00:01:06 -!- tromp has joined.
00:04:03 <shikhin> I've released a new IDE with fun support for all esoteric languages - http://shikhin.in/2014/04/01/wodscipe-ide.html & http://f.osdev.org/viewtopic.php?f=2&t=27885.
00:06:05 -!- augur has quit (Remote host closed the connection).
00:06:37 -!- augur has joined.
00:09:18 <elliott> well, I don't actually mean that.
00:10:35 <Bicyclidine> doesthiswork: i'll play it later. i'm just thinking of irl chemistry which is where axiomatism goes to die http://en.wikipedia.org/wiki/Relativistic_quantum_chemistry
00:11:08 -!- augur has quit (Ping timeout: 240 seconds).
00:17:31 -!- nooodl has quit (Quit: Ik ga weg).
00:34:52 <shikhin> elliott: D'oh, that was actually a typo. *some -- go check it out, it actually works :-)
00:35:22 <elliott> does it all fit in a boot sector?
00:35:27 <elliott> I almost managed to fit half a Forth into one.
00:36:24 <shikhin> elliott: We've split the editor and the interpreter.
00:36:39 <shikhin> elliott: So, yes, the editor fits into a boot sector, and all interpreters fit in another 512B.
00:36:46 <shikhin> But, hey, the editor's a quite functional ed :-)
00:36:53 <elliott> I'm sure you can halve them both
00:38:47 <shikhin> The editor's... really nasty.
00:39:09 -!- shikhin has quit (Read error: Connection reset by peer).
00:39:53 <elliott> it can't possibly need all those bytes
00:40:36 -!- shikhin has joined.
00:42:46 -!- augur has joined.
00:43:15 -!- augur has quit (Remote host closed the connection).
00:43:24 -!- augur has joined.
01:05:05 -!- conehead has quit (Quit: Computer has gone to sleep.).
01:11:17 -!- augur_ has joined.
01:11:55 -!- augur has quit (Ping timeout: 240 seconds).
01:41:25 <Sgeo> Is it wrong for me to want Snap on WAI?
01:41:57 <Sgeo> Also, is there any good reason that Scotty doesn't allow for installing middleware in a route?
01:42:09 <Sgeo> I certainly don't want to apply jsonp to my entire application
01:42:26 <Sgeo> (Not that I like Scotty. I really, really, don't)
01:53:59 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
02:04:13 <quintopia> re: freenode-G+ integration: I lolled
02:05:28 -!- ^v has quit (Read error: Connection reset by peer).
02:05:52 <doesthiswork> have you read the paper on managed time in programming languages?
02:05:56 -!- ^v has joined.
02:07:27 <doesthiswork> well it is interesting http://research.microsoft.com/pubs/211297/managedtime.pdf
02:10:29 <Jafet> "Section 6 concludes with a future of managed time."
02:12:44 <doesthiswork> what else would come after section 5 "The past and present of managed time"
02:58:48 -!- Sellyme has quit (Excess Flood).
02:59:41 -!- Sellyme has joined.
03:00:52 <zzo38> I was looking at some things and found a Java program written by a pretty bad compiler... to create a text value with "pick one" written in it, the code looks like: temp7 = new TTText("A"); hand = temp7; hand.keyboard('\b', false); hand.keyboard('p', false); hand.keyboard('i', false); hand.keyboard('c', false); ... hand.stoppedTyping(); notebook.gets(hand);
03:04:01 <Jafet> I wonder what was the reason for the \b.
03:29:33 -!- BeingUntoDeath has quit.
03:37:07 -!- Sorella has quit (Quit: It is tiem!).
03:43:29 -!- tertu has joined.
03:44:37 <zzo38> The \b is backspace, I think, to delete the "A"
03:45:28 <zzo38> And, I think the macro recorder in Microsoft Office probably does a better job than this...
03:46:36 <zzo38> (Actually the program contains a comment that says \b is the backspace key)
04:22:18 -!- doesthiswork has quit (Ping timeout: 245 seconds).
04:31:39 <zzo38> There are also things like this: temp1 = new TTNumber(1); hand = temp1; temp1 = hand; TTVacuum vacuum = new TTVacuum(); hand = vacuum; hand.keyboard('e', false); hand.stoppedTyping(); vacuum.suckUp(temp1); (temp1 and hand are both local variables of type TTObject)
04:35:14 -!- conehead has joined.
