor battlefield
16:56:25 <elliott> honestly i don't understand the mechanism inside rubik's cubes
16:56:27 <int-e> elliott: It was my account name at my first university.
16:56:29 <elliott> their rotational abilities are a mystery to me
16:56:38 -!- boily has joined.
16:56:40 <elliott> please don't tell me. i love the mystery
16:56:43 <b_jonas> elliott: which one? the 3x3, or some different size?
16:56:47 <int-e> elliott: Have you ever taken apart a 3x3x3 one?
16:56:59 <elliott> no. honestly I've had very little interactions with them full stop
16:57:14 <elliott> I've probably tried to solve one, like, five times.
16:57:22 <b_jonas> elliott: the best way to understand it is to take a 3x3x3 apart then
16:57:23 <olsner> elliott: there are, like, twisty-turny things inside it
16:57:47 <b_jonas> vanila: just how the algorithms work in detail and when it's worth to use what variant
16:58:00 <b_jonas> maybe I should try to implement some as a test
16:58:13 <int-e> the 3x3x3 one is actually really simple. There are exactly as many moving parts as you can see (thinking of the cross in the middle as fixed)
16:58:44 <olsner> I encountered a rubik's cube that had differently shaped tiles instead of different colors, that thing really looked like it shouldn't spin at all
16:58:48 <elliott> how does the complexity of the internals scale with the size
16:59:09 <b_jonas> olsner: do you mean the silver mirror cube in particular, or some other variant?
16:59:27 <int-e> I got myself a https://en.wikipedia.org/wiki/Megaminx recently.
16:59:38 <b_jonas> elliott: hard to tell, because they can't do it for arbitrarily large size, and I think there's more than one mechanism for some large sizes
16:59:52 <b_jonas> funnily the 3x3x3 is the most natural
16:59:58 <elliott> olsner: wow this is terrifying
17:00:00 <b_jonas> because of what int-e says
17:00:06 <olsner> actually it might be *easier* to figure out how it works from a silver mirror cube
17:00:12 <vanila> I can't solve the rubiks cube :(
17:00:20 <b_jonas> it's a bit harder to solve than the ordinary cube,
17:00:27 <vanila> I tried to solve it for a long time but I didn't figure it out
17:00:53 <vanila> people who have solved it: did you look up a guide or get told what to do or figure it out youreslf?
17:00:58 <b_jonas> but I wish I had had it when I was in high school, because it's possible to solve it without looking, so I could have solved it under the desk during a class while pretending to listen to the teacher
17:01:16 <b_jonas> vanila: looked up guides, and figured out a few changes myself
17:01:41 <b_jonas> but I haven't practiced much so I still solve it somewhat slowly (and ever more slowly as I forget)
17:01:49 <int-e> vanila: I looked up guides, forgot half of them, discovered a few combinations myself, learned some from other people ... and by now I know enough to be able to solve it from scratch /in principle/.
17:02:07 <vanila> I think I could write a comupter program to solve it
17:02:18 <b_jonas> also, I'm using the third method to solve it so far
17:02:26 <b_jonas> I first learnt a very bad method
17:02:29 <int-e> (Meaning I know enough theory to solve pretty arbitrary permutation puzzles.)
17:02:50 <b_jonas> by the way, there's a channel for the rubik's cube on, um, probably freenode, let me check
17:03:13 <vanila> once I tried to join the twistypuzzles forum
17:03:19 <vanila> they seem kinda weird :/
17:03:24 <int-e> (Or, failing that, using GAP to do it for me)
17:03:30 <vanila> they dont like new members
17:06:08 -!- SopaXorzTaker has quit (Remote host closed the connection).
17:06:18 <vanila> I wonder if i can solve the rubiks cube if i keep trying
17:06:30 <vanila> the thing is, the closer you get to solved.. the less freedom you have to solve it
17:06:50 <vanila> so unless it magically falls into place near the end you might as well scramble it randomly and start again
17:07:00 <int-e> vanila: the trick is to find combinations that affect as few cubes as possible.
17:07:32 <vanila> http://www.telegraph.co.uk/news/newstopics/howaboutthat/4217732/Rubiks-Cube-finally-solved-after-26-years-by-avid-fan.html
17:07:51 <int-e> Conjugates and commutators work pretty well.
17:08:07 <elliott> Long-suffering wife Jean, 47, said the cube has frequently put a strain on their marriage, causing blazing rows between the pair.
17:08:46 <elliott> Ray Hodgkin of the governing body for Rubik's Cube competitions, the World Cube Association (WCA), said: "I think this is definitely the longest it has ever taken someone to complete a Cube.
17:09:34 <vanila> Emacs Pinky and Cubist's Thumb
17:10:04 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:10:45 -!- cpressey has quit (Ping timeout: 252 seconds).
17:10:56 <elliott> it's kind of inspiring to me that I just have to achieve something really, really slowly to get on the news
17:12:30 -!- boily has quit (Quit: TAGGED CHICKEN).
17:14:01 <b_jonas> elliott: yeah. there's a joke about that but it doesn't work so well in English: an <approperiate target> says he's achieved a record because he's completed a jigsaw puzzle in three years, when its packaging says [for ages] over six years
17:14:14 <int-e> elliott: I wonder if we could do this with a 20 pieces puzzle (with a staggering number of 2675004047229796708138352640000 possibilities (20! placements * 4^20 orientations))
17:15:58 <int-e> (That's more possibilities than the Rubik's cube has.)
17:18:17 <b_jonas> by the way, if you like permutation puzzles in general, I recommend http://www.jaapsch.net/puzzles/
17:18:43 <vanila> I like oscars channel on youtube
17:19:18 <vanila> https://www.youtube.com/user/OskarPuzzle/videos
17:29:11 <myname> another haskell: so... i want to make read for an enum based on a simple char matching. any examples that is not this oversized tree thingie? i really just need to do "x" -> Foo
17:30:00 <vanila> case str of "x" -> Foo ?
17:31:10 <myname> yeah, my problem is the Read class
17:31:25 <vanila> well just call this something else than read
17:31:28 <myname> as far as i understand you cannot just simply write a read function
17:31:34 <vanila> you can do that, but dont
17:36:54 -!- ais523 has joined.
17:37:57 -!- SopaXorzTaker has joined.
17:53:00 -!- cpressey has joined.
17:54:01 <cpressey> <elliott> is it superexponential
17:54:14 <cpressey> if it's not, we should invent one where it is, because that's a very entertaining thought
17:56:21 -!- not^v has quit (Ping timeout: 244 seconds).
17:56:48 -!- not^v has joined.
18:01:37 -!- not^v has quit (Ping timeout: 264 seconds).
18:07:55 -!- adu has quit (Quit: adu).
18:15:31 -!- ThisFalseReality has joined.
18:15:51 -!- ThisFalseReality has left.
18:18:55 <cpressey> yea, ThisFalseReality, this channel is not what you thought
18:19:24 <cpressey> is there a way to download all (or a years' worth of logs) in a tarball or eqv?
18:19:51 <cpressey> i want to grep them for a language name I proposed years ago
18:20:12 <cpressey> i don't remember the full name and I doubt any web search will let me search by part of name or regexp
18:20:33 <cpressey> i don't want to crawl codu or tunes but, if i have to, i guess i can
18:23:25 <cpressey> "Apache/2.2.22 (Debian) PHP/5.4.36-0+deb7u3 mod_ssl/2.2.22 OpenSSL/1.0.1e Server at tunes.org Port 80"
18:24:58 <elliott> and you'll get instructions in /notice
18:25:23 <cpressey> whoever runs tunes.org: you might want to think about upgrading your openssl
18:26:35 -!- boily has joined.
18:28:39 <cpressey> no rsync server on codu.org it seems
18:28:50 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:28:52 <elliott> well I have the logs up to 2014-09
18:28:58 <elliott> I can get them to you if you want
18:32:22 <elliott> by which I mean, three and a half minutes, approximately
18:33:24 <int-e> I've done crazy things like wget -c http://codu.org/logs/_esoteric/2015-02-{1,2,3}{0,1,2,3,4,5,6,7,8,9}{-raw,}.txt ever since the rsync server was disabled
18:33:49 <elliott> but for pre-2012ish stuff the codu ones are nice
18:54:09 <boily> just drank a potion of mut, and got three beneficial mutations. the RNG will punish me hard an soon...
18:57:49 -!- ProofTechnique has joined.
19:02:45 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
19:13:12 -!- boily has quit (Quit: BLOCK CHICKEN).
19:16:24 -!- devdean has joined.
19:18:25 -!- ais523 has quit.
19:18:37 -!- ais523 has joined.
19:26:10 -!- callforjudgement has joined.
19:27:15 <cpressey> 2010-09-14.txt:01:15:57: <cpressey> olsner: you should do that. and you should name it "Jonguilexiphonaugh"
19:27:54 <olsner> I haven't started on that project yet :)
19:28:22 <olsner> or, I have created the git repo for it, but it is still empty
19:28:42 -!- scarf has joined.
19:28:49 -!- ais523 has quit (Disconnected by services).
19:28:53 -!- callforjudgement has quit (Disconnected by services).
19:28:55 -!- scarf has changed nick to ais523.
19:36:52 <Koen_> sounds like a korean musical instrument thing
19:37:41 <cpressey> olsner: if you're still using it, then i won't be tempted to borrow it back, but it was really nice to recall just what it was
19:38:31 <cpressey> i have ideas and sketches that linger in a textfile in a repo that sometimes stay there for years before i do anything with them
19:38:57 <olsner> well, if you have a use for the name that might actually materialize, feel free to take it back :)
19:39:32 <cpressey> well, i discovered that simply grepping the logs for 'good name' reveals a treasure trove, so there's no shortage
19:40:37 <cpressey> i also have a bunch of names in the aforementioned textfile, and a bunch of chronically incomplete ideas, and so forth
19:42:03 <cpressey> slightly tempted to write up this kolmogorov-ais523-counterexample-thing, but i guess i already named it EXP[L]BLARGL anyway
19:42:05 <ais523> I rarely have trouble naming esolangs
19:42:40 -!- arjanb has joined.
19:42:54 <elliott> cpressey: just look at the deleted page list
19:43:01 <elliott> the entertaining titles were mostly from a few years ago
19:43:34 * int-e looks for http://esolangs.org/wiki/I_rarely_have_trouble_naming_esolangs but finds nothing
19:44:03 <cpressey> ais523: we seem to have blown some large holes in your "write byte #n in O(1) time" idea, btw. sorry.
19:44:17 <cpressey> i mean it's entirely possibly i don't understand exactly what your approach is, too
19:44:40 <ais523> cpressey: the idea was unfinished, so I'm not surprised that there are problems with it
19:56:36 -!- ais523 has quit.
19:56:41 -!- callforjudgement has joined.
19:57:47 -!- callforjudgement has changed nick to ais523.
20:02:45 <Koen_> int-e: do you often have trouble finding esolangs?
20:03:43 <int-e> Koen_: Not really.
20:04:02 -!- cpressey has quit (Ping timeout: 246 seconds).
20:04:07 <Koen_> "for instance I find brainfuck derivatives all the time"
20:04:09 <int-e> Koen_: As a rule it only happens if I make up a name.
20:05:24 <b_jonas> yeah, there are too many brainfuck derivatives
20:05:51 <ais523> there are always too many bad BF derivatives
20:05:55 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
20:05:59 <ais523> there are occasional good BF derivatives, but that's the exception rather than teh rule
20:06:00 <b_jonas> are there any underload variants yet, or unlambda variants, or Chef variants?
20:06:11 <ais523> underlambda's arguably an underload variant
20:07:33 <ais523> or, not arguably, underload-minus-S was my starting point for it
20:10:23 -!- ais523 has quit (Remote host closed the connection).
20:10:32 -!- ais523 has joined.
20:17:51 -!- cpressey has joined.
20:28:54 <cpressey> btw, does anyone here have an ACM subscription, and if so, would you be willing to download a recent article and tell me if you think it is satirical or not?
20:30:17 <cpressey> http://cacm.acm.org/magazines/2015/2/182650-in-defense-of-soundiness/abstract
20:30:36 <cpressey> if that is a joke, the abstract is quite deadpan
20:30:53 <cpressey> and if it's not a joke, i'm slightly terrified that static analysis has come to this
20:35:25 <b_jonas> cpressey: downloaded, grab it quickly from http://russell2.math.bme.hu/~ambrus/pu/a.pdf
20:36:33 <cpressey> thanks for lending me your copy. i'll return it forthwith
20:37:22 <olsner> I thought soundness would be the other way around, e.g. completely sound = excluding all impossible executions, while not saying anything about the possible ones
20:40:28 <olsner> so an "everything is fine because I don't know that any part of your program will execute" analysis would be completely sound, but lacking in completeness?
20:42:37 <olsner> hmm, maybe it just depends on whether you're proving that a program has problems, or that it does not
20:44:24 <int-e> Without reading the article... program analysis is hard, which means that sound tools will produce lots of false positives, which means that programmers will be discouraged from using the tools.
20:46:06 -!- AnotherTest has joined.
20:46:20 <int-e> olsner: Anyway, "soundness" tends to be defined from the perspective of positive answers. So a tool is sound if, when it finds not problems, the program is correct.
20:47:58 <int-e> Actually that should extend to definitive answers. But that leaves a lot of cases where all a tool can say is "I don't know, but this piece of code looks suspicious."
20:48:04 <cpressey> it's far more the adding of -y to a piece of mathematical terminology that freaks me out
20:48:44 <cpressey> we analyze models of programs, not programs themselves (although they are far closer to each other than, say, bridges and structural engineering calcs)
20:48:58 <int-e> maybe I should have a look after all
20:53:30 <int-e> "eval" is a nice example. Either you flag every program containing eval as dangerously wrong, or you trust the programmer.
20:57:53 <int-e> "Soundy is the new sound", well, eww.
20:58:24 <cpressey> "our analyzer is sound for Language-{eval}", is it so hard to just say that?
20:58:45 <cpressey> anywa, appears to not be a joke
20:59:11 <int-e> I think I'm more upset about the silly name ("soundy") than about the concept as such.
21:00:13 <olsner> my impression is that these static analysis tools make no attempt to be sound like that - they are very concerned about not having false positives, not concerned with being able to find all problems
21:00:36 <cpressey> false positives ARE a pain, but
21:00:46 <int-e> Yes, I believe it's all about avoiding false positives.
21:02:54 <int-e> (I also disagree with the article where it says that we know how to model features like "eval" in principle. I don't think we can say much beyond "anything may happen", which for an analysis tool is tantamount to throwing in the towel. "Loss of precision" is just a technical phrase describing this phenomenon.)
21:03:05 <cpressey> to be fair, this is not *as* bad an article as I have seen in the ACM in the past
21:04:49 -!- AnotherTest has quit (Ping timeout: 245 seconds).
21:05:22 <int-e> ("eval" is extreme of course. I'm a bit surprised that tools would treat it as doing nothing. For setjmp/longjmp, I guess the excuse is that people (hopefully!) only use it for exceptions, and in the case of casts, that programmers have been trained to think long and hard about them. I don't know about Java's reflection.)
21:06:53 <cpressey> eval("literal code") is obviously easy; eval(random_string()) is obviously impossible; I imagine there are a few cases (like eval("temp %s late" % foo)) where you could pick it apart; but it's probably not used frequently enough to justify it
21:06:54 <int-e> Oh and of course the performance measure for these tools is "found NNN real bugs with N false positives" rather than "missed MMM bugs".
21:08:39 <cpressey> bugs me to pieces when i see Python code like getattr(a, 'thing_' + b)
21:09:12 <cpressey> even if you've given up hope of ever running a static analyzer on it
21:09:25 <cpressey> when I see a.thing_foo in code, I expect to be able to grep for thing_foo
21:09:39 <cpressey> and have it, like, you know... show where it is defined
21:10:25 <int-e> Yes, that's awful.
21:12:06 -!- devdean has left.
21:13:46 -!- TieSoul has changed nick to TieSleep.
21:17:58 <cpressey> and as I understand it, Java reflection is a bit like that - here's a string, get me the method with that name
21:20:46 <int-e> And if you want to go wild, you can implement your own ClassLoader and generate bytecode on the fly.
21:22:42 <int-e> And you know that when it's possible, it's also done. (The keyword here is "bytecode enhancer".)
21:23:11 <cpressey> dim memories of using one of those, once
21:24:01 <int-e> Another problem with Java is, things often hide behind interfaces, which are instantiated by frameworks like Spring, which means you get to browse XML files (joy!) to find what classes are actually used to implement them.
21:24:33 <int-e> I try to stay far away from that stuff.
21:25:24 <int-e> https://en.wikipedia.org/wiki/Dependency_injection
21:27:12 <int-e> oh and this discussion reminded me of https://github.com/EnterpriseQualityCoding/FizzBuzzEnterpriseEdition
21:27:24 <vanila> java has some esotericness that could not happen intentionally
21:28:15 <int-e> Because how could anybody make the code modular and reusable without a FizzBuzzSolutionStrategyFactory!
21:28:25 -!- Patashu has joined.
21:34:08 -!- Patashu has quit (Remote host closed the connection).
21:34:27 -!- Patashu has joined.
21:40:11 * cpressey makes his first edit to the esowiki in, pfff, years
21:42:30 -!- AnotherTest has joined.
21:48:10 <ais523> hmm, it didn't get announced in #esoteric, most wiki edits do
21:48:32 <ais523> it showed up on RSS though
21:48:44 <cpressey> didn't know there was an editbot
21:51:14 <ais523> there is normally, but I suspect it's down right now
21:52:55 <b_jonas> maybe it is on the vacation with fungot?
21:58:33 <cpressey> do not like that 'cabal update' gives you no progress bar
22:00:02 <cpressey> maybe i should be carping about that in #haskell and not here, apologies
22:01:03 * cpressey has caved in and is going to try writing something in Agda
22:01:16 <cpressey> "try" being the operative word there
22:03:50 <lambdabot> Exception e => IO a -> IO (Either e a)
22:03:57 <Taneb> Apparently there is try
22:06:47 * cpressey watches seven zillion haskell libraries build
22:18:14 * int-e watches cpressey exaggerate.
22:18:59 * int-e is building ghc on a ramdisk out of sheer boredom.
22:20:12 <Taneb> cpressey, Agda is a function that maps cabal install to an electric heater
22:35:36 -!- ProofTechnique has joined.
22:38:49 -!- Lymia has joined.
22:40:01 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
22:44:37 <cpressey> Taneb: ah! but at least it is a *total* function that maps cabal install to an electric heater
22:45:00 <cpressey> hrm, it errored while I was writing an article
22:45:01 <cpressey> http://esolangs.org/wiki/EXPBLARGL
22:48:19 <cpressey> heck, I dunno ais523 , that might actually be relevant to you
22:49:17 -!- ais523 has quit (Read error: Connection reset by peer).
22:49:19 <Taneb> cpressey, I think all brainfuck programs are valid Underload programs and vice versa.
22:49:25 -!- ais523 has joined.
22:49:32 <Taneb> (both have very unrestrictive grammars)
22:49:52 <cpressey> Taneb: if you like, I can clarify that
22:50:01 <Taneb> Although an Underload program beginning with ++[>+++++<-] would be pretty useless
22:50:18 <Taneb> cpressey, I mean, it's like the least important thing with the language
22:50:42 <ais523> it's easy to make a BF/Underload polyglot
22:50:43 <cpressey> apparently [] are reserved in Underload, so that's one thing
22:50:49 <ais523> by using the ()! convention
22:50:55 <ais523> and ignoring the reserved characters because everyone else does
22:51:29 <Taneb> cpressey, they're required to be balanced, but brainfuck also has that restriction
22:51:44 <Taneb> Although "(" is a valid brainfuck program but not valid Underload...
22:51:55 <ais523> it's because Overload uses [] for pointers
22:52:15 <cpressey> well, assume that if it contains only +-><[]., it's brainfuck, else it's Underload
22:52:37 <ais523> (Underload is a derivative of a vaporware language, how's that for weird things to be derivatives of?)
22:52:51 <Taneb> cpressey, thus preventing the brainfuck from having any comments?
22:52:52 <cpressey> this may exclude some Underload programs, force them to be interpreted as brainfuck -- I don't care, it matters not
22:53:13 <Taneb> ais523, I have (or had) an Ook! derivative somewhere
22:53:16 <cpressey> after all, these are not really meant to be generated by hand
22:53:27 <cpressey> this is essentially the target language of a TM-compiler
22:53:56 <cpressey> which sounds weird but is actually a central thing in computability, innit
22:55:02 <ais523> I think one shortcoming of EXPLBARGL is that it also needs exptime to /run/
22:55:37 <Taneb> Sorry, dropped my keyboard
22:57:27 <cpressey> ais523: you saw shortcoming, I say AWESOME
22:58:03 <cpressey> my quips would have so much better delivery if I didn't typo so much
22:58:30 <Taneb> That worked even with the typo, I think
23:01:00 <cpressey> it's probably very difficult to find a way to make a mapping that is hard to compute, while letting the target language itself be easy to interpret
23:01:19 <cpressey> certainly beyond my current reasoning capacity
23:07:52 <cpressey> actually, a much simpler way to ensure it's outside of P would be to use int-e 's trick but replace "fibonacci" with "ackermann"
23:08:54 <Taneb> If you're using the ackermann function, you mayswell have it in a sensible base
23:09:05 <Taneb> log(A(5,5)) is still huge
23:10:01 <cpressey> also, it violate's Minsky's Maxim if you use ack
23:10:17 <cpressey> (said maxim being the mapping should be at most PR)
23:11:36 <Taneb> Oh, primitive recursive
23:12:44 -!- AnotherTest has quit (Remote host closed the connection).
23:16:02 <cpressey> Taneb: yes. although, I think that was more or less an offhand remark he made, since he was considering rather more efficient mappings, and not pathological cases like this.
23:16:44 <cpressey> it's difficult for me to say, "well, the mapping is total and terminating, but it's not primitive recursive, so the language isn't turing complete"
23:38:18 -!- zzo38 has joined.
23:48:33 <Taneb> @tell oerjan Because of you, "hth" has entered my general vocabulary. I am not happy about this circumstance.
23:53:13 <Koen_> I still don't know whether to read it "hopes that helps" or "happy to help"
23:53:35 -!- boily has joined.
23:53:43 <ais523> I think the meaning is more along the lines of "this sentence is slightly informative, but mostly trolling"
23:53:48 <Taneb> Koen_, I've always read it as "Hope this helps"
23:54:19 <HackEgo> hth is help received from a hairy toe. It is not at all hambiguitous.
23:56:07 <Taneb> Koen_, I've always assumed that to mapole something is to hit them with a maypole
23:56:43 <Koen_> I've been assuming that for the past two minutes too
23:56:46 <elliott> ais523: that's overestimating the informativity in my expeirence :p
23:57:07 <ais523> no, "expeirence" is not a word hth
23:57:15 -!- ChanServ has set channel mode: +o elliott.
23:57:17 <HackEgo> A mapole is a thwackamacallit built from maple according to Canadian standards.
23:57:20 -!- elliott has set channel mode: -o elliott.
23:57:36 <boily> Koen_: Khelloen_! long time no see!
23:57:56 <boily> Taneb: tanelle. the mapole is good all year long. it's more than a maypole!
00:05:39 -!- vanila has quit (Quit: Leaving).
00:22:11 <Jafet> EXPBLARGL': given N, take the Nth prime number and split every 3 bits to get a brainfuck program.
00:31:16 -!- GeekDude has joined.
00:34:45 -!- not^v has joined.
00:39:11 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:40:55 <Koen_> Jafet: what is the proportion of prime numbers that yields correct brainfuck programs?
00:41:02 <Koen_> and terminating brainfuck programs?
00:41:28 -!- Phantom_Hoover has joined.
00:41:52 <Koen_> and with that I wish you all a good night
00:42:16 -!- 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?").
00:45:29 -!- doesthiswork has joined.
00:49:25 <cpressey> neither http://esolangs.org/wiki/Underload nor http://esolangs.org/wiki/INTERCAL has been a featured page?!??!
00:50:30 <zzo38> I don't know, but I think it probably ought to be
00:51:26 <ais523> cpressey: basically the problem is that elliott keeps making me do the featured article process, so I can't really feature languages I've had a large hand in for fear of bias accusations
00:51:47 <ais523> admittedly I didn't invent INTERCAL, but I am responsible for much of its recent development
00:51:51 <zzo38> Then other people should try to help too?
00:52:06 <dulla> it's prec prec prec prec
00:52:08 <elliott> I nominate cpressey. he's a sysop and everything
00:52:21 -!- GeekDude has quit (Quit: ZNC - http://znc.in).
00:52:48 <dulla> I nominate Linus Torvald
00:53:16 <elliott> hopefully linus torvalds will go nowhere near the esolangs wiki
00:54:30 <boily> I nominate elliott, because because something something elliott something.
00:54:32 <ais523> I'd be honoured if he did, but I think he has better things to be doing
00:54:39 <dulla> so, is it an issue of needing seven proxies so skiddies don't shit up the place, or what, elliott
00:54:44 <zzo38> I want to nominate cpressey
00:54:55 <ais523> that said, the last C-INTERCAL release /was/ at the request of Donald Knuth
00:54:58 <dulla> like shitting o people that deserve it? ais523
00:55:05 <ais523> we went really fast on that one, just in case it was somehow holding up TAOCP
00:55:37 <dulla> All I know is some big wig, probably torvald gordon ramseys the tech world
00:56:14 <elliott> are you going to get more coherent over time or should I just put you on ignore now
00:56:25 <dulla> I'm having a bad day?
00:56:28 <boily> dulla: I thinkg to gordonramsey is a perfectly cromulent verb.
00:57:05 <dulla> english, where everything is a verb, and an idiom
00:57:28 <dulla> behind seven layers of postmodernism irony, more like it
00:58:16 <oren> Can someone invent a VCS that works on .doc files?
00:58:31 <boily> oren: I thinkg M-Files already does it.
00:58:58 <boily> (ah bordel de... why must I type a g after a k?)
00:59:07 <zzo38> oren: Do you need such thing so much?
00:59:09 <ais523> there's also the "track changes" thing built into Word but it's really bad for VCS purposes IMO
00:59:28 <ais523> you could also just put the .doc files in git or something, it'll still track versions
00:59:31 <ais523> and Word has a diff feature
00:59:41 <ais523> dulla: version control system
00:59:43 <boily> dulla: version control system.
00:59:46 <elliott> http://ben.balter.com/2015/02/06/word-diff/
00:59:56 -!- GeekDude has joined.
01:00:14 <zzo38> Although Microsoft Word isn't really the best way to do these kind of things anyways especially use with VCS
01:00:42 <elliott> hm, http://blog.martinfenner.org/2014/08/25/using-microsoft-word-with-git/ looks fun too
01:03:51 <ais523> "As you work, Word Diff sits on a server (in my case Heroku), waiting for you to push your changes. When you do, it springs into action, automatically converting the Word document to Markdown after each commit:"
01:04:03 <ais523> I'm trying to work out whether this is better or /even worse/ than Word's built-in diff funciton
01:05:20 <ais523> it assumes that Word documents can't have complex formatting at all
01:05:34 <ais523> which in turn, implies that whatever task you're doing, it's one for which Word is the wrong tool
01:06:04 <elliott> well, it assumes that you're okay with diffs that ignore complex formatting things most of the time
01:11:06 <dulla> or makes noobish tuples
01:11:20 <dulla> (<what is this formatting>, "words")
01:15:38 <dulla> and then probably highlight color it to preserve it
01:36:49 -!- oerjan has joined.
01:37:44 <lambdabot> Taneb said 1h 49m 11s ago: Because of you, "hth" has entered my general vocabulary. I am not happy about this circumstance.
01:39:24 <oerjan> myndzi: your script is still broken hth
01:56:02 <zzo38> I almost written the session 63
01:56:32 <oerjan> then you'll have to start using 6 bit numbers!
01:57:13 <oerjan> another one-off joke ruined by off-by-one error
01:57:34 <zzo38> Well, I am using entirely decimal numbers in ASCII for the session numbers here anyways anyone who want to store in binary should probably use at least 16-bits though
01:58:45 <oerjan> i see you are expecting to go on for a while.
01:59:14 -!- not^v has quit (Ping timeout: 246 seconds).
01:59:25 <zzo38> I don't actually know how long it expects to go on, but I expect 16-bits is going to be enough even if it is longer than expected.
02:03:22 <HackEgo> hth is help received from a hairy toe. It is not at all hambiguitous.
02:04:36 <oerjan> are you saying that doesn't help?
02:05:17 -!- not^v has joined.
02:05:20 <dulla> hackego is a hackkkkk
02:05:55 <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.
02:06:07 <olsner> oerjan: 6 bits is enough to fit 0 to 63, hth
02:07:15 <olsner> this may or may not mean that your joke is still off by one, because 64 will need an extra bit
02:08:08 <oerjan> dead horse floggers anonymous is thataway --->
02:08:43 <oerjan> I MAD LIKE HELL AND CANOT TAKE IT ANY MORE
02:09:11 <dulla> you should become a CTO
02:09:26 <dulla> I hear when the servers go down, the server admins are the least of your problems
02:09:53 <dulla> though that story was probably a joke, it's probably not a lie
02:09:54 <oerjan> no intention to become any kind of O
02:10:56 <olsner> in your case it would have to be CTØ
02:11:37 <dulla> if only I knew what encoding I need to see that
02:11:46 <HackEgo> [U+A66E CYRILLIC LETTER MULTIOCULAR O]
02:12:14 <elliott> was that the first unironic "u mad" in this channel
02:12:35 <oerjan> now _font_ might be a bit harder.
02:12:40 <dulla> I'm already utf-8, oerjan
02:12:47 <oerjan> elliott: is anything dulla says unironic?
02:13:06 <elliott> oerjan: if the answer is no then it might as well be yes
02:13:17 <elliott> if you hide absolutely everything behind irony I'm just going to take you sincerely :p
02:13:20 -!- ProofTechnique has joined.
02:13:42 <dulla> I don't think my oration skills are good enough for intentional irony
02:13:57 <ais523> `addquote <elliott> oerjan: if the answer is no then it might as well be yes
02:14:01 <ais523> that one's good both in context and out of context
02:14:05 <HackEgo> 1232) <elliott> oerjan: if the answer is no then it might as well be yes
02:14:57 <oerjan> dulla: anyway if it's any consolation i cannot see the multiocular o in my client either.
02:15:07 <dulla> It's not descriptive
02:15:18 <dulla> multiocular is not in my scope
02:15:24 <ais523> I can't in mine either, despite the fact that I recently installed a font whose entire purpose is that it contains obscure Unicode
02:15:32 <oerjan> i can only imagine its greatness. or check the logs.
02:15:48 <dulla> or search the unicode site for it
02:16:20 <oerjan> alternatively, i can cut and paste it into my browser, which shows it just fine.
02:17:07 <ais523> mine still doesnt like it
02:17:47 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
02:18:01 * oerjan checks the repository browser now that HackEgo is present again
02:18:19 <oerjan> the only thing of note is shachaf removing pbflistdeluxe.
02:19:18 <oerjan> dulla: i believe there's a separate double o character
02:20:07 <oerjan> that one has upper and lower case variants
02:21:24 <HackEgo> [U+A66C CYRILLIC CAPITAL LETTER DOUBLE MONOCULAR O]
02:21:57 <oerjan> those cyrillic monks had a strange relationship with eyes
02:23:08 <oerjan> https://en.wikipedia.org/wiki/Double_O_(Cyrillic) is one my browser doesn't show either
02:25:20 <zzo38> They don't even agree how many eyes seraphim have, I think?
02:30:24 <lambdabot> Plugin `unmtl' failed with: `StateT IO' is not applied to enough arguments, giving `/\A B. IO -> A (B, IO)'
02:30:30 <lambdabot> Plugin `unmtl' failed with: `StateT s IO' is not applied to enough arguments, giving `/\A. s -> IO (A, s)'
02:31:10 <oerjan> zzo38: it's probably more than you can draw, anyway.
02:36:22 <oerjan> <elliott> for the sake of fantasy i would like you all to believe that i have irc pings hooked up to an alarm <-- works for me
02:46:30 -!- bb010g has joined.
02:49:47 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
03:13:33 <oren> Note to self: building a massive watermill complex to power your massive water pumping complex does not work when the pumps drain the very water that powers the watermills.
03:15:32 <boily> oren: playing dwarf fortress?
03:16:04 <oren> now I have watermills over dry land
03:16:32 <oerjan> r.i.p. obsidian apocalypse
03:16:54 <oren> I need to rethink this
03:17:48 <oren> Maybe I'll route a few aquifers into the cistern
03:20:45 <oren> (The cistern exists because the river stops during the winter)
03:21:45 <oren> Here is the massive water mill complex http://snag.gy/Z4QOq.jpg
03:25:13 <oren> It is built to provide 1000 units of power, currently providing 300, which isn't enough to move it
03:33:23 <dulla> i have the feeling this is a dwarf fortress thing
03:36:51 <oren> dulla: yup. It is part of a plan to glass the whole panet
03:37:49 -!- boily has quit (Quit: CLARIFIED CHICKEN).
03:37:53 <dulla> recall the blunderbuss minecart exploit
03:38:13 <dulla> the things you can do with that
03:38:51 <oren> Well, eventually the watermills will be self-powered when the cistern has been filled properly.
03:39:29 <oren> So then I'll have lots of power available to power, well, anything I want
03:39:42 <dulla> and then there is the catapult exploit, I wonder if that works with warheads, too
03:40:19 <dulla> though, you honestly don't need it for catapults, stones are cheap as dirst
03:40:41 -!- not^v has quit (Ping timeout: 252 seconds).
03:40:59 <oren> Ooh a cyclops. pull the lever of death, and pump the pumps of death!
03:41:16 -!- callforjudgement has joined.
03:41:50 <oren> currently, the pumps of death are dwarfpowered. Soon, very soon, they will be water-powered.
03:43:24 <dulla> Wouldn't it be more efficient to have more pumps?
03:44:02 -!- ais523 has quit (Ping timeout: 245 seconds).
03:46:17 <oren> http://snag.gy/6hG8F.jpg shown is a cyclops murdering the merchants, the entrance (currently being pumped full of water to prevent any dwarves being stupid enough to run outside), and part of aqueducts running to the power plant
03:46:50 <dulla> Does pressurised water still do that thing?
03:46:57 <dulla> Where it moves faster than a game tick?
03:47:38 <dulla> It'd be a great way to make sure things in the aquaduct stay in the aquaduct
03:48:04 <HackEgo> danddreclist 63: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
03:50:17 <oren> The merchants are leaving, porbably because their merchandise is being carried away by pressurized water
03:50:45 <oren> oh and because most of them have been dismembered by a cyclops
03:51:14 <dulla> it's probably the dismemberment
03:51:28 <dulla> You know how the merchants can't take the heat
03:52:13 <zzo38> Do you like this level20.tex? This is the one involving the rune caster
03:53:45 <oren> the cyclops apparently dorwned before the magma could even getnear it
03:54:04 <oren> or maybe the merchants killed it.
03:58:23 <oren> "some migrants have arrived, despite the danger"
04:00:46 <oren> Oh come on guys, come right on in, never mind the drowned merchants and cyclopes...
04:07:29 -!- MDude has changed nick to MDream.
04:08:38 <oren> http://snag.gy/Obzd2.jpg
04:22:24 -!- callforjudgement has quit (Read error: Connection reset by peer).
04:22:32 -!- callforjudgement has joined.
04:26:34 <oerjan> eek anagol's recent entries has moved too fast
04:28:05 <oerjan> surely it used to be more than 24 hours before?
04:34:19 -!- cpressey has quit (Ping timeout: 256 seconds).
04:41:19 -!- cpressey has joined.
05:09:24 -!- ProofTechnique has joined.
05:11:35 -!- callforjudgement has quit.
05:12:06 -!- callforjudgement has joined.
05:17:09 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
05:36:26 -!- dianne has quit (Ping timeout: 264 seconds).
05:38:10 -!- dianne has joined.
05:38:58 -!- chaosagent has joined.
05:39:16 -!- doesthiswork has quit (Quit: Leaving.).
05:54:46 -!- callforjudgement has quit.
05:55:02 -!- callforjudgement has joined.
06:05:14 -!- cpressey has quit (Ping timeout: 264 seconds).
06:06:33 <oren> Oh shit, a miner was caught in a cave in, got confused by the dust, and fell into the cistern.
06:07:33 <oerjan> is the water undrinkable now
06:08:22 <oren> I dunno. Hopefully we can wash the blood away after the fishermen retrieve the corpse.
06:09:23 <oren> This is why I hate using cave ins, though it is sometimes necessary
06:10:07 <oerjan> will they now all die from waterborn disease
06:10:41 <oren> I don't think that's modeled, though I could be wrong. In any case they have plenty of booze to drink
06:12:10 <oren> The cistern is for the generation of energy during the winter when the river stops.
06:12:13 -!- cpressey has joined.
06:13:23 <oren> holy crap, hes actually alive still.
06:14:00 <oren> and he swam out! he's a good swimmer I guess
06:14:53 <oerjan> all's well that ends well
06:15:38 <oren> with luck now I can pressurize the cistern
06:16:18 <oren> thus having a way to literally blast enemies to death
06:27:48 <oerjan> <elliott> is this the onion <-- possibly r/nottheonion?