04:39:08 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
04:44:49 -!- doesthiswork has joined.
04:46:23 <nortti> http://shikhin.in/2014/04/01/wodscipe-ide.html http://github.com/Shikhin/wodscipe
04:47:13 -!- conehead has quit (Quit: conehead).
04:47:58 -!- Zerker has joined.
04:51:31 -!- ^v has quit (Read error: Connection reset by peer).
04:51:59 -!- ^v has joined.
04:52:27 -!- conehead has joined.
04:56:45 <Sgeo> kmc: Just learned that Snap framework apparently uses a Haskell library for SSL that uses OpenSSL, and someone on the mailing list was asking why thye're not using the pure Haskell version
04:57:10 <Sgeo> I think I am that much more confident in Snap doing the right thing (in that they're doing the right thing here using OpenSSL)
04:59:47 <elliott> I'd trust some random Haskell code over OpenSSL :/
05:05:06 <shachaf> Random Haskell code implementing SSL? Really?
05:05:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
05:08:31 <maurer> pure haskell version also has some oddities, e.g. not reading modern key formats
05:12:17 <HackEgo> mariolacoin fobcoin cuttcoin argfalcoin pathcoin subjicidecoin sympcoin resscoin middcoin torcoin ext()coin bitioncoin parackcoin clunecoin pictcoin billiicoin reverecoin andcoin bfirdinarizcoin ~coin
05:13:05 <quintopia> the channel for the freenode/google integration is so much fun
05:14:53 -!- Zerker has quit (Ping timeout: 268 seconds).
05:19:16 <Sgeo> I was hoping they actually changed NickServ to suppport it
05:22:29 <lambdabot> Not in scope: type constructor or class `Void'
05:23:00 -!- Zerker has joined.
05:23:19 <Sgeo> Did... Reddit implement face recognition technology for an April Fools prank?
05:23:20 <newsham> ?type fix id :: AprilFOols
05:23:21 <lambdabot> Not in scope: type constructor or class `AprilFOols'
05:23:21 <lambdabot> Perhaps you meant `AprilFools' (line 153)
05:23:25 <newsham> ?type fix id :: AprilFools
05:23:53 <Sgeo> I mean, the webcam video genuinely was recongizing where my face was
05:24:13 <elliott> that must have taken, like, three lines of OpenCV calls
05:24:16 <fizzie> Sgeo: I would assume they just picked an off-the-shelf one. There's one as a standard module in OpenCV.
05:25:01 <Sgeo> I couldn't do anything but downvote
05:25:08 <Sgeo> But then I hadn't read the blog yet
05:26:47 <Bike> happy internet uselessness day
05:27:48 -!- oklopol has joined.
05:29:11 <fizzie> I've got a weekly exercise session to run for that machine learning course, and I didn't even think of putting any FOOLERY in the questions. :/
05:34:57 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
05:45:52 <lambdabot> Yow! And then we could sit on the hoods of cars at stop lights!
05:54:15 -!- password2 has joined.
06:05:39 <Sgeo> If I believe something for half a second, does that still count as falling for it?/
06:06:14 <Bike> yes. feel shame.
06:06:38 <Sgeo> http://www.nordicgoacademy.com/2014/04/01/9x9-go-has-been-solved/
06:06:41 <Sgeo> I didn't even read the article
06:07:41 <Bike> god damn it, the internet has made me hate a holiday as innocuous as april fool's
06:08:30 <Sgeo> "Similarly, now we have type holes that let us see what types should be inserted in various spots. -fvalue-holes is the next logical step, to tell us what terms we should be writing."
06:08:43 <Sgeo> Isn't that what automated proofs in dependently typed languages assist with?
06:11:20 -!- tertu has quit (Ping timeout: 246 seconds).
06:16:55 -!- Sprocklem has joined.
06:21:17 -!- tromp_ has joined.
06:23:57 -!- tromp has quit (Ping timeout: 268 seconds).
06:30:27 -!- jix_ has quit (Ping timeout: 265 seconds).
06:30:35 -!- jix has joined.