06:29:55 -!- cpressey has quit (Ping timeout: 256 seconds).
06:37:04 -!- cpressey has joined.
06:40:17 -!- hjulle has quit (Ping timeout: 245 seconds).
06:44:46 <oren> It appears that drowning merchants is a good way to get free stuff
06:46:18 <zzo38> That's your way of getting free stuff?
06:46:54 <oren> Well they come every season, even if i drown them every season, so yeah
06:47:25 <oren> I seal the doors and pump water into the trade depot
06:47:54 <zzo38> It seems like merchants should sue you if that happen a lot it will be recognized?
06:48:08 <oren> I dunno, we'll see
06:48:23 <oren> If they try to sue me I'll drown thelawyers
06:52:32 -!- cpressey has quit (Ping timeout: 246 seconds).
06:52:33 <oerjan> @tell fizzie btw the wiki bridge isn't working either hth
06:53:53 -!- cpressey has joined.
06:55:43 <oerjan> `addquote <Taneb> cpressey, Agda is a function that maps cabal install to an electric heater
06:55:56 <HackEgo> 1233) <Taneb> cpressey, Agda is a function that maps cabal install to an electric heater
06:56:31 -!- oren has quit (Ping timeout: 244 seconds).
06:58:39 <zzo38> O, that's what it is?
06:59:06 -!- cpressey has quit (Ping timeout: 244 seconds).
07:01:43 <bb010g> I wish Haskell would steal Agda's operator syntax. If then else is so nice there.
07:42:46 -!- CADD has joined.
07:57:25 -!- callforjudgement has quit (Ping timeout: 264 seconds).
08:29:42 -!- oren has joined.
08:32:09 <oren> I am now testing to see if killing merchants over and over has any consequences
08:35:06 <oren> I have started a new game, and built the depot in an area designed so I can flood it whenever I want
08:56:50 -!- CADD has quit (Ping timeout: 264 seconds).
10:02:18 -!- Phantom_Hoover has joined.
10:16:51 -!- cpressey has joined.
10:17:06 <cpressey> I just wrote my first Agda program!
10:17:14 <cpressey> Actually, I typed it in from a book
10:23:20 <cpressey> and yes, I am an esowiki sysop I think, so if someone wants to bug me to slap a green checkmark on the Underload page and put an abstract on the front page,... do that
10:24:56 -!- oerjan has quit (Quit: Famous last words).
10:25:28 -!- oerjan has joined.
10:25:47 -!- oerjan has quit (Client Quit).
10:30:20 <cpressey> oh, oh, "famous last words", right, right
10:30:27 <cpressey> this is mediawiki we're talking about
10:52:29 -!- kapil___ has quit (Quit: Connection closed for inactivity).
11:01:47 <cpressey> Jafet: I did consider prime numbers, but, y'know... PRIMES is in P. can't be too careful.
11:02:29 -!- cpressey has quit (Quit: leaving).
11:39:51 -!- SopaXorzTaker has joined.
11:40:37 <fizzie> Why does that thing have such a ridiculous number of underscores in it.
11:40:48 -!- zemhill___ has quit (Remote host closed the connection).
11:41:11 -!- zemhill has joined.
11:43:21 <fizzie> Oh, the wiki bridge. Blah. I'll try to remember to fix that, though it would be easier with proper internet.
12:00:04 -!- vanila has joined.
12:00:34 -!- Patashu has quit (Ping timeout: 255 seconds).
12:16:25 -!- kapil___ has joined.
12:38:00 -!- chaosagent has quit (Ping timeout: 252 seconds).
13:06:48 -!- oren has quit (Quit: Lost terminal).
13:37:29 <vanila> http://jzt.xyz/worlds/village-of-jzt
13:54:19 -!- boily has joined.
13:57:39 -!- boily has quit (Client Quit).
13:59:46 -!- boily has joined.
14:06:57 <boily> elliott: helliott. CAO is down :(
14:09:23 -!- reynir has quit (Quit: brb).
14:12:20 <elliott> boily: play on cdo or cszo or whatever?
14:12:26 <elliott> there's like fifty servers these days aren't there
14:17:21 <boily> it doesn't feel right, but I'm on CDO.
14:19:13 <elliott> cdo has always been the cool server
14:19:44 <boily> let me dehuge my term.
14:21:13 <elliott> I have no idea whaty ou do when you do that but it definitely doesn't make your terminal any smaller :P it's fine though I can just make my font tiny
14:23:32 <boily> I put in 80x24 for the max width and height?
14:23:49 <elliott> I mean, you can tell there's more than 80 columns and 24 rows to your terminal right now, right >.>
14:24:09 <elliott> it's fine though I just made my font smaller and now it fits on my screen
14:24:24 <boily> aaaah. it goes with the terminal size. makes sense. tdh
14:24:37 <boily> I like my terminal to be full screen :D
14:26:13 <elliott> you could "stty cols 80 rows 24" before running ssh I guess but that'd lead to a hell of a lot of wasted space
14:28:52 * boily is hungry and should go breakfast...
14:33:17 -!- heroux has quit (Ping timeout: 256 seconds).
14:35:06 -!- heroux has joined.
14:36:57 -!- MDream has changed nick to MDude.
14:42:29 -!- kapil___ has quit (Quit: Connection closed for inactivity).
15:13:17 -!- hjulle has joined.
15:23:58 -!- int-e has quit (*.net *.split).
15:23:59 -!- kline has quit (*.net *.split).
15:24:05 -!- int-e has joined.
15:24:05 -!- lambdabot has quit (Quit: brb).
15:25:41 -!- kline has joined.
15:28:06 <vanila> what program could i use on linux to measure/grapha processes memory use?
15:28:16 -!- doesthiswork has joined.
15:28:34 -!- lambdabot has joined.
15:29:45 <boily> elliott: breakfasting is dangerous here. a haircut happened.
15:30:04 <boily> vanila: vanelloa. ksysguard perhaps?
15:59:55 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
16:02:02 -!- Phantom_Hoover has joined.
16:03:46 -!- SopaXorzTaker has quit (Ping timeout: 265 seconds).
16:16:15 -!- SopaXorzTaker has joined.
16:24:13 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
16:26:40 -!- aretecode has quit (Read error: Connection reset by peer).
16:30:48 -!- aretecode has joined.
16:53:00 -!- GeekDude has joined.
16:59:42 -!- Koen_ has joined.
17:00:30 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
17:00:36 -!- Phantom__Hoover has joined.
17:02:21 -!- Tritonio has joined.
17:02:34 -!- FreeFull has quit (Quit: BBL).
17:17:50 <lambdabot> freshname. Return a unique Haskell project name.
17:18:44 <int-e> It starts out with "Ha" and adds some random letter. VERY useful.
17:19:09 <vanila> its generating a fresh symbol
17:19:20 <lambdabot> Plugin `compose' failed with: Unknown command: "fresh"
17:25:59 <vanila> my program has a new bug
17:26:08 <vanila> it is segfaulting before it even reaches line 1
17:26:16 <vanila> i dont know what is going on !
17:27:48 <vanila> how do i even debug this.
17:31:31 <boily> vanila: which language?
17:33:32 <boily> what #includes do you have? any esoteric, anormal, unusual or experimental libraries?
17:38:37 <vanila> it was working a second ago
17:38:40 <vanila> and we just changed one function
17:42:43 <Koen_> also did you include some .h that you wrote yourself?
17:43:07 <Koen_> and which you changed less than a second ago?
17:50:24 <vanila> it's really fascinating a weird way
17:50:32 <vanila> i hope i get to the bottom of it, but i really have no idea how
17:50:41 <vanila> i looked at the assembly code for the prelude of main but i cant understand it
17:53:30 <Koen_> vanila: can you show us what you changed in the .h ?
17:56:49 <vanila> i didnt change any headers
18:00:15 <Koen_> and if you put a putstr as the very first line of the main it's not printed out?
18:00:31 <Koen_> or a printf("\n");
18:00:32 <vanila> that shouldn't be possible
18:01:00 <Koen_> (don't omit the \n to flush the output)
18:02:33 -!- Phantom__Hoover has quit (Ping timeout: 250 seconds).
18:35:33 -!- cpressey has joined.
18:36:08 <vanila> i wonder if it's theoretically impossible cpressey - maybe focus on proving that rather than making a language?
18:36:13 <cpressey> the compiler can always artificially extend the program by adding e.g. +- to the front of it, then it knows there's a shorter program
18:36:48 <cpressey> i'm sure it's not theoretically impossible, because int-e
18:37:16 <cpressey> turn brainfuck program into integer, program is ackermann of that integer
18:40:15 <cpressey> but it has sort of raising an interesting conjecture, which is
18:40:43 <cpressey> if the mapping from TM's to language X programs is complex, running programs in language X will also be complex
18:41:30 <cpressey> which sounds perfectly intuitive, but -- no idea how one would go about proving it
18:41:51 <cpressey> other things I have failed at this weekend: Agda
18:42:02 <vanila> yes I agree about the 'if mapping, then running' thing
18:42:13 <vanila> that's what I realized from the idea of encrypted source code
19:06:12 -!- TieSleep has changed nick to TieSoul.
19:12:28 -!- boily has quit (Quit: RELATIVE CHICKEN).
19:14:47 <cpressey> hmm, maybe EXPBLARGL could force to try all the permutations of the program -- wouldn't work well with brainfuck because +- = -+ ... but maybe some other language
19:16:06 <cpressey> nah, i think you could still inject some kind of "identity" instruction, then you know there's another permutation that also works
19:16:18 <cpressey> maybe i'll keep banging my head against agda
19:16:39 <vanila> i could help with agda maybe?
19:18:27 <elliott> cpressey: did you ever figure out the Burro/Cabra type things
19:18:51 <vanila> https://www.youtube.com/watch?v=uxRjp4LVuo4
19:18:52 <bluckbot> YouTube 「title: Amor incondicional entre un burro y una cabra」 「uploaded by: Univision Noticias」 「duration: 00:01:21」 「views: 6413」 「likes: 67」 「dislikes: 0」
19:19:18 -!- ChanServ has set channel mode: +o elliott.
19:19:20 -!- elliott has kicked bluckbot bluckbot.
19:19:41 <elliott> 2015-02-17.log:07:08:01 <dulla> oerjan kick bluckbot
19:19:43 -!- elliott has set channel mode: -o elliott.
19:20:01 <elliott> that's one garish YouTube logo colour
19:20:18 <vanila> Unconditional love between a donkey and a goat
19:25:17 <elliott> stronger algebraic structures
19:26:00 <cpressey> There, and elsewhere, I basically ran up against "imaginary functions" and gave up
19:26:28 <elliott> there was something about being able to do gcd on programs
19:26:32 <cpressey> been meaning to add I/O to Burro and to rewrite the docs, but
19:26:43 <cpressey> yeah that's a... what's it called
19:26:49 <elliott> hmm, what kinda imaginary functions
19:27:01 <vanila> You can take the derivative of a lambda term
19:27:12 <vanila> there's a new paper about it, it's silly but neat
19:27:30 <cpressey> http://esolangs.org/wiki/Imaginary_function
19:28:41 <cpressey> vanila: given the awesome power of taking a derivative of a CFG, I dunno, this could all be very wild
19:30:19 <cpressey> really can't even get near rings, I don't know how one would get up to integral domains and such
19:30:51 -!- naturalog has quit (Ping timeout: 244 seconds).
19:31:13 <elliott> vanila: do you have a link to that paper?
19:31:42 -!- naturalog has joined.
19:31:51 <vanila> http://www.informatik.uni-marburg.de/~pgiarrusso/papers/pldi14-ilc-author-final.pdf
19:32:00 <elliott> cpressey: with imaginary functions: isn't it simple enough to just to add thunk(F) where F is a function to your primitive values
19:32:05 <elliott> and have apply send thunk(F) to F
19:32:06 <vanila> they get some good results speeding up code with it
19:32:10 <elliott> not exciting, but it seems to meet your spec just fine
19:32:29 <vanila> applied to pure lambda calculus, it has no effect
19:32:40 <vanila> its' only when you make special primitives with differentiation support
19:32:44 <vanila> just to spoil the ending
19:34:44 <cpressey> i think that's occurred to me but i got too sick of it to follow up on it
19:35:13 <elliott> as in data Expr = ... | Thunk Expr | Apply Expr | ...; data Value = ... | NativeFn (Value -> Value) | Closure Env Args Expr | ThunkV Value | ...; ... eval (Apply e) = apply (eval e); eval (Thunk e) = thunk (eval e); ...; apply (ThunkV v) = v; ... thunk v | isFun v = ThunkV v | otherwise = undefined or whatever
19:35:21 <elliott> it's sorta like adding an axiom
19:35:25 <cpressey> basically you'd have a type constructor Thunk x and (apply Thunk x = x) but apply (a-real-function-value) would actually apply it
19:36:02 <cpressey> istr thinking there was some little bumpy inconsistency. but if there isn't
19:36:49 <cpressey> yeah maybe you could invert things, or at least pretend to, to cover "for every X there is a -X" type axioms in algebraic structures
19:36:57 <elliott> I should get back into esolangs.
19:38:02 <elliott> data Unit : Set where tt : Unit; apply : forall {A} -> (Unit -> A) -> A; apply f = f tt
19:38:50 <elliott> probably best not to think about this kind of thing in a setting with types
19:40:38 <cpressey> I can't wrap my head around Agda. writing a function and writing a proof are seperate things in my head, and it wants me to moosh them together
19:41:13 <cpressey> I write my theorem as....... a type? Of a function? Then write the proof as the body of the function?
19:41:55 <vanila> values are proofs and types are propositions
19:42:07 <vanila> lambda is used to prove implication
19:44:29 <cpressey> Here are two very simple propositions, the
19:44:29 <cpressey> true proposition and the false proposition:
19:44:46 <elliott> that's one awkward way to present it
19:44:46 <cpressey> indent didn't get preserved :(
19:44:56 <elliott> data True : Set where { true-is-true : True }
19:44:57 <cpressey> sign that I'm reading maybe not the best paper, huh
19:45:00 <elliott> might be clearer than that record silliness
19:45:11 <vanila> yeah elliott s way is much nicer
19:45:17 <elliott> there are reasons to use the record one For Real
19:45:27 <elliott> but it's not exactly great pedagogically
19:46:10 <cpressey> ok, so in the above, "False" is not a value, it's a proposition.
19:46:32 <elliott> (because types are values)
19:46:32 <vanila> wellll... it's a type but types are values....
19:46:50 <elliott> think of haskell where all the levels are collapsed
19:47:03 <elliott> instead of values having types which have kinds it's just values have types (which are values)
19:47:16 <elliott> ...but not just any values! they have to be type-typed values. I'm helping
19:47:32 <cpressey> "I'm helping" is the new "hth"
19:47:49 <vanila> A good thing to try is proving thinsg with lambda
19:47:53 <elliott> you can do, like, helping : if true then Nat else Bool
19:48:03 <vanila> not geetting data types involved first
19:48:27 <vanila> theorem1 : (P : Set) -> (Q : Set) -> P -> Q -> P
19:48:32 <cpressey> I got as far as defining the Peano numbers
19:48:58 <vanila> and theorem2 : (P : Set) -> (Q : Set) -> P -> (P -> Q) -> Q
19:49:12 <elliott> theorem1 : forall {P Q} -> P -> Q -> P would be even better for avoiding thinking about types
19:49:38 <b_jonas> aren't there libraries for these things?
19:49:56 <elliott> cpressey: if it helps at all for understanding how to write proofs as lambda terms: you use modus ponens by application
19:50:15 <elliott> to prove Q from (P -> Q) and P, let's say we have proofs p-implies-q : P -> Q and p : P
19:50:21 <elliott> then we have the proof p-implies-q p : Q
19:50:56 -!- bb010g has quit (Ping timeout: 265 seconds).
19:50:56 -!- supay has quit (Ping timeout: 265 seconds).
19:50:56 -!- mbrcknl has quit (Ping timeout: 265 seconds).
19:51:13 <cpressey> i see a type signature (that is to say, proposition (that is to say, theorem)) for a function called theorem1, above.
19:51:25 -!- jameseb has quit (Ping timeout: 265 seconds).
19:51:27 <cpressey> let's go with elliott's version
19:51:55 <cpressey> as i understand it they're NOT that different
19:52:06 <cpressey> one has explicit types passed to it, is all
19:52:09 <elliott> they are the same logically
19:52:18 <elliott> yeah in one of them the set arguments are implicit
19:52:23 -!- fractal has quit (Ping timeout: 265 seconds).
19:52:34 <elliott> which is more natural if you're thinking of them as foralls
19:52:52 -!- spiette has quit (Ping timeout: 265 seconds).
19:53:25 <cpressey> how do you implement it, and why? theorem1 p q -> p ? that makes no sense
19:53:42 <cpressey> sorry, there should be a = in there
19:53:48 <elliott> cpressey: think of it like
19:53:50 -!- merdach has quit (Ping timeout: 265 seconds).
19:54:14 <elliott> the (p :)s giving labels to the proofs
19:55:05 <elliott> if we have a proof p of P and a proof q of Q, then we can prove P with p
19:55:55 <elliott> (if we have a proof x of P -> Q and a proof y of P, then we can prove Q with modus ponens on x and y; theorem2 : forall {P Q} -> (P -> Q) -> P -> Q; theorem2 x y = x y)
19:56:28 -!- merdach has joined.
19:56:32 -!- Tritonio has quit (Ping timeout: 252 seconds).
19:56:38 <elliott> it's like deducing P, Q |- P except you label everything in the context
19:57:00 <vanila> well i was trying to leave theorem1 and theorem2 undefedin so cpressey could use them for practice
19:57:15 -!- spiette has joined.
19:57:35 <cpressey> i have no idea how you "practice" that
19:57:39 -!- mbrcknl has joined.
19:57:43 -!- jameseb has joined.
19:58:06 -!- supay has joined.
19:58:37 <elliott> you can just think of "theorem1 p q" as syntax for "by theorem1, using p and q as the assumptions P and Q", so that's giving a definition for how the proof works
19:59:25 <vanila> i looked up 'learn you an agda' it seems way more difficult than things need to be
19:59:39 <cpressey> vanila: well, it's only 2 pages, and the 2nd one is under construction
19:59:47 <vanila> I can write a much simpler tutoral
19:59:51 <vanila> that is easier to learn from
20:00:24 <cpressey> the problem, one problem, is that modus ponens has a conjunction in it, doesn't it? if p -> q, and if p, then q
20:00:38 <cpressey> i mean there are too many "ifs" in my description but
20:00:45 <elliott> ok yes it's using currying
20:00:51 <elliott> "if p -> q, then if p, then q"
20:01:04 <elliott> you can use conjunction if you want though
20:01:07 -!- incomprehensibly has quit (Ping timeout: 250 seconds).
20:01:12 <elliott> but that involves data types :P
20:01:20 <elliott> think of propositional logic with just -> as the connector
20:01:40 <elliott> and the metalogical deduction rule "if you have a proof of (P -> Q) and you have a proof of P, then you have a proof of Q"
20:02:11 -!- fractal has joined.
20:02:17 <elliott> we have that rule in agda, and we write it syntactically by putting the proof of (P -> Q) and the proof of P adjacent: proof-of-imp proof-of-P is a proof of Q
20:02:19 -!- Patashu has joined.
20:02:24 -!- incomprehensibly has joined.
20:04:17 <vanila> if f : P -> Q (f is a proof that P implies Q)
20:04:23 <vanila> and x : P (x proves P)
20:04:31 <vanila> then f x : Q (f of x proves Q)
20:05:46 -!- bb010g has joined.
20:05:51 <cpressey> i'm going to look for a different proof system. this one sucks.
20:06:10 <vanila> if you still want dependent types
20:06:27 <elliott> yeah, and then he gets to learn "match"
20:07:44 -!- nyuszika7h has quit (Read error: Connection reset by peer).
20:09:26 -!- nyuszika7h has joined.
20:09:54 <cpressey> http://at.metamath.org/index.html
20:19:07 <cpressey> the rainbow colouring and serif font do kind of scream "1999", i admit
20:20:08 -!- bb010g has quit (Quit: Connection closed for inactivity).
20:24:52 -!- Patashu has quit (Ping timeout: 240 seconds).
20:30:19 <elliott> good luck reading metamath proofs in their source form
20:34:24 <cpressey> looks like forth with lots of $'s
20:37:33 <int-e> I'm reading proofs and the typesetter "corrected" "well-founded" to "well founded".
20:38:08 <int-e> (so now we have a well founded relation. great.)
20:41:30 <cpressey> i read a horror story once about a publisher "correcting" "homeomorphism" to "homomorphism" (in a paper which also contained instances of "homomorphism")
20:41:49 -!- FreeFull has joined.
20:42:57 * cpressey sighs and tries the other paper, the one that doesn't define True as a record type
20:44:24 <int-e> (Another ... fun ... thing is that we use \mathsf{} in our paper. The computer modern scripts all have the same x-height and work well together. With the publisher's font the sans-serif characters look *big*)
20:44:27 <FreeFull> Why would one define True with a record type?
20:45:15 <int-e> But I'm more upset about having to go through everything word by word because I expect some more nasty surprises.
20:45:30 <int-e> (At least we have no homeomorphisms.)
20:47:11 <int-e> They also changed non-variable (meaning: not a variable) to nonvariable. Isn't that great...
20:47:44 <cpressey> FreeFull: to avoid elliott 's true-is-true thing, see above
20:49:26 <cpressey> i do hope it's a well founded nonvariable
20:53:45 -!- TieSoul has changed nick to TieSleep.
20:58:44 <cpressey> apparently this is the same paper
21:02:20 -!- bb010g has joined.
21:03:12 -!- TieSleep has quit (Ping timeout: 245 seconds).
21:06:07 <FreeFull> cpressey: I'll look in the logs
21:10:30 -!- TieSoul has joined.
21:10:32 <cpressey> oho http://oxij.org/note/BrutalDepTypes/
21:17:08 <cpressey> much clearer descriptions of some things
21:18:18 -!- TieSoul_ has joined.
21:18:37 -!- TieSoul has quit (Ping timeout: 245 seconds).
21:24:40 -!- doesthiswork has quit (Quit: Leaving.).
21:37:43 <cpressey> bugs me that -> is more like punctuation than a function constructor in this thing
21:42:57 <vanila> X -> Y could be thought of a syntactic sugar for (_ : X) -> Y
21:43:00 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
21:45:43 <cpressey> ah, there's no way. i'm too old for this.
21:53:09 <cpressey> and although it would be really cool to use metamath to prove properties of functions *starting from ZFC*
21:53:39 <cpressey> i think the obvious thing for me to do is write my own proof-checking language instead
21:59:36 -!- Phantom__Hoover has joined.
22:00:12 <cpressey> and, strangely, easier than learning Agda.
22:02:21 <b_jonas> I wouldn't think it'd be easy, but then, if you want to create a new esolang, I won't stop you in this channel.
22:12:39 <cpressey> tbh, i have had some ideas about one for a long time, but never went as far as implementing them. also, nb: proof-checker, not theorem-prover
22:16:41 <cpressey> there's a checker for metamath in 300-odd lines of Python, so it can't be ridiculously hard.
22:28:34 -!- cpressey has quit (Ping timeout: 245 seconds).
22:34:13 -!- AndoDaan has joined.
22:35:22 <AndoDaan> How do I ask for my messages again?
22:40:10 <AndoDaan> And how to record a message for someone?
22:40:54 <vanila> @tell AndoDaan like this
22:41:30 <AndoDaan> Grand. Thanks. I wish I had a better memory. Or more discipline to keep a cheat-sheet.
22:42:45 -!- Lymia has quit (Ping timeout: 250 seconds).
22:42:57 <AndoDaan> @tell mroman I actually took a look at the p section of FMNSSun a few days ago. And I'm thinking p~ still might be a little too complex for me atm.
22:45:47 -!- Lymia has joined.
23:01:09 <fizzie> Wiki gateway should be up now.
23:05:17 -!- spiette has quit (Ping timeout: 250 seconds).
23:14:29 <fizzie> The thing that puts esowiki edit info on the channel.
23:14:53 <fizzie> You know, the [wiki] things.
23:15:22 <fizzie> (It was allegedly down.)
23:15:49 <AndoDaan> Ah, thought it was something new
23:19:51 -!- arjanb has quit (Quit: zzz).
23:21:42 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
23:23:59 -!- chaosagent has joined.
23:27:16 -!- J_Arcane_ has joined.
23:28:31 -!- J_Arcane has quit (Ping timeout: 244 seconds).
23:28:38 -!- Phantom_Hoover has joined.
23:28:40 -!- J_Arcane_ has changed nick to J_Arcane.
23:31:36 -!- GeekDude has joined.
00:04:39 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
00:12:13 -!- mitchs has quit (Quit: mitchs).
00:15:09 -!- doesthiswork has joined.
00:19:23 -!- doesthiswork has quit (Ping timeout: 250 seconds).
00:39:53 -!- 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?").
01:21:27 -!- TieSoul_ has quit (Quit: No Ping reply in 180 seconds.).
01:22:52 -!- TieSoul has joined.
01:26:08 <vanila> i made gcc produce 400 lines of error mesages with a 3 line file
01:28:51 <lifthrasiir> vanila: http://tgceec.tumblr.com/post/74534916370/results-of-the-grand-c-error-explosion
01:30:36 <AndoDaan> Lol. There's a place for ppl like you, vanila. You belong.
01:33:08 -!- Tritonio has joined.
01:33:43 -!- simpleirc1 has joined.
01:35:15 <HackEgo> [wiki] [[EXPBLARGL]] http://esolangs.org/w/index.php?diff=42004&oldid=42003 * AndoDaan * (-11) Fixed "a language a language" typo.
01:36:05 <vanila> 647976 lines of errors from 2 lines of code
01:36:28 -!- simpleirc1 has quit (Remote host closed the connection).
01:41:01 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
01:50:25 -!- ProofTechnique has joined.
01:54:49 -!- vanila has quit (Quit: Leaving).
02:03:08 -!- AndoDaan has quit (Read error: Connection reset by peer).
02:21:01 -!- mitchs has joined.
03:17:25 <zzo38> That would be a lot, but, how long is each line and each error message?
03:30:08 -!- TieSoul has quit (Quit: No Ping reply in 180 seconds.).
03:31:31 -!- TieSoul has joined.
03:36:08 -!- Tritonio has quit (Remote host closed the connection).
03:39:55 -!- kapil___ has joined.
03:53:36 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:57:47 -!- Lymia has quit (Ping timeout: 250 seconds).
04:04:23 -!- Lymia has joined.
04:37:48 -!- Sketra has joined.
04:39:49 -!- TieSoul has quit (Quit: No Ping reply in 180 seconds.).
04:41:17 -!- TieSoul has joined.
04:42:39 -!- MDude has changed nick to MDream.
04:56:01 -!- Sketra has quit (Remote host closed the connection).
04:58:45 -!- dts|pokeball has joined.
04:58:58 -!- Sketra has joined.
04:59:46 -!- dts|pokeball has quit (Remote host closed the connection).
05:02:30 <HackEgo> [wiki] [[Clip]] N http://esolangs.org/w/index.php?oldid=42005 * Ypnypn * (+4023) Created page with "'''Clip''' is a functional language designed for both elegance and brevity. It was inspired by CJam, Lisp, Iota, and Pyth, in that order. ==Basics== ===Functions and supplier..."
05:17:35 -!- Sketra has quit (Remote host closed the connection).
05:19:37 <dulla> also, you guys were saying something about interplanetary ping, and such?
05:20:46 <dulla> apparently the guys behind ipfs hope to be solution for that in the future, via cache local friendliness, merkle dag based file addressing
05:41:10 -!- TieSoul_ has joined.
05:42:47 -!- TieSoul has quit (Ping timeout: 245 seconds).
05:48:47 -!- Lymee has joined.
05:50:16 -!- Lymia has quit (Ping timeout: 265 seconds).
06:34:23 -!- doesthiswork has joined.
06:37:22 -!- doesthiswork has quit (Quit: Leaving.).
06:41:14 -!- oerjan has joined.
06:55:56 -!- hjulle has quit (Ping timeout: 246 seconds).
07:20:40 <lambdabot> Plugin `compose' failed with: Unknown command: "fresh"
07:21:26 <oerjan> so @@ doesn't actually have access to all commands
07:21:53 <oerjan> and that one seems like it could be useful in @@, too
07:31:25 -!- Patashu has joined.
07:52:27 -!- mitchs_ has joined.
07:53:52 -!- chaosagent has quit (Ping timeout: 240 seconds).
07:54:49 -!- mitchs has quit (Ping timeout: 250 seconds).
07:56:57 -!- mitchs_ has quit (Ping timeout: 245 seconds).
08:33:51 -!- mitchs has joined.
09:16:57 -!- TieSoul has joined.
09:17:20 <int-e> always those extended cliff-hangers. http://www.schlockmercenary.com/2015-02-23
09:20:17 -!- TieSoul_ has quit (Ping timeout: 245 seconds).
09:20:56 <int-e> oerjan: early GG btw
09:32:15 -!- TieSoul_ has joined.
09:35:36 -!- AnotherTest has joined.
09:35:42 -!- TieSoul has quit (Ping timeout: 245 seconds).
09:39:55 -!- AnotherTest has quit (Ping timeout: 252 seconds).
09:59:02 <oerjan> int-e: i've closed my anagol tabs, it
09:59:38 <oerjan> 's begun to do that same annoying thing that got me to stop following the godel's letter blog
10:00:22 <oerjan> namely, at least with recent activity level, it has a recent entries list which cuts off after far less than a day
10:01:30 <oerjan> (i was far more interested in the blog, back then, but when it got to the point where i was checking rss last thing before going to bed _and_ first thing when getting up, i called it enough.)
10:01:41 <oerjan> *, and _still_ lost comments,
10:02:30 <oerjan> it had only a 10 comment buffer
10:03:14 <oerjan> and the admins ignored my pointing out the problem.
10:09:01 -!- TieSoul has joined.
10:09:02 <oerjan> last friday's xkcd was really good, especially the hover text
10:10:15 -!- NotSoul has joined.
10:10:17 -!- TieSoul_ has quit (Ping timeout: 245 seconds).
10:13:12 -!- TieSoul has quit (Ping timeout: 245 seconds).
10:19:14 <oerjan> int-e: hm could it be that martellus is the apprentice? he's "good" with animals and i recall violetta saying he also did things with bears.
10:19:49 <oerjan> the alternative would seem to be volkerstorfer
10:20:44 <oerjan> who's good with magnets instead
10:21:02 -!- AnotherTest has joined.
10:24:43 <oerjan> oh wait it explicitly addresses martellus as apprentice
10:29:20 -!- AnotherTest has quit (Ping timeout: 244 seconds).
10:51:17 -!- Tritonio has joined.
11:01:40 -!- Tritonio has quit (Remote host closed the connection).
11:02:25 -!- oerjan has quit (Quit: leaving).
11:19:02 -!- boily has joined.
11:19:42 <int-e> @tell oerjan yes I've noticed the recent activity cutoff on anagol as well. So I tend to just check the current problems for changes
11:34:24 -!- NotSoul has changed nick to TieSoul.
11:42:08 -!- Patashu has quit (Ping timeout: 265 seconds).
11:51:37 <HackEgo> [wiki] [[EXPBLARGL]] http://esolangs.org/w/index.php?diff=42006&oldid=42004 * Esowiki201529A * (-1) Fixed "estoteric" typo.
11:56:59 -!- Koen_ has joined.
11:57:54 -!- Koen__ has joined.
11:57:54 -!- Koen_ has quit (Read error: Connection reset by peer).
12:20:58 -!- boily has quit (Quit: PERIODIC CHICKEN).
12:31:40 -!- AnotherTest has joined.
12:42:23 -!- hjulle has joined.
12:51:28 -!- AnotherTest has quit (Ping timeout: 252 seconds).
13:06:00 -!- AnotherTest has joined.
13:11:04 -!- FreeFull has quit (Ping timeout: 265 seconds).
13:17:47 -!- vanila has joined.
13:45:04 -!- SopaXorzTaker has joined.
14:12:04 -!- FreeFull has joined.
14:18:21 -!- MDream has changed nick to MDude.
14:19:22 <MDude> Not bad, I woke up and so far not much is happening,.
14:19:34 <vanila> i might implement a language
14:26:09 <Koen__> vanila: you should implement When
14:28:37 <MDude> And also, genetically engineer an ostritch size bird with parrot-like intelligence and vocalization skill.
14:30:16 <Gregor> If we're genetically engineering birds, we may as well go all-out.
14:30:39 <Gregor> Genetically-engineer an ostrich size bird to have sauroid raptor-like claws and human intelligence.
14:31:13 <MDude> I'd stick with parrot-like and see where that goes.
14:31:16 -!- GeekDude has joined.
14:31:41 <MDude> If it was too smart, I'd know it'd be easy to negotiate with rationally.
14:32:04 <MDude> I want to see if parrots flip out as easily when they can build stuff with ahnds isntead of pecking and clawing madly.
14:33:27 <MDude> Some other birds might be even ebtter at sound mimmicry, though, so I might try to give them that.
14:33:47 <MDude> Like whatever it is that can mimmic camera shutter noise.
15:02:44 -!- AnotherTest has quit (Ping timeout: 252 seconds).
15:18:55 -!- `^_^v has joined.
15:21:58 -!- cpressey has joined.
15:24:58 <cpressey> elliott: if you're dealing with total functions, btw, some of the "shoehorn this into an algebraic structure" problems become a lot simpler
15:25:12 <elliott> wasn't burro sub-TC anyway
15:25:44 <vanila> cpressey, is burro related to that video i linked
15:25:46 <cpressey> potro was the one I was looking for
15:26:09 <elliott> TC would be nice/fun but annoying
15:26:15 <elliott> probably starting with something sub-TC to figure out how it'd all even work is best
15:26:18 <cpressey> vanila: i don't generally watch videos, so, i don't know
15:27:14 <cpressey> elliott: cabra was the result of trying to cram something TC into a ring, weakening the ring axioms and getting a dioid, which works, but is relatively boring b/c dioids are not uncommon
15:27:39 <elliott> didn't you just say cabra wasn't tc
15:27:43 <cpressey> could go the other way, "weaken" TC into... that
15:27:49 <cpressey> er, well, tbh i don't remember
15:28:01 <cpressey> i don't even remember what "potro" is spanish for anymore
15:28:15 <elliott> what does max on cabra programs actually do
15:28:31 <cpressey> max takes the one which... ran longer, i think
15:28:39 <elliott> butter, goat, foal apparently
15:28:44 <elliott> do you think butter is an animal
15:28:50 <elliott> that was google translate guessing diferent languages, heh
15:29:01 <elliott> okay donkey, goat, foal, that's much more boring
15:29:18 <elliott> please officially declare that burro's name is to be read in italian
15:29:36 <elliott> 15:28:39 <elliott> butter, goat, foal apparently
15:30:52 <cpressey> i remember once someone emailed me about cabra, complaining that it... abstracted to computations, but then cast it all in concrete terms of execution steps
15:31:21 <cpressey> well, yes, ok, that's a fair criticism, if that's the sort of thing you care about, i suppose
15:31:33 <cpressey> sometimes i get the feeling like i'm shouting into a paper bag
15:31:44 <elliott> i don't understand that criticism
15:33:10 <cpressey> oh wow I never markdown-ized the cabra docs
15:33:21 <elliott> yes I was reading html docs yesterday
15:33:21 <cpressey> oh, right, they have, like, superscripts and stuff in them
15:33:37 <elliott> well you can just use <sup> in markdown, better than nothing
15:33:56 <elliott> by "reading html" I mean the html source, on github.
15:34:53 <cpressey> https://rawgit.com/catseye/Cabra/master/doc/cabra.html
15:35:07 <cpressey> rawgit is good for reading HTML files on github
15:35:27 <elliott> there's no way I can remember that by the next time I need it
15:35:38 <vanila> is there a name for this restricted subset of js? http://patriciopalladino.com/blog/2012/08/09/non-alphanumeric-javascript.html
15:35:46 <vanila> is there an esowiki page for it?
15:35:50 -!- spiette has joined.
15:37:01 <HackEgo> [wiki] [[Special:Log/upload]] upload * Gamemanj * uploaded "[[File:BytePusherGamemanjConsoleTest.png]]": A picture of the "Console Test" program for BytePusher.
15:37:04 <elliott> cabra seems a bit close to the kind of cheating you ruled out for burro
15:37:10 <elliott> ("just do pointwise operations on the results or whatever")
15:37:22 <elliott> I guess * and + are different.
15:39:02 <cpressey> (as for the criticism, i'm pretty sure it was mostly a matter of someone not expecting to see the word "cycles" in the description of an abstract language)
15:39:26 <elliott> I guess your quotienting is quite weak, in effect
15:39:30 <HackEgo> [wiki] [[BytePusher]] http://esolangs.org/w/index.php?diff=42008&oldid=40701 * Gamemanj * (+453) /* Programs */ Added a new program("Console Test")
15:39:31 <cpressey> "just do pointwise..." not sure i understand
15:39:34 <elliott> you're exposing cycles rather than just taking functional extensionality or whatever
15:39:59 <cpressey> well, i mean, i really couldn't think of any other way to do it, mainly
15:40:18 <elliott> https://github.com/catseye/Chrysoberyl/blob/master/data/ideas.yaml#L540 okay yeah, this thing
15:40:23 <elliott> it's not really like that though after reading more
15:40:39 <elliott> extensionality is a nice concept
15:43:33 <cpressey> maybe you could do max by running the two programs "concurrently" and selecting the one that made a "larger" result, regardless of its runtime (like, it wrote more symbols to its tape?)
15:43:49 <cpressey> or smth. haven't thought about this in ages
15:44:21 <cpressey> but yeah, that Potro idea-entry explains why it's even tricky if the functions are total
15:44:50 <elliott> I mean with extensionality the most you can do is pointwise
15:44:59 <HackEgo> [wiki] [[Swearjure]] N http://esolangs.org/w/index.php?oldid=42009 * Cluid Zhasulelm * (+842) Creation
15:45:10 <elliott> like max of p and q is the program x |-> p(x) max q(x)
15:46:36 <cpressey> i believe you, and i'm sure it has implications that i can barely intuit
15:46:47 <elliott> afaict it's a boring observation
15:46:57 <elliott> also it's not like formally true probably you could come up with other weird operations that work
15:47:00 <elliott> they might not be computable though
15:47:05 -!- tromp_ has quit.
15:47:55 <cpressey> i'm sure i had other ideas of other things to do but i keep getting distracted
15:48:36 <elliott> you can probably define a TC ring programming language where the ring operations just aren't computable
15:48:41 <elliott> but it's not very exciting.
15:50:04 -!- tromp_ has joined.
15:56:01 <MDude> Makes some visuals in IBNIZ: dd80/s^1%?vv:vvq;^^1@-d1!
16:02:37 <cpressey> apparently, sometime last year, I stuffed crippled regular expressions into a ring
16:03:29 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] M http://esolangs.org/w/index.php?diff=42010&oldid=41552 * Cluid Zhasulelm * (+174)
16:03:29 <cpressey> crippled meaning, there's alternation and concatenation but no asteration
16:03:42 -!- SopaXorzTaker has quit (Ping timeout: 246 seconds).
16:16:10 <mroman> http://codepad.org/zxbyo6BU
16:16:13 <mroman> pretty trivial I guess
16:16:20 <mroman> shouldn't be hard to guess what does what
16:16:39 -!- SopaXorzTaker has joined.
16:20:16 <MDude> But what is it written in?
16:21:32 <mroman> my new language I just made up the last half hour
16:21:45 <vanila> whats unique about it?
16:22:15 <mroman> It's got blackjack and hookers
16:22:28 <mroman> It's just a very, very simple language
16:28:29 <Koen__> I don't see the blackjack and hookers :(
16:28:59 <Gregor> You can't SEE the blackjack and hookers. You just have to EXPERIENCE the blackjack and hookers.
16:29:23 -!- AndoDaan has joined.
16:29:44 <mroman> No, it's essentially just a stripped down imperative programming language
16:30:25 <mroman> that's what you pay them for
16:34:18 -!- gamemanj has joined.
16:34:45 <elliott> it would be cool if we stopped being gross
16:36:33 <vanila> I think it would be nice to have a language based on symbols other than ascii
16:36:53 <vanila> you could make an editor in javascript so pepole can use it from a webpage
16:37:38 <vanila> there was an elvish language with no example code recently.. and an arabic lisp
16:37:49 <vanila> and there's those picture based languages (colored pixels)
16:38:06 <elliott> there's that one korean fungelike
16:38:12 <elliott> fungeoid. whatever. *defers to cpressey*
16:38:27 <gamemanj> ...KlingonCode uses the Klingon alphabet, but there's no example programs...
16:39:30 <elliott> by defer I mean as to whether it's fungelike or fungeoid
16:39:36 <elliott> it's lifthrasiir's I think?
16:39:40 <int-e> Oh RingCode. RingCode seems to be more focussed on syntax than semantics.
16:40:07 <cpressey> today i feel like it should be "fungeistic". tomorrow i will feel differently
16:40:36 <cpressey> i was actually just impressed by the number of implementations of aheui
16:41:06 <gamemanj> ...Well, they're all by the same account, so maybe that person is just good at implementing aheui.
16:41:33 <gamemanj> (Unless there's others not on the github page?)
16:42:05 <cpressey> gamemanj: that's an organization account, there are like 8 or more members
16:42:19 <MDude> Sarus language has a nice set of symbols, though there's also an ASCII representation.
16:43:31 <cpressey> lifthrasiir: you don't happen to have a copy of the Udage spec, do you? :)
16:43:42 <MDude> There's also exactly seven of them, plus spaces. So I would encode each character as a single hex digit with one bit used for parity.
16:45:08 <cpressey> wayback machine didn't archive it when its site went down, and the wiki article is only partial: http://esolangs.org/wiki/Udage ... there is an implementation, so a spec could be reverse-engineered, sort of, if the spec is really gone
16:45:43 <gamemanj> If there's a implementation, but no spec, all that can really be done is to let the implementation take precedence.
16:46:22 <gamemanj> (Just hope the implementation doesn't have bugs that get written into the replacement spec.)
16:46:29 <cpressey> except where the implementation is "obviously" approximating things :)
16:47:39 <gamemanj> It's a esoteric language, obviously approximating is hard to define.
16:48:35 <gamemanj> If brainf*** was only defined by the implementation the old "cheating quine" would still be valid.
16:51:49 <vanila> I guess things like 'the ultimate machine' or whatever
16:51:59 <vanila> where you build a physical system that marbles fall etc..
16:52:32 <cpressey> I think that was called "The Incredible machine"
16:52:32 -!- sebbu2 has joined.
16:52:57 <gamemanj> ...Well, you can still define specs for marble-based computing.
16:53:11 -!- sebbu2 has quit (Changing host).
16:53:12 -!- sebbu2 has joined.
16:53:25 <gamemanj> You still need to define the "instruction set", in whatever form.
16:53:34 <Gregor> Damn it, you got the Marble Madness music stuck in my head.
16:54:15 -!- sebbu has quit (Ping timeout: 244 seconds).
16:58:52 -!- gamemanj has quit (Quit: ircII EPIC4-2.10.5 -- Are we there yet?).
17:00:39 -!- AndoDaan has quit (Ping timeout: 252 seconds).
17:01:33 -!- adu has joined.
17:05:05 -!- AndoDaan has joined.
17:14:51 -!- AnotherTest has joined.
17:20:12 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:25:47 -!- spiette has quit (Ping timeout: 265 seconds).
17:26:25 -!- sebbu2 has changed nick to sebbu.
17:44:09 -!- arjanb has joined.
18:01:53 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:02:14 -!- Tritonio has joined.
18:06:54 -!- Tritonio has quit (Remote host closed the connection).
18:18:25 <vanila> http://akira.ruc.dk/~madsr/webpub/absint.pdf
18:18:45 <vanila> could anyone help me understand page 8/9 of this please?
18:19:22 <vanila> I don't know what E[[ a_i(e_1, ..., e_k) ]] phi nu = strict basic_i < ... > means
18:19:52 -!- FreeFull has quit (Ping timeout: 245 seconds).
18:21:46 <cpressey> that said, i don't know if i can help
18:25:04 <vanila> so that would be stuff like + I guess, which is trict
18:25:30 <vanila> would have made sense for them to put all that before using it...
18:27:41 -!- FreeFull has joined.
18:37:58 <vanila> so this is about strictness analysis
18:38:04 <vanila> and they give examples of strict functions
18:38:12 <vanila> but I don't think there is any such thing as a non-strict function in this language
18:38:20 <vanila> except one ones that ignore their arguments completely
18:40:56 <cpressey> i might try actually reading it at some point.
18:41:13 -!- cpressey has quit (Quit: leaving).
18:56:55 <vanila> ok there non trivial thing is not 'is this function strict' but 'is there any way for this function to return a value given these inputs'
19:14:33 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42011&oldid=42005 * Ypnypn * (+1853)
19:20:40 -!- ais523 has joined.
19:29:03 <J_Arcane> hah hah. that syntax reminds me of ANSI sequences.
19:33:55 -!- callforjudgement has joined.
19:34:03 -!- ais523 has quit (Disconnected by services).
19:34:05 -!- callforjudgement has changed nick to ais523.
19:37:53 -!- callforjudgement has joined.
19:38:04 -!- ais523 has quit (Disconnected by services).
19:38:05 -!- callforjudgement has changed nick to ais523.
20:02:34 -!- Patashu has joined.
20:04:13 <myname> since i cannot find anythig about it: will haskell automatically make Directory/File.hs into something importable as Directory.File?
20:10:04 <myname> if so, what do i have to put in the module name?
20:16:11 <myname> and how do i import something from a parent directory?
20:17:05 <elliott> Foo/Bar/Baz.hs can import Foo.Quux
20:17:17 <elliott> well, it's relative from where you run GHC
20:17:23 <elliott> but really you should be using cabal or something
20:25:35 -!- Patashu has quit (Ping timeout: 265 seconds).
20:45:18 -!- AndoDaan has quit (Quit: Going, going, gone.).
20:51:19 -!- zzo38 has quit (Remote host closed the connection).
21:06:32 -!- spiette has joined.
21:11:16 -!- bb010g has joined.
21:15:32 -!- sebbu has quit (Ping timeout: 246 seconds).
21:23:34 -!- dts|pokeball has joined.
21:29:24 -!- dts|pokeball has quit (Quit: Leaving).
22:09:05 -!- ais523 has quit (Read error: Connection reset by peer).
22:09:18 -!- ais523 has joined.
22:09:21 -!- AnotherTest has quit (Ping timeout: 256 seconds).
22:16:00 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42012&oldid=42011 * Ypnypn * (+1754)
22:36:44 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:37:14 -!- callforjudgement has joined.
22:37:42 -!- ais523 has quit (Disconnected by services).
22:37:44 -!- callforjudgement has changed nick to ais523.
22:38:13 -!- `^_^v has joined.
22:39:32 <vanila> what's happening esoteric
22:42:14 <MDude> Wait, I think I forgot to save the thing I was making earlier.
22:43:21 <vanila> IBNIZ is a virtual machine designed for extremely compact low-level audiovisual programs
22:47:10 -!- callforjudgement has joined.
22:47:10 -!- ais523 has quit.
22:47:15 -!- callforjudgement has changed nick to ais523.
22:50:55 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42013&oldid=42012 * Ypnypn * (+1127)
23:02:58 -!- Tritonio has joined.
23:04:30 <MDude> And that is what's happening.
23:05:33 <MDude> 10000@@//+d10000@!
23:07:40 <MDude> Actually, make that + a ^
23:14:32 -!- sebbu has joined.
23:14:52 -!- MDude has quit (Ping timeout: 245 seconds).
23:15:11 -!- sebbu has quit (Changing host).
23:15:11 -!- sebbu has joined.
23:17:42 -!- 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?").
23:26:44 -!- chaosagent has joined.
23:27:00 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:27:49 -!- `^_^v has joined.
23:28:21 -!- Phantom_Hoover has joined.
23:34:47 <Phantom_Hoover> you know, i like the general trajectory my topology courses have followed
23:36:01 <Phantom_Hoover> you start out defining general point-set topology and learning all these insane counterexamples to every property you encounter
23:36:22 <Phantom_Hoover> by the time you get to homology, you assume everything is a CW complex
23:36:22 -!- adu has quit (Ping timeout: 240 seconds).
23:38:35 -!- ais523 has quit.
23:38:46 -!- ais523 has joined.
23:39:41 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:40:57 -!- boily has joined.
23:48:08 -!- ais523 has quit (Remote host closed the connection).
23:48:16 -!- ais523 has joined.
23:48:30 -!- ais523 has quit (Changing host).
23:48:30 -!- ais523 has joined.
23:48:53 <dulla> ok? Phantom_Hoover
23:56:13 -!- adu has joined.
23:56:39 -!- oerjan has joined.
23:58:01 <lambdabot> shachaf said 12h 54m 49s ago: only occasionally, mostly to search for my name
23:58:01 <lambdabot> int-e said 12h 38m 18s ago: yes I've noticed the recent activity cutoff on anagol as well. So I tend to just check the current problems for changes
00:02:56 -!- Tritonio_ has joined.
00:05:24 -!- Tritonio has quit (Ping timeout: 272 seconds).
00:06:30 <HackEgo> [wiki] [[EXPBLARGL]] http://esolangs.org/w/index.php?diff=42014&oldid=42006 * Chris Pressey * (+1846) Fix EXPBLARGL (hopefully) and add history section
00:07:59 -!- Tritonio_ has changed nick to Tritonio.
00:20:05 * oerjan hopes boily is referring to what he thinks and not the file transfer protocol
00:20:16 <oerjan> and i didn't even answer the poll
00:24:14 <boily> I didn't even the poll answer too. and yes I was mentioning the FTP, not FTP.
00:24:59 <lambdabot> CYUL 240000Z 24008KT 15SM FEW240 M21/M29 A3034 RMK CI1 CI TR SLP277
00:25:35 <elliott> Data.List is going to be a real mess.
00:26:06 <boily> and? we've got the AMP, the FTP, Stackage with LTS. we live in good times!
00:26:23 <oerjan> (good acronymical times)
00:27:19 <oerjan> you may think so, good times ???
00:27:26 <elliott> haskell is so ugly from a distance :p
00:28:09 <boily> You Meant To Say Good TLA Times.
00:29:21 <oerjan> a bucket of flowers, that's the best gift
00:29:37 * boily twitches “/ɛ/ is not /e/!”
00:30:13 <oerjan> wait which one of those is /ɛ/
00:30:33 <oerjan> i'm not sure our french class even taught that properly
00:30:48 <boily> /ɛ/, commonly written è or ê, as in père, fête...
00:31:08 <oerjan> yes, but are you saying the -ET in BOUQUET is pronounced that way?
00:31:52 <boily> but then, word end /ɛ/ and /e/ has mostly merged together in France French, resulting in endless grammatical errors.
00:32:01 <oerjan> technically i should have noticed that three minutes ago when i googled bouquet
00:32:16 <oerjan> although i was only looking to check the spelling
00:32:18 <boily> (much confusion going on between the future and conditional, e.g. «j'aurai» and «j'aurais»)
00:32:50 <boily> Jafellot. good Japanese example.
00:34:53 <oerjan> boily: 's ok our class never got beyond the simplest past tense anyway
00:35:24 <boily> the joys of irregular verbs ^^
00:36:36 <oerjan> which confusingly is the _opposite_ of what french calls passé simple
00:37:26 <boily> nobody (except poets) use the passé simple anymore, not even books. the third person plural passé simple lingered last, but went extinct.
00:38:11 <boily> it's all passé composé, imparfait, plus-que-parfait, and some weird subjunctive mood if you're feeling fancy.
00:40:01 <oerjan> wikipedia says the opposite
00:40:18 <oerjan> "Many students of French are surprised to find that even books for elementary-aged French children are written using the passé simple, even though it is only taught to learners of French in advanced classes."
00:41:07 <boily> “In modern spoken French, the passé simple has practically disappeared.”
00:41:46 <boily> “... which are rarely if ever used in contemporary French, even in writing.”
00:42:05 <oerjan> that's about the plurals
00:43:22 <boily> the French version has «À l'écrit, en revanche, le passé simple reste extrêmement vivant et productif aux troisièmes personnes du singulier et du pluriel.»
00:43:26 <boily> I stand corrected.
00:43:54 <boily> dulla: a French verb conjugation.
00:44:49 <boily> oerjan: so both versions agree that it almost completely disappeared from oral communication, but it remains commonly written.
00:45:01 <boily> (except for regional variations.)
00:47:29 <boily> it remains the case that I need references when I use it. for me it's all imparfait and passé composé.
00:48:00 <boily> otoc, are there any weird Norwegian conjugation variations?
00:48:07 <boily> (otoc: on the other continent)
00:49:06 <oerjan> i think the subjunctive counts as extremely archaic
00:49:56 <oerjan> there's only the present subjunctive, which is identical to the infinitive, and the only use i can think of on the spot is "leve kongen" ((long) live the king)
00:50:44 <boily> same here. «Vive le Roi».
00:50:51 <oerjan> other than that, norwegian verb forms are basically the same as english minus progressive and person/number
00:52:09 <oerjan> in some dialects, the past participle may get inflected for gender when _not_ used with the verb "ha"
00:52:27 <oerjan> (where "some dialects" includes nynorsk)
00:54:40 <oerjan> norwegian verbs aren't very complicated. although we also have irregular/strong verbs like synge/sang/sunget
00:55:43 <oerjan> hm actually the suffixes for "regular" verb pasts are more complicated than in english.
00:56:33 <oerjan> -et, -dde, -te are some possibilities.
00:57:40 <oerjan> mostly guessable from phonology, though.
00:58:35 <boily> we should unify French and Norwegian verbs together. je mangedde.
00:59:13 <oerjan> basically -dde is used for verbs with a vowel-ending stem
00:59:54 <oerjan> and -te is used otherwise unless the result would be hard to pronounce, in which case you use -et.
01:00:52 <oerjan> this is bokmål, nynorsk has -a, -dde, -te/-de or thereabouts
01:01:33 <oerjan> with -a occasionally being used in "radical" bokmål.
01:04:50 -!- AndoDaan has joined.
01:05:00 <oerjan> there's a kind of continuum from conservative "riksmål" through ordinary bokmål, via the mostly abandoned "samnorsk" which was an attempt to merge all the writing forms, via normal nynorsk and then to conservative "høgnorsk"
01:06:15 <oerjan> the radical bokmål is somewhere between bokmål and samnorsk, and it's stereotypically connected to 70s communists i think.
01:06:33 * boily sips some scotch, nods, and lightly grunts in approval while he tries to hide the vacant look in his eyes
01:06:50 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds).
01:06:57 * oerjan approves of the scotch
01:07:09 <boily> (no, I'm not scared by the plural multiplicity of Norwegian varieties. not at all.)
01:07:25 <boily> Laphroaig Quarter Cask, straight with a glass of water.
01:07:56 <oerjan> _most_ people write bokmål, which has slipped gradually back toward the conservative after the samnorsk fiasco ended. i think.
01:08:17 <oerjan> i am not very up to date to the developments in the last 20 years or so.
01:08:39 <oerjan> i hear in oslo they generally speak "kebabnorsk" these days, because of all the immigrants.
01:10:53 <oerjan> with some luck the labor party may get a muslim vice leader this year
01:11:09 <oerjan> she did well as a government minister
01:12:53 <oerjan> (she's of course of the very liberal kind)
01:14:11 * oerjan tries to get back to ghc news
01:35:29 -!- ais523 has quit (Remote host closed the connection).
01:35:36 -!- callforjudgement has joined.
01:37:20 -!- AndoDaan_ has joined.
01:37:42 -!- ais523 has joined.
01:39:29 -!- AndoDaan has quit (Ping timeout: 252 seconds).
01:39:52 -!- skj3gg has joined.
01:40:01 -!- callforjudgement has quit (Ping timeout: 264 seconds).
01:58:58 <boily> elliott: I think I'm going to like lignification potions. trees hit hard!
01:59:31 <elliott> they also can't move right
01:59:41 <elliott> go chei for synergy with potion of tree
01:59:43 -!- vanila has quit (Quit: Leaving).
02:08:45 -!- Tritonio has quit (Remote host closed the connection).
02:08:49 -!- _AndoDaan_ has joined.
02:11:00 -!- skj3gg has quit (Quit: ZZZzzz…).
02:11:09 -!- AndoDaan_ has quit (Ping timeout: 250 seconds).
02:13:51 <HackEgo> [wiki] [[Esolang talk:About]] http://esolangs.org/w/index.php?diff=42015&oldid=30624 * 189.78.226.185 * (+114) limes?
02:14:12 <ais523> ooh, someone asked about the limes again
02:16:04 <HackEgo> [wiki] [[Esolang talk:About]] http://esolangs.org/w/index.php?diff=42016&oldid=42015 * Ais523 * (+320) my memory of the limes
02:16:49 <boily> ais523: what limes?
02:17:17 <ais523> is a picture of some limes
02:17:23 * boily suddenly feels very stupid.
02:20:08 <oerjan> limes computandi esoterici
02:21:00 <oerjan> limes computandus esotericus
02:22:23 <boily> the urge to do something similar to Resplicate intensifies.
02:22:34 <boily> quintopia: speaking of Resplicate, quinthellopia!
02:29:50 <oerjan> i think it may be the simplest queue-that-contains-both-data-and-program language that i've seen proved TC yet
02:30:30 <oerjan> unlike fueue, it doesn't contain arbitrarily complicated elements.
02:30:56 <oerjan> however, it still needs arbitrarily large numbers in its elements
02:31:47 <oerjan> i don't think i've seen yet a TC queue language in which there is a strict boundary to how much data a single command can affect
02:34:26 <oerjan> i suppose you could _probably_ make something that emulated a chosen CA with the ability to insert new cells
02:37:57 <boily> what is the probable minimum limit on the kinds of cells in a variable width CA that would make it "interesting" and/or TC?
02:38:34 <oerjan> "variable width" is like not CA by definition
02:39:21 <boily> that's the thing :/
02:40:07 <oerjan> i am thinking in terms of "enough power to simulate a TM" here
02:40:23 <boily> (please don't tell me it's a kind of lime.)
02:40:26 <oerjan> which means you need only CA things + the ability to extend the type
02:41:18 -!- callforjudgement has joined.
02:41:31 -!- ais523 has quit (Disconnected by services).
02:41:33 -!- callforjudgement has changed nick to ais523.
02:41:52 <boily> oh. right. tdh. >_>'...
02:42:01 <oerjan> i am still not sure that rule 110 with all but finitely many cells 0 isn't enough
02:42:25 <oerjan> because it can grow leftwards just fine
02:42:54 -!- doesthiswork has joined.
02:43:12 <oerjan> and at least one glider gun is known
02:44:17 <boily> the game of life is very much well très TC.
02:44:57 <oerjan> ...although i wonder if anyone has found a way to make it "halt"
02:45:19 <oerjan> as in, like, delete itself
02:45:53 <oerjan> the game of life is, however, 2d, which is rather impractical to use as target for a queue emulation.
02:47:03 <boily> hmm... perhaps some puffer train? I haven't seen, nor heard of any patterns outside of trivial ones that purposefully delete themselves.
02:47:19 -!- callforjudgement has joined.
02:47:23 <boily> (trivial encompassing only very small about-three-live-cells patterns.)
02:47:39 -!- ais523 has quit (Disconnected by services).
02:47:40 -!- callforjudgement has changed nick to ais523.
02:48:24 <oerjan> i assume you could maybe run that universal constructor thing in reverse
02:48:45 <oerjan> except you'd have to be clever to make it work on itself...
02:49:03 <ais523> oerjan: you could create some glider reflectors at huge distance
02:49:10 <ais523> that get destroyed upon reflecting a glider
02:49:17 <ais523> then you just need a glider desynthesis that works on your TM pattern
02:49:46 <oerjan> yeah it doesn't sound impossible
02:49:53 <boily> glider desynthesase!
02:51:31 <oerjan> hm i wonder if von neumann's original self-replicating CA was inspired by knowledge about dna and stuff, or if he just considered it the obvious way to do it
02:54:03 <oerjan> "This insight is all the more remarkable because it preceded the discovery of the structure of the DNA molecule by Watson and Crick, though it followed the Avery-MacLeod-McCarty experiment which identified DNA as the molecular carrier of genetic information in living organisms."
03:02:23 -!- boily has quit (Quit: LAMINATED CHICKEN).
03:08:21 -!- skj3gg has joined.
03:17:59 -!- skj3gg has quit (Quit: ZZZzzz…).
03:50:43 -!- arjanb has quit (Quit: zzz).
03:51:15 -!- skj3gg has joined.
03:53:40 -!- MoALTz_ has quit (Ping timeout: 255 seconds).
03:55:01 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
03:58:42 -!- ProofTechnique has joined.
04:09:57 -!- Magnet_Dude has joined.
04:29:50 -!- dts|pokeball has joined.
04:36:49 -!- _AndoDaan_ has quit (Quit: Going, going, gone.).
04:44:52 -!- dts|pokeball has quit (Ping timeout: 240 seconds).
04:50:11 -!- Lymee has quit (Ping timeout: 265 seconds).
04:57:27 -!- Magnet_Dude has changed nick to MDream.
05:02:38 -!- Lymia has joined.
05:10:04 -!- doesthiswork has quit (Quit: Leaving.).
05:16:06 -!- doesthiswork has joined.
05:17:33 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
05:19:09 -!- callforjudgement has joined.
05:19:14 -!- ais523 has quit (Disconnected by services).
05:19:16 -!- callforjudgement has changed nick to ais523.
05:24:57 -!- skj3gg has quit (Quit: ZZZzzz…).
05:39:19 -!- skj3gg has joined.
05:50:00 -!- ais523 has quit.
06:03:19 -!- doesthiswork has quit (Quit: Leaving.).
06:07:25 -!- skj3gg has quit (Quit: ZZZzzz…).
07:23:38 -!- AnotherTest has joined.
07:49:14 -!- Patashu has joined.
07:54:34 -!- Lymia has quit (Ping timeout: 256 seconds).
07:55:40 -!- Lymia has joined.
08:14:57 -!- CADD has joined.
08:32:03 -!- Lymia has quit (Ping timeout: 250 seconds).
08:34:29 -!- Lymia has joined.
08:54:08 -!- chaosagent has quit (Ping timeout: 246 seconds).
09:04:41 -!- weissschloss has quit (Remote host closed the connection).
09:12:30 -!- kapil___ has quit (Quit: Connection closed for inactivity).
09:21:08 <myname> is there any way to resolve cyclic dependencies in cabal?
09:21:32 <myname> i fear it will lead to an extra module ...
09:22:05 <oerjan> what does cabal have to do with it?
09:23:27 <oerjan> https://downloads.haskell.org/~ghc/latest/docs/html/users_guide/separate-compilation.html#mutual-recursion
09:23:52 <oerjan> you do, in fact, need an extra file.
09:25:43 <oerjan> i think recommended practice is to reorganize your modules instead whenever possible
09:27:02 <myname> yeah, i think i will do that
09:28:51 -!- Patashu has quit (Remote host closed the connection).
09:28:52 <myname> i am currently rewriting older stuff of myself to make stuff more exchangeable
09:29:10 -!- Patashu has joined.
09:57:43 -!- AnotherTest has quit (Ping timeout: 255 seconds).
10:01:14 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[JSFuck]] to [[Javascript fuck]]
10:01:55 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Esowiki201529A * moved [[Javascript fuck]] to [[JSFuck]] over redirect
10:02:41 -!- oerjan has quit (Quit: Later).
10:18:36 -!- Phantom_Hoover has joined.
10:21:35 -!- gamemanj has joined.
10:36:54 -!- SopaXorzTaker has joined.
10:44:07 <HackEgo> [wiki] [[Template:X1]] N http://esolangs.org/w/index.php?oldid=42021 * Esowiki201529A * (+264) "wiki cyclic tag" test.
10:53:08 <gamemanj> ...what the... what is that, exactly...?
10:54:46 <gamemanj> Judging by the name, I'm guessing something to do with cyclic tags....Are you trying to use the wiki as a esoteric programming language???
10:55:51 <b_jonas> gamemanj: it's an implementation of cyclic tag with mediawiki templates I think
11:00:29 <b_jonas> gamemanj: http://esolangs.org/wiki/Wiki_Cyclic_Tag
11:04:36 -!- Patashu has quit (Disconnected by services).
11:04:36 -!- Patashu_ has joined.
11:24:10 -!- boily has joined.
11:24:56 <gamemanj> I wonder why BytePusher is so unpopular?
11:26:30 -!- adu has quit (Quit: adu).
11:38:54 -!- gamemanj has quit (Quit: ircII EPIC4-2.10.5 -- Are we there yet?).
12:12:41 -!- vanila has joined.
12:13:49 -!- hjulle has quit (Ping timeout: 252 seconds).
12:15:48 -!- Patashu_ has quit (Ping timeout: 256 seconds).
12:17:13 -!- vanila has quit (Ping timeout: 264 seconds).
12:22:21 -!- vanila has joined.
12:25:17 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
12:27:59 -!- AnotherTest has joined.
12:31:17 -!- boily has quit (Quit: BARYCENTRIC CHICKEN).
12:45:55 -!- ais523 has joined.
12:49:33 -!- kapil___ has joined.
13:02:31 <HackEgo> [wiki] [[MICE]] M http://esolangs.org/w/index.php?diff=42022&oldid=40943 * Ais523 * (-195) fix the spec to not trigger the spam filter; most of our spambots don't know how newlines work, apparently this page didn't either
13:03:34 <vanila> haha that edit summary :P
13:04:03 <ais523> caught that one looking over past spam filter hits
13:04:19 <ais523> although the last person to trigger it is oerjan, who (being an admin) was able to override it
13:05:24 <vanila> http://esolangs.org/wiki/Java%27
13:05:28 <vanila> this sounds silly and not esoteric
13:06:06 <ais523> also I'm not sure if the statement made there is even correct
13:07:13 <ais523> I mean, Java-minus-Object is still TC
13:07:21 <ais523> but I don't think you can compile Java into it directly
13:07:36 <ais523> because heterogeneous lists would no longer be implementable
13:09:32 -!- skj3gg has joined.
13:11:36 <vanila> ais523, do you want to look at my quine in minikanren (its a schemey prolog)?
13:12:07 <vanila> http://lpaste.net/121083
13:12:36 <vanila> it's so long, I wonder if it can be shorter
13:12:53 <vanila> there's an online interpreter if you want to try it
13:12:58 <vanila> although you can probably guess what it outputs
13:14:27 <ais523> someone on some mailing list used to have a signature along the lines of "I lost the source code to all my quines! How will I recover it from the binaries?"
13:17:17 -!- SopaXorzTaker has quit (Remote host closed the connection).
13:24:57 -!- SopaXorzTaker has joined.
13:30:27 -!- _AndoDaan has joined.
13:33:53 -!- skj3gg has quit (Quit: ZZZzzz…).
13:41:49 -!- vanila has quit (Ping timeout: 264 seconds).
13:42:09 -!- skj3gg has joined.
13:57:14 -!- SopaXorzTaker has quit (Remote host closed the connection).
14:04:00 <tromp_> too verbose. how about just: "can someone help me disassemble these quines?"
14:10:40 <ais523> e.g. via using a compiler?
14:15:00 <int-e> . o O ( Unfortunately I also lost the Turing Machine that could run those binaries them. )
14:18:02 <ais523> how do you create a turing machine quine anyway?
14:19:11 <tromp_> by making a programming language resembling TMs. e.g. bf
14:25:06 <Taneb> ais523, I want to actually demonstrate a StackFlow MtG game at some point
14:25:11 <Taneb> What cards will I need?
14:25:23 <ais523> Taneb: b_jonas has some concerns about the construction
14:25:39 <ais523> but basically, it's just the cards mentioned in the article, plus a bunch of copy effects
14:25:44 <ais523> plus some way to loop your library
14:26:01 <ais523> also, if you plan to do this competitively, you'll need some way to stop your opponent winning until you can set the situation up
14:26:33 <ais523> there's a combo deck around somewhere which needs a lot of luck, but gives you perfect control of the gamestate if you're lucky enough that the combo gets set off
14:26:43 <ais523> wouldn't be 100% impossible that you could pull it off in a tournament
14:27:00 <Taneb> One concern a friend of mine who knows Magic better than I do raised was table space, if you need a large number of creatures
14:27:19 <ais523> you do need a large number of creatures
14:27:55 -!- SopaXorzTaker has joined.
14:28:06 <ais523> anyway, the critical cards to the combo are: Noxious Ghoul; Dralnu's Crusade; Cathar's Crusade
14:28:27 <ais523> plus you need a text-changing effect, Artificial Evolution is the one mentioned in the article, but you could swap it out with anything that changes creature types
14:28:44 <ais523> finally, you need Engineered Plague or an equivalent
14:28:58 <ais523> oh, and Rotlung Reanimator
14:29:04 <ais523> I think that's it for the cards that don't have easy substitutes
14:29:33 <Taneb> I went through the construction listed on the wiki and I have a list of needed cards, but I don't know a thing about quantities or anything I am afraid
14:29:42 -!- _AndoDaan has quit (Ping timeout: 265 seconds).
14:30:02 <ais523> basically you need hundreds of copies of most of the cards; you can only run 4 in a deck
14:30:08 <ais523> so what you do is run a huge number of copy effects
14:30:12 <ais523> rite of replication is a good one
14:30:14 -!- _AndoDaan has joined.
14:30:18 <ais523> then you need to run library loop effects too
14:30:23 <ais523> so that you don't run out of cards
14:30:29 <ais523> two copies of elixir of immortality will do for that
14:31:11 -!- skj3gg has quit (Quit: ZZZzzz…).
14:31:45 <ais523> Taneb: so basically what you actually need, if you have infinite time to set up
14:32:01 <ais523> is all the cards listed on the wiki, plus rite of replication, plus two copies of elixir of immortality
14:32:11 <ais523> actually I think you can make do with one?
14:32:18 <ais523> also, plus enough land to get this started
14:32:33 <ais523> I recommend running an infinite mana combo too
14:32:44 <ais523> (my favourite is izzet guildmage + three copies of rite of flame, but there are tons)
14:33:54 <ais523> anyway, bear in mind that that construction will take a long, long time to set up
14:34:11 <ais523> I'd guess it'd be on the order of 1000 creature and enchantment tokens just to start the thing off
14:34:44 <ais523> anyway, b_jonas is right in that the triggers for "pop" actions can stack in the wrong order
14:35:15 <HackEgo> [wiki] [[Talk:StackFlow]] http://esolangs.org/w/index.php?diff=42023&oldid=41663 * Ais523 * (+201) suggestions for a fix?
14:38:55 <Taneb> I only started playing Magic a couple of months ago - partially because I wanted to understand this construction - and I am not very good at it yet
14:39:24 <ais523> that's a really bad reason to start Magic
14:39:49 <Taneb> Also because a few of my friends play it often and it seemed fun
14:40:22 -!- Koen__ has joined.
14:40:31 <ais523> it's fun-ish but terrible value for money
14:40:48 <Taneb> I have thus far avoided spending any money on it
14:40:48 -!- Koen__ has quit (Read error: Connection reset by peer).
14:41:02 -!- Koen__ has joined.
14:41:33 <ais523> oh, in that case, continue as you are
14:41:41 <Taneb> I was going to go to a prerelease but I felt ill/anxious
14:41:45 -!- ais523 has quit (Quit: meeting).
14:52:51 -!- Lymia has quit (Remote host closed the connection).
14:54:55 -!- Lymia has joined.
14:55:06 <b_jonas> wait, this construction has actually inspired you to start playing Magic? then esolangs are totally WORTH and have good unintended side effects!
14:55:26 <b_jonas> "Also because a few of my friends play it often and it seemed fun" -- aww, why do you have to ruin the illusion
14:56:03 <Taneb> b_jonas, it largely seemed fun because "Wow, this card game is TURING COMPLETE? This is exactly the sort of ridiculousness that I think I like!"
15:06:31 -!- `^_^v has joined.
15:06:45 <dulla> magic? the deck shuffling one?
15:22:30 -!- kapil___ has quit (Quit: Connection closed for inactivity).
15:40:51 -!- MDream has changed nick to MDude.
16:04:10 -!- SopaXorzTaker has quit (Ping timeout: 256 seconds).
16:17:23 -!- SopaXorzTaker has joined.
16:32:58 -!- _AndoDaan has changed nick to AndoDaan.
16:55:31 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42024&oldid=42013 * Ypnypn * (+3222)
16:57:03 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42025&oldid=42024 * Ypnypn * (+34)
17:12:13 -!- oerjan has joined.
17:14:58 -!- Tritonio has joined.
17:15:22 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
17:16:35 -!- ^v has quit (Quit: Network ban).
17:16:51 -!- ^v has joined.
17:20:13 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:21:41 -!- ^v has quit (Client Quit).
17:22:19 -!- ^v has joined.
17:30:01 -!- ^v has quit (Quit: Network ban).
17:30:20 -!- ^v has joined.
17:45:16 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42026&oldid=42025 * Ypnypn * (+2632)
17:48:03 -!- adu has joined.
17:54:28 -!- Tritonio has quit (Ping timeout: 272 seconds).
17:55:16 -!- Tritonio has joined.
17:58:08 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42027&oldid=42026 * Ypnypn * (+1085)
17:59:31 -!- MoALTz has joined.
18:03:28 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42028&oldid=42027 * Ypnypn * (+128)
18:04:21 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42029&oldid=42028 * Ypnypn * (+3)
18:07:21 * oerjan checks awkward fumbles on mezzacotta and notices there have been several new comics since last he checked
18:09:08 -!- FreeFull has quit (Ping timeout: 265 seconds).
18:10:01 <oerjan> well, there were two, which appeared less than a month after the last one i remember
18:14:34 -!- AndoDaan has quit (Quit: Bye).
18:15:00 -!- AndoDaan has joined.
18:23:11 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=42030&oldid=41870 * Oerjan * (-13) /* A colon semicolon */ Name
18:23:12 -!- ProofTechnique has joined.