06:34:49 <oklopol> i fell for it even though i read Sgeo's first message, and even though i was informed the first thing in the morning that it's 1.4. and if i go to work i should be careful.
06:34:54 -!- olsner has joined.
06:35:26 <oklopol> (i asked why i got a warning instead of trickery, but apparently i'm too gullible for it to be interesting.)
06:36:20 <Sgeo> I don't get the meaning of precise-exceptions
06:41:03 -!- shikhout has joined.
06:41:38 <variable> Sgeo: on some processors exceptions, such as div-by-zero, etc. are not guaranteed to be reported in exact temporal location
06:41:55 <variable> other instructions may have already been executed by the time it is reported
06:43:43 -!- shikhin has quit (Ping timeout: 264 seconds).
06:43:45 -!- shikhout has changed nick to shikhin.
06:44:18 <HackEgo> divzerosisivecoin phildcoin smal-xcoin bash-01coin asingcoin aarghcoin shacoin magincoin cratorycoin upakcoin possologelcoin perparcoin opparcivilcoin etchcoin selfcoin iotoncoin braincoin nutcoin niocoin kensigcoin
06:44:55 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
06:44:55 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c |
06:44:55 <myndzi> /^\ c.c |\ |\| | >\ c.c /< | /| |/< c.c /|
06:49:40 <fizzie> "For light computing there will now be two servers, brute.aalto.fi and force.aalto.fi."
06:50:54 <fizzie> "Mathematica, MatLAB etc will be removed from kosh and lyta [general shell servers], and it is now forbidden to run CPU and/or memory-intensive processes there, and Aalto IT may kill those processes. -- There will be two new Ubuntu shell servers (brute.aalto.fi, force.aalto.fi), both of which have 256GB RAM and 16 cores. These are meant for light computing. All users are asked to be ...
06:51:00 <fizzie> ... considerate of other users and nice their processes. Any commercial use of these servers is prohibited. As an extreme example, 'mining' of any electronic currencies is strictly prohibited."
06:51:04 <fizzie> Makes me wonder if anyone has actually mined some bitcoins on the shell server.
06:51:28 <olsner> kosh and lyta were nice names too
06:54:07 -!- doesthiswork has quit (Quit: Page closed).
06:54:26 <fizzie> "Solve::nsmet: This system cannot be solved with the methods available to Solve." Mathematica, you've let me down!
07:08:25 -!- Sprocklem has quit (Quit: Lost terminal).
07:10:07 <^v> esolang.org is going down
07:10:14 <^v> due to lack of funding
07:11:07 <^v> here is the info: http://goo.gl/6zh5
07:11:12 <quintopia> but esolangs.org is here to stay :D
07:11:48 <Sgeo> http://www.scp-wiki.net/ aww, such super cute pets
07:14:08 -!- heroux has quit (Ping timeout: 240 seconds).
07:15:21 -!- ChanServ has set channel mode: +o elliott.
07:15:28 <Sgeo> I should sleep
07:15:37 -!- elliott has kicked ^v it's april fool's day, not just be stupid day.
07:15:39 -!- elliott has set channel mode: -o elliott.
07:16:22 <Bike> is the link goatse or what
07:17:09 -!- ^v has joined.
07:17:14 <Bike> why does goo.gl not have an expander...
07:17:16 <Sgeo> As of this line, neither the most recent link I linked to nor the most recent link ^v linked to is goatse
07:17:46 <Bike> well what is it then. lemonparty? screamer? 2048? pentagon papers?
07:17:53 <Sgeo> I am aware of the potential race condition, but it seemed to not have occurred
07:18:41 <Bike> jesus christ dude
07:18:59 <Sgeo> It is not lemonparty nor screamer nor 2048. I am not sure what pentagon papers is, but it's not that either, unless pentagon papers means something really non-obvious
07:19:31 <Sgeo> (It's rickroll)
07:19:38 <Sgeo> I should sleep
07:24:40 -!- Patashu has joined.
07:25:00 <^v> No, its illuminati
07:29:45 <^v> http://i.imgur.com/9IR3V86.png
07:29:54 <^v> its illuminati
07:30:02 <^v> they are taking over the world
07:31:12 <kmc> `addquote <Sgeo> It is not lemonparty nor screamer nor 2048. I am not sure what pentagon papers is, but it's not that either
07:31:14 <HackEgo> 1180) <Sgeo> It is not lemonparty nor screamer nor 2048. I am not sure what pentagon papers is, but it's not that either
07:34:30 <Sgeo> Fark put up their April Fools Day prank
07:38:41 -!- Patashu[Zzz] has joined.