18:26:02 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:27:36 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
18:28:38 <HackEgo> [wiki] [[EsoInterpreters]] http://esolangs.org/w/index.php?diff=42031&oldid=41918 * Oerjan * (+495) /* Main table */ Deadfish in A:;
18:31:54 -!- rsal has left.
18:50:41 <HackEgo> [wiki] [[EsoInterpreters]] http://esolangs.org/w/index.php?diff=42032&oldid=42031 * Oerjan * (+3511) /* Main table */ Deadfish in Burlesque, Chicken, DL, Forobj, Stackstack, StaPLe, WARP
18:54:19 -!- bb010g has joined.
18:54:58 <AndoDaan> Cleaning house in case reddit might call, Oerjan? (well, that Hello World website via reddit)
18:58:25 <HackEgo> [wiki] [[List of ideas]] M http://esolangs.org/w/index.php?diff=42033&oldid=41947 * Oerjan * (-1) tpyo
19:02:14 -!- GeekDude has joined.
19:02:58 <HackEgo> [wiki] [[Esolang talk:Categorization]] M http://esolangs.org/w/index.php?diff=42034&oldid=41977 * Oerjan * (+1) /* Proposed Category:Big Five */ fix category link
19:09:17 -!- Tritonio_ has joined.
19:11:14 -!- Tritonio has quit (Ping timeout: 252 seconds).
19:14:49 -!- Tritonio_ has changed nick to Tritonio.
19:22:53 -!- coppro has quit (Remote host closed the connection).
19:23:25 <HackEgo> [wiki] [[Talk:Onoz]] M http://esolangs.org/w/index.php?diff=42035&oldid=42001 * Oerjan * (+55) unsigned
19:32:50 -!- coppro has joined.
20:03:41 -!- Patashu has joined.
20:05:07 -!- kcm1700_ has quit (Remote host closed the connection).
20:05:27 -!- kcm1700 has joined.
20:24:25 -!- Patashu has quit (Ping timeout: 256 seconds).
20:36:39 <b_jonas> hey look, if I pass the right arguments to the compiler, it generates better optimized code
20:36:51 <b_jonas> the hard part is to figure out what the right arguments are
20:37:17 <int-e> --ignore-source-code --use-this-optimized-object-file
20:37:57 -!- ^v^v has joined.
20:39:15 <b_jonas> I still don't understand some of the stuff it does though
20:40:27 <b_jonas> are these pointless register moves really necessary?
20:40:55 -!- ^v has quit (Ping timeout: 250 seconds).
20:41:04 <int-e> b_jonas: there are papers on this with titles like "A Genetic Algorithm approach towards compiler flag selection based on compilation and execution duration."
20:41:26 -!- Tritonio has quit (Ping timeout: 252 seconds).
20:42:41 -!- Tritonio has joined.
20:42:44 <int-e> (Ok, I actually stopped looking after I found the first one. I bet there are more though.)
20:48:02 -!- nys has joined.
20:50:14 -!- AndoDaan has quit (Ping timeout: 245 seconds).
20:51:43 -!- AndoDaan has joined.
20:53:49 -!- SirCmpwn has quit (Quit: ZNC - http://znc.in).
20:55:50 -!- AndoDaan has quit (Read error: Connection reset by peer).
20:57:57 -!- SirCmpwn has joined.
21:10:25 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42036&oldid=42029 * Ypnypn * (+1021)
21:24:46 -!- oerjan has quit (Quit: Nite).
22:00:59 -!- ProofTechnique has joined.
22:05:25 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
22:06:24 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
22:10:13 <Taneb> I need to get out of my habit of eating business cards...
22:11:26 -!- FreeFull has joined.
22:12:17 <HackEgo> [wiki] [[Clip/Examples]] N http://esolangs.org/w/index.php?oldid=42037 * Ypnypn * (+2271) Created page with "==Hello world== "Hello world Self-explanatory, but note that the closing quotation mark is not needed. ==Cat== When compiled, this is expanded to: [M ] Thus, the..."
22:19:11 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42038&oldid=42036 * Ypnypn * (+14)
22:20:08 -!- bb010g has quit (Quit: Connection closed for inactivity).
22:31:10 -!- AnotherTest has quit (Remote host closed the connection).
22:31:17 -!- GeekDude has joined.
22:36:18 -!- ^v^v has quit (Ping timeout: 256 seconds).
22:42:27 -!- Phantom_Hoover has joined.
22:46:44 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:57:49 <HackEgo> [wiki] [[FlogScript]] http://esolangs.org/w/index.php?diff=42039&oldid=37852 * 63.232.95.4 * (+46) /* Examples from anarchy golf */ Added FlogScript quine, from http://golf.shinh.org/reveal.rb?Quine/milieu_1281794781&flog
23:01:20 -!- skj3gg has joined.
23:13:16 -!- adu has quit (Quit: adu).
23:24:22 -!- Taneb has changed nick to nvd.
23:25:09 -!- Lymia has quit (Ping timeout: 250 seconds).
23:25:10 -!- skj3gg has quit (Quit: ZZZzzz…).
23:27:35 -!- nvd has changed nick to Taneb.
23:36:16 -!- adu has joined.
23:48:33 -!- mitchs has quit (Quit: mitchs).
23:49:56 -!- 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?").
23:51:19 -!- boily has joined.
23:55:22 -!- mitchs has joined.
23:55:25 -!- Tritonio has quit (Remote host closed the connection).
00:01:56 -!- Tritonio has joined.
00:26:13 -!- Phantom__Hoover has joined.
00:28:39 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
00:28:55 <HackEgo> olist 976: shachaf oerjan Sgeo FireFly boily nortti
00:32:00 -!- ^v has joined.
00:34:18 -!- skj3gg has joined.
00:43:34 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
00:48:17 -!- skj3gg has quit (Quit: ZZZzzz…).
00:48:28 <boily> Sgello! long live the olist!
00:52:04 -!- Phantom_Hoover has joined.
01:00:42 -!- Lymia has joined.
01:00:52 -!- ProofTechnique has joined.
01:02:17 <olsner> hmm, istr that doing something slightly less boring
01:04:06 -!- gde33|2 has joined.
01:05:15 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
01:08:36 -!- gde33 has quit (Ping timeout: 264 seconds).
01:11:47 <boily> olsner: btw, istr?
01:12:52 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ello: not found
01:13:29 <boily> and there I was suspecting some elliott shenanigan...
01:16:53 -!- jameseb has quit (*.net *.split).
01:16:53 -!- zemhill has quit (*.net *.split).
01:16:55 -!- digitalcold has quit (*.net *.split).
01:20:05 -!- int-e_ has joined.
01:20:20 -!- jameseb has joined.
01:20:20 -!- zemhill has joined.
01:20:20 -!- digitalcold has joined.
01:24:56 -!- int-e has quit (Ping timeout: 264 seconds).
01:29:00 -!- adu has quit (Remote host closed the connection).
01:35:26 -!- ineiros has quit (*.net *.split).
01:35:29 -!- diginet has quit (*.net *.split).
01:35:29 -!- vifino has quit (*.net *.split).
01:35:29 -!- nisstyre has quit (*.net *.split).
01:35:29 -!- atehwa has quit (*.net *.split).
01:35:30 -!- relrod has quit (*.net *.split).
01:35:30 -!- myname has quit (*.net *.split).
01:35:31 -!- fizzie has quit (*.net *.split).
01:37:50 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:38:07 -!- adu has joined.
01:39:22 -!- diginet has joined.
01:39:23 -!- ineiros has joined.
01:39:23 -!- vifino has joined.
01:39:23 -!- atehwa has joined.
01:39:23 -!- relrod has joined.
01:39:23 -!- myname has joined.
01:39:23 -!- fizzie has joined.
01:40:17 -!- ineiros has quit (*.net *.split).
01:40:20 -!- diginet has quit (*.net *.split).
01:40:20 -!- vifino has quit (*.net *.split).
01:40:21 -!- atehwa has quit (*.net *.split).
01:40:22 -!- relrod has quit (*.net *.split).
01:40:22 -!- myname has quit (*.net *.split).
01:40:23 -!- fizzie has quit (*.net *.split).
01:41:11 -!- AndoDaan has joined.
01:41:36 -!- diginet has joined.
01:41:36 -!- ineiros has joined.
01:41:36 -!- vifino has joined.
01:41:36 -!- atehwa has joined.
01:41:36 -!- relrod has joined.
01:41:36 -!- myname has joined.
01:41:36 -!- fizzie has joined.
01:44:23 -!- skj3gg has joined.
01:46:54 -!- jameseb has quit (Ping timeout: 276 seconds).
01:47:17 -!- Taneb has quit (Ping timeout: 250 seconds).
01:53:23 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42040&oldid=42038 * Ypnypn * (+3)
01:56:08 -!- chaosagent has joined.
01:59:13 -!- Mal_ has joined.
02:01:11 <Mal_> I was just wondering if anyone has used occult.vs
02:02:06 <HackEgo> Mal_: 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.)
02:02:08 <elliott> this may not be the channel you're looking for, sadly >_>
02:07:20 <Mal_> what's it for?
02:07:44 <Mal_> thanks anyway.
02:07:51 -!- Mal_ has quit (Quit: AndroidIrc Disconnecting).
02:08:30 -!- chaosagent has quit (Ping timeout: 252 seconds).
02:09:44 -!- skj3gg has quit (Quit: ZZZzzz…).
02:09:45 <AndoDaan> Idea: a esolang based on the Ouija board.
02:16:22 -!- chaosagent has joined.
02:26:27 <boily> a trolling ouija board, where the ghost spells out “I... have... an... idea... for... a... brainfuck... der” *chucks the board out the window*
02:29:00 <AndoDaan> Hmm. That could work. I'm figuring the indicator is weakly controlled by the input stream and several other hidden data streams.
02:30:20 <boily> considering my constant RNG abuse, I wouldn't touch that language without a 10' mapole.
02:31:01 <AndoDaan> Are you the abuser or the abusee?
02:33:10 <boily> I guess all roguelike players fear good events; they always mean something very nasty is juuuust around the corner, patiently waiting for a very painful, sudden and cruel demise.
02:35:53 <AndoDaan> I'm thinking of soup... crawl soup? Is that roguelike game?
02:36:26 <boily> Dungeon Crawl Stone Soup. it's a roguelike like no others.
02:36:52 <boily> you should yield to the temptation. you know you want it. it's for your own good.
02:37:20 <AndoDaan> I played it a bit a couple of months ago.
02:38:02 <AndoDaan> I can't remember what it was exactly, but I guess it couldn't hold my interest.
02:39:20 -!- kapil___ has joined.
02:44:31 <HackEgo> kapil___: 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.)
02:47:21 -!- boily has quit (Quit: APOSTOLIC CHICKEN).
02:50:17 -!- AndoDaan has quit (Quit: Going, going, gone.).
03:07:48 -!- doesthiswork has joined.
03:20:46 -!- doesthiswork has quit (Ping timeout: 256 seconds).
03:25:52 -!- skj3gg has joined.
03:34:56 -!- ProofTechnique has joined.
03:36:02 -!- skj3gg has quit (Quit: ZZZzzz…).
03:59:52 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
04:13:13 -!- nys has quit (Quit: quit).
04:28:18 -!- hjulle has joined.
04:49:42 <J_Arcane> http://int-index.github.io/sodium/
05:15:36 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
05:52:55 -!- bb010g has joined.
06:01:44 <Sgeo> And Randal Munroe puts a heck of a lot of effort into an incomprehendible chart
06:30:13 -!- oerjan has joined.
06:31:09 <oerjan> `addquote <Taneb> I need to get out of my habit of eating business cards...
06:31:29 <HackEgo> 1234) <Taneb> I need to get out of my habit of eating business cards...
06:41:31 -!- SirCmpwn has quit (Quit: bouncer maintenance).
06:43:06 -!- chaosagent has quit (Ping timeout: 264 seconds).
06:47:56 -!- SirCmpwn has joined.
06:48:39 -!- ^v has quit (Read error: Connection reset by peer).
06:49:05 -!- ^v has joined.
07:28:07 -!- SirCmpwn has quit (Remote host closed the connection).
07:30:43 -!- Patashu has joined.
07:35:05 -!- SirCmpwn has joined.
08:39:49 -!- hjulle has quit (Ping timeout: 245 seconds).
09:20:26 -!- jameseb has joined.
09:39:25 -!- FreeFull has quit (Ping timeout: 264 seconds).
09:49:01 -!- AnotherTest has joined.
09:51:19 <myname> so... i can convert [Word8] to String but not Word8 to Char?
10:02:01 <oerjan> myname: toEnum . fromIntegral
10:04:47 <oerjan> it's not very unicode-ready to do that.
10:10:28 -!- Tritonio_ has joined.
10:11:24 -!- Tritonio has quit (Ping timeout: 252 seconds).
10:14:50 -!- Tritonio_ has changed nick to Tritonio.
10:22:13 -!- Tritonio_ has joined.
10:24:35 -!- adu has quit (Quit: adu).
10:25:00 -!- Tritonio has quit (Ping timeout: 272 seconds).
10:26:54 -!- Tritonio_ has quit (Ping timeout: 272 seconds).
10:51:54 -!- nisstyre has joined.
10:54:33 -!- oerjan has quit (Quit: leaving).
10:55:37 -!- ^v has quit (Read error: Connection reset by peer).
10:56:05 -!- ^v has joined.
11:15:03 -!- hjulle has joined.
11:20:03 -!- Taneb has joined.
11:26:24 -!- boily has joined.
11:33:05 -!- TieSoul has quit (Quit: No Ping reply in 180 seconds.).
11:34:23 <Taneb> Help, I seem to be trying to golf an already quite short APL program
11:34:31 -!- TieSoul has joined.
11:36:42 <b_jonas> Taneb: great, show it to nerd snipe us too
11:37:31 <Taneb> b_jonas, it's the first Project Euler problem
11:37:39 <Taneb> Sum of all multiples of 3 or 5 less than 1000
11:37:55 <b_jonas> oh, can't you just golf that to a constant anyawy?
11:37:55 <Taneb> +/X×∼(×3|X)∧×5|X←⍳999 is what I am up to
11:40:38 <int-e_> > (3*333*334 + 5*199*200 - 15*66*67) `div` 2
11:41:01 -!- FreeFull has joined.
11:41:26 <Taneb> My rule of thumb is it's not cheating if I only need to change one value to make it go up to 1000000 rather than 1000
11:41:54 -!- int-e_ has changed nick to int-e.
11:42:26 <int-e> I only need to change the 233168
11:42:52 <Taneb> Maybe I haven't rigorously defined my concept of what is cheating and what isn't
11:43:35 <int-e> Back when I did the problem I treated it as a pen&paper problem. (With a calculator because I'm not too keen on multiplying 3-digit numbers)
11:43:52 <int-e> interestingly, my notes have the result as 3*334*333/2 + 5*201*200/2 - 15*67*66/2 - 1000
11:44:53 <int-e> (I think PE problems are deliberately designed to cause off-by-one errors one problem out of three)
11:44:57 -!- barrucadu has joined.
11:49:28 -!- Patashu has quit (Disconnected by services).
11:49:29 -!- Patashu_ has joined.
11:53:38 -!- Patashu_ has quit (Ping timeout: 246 seconds).
11:56:18 -!- TieSoul has quit (Quit: No Ping reply in 180 seconds.).
11:57:43 -!- TieSoul has joined.
12:09:41 -!- AnotherTest has quit (Ping timeout: 252 seconds).
12:19:55 -!- Koen_ has joined.
12:21:43 -!- boily has quit (Quit: SOPRANO CHICKEN).
12:35:09 -!- SopaXorzTaker has joined.
12:47:15 -!- skj3gg has joined.
13:09:56 -!- skj3gg has quit (Quit: ZZZzzz…).
13:17:46 -!- ProofTechnique has joined.
13:20:46 <Taneb> Today I learnt that the field of complex numbers is isomorphic to the quotient ring R[x]/(x^2+1)R[X]
13:28:23 <int-e> and suddenly the fact that the complex numbers are a commutative ring loses all its mystery...
13:48:11 -!- skj3gg has joined.
14:09:38 -!- impomatic has joined.
14:10:55 -!- skj3gg has quit (Quit: ZZZzzz…).
14:16:27 <myname> so... how do i compile stuff in cabal in a way that error messages are actually useful? i.e. file and line number or the like
14:23:45 <int-e> Perhaps you want cabal -j1 or find the actual log files (I believe cabal prints log file locations when it fails to compile a package.)
14:24:31 <int-e> then cabal is no longer involved. it's all up to ghc and its runtime
14:25:13 <myname> well, i thought i could tell cabal to tell ghc to make stack traces on errors
14:26:53 <int-e> there is limited support for getting stack traces if you compile libraries and executables with profiling information. https://wiki.haskell.org/Debugging#Stack_trace
14:31:14 <mroman> @hoogle defaultTimeLocale
14:31:18 <lambdabot> System.Locale defaultTimeLocale :: TimeLocale
14:37:16 <myname> okay, i did this and all i get is the help message of RTS
14:37:23 -!- AnotherTest has joined.
14:51:17 <int-e> myname: I should've said this earlier: ask on #haskell.
14:56:48 -!- `^_^v has joined.
15:02:32 -!- ^v has quit (Read error: Connection reset by peer).
15:02:59 -!- ^v has joined.
15:10:45 -!- Phantom_Hoover has joined.
15:13:14 -!- arjanb has joined.
15:27:51 <Jafet> Ah yes, R[x]/(x^2+1) the smallest algebraically closed extension of R.
15:29:34 <int-e> I prefer R[x]/(x^2+pi), just to be contrarian.
15:30:14 <int-e> Or perhaps that's too obviously isomorphic...
15:30:56 <int-e> Let's take R[x]/(x^2+sqrt(2) x+pi)R[x]
15:41:51 -!- CADD has quit (Remote host closed the connection).
15:46:01 -!- FreeFull has quit (Ping timeout: 264 seconds).
15:47:42 -!- FreeFull has joined.
15:55:02 -!- GeekDude has joined.
16:04:28 -!- SopaXorzTaker has quit (Ping timeout: 255 seconds).
16:10:56 <Koen_> Taneb: I'm confused. which studies are you in?
16:18:00 -!- SopaXorzTaker has joined.
16:42:16 <mroman> He studies tanebventions
16:42:45 <mroman> but mostly he pretends to be british even though he's cleary finish.
16:42:54 <mroman> and I'm an asshole making stuff up.
16:45:09 <int-e> a bit pricey, hmm. http://www.perthmint.com.au/1-tonne-gold-coin.aspx
16:46:16 <Koen_> sounds like unpure gold to me!
16:47:01 <int-e> 99.99% is what it says
16:47:45 <int-e> But that's still 100g of non-gold in that "coin".
16:48:06 <HackEgo> ` \ ^.^ \ ̊ \ ! \ ? \ ¿ \ ' \ @ \ ؟ \ ＷＥＬＣＯＭＥ \ \ \ 2014 \ 2015 \ 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 \ ctof \ dandd
16:48:06 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `ls: not found
16:48:17 <int-e> Hah, they should try flipping that coin.
16:48:23 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: aaaaaaaa: not found
16:48:24 <HackEgo> :-( \ 113500 \ a.out \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dc \ dog \ error.log \ etc \ factor \ faith \ head \ hello \ hello.c \ ibin \ index.html?dl=1812 \ interps \ lib \ MaFV \ paste \ pref \ prefs \ py.py \ quines \ quotes \ script.py \ share \ src \ test \ test.c \ Wierd \ wisdom \ wisdom.pdf
16:48:40 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: :-D: not found
16:49:12 <mroman> `run echo ᶠᶸᶜᵏ♥ᵧₒᵤ > fu
16:49:55 <HackEgo> cat: fu: No such file or directory
16:50:36 <mroman> `run 'echo ᶠᶸᶜᵏ♥ᵧₒᵤ > fu'
16:50:37 <HackEgo> bash: $'echo \341\266\240\341\266\270\341\266\234\341\265\217\342\231\245\341\265\247\342\202\222\341\265\244 > fu': command not found
17:00:05 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:16:26 -!- Koen_ has quit (Quit: Koen_).
17:24:33 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
17:57:02 -!- SopaXorzTaker has joined.
18:04:35 -!- SopaXorzTaker has quit (Quit: I said GTG. :3).
18:07:31 -!- vanila has joined.
18:12:41 -!- bb010g has joined.
18:16:25 <tswett> Y'know, HackEgo is weird.
18:18:29 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
18:23:10 <HackEgo> [wiki] [[Special:Log/newusers]] create * Entropy * New user account
18:28:09 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
18:30:01 -!- uio has joined.
18:30:15 -!- uio has quit (Client Quit).
18:51:05 <olsner> it's a nice contradiction with a <3 in the middle of that... I can't decide if it's nice or only offensive
18:54:12 -!- Tritonio has joined.
19:09:44 -!- ^v has quit (Read error: Connection reset by peer).
19:10:07 -!- ^v has joined.
19:16:29 -!- FreeFull has quit (Ping timeout: 252 seconds).
19:17:00 <HackEgo> [wiki] [[Clip/Examples]] http://esolangs.org/w/index.php?diff=42041&oldid=42037 * Ypnypn * (-9)
19:17:13 -!- naturalog has quit (Ping timeout: 264 seconds).
19:18:25 -!- FreeFull has joined.
19:18:30 -!- FreeFull has quit (Changing host).
19:18:31 -!- FreeFull has joined.
19:18:36 -!- naturalog has joined.
19:26:25 -!- CADD has joined.
19:48:48 <HackEgo> [wiki] [[Clip/Examples]] http://esolangs.org/w/index.php?diff=42042&oldid=42041 * Ypnypn * (+0) /* Fibonacci (inefficient) */
19:56:53 <J_Arcane> OMG. https://www.destroyallsoftware.com/talks/useing-youre-types-good
20:05:08 -!- Patashu has joined.
20:20:22 -!- FreeFull has quit (Ping timeout: 240 seconds).
20:25:25 -!- Patashu has quit (Ping timeout: 252 seconds).
20:43:26 -!- GeekDude has quit (Ping timeout: 256 seconds).
21:10:44 -!- GeekDude has joined.
21:18:28 -!- FreeFull has joined.
21:18:30 -!- FreeFull has quit (Changing host).
21:18:30 -!- FreeFull has joined.
21:52:44 -!- AnotherTest has quit (Ping timeout: 245 seconds).
22:02:26 -!- mihow has quit (Quit: mihow).
22:15:22 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42043&oldid=42040 * Ypnypn * (+4)
22:19:22 -!- `^_^v has quit (Ping timeout: 240 seconds).
22:22:01 -!- augur has quit (Ping timeout: 250 seconds).
22:25:49 <HackEgo> [wiki] [[Clip/Examples]] http://esolangs.org/w/index.php?diff=42044&oldid=42042 * Ypnypn * (-151) /* Fibonacci (efficient) */
22:31:59 -!- naturalo1 has joined.
22:33:17 -!- naturalog has quit (Ping timeout: 250 seconds).
22:33:37 -!- naturalo1 has changed nick to naturalog.
22:34:29 -!- augur has joined.
22:39:37 -!- impomatic has quit (Read error: Connection reset by peer).
23:03:53 -!- Tritonio_ has joined.
23:05:33 -!- Koen_ has joined.
23:06:16 -!- Tritonio has quit (Ping timeout: 272 seconds).
23:06:25 <HackEgo> merdach: 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.)
23:07:27 <Koen_> there is no going back now
23:08:21 <HackEgo> grep: /var/irclogs/_esoteric/201[3-9]-??-??.txt: No such file or directory
23:08:26 -!- TieSoul has quit (Remote host closed the connection).
23:08:48 -!- Tritonio_ has changed nick to Tritonio.
23:09:04 <elliott> this is what you get for saying h >_>
23:09:06 <Koen_> I'd venture the regexp asn't interpreted as expected
23:11:48 -!- ProofTechnique has joined.
23:26:57 -!- Phantom_Hoover has joined.
23:36:51 -!- boily has joined.
00:00:22 <boily> suffering from an East Coast Endless Snow Syndrome?
00:02:28 <lambdabot> KLGA 252351Z 29006KT 10SM BKN250 02/M11 A2992 RMK AO2 SLP132 4/005 T00171106 10033 20017 53024
00:02:38 <lambdabot> KBOS 252354Z 29014G19KT 10SM CLR M01/M14 A2986 RMK AO2 SLP111 T10061139 10017 21006 53035
00:02:42 <lambdabot> KATL 252352Z 07011KT 5SM -RA BR BKN006 OVC040 02/01 A2973 RMK AO2 PRESRR SLP076 CIG 004V008 P0006 60044 T00170006 10033 20017 58025
00:03:09 <lambdabot> KIAD 252352Z 00000KT 10SM BKN180 OVC220 01/M08 A2996 RMK AO2 SLP148 T00061078 10033 20000 53015
00:03:44 <lambdabot> CYUL 252300Z 27016G22KT 15SM DRSN FEW035 SCT050 M09/M19 A2987 RMK SC1SC3 SLP118
00:05:46 <boily> for once, today was normaler than the past few weeks. just ate some pig skin salad (it tasted Vietnamese).
00:08:10 -!- oren has joined.
00:08:20 -!- adu has joined.
00:23:55 <lambdabot> ESSB 252350Z AUTO 15003KT 9999 NCD 00/M01 Q1018
00:25:26 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
00:28:47 <lambdabot> CYYZ 260000Z 30009KT 15SM FEW030 M13/M19 A3004 RMK SC1 SC TR SLP188
00:34:42 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42045&oldid=42043 * Ypnypn * (-1)
00:38:46 <boily> helloren. not freezing too much in the big T?
00:41:57 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
00:43:42 <quintopia> LET'S PLAY A GAME. i will not have this opportunity again until summer.
00:45:08 <boily> OKAY. does it need a powerful machine?
00:45:09 -!- Phantom_Hoover has joined.
00:46:16 -!- aloril has quit (Remote host closed the connection).
00:46:49 -!- aloril has joined.
00:46:54 <quintopia> get on steam, let's find out what you have
00:50:21 -!- boily_ has joined.
00:50:39 -!- boily_ has changed nick to boilaptop.
00:50:53 <boilaptop> let me launch Steam from this here machine...
00:52:33 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42046&oldid=42045 * Ypnypn * (+103)
00:56:31 -!- tromp has quit.
00:56:57 <boilaptop> I fear the last distupgrade removed it... :(
00:57:28 <quintopia> well that's something i should be working on anyway
00:57:38 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42047&oldid=42046 * Ypnypn * (+4)
00:57:53 -!- tromp has joined.
00:58:04 <quintopia> but it seems such a waste to be productive on a snow day
00:59:49 <boilaptop> it sees this computer as a new one. tout s'explique.
01:14:58 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:15:43 -!- skj3gg has joined.
01:23:42 -!- Tritonio has quit (Ping timeout: 272 seconds).
01:24:15 -!- chaosagent has joined.
01:24:34 -!- chaosagent has quit (Remote host closed the connection).
01:24:52 -!- chaosagent has joined.
01:28:21 -!- Tritonio has joined.
01:36:30 -!- 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?").
01:37:35 -!- Tritonio has quit (Remote host closed the connection).
01:44:39 -!- vanila has quit (Quit: Leaving).
02:03:37 -!- hjulle has quit (Ping timeout: 265 seconds).
02:15:21 -!- skj3gg has quit (Quit: ZZZzzz…).
02:17:31 -!- oerjan has joined.
02:23:11 -!- adu has quit (Quit: adu).
02:30:09 <oerjan> > 3*334*333/2 + 5*201*200/2 - 15*67*66/2 - 1000
02:34:58 -!- boilaptop has quit (Quit: PORTABLE CHICKEN).
02:36:18 -!- boily has quit (Quit: BISECTING CHICKEN).
02:55:01 -!- adu has joined.
02:59:58 -!- adu has quit (Quit: adu).
03:27:14 -!- doesthiswork has joined.
03:34:05 -!- irctc975 has joined.
03:36:12 <HackEgo> irctc975: 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.)
03:38:11 <oren> adonakunarimasu
03:38:12 <irctc975> Wierd shit right there oren...
03:38:28 <oren> I am conjugating adonai as a japanese adjective
03:38:49 -!- Taneb has quit (Ping timeout: 252 seconds).
03:39:47 <irctc975> Don't actualy understand that.. but I can read :/
03:39:56 <oren> japanese adecives often end in 'ai' like mijikai (small)
03:40:24 -!- jameseb has quit (Ping timeout: 276 seconds).
03:41:51 <oren> nope. never heardof that before.
03:42:08 <irctc975> Yeah I think you might know i'm outie but i'll be back
03:42:25 -!- irctc975 has quit (Quit: Page closed).
03:47:13 -!- adu has joined.
03:50:22 -!- adu has quit (Client Quit).
03:59:11 <oerjan> @tell boily <boilaptop> I fear the last distupgrade removed it... :( <-- itym disturbgrade hth
04:05:25 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:23:00 <oren> never build a pump without an acqueduct to carry the water
04:23:36 * oerjan says that and immediately starts wondering about the metaphorical meanings
04:24:48 <oerjan> a civilization whose proverbs were all literally correct technical recommendations but with connotations everywhere
04:26:18 <MDude> Sometimes you just don't realize you're actually on fire.
04:27:01 <oerjan> i don't think that counts hth
04:27:42 <oerjan> my point is that they wouldn't _sound_ like they were metaphoric to us
04:28:08 -!- nisstyre has quit (Changing host).
04:28:08 -!- nisstyre has joined.
04:29:55 <oerjan> don't tighten a bolt with your strongest wrench; you may then be unable to loosen it again.
04:29:56 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42048&oldid=42047 * Ypnypn * (+1121)
04:31:40 <oren> Always detach the gears /before/ connecting the power.
04:32:45 <oren> You can never construct enough magma-safe mechanisms.
04:33:56 -!- skj3gg has joined.
04:37:24 -!- Taneb has joined.
04:37:30 -!- jameseb has joined.
04:46:55 <oren> ooh an eleven caravan! ready the lever of drowning!
04:47:24 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42049&oldid=42048 * Ypnypn * (+52) /* Constants */
04:49:05 -!- skj3gg has quit (Quit: ZZZzzz…).
04:50:43 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42050&oldid=42049 * Ypnypn * (+0) /* Constants */
04:53:20 <oerjan> oren: if df only tracked insurance premiums, your trading policy would be so hosed...
04:53:35 <oerjan> (for all i know it might do...)
04:54:32 -!- ProofTechnique has joined.
04:58:09 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42051&oldid=42050 * Ypnypn * (+117) /* Constants */
05:00:08 -!- doesthiswork has quit (Quit: Leaving.).
05:00:30 -!- doesthiswork has joined.
05:18:57 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42052&oldid=42051 * Ypnypn * (+192) /* Constants */
05:21:46 -!- MDude has changed nick to MDream.
05:41:29 <oren> oerjan: they had an economy simulation in a previous version but it was removed
05:47:42 <oren> I have accidentally invented a water diode
05:50:09 <oren> If you put a water wheel next to a pump side-by side in a 2 space wide passage, water can flow one way but not the other
05:54:50 <oren> Hmm... I think something like a pump, with a water-activated pressure plate?
06:06:17 -!- doesthiswork has quit (Ping timeout: 246 seconds).
06:32:55 <oren> I can't find anything but useless sphalerite? What is Zinc even good for?!?!?
06:44:24 -!- augur has quit (Ping timeout: 245 seconds).
06:45:30 <b_jonas> oren: um, doesn't an ordinary slope act as a water diode?
06:47:55 -!- augur has joined.
06:51:23 <oren> b_jonas: no, because of pressure modeling, water can be pushed up a slope
06:53:02 <b_jonas> oren: but what if you put a long enough slope, then a pump to cover the difference?
07:00:21 <oren> I guess, but with my method the diode's pump is powered directly by the water in the channel and doesn't need external power
07:22:28 -!- arjanb has quit (Quit: bbl).
07:26:09 -!- chaosagent has quit (Ping timeout: 252 seconds).
07:31:14 -!- chaosagent has joined.
07:36:41 -!- chaosagent has quit (Ping timeout: 250 seconds).
07:40:03 -!- Patashu has joined.
07:44:21 -!- Patashu has quit (Disconnected by services).
07:44:22 -!- Patashu_ has joined.
08:24:44 <int-e> the sun here seems to agree
08:34:44 <lambdabot> Control.Monad forever :: Monad m => m a -> m b
08:35:44 -!- ^v has quit (Read error: Connection reset by peer).
08:36:10 -!- ^v has joined.
08:42:23 <mroman> PortNumber (read "10") fucks up?
08:42:39 <mroman> because there's no (Read PortNumber)
08:43:41 <mroman> PortNumber :: PortNumber -> PortID
08:44:02 <mroman> PortNumber must have a Num instance if 10 works
08:44:38 <mroman> meaning fromIntegral should fix it
09:06:38 -!- Frooxius has joined.
09:43:46 -!- AnotherTest has joined.
09:48:12 -!- AnotherTest has quit (Ping timeout: 252 seconds).
10:19:58 -!- AnotherTest has joined.
10:26:42 -!- AnotherTest has quit (Ping timeout: 252 seconds).
10:28:43 -!- FreeFull has quit (Ping timeout: 250 seconds).
10:31:43 <oren> Speed limit reform: change all speed limits to the same number of Kim/h
10:32:49 <b_jonas> oren: um, that doesn't work. there's a good reason why there has to be different speed limits in different places and for different vehicles.
10:33:15 <oren> No I mean if it currently is 30 km/h change it to 30 Kim/h
10:33:18 <b_jonas> like, why highways have a higher speed limit than towns
10:34:08 <b_jonas> so basically you just want to raise the speed limits
10:34:23 <oren> by 2.4 percent
10:34:31 <b_jonas> that happens anyway, but less often (say once every two decades) and by higher amounts, as vehicles get safer
10:35:46 <b_jonas> the town speed limit got lowered from 60 to 50 here, but the highway limit got raised form 120 to 130
10:35:52 <b_jonas> more than a decade ago now
10:36:00 <oren> My dad went to the expo 67 in montreal and they said they were going to have self-driving cars by the 90's but they're still not here
10:36:10 -!- vanila has joined.
10:36:16 <mroman> I think inches per milliseconds is much more american
10:36:19 <b_jonas> some of this might be political in natures
10:37:01 <oren> bah, they should really specify rapidities in radians
10:38:05 <oren> atan2(v,c) isthe rapidity
10:39:16 <oerjan> mroman: that's not american it has "milli-" in it
10:39:17 <mroman> (inches per millihour)
10:40:06 <mroman> oerjan: you could also use fujita classifications
10:40:12 <oren> The federal rapidity limit is 9.2656693E-8 radians
10:40:34 <mroman> technically 120 to 180
10:40:53 -!- Patashu_ has quit (Remote host closed the connection).
10:41:04 -!- Patashu has joined.
10:41:07 <HackEgo> [wiki] [[Lisp2d]] M http://esolangs.org/w/index.php?diff=42053&oldid=41649 * Cluid Zhasulelm * (+1212) permission to include fizzbuzz example granted in correspondence
10:43:03 <fizzie> 120km/h is about 1.79 miles/.beat.
10:44:50 <oren> By federal law, you may only approach 4.02402923E-8 nines to cee!
10:45:46 <oren> ( 'nines to cee' is the formula -log(1-v/c) )
10:45:47 <idris-bot> (input):1:43: error: expected: "!!",
10:46:25 <idris-bot> (input):1:1: error: expected: ":",
10:46:29 <idris-bot> (input):1:1: error: expected: ":",
10:47:44 <idris-bot> (input):1:5:When elaborating an application of function Data.Fin.+:
10:47:50 <idris-bot> Can't disambiguate name: Data.HVect.++, Prelude.List.++, Prelude.Strings.++, Data.VectType.Vect.++
10:47:59 <mroman> ( [1] Prelude.List.++ [2]
10:48:00 <idris-bot> (input):1:18:When elaborating an application of function Data.VectType.Vect.++:
10:48:12 <mroman> ( [1] Prelude.VectType.Vect..++ [2]
10:48:12 <idris-bot> (input):1:28:When elaborating an application of function Data.VectType.Vect.++:
10:48:25 <mroman> idris-bot is just screwing with me
10:48:35 <mroman> ( [1] Prelude.VectType.Vect.++ [2]
10:48:36 <idris-bot> (input):1:27:When elaborating an application of function Data.VectType.Vect.++:
10:48:40 <mroman> ( [1] `Prelude.VectType.Vect.++` [2]
10:48:41 <idris-bot> (input):1:28: error: expected: "`"
10:48:41 <idris-bot> [1] `Prelude.VectType.Vect.++` [2]<EOF>
10:58:43 <HackEgo> [wiki] [[User:Cluid Zhasulelm]] M http://esolangs.org/w/index.php?diff=42054&oldid=42010 * Cluid Zhasulelm * (+10) added another cool stuff
11:07:40 <oren> I want a partial implementation of C preprocessor, that subs in files only if they are part of my porject
11:09:09 <b_jonas> oren: ask ais523 (he might not have exactly that, but he might still be able to help in what you want)
11:09:53 <oren> Hmm... maybe i can write a perl script that does mostly what I want
11:11:07 <oren> but then I'd have to complicate my makefiles
11:11:35 <b_jonas> technically it's not really easy to include just your files, because what files you include could depend on macros predefined by your compiler (depending on architecture) or defined in headers, but if you know you don't do conditional includes like that then it might be possible
11:13:40 <oren> well, of you have a sequence like #ifdef windows #include file #endif then the included text will be cut out anyway, right?
11:16:14 <b_jonas> oren: technically you can have indirect incldues, but few people use those
11:16:23 <b_jonas> and you probably knew if you did tricks like that
11:26:15 -!- boily has joined.
11:32:56 <Lymia> ( [1] Data.HVect.++ [2]
11:32:57 <idris-bot> (input):1:16:When elaborating an application of function Data.VectType.Vect.++:
11:33:08 <Lymia> ( Data.HVect.++ [1] [2]
11:33:08 <idris-bot> When elaborating an application of function Data.VectType.Vect.++:
11:34:14 -!- Patashu has quit (Ping timeout: 272 seconds).
11:34:30 <idris-bot> (input):1:5:Can't disambiguate name: A.::,
11:34:55 <lambdabot> oerjan said 7h 35m 44s ago: <boilaptop> I fear the last distupgrade removed it... :( <-- itym disturbgrade hth
11:35:27 <Lymia> ( Data.HVect.app [1] [2]
11:35:35 <Lymia> ( Data.HVect.::app [1] [2]
11:35:36 <idris-bot> When elaborating argument x to constructor Data.VectType.Vect.:::
11:35:40 <Lymia> ( Data.HVect.:: [1] [2]
11:35:40 <idris-bot> When elaborating argument x to constructor Data.VectType.Vect.:::
11:35:47 <idris-bot> When elaborating argument x to constructor Data.VectType.Vect.:::
11:35:51 <Lymia> ( [1] Data.HVect.:: [2]
11:35:51 <idris-bot> (input):1:16:When elaborating argument x to constructor Data.VectType.Vect.:::
11:35:59 <Lymia> ( [1] Data.HVect.app [2]
11:36:25 <boily> @tell oerjan hellørjan. I don't think I'm used to having ubuntal disturbgrades, from having spent too much time on Arch. the consequences are unknown to me.
11:36:29 <Lymia> ( (\x -> \y -> x ++ y) [1] [2]
11:36:29 <idris-bot> (input):1:5: error: expected: ",",
11:37:11 <Lymia> ( (\x => \y => x ++ y) [1] [2]
11:37:12 <idris-bot> (input):1:22:Can't disambiguate name: Data.HVect.++, Prelude.List.++, Prelude.Strings.++, Data.VectType.Vect.++
11:37:28 <Lymia> ( map (\x => x + 1) [1, 2, 3]
11:37:29 <idris-bot> When elaborating an application of function Prelude.Functor.map:
11:37:47 <Lymia> ( map (\x => x + 1) 1 :: 2 :: 3 :: Nil
11:38:01 <Lymia> ( map (\x => x + 1) 1 Data.HVect.:: 2 Data.HVect.:: 3 Data.HVect.:: Nil
11:38:02 <idris-bot> (input):1:5:When elaborating argument x to constructor Data.VectType.Vect.:::
11:38:17 <zemhill> Lymia: I do !zjoust; see http://zem.fi/bfjoust/ for more information.
11:38:17 <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>.
11:38:42 <idris-bot> (input):1:1: error: expected: ":",
11:38:46 <idris-bot> When elaborating argument x to type constructor =:
11:43:57 -!- AnotherTest has joined.
11:48:49 <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/
11:49:12 <HackEgo> [U+0068 LATIN SMALL LETTER H] [U+0065 LATIN SMALL LETTER E] [U+006C LATIN SMALL LETTER L] [U+0070 LATIN SMALL LETTER P]
11:50:24 <oren> `help unidecode
11:50:25 <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/
11:51:06 <oren> `man unidecode
11:51:07 <HackEgo> man: can't open the manpath configuration file /etc/manpath.config
11:51:26 <oren> arbitrary code my arse
11:51:55 <HackEgo> man: can't open the manpath configuration file /etc/manpath.config
11:58:34 <HackEgo> Usage: multicode [options] arg \ \ Options: \ -h, --help show this help message and exit \ -x, --hexadecimal Assume arg to be hexadecimal number \ -o, --octal Assume arg to be octal number \ -b, --binary Assume arg to be binary number \ -d, --decimal Assume arg to be decimal number \ -r, --rege
12:01:53 -!- koo7 has quit (Ping timeout: 252 seconds).
12:03:00 <oerjan> oren: `unidecode is a command we made ourselves. you won't find a manpage hth
12:03:10 -!- idris-bot has quit (Quit: Terminated).
12:03:26 -!- idris-bot has joined.
12:05:56 <oren> well at least I found two more insane fonts: http://snag.gy/Y6rMM.jpg
12:06:13 -!- Tritonio has joined.
12:06:51 <boily> helloren. isn't the one to the left your regular terminal font?
12:07:18 <oren> No, that one was more cursive and had | as heart instead of o.
12:07:37 <Melvar> mroman, Lymia: Idris doesn’t currently allow using qualified operators infix, and to use them prefix, there must be parens around the operator (but not the namespaces).
12:08:21 <oren> I do like the idea of overdotting the letters instead of having capitals
12:08:58 <Lymia> That heart font looks fun.
12:09:15 <Lymia> (I'm surprised someone would make a monospace font like that though)
12:10:11 <oren> It is a Japanese font, they are almost always monospace
12:11:27 <oren> Because Japanese text is sort of monospaced even in handwriting (they have special paper with boxes for essays and such)
12:13:09 <oren> Which conveniently means you can get lots of crazy terminal fonts by searching for crazy fonts in japanese
12:14:35 -!- oerjan has quit (Quit: leaving).
12:15:41 <b_jonas> oren: are those two really japanese fonts?
12:15:57 <oren> The one on the right isn't. the one on the left is.
12:16:05 -!- Tritonio_ has joined.
12:17:33 <b_jonas> I have recently fixed an error in my terminal font
12:17:56 <b_jonas> I found out that lowercase u with brevis and u with ring were drawn too wide, a mistake I haven't noticed before
12:17:57 <oren> http://s2g.jp/font/index.htm It is called S2Gらぶ
12:18:19 <b_jonas> this font (I hope it has the updated version there) => http://www.math.bme.hu/~ambrus/pu/fecupboard20-c.pcf.gz
12:18:34 -!- Tritonio has quit (Ping timeout: 272 seconds).
12:19:00 <b_jonas> but at least it's my font so it was easy to fix
12:19:21 <b_jonas> it was worth to make my own rather than try to switch all the time after I find each other terminal font sucks
12:19:43 <b_jonas> (this is a bitmap font so it was easy to draw, much easier than graymap fonts generated from vector fonts)
12:21:04 -!- Tritonio_ has changed nick to Tritonio.
12:21:15 -!- boily has quit (Quit: EPHEMERAL CHICKEN).
12:23:28 <oren> Here is the font (in a bullshit adhoc format) which I used in one of my games: http://postimg.org/image/tjxgpkkj5/
12:29:21 <oren> Ommitting distinction between identical characters makes it easy to have greek, cyrillic and latin.
12:29:52 -!- AnotherTest has quit (Ping timeout: 245 seconds).
12:30:29 -!- FreeFull has joined.
12:32:19 -!- AnotherTest has joined.
12:44:20 -!- hjulle has joined.
12:50:10 <b_jonas> oren: why are the digits 4 and 5 and a few other chars partly gray instead of black and white
12:51:03 <b_jonas> oren: hmm, those greek letters are in a strange order
12:51:08 <mroman> hReady returns IO Bool
12:51:09 <b_jonas> is there a mapping table to this?
12:51:13 <mroman> but it fails when nothing is ready
12:51:17 <mroman> it either returns True or Fails?
12:51:28 <mroman> that's pretty fucking stupid
12:52:16 -!- AnotherTest has quit (Ping timeout: 252 seconds).
12:52:28 <b_jonas> oren: and what is the character in the 0x80 position?
12:52:39 <b_jonas> what's it supposed to represent?
12:54:02 <oren> THe 0x80 is a diamond, representing energy credits.
12:54:17 <oren> or at least it would if I had finished the damn game
12:54:55 <oren> the greek letters are in a pseudo-enlish order with the big letters put in wherever they fit
12:55:10 <b_jonas> I wonder what game is it that requires these particular letters
12:55:28 <FireFly> The diamond reminds me of the statement separator in APL
12:55:35 <b_jonas> FireFly: isn't that a small diamond?
12:55:54 <FireFly> It's looked fairly large in the fonts I've seen, but I don't know
12:56:30 <oren> It was going to be a futuristic RTS with units named in Russian, japanese, and greek (for the aliens)
12:56:53 <b_jonas> oren: but only all uppercase russian?
12:57:41 <oren> right. Because in novaya rossiya, they are CAPITALIST NOW!
12:58:04 <b_jonas> oren: what about the gray stuff?
12:58:37 <oren> the gray is an error that my program doesn't care about for some reason
12:58:41 <b_jonas> and which glyph represents Э
13:00:02 <b_jonas> I figured your W stands in for Ш
13:01:15 <oren> I make economical use of code space unlike those unicode wastrels
13:01:37 <b_jonas> and what char does the glyph at 0xa1 represent?
13:02:41 <b_jonas> oh! I thought we had an infinity glyph for that
13:03:13 <oren> infinity is kind of hard to make half-width.
13:03:39 <oren> So i improvized a substitite
13:03:39 <b_jonas> sure, it looks ugly in all the 9 wide fonts
13:03:55 <vanila> half of infinity is still infinity
13:03:56 <b_jonas> but cp437 still has it, even if it's ugly
13:06:03 <oren> yah. I included only 2 kanji: 日 and 月 which are used in dates
13:06:08 <b_jonas> the slash character seems ugly
13:06:39 <oren> yah it's jagged. needs anti-aliasing
13:07:09 <oren> or maybe to be less high
13:08:52 <FireFly> You could make infinity two characters wide (though I guess you're starved for space as it is already)
13:09:31 <FireFly> wait, not nabla.. partial derivative
13:09:35 <oren> partial derivative.
13:09:52 * FireFly wonders what that would be used for in an RTS
13:09:58 <b_jonas> are the characters at 0xf5, 0xf6, 0xf7, 0xf8 supposed to represent ∈∪∩⊂ ? if so, they seem to be raised too high I think
13:10:24 <b_jonas> FireFly: yes, it's partial
13:10:44 <oren> hmm... yeah maybe they are a lil high
13:11:58 <FireFly> Reminds me of the japanese postal mark
13:12:02 <oren> japanese postal sign.
13:12:10 <Melvar> oren: I would have expected 3 to be used for З. As it is your З looks more like a 3 than your 3 does.
13:12:38 <oren> It was going to be 年 but i couldn't get it small enough
13:13:20 <oren> on paper i write my 3's like that
13:14:05 <oren> in fact all those numbers are how i write them on paper
13:14:41 <b_jonas> oren: you write dotted zeros?
13:15:55 <FireFly> I write underscored ones when I want to emphanize it is a one
13:16:13 <Melvar> And angular fours and fives.
13:16:44 <b_jonas> I expect there should be one if there's what looks like an ü and an å
13:17:18 <FireFly> Or better yet, separate the diacritics from the symbols and use overstriking
13:17:19 <oren> yeah. that would be better than quite a few of those charcters
13:17:52 <oren> overstriking ftw.
13:18:05 <FireFly> Speaking of which, I learned yesterday that `less` will interpret A^HA as boldface A and _^HA as underlined A
13:18:15 <FireFly> Which is how man communicates these to less
13:18:28 <FireFly> Funny how traces of overstriking still remains
13:19:21 <oren> yeah, overstriking is probably the way to go
13:19:30 <b_jonas> I prefer not to limit myself to 256 glyphs, so my font has over two thousand characters, and even a very few identical pairs (mostly just multiple completely empty ones)
13:19:52 <FireFly> do you use your own monospace font for everyday use?
13:19:59 <b_jonas> FireFly: yes, in terminals
13:20:04 <oren> I'm using it right now
13:20:16 <b_jonas> FireFly: => http://www.math.bme.hu/~ambrus/pu/fecupboard20-c.pcf.gz
13:20:20 <b_jonas> 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)
13:20:46 <oren> well, in this terminal anyway. the other one is still on that crazy-ass klingon looking font
13:20:53 <b_jonas> hmm, I should update that short description
13:21:08 <FireFly> I'm fairly happy with the font I currently use, but curious what it looks like either way
13:21:09 <Melvar> b_jonas: Does it have l with belt?
13:21:31 <b_jonas> Melvar: I don't think so... let me check
13:21:45 <b_jonas> oren: what? isn't that the crossed l?
13:21:53 <Melvar> oren: That’s l with stroke.
13:22:46 <b_jonas> fecupboard20 is supposed to have all characters required for all major European languages that are written in the latin script
13:23:35 <oren> doesn't look like in has that curly thing l
13:24:55 <b_jonas> yes, definitely doesn't have l with belt
13:26:31 <b_jonas> is l with belt used only as a pronunciation symbol?
13:26:49 <Melvar> I’m happy with DejaVu Sans Mono. I particularly like the l in it, and moreso that all the variants have the same shape because it has all of them, except turned l.
13:27:14 <Melvar> b_jonas: I believe it’s only used in IPA, yes.
13:27:34 <b_jonas> ok, then that's why I don't have it. I've added only a few of the characters that are used only in IPA
13:28:17 <Melvar> A consequence of this is that there is no uppercase version, since IPA uses only lowercase and caseless letters.
13:28:26 <FireFly> This font reminds me of MS DOS for some reason
13:28:51 <b_jonas> FireFly: yes, some of the pc fonts have inspired me
13:29:05 <oren> It is quite similar to the one in MS DOS (which i recently installed on an old computer to play DOOM)
13:29:11 <b_jonas> I've observed at least three different 9x16 fonts before I made this 10x20 one
13:29:21 <b_jonas> oren: there's no _one_ font in MS DOS
13:29:34 <oren> I mean the default one then
13:29:40 <b_jonas> there's various ones hard-coded in VGA cards
13:29:44 <b_jonas> at least three different ones
13:29:55 <b_jonas> all with cp437 encoding and very similar
13:30:01 <b_jonas> but different in the details
13:30:36 <oren> well Iwasn't around in the old MS DOS days so you'd know better than I
13:30:46 <FireFly> Funny, the l with belt renders just fine for me and doesn't look out-of-place compared to the other glyphs.. I guess it happened to fall back to a similar font
13:30:47 -!- ais523 has joined.
13:32:07 <oren> I do like that way `works with' to make quotes
13:32:26 <ais523> it really depends on the font
13:32:39 <ais523> they don't look very similar in the one I'm using
13:32:52 <oren> In b_jonas's font it works, is what I mean
13:33:23 -!- AnotherTest has joined.
13:33:50 <b_jonas> ais523: we were talking about fonts, and in particular this crazy one with a custom encoding by oren: http://postimg.org/image/tjxgpkkj5/
13:34:43 <ais523> a custom encoding that is nonetheless almost consistent with ASCII
13:34:48 -!- FreeFull has quit (Ping timeout: 252 seconds).
13:34:49 <oren> the custom encoding is mostly designed so I can write the actual strings in latin and then shift ehm by varying amounts
13:34:52 <ais523> (having a printable character where newline should be is a problem, though)
13:34:55 <b_jonas> ais523: yes, it's certainly consistent with ascii
13:34:56 <FireFly> It looks like an extended ASCII variant to me
13:35:10 <b_jonas> ais523: um no, it's not a problem for cp437 either
13:35:22 <b_jonas> becuse the newline is transformed by the terminal layer and never gets into video memory
13:35:54 <b_jonas> (similarly how having a printing character at the position of space isn't a problem for TeX's oT1-encoded fonts, because the TeX engine emits a glue rather than a character when you type space)
13:36:20 <oren> Like I write @amma and it becomes Γαμμα
13:36:53 <oren> whoops I mean `amma
13:37:09 <b_jonas> ah, that explains the positions of the russian uppercase things
13:37:39 -!- AnotherTest has quit (Ping timeout: 250 seconds).
13:37:45 <Melvar> lľŀłƚljȴɭʪʫˡᶅᶩỻₗⅼⱡꝇꝉꞁꞎꭝꭞｌ
13:38:45 <b_jonas> Melvar: my font has l, l with caron, l with acute, l with slash out of those
13:38:47 <FireFly> Those are all supported by DejaVu Sans Mono?
13:38:51 <b_jonas> (and maybe something else, I don't know)
13:38:54 <ais523> rather than Russian specifically
13:39:05 <Melvar> FireFly: No, that’s just all of them I could find at all.
13:39:28 <ais523> I tried to learn cyrillic, but it has too many vowels :-(
13:39:31 <b_jonas> ais523: look at oren's font, it only has glyphs for russian uppercase letters, not for the letters used in macedonian or serbian
13:40:19 <b_jonas> ais523: there's some tricks, namely how in that font 34W stand for the russian letters (which wasn't obvious to me at first)
13:40:26 <b_jonas> so there's no other glyphs for those
13:40:55 <ais523> oh, like the beta in CP437 which is also an ß
13:41:36 <b_jonas> ais523: also this doesn't have a russian F because the cyrillic one stands for it
13:41:44 <Melvar> FireFly: Excepting ones that are particularly simple l with an accent; I didn’t list those.
13:41:48 <ais523> apparently, some typewriter keyboards don't have a 0 or 1
13:42:06 <ais523> because they can use O and I instead
13:42:06 <b_jonas> it doesn't have a russian F because the greek Phi stands for it
13:42:06 <b_jonas> ais523: yes, but it's O and l actually
13:42:23 <Melvar> lľŀłƚȴɭˡᶅᶩ are the ones of that list in DejaVu Sans Mono.
13:43:44 <Melvar> No, wait, actually more, but weechat fails to display them because they aren’t listed in whatever lib resource that one thing was.
13:45:36 <Melvar> And ʪʫ are actually in it but the l parts don’t have the usual shape; it probably doesn’t fit in a cell well enough.
13:48:58 <FireFly> I guess that works for presentational purposes, but it can't be fun to try to analyse/deal with text where a particular glyph could represent multiple characters
13:50:50 <FireFly> I tried to make a 3px-high font once, it didn't go terribly well
13:51:01 <FireFly> http://xen.firefly.nu/up/pixfont/index.html
13:54:08 <FireFly> I decided to disregard case, which is something I usually strongly dislike, because at that scale there isn't much choice
13:55:09 <b_jonas> FireFly: just add a colon before each uppercase letter
13:55:40 <vanila> this is a good way to generate an alphabet maybe
13:55:57 <FireFly> b_jonas: I meant more the way I use lowercase b and n
13:55:59 <vanila> just create a set of small bitmaps that are visually as far apart as possible
13:56:17 <b_jonas> vanila: yes, people have tried that
13:56:31 <vanila> id like to see some of the results
13:57:36 <b_jonas> but I for am a typogeek and care about the text looking very similar to existing beautiful texts, rather than inventing something entirely new
13:59:02 -!- hjulle has quit (Ping timeout: 245 seconds).
14:02:17 <Melvar> vanila: You mean this thing: http://dotsies.org/ ?
14:04:52 <Melvar> Sadly that seems to have put the dot patterns in some order and zipped them with the supported alphabet in order, instead of thinking about distinctiveness vs. frequency.
14:04:53 -!- doesthiswork has joined.
14:05:35 <vanila> yeah, ithink better can be done
14:07:19 <vanila> it doesnt have to bereated to english either
14:11:00 -!- SopaXorzTaker has joined.
14:12:41 -!- AnotherTest has joined.
14:13:36 -!- skj3gg has joined.
14:14:26 -!- TieSoul has joined.
14:15:32 -!- GeekDude has joined.
14:17:31 -!- TieSoul has quit (Client Quit).
14:18:00 -!- TieSoul has joined.
14:19:20 -!- Koen_ has joined.
14:19:45 -!- Koen_ has quit (Client Quit).
14:20:00 -!- Koen_ has joined.
14:24:52 -!- ais523 has quit (Ping timeout: 240 seconds).
14:27:35 -!- jameseb- has joined.
14:27:56 -!- Taneb has quit (Read error: Connection reset by peer).
14:27:58 -!- jameseb has quit (Read error: Connection reset by peer).
14:28:16 -!- Taneb has joined.
14:28:56 <FireFly> I'm pretty sure the latin alphabet is a lot more efficient when it comes to reading than those dot patterns..
14:29:09 -!- jameseb- has changed nick to jameseb.
14:30:30 -!- FreeFull has joined.
14:36:22 -!- ais523 has joined.
14:39:38 -!- AnotherTest has quit (Ping timeout: 265 seconds).
14:40:33 -!- doesthiswork has quit (Quit: Leaving.).
14:41:13 <int-e> FireFly: it'd be hard to surpass several decades of training, that's certain. but in principle, I guess you can recognize larger patterns the same way you'd do with english text.
14:41:58 <int-e> so tricky to predict. one should do this with more versatile features than squares.
14:43:48 <int-e> one criticism I'd have is that in isolation, a,b,c,d,e all look the same. that's quite awful.
14:43:57 <FireFly> Yeah, that was mostly what I was thinking of
14:44:13 <FireFly> Having to judge distance between objects to read seems bad
14:44:37 <FireFly> Same for the different letters that all look visually like variations of '!'
14:47:50 -!- GeekDude has changed nick to GibVent.
14:48:13 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
14:49:12 <HackEgo> [wiki] [[Eodermdrome]] http://esolangs.org/w/index.php?diff=42055&oldid=41608 * Chris Pressey * (+364) /* Computational class */ not TC in the usual(?) sense; someone on IRC pointed this out the other day
14:49:55 <HackEgo> [wiki] [[Eodermdrome]] M http://esolangs.org/w/index.php?diff=42056&oldid=42055 * Chris Pressey * (+10) /* Computational class */ *universal Turing machine
14:53:02 <HackEgo> [wiki] [[Eodermdrome]] M http://esolangs.org/w/index.php?diff=42057&oldid=42056 * Chris Pressey * (-7) /* Computational class */ link to ℒ
14:57:35 -!- SopaXorzTaker has joined.
14:58:44 -!- ais523 has quit (Quit: meeting).
15:02:09 -!- oren has quit (Ping timeout: 250 seconds).
15:07:49 -!- skj3gg has quit (Quit: ZZZzzz…).
15:13:38 -!- skj3gg has joined.
15:13:42 -!- skj3gg has quit (Client Quit).
15:18:36 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42058&oldid=42052 * Ypnypn * (+0)
15:19:28 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42059&oldid=42058 * Ypnypn * (+143)
15:24:25 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42060&oldid=42059 * Ypnypn * (+6) /* Types */
15:24:43 -!- `^_^v has joined.
15:26:53 -!- AnotherTest has joined.
15:28:57 -!- koo7 has joined.
15:31:15 -!- AnotherTest has quit (Ping timeout: 256 seconds).
15:34:40 -!- Tritonio_ has joined.
15:35:55 -!- mihow has joined.
15:36:10 -!- Tritonio has quit (Ping timeout: 272 seconds).
15:41:04 -!- Tritonio_ has changed nick to Tritonio.
15:50:04 -!- GibVent has quit (Read error: Connection reset by peer).
15:50:14 -!- GibVent has joined.
15:53:16 -!- G33kDude has joined.
15:53:26 -!- GibVent has quit (Read error: Connection reset by peer).
15:53:31 -!- G33kDude has changed nick to GibVent.
15:56:32 -!- MDream has changed nick to MDude.
15:56:34 -!- GibVent has changed nick to GeekDude.
15:56:39 <Melvar> FireFly, int-e: I am reminded of one thing that someone proposed dotsies were good for: Writing Lojban into five-block-high walls in Minecraft.
15:58:18 <MDude> There is one problem I ahve with dotsies.
15:58:47 <MDude> And this is that it uses a special character for full stops that breaks the pattern it uses.
15:58:51 <FireFly> Maybe I should learn to read it.. I could see it being useful in some circumstances with very limited resolution, like that
15:59:12 <MDude> When really, it could ahve just gone with a solid, fife-dot line instead for that purpose.
15:59:18 <Melvar> (With the additional fun that Lojban’s root words are five letters long, so they become 5×5-block squares.)
15:59:55 <MDude> As it is, you can't use punctuation with it as all if you're actually displaying it at minimal resolution.
15:59:59 <Melvar> (And that Lojban doesn’t strictly require any punctuation.)
16:00:38 <FireFly> I mean, it isn't punctuation in Lojban, but you need it as well, no?
16:00:57 <Melvar> FireFly: Using the h-dotsie should be fine.
16:01:29 <Melvar> I mean the only reason ' isn’t h in the latin orthography is that it’s supposed to be “light”.
16:02:47 <Melvar> (Basically, it’s unlike any other consonant in that it can only appear between vowels and usually doesn’t count for purposes of general word-shape validity.)
16:03:29 -!- Tritonio has quit (Remote host closed the connection).
16:03:30 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
16:04:38 -!- ais523 has joined.
16:06:11 <Melvar> (I sometimes like to think of it as an overgrown vowel hiatus instead of a real consonant, because that’s what it looks like to me.)
16:22:06 <b_jonas> ais523: wait, I want to show something to you as well
16:22:28 <b_jonas> ais523: http://www.math.bme.hu/~ambrus/pu/ccache.png
16:23:06 <b_jonas> ais523: I did a measurement on how quickly my computer can read memory. the goal was to show the impact of the L1 cache and the L2 cache. that much works:
16:23:26 <ais523> b_jonas: you're reading the same area of memory over and over again, I take it?
16:23:59 <b_jonas> on the left third of the diagram, I read from the L1 cachce, so the speed is bound by executing the instructions, not by the memory loads
16:24:14 <b_jonas> this shows that this computer has 32 kibibytes of L!h1 cache
16:25:11 <b_jonas> the middle third of the diagram shows reading from L2 cache, there the speed is bound mostly or completely by the speed of that cache.
16:26:00 <b_jonas> there's 2 mebibytes of L2 cache in this machine, but the speed starts getting worse below that, because this is ran on a multitasking OS which does stuff other than running this program, and switches often enough that the program can't use the L2 cache fully
16:26:12 <b_jonas> this much is what I expected.
16:26:45 <b_jonas> The surprising part is the right third, where the speed is bound by the read speed of the main memory.
16:27:34 <b_jonas> You can see that there are two different possible speeds, one around 4.5 GiB/s and one around 4 GiB/s. That diagram doesn't explain why there are two speeds, and it took me a while (and some experiments other than looking at this diagram) to figure out the reason.
16:31:32 <vanila> These graphs are wonderful
16:32:46 <b_jonas> ais523: no. this is my old home computer and definitely doesn't do NUMA.
16:32:48 <int-e> b_jonas: would the density of the 4.5GB/s be about 1/3 of the 4GB/s line? (so 1/4 vs 3/4 total)?
16:33:09 <ais523> maybe not intentional NUMA, but I'd expect some of the cores would be closer to certain parts of memory
16:33:18 <b_jonas> int-e: no, the 4.5 GB is denser, but that's a red herring
16:33:42 <int-e> b_jonas: oh. right. reading it wrong.
16:34:12 <b_jonas> ais523: I don't see how that would happen because there's only a single memory card (512 MiB size) and a single intel CPU chip with two cores
16:34:18 <int-e> "old" ... upgraded memory?
16:35:25 <b_jonas> ais523: and even still, the measurements for that part of the grpah take two or three seconds, so if it depended on the cores I'd expect to see intermediate results where the process is placed to another core during a run,
16:35:35 <int-e> My ideas would be alignment of reads, and actually different memory behavior in different address ranges.
16:35:40 <b_jonas> but there don't seem to be such things, or only one or two in the thousands of run
16:36:17 <ais523> I know that at least on Linux, processes tend to stay pegged to one core unless there's a good reason to move
16:36:32 <b_jonas> int-e: all the reads are 64-byte aligned, so if alignment matters it could be through affecting whcih L2 cache lines are emptied, but that's unlikely to show up on the rightmost part of the graph, or through page caches
16:36:54 <b_jonas> ais523: hmm... ok, then maybe you could suppose it's related to cores
16:40:52 <b_jonas> int-e: or, I guess, alignment could perhaps matter for how the bits are layed out on the memory chips
16:41:17 <b_jonas> however, I don't see how that could result in two so different discrete constant speeds even for the longest (64 megabyte long) memory reads
16:53:45 <int-e> Too many unknowns. I'd like to know which processor, I'd like to see the code, I'd like to see kernel events (any frequency scaling?), I'd probably spend a bit on the actual machine code (any funny loop unrolling?); lots of things to poke at with no clear idea.
16:54:13 <b_jonas> Here's a clue: all the results I got in the first hour of the experiment were the slower speed, and all the results in the following two hours are of the higher speed.
16:54:17 <b_jonas> int-e: wait, I can tell you some of the bit
16:55:04 <b_jonas> int-e: the cpu is an intel Core2 6300 1.86 GHz
16:55:26 <b_jonas> I can show you the source code and the assembled code because I've looked at it myself
16:55:56 <b_jonas> there's some extra register moves that the compiler left in and that are probably pointless
16:57:51 <b_jonas> the loop unrolling is manually done by me, I read 256 bytes in each loop iteration
16:58:10 <b_jonas> the compiler kept that, it's just reordered whcih order the 16 reads happen
17:02:15 <int-e> hmpf, now I want to make a "hot cache" joke (they make things go fast)
17:03:31 <b_jonas> int-e: here's the program, the compile options, and the assembly: http://dpaste.com/04KPY18 http://dpaste.com/1CTY8S8 http://dpaste.com/3F6YPN7
17:04:04 <b_jonas> int-e: in the assembly program, the relevant loop starts at the label .L94
17:04:59 <b_jonas> you can see that it does the 16 memory reads, each 16 bytes long, and no other memory access
17:05:30 <b_jonas> (well, apart from accessing the page table, page table caches, and code cache of course)
17:10:22 <int-e> Yes. I did think of the page tables, but I believe the effects caused by those are hidden in the noise.
17:11:22 -!- ProofTechnique has quit (Ping timeout: 240 seconds).
17:11:53 <int-e> (there aren't enough accesses to explain a 10% difference; besides the allocation is so big that the libc should request 4MB pages anyway)
17:12:02 <int-e> (making the effect even smaller)
17:12:26 <b_jonas> int-e: the problem with the page tables is that the intel manuals don't give any details about how the page table cache in their cpus work. they mention that the page table cache exists, but calls it somethign else, not page table cache.
17:12:44 <int-e> translation lookaside buffer, tlb
17:13:02 <int-e> not sure I got the middle word correct
17:13:18 <int-e> but I did, apparently
17:15:06 <int-e> and yes, tlb's are secret sauce in intel processors - all automatic and therefore deeply magical.
17:16:44 -!- arjanb has joined.
17:16:50 -!- ProofTechnique has joined.
17:21:11 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
17:34:59 <b_jonas> yes, I think it's called TLB
17:36:20 <int-e> Anyway, the effect of TLBs may be larger than I thought (it's hard to say; there's prefetching magic that will hide a lot of latency), but I don't see how it could be so uniform.
17:38:41 <b_jonas> int-e: the prefetching magic certainly matters to increase the speed of these kinds of loops, because they mean that even without explicit prefetch instructions the memory load throughput will always be used to the full, rather sitting idle half the time and then acting only when the load instruction is issued
17:39:30 <b_jonas> this matters especially in the L2 cache case, the middle part of the diagram
17:40:04 <int-e> (The theory would be that at some point, enough contiguous memory is free that the program can allocate its buffer in one contiguous chunk in memory that can be described with just a few pagetable entries. but I'd expect more noise between the two lines.)
17:40:14 <b_jonas> I don't know how that interacts with the page cache, or whether the page cache is ever speculatively fetched though
17:40:52 <int-e> It also depends on the machine being heavily loaded (at least memory-wise)
17:41:38 <int-e> Oh well. Time to go home. Laters
17:43:42 <b_jonas> in theory, if the page cache mattered, you could see that a third step in the stairs, but it's a very small step so it might be hidden by the noise, and it might be very close to the step from L2 cache to main memory, so it could be masked
17:43:57 <b_jonas> I don't know how the page cache really works, so I can't really tell what to expect
17:46:31 <b_jonas> anyway, I deliberately chose _sequential_ memory reading, rather than random access, so that the prefetcher and speculative execution can do its best, and so that the page cache doesn't matter much
17:47:21 <b_jonas> (technically it's not completely sequential, because the four lines in each loop iteration aren't read in the right order, but it's sequential if you're looking at it in larger scale)
17:47:53 <b_jonas> I'm leaving too, if you want to know the solution, I'll tell you in the evening.
17:53:21 -!- hjulle has joined.
18:00:05 -!- bb010g has quit (Quit: Connection closed for inactivity).
18:12:08 -!- ais523 has quit.
18:16:56 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:17:08 -!- Lymia has quit (Ping timeout: 256 seconds).
18:17:29 -!- bb010g has joined.
18:35:11 -!- oren has joined.
18:46:53 <int-e> b_jonas: I'm definitely interested in the answer.
19:10:24 -!- Frooxius has quit (Ping timeout: 256 seconds).
19:34:44 -!- AnotherTest has joined.
19:38:52 -!- AnotherTest has quit (Ping timeout: 240 seconds).
19:47:35 -!- ProofTechnique has joined.
19:47:37 -!- mihow has quit (Quit: mihow).
19:48:22 -!- Frooxius has joined.
19:49:11 -!- Froox has joined.
19:53:13 -!- Frooxius has quit (Ping timeout: 264 seconds).
20:06:13 -!- Patashu has joined.
20:11:54 -!- augur has quit (Read error: Connection reset by peer).
20:12:33 -!- augur has joined.
20:23:39 -!- mihow has joined.
20:24:25 -!- Patashu has quit (Ping timeout: 264 seconds).
20:49:33 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42061&oldid=42060 * Ypnypn * (+75)
20:50:01 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42062&oldid=42061 * Ypnypn * (+25)
20:55:35 -!- kcm1700 has quit (Remote host closed the connection).
20:55:48 -!- kcm1700 has joined.
21:20:15 -!- bb010g has quit (Quit: Connection closed for inactivity).
21:22:56 -!- mihow has quit (Quit: mihow).
21:35:10 -!- Lymia has joined.
21:38:07 -!- FreeFull has quit (Ping timeout: 265 seconds).
21:42:28 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42063&oldid=42062 * Ypnypn * (+33) /* Constants */
21:45:39 -!- augur has quit (Ping timeout: 245 seconds).
21:50:59 -!- augur has joined.
22:01:43 -!- AnotherTest has joined.
22:05:17 -!- augur has quit (Ping timeout: 245 seconds).
22:07:51 <b_jonas> int-e, FireFly: ok, telling answer now
22:08:02 <b_jonas> the difference was because of the video card built in to the motherboard
22:08:15 <b_jonas> the setting was such that after about an hour, the screen was blanked
22:08:37 <b_jonas> before that, the video card had to read the ten megabyte sized screen buffer fifty times per second
22:09:02 <b_jonas> sixty times per second in fact
22:09:16 <b_jonas> [ 1920*1280*4*60 NB. bytes per second
22:09:16 <j-bot> b_jonas: 589824000
22:09:18 <int-e> Right. That never happened to me; I buy "proper" graphics adapters.
22:09:33 <b_jonas> ^ that's the half gigabyte per second difference
22:09:46 <int-e> Nice trap. Thanks for sharing.
22:10:07 <b_jonas> I later measured to verify this by deliberately blanking the screen then resuming, and got consistent results
22:11:07 -!- arjanb has quit (Ping timeout: 246 seconds).
22:11:34 <b_jonas> int-e: if the proper graphics adapter uses a separate memory from the main ram, don't you pay for that because then the cpu can access that ram slower?
22:12:33 <int-e> hmm, but at least they're separate buses though, and I only pay for that when updating the screen.
22:13:07 <b_jonas> int-e: yes, that's true, which would make a difference in this case
22:13:12 <int-e> (I also don't use a compositing manager)
22:13:25 <int-e> (so the math is all different)
22:14:14 <b_jonas> the screen was barely touched in this case, so a separte video card would certainly make it easy
22:14:59 <b_jonas> the fun part is that I still pay for the video card when the display is turned off with its power button
22:15:45 <b_jonas> of course, in this case just buying a more modern machine would double the memory speed, which would count for much more than anything about the video card
22:16:27 -!- augur has joined.
22:17:45 <int-e> but it'd still be 5%
22:18:17 <int-e> you should lower the screen resolution to 640x480 ;-)
22:18:31 <b_jonas> int-e: or switch to text mode, or lower the resolution and the refresh rate too
22:18:38 -!- augur has quit (Read error: Connection reset by peer).
22:18:42 <b_jonas> switching to text mode might be the most practical
22:19:32 <b_jonas> putting the slow computations to faster server machines I have access to rather than my home machine is the most practical
22:20:04 <b_jonas> it's exactly because I don't do tasks that need lots of computations on my home machine why I haven't bought a faster home computer yet
22:20:21 <b_jonas> when I'll need fast computations, I'll just buy a modern machine with lots of RAM
22:21:53 <int-e> The whole thing is funny. If you listen to John Carmack, he's saying that the unified memory for GPU and CPU is going to win. But he's interested in high-end graphics, where the bottleneck is getting all the data for the next frame to the GPU.