07:38:41 -!- Patashu has quit (Disconnected by services).
07:40:14 <olsner> went to the page (I think) and it wasn't obvious, so I left
07:40:45 <quintopia> so they just reset the page back to some day in 2004? lame
07:41:37 <olsner> I imagine it's great if you were a regular visitor in 2004
07:43:35 <kmc> I actually was a regular visitor in 2004
07:44:06 <kmc> fungot: what would you do if your toilet came to life
07:44:06 <fungot> kmc: we need to get and up here, shouldn't there be, exactly, i don't get to live. your trial that would appear to you in the bedroom. or any room with that."
07:44:08 <olsner> was it a good joke for you then?
07:45:22 -!- Patashu[Zzz] has quit (Ping timeout: 265 seconds).
07:48:41 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
07:50:41 -!- Slereahphone has joined.
07:52:48 -!- Tritonio has joined.
07:55:03 <olsner> hmm, is "passionated" a word?
08:25:06 -!- oerjan has joined.
08:46:41 -!- olsner has quit (Quit: Leaving).
08:59:00 <ion> @tell olsner It is if you word it.
08:59:24 -!- Slereahphone has quit (Remote host closed the connection).
09:05:06 -!- Slereahphone has joined.
09:18:10 -!- oerjan has quit (Quit: leaving).
09:43:04 <quintopia> ion: it also depends on how it's encoded, and the size of a word on your system
10:01:44 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
10:12:53 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi).
10:13:27 -!- Slereahphone has joined.
10:13:37 -!- boily has joined.
10:20:57 -!- yorick has joined.
10:26:04 -!- Slereahphone has quit (Remote host closed the connection).
10:26:25 -!- Slereahphone has joined.
10:34:04 -!- JesseH has joined.
10:34:32 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi).
10:59:31 -!- boily has quit (Quit: Poulet!).
11:23:32 -!- Phantom_Hoover has joined.
11:34:45 -!- JesseH has quit (Ping timeout: 268 seconds).
11:42:00 -!- yorick has quit (Remote host closed the connection).
11:42:17 -!- yorick has joined.
11:47:08 -!- tertu has joined.
12:03:20 -!- Sorella has joined.
12:32:55 -!- Sgeo has quit (Read error: Connection reset by peer).
12:34:56 -!- MoALTz has quit (Read error: Connection reset by peer).
12:35:03 -!- MoALTz has joined.
12:38:20 -!- MoALTz_ has joined.
12:40:26 -!- shikhout has joined.
12:41:58 -!- MoALTz has quit (Ping timeout: 268 seconds).
12:43:43 -!- shikhin has quit (Ping timeout: 264 seconds).
12:43:44 -!- shikhout has changed nick to shikhin.
13:11:28 -!- vravn has quit (Ping timeout: 255 seconds).
13:12:37 -!- vravn has joined.
13:43:30 <shikhin> Has everyone here checked out Wodscipe? It's an insane IDE for esoteric languages! http://shikhin.in/2014/04/01/wodscipe-ide.html (github: http://github.com/shikhin/wodscipe)!
13:44:07 <zzo38> I have read that article about it, at least
15:03:32 -!- MoALTz_ has quit (Quit: bbs).
15:18:25 -!- nooodl has joined.
15:26:30 -!- Tritonio has quit (Ping timeout: 252 seconds).
15:44:21 -!- MindlessDrone has joined.
15:50:39 -!- spiette has quit (Ping timeout: 265 seconds).
15:55:35 -!- olsner has joined.
15:57:31 -!- idris-ircslave has quit (Quit: Terminated).
15:57:50 -!- idris-ircslave has joined.
16:01:00 -!- oerjan has joined.
16:30:32 <mroman> I've grown to hate Smalltalk and Modula
16:30:48 <mroman> and everything that is similar to it
16:32:03 <mroman> elliott: Thank you for listening.
16:32:09 <mroman> I really appreciate it.