22:22:43 -!- ^v has quit (Read error: Connection reset by peer).
22:22:54 <b_jonas> I don't do GPU programming, so I don't really have an opinion on this. I'm more interested in how I can do more efficient computations on the CPU.
22:23:04 <int-e> (I forgot where he said that, the quakecon talk last year would be my guess)
22:23:09 -!- ^v has joined.
22:23:13 <b_jonas> That's why I'm trying to understand how the CPU accesses memory and how its caches work.
22:23:24 <b_jonas> (And also other stuff about CPUs.)
22:24:32 <int-e> Oh, and let's do the same math for a 4K resolution.
22:24:42 -!- GeekDude has joined.
22:25:51 <b_jonas> int-e: machines with 4K resolution probably have a twice faster ram than this one
22:25:56 -!- augur has joined.
22:25:56 <b_jonas> even my work machine has a twice faster ram
22:26:17 <b_jonas> this is an old but beloved computer
22:26:20 <int-e> b_jonas: yes, 4x more bandwidth for driving the monitor when you have 2x more memory bandwidth. :)
22:26:45 <b_jonas> int-e: yes, a recent machine _might_ have 4x this bandwith possibly, if you pay enough
22:26:49 <olsner> shouldn't the gpu have some sort of cache? maybe not a whole frame buffer though...
22:27:04 <int-e> But whatever. 4k resolution is silly anyway.
22:27:36 <b_jonas> olsner: yes, it should probably have enough cache to cache the text mode font, which is usually only 4 kilobytes, but can be up to 16 kilobytes in size
22:27:51 <int-e> olsner: I expect it has a cache for textures and the like, to speed up the actual rendering.
22:28:00 <b_jonas> olsner: or enough to cache a line in a double-scan graphics mode (say 320x200 on a crt)
22:28:17 <b_jonas> but a cache won't help for the whole screen unless you have 10 megs of it
22:30:47 <b_jonas> int-e: also, it's not really 4 times the bandwidth, only 3.2 times. I have 1.25 the resolution of a normal monitor because I use a true 1920x1280 one rather than the usual 1920x1080.
22:31:35 <b_jonas> no, 3.4 times the bandwidth
22:33:56 <int-e> I think I'll condense this to "if you want the program to run faster, switch to text mode" and go annoy some people with this wisdom.
22:34:48 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
22:37:28 <b_jonas> int-e: not quite, because it's only true to programs that are truly memory-bound
22:37:59 <int-e> Yes, it's wrong in many cases.
22:38:16 <b_jonas> and of course it depends on the computer too
22:38:25 <int-e> (the aforementioned standalone graphics adapter is another)
22:38:53 <b_jonas> wouldn't "if you want the program to run faster, turn off the video signal blanking the screen" be more annoying though?
22:39:08 <int-e> and it's even conceivable that an on-board GPU comes with its own video buffer anyway.
22:43:08 <b_jonas> int-e: especially since AMD has bought ATI, they can now make both motherboards and videocards
22:44:58 -!- augur has quit (Ping timeout: 255 seconds).
22:45:32 <int-e> and combine CPU/GPU into a single chip. https://en.wikipedia.org/wiki/AMD_Accelerated_Processing_Unit
22:46:40 <b_jonas> but yes, that's exactly the sort of advice that should be spread to annoy people who want to use multithreading and JIT and GPU computing to add two numbers, because they heared the GPU can add numbers faster, but actually care more about the buzzwords than the performance.
22:47:56 <b_jonas> they really annoy me for some reason. especially in the few cases when it's people at work.
22:48:31 <int-e> I hope it's not literally 2 numbers.
22:48:58 -!- augur has joined.
22:49:43 <b_jonas> and the problem is only partly that they want to use it for inapproperiate tasks, but also that they try to jump to these difficult to use techniques while ignoring much easier possibilities for optimizing their code, like correcting obvious wastes of time.
22:50:19 -!- AnotherTest has quit (Remote host closed the connection).
22:50:22 <int-e> > foldl (\x y -> 1 + y/(y+10) * x) 0 [0..490] :: Rational -- d'oh!
22:50:51 <b_jonas> and I admit that there's at least one case when multithreading actually helps, at least one case when JIT actually helps, and at least one case when GPU programming actually help. it's just that people ignore the basics like how to write programs for the cpu properly before trying to learn these stuff.
22:51:20 <b_jonas> and they don't care to measure what's actually slow in their program or whether their changes actually help in any way or preserve correctness.
22:52:37 <int-e> right, profile, reconsider algorithms, and it doesn't hurt to think about parallelizing stuff (we have many multicore cpus nowadays) when the algorithm looks good.
22:52:42 <b_jonas> nor do they learn how to apply these advanced techniques properly, which is not surprising, because you can't use them efficinetly withotu using the basics.
22:52:55 <b_jonas> they write unsafe multithreaded programs that then crash.
22:53:02 <int-e> of course, keep an eye on the cache hierarchy (part of the algorithm...)
22:53:59 <b_jonas> and they write unsafe single-threaded code that trashes memory by writing past array bounds or to freed memory or through uninitialized pointers, and then the program crashes.
22:54:18 <b_jonas> and then they try to blame _my_ good code which they happen to run in the same process.
22:54:28 <int-e> great, now take that to the GPU. the OS won't save you this time *g*
22:55:05 <b_jonas> they can't even write correct code, not even robust or performant or multithreaded one.
22:55:20 <b_jonas> of course, this is not universal. I also have good experiences at work, with colleages from whom I can learn a lot.
22:55:53 <int-e> I don't want those times back, but having to reboot the computer when you did a programming mistake was good for teaching me a minimal amount of care.
22:57:34 -!- augur has quit (Ping timeout: 255 seconds).
22:59:16 -!- augur has joined.
23:03:16 <b_jonas> I think only one of them does irc though.
23:11:36 -!- ^v has quit (Quit: Network ban).
23:17:39 -!- `^_^v has quit (Ping timeout: 252 seconds).
23:22:35 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
23:25:03 -!- 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?").
23:28:14 -!- chaosagent has joined.
23:30:40 -!- vanila has quit (Quit: Leaving).
23:34:20 -!- GeekDude has joined.
23:34:44 -!- boily has joined.
23:38:07 -!- Phantom_Hoover has joined.
23:39:34 -!- FreeFull has joined.
23:53:54 -!- FireFly has quit (Quit: WeeChat 0.4.0).
00:13:23 -!- adu has joined.
00:18:05 -!- ProofTechnique has joined.
00:22:44 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
00:27:33 -!- Phantom__Hoover has joined.
00:29:13 -!- fractal has quit (Ping timeout: 265 seconds).
00:30:11 -!- aretecode has quit (Ping timeout: 265 seconds).
00:30:15 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
00:32:50 -!- aretecode has joined.
00:34:25 -!- Tritonio has joined.
00:37:02 -!- fractal has joined.
00:46:21 <oren> I usually run long-running jobs on the university's computer
00:47:56 <oren> because as some of you know, my personal computer is total crap
00:54:42 <boily> helloren. what kind of long-running jobs are they?
00:59:49 <oren> graphics rendering, ai training, that sort of thing
01:19:06 -!- ProofTechnique has joined.
01:24:25 <boily> elliott: helliott. I find this acceptable: the +1 long sword of Punishment (weapon) {drain, +Blink +Fly rElec rPois Dex+2}
01:26:11 <elliott> that's a very caster weapon, heh
01:27:16 -!- zemhill_ has joined.
01:27:54 -!- zemhill has quit (Remote host closed the connection).
01:29:17 <oren> #define up2(i,n) for(i=0;i<(n);i++)
01:29:33 <elliott> boily: your term is slightly less huge than usual. I find this commendable.
01:33:32 <oren> #define up3(i,q,n) for(i=(q);i!=(n);i++)
01:34:00 <pikhq> #define malloc(x) ((void*)&(x))
01:34:44 <oren> #define new(T) (T*)malloc(zv(T))
01:34:58 <oren> #define zv(T) sizeof(T)
01:35:41 <pikhq> #define return for(;;)
01:36:54 <oren> #define zzzzz do{printf("FUUUUUU");exit(374872);}while(1)
01:36:57 -!- zzo38 has joined.
01:37:20 <pikhq> On a vastly more serious note, unshare() is neat.
01:38:32 <boily> elliott: my term is slightly huger when I'm on my laptop hth
01:38:43 <elliott> that sounds a bit backwards.
01:38:46 <boily> elliott: also, I'm experimentaling with my skills.
01:39:10 <boily> my laptop's display is 1920×1080, whereas my desktop's is 1680×1050.
01:39:47 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
01:41:32 <oren> #define randi(l,u) rand()%(u-l+1)+l
01:42:42 <boily> I got splattered to smithereens.
01:43:03 <boily> mismanaged the mob and I was exploded into tiny slimy bloody fragments.
01:43:44 -!- Tritonio has quit (Ping timeout: 252 seconds).
01:47:13 -!- Lymia has quit (Ping timeout: 250 seconds).
01:47:21 -!- oerjan has joined.
01:48:13 -!- Froo has joined.
01:52:01 -!- Froox has quit (Ping timeout: 264 seconds).
01:57:16 -!- FireFly has joined.
02:17:19 -!- hjulle has quit (Ping timeout: 245 seconds).
02:29:33 -!- Lymia has joined.
02:37:46 <boily> quinthellopia! DCSS.
02:38:08 <boily> well, playing is a fancy word. I'm more down to earth, back to dying simply and effectively.
02:39:33 <oerjan> always look at the bright side of death
02:40:18 <boily> hellørjan. the more practice you have dying, the better you get at avoiding it!
02:46:05 * boily is thinking to himself “I am not being called Girly Molly. I am not being called Girly Molly. Brain, stop being dyslexic.”
02:46:43 <oerjan> ye brane, staff beeing disliking
02:46:57 -!- dianne has quit (Ping timeout: 245 seconds).
02:48:04 <boily> I could be Molly Grue for all I know... self identity is such a hazy concept.
02:48:55 -!- dianne has joined.
02:55:24 -!- boily has quit (Quit: UNICORN CHICKEN).
02:59:54 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:19:36 -!- GeekDude has joined.
03:22:08 -!- GeekDude has quit (Client Quit).
03:46:19 <oren> confirmed: a single-layer perceptron utterly fails at doing xor
03:48:24 -!- MDude has changed nick to MDream.
03:49:18 <oren> But ti works with a 2-2-1 network, thus showing that my code is correctly implemented. ieiii!
04:13:29 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
04:52:13 -!- bb010g has joined.
04:54:07 <Sgeo> https://www.reddit.com/r/videos/comments/2ujjl8/he_may_be_british_but_the_point_applies_in_the_us/
04:54:20 <Sgeo> Horrifically anti-intellectual video or important point about missing priorities?
04:54:40 <Sgeo> I tend to think it's both, that the things people aren't taught in school that he mentions absolutely should be
04:54:55 <Sgeo> But don't really see a downside to teaching those 'useless' things as much
04:55:06 <Sgeo> (Except that priotization is a thing)
05:12:01 <oren> Most of the things he mentions were taught to me by my parents
05:12:59 <Sgeo> I don't think it's necessarily a good idea to rely on that in general though
05:13:33 <Sgeo> Especially for important-but-not-yet-commonly-known things, such as recognizing signs of mental illness. Can't teach how to treat or perfect detail maybe, but can teach at least some recognition signs
05:14:51 <oren> True, that one is a good idea
05:15:37 <oren> But how to vote, pay taxes or budget, and the laws, were all taught to me by my parents
05:17:01 <oerjan> hm i don't think my parents taught me any of those
05:17:03 <Sgeo> I still don't know how to budget >.> I just sort of assume that if I set aside 20% of my income as 'allowed to spend frivolously' I'm good. Except that that account has become my -pay stuff online- account, which isn't perfectly correlation with -stuff I want but don't need-
05:17:18 <oerjan> although my mom was darn good at budgeting so i'm sure she would have if i'd asked
05:17:55 <Sgeo> Also going to need to figure out taxes for the first time this year
05:18:22 <oren> One thing that he didn't mention is cooking. Absolutely everyone should be able to cook a meal for themselves.
05:18:23 <Sgeo> (Last year my dad did them for me. Totally educational. I need to stop relying on him)
05:18:26 <oerjan> (i suppose they may have told me _some_ laws. i'm still unsure about many.)
05:20:55 <oerjan> i knew how to do my taxes once, but the government has made it so easy that i don't need to any more
05:21:10 <oren> The best point he makes imo is the one about history. I only know what the Cold War was abut because my father explained it. it was never covered in school.
05:22:25 <oren> They covered c. 1912-1945 when they should have covered 1950-2000
05:23:16 <lifthrasiir> education was never free from the influence of politics
05:25:23 <oerjan> (basically everyone who doesn't have a complex economy (like running your own business or the like) gets a suggested tax form from the government, and if you basically agree with it you don't need to do _anything_)
05:28:52 <oerjan> the insane part is that this makes the tax authorities the most service-minded branch of the norwegian government, with the best publicity.
05:28:57 <oren> "you won't have a calculator every day" -- only true in primary education system. In University either the numbers are so small you don't need them, or you DO get a calculator
05:29:27 <oerjan> ...until you actually _disagree_ with them, that is. then things can get rather ugly.
05:30:19 <oren> I don't know my times tables, and this has not been a detriment since grade 11.
05:30:33 <oerjan> (but i don't expect they're worse than other countries in that respect.)
05:32:55 <Sgeo> There were a few current event projects in my school, where we were tasked with writing about whichever current event we wanted
05:33:12 * oerjan does know his times tables. helps a lot with that calculator crossword in the newspaper. also, prime numbers.
05:33:31 <Sgeo> The thing about calculators I disagree with though. Yes, we carry around calculators, but there's no way any of my teachers could have predicted that.
05:33:50 <Sgeo> Most teachers can't see the future.
05:34:04 <oren> When i was in school hand calculators were already universal
05:34:21 <oren> it was the 90's after all
05:34:26 <Sgeo> Would you have believed you would carry one in your pocket every day?
05:34:32 <Sgeo> For your adult life?
05:35:03 <oren> My friend had one on his keychain, so yes.
05:36:33 <oren> I mean-- I was born in 1993. There were cell phones, laptops, etc throughout my childhood
05:37:04 <oerjan> the year september never ended
05:37:42 <oerjan> that's how i know i'm old on the internet, i was there _before_ that.
05:38:23 <oren> My dad told be email addresses used to look like name!name!name
05:38:34 <Sgeo> I had crappy laptops during my childhood
05:38:59 <Sgeo> I remember bringing a DOS laptop to my babysitter's house when I was a kid
05:39:21 <zzo38> I often make calculation by hand or by mind if it is simple enough, although I also have a TI-92 calculator that I usually have when traveling somewhere
05:39:35 <oren> My mom had a IBM DOS laptop that she made my dad carry because it was heavy as hell.
05:42:57 <oerjan> i still have the Oric-1 down in the storage room (technically it's my dad's), i think if i tried to turn it on the neighbors would call the cops on me, that had some _ugly_ radio interference.
05:45:12 -!- adu has quit (Quit: adu).
06:28:45 -!- Froo has quit (Quit: *bubbles away*).
07:31:00 -!- Patashu has joined.
07:34:32 -!- chaosagent has quit (Read error: Connection reset by peer).
07:59:19 <zzo38> The rules of golf says that ice can be considered as casual water or as loose impediments at your choice. If it is loose impediments then you can remove it, but what happen if both balls are on the putting green, whoever ball is farther away from the hole wants to remove it, is the other player allowed to put it back exactly where it was before in order to treat it as casual water or you have to do without it instead?
08:03:50 -!- FreeFull has quit (Ping timeout: 246 seconds).
08:05:40 -!- tromp__ has joined.
08:05:40 -!- zzo38 has quit (Read error: Connection reset by peer).
08:09:16 -!- tromp has quit (Ping timeout: 255 seconds).
08:09:25 -!- zzo38 has joined.
08:12:05 <zzo38> What is "/w00tw00t.at.blackhats.romanian.anti-sec:)"?
08:18:55 <b_jonas> zzo38: well, if both players can choose to remove or replace the ice at will any number of times, then clearly the non-active player gets to decide the outcome due to the infinite loop rules.
08:22:07 <zzo38> I get other strange HTTP requests too such as for "/lolo/lol/lo.php" and "/tmUnblock.cgi" and "/wqwq/wqw/wq.php" as well as one that doesn't have a valid request method; the entire request is "\xa7\x02" without GET or anything else.
08:22:57 <b_jonas> zzo38: maybe that tried to be some request for some protocol other than HTTP
08:23:42 <zzo38> Well, it isn't a protocol I recognize. Other malformed requests include "\xff\xff\xff\xff@\x01r" and "\xff\xff\xff\xff@\x01s"
08:24:10 <zzo38> (I also don't know what "/muieblackcat" is.)
08:24:16 <zzo38> Do you recognize any of these?
08:25:01 -!- Frooxius has joined.
08:25:10 <oren> I reimplemented this font http://www.arcavia.com/Software/ProgFont/. http://snag.gy/lkMAc.jpg
08:26:52 <oren> All kinds of crazy code is running out there. Could be a malformed student project, a malfunctioning botnet, who knows
08:30:10 <zzo38> Also "/rom-0" and "/back.css" and "/tag_products.php?id_tag=%27" and "/w00tw00t.at.ISC.SANS.DFind:)" and "/1gophserv" (this last one seems to be a misinterpretation of a gopher URL as HTTP). And even "/user/soapCaller.bs" and various requests for stuff in /cgi-bin/ (I have nothing there) and many things that are trying to be proxy requests.
08:31:52 <oren> requests for cgi-bin are possibly hacking attempts?
08:32:24 <zzo38> I would think they try to see what software is installed. Well, there is no such file.
08:33:34 <zzo38> However, they try the same file too often, and they shouldn't do that after you can already see there is no such files.
08:46:40 <b_jonas> zzo38: I've got /muieblackcat in my apache logs, let me see the others
08:47:44 <zzo38> Do you have files with any of those names on your computer?
08:48:01 <b_jonas> well, let me locate, but definitely not in the HTTP
08:48:04 -!- Frooxius has quit (Quit: *bubbles away*).
08:49:48 <b_jonas> I've got requests for /rom-0 (maybe it's some router or other embedded device thing), requests with User-Agent starting with () to try to use that bash vulnerability,
08:50:59 <Jafet> http://blog.malwaremustdie.org/2013/10/a-disclosure-of-whats-behind-w00tw00t.html
08:51:41 <b_jonas> and yes, I've got /w00tw00t.at.blackhats.romanian.anti-sec:) too
08:52:04 <b_jonas> what other files did you say? let me see
08:53:16 <b_jonas> and also /user/soapCaller.bs
08:53:27 <b_jonas> so basically all of them, except /1gopherserv
08:57:08 <zzo38> /1gophserv is specific to my computer because probably someone tried to follow a gopher:// URL but it changed to http:// and then it didn't work.
08:58:54 <b_jonas> I get hits to files that actually exist, very often apparently from the bots of google, yahoo, and baidu
09:01:05 <b_jonas> zzo38: have you got any of the bash bug requests?
09:03:27 <zzo38> I don't know; I cleaned the log now and don't log user-agents
09:03:34 <mroman> If you multiply an MVar Double with a Double
09:03:56 <mroman> in a function like foo someMVar someDouble
09:04:07 <mroman> it will say: Expected type MVar Double -> MVar Double
09:06:36 <mroman> http://codepad.org/dE059AxK
09:06:55 <mroman> or is there a Num instance for MVars?
09:07:08 <mroman> I'd expect it to report No Instance Num (MVar Double)
09:07:30 <b_jonas> wouldn't you need to read the mvar and then >>= multiply it
09:08:37 <b_jonas> like, fmap (2.7*) :: MVar Double -> IO Double
09:48:10 -!- Tritonio has joined.
09:59:22 <oerjan> mroman: pretty sure your last $ var should be $ value hth
10:02:16 <oerjan> also that error message doesn't contain "Expected type MVar Double -> MVar Double" so what are you babbling about
10:06:53 <oerjan> you _could_ actually make a Num instance for MVars, couldn't you. or even an Applicative instance. it would be weird and not very thread-safe...
10:07:41 <oerjan> not without unsafeSomething.
10:07:57 -!- Phantom_Hoover has joined.
10:08:59 <oerjan> otoh if you had newtype CrazyApp a = CrazyApp (IO (MVar a))
10:30:36 <Jafet> instance (Appicative f, Num a) => Num (f a)
10:31:32 <oerjan> that's what i was alluding to
10:33:10 <oren> Between 1788 and 1868, approximately 165,000 convicts were transported to various parts of Australia. All of them were category theorists.
10:41:47 -!- SopaXorzTaker has joined.
10:58:58 -!- Patashu_ has joined.
10:58:58 -!- Patashu has quit (Disconnected by services).
10:59:58 -!- Patashu_ has quit (Client Quit).
11:06:27 -!- Patashu has joined.
11:10:52 -!- oerjan has quit (Quit: leaving).
11:17:50 <Jafet> The nvicts were hanged.
11:24:32 -!- Tritonio has quit (Ping timeout: 252 seconds).
11:26:40 -!- boily has joined.
12:00:31 <J_Arcane> Well, this is some wild stuff. Like Haskell in Lisp-ish syntax. https://github.com/ympbyc/Carrot
12:08:55 -!- oren has quit (Quit: Lost terminal).
12:22:18 -!- boily has quit (Quit: WHITEPOINT CHICKEN).
12:27:59 -!- Koen_ has joined.
12:28:44 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
12:31:13 -!- vanila has joined.
12:33:32 <vanila> http://esolangs.org/wiki/--C-%3DC-C--
12:33:35 <vanila> how is this turing complete?
12:34:54 -!- hjulle has joined.
12:40:34 <Jafet> You can write hello world and 99 beers in it, qed
12:49:29 -!- oren has joined.
12:53:52 -!- Patashu has quit (Ping timeout: 240 seconds).
13:29:04 <vanila> is C++ templates an esolang
13:31:06 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
13:31:45 -!- ProofTechnique has joined.
13:31:46 <oren> c++ templates is some kind of language
13:43:05 <vanila> http://en.wikipedia.org/wiki/Barton%E2%80%93Nackman_trick
13:43:22 <vanila> this is like math or something
13:50:45 <oren> everything is like math or something. usually like something, but sometimes like math.
13:54:11 <Jafet> Nah, this is a pointer.
14:01:47 <oren> But basically this whole trick is just a workaround of the fact that c++'s algolish syntax doesn't define which operand of == is the "self".
14:02:06 <b_jonas> algolish as opposed to smalltalkish?
14:03:03 <oren> as opposed to all the excellent alternatives
14:03:53 <oren> for example, you could make a rule that a==b is always a.equals(b)
14:04:36 <b_jonas> oren: that would be a bad idea, because then you could no longer write (0 == smartpointer) or write (nullptr == smartpointer)
14:05:24 <Jafet> You can, in fact, have two different definitions for a==b and b==a
14:05:52 <oren> good point. maybe b.equals(a) would be better for the constant == variable convention (which is only necessary because they used = for assignement)
14:06:24 -!- FreeFull has joined.
14:16:16 <oren> http://snag.gy/uZKT8.jpg
14:19:02 <oren> C++'s resolution rules are way too complex enyway
14:19:06 <vanila> lol the size difference
14:19:16 <vanila> btw you might be interested in PNG
14:22:20 <oren> vanila: Oh, you mean in the picture. yah, artists cometimes screw up the perspective like that
14:25:06 <myname> quick haskell question: in an Array Int (Map foo bar) will i be able to somehow update the map without changing the array?
14:26:24 <Jafet> Array e a is just a faster [a]
14:27:07 <myname> that doesn't answer the question
14:27:29 <Jafet> You're right, it doesn't
14:27:58 <myname> like: can i update a single element?
14:28:11 <oren> does haskell have mutable state?
14:28:31 <vanila> you could use a mutable array instead of Array
14:29:04 <myname> isn't that horribly slow at writing?
14:29:15 <vanila> I don't think so, I dont really know though
14:30:16 <tromp_> not slow at all. it just mutates in place
14:31:39 <dulla> was there any progress on diff arrays to not suck
14:31:43 -!- FireFly has quit (Changing host).
14:31:43 -!- FireFly has joined.
14:32:35 <tromp_> yes, mutable arrays live in IO or ST monad
14:33:14 <Jafet> If you don't know, use Data.Sequence.
14:33:59 <vanila> ST is really cool because it is mutable internally, but can be used in a pure way
14:36:10 <dulla> set aside the state
14:36:28 <dulla> when you use the state, it's impure
14:36:29 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
14:37:06 <dulla> boxed versus unboxed
14:42:31 <myname> okay, sequence is too slow
14:45:49 -!- FreeFull has quit (Ping timeout: 256 seconds).
14:48:57 <TieSoul> http://www.reddit.com/r/dailyprogrammer/comments/2ww3pl/2015223_challenge_203_easy_the_start_of_something/coyxvoj
14:49:21 <TieSoul> most of the program is just gibberish.
14:52:37 <TieSoul> of course, the program isn't actually square
14:52:48 <TieSoul> it just looks square when printed in plaintext
14:54:35 <vanila> http://www.netfunny.com/rhf/jokes/88q3/0tenny.html
14:54:41 <vanila> saw this on the wiki..
14:57:32 <TieSoul> https://gist.github.com/TieSoul/0e116f1156e2ae1d5ffe here's the "clean" version
14:58:47 <TieSoul> also, Gist has a Befunge language category, but no highlighting.
15:02:41 -!- `^_^v has joined.
15:06:24 <J_Arcane> TieSoul: I think HackerRank supports doing exercises in Befunge.
15:07:30 <J_Arcane> Ahh, no, I'm mistaken, I think I was thinking of somewhere else.
15:07:40 <J_Arcane> It does have Brainfuck and Whitespace though.
15:08:31 <fizzie> I promoted Befunge at work the other day.
15:08:44 <fizzie> Mainly by showing fungot sources to colleagues.
15:08:44 <oren> how complex would the highlighting regexes for befunge be?
15:09:00 <fizzie> They commented that it all seemed very practical.
15:09:33 <fizzie> (I also showed them the graphified version.)
15:09:37 <b_jonas> did someone say fungot? is he back?
15:09:57 <fizzie> A BT engineer has promised to visit on March 3rd.
15:10:06 <TieSoul> sounds like an interesting challenge
15:10:30 <oren> in most editors, regexes are used to decide the syntax colorings.
15:10:53 <fizzie> Of course, I'll be off-country the next two weeks or so, so the fungot shortage shows no signs of abating.
15:11:31 <fizzie> You could do the trivial context-free highlighting trivially.
15:11:40 <TieSoul> I don't think you could accurately tell what's a string and what's not without running it
15:11:47 <fizzie> And the more complicated thing not at all, pretty much.
15:12:02 <TieSoul> and some things could be both a string AND not
15:12:19 <b_jonas> and the contents of cells can change during running the program too
15:12:30 <TieSoul> so context-free highlighting is pretty much the best you're going to get
15:12:38 <fizzie> Being both string and commands is just a matter of translucency.
15:13:11 <fizzie> For a "well-behaved" program, you can do quite a bit with static analysis, but the editor context is worse for that kind of stuff, since the code would spend most of the time being invalid.
15:13:38 <fizzie> Every time you misplace a >, the rest of the program would be re-highlighted completely differently.
15:13:39 <b_jonas> fizzie: translucency if it's achieved using bridges (trampoline instructions), polarized light if it's achieved using different directions of execution
15:14:14 <TieSoul> befunge highlighting can't be properly done with regexes.
15:14:17 <fizzie> b_jonas: Combined with one of those polarized 3D glasses, that'd be nice.
15:17:08 <fizzie> http://users.ics.aalto.fi/htkallas/fungot.png for those who haven't seen it yet.
15:17:52 <oren> it can't be displayed because it has errors
15:18:07 <fizzie> Works for me. It's a biggish file, though.
15:19:04 <TieSoul> automatically generated Befunge flowcharts?
15:19:16 <fizzie> http://users.ics.aalto.fi/htkallas/fungotsmall.png is a 1:5 scale replica, if 7485x15016 sounds scary.
15:20:02 <fizzie> There's a bit of crude heuristics to handle things like j.
15:20:45 <oren> jesus christ... pkill -9 firefox
15:21:30 <fizzie> Also I think there was some heuristic about ignoring reflections from fingerprint instructions that don't "look like" they're being handled, since those are a big source of potential static control flows that don't (or shouldn't) occur in practice.
15:22:36 <TieSoul> is the flowchart generator up for download? :P
15:22:38 <b_jonas> what are fingerprint instructions?
15:23:21 <Deewiant> oren: https://groups.google.com/d/msg/comp.unix.questions/Pg0Gv1Vk9G4/O-k8lym2DXoJ
15:33:32 -!- CADD has quit (Ping timeout: 265 seconds).
15:37:13 -!- tomlukeywood has joined.
15:37:23 -!- tomlukeywood has left.
15:37:37 -!- dulla has quit (Ping timeout: 264 seconds).
15:47:17 -!- dulla has joined.
15:48:24 <fizzie> TieSoul: I don't think so, I think I did it as a ugly one-off Java thing or something.
15:49:28 <fizzie> b_jonas: The A..Z commands can be redefined by loading fingerprints. They have a general contract (of sorts) that they reflect on error, but of course for many fingerprints there are often instructions that never fail.
15:53:49 <oren> I use pkill -9 firefox when firefox has started swapping and is threatening to hang my system.
15:55:27 <Melvar> oren: Do you need swap?
15:57:23 <oren> I have only 2GB memory
15:59:19 <oren> Some programs need morethan that, but unlike Firefox they don't need it all at once
16:01:04 <Melvar> oren: I see. Perhaps you could run firefox with a resource limit on memory if you know its behavior in this regard?
16:02:11 <oren> I tried that, it doesn't seem to work well. If only I could ban firefox from swap while letting other procs use it
16:03:34 -!- paul2520 has quit (Ping timeout: 245 seconds).
16:04:01 -!- GeekDude has joined.
16:06:23 -!- FreeFull has joined.
16:07:16 <oren> hmm... maybe the problem would be less if I made a sawp file on a n SD card...
16:07:37 <Lymia> Why are all your strings backwards.
16:08:43 <fizzie> Lymia: You know, stacks.
16:09:24 <oren> why not by convention put all strings in < direction then
16:10:19 -!- mihow has joined.
16:13:42 <Koen_> `befunge <@."hello"
16:13:59 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: befunge: not found
16:14:59 <Lymia> Clearly strings should all be in ^ direction
16:16:09 <Koen_> `funge <@_.<0"hello"
16:16:09 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: funge: not found
16:16:52 <Koen_> ergo: forward strings don't work in befunge
16:24:49 -!- Lymia has quit (Remote host closed the connection).
16:25:14 -!- Lymia has joined.
16:33:25 -!- paul2520 has joined.
16:33:31 -!- paul2520 has quit (Changing host).
16:33:31 -!- paul2520 has joined.
16:34:58 -!- TieSoul_ has joined.
16:35:52 -!- TieSoul has quit (Disconnected by services).
16:35:58 -!- TieSoul_ has changed nick to TieSoul.
16:43:53 -!- augur has quit (Read error: Connection reset by peer).
16:44:12 -!- ^v has joined.
16:44:38 -!- augur has joined.
16:55:36 -!- ^v has quit (Read error: Connection reset by peer).
17:00:01 -!- Phantom_Hoover has joined.
17:00:02 -!- oren has quit (Ping timeout: 252 seconds).
17:05:02 -!- SopaXorzTaker has quit (Remote host closed the connection).
17:07:53 -!- oerjan has joined.
17:09:40 <oerjan> <J_Arcane> Well, this is some wild stuff. Like Haskell in Lisp-ish syntax. https://github.com/ympbyc/Carrot <-- i am pretty sure there used to exist a "liskell"
17:10:15 <J_Arcane> oerjan: There's been a couple. There's even a "Haskell Lisp" Twitter account. But sadly none seem to have ever gone anywhere.
17:11:33 -!- AnotherTest has joined.
17:11:51 <vanila> MLs don't work well with lisp syntax
17:12:04 <vanila> that's why they usually use ML-like syntax
17:22:17 -!- FreeFull has quit (Ping timeout: 265 seconds).
17:22:30 <Koen_> vanila: is there a proof or something?
17:23:27 <J_Arcane> vanila: Well, what's weird about Carrot is, it does use an ML-like syntax, but with everything still being in prefix notation.
17:23:41 <J_Arcane> So = is still the declaration operator...
17:23:50 <J_Arcane> I also couldn't make heads or tails of the conditional syntax.
17:25:07 <lambdabot> (a -> c) -> (b -> c) -> Either a b -> c
17:25:16 <lambdabot> ArrowChoice a => a b d -> a c d -> a (Either b c) d
17:25:29 <oerjan> i guess either is the specialization
17:25:59 <lambdabot> (Data.Bitraversable.Bitraversable r, Applicative f) => (a -> f b) -> r a a -> f (r b b)
17:26:09 <lambdabot> Arrow a => a b c -> a b c' -> a b (c, c')
17:28:24 <oerjan> maybe because c is not to c' as a is to b (because a is the arrow itself)
17:29:08 <oerjan> except, of course, ||| does it anyway
17:29:35 <oerjan> conclusion: it's to confuse people
17:30:25 <Koen_> I seem to recall a haskell manual stating "giving the type of a simple function is usually enough to understand what it does"
17:31:03 <oerjan> it has to be very simple and very polymorphic, though
17:31:05 <Koen_> I guess if I knew what Arrow meant I'd understand though so that's ok
17:31:22 <oerjan> Arrow is kind of a mess
17:32:08 <oerjan> in afterthought it is like a mix of Applicative and Category, but not exactly the former because it has an extra argument
17:32:10 <Koen_> to be honest I don't even know what "a b c" means
17:32:40 <oerjan> a good approximation is to say a = (->), so a b c = (b -> c)
17:32:58 <oerjan> that's the arrow used for 90% of use cases, anyhow.
17:33:38 <Koen_> so &&& merges two functions or something
17:33:46 <oerjan> (it turns out that several of the Arrow methods happened to be useful, not already defined functions for the (->) case)
17:34:29 <oerjan> > (succ *** pred) ('b', 'K')
17:34:34 <b_jonas> they aren't already defined _because_ Arrow existed early enough in the library that people didn't bother to define specializations
17:35:58 <Koen_> and ||| despecializes
17:36:19 <Koen_> takes two functions and merges the domains
17:36:35 <oerjan> > (succ ||| chr) (Left 'a')
17:36:48 <oerjan> > (succ ||| chr) (Right 48)
17:39:35 <oerjan> i think Arrow was invented before Applicative and had some of the same intended uses, so when the latter got more popular Arrow (which is really complicated in comparison) got much less use except for the (->) specializations
17:39:49 <oerjan> (both can be used for parsers, e.g.)
17:39:50 -!- MoALTz has quit (Quit: Leaving).
17:40:20 <Koen_> do you have an example of when Arrow isn't -> ?
17:41:02 <oerjan> when m is a Monad, Kleisli m is an Arrow
17:42:07 <b_jonas> so these days we just use Applicative instead? that's good, because I know what Applicative does.
17:42:25 <Koen_> well thank you for the lesson :)
17:42:32 <oerjan> > (Kleisli $ \x -> [x]) &&& (Kleisli $ \x -> [x+1]) $ 3
17:42:33 <lambdabot> Couldn't match expected type ‘s0 -> t’
17:42:33 <lambdabot> with actual type ‘Control.Arrow.Kleisli [] c'0 (c'0, c'0)’
17:43:19 <oerjan> b_jonas: there's a sense in which Arrow = Applicative + Category + a law or two
17:44:11 <b_jonas> I don't think I understand that but ok
17:44:26 <oerjan> well first of all every Arrow is a Category
17:44:56 <oerjan> secondly, if a is an Arrow then a b is morally an Applicative
17:45:25 <oerjan> (although haskell's class system doesn't allow this to be expressed as a superclass)
17:45:51 <oerjan> and you can define the functions going back and forth
17:45:58 <Koen_> the limits of hskell
17:46:41 <oerjan> although you need some extra laws to get the full Arrow laws
17:47:37 <oerjan> https://cdsmith.wordpress.com/2011/07/30/arrow-category-applicative-part-i/
17:47:45 -!- MoALTz has joined.
17:48:27 <b_jonas> oerjan: and does it work backwards too? can you take any Applicable m => m and make an Arrow a => a from it such that a b c is similar to b -> m c ?
17:48:47 -!- vanila has quit (Quit: Leaving).
17:48:56 <b_jonas> wait, that's what you said Kleisli does
17:49:06 <oerjan> b_jonas: no Kleisli needs Monad
17:49:33 <TieSoul> I'm trying to figure out how to write a binary counter in Brainfuck with a non-wrapping implementation
17:49:36 <oerjan> you need Category as well, and some compatibility laws
17:50:07 <TieSoul> (it throws an error if you decrement from zero or increment from 255)
17:50:31 <oerjan> TieSoul: well you should be able to do it with just 0,1 values :P
17:50:59 <oerjan> i think you want internal padding
17:51:33 <oerjan> 0 bit0 1 bit1 1 bit2 ... bitn 0
17:52:11 <oerjan> i guess you can do without the padding then, in principle
17:52:27 <oerjan> probably may need a temporary cell somewhere, though
17:52:38 <TieSoul> the thing is, I can't figure out how to check for 1s without decrementing from zero.
17:53:15 <b_jonas> juse use a couple of temp cells
17:53:58 <oerjan> everything's better with temp cells
17:55:22 <TieSoul> ...I don't get how temp cells would help
17:56:07 -!- oren has joined.
17:56:12 <oren> I like dempster-shafer theory
17:56:42 <TieSoul> I want to convert a number under 32 to its binary representation.
17:56:51 <oren> use a lookup table
17:57:31 <TieSoul> it's a code golf thing btw
17:57:45 <oren> ohhhh then don't use a lookup table
17:59:03 <TieSoul> I want to use a binary counter
17:59:18 <TieSoul> but I have trouble figuring out how to do that in a non-wrapping implementation
17:59:31 <TieSoul> (checking for 1s without decrementing from 0)
18:00:39 <oren> check for zero, then decrement, then check for zero again?
18:01:33 <TieSoul> I could... have a 0 cell before/after every 'binary cell'
18:01:39 <TieSoul> and then increment to 2 if it's 0
18:02:14 <oren> yeah, you need a zero cell handy anytime you want to do an if instead of a while
18:04:14 <TieSoul> I think I got confused there
18:04:19 <TieSoul> what I said doesn't make sense
18:04:34 <TieSoul> it's an 'if-nonzero', not 'if-zero'
18:05:35 <oren> that doesn't make much difference except the order of blocks
18:06:12 <Koen_> of, if-zero is ] [ right?
18:06:19 -!- FreeFull has joined.
18:07:00 <oren> Koen: something like >(moving to zerocell) ] [
18:08:12 <oren> sorry no [<]>[ ... ]
18:08:58 <TieSoul> that should be a binary counter?
18:09:40 <TieSoul> and then returning to the original cell... somehow
18:09:44 <oren> if you reset to the first cell before it
18:10:20 <oren> you need some postioning data in a parallel set of cells
18:10:39 -!- MDream has changed nick to MDude.
18:10:45 <TieSoul> I have a group of 'filled' cells to the right
18:10:57 <TieSoul> and a fixed-size binary counter to the left (5 bits)
18:11:11 <TieSoul> so I could just do >>>>>>[<]> to return to the original cell
18:11:36 <TieSoul> assuming there's a 0 cell between them
18:14:06 -!- Frooxius has joined.
18:15:00 -!- Froox has joined.
18:18:23 -!- Frooxius has quit (Ping timeout: 246 seconds).
18:23:04 <oren> What if allocation and garbage collection were hardware features?
18:23:28 <TieSoul> then that'd be some slow hardware
18:24:24 <oren> in particular, what if you had a separate, primitive core that did the gc continuously
18:24:28 <TieSoul> my binary converter seems to work
18:24:51 -!- mitchs has quit (Quit: mitchs).
18:25:42 <oren> did you test it on all 0-32
18:34:58 -!- oren has quit (Ping timeout: 272 seconds).
18:38:02 -!- FreeFull has quit (Ping timeout: 246 seconds).
18:39:27 <oerjan> `! befunge <@_.<0"hello"
18:39:46 <HackEgo> Unsupported instruction '' (0xffffffff) (maybe not Befunge-93?) \ 0
18:40:24 <oerjan> `! funge98 <@_.<0"hello"
18:40:28 <HackEgo> /hackenv/bin/!: 4: exec: ibin/funge98: not found
18:40:37 <oerjan> `! befunge98 <@_.<0"hello"
18:53:16 -!- mitchs has joined.
18:56:44 -!- oren has joined.
19:04:45 -!- Lymia has quit (Ping timeout: 265 seconds).
19:08:12 -!- Lymia has joined.
19:20:42 -!- adu has joined.
19:20:42 -!- adu has quit (Client Quit).
19:21:07 -!- oren has quit (Ping timeout: 245 seconds).
19:21:19 -!- vanila has joined.
19:36:02 -!- mihow has quit (Quit: mihow).
19:48:47 -!- mihow has joined.
20:10:05 <TieSoul> https://www.hackerrank.com/challenges/baconian-cipher
20:10:16 <TieSoul> I just made a 209-character solution
20:10:29 <TieSoul> I'm pretty proud of myself :P
20:10:36 -!- oren has joined.
20:10:45 <TieSoul> especially since I've never seriously done anything in brainfuck before
20:12:13 <oren> I have tried to write programs that /write/ BF prgorams, but i have not tried to write bf prgrams.
20:12:50 <TieSoul> https://www.hackerrank.com/challenges/baconian-cipher I just did this challenge
20:13:00 <TieSoul> my solution is 209 characters
20:13:05 <TieSoul> could probably shorten it a bit
20:13:46 <J_Arcane> Huh. If I'm reading that correctly, isn't that just 5-bit text encoding?
20:14:19 -!- mihow has quit (Quit: mihow).
20:14:21 <TieSoul> that's what I needed the binary conversion for
20:14:33 <vanila> i couldnt write this in BF at all, let alone 200 chars
20:14:41 <TieSoul> hackerrank's implementation has no wrapping
20:14:46 <TieSoul> so that makes the challenge harder
20:14:52 <J_Arcane> I couldn't write jack squat in BF.
20:15:05 <TieSoul> https://gist.githubusercontent.com/TieSoul/17f9670ed239ad94f2be/raw/1d3ea0c59b409b76a70f3ba8140f9e26619c0298/bacon.b
20:15:20 <J_Arcane> But I might have a stab at it in F# just for fun. Give me an excuse to try out fsharp-mode in emacs now that I've got the intellisense working.
20:15:45 <TieSoul> I could probably do a Ruby/Python one liner
20:15:59 <oren> you use an advanced editor, J_arcane.
20:16:33 <oren> I only have synatax highlighting
20:16:45 <oren> because I use mcedit
20:17:26 <oren> so emacs is very advanced compared to what i use, no saracsm
20:17:28 <J_Arcane> What I use really depends on the language.
20:17:51 <TieSoul> > people with scores of 98.46
20:17:53 <lambdabot> <hint>:1:20: parse error on input ‘of’
20:29:18 -!- TieSoul has changed nick to TieSleep.
20:33:44 -!- CADD has joined.
20:38:38 <oren> a language in which it is impossible to write an interpreter for a language unless that language is TC
20:39:22 <coppro> oren: that's impossible
20:39:55 <coppro> actually... hmm, no, it's not *obviously* impossible.
20:40:03 <coppro> if you maintain a source/input distinction
20:40:18 <coppro> but I would be very surprised if you could do that
20:40:34 -!- oerjan has quit (Quit: ZZZZ).
20:42:40 -!- arjanb has joined.
20:43:03 <oren> wait. trivially, a restricted compiler for any language, which only accepts the source code of a BF interpreter
20:43:17 <Gregor> It depends on whether that is your only restriction.
20:43:29 <Gregor> If it is only impossible to write ONE interpreter for ONE language, that's easy :)
20:43:56 <Gregor> But a language which will accept ANY interpreter for ANY TC language, but will reject any other program is a halting problem solver.
20:45:29 <pikhq> Yep, you either managed to make it trivial and uninteresting *or* impossible.
20:45:32 <oren> it might be even worse than that actually. it basically has to tell whether the halting problem is unsolvable on the langugae defined by its input program.
20:46:43 <oren> wait. DOES the haltingproblem thing go both ways?
20:46:53 -!- Patashu has joined.
20:47:15 <oren> are there languages where the halting problem is unsolvable, but the language is not TC?
20:47:49 <vanila> there are undecidable problems in context-free grammars
20:51:45 <oren> http://www.pentacom.jp/pentacom/bitfontmaker2/
20:51:56 <oren> this site is awesome
21:07:07 <FireFly> Hm, I just use a generic bitmap editor
21:08:35 <oren> I was doeing it with mtpaint
21:08:54 <oren> but this thing is way easier if a little limited
21:09:41 <J_Arcane> Wee! I have my char lookup table now.
21:14:00 <oren> So i made an utterly insane font, which I posted a screenshot of earlier
21:15:30 <b_jonas> oren: where's the screenshot?
21:15:42 <oren> http://snag.gy/GZVB3.jpg
21:15:47 <oren> heres a new screen
21:16:19 <FireFly> That's really hard to read
21:16:31 <b_jonas> no, it's not very hard to read actually
21:16:38 <oren> it uses underdot instead of capitals
21:16:48 <b_jonas> but the v looks ugly to me
21:16:49 <FireFly> Well, apart from t and h I guess it's fairly readable
21:17:09 <oren> what bout the f
21:17:16 <FireFly> My brain really doesn't like the way "that" looks
21:17:25 <b_jonas> oren: nice, thank you for sharing
21:18:07 <FireFly> the f isn't too bad for me from a readability perspective
21:19:20 <FireFly> I made this bitmap font a while ago: http://xen.firefly.nu/up/pixfont/index.html
21:19:31 <b_jonas> oren: what does the "z" look like? "z" is ugly in many fonts but you don't find that out from screenshots like this
21:19:34 <FireFly> Though I didn't try it out properly until yesterday
21:20:40 <oren> `1234567890-=qwertyuiop[]\asdfghjkl;'zxcvbnm,./~!@#$%^&*()_+QWERTYUIOP{}|ASDFGHJKL:"ZXCVBNM<>?
21:20:41 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/1234567890-=qwertyuiop[]\asdfghjkl;'zxcvbnm,./~!@#$%^&*()_+QWERTYUIOP{}|ASDFGHJKL:"ZXCVBNM<>?: No such file or directory
21:21:10 <FireFly> ...that's one way to do it
21:21:53 <oren> http://snag.gy/0dBxW.jpg
21:22:29 <b_jonas> wow, that dollar sign is ugly
21:23:11 -!- mihow has joined.
21:24:54 -!- ais523 has joined.
21:24:54 <oren> here is the font file for pasting into the editor https://gist.github.com/orenwatson/55b014da50347d032b1f
21:26:24 <FireFly> Hmm, I should try to convert my bitmap font to a proper font file
21:26:48 <oren> once again the numbers are the way I write them...
21:26:49 -!- augur has quit (Ping timeout: 252 seconds).
21:27:16 <oren> well, except I usually put a dot in my zeros
21:29:23 <oren> firefly: thta font is nice and small
21:30:06 <oren> I like small fonts when I'm programming
21:31:03 <FireFly> I actually prefer larger fonts personally, but I wanted to make a small but legible bitmap font for platforms where screen space is more limited
21:31:14 <b_jonas> oren: wait, I have an old crazy font I'd like to show to you
21:32:36 <oren> In particular, I like fonts that conserve vertical space
21:32:58 <FireFly> As for smallness, I have this thing I made a long time ago: http://xen.firefly.nu/up/pixel-font.png
21:33:11 <FireFly> Though it uses manual anti-aliasing so it kinda doesn't count
21:33:43 <FireFly> It's surprisingly legible for being 3x5px glyphs, to me anyway
21:34:02 <oren> that's pretty damn good
21:35:49 -!- hassa-aravit has joined.
21:37:20 <FireFly> The S looks pretty ugly, hmm
21:38:12 <fizzie> I've made a 3x5 (well, 4x6 cell) font too, for rfk86.
21:39:35 <fizzie> https://zem.fi/rfk86/ should render using it, if things work out right.
21:42:27 <fizzie> I like the lowercase s/z trick it uses, which I think I adapted (or even just copied) from mooz's TI-86 befunge interpreter.
21:45:31 -!- idris-bot has quit (Quit: Terminated).
21:45:52 -!- Melvar has quit (Quit: rebooting).
21:47:39 -!- augur has joined.
21:48:46 <FireFly> Hmm, it shouldn't be too hard to tweak my JS thing to generate a BDF font file
21:50:11 -!- Melvar has joined.
21:51:48 -!- Lymia has quit (Ping timeout: 256 seconds).
21:54:13 <b_jonas> oren: http://www.math.bme.hu/~ambrus/pu/stickfont-screenshot0.png
21:54:36 <b_jonas> it's a 16x9 font because I originally used it for VGA console
21:54:49 -!- idris-bot has joined.
21:54:53 <b_jonas> not for serious purposes though, it was always intended as a silly font
21:55:08 -!- ais523 has quit.
21:55:23 -!- ais523 has joined.
21:55:35 <J_Arcane> Part 1: http://rextester.com/UUWO55700
21:56:18 <b_jonas> I didn't draw more characters than what you can see there though
21:57:11 -!- AnotherTest has quit (Remote host closed the connection).
21:57:32 <b_jonas> FireFly: that small font looks nice
21:57:48 <b_jonas> though I'm not sure I like the "S"
21:58:05 <oren> it is a little too light isnt it?
21:58:08 <b_jonas> nor the way the N and H look very similar
21:58:32 <b_jonas> the "S" is too closed, that is, the top and bottom curve too much down
21:58:55 <b_jonas> the N and H might be a bigger problem though
21:59:47 -!- callforjudgement has joined.
21:59:51 -!- ais523 has quit (Read error: Connection reset by peer).
22:00:05 -!- callforjudgement has changed nick to ais523.
22:01:25 <FireFly> b_jonas: the 3×5 one, or the bigger one?
22:01:51 <b_jonas> By the way, I like the “Munka és béke” poem (displayed in that screenshot) partly because it has almost every letter, and has most letters in both the first four lines and the last four lines, which is quite remarkable for such a short poem.
22:01:59 -!- tromp_ has quit (Ping timeout: 244 seconds).
22:02:07 <b_jonas> So it's not really a pangram, but close.
22:02:11 <b_jonas> Useful for demonstrations like this.
22:02:57 <FireFly> Poems for demoing charsets reminds me of Iroha
22:03:16 <b_jonas> FireFly: is that the Japanese one that helps demo kana?
22:03:32 <FireFly> It uses every syllable exactly once
22:04:00 <oren> it now contains ones that don't exist in modern japanese like wi
22:04:21 <oren> (well, wi does occur in names, like arawi keiichi)
22:05:00 <ais523> hmm, I wonder if using every syllable exactly once is possible in English
22:05:01 -!- Lymia has joined.
22:05:04 <ais523> it seems like it might be
22:05:37 <b_jonas> ais523: there are too many syllables so you'd need a longer text, which is hard without reusing “the” more than twice
22:06:05 <ais523> yep, you'd have to avoid common words
22:06:14 <ais523> but long English prose that avoids common words has been done before
22:06:14 <FireFly> Well, if you can write a book without using the letter 'e'...
22:06:21 <ais523> FireFly: the great thing about that book
22:06:28 <ais523> is that it's a translation of a French book that also doesn't use the letter 'e'
22:06:41 <ais523> ('e' is the most common letter in French too, IIRC)
22:06:43 -!- FreeFull has joined.
22:06:50 <oren> http://snag.gy/tRIpP.jpg
22:06:56 <FireFly> that's what I usually say when that book is bought up--the translator's job is more impressive than originally writing it
22:07:04 <oren> my font works well at small sizes too
22:07:18 <FireFly> (not to say that authoring it isn't also impressive)
22:08:12 <oren> without 'e' in FRENCH?? very impressive,
22:08:47 <b_jonas> The fun part of Munka és béke is that it has two variants. The other variant has an “ű” but doesn't have “ő” in exchange
22:08:58 <b_jonas> no wait, that can't be true
22:09:07 <b_jonas> there are two “ő” so one must remain
22:09:20 <b_jonas> it doesn't have some other letter
22:11:01 <Taneb> I have written a quine in Haskell
22:11:33 <b_jonas> hmm, maybe it has “ű” but doesn't lose anything in exchange?
22:11:45 <b_jonas> but I seem to remember it wasn't more close to a pangram than this version
22:12:03 <b_jonas> whatever, I'm too tired to figure it out now
22:12:17 <oren> maybe there are 3 versions?
22:12:29 <zzo38> Does not 'e' in French also mean doesn't have any 'e' with accent mark too, or not?
22:13:05 <b_jonas> oren: could be, but I only know of two
22:16:18 <zzo38> Do you know of any Z-machine implementation that actually supports small-endian other than ZORKMID?
22:16:29 <zzo38> (ZORKMID does support big-endian too)
22:16:51 <b_jonas> isn't it called "little-endian"?
22:17:54 <zzo38> I don't know, I called it "small-endian"; Infocom called them "byte-swapped" story files (and as far as I know, never created any such story files nor ever implemented an interpreter that would support them).
22:19:41 -!- gamemanj has joined.
22:24:52 -!- augur has quit (Remote host closed the connection).
22:31:29 -!- aloril has quit (Remote host closed the connection).
22:32:22 -!- gamemanj has quit (Ping timeout: 246 seconds).
22:38:46 <Koen_> ais523: e is far more common in french than in english, i reckon
22:39:08 <ais523> Koen_: does that include é and ê and è or not?
22:40:10 <Koen_> not sure they make a relevant difference though
22:40:59 <Koen_> but that's also just based on my impressions as a native french speaker
22:41:04 -!- aloril has joined.
22:41:28 <Koen_> i think it's easier to write in alexandrines than without the letter e
22:41:46 -!- `^_^v has quit (Ping timeout: 244 seconds).
22:43:03 -!- gde33|2 has quit (Read error: Connection reset by peer).
22:45:11 -!- tromp has joined.
22:57:14 <FireFly> Hmm, I don't think it's possible to do an 8×5 monochrome '½' that doesn't look like crap...
22:57:38 <Koen_> the bar is too long imho
22:59:04 <FireFly> http://xen.firefly.nu/up/2015-02-27_235830.png here's my best attempt at ¼ ½ ¾
22:59:55 <FireFly> Oh, I meant 8-high and 5-wide
23:01:42 <Koen_> "just tilt your head right"
23:02:07 <Koen_> are you designing a game boy?
23:02:32 <ais523> the trick's to leave out the slash
23:03:04 <ais523> I'm juts being creative
23:03:15 <elliott> here's my glyph: [0.5 just mashed into the available space]
23:04:07 <int-e> 1/2 works, but the rest is hard :)
23:04:18 <Koen_> ais523's try was friendlier to proportionate fonts irc clients
23:04:35 <ais523> Koen_: I use a proportional font in my client
23:04:35 <FireFly> I found the 2 to be hardest actually
23:04:57 <ais523> actually, this reminds me of a table I saw on a proportional-font-using forum
23:05:07 <ais523> that used ' and ` as spacers in order to make all the columns line up
23:05:08 <fizzie> The "leave something out" trick is a good one, it's the basis for the rfk86 s/z too.
23:05:11 <ais523> despite the proportional font
23:05:31 <ais523> fizzie: that reminds me of the trick I used when trying to fit the whole alphabet on a 7-segment display
23:05:44 <ais523> (M was the top segment, middle segment, and the two lower sides)
23:05:52 <FireFly> Koen_: the font? I had the TI-84 in mind at first, now I'm just adding some more glyphs because I was happy with how it turned out
23:06:52 <vanila> can we generate a new font
23:06:54 * Koen_ had a ti-84 but it was stolen during mardi gras in prepschool
23:07:01 <ais523> I remember that Windows 3.1 shipped with a set of raster fonts of very small sizes
23:07:35 -!- Fleur has joined.
23:09:38 <fizzie> I had a script somewhere for IRCing with the rfk86 font, based on the 2x2 Unicode quarter-block things.
23:10:31 <fizzie> There's the full set of them, so 3 lines is enough for a font 6 pixels high.
23:11:01 <int-e> FireFly: http://int-e.eu/~bf3/tmp/6x13frac.png .. the fixed font here also leaves out the / (or bar)
23:11:03 <FireFly> You can do better if you abuse the Braille Unicode block
23:11:15 <fizzie> I'm typing with a speech recognizer again
23:11:25 <int-e> FireFly: but of course those extra vertical pixels help a lot
23:11:26 <FireFly> That gives you 8×2 "pixels" per character
23:11:41 <HackEgo> Fleur: 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.)
23:11:43 <nortti> int-e: that link gives not found error for me
23:11:46 <elliott> happy birthday 30 pussy Busy Busy fizzy
23:11:55 <fizzie> Elliot how did you get the backtick
23:12:05 <int-e> nortti: right, forgot to press enter for the scp command. should be ok now.
23:12:06 <vanila> Hey i have an idea lets make an esoteric font
23:12:32 <fizzie> I think they have improved the voice typing
23:12:41 * FireFly ponders whether to remove the fractional slash or keep his current glyphs
23:12:44 <zzo38> vanila: OK, what are you going to put on it, and is it METAFONT or PC 8x8 bitmap font or whatever?
23:12:49 <fizzie> Although this is far less hilarious than last time
23:12:52 <FireFly> I could do alternate characters
23:13:10 <elliott> Fleur: came here from the wiki?
23:13:19 <int-e> FireFly: I believe you'll find that it's 4x2 pixels
23:13:20 <vanila> zzo38, I thought it could be generated randomly, by trying to find a set of images which look very different (by some metric)
23:13:21 <fizzie> Maybe this phone just has a better microphone
23:13:27 <FireFly> int-e: oh. yes, I meant that
23:13:38 -!- boily has joined.
23:14:07 <Fleur> elliott: Sort of - I've always loved browsing the wiki for pleasure, and then nortti told me there was an IRC channel so I thought I'd join
23:14:48 <elliott> well, there are significantly fwer brainfuck derivatives here
23:14:57 <elliott> also significantly fewer esolangs in general though really...
23:15:05 <vanila> Fleur, did you invent any esolangs or have some favorites
23:15:58 <Fleur> vanila: I don't really have any particular favourites, I just keep clicking the random page button until something catches my eye :P
23:16:25 <Fleur> But I have attempted in the past to create my own (but nothing has particularly taken off further than ideas in my mind)
23:19:45 <boily> Flellour! first time on the channel?
23:19:54 <Koen_> elliott: am I allowed to delete the pages of brainfuck derivatives I made or would that be vandalism?
23:20:15 <ais523> Koen_: if they suck, I personally wouldn't mind
23:20:22 <ais523> however, you don't have the permissions to delete pages
23:20:37 <ais523> put {{delete}} on them, if there's been no significant activity from others on them
23:20:40 <ais523> I'll delete them for yo
23:21:45 <vanila> Koen_, how many are we talking
23:27:04 -!- Fleur has quit (Remote host closed the connection).
23:31:27 <boily> she left. we had a talkative newcomer...
23:36:39 -!- mihow has quit (Quit: mihow).
00:02:31 -!- chaosagent has joined.
00:03:09 <quintopia> dammit. how am i going to overwrite my OS with this one if ubi-partman always crashes :(
00:05:19 -!- callforjudgement has joined.
00:05:32 -!- ais523 has quit (Disconnected by services).
00:05:34 -!- callforjudgement has changed nick to ais523.
00:10:14 -!- vanila has quit (Quit: Leaving).
00:14:28 <boily> what's an ubi-partman?
00:15:15 <quintopia> now i'm having trouble even getting the graphics to boot
00:15:18 <ais523> thought experiment: someone new joins the channel, claiming to be really interested in an obscure bad esolang
00:15:30 <ais523> how bad does it have to be before you assume they are / they are in league with its creator?
00:15:44 <boily> quintopia: don't worry. partitioning is either the simplest thing, or the hardest thing.
00:16:08 <quintopia> partitioning will be easy if i can even GET to that point
00:16:20 <boily> (one of my friends has a desktop. I don't want to touch that desktop anymore. the boot process on that thing greatly surpasses my necromancy skills.)
00:16:22 <quintopia> since i'm just going to wipe every thing and start over
00:16:49 <quintopia> right now all i'm getting is a screen that keeps flashing
00:16:56 <FireFly> ais523: I think that might describe my first visit to the channel
00:16:59 <boily> quintopia: if you haven't done it yet, burn an image of grml on a disc or stick, and boot that. this distro is magic.
00:17:05 <ais523> FireFly: which language was it?
00:17:18 <boily> quintopia: it should most verily probably solve almost all your problems.
00:17:25 <boily> (almost used in the mathematical sense.)
00:18:02 <quintopia> that implies that the number of possible problems is infinite
00:18:02 <boily> quintopia: it has heavy hardware autodetection, with manual options in case your machine is rebarbative and resists your dominance.
00:18:13 <quintopia> i think the number of possible problems is really a large finite number
00:18:18 <boily> I never said that the set of possible problems is finite.
00:18:31 <boily> large finite numbers are good approximations of infinity.
00:18:34 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:18:56 <quintopia> every finite number i know is much less than infinity
00:19:56 <boily> large numbers either hit NaN or Infty. therefore, they are good approximations.
00:20:24 <boily> but apart from that, you really should get a copy of grml.
00:20:45 * boily doesn't have any sentimental attachment towards grml, I swear.
00:21:28 <quintopia> i have a sentimental attachment to the obsolete system i am replacing
00:22:34 <Koen_> quintopia: sequences of large finite numbers are a good approximation of infinity
00:22:38 -!- ais523 has quit (Read error: Connection reset by peer).
00:22:53 -!- ais523 has joined.
00:23:23 <quintopia> Koen_: only infinite sequences! but that's beggaring the question!
00:25:15 <Koen_> quintopia: are you trying to tell ihatehex he's a value virgin?
00:26:03 <quintopia> mostly i'm just complaining about people hinting at problems they are trying to solve without actually saying what problem it is
00:29:52 <quintopia> i feel like i've broken this usb drive by trying to boot from it >.>
00:30:57 <oren> that can happen
00:33:21 <quintopia> it worked once, but now it only ever goes into an infinite loop of turning the display off and on (sleep/wake). i will deal with this another day.
00:57:44 -!- hjulle has quit (Ping timeout: 245 seconds).
01:01:28 -!- 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?").
01:03:27 -!- Patashu_ has joined.
01:03:36 -!- Patashu has quit (Disconnected by services).
01:25:36 <ais523> irrelevant URL for the content, but for anyone interested in esoprogramming in Magic: the Gathering, this page trying to find the largest non-infinite combo in Magic is pretty amusing: http://www.rpgdl.com/metroidcomposite/phpconversion.php
01:36:57 -!- ais523 has quit (Read error: Connection reset by peer).
01:36:58 -!- callforjudgement has joined.
01:37:26 -!- callforjudgement has changed nick to ais523.
01:57:24 -!- koo7 has quit (Quit: Leaving).
01:59:11 -!- koo7 has joined.
02:16:56 -!- callforjudgement has joined.
02:16:57 -!- ais523 has quit (Read error: Connection reset by peer).
02:22:26 -!- scarf has joined.
02:24:25 -!- callforjudgement has quit (Ping timeout: 264 seconds).
02:24:40 -!- scarf has changed nick to ais523.
02:57:44 <oren> this just in-- woman asks what color dress is, internet goes down in flaming ruins
02:58:47 <ais523> I assume this is some sort of huge meme
02:58:57 <ais523> because I've seen it be brought up unprompted in like 4 different places
03:00:23 <oren> basically people can't all agree on whether the dress is white and gold (me) or blue and black
03:00:51 <ais523> based on what? seeing it in person? photos?
03:01:02 <ais523> with photos it could literally be white and gold in one, and blue and black in another, depending on lighting
03:01:12 <oren> http://swiked.tumblr.com/post/112073818575/guys-please-help-me-is-this-dress-white-and
03:01:20 <oren> this photo specifically
03:02:19 <ais523> oh, that depends a lot on gamma
03:02:33 <ais523> if you're viewing it on a laptop screen, try changing your viewing angle
03:02:38 <oren> https://twitter.com/emmyrossum/status/571128558325608448
03:02:55 <ais523> it's black and blue when viewed from below, white and gold when viewed from above
03:03:14 <ais523> so different people could genuinely be seeing different colours
03:03:28 <oren> HOLY SHIT how did that happen
03:04:06 <ais523> so I guess what's happened is that the Internet hasn't discovered the existence of gamma yet
03:04:14 <ais523> (also, fwiw, I see it as blue and gold in an in-between gamma)
03:08:40 <oren> so if the screen angle is causing it, maybe different people naturally hold their tablets at different angles
03:09:18 <Jafet> Tablets that use IPS shouldn't be affected by viewing angle
03:09:23 <ais523> inconsistent gamma based on viewing angle is one of the major disadvantages of LCDs
03:13:00 <int-e> I'm so tempted to make a screenshot to prove that it's blue and black :P
03:15:06 <ais523> we could use the xkcd colour classification chart, perhaps?
03:15:14 <ais523> although I'm not sure the whole three-color-dimensional thing is public
03:17:50 <int-e> there are lengthy (though not very substantial) articles about this... http://motherboard.vice.com/en_ca/read/there-is-the-dress-and-only-the-dress
03:20:09 <quintopia> i cant see white and gold at any angle
03:23:13 <ais523> anyway, one way to think about it
03:23:17 <int-e> I'd like to know whether this was accidential (an actual photograph that was hopelessly overexposed) or deliberate.
03:23:20 <ais523> is that white and blue are adjacent colors (in between, you just have light blues)
03:23:25 <ais523> and likewise, black and gold are adjacent
03:23:36 <ais523> so there have to be some colors that land right on the boundary
03:29:32 <oren> Haha! I jury rigged an LCD monitor SIDEWAYS and it doesn't have the problem. (instead the colrs shift with left-right viewing angle)
03:31:55 <ais523> I'm not sure that counts :-)
03:32:08 <int-e> oren: that sounds awful
03:33:04 <oren> I taped the mount on the bottom to the wall with a lot of duck tape
03:36:14 <oren> I think I might keep it like this
03:36:57 -!- arjanb has quit (Quit: .).
03:41:46 <oren> http://ctrlv.in/509633
03:45:30 <oren> actually nahhh it does'nt work with fullscreen
03:47:10 <oren> Hmmm, what If I took two and taped them side-by side
03:48:22 <oren> if each one is 16:9 then the result would be 18:16
03:50:10 <oren> but I would need to knock together a wooden frame to hold them, too much work
03:52:20 <Jafet> Multiple screens h ave other problems.
04:02:59 <oren> hmm, I can also tape the monitor over my head
04:03:29 <oren> yeah, that workd
04:04:08 -!- boily has quit (Quit: TAPERED CHICKEN).
04:06:41 <oren> ideally it would be even more overhead, but I think i would need to find a stud to nail the monitor up
04:07:22 <oren> http://ctrlv.in/509648
04:08:03 -!- MDude has changed nick to MDream.
04:10:28 <oren> hold on, maybe I can suppor the monitor overhead with a wooden frame
04:12:15 <quintopia> why the heck do you want it overhead?
04:12:56 <oren> So I can be even more lazy and not even lift my head to loom at my screen
04:13:06 <HackEgo> [wiki] [[Deviating Percolator]] http://esolangs.org/w/index.php?diff=42064&oldid=42000 * AJF * (+56) /* Expressions */ Munroe algorithm
04:18:56 <FireFly> So I turned my font into a proper one; here's what IRC looks like: http://xen.firefly.nu/up/2015-02-28_051818.png
04:21:16 <zzo38> The font is not bad
04:21:50 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:34:13 -!- PinealGlandOptic has joined.
04:34:31 <zzo38> When trying to send something to sprunge now I get a HTML document back instead of the proper response; the HTML document says "503 Over Quota" on it.
04:35:25 <ais523> zzo38: presumably you've uploaded too much to sprunge, and it isn't accepting any more right now
04:35:38 <ais523> although that should be a 4xx rather than 5xx code
04:35:53 <ais523> whatever the user error code is
04:37:06 <zzo38> When am I supposed to try again?
04:37:37 <zzo38> It says "Please try again later." but I don't know what time
04:39:00 <zzo38> Even such a simple HTML document is full of worthless junk
04:40:03 -!- chaosagent has quit (Remote host closed the connection).
04:40:22 -!- chaosagent has joined.
04:57:52 <Jafet> It's called markup because it's so expensive to parse
04:59:09 <MDream> "Please try again harder."
05:00:12 -!- Lymia has quit (Ping timeout: 256 seconds).
05:11:48 -!- ProofTechnique has joined.
05:24:22 <zzo38> Is there any Magic: the Puzzling that involves conceding and/or subgames?
05:25:16 <ais523> I doubt it; conceding doesn't fit into the normal 1v1 setups, and in order to work out what would happen in a subgame, you'd need to know what's in the opponent's deck
05:26:16 <zzo38> Yes, although some puzzles tell you what's in the opponent's deck; there are also things you can use to affect the opponent's library before the subgame starts.
05:26:56 <zzo38> The possibility to concede also might be important if there are subgames
05:27:22 <zzo38> Or if you are making a puzzle involving Team vs Team instead of 1v1
05:31:56 <zzo38> Maybe it is even necessary to concede a subgame you have started, and to somehow stop your opponent from conceding before you have completed what you need to do, perhaps by making opponent have only 1 life point in the main game, and then if Shahrazad is used they will lose half, rounded up
05:38:36 <oren> Shahrazad? How many other cards refer to reality like that?
05:39:03 <oren> Well, real literature anyway
05:39:54 <zzo38> Some very old flavor texts do refer to real literature
05:40:43 <oren> Holy shit therea re cards alled "jihad" and "army of allah" how did they get away with that?!?!?
05:41:00 <zzo38> Yes, those are very old
05:41:10 <zzo38> Also there is a card "Aladdin"
05:41:41 <ais523> I think the origin arabian nights stories are out of copyright by now
05:42:10 <zzo38> But even outside of the Arabian Nights set, some old cards referenced older literature including Shakespeare and the Bible and a few others
05:44:38 <oren> oh, they got away with it because they came out the year I was born... the whole war hadn't started yet
05:46:05 <oren> I like how "king suleiman" is a card.
05:46:32 <oren> since he was a completely real person, but from CENTURIES later
05:49:34 <oren> He appears as a enemy ai character in aOE3
05:50:36 -!- Froox has quit (Quit: *bubbles away*).
05:53:06 <oren> Interesting to scroll chronologically through the versions of a card. Like apparently before I was playing, there was a period where "destroy, it can't be regenerated" was shortened to "bury"
05:54:26 <oren> But before that, it was originally "destroy, it can't regenerate"
05:55:15 <zzo38> The original "Flight" said "Target creature is now a flying creature."
05:55:42 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
05:57:39 <zzo38> The original text of "Black Lotus" didn't list an activation cost; it said "Adds 3 mana of any single color of your choice to your mana pool, then is discarded. Tapping this artifact can be played as an interrupt."
05:57:59 <ais523> zzo38: that's because it had "mono artifact" on its type line
05:58:15 <ais523> which means that anything that looks like a tap ability in its text box is a tap ability
05:58:39 <zzo38> Yes, I know, "mono artifact" means it can be activated by tapping in additional to any other activation costs if any.
05:59:06 <zzo38> And then there is also "poly artifct" which is similar but doesn't require tapping; however I think it still can't be used if it is already tapped
06:00:32 <zzo38> However, there is another thing too: Before the Alpha cards were even released, they originally had the activation costs printed next to the mana cost, and there was no "mono artifact" and "poly artifact" either; any card that did not require tapping to activate explicitly said so.
06:01:06 <zzo38> Another thing about the pre-Alpha cards is that the Plains had pictures of airplanes on them.
06:01:23 <zzo38> Did you know any of these things before?
06:05:44 <oren> no... how the hell does "Copper Tablet"'s effect make any sense?
06:06:56 <oren> actually better question: why does it say "does X damage" instead of "deals X damage" on old cards?
06:08:09 <oren> "does damage" sounds childish to me somehow
06:13:52 <oren> Ok weirdest thing: one particular version of the card "wrath of god", instead of saying "destroy all creatures, they can't be regenerated", instead says ""
06:13:55 <oren> Put all creatures into their owners' discard piles. (This includes your creatures.)
06:15:10 <oren> I don't even know if that's equivalent
06:16:49 <oren> well, assuming that regeneration refers to "destroying" a creature, then it might be
06:18:28 -!- password2 has joined.
06:18:47 -!- password2 has quit (Max SendQ exceeded).
06:19:23 -!- password2 has joined.
06:19:50 -!- password2 has quit (Max SendQ exceeded).
06:20:31 -!- password2 has joined.
06:23:21 <ais523> hmm, repeated joining + Max SendQ exceeded is rarely a good sign
06:29:02 -!- password2 has quit (Read error: Connection reset by peer).
06:38:21 -!- Lymia has joined.
06:45:28 -!- password2 has joined.
06:46:30 -!- password2 has quit (Read error: Connection reset by peer).
06:57:07 -!- Frooxius has joined.
07:02:06 -!- password2 has joined.
07:11:08 -!- password2 has quit (Ping timeout: 245 seconds).
07:33:54 -!- ais523 has quit (Read error: Connection reset by peer).
07:34:10 -!- ais523 has joined.
07:38:10 -!- ais523 has quit (Read error: Connection reset by peer).
07:38:25 -!- ais523 has joined.
08:23:05 -!- oerjan has joined.
08:29:02 -!- chaosagent has quit (Ping timeout: 245 seconds).
09:10:05 -!- bb010g has quit (Quit: Connection closed for inactivity).
09:29:03 -!- atehwa has quit (Remote host closed the connection).
09:29:03 -!- villasukka has quit (Remote host closed the connection).
09:36:56 -!- ais523 has quit.
09:55:38 -!- TieSleep has changed nick to TieSoul.
10:19:58 -!- AnotherTest has joined.
10:27:28 -!- Zuu has joined.
10:39:24 -!- Fleur has joined.
11:00:05 -!- AnotherTest has quit (Ping timeout: 246 seconds).
11:08:05 -!- oerjan has quit (Quit: leaving).
11:20:00 -!- Koen_ has joined.
11:26:07 -!- Patashu_ has quit (Ping timeout: 252 seconds).
11:26:26 -!- arjanb has joined.
11:28:33 -!- Zuu has quit (Remote host closed the connection).
11:28:48 -!- Zuu has joined.
12:12:33 -!- FreeFull has quit (Ping timeout: 264 seconds).
12:13:38 -!- Tritonio has joined.
12:33:00 -!- Tritonio has quit (Ping timeout: 252 seconds).
12:59:01 -!- vanila has joined.
13:15:30 -!- ProofTechnique has joined.
13:16:53 <vanila> https://t.co/etIIQZzvFQ
13:16:56 -!- SopaXorzTaker has joined.
13:17:00 <vanila> https://www.youtube.com/watch?v=unCQHAbGsAA
13:17:09 <vanila> what's it like to write a nethack bot
13:20:18 <vanila> im curious how the sokoban bits are done...
13:20:26 <vanila> those are very hard to solve with a program
13:22:00 <int-e> you can always hardcode some bits
13:23:25 <vanila> yeah i guess the sokobans are hard coded, so the solver doesn't need to be general
13:24:10 <int-e> generating sokoban puzzles is even harder (except for very small sizes, but then solving is still easy...)
13:25:30 <int-e> (There are some collections of automatically generated puzzles, based on the principle that one looks for long shortest solutions. They're somewhat interesting for humans to solve because the taxicab metric is generally useless for them.)
13:26:16 <int-e> Not sure if there are more interesting puzzles, I'm not really up-to-date on this topic; perhaps ais523 knows more.
13:26:33 <int-e> ... more interesting puzzle generators, that is.
13:34:45 -!- boily has joined.
13:38:13 -!- MoALTz_ has joined.
13:41:47 -!- MoALTz has quit (Ping timeout: 252 seconds).
13:45:41 -!- AnotherTest has joined.
13:49:28 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
14:06:46 <Jafet> It's PSPACE-complete, so puzzles can contain an unlimited variety of interesting devices that are difficult to invent automatically.
14:14:11 -!- FreeFull has joined.
14:31:47 -!- Koen__ has joined.
14:33:59 -!- Koen_ has quit (Ping timeout: 246 seconds).
14:40:14 -!- GeekDude has joined.
14:41:57 -!- gde33 has joined.
14:53:36 <Jafet> Also beating nethack with a pudding farming dvalk... not exactly impressive
15:04:14 -!- villasukka has joined.
15:16:06 <boily> `relcome villasukka
15:16:07 <HackEgo> villasukka: 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.)
15:21:34 -!- AnotherTest has quit (Ping timeout: 264 seconds).
15:24:39 -!- ProofTechnique has joined.
15:36:34 -!- MDream has changed nick to MDude.
15:37:04 <vanila> hows it going? any news
16:00:12 -!- Fleur has quit (Remote host closed the connection).
16:07:04 -!- ^v has joined.
16:09:07 <vanila> https://www.youtube.com/watch?v=vEVq295zKps
16:10:39 <MDude> Well I still ought to make a compiler.
16:10:55 <MDude> Yestersay I tried to figure out some stuff about how IBNIZ works.
16:11:55 <MDude> For an esoteric language I want to make.
16:12:04 <vanila> i like learning about compilers
16:14:22 <vanila> i want to make something
16:14:30 <MDude> I plan to have it compile to IBNIZ code, actually, which is one reason I was trying to start using IBNIZ's memory system.
16:14:44 <MDude> As oppossed to just using stack commands.
16:18:10 -!- Lymia has quit (Ping timeout: 250 seconds).
16:20:54 <MDude> OK, this is annyoing.
16:21:13 <MDude> I try something out and it seems to work differently than when i tired the exact same thing last night.
16:21:23 -!- nortti has changed nick to lawspeaker.
16:21:30 -!- lawspeaker has changed nick to nortti.
16:22:25 -!- Lymia has joined.
16:23:32 <MDude> What I'm trying to do is take the time value, and store that in the memory cell equal to itself modulo the number of display pixels.
16:24:41 <MDude> Then take the X and Y values and turn them into a single number, each cooresponding to one of the same numbers.
16:25:12 -!- Tritonio has joined.
16:25:28 <MDude> With the desired result being that the screen just gets slowly scanned over and filled.
16:37:37 -!- aretecode has quit (Quit: Toodaloo).
16:49:52 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
16:56:30 <HackEgo> 1206) <ais523> wait, is Pluso basically a more limited version of Deadfish? <ais523> Deadfish minimization is not an area of esolang development I had really considered
17:02:00 <HackEgo> 1124) <Taneb> kmc, I was trying to go to a sci-fi and fantasy society social, and I went to the wrong bar <Taneb> Wound up at my university's fetish society <Taneb> Didn't realise for an hour and a half
17:02:18 <boily> ah! my favourite Tanebquote :)
17:02:29 <Taneb> Yes, it was quite an evening
17:02:39 <Taneb> Over a year ago now, wow
17:07:01 <Taneb> Apparently someone made the opposite mistake this year
17:08:27 -!- Frooxius has quit (Quit: *bubbles away*).
17:19:53 -!- Koen__ has quit (Ping timeout: 250 seconds).
17:22:19 -!- oren has quit (Quit: Lost terminal).
17:24:32 -!- bb010g has joined.
17:24:39 <boily> Taneb: you ought to merge the two societies together to prevent unnecessary confusion hth
17:34:49 <olsner> you could send out fake invites inviting the sci-fi/fantasy people to a social at the same place and time whenever the fetish society does something, and vice versa
17:57:13 -!- herbary has joined.
17:57:23 -!- herbary has left.
18:12:07 -!- vanila has quit (Quit: Leaving).
18:13:01 -!- CADD has quit (Quit: Lost terminal).
18:13:21 -!- CADD has joined.
18:14:49 -!- v4s has joined.
18:21:30 -!- boily has quit (Quit: SPREAD CHICKEN).
18:27:15 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:45:46 -!- Frooxius has joined.
18:46:23 <MDude> I just realized the Ibniz instruction manual mentions a "movesp" command that it does not actually describe.
18:46:37 -!- Froox has joined.
18:50:08 -!- Frooxius has quit (Ping timeout: 246 seconds).
18:59:00 -!- Fleur has joined.
19:04:43 -!- gamemanj has joined.
19:46:43 <mroman> Couldn't match expected type `()' with actual type `Maybe t1'
19:46:44 <mroman> In the pattern: Nothing
19:47:02 <mroman> so why the hell does it expect ()?
19:47:34 <int-e> mroman: such complaints are useless without context.
19:47:47 <int-e> > case () of Nothing -> ()
19:47:48 <lambdabot> with actual type ‘Data.Maybe.Maybe t0’
19:50:54 <gamemanj> ...Just read about lambdabot. Interesting. So if I were to do...
19:51:36 <int-e> mroman: fwiw, I treat "Couldn't match expected type 'a' with actual type 'b'" symmetrically; it's hard to predict which of two mismatching types will be 'a' and which will be 'b' for a given type-incorrect program.
19:52:57 <int-e> gamemanj: sorry, #esoteric becomes a secondary #haskell from time to time.
19:53:37 <gamemanj> int-e: ...That's fine. Lambdabot does seem fun for people to play with, and judging by that error certainly esoteric :)
19:55:03 <gamemanj> ...Course, maybe that's just a special case. What would "case () of Nothing" be useful for, exactly?
19:55:57 <int-e> gamemanj: nothing. it was meant to illustrate, by a simple example, how the type error mroman was complaining about could arise in practice
19:56:27 -!- Koen_ has joined.
19:57:48 <int-e> > let f Nothing = 1; f () = 2 in undefined -- testing
19:57:49 <lambdabot> Couldn't match expected type ‘Data.Maybe.Maybe t1’
19:58:08 <int-e> anyway, plenty of possibilities.
20:23:42 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
20:34:28 -!- ais523 has joined.
20:34:42 <gamemanj> I'm messing around with making a "light" esolang. One that won't hurt people's brains too much, but will compile to another esolang so they can study the results :)
20:37:20 -!- J_Arcane has joined.
20:43:49 -!- ais523 has quit (Ping timeout: 252 seconds).
20:47:29 -!- oerjan has joined.
20:49:03 <int-e> oerjan: did you see Dewcup resurface?
20:49:57 <int-e> (yafgc has such a funny update style; rather than having a buffer, the updates tend to happen in batches...)
20:51:19 <int-e> (Oh and I'm now totally confused about the relative timing of the various stories.)
20:51:34 <oerjan> int-e: there's a forum post with a chronology
20:51:55 <oerjan> unfortunately it's by chapter name, not comic numbers, so still a bit confusing
20:52:51 <oerjan> or rather, not confusing, but it makes it impossible to see where the actual jumps are, when you don't remember the _posting_ chronology
20:52:53 <Koen_> "yet another freaking golf compiler"?
20:53:05 <oerjan> fantasy gamer comic hth
20:53:37 <oerjan> it's sort of D&D based story like oots
20:54:02 <int-e> unlike oots, it doesn't take miles of text to get to a punchline
20:54:08 <oerjan> better drawing (but usually sketches, not properly inked) and frequently somewhat nsfw
20:54:14 <int-e> (sorry, I know I'm repeating myself there)
20:55:35 <oerjan> int-e: the updates are whenever he has free time to draw, i take. and also the recent server move has taken a lot off that time.
20:55:41 <int-e> The very first one is an indicator of how unsafe for work it gets, though maybe the Drow's dungeon (very SM) is worse. http://yafgc.net/comic/bob-meets-gren/
20:56:01 <oerjan> mostly because he's individually reuploading and reindexing every comic
20:56:45 <oerjan> (i could say something about obvious lack of scripting skills, but otoh the new indexing system is pretty nice)
20:57:03 <oerjan> also he isn't finished yet, so some comics are actually missing from the new archive
20:58:51 <oerjan> int-e: hm was i the one who pointed you to yafgc? that makes at least two of your comics my fault, then :P
20:59:13 <int-e> no, I've been reading yafgc like forever.
20:59:34 <int-e> "like" -- I really need to work on my English skills.
20:59:38 <oerjan> maybe it was the other way around, then, i don't actually remember where i learned of its existence
20:59:56 <oerjan> int-e: i think that's pretty normal english in certain sociolects
21:00:19 <oerjan> possibly you'd want it between commas
21:00:20 <int-e> oerjan: It might have been an independent discovery. The comic isn't exactly hard to find.
21:00:48 -!- AnotherTest has joined.
21:01:04 <oerjan> maybe. it was pretty old when i found it. i think it was in the middle of the vampire story.
21:01:28 <oerjan> the one with the penanggalan
21:01:54 <oerjan> (there were some vampires earlier who moved in when lewie left)
21:03:03 <oerjan> it's a bit confusing now with _both_ a bbs-like forum and comments on individual comics
21:03:46 <oerjan> the latter having the annoying property that afaict you have to check every comic to see them.
21:04:53 <oerjan> dewcup resurfacing near lewie was like pretty predictable
21:05:12 <oerjan> now i'm waiting to see how the meeting with ata goes
21:05:34 -!- chaosagent has joined.
21:05:41 <int-e> I didn't make the connection(sic!) between that one underground cave and the other.
21:06:06 <oerjan> um i think that was pretty ad hoc
21:06:22 <oerjan> they're meeting because the plot requires lewie to meet ata
21:06:39 <int-e> oerjan: and of course we still have to see Dewcup's other half to turn up. That will be fun. I expect them both to be evil, but it's hard to predict.
21:07:03 <oerjan> maybe the other half is still in the tomb city
21:07:31 <int-e> Yeah, I've also lost track of the plot, because of all the stories inbetween. :)
21:07:37 <oerjan> or maybe, as some predicted on the forum, dewcup is so unrestrained that she simply doesn't have any repressed sides for a succubus to form with
21:08:27 <oerjan> i think some years passed between dewcup getting captured and finding her way out
21:08:48 <oerjan> although i cannot say how many
21:09:30 <int-e> And what does the Ata priestess have to do with Kila, if anything?
21:10:56 <int-e> Hah, knowing Dewcup's natural charm I bet the priestess didn't last a week before giving her the run of the place (in order to get her out of sight.)
21:10:57 <oerjan> int-e: i suggest clicking on the link to Ata in the index for the comic
21:14:40 <oerjan> maybe i should find it, since it's not on the _current_ comic
21:15:40 <oerjan> um does that mean you found it
21:16:00 <oerjan> http://yafgc.net/character/princess-ata/ anyway
21:16:59 <int-e> Yes, it meant that I found it.
21:17:26 -!- ProofTechnique has joined.
21:19:30 <oerjan> *sigh* the ventilation system has started making that annoying sound again.
21:19:31 -!- Patashu has joined.
21:21:27 <mroman> can you do incremental parsing with parsec?
21:21:47 <oerjan> what kind of incremental
21:22:12 <mroman> Let's say what I want to parse comes from a stream
21:22:24 <oerjan> it's not very designed for it
21:22:26 <mroman> and I don't know if I have enough data present for parsing the next entry
21:22:41 <mroman> also there might be one entry in the buffer + half of the next entry
21:22:50 <mroman> parsec can't really deal with that
21:22:54 <oerjan> but i _think_ you can do it by parsing with a monad transformer
21:23:25 <oerjan> not sure how that interacts with backtracking though
21:23:30 <mroman> can parsec return me as a string what it couldn't parse?
21:24:50 <mroman> You can always wrap everything in a try I guess
21:25:08 <mroman> but that wouldn't tell me how far it parsed
21:26:02 <oerjan> "attoparsec supports incremental parsing directly"
21:26:38 <oerjan> http://stackoverflow.com/questions/15752243/incremental-parsing-from-handle-in-haskell
21:27:05 <oerjan> "Parsec, alas, doesn't."
21:29:33 <mroman> you can use try lookAhead I guess
21:29:52 <mroman> and call getPosition to determine how far it parsed
21:30:00 <mroman> but I think you *could* still do it
21:30:01 <int-e> Hmm, is that true? http://hackage.haskell.org/package/parsec-3.1.8/docs/Text-Parsec.html#t:Stream looks like this is now possible, though I'm not sure it's possible to not store everything that was already read for potential backtracking...
21:30:17 <mroman> "Returns the full parser state as a State record."
21:31:30 <oerjan> int-e: the problem isn't _reading_ incrementally, but parsing incrementally if you need lookahead.
21:32:23 <oerjan> parsec returns just one result, in bulk, and if that result used lookahead at the end your Stream will have read it, i think.
21:32:35 <oerjan> so restarting won't do the right thing.
21:34:12 <int-e> oerjan: well, it's a bit of both
21:34:30 <int-e> reading on demand and returning partial results
21:35:21 <mroman> oh well you can totaly do that
21:35:25 <int-e> Note also that that Stream class is a recent addition to Parsec, added in September last year, in version 3.1.6.
21:35:36 <oerjan> mroman: that's not likely to be lazy, though.
21:35:37 <mroman> *Main> runParserWithString parseIt "(9 9)(8"
21:35:38 <mroman> ("(8",RLON_Object (RLON_Integer 9) [RLON_Integer 9])
21:36:01 <mroman> state <- getInput; return $ (state, rlon)
21:36:10 <int-e> lambdabot is still on parsec-3.1.5
21:36:12 <mroman> you can call the parser
21:36:31 <mroman> then use getInput at the and of your parse function and return a tupel of the parsed stuff and a string of what's left to parse
21:36:32 <oerjan> mroman: i'm saying that you won't get lazy parsing this way
21:36:50 <mroman> why would I need lazy parsing?
21:37:11 <oerjan> well if you are reading from a file...
21:37:46 <oerjan> hm if you are reading from a list, will getInput just return it
21:38:04 <int-e> Parsec isn't the only parsing library out there. I wonder if anybody has done a comprehensive survey...
21:39:05 <mroman> I think try isn't that lazy anyway
21:39:10 <mroman> it requires backtracking after all
21:39:30 <mroman> so having a huge try will cause parsec anyway to keep the whole stuff in memory all the time
21:40:06 -!- bb010g has quit (Quit: Connection closed for inactivity).
21:40:44 <mroman> but you need a dummy thing you can return when parsing failed
21:40:50 <mroman> (i.e. when nothing could be completely parsed)
21:40:58 <mroman> http://codepad.org/LfQ80IF7
21:41:05 <mroman> wrap the outermost parse function in a try
21:41:08 <oerjan> mroman: i am thinking that you can parse a list incrementally in parsec by using ParsecT ... (Writer [...])
21:41:13 <mroman> then do (try outer) <|> (return DummyShit)
21:41:40 -!- sdegutis has joined.
21:41:43 -!- sdegutis has left ("Leaving...").
21:41:43 <oerjan> and _instead_ of return a result, you just lift $ tell ... each list item once you're sure of it
21:42:29 <oerjan> ...i guess this will ruin the normal error reporting, though.
21:42:41 <mroman> you can't tell if a parse error occured
21:42:45 <mroman> or not enough input is there
21:43:32 <mroman> so if I ever need incremental parsing
21:43:54 <mroman> (I don't actually need it right now, I was just curious)
21:44:01 <int-e> oerjan: lazy, incremental parsing is conceptually weird. you have to accept that you process partial results before you know that there won't be a syntax error later on.
21:44:14 <mroman> (I might do some network stuff some day)
21:44:50 <mroman> can you parse integer <> double without try btw?
21:44:56 <int-e> oerjan: And it gets weird if the result is in any way tree-structured, rather than a stream.
21:45:19 <oerjan> mroman: definitely not without making a custom combinator
21:45:39 <mroman> I usually use (try parseDouble) <|> parseInt
21:45:45 <mroman> and parseDouble expects a "."
21:45:49 <oerjan> 12 and 12.0 cannot be distinguished without reading input
21:45:54 <mroman> so when no "." is present it fails and parseInt will parse it
21:46:01 <mroman> but that requires a try
21:46:53 <mroman> it looks ahead on symbol
21:47:10 <oerjan> it's LL(whateveryouneed)
21:47:35 <mroman> having a char 'a'; char 'b'; and a char 'a'; char 'c' wont work
21:47:53 <mroman> because once it sees an 'a' it will expect 'b' ALWAYS
21:47:59 -!- Patashu has quit (Remote host closed the connection).
21:48:18 <int-e> that's actually the main innovation of Parsec
21:48:20 -!- Patashu has joined.
21:49:24 <int-e> (Bounding backtracking so that input can be discarded even after encountering an alternative.)
21:49:44 <oerjan> mroman: you cannot combine an integer and a double parser without try, but you can certainly refactor integer <|> double into something that doesn't use try
21:50:10 <oerjan> it's a regular sublanguage, after all
21:55:06 -!- Tritonio has quit (Ping timeout: 252 seconds).
21:57:17 <fizzie> I tried our home internet out, and it was not there yet. You will be fungotless for two more weeks.
21:58:16 <oerjan> or well, lookahead might still be a problem. e.g. how do you parse 12e
21:58:30 <fizzie> (In retrospect, I should have probably just moved it on a different server, but I didn't expect a delivery time this long.)
22:04:07 -!- CADD has quit (Remote host closed the connection).
22:05:51 <fizzie> The state of not having a fungot.
22:06:16 <fizzie> (See, it's been so long everyone has already forgotten.)
22:06:41 <oerjan> i am not sure gamemanj was here when it started hth
22:06:58 <J_Arcane> http://www.theguardian.com/tv-and-radio/2015/feb/27/finnish-punk-band-take-punt-eurovision-title
22:08:29 <gamemanj> I don't appear much on IRC, so I wouldn't know what a fungot is...
22:09:01 <gamemanj> Judging by the channel topic, it likes the internet.
22:09:13 <int-e> fungot is a treasure trove of wisdom
22:09:27 <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
22:09:43 <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!
22:10:11 <int-e> a bot, trained in linguistics. or something.
22:10:48 <int-e> (It can generate sentences using some Markov-ish language models.)
22:11:30 <gamemanj> ...Sounds fun....hang on, why can't fizzie just download fungot and connect from the same place he's IRCing from?
22:11:31 <int-e> The more impressive part is that it's written in Befunge.
22:11:51 * int-e is hazy on the fungoids.
22:11:54 <gamemanj> Or is fungot's code currently--WHAT.
22:12:22 <gamemanj> I know of the SOCK fingerprint, but still...
22:13:12 <fizzie> gamemanj: It felt like too much work to move everything (a gigabyte of data, plus having to build a patched cfunge) for such a should-have-been-short while.
22:13:13 <int-e> https://github.com/fis/fungot lists the fingerprints. (The code is there as well. Fizzie might give you a tour if you ask nicely, or not. I've never tried.)
22:13:29 <gamemanj> ...wait, really? A gigabyte of data? That's a bit of a large Befunge program.
22:13:44 <oerjan> i think that's the markov styles
22:13:53 <int-e> fizzie: patched how?
22:13:54 <fizzie> https://github.com/fis/fungot/blob/master/fungot.b98
22:13:57 <oerjan> the rest shouldn't be very large.
22:14:17 <oerjan> in theory there could be some huge ^def'ed commands, i guess
22:15:12 <int-e> (I didn't patch cfunge when I tried--unsuccessfully--to get fungot to run. Did I miss anything?)
22:15:31 <fizzie> int-e: There's a built-in chroot-and-drop-privs thing I wrote. Could go without or use some other (stronger) sandboxing, but haven't had the inclination.
22:16:14 <gamemanj> Well, what is the sandboxing needed for?
22:16:15 <fizzie> It should work just fine with the regular one. Though I may have not tried the most recent versions.
22:16:53 <fizzie> At any rate, I have no reasonable means of moving the data files out from here.
22:16:56 <oerjan> to protect against evil befunge hackers, of course
22:18:13 <gamemanj> How on earth did Fungot get so big in data?
22:18:31 <fizzie> It's the babbling styles.
22:19:03 <fizzie> Some of them were trained from relatively large source materials.
22:19:27 <fizzie> Like europarl, or even the irclog one.
22:19:52 <int-e> gamemanj: "Nonsense generation based on variable-length ngram models." -- there's a link to the variKN toolkit that fizzie used to generate the models (I think).
22:19:59 <gamemanj> ...And how are those loaded in?
22:20:18 <int-e> seek and destroy ... err, open, seek and read
22:20:24 <fizzie> Also the old (pre-varikn) training script did fixed-length unpruned models.
22:21:06 <fizzie> Yes, they're not loaded to fungespace, I seek/read with FILE on-demand.
22:21:30 <fizzie> Very inefficiently. Though I assume they do end up in caches.
22:21:30 <gamemanj> Sensible if they're a gigabyte.
22:23:17 <fizzie> `run quote 'department research' # is about the VariKN thing
22:23:18 <HackEgo> 13) <fizzie after embedding some of his department research into fungot> Finally I have found some actually useful purpose for it.
22:24:12 <fizzie> The biggest individual styles are (IIRC) 300 megs or so, but these days there are so many of them.
22:26:44 <fizzie> (Although many are real - too - small.)
22:28:34 <int-e> fizzie: can you get the fungot.dat file out?
22:30:33 <fizzie> Circuitously. But yes, in theory. I have something to do first, but I'll try to remember to put a link to it here within the next two hours.
22:30:39 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
22:31:05 * FireFly isn't sure if "it" is the department research or fungot.
22:31:15 -!- bb010g has joined.
22:31:36 <fizzie> (Things would be easier if I'd just tether this mobile thing, but it's so explicitly against the terms of service.)
22:32:10 <int-e> FireFly: I read it as referring to the research
22:32:22 <gamemanj> I've made a "temporary" model so Fungot can be booted, although he only says "hello" with this model. And it's not much of a model...
22:32:32 <gamemanj> ...and I'm not sure if it'll work.
22:33:25 <fizzie> It should boot with no babbling models too, it just requires a fungot.dat miscellaneous data file.
22:34:34 <fizzie> int-e: I'm not sure if it wants a '\0'-terminated 'styles.list' file too, by the way.
22:34:52 <gamemanj> Oh. I just went ahead and read your file format documentation :)
22:35:02 <int-e> fizzie: I have that. I even have a style.
22:36:52 <gamemanj> ...Does styles.list have newlines or not? It's written as having "lines" which ALSO have \0 in them.
22:39:28 -!- fnordbot has joined.
22:39:38 <fnordbot> int-e: hitch the length, he rather suspected this. trillian had turned aside in disgust they all went, " yuch." it's a lot. " so," said ford, " you reckon, what's the problem? a sudden silence afterwards." you can tell. at the moment. a slight hiss built into a deafening roar the engines. a galactic civilization, leapt to the controls, " i didn't pick up hitch the length, he rather suspected this. trillian had turned aside in d
22:39:47 -!- ProofTechnique has joined.
22:39:49 <int-e> fizzie: ok, it was the cfunge version
22:40:13 <int-e> (and the language model doesn't know when to stop)
22:40:18 <oerjan> i see it starts with a loop
22:41:08 <fnordbot> Selected style: Not really what you'd expect
22:41:34 <int-e> gamemanj: so as far as I can see it's actual lines, just as described.
22:41:52 <fizzie> gamemanj: It needs both \0\n at the ends of lines, and a \0 in first column after the entries.
22:42:25 <int-e> fizzie: so I guess I won't need that state file after all. but thanks for the offer.
22:42:32 <fizzie> Er, that is, \0 in first column on the line after the entries.
22:42:44 <gamemanj> Should styles.list and the model files be in data\ ?
22:43:06 <fizzie> int-e: Good, less work for me. Though you are missing the defined commands without it.
22:43:33 <fizzie> gamemanj: I think not. Which is a bit silly.
22:43:59 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
22:44:22 <fizzie> fnordbot: So which IRC channel was that from?
22:44:22 <fnordbot> fizzie: for. " all the doors." " a what? far out in the dordellis wars, and the megafreighters had to be equipped with the most fantastic. in a few seconds," he continued, " you just let the machines began to think that the chances of getting picked. he was a hell of a lot. " so," said ford, " you reckon, what's the problem? all his heirs are now long dead, and this is frankie, " a simple one!" " i just don't say things like th
22:44:25 <int-e> fizzie: right. but mainly I was curious whether I could get it to run at all. I didn't expect cfunge 0.9 to be incompatible with 0.3.3 (I haven't tried 0.4.1)
22:44:59 <int-e> fizzie: none. it's trained from the first volume of hitchhiker
22:45:23 <gamemanj> ...I'm guessing it doesn't work with CCBI?
22:46:11 <fizzie> int-e: Bizarre. I'm pretty sure I've ran it post-0.9. I'd like to debug this out, but the circumstances are not good for it right now. Perhaps when I get back from the Americas.
22:46:53 <fizzie> int-e: Feel free to report a github issue. :p (Might even be the first one.)
22:50:33 -!- ProofTechnique has joined.
22:53:20 <gamemanj> Well, after finding out I messed up the config, CCBI starts fungot! bad news: it doesn't give a nickname.
22:54:12 <int-e> did you edit the fungot-load-whatever.b98 file?
22:54:30 <gamemanj> Yep, that's what I broke(and then fixed, and then it still failed)
22:56:07 <gamemanj> Seems I didn't mess up config, and "-" isn't a banned letter in IRC AFAIK.
22:56:17 <gamemanj> (didn't mess it up twice, that is)
22:59:49 -!- fnordbot has quit (Remote host closed the connection).
23:03:58 <gamemanj> Fizzle, are the bot owner details still valid?
23:04:59 -!- Tritonio has joined.
23:05:36 <int-e> gamemanj: did you align the v above the strings with the < at the end of the lines, and make sure that there's no strage letter inbetween?
23:06:04 <gamemanj> Well, that was what my first mistake was. I've fixed that now, but I'm using CCBI, so I'm trying with the right version of cfunge.
23:06:05 -!- AnotherTest has quit (Ping timeout: 252 seconds).
23:06:49 <gamemanj> I'm probably going to lose connection for the night soon, though.
23:10:24 <gamemanj> ...cmake is starting, I'm compiling cfunge on the target server(which has a mostly-reliable connection)
23:10:46 <gamemanj> (and more importantly can run cfunge)
23:11:36 <fizzie> int-e: Did you test out the bf/ul interpreters while it was online?
23:12:01 <gamemanj> I didn't see any testing(could be done via PM)
23:12:53 <fizzie> (I went and got the Bluetooth keyboard, this seems so involved.)
23:13:06 -!- fnordbot has joined.
23:13:28 <fizzie> As for the owner details, you're supposed to fill them with your own, and then it'll accept the "owner" commands only from that nick!user@host prefix.
23:13:30 <gamemanj> Cfunge built on Raspberry Pi B+, who should own the bot?
23:13:49 <int-e> oh right, underload.
23:14:46 <int-e> ^bf ++++[>++++++++<-]>+.+.+.+.+.+.
23:15:08 <gamemanj> Starting...Still "no nickname given". Re-re-checking config.
23:16:43 -!- oerjan has quit (Quit: ZZZ).
23:18:22 <Koen_> ^befunge <@_.<0"hello"
23:18:26 <int-e> what's that funge testsuite...
23:19:26 <Koen_> ^funge <@_.<0"hello"
23:19:28 <fizzie> Koen: It only does the two.
23:20:02 <Koen_> I guess an inline interpreter for a 2d language wasn't that useful anyway
23:20:07 <fizzie> Although there's an owner-only command to run "raw" Funge-98 code, but it's mostly just useful for hot-patching (more like hot-breaking).
23:20:53 <fizzie> I can't get a hat out of this keyboard.
23:21:27 <gamemanj> fizzie: "fungot-g" is under your control. Have fun with it until you can run real fungot again. Don't abuse that feature I didn't know about until you mentioned it.
23:21:29 <Koen_> I can't get a bakslash out of mine
23:21:46 <fizzie> It has the Finnish keyboard, so the key with all kinds of diacritics is dead. Normally you get the ASCII hat with that + space, but on Android it just gives a ˆ.
23:21:57 <fizzie> Which is some other kind of a hat.
23:22:24 <Koen_> do you know if i can plug my phone to the computer and type with the phone keyboard?
23:23:14 <gamemanj> fizzie:try the brainf*** code: ++++++++++[->+++++++++<]>++++.[-]<
23:23:35 <fizzie> Koen_: I've done something like that by using a SSH client on the phone, and then doing screen -x to attach to a screen on the computer.
23:24:07 -!- Fleur has quit (Read error: Connection reset by peer).
23:24:15 <fizzie> Koen_: Though that didn't involve any plugging in. I would be surprised if it could (at least out-of-the-box) pretend to be a USB keyboard or something, if that's what you mean.
23:24:15 <gamemanj> Koen_:RDP,VNC are capable, but why type with a phone keyboard...?
23:24:29 <Sgeo> https://www.reddit.com/r/netsec/comments/2xgypm/using_rubys_openuri_one_step_away_from_rce/
23:24:53 <Koen_> my right hand is in a cast and has been for over two weks
23:25:21 <Koen_> i've practised typing with three fingers from the left hand but that'sstill slow
23:25:37 <Koen_> and some chars are hard to get
23:25:53 <fizzie> ^ul (Thanks for the copy-hat.)S
23:25:58 <Koen_> the backslash is downright impossible, it's alt+shift+/
23:26:32 <Koen_> and the alt key is only on the left side of the keyboard
23:27:06 <int-e> fizzie: so 0.3.3 is the latest cfunge that works for me.
23:28:00 <fizzie> int-e: And what did you say happened on the newer versions? Infinite loop parsing fungot.dat?
23:28:01 <gamemanj> What happens when there's two fungots on the same channel?
23:28:24 <fizzie> The command character (^) is in the configuration, I think.
23:28:31 <fizzie> You can have two non-conflicting fungots.
23:29:30 <gamemanj> So, if you had to choose a command character(under this scenario) what would it be?
23:30:29 <int-e> fizzie: it's playing ping-pong: http://dpaste.com/26CHQMY
23:31:28 <fizzie> I guess that wasn't the ASCII backtick either.
23:31:36 <fizzie> Man, this keyboard layout sucks.
23:31:37 <int-e> so yes that looks like the code reading fungot.dat (line 15 of fungot.b98)
23:32:20 <gamemanj> ...Actually, let me check...Fizzie, it *is* the ASCII backtick.
23:33:38 <gamemanj> At least, as far as I can tell from this web client, anyway.
23:34:57 <fizzie> int-e: And what was your fungot.dat like again? I keep forgetting.
23:35:01 <HackEgo> [U+02CB MODIFIER LETTER GRAVE ACCENT]
23:35:13 <int-e> fizzie: just 10 newlines
23:37:04 <HackEgo> U+0060 GRAVE ACCENT \ UTF-8: 60 UTF-16BE: 0060 Decimal: ` \ ` \ Category: Sk (Symbol, Modifier) \ Bidi: ON (Other Neutrals)
23:37:20 <FireFly> <gamemanj> So, if you had to choose a command character(under this scenario) what would it be? ← It occurred to me to check the list of botprefixes, but then I realised it's provided by fungot...
23:37:59 <fizzie> int-e: Okay, I have a hypothesis.
23:38:25 <fizzie> int-e: It has to do with the way STRN's substring things got more exact specifications for edge cases.
23:38:42 <gamemanj> FireFly: Well, fnordbot is fungot, but with the model database "modified".
23:38:42 <fnordbot> gamemanj:. " you see," he shouted to the guard, " not really. " we had a look at this," said slartibartfast, " that was one of mine," shouted ford. " i don't want to go to work at," and he turned. " but who the man with the five heads all the tests, learning to distinguish between him pretending to be an out a wild whoop in major thirds, threw ford prefect, " it's dark," he shouted to the guard, " not really. " we had a look at
23:39:17 <FireFly> gamemanj: sure, but it was stored as a defined command, so it's in the fabled fungot.dat file I suppose
23:39:55 <fizzie> int-e: Try with 10 non-empty lines.
23:40:36 -!- 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?").
23:42:33 <fizzie> int-e: (I think the problem is that the newline-stripping code no longer works on an empty line. Maybe.)
23:42:39 <int-e> fizzie: that gets past parsing the fungot.dat file, apparently, but loops later on, printing lots of numbers.
23:45:14 <fizzie> Maybe I should still just give you the .dat file.
23:45:58 <int-e> it gets to the point where it connects to the server, at least.
23:46:07 -!- gamemanj has quit (Ping timeout: 246 seconds).
23:46:49 <fizzie> FireFly: "All" the bots provide the list of botprefixes, that's one of the points of it.
23:47:02 <fizzie> FireFly: That's no longer quite true, but I think at least HackEgo's got it.
23:47:18 <fizzie> FireFly: (That's what I was trying to do there, with the backtick.)
23:47:30 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: botnames: not found
23:47:38 <fizzie> It's "prefixes". I think.
23:47:53 <HackEgo> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
23:48:06 <EgoBot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-bot ( , jconn ) , blsqbot !
23:48:35 <fizzie> That might be it. I don't think lambdabot is #esoteric-specific enough for that. :)
23:48:39 <int-e> fizzie: http://dpaste.com/3ZG5D0Z ... playing pingpong with the very top and bottom of funge-space.
23:49:03 <FireFly> Rather than having bots ignore other bots, I think other bots should adopt HackEgo's ZWSP prefix, and then ignore incoming lines starting with ZWSP
23:49:36 <int-e> fizzie: but how does a space go from 22/192 to 3/192... that's wild.
23:49:41 <FireFly> (well, I suppose specifically ignoring lines starting with ZWSP is redundant if it only takes action on a certain prefix)
23:50:16 <FireFly> int-e: I think it might skip until the next non-space characer
23:50:31 <fizzie> Yes, spaces are coalesced in Funge-98.
23:51:05 <fizzie> Sounds like something that might be a bonafide fungot bug.
23:51:19 <fizzie> Or maybe just another "unexpected reflect".
23:51:32 <int-e> anyway, these are the last few instructions before it veers off like that: http://dpaste.com/0HYK3CC
23:52:46 <int-e> fizzie: if you give me the .dat file I can put it up with fnordbot.
23:52:47 <fnordbot> int-e: what a day. " no you can't possibly, let out a wild whoop in major thirds, threw ford prefect, " it's dark," he shouted to the guard, " not really. " we had a look at this," said slartibartfast, " that was one of mine," he was saying, " magrathea is a myth, a fairy story, it's what parents tell their kids at school nicknamed him ix, which in the language. you want to try a guess at all, ford?" " well you see," he shouted
23:54:12 <fizzie> int-e: I think I'll do that. I'd like to figure out what's wrong for realsies, but I don't think I'll be doing that on this phone.
23:57:07 <fizzie> Okay, file is on the phone, thanks to adb push.
23:57:15 <fizzie> Now I just need to stuff it somewhere.
23:57:23 <fizzie> I don't have a Dropbox client on this thing.
23:57:33 <fizzie> Maybe you can share a file from Google Drive or something.
23:58:42 * int-e would be lost, and try to look for an ssh/sftp client...
23:59:05 <fizzie> I had one, but it was not a good one.
23:59:24 <fizzie> You could try what happens if you click at https://docs.google.com/file/d/0B4J9OAzXNfZAX2Z6OW15YXZGaWM/edit?usp=docslist_api