16:32:35 <mroman> In other channels I would have gotten banned for such promising statements.
16:33:02 <oerjan> i didn't think smalltalk, modula and fortran were very similar.
16:33:37 <elliott> mroman: that can still be arranged if you'd like.
16:33:42 <oerjan> are you sure you don't just hate programming languages in general.
16:33:46 <elliott> oerjan: smalltalk and modula are at least both early OO languages...
16:33:57 <mroman> oerjan: No. Just the old ones that feel impractical ;)
16:33:58 <olsner> ion: if someone worded it, it wasn't me (looked like swenglish to me)
16:34:11 <elliott> have you ever read a line of smalltalk in your life?
16:34:18 <elliott> it's far more comparable to something like Ruby than Fortran...
16:34:23 <oerjan> elliott: depends on if it's modula 2 or 3, i think. (i learned 2 which wasn't very oo iirc)
16:34:32 <mroman> elliott: I've even written lines in smalltalk
16:34:59 <mroman> honestly the worst part about smalltalk is that workspace thingy
16:35:09 <mroman> other than that it's not so bad actually
16:35:20 -!- olsner has quit (Quit: Leaving).
16:35:30 <elliott> and eclipse, the worst part of java
16:35:47 <mroman> Eclipse isn't that tightly coupled to java
16:35:49 <elliott> (though Workspace is just the REPL type thing, maybe you didn't mean that?)
16:36:13 <elliott> anyway I'm actually so tired of bickering about this stuff and am hereby retiring from it.
16:36:43 <mroman> I obviously wasn't prepared to discuss it anyway ;)
16:38:04 <mroman> There really isn't a way to return an open array from a procedure in Modula?
16:38:45 <elliott> well, I also retired from complaining, just more relapses
16:39:47 <elliott> oerjan: I wasn't aware. silly Wirth reusing language names so much
16:39:54 <elliott> or, maybe I was aware but only dimly
16:40:08 <mroman> I'm not asking you to complain. And I'm not complaining.
16:43:23 <elliott> we are, by the way, now bickering over this.
16:45:01 <zzo38> oerjan: No, *you* are not.
16:49:30 <mroman> fungot: What's your position on this.
16:49:31 <fungot> mroman: he be tha heart an' soul o" tiles because my father, and i would not be so dismissive of.
16:50:09 -!- ^v has joined.
16:50:42 <oerjan> and possibly vaarsuvius
16:52:44 <zzo38> FORTRAN is including many things that they forgot to put in modern programming languages, such as FREQUENCY statement, arithmetic IF, arithmetic overflow checking, ASSIGN, etc and some of these features have been removed or made useless in Fortran 95 and newer versions.
17:00:46 <zzo38> Although FORTRAN does have some new features which are pretty good too, such as coarrays, and a few others.
17:07:26 <mroman> incindentally I hate all programming languages
17:12:25 <int-e> mroman: It's not often that I quote Stroustrup, but I like this statement: "There are only two kinds of languages: the ones people complain about and the ones nobody uses."
17:13:27 <kmc> two kinds of fungot
17:13:28 <fungot> kmc: me too! neat, having dinner together, and i know that, i'm no better than my own, but
17:14:28 <oerjan> fungot: now you're going around being disturbingly appropriate again
17:14:28 <fungot> oerjan: get down! take a load and unload the camels for a second, any spell you are working on.
17:15:20 <int-e> two fungot (or is the plural "fungots"?) and "me too", does that make three?
17:15:21 <fungot> int-e: we need to get that " video games, but you and the idiot paladin understands better, i once saw head-butt an elderly gnome woman into a coma, he's been too tired and panicked! it's all i could get the scene.
17:15:48 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots* pa qwantz sms speeches ss wp youtube
17:19:13 <Jafet> fungot, what do you think about fungoots
17:19:14 <fungot> Jafet: this " treasure" idea intrigues me and i wish. but elan, we're doing here in, say, " hold half-orc" for the hell, i rolled a 1 gp fee, we'll see if, for that kind of stuff, i figured that one out on my own, but
17:19:30 <Jafet> I think this corpus isn't quite large enough.
17:20:11 <int-e> "iwcs" would be the irregular webcomics?
17:20:17 <kmc> wouldn't the plural be "fungi"
17:20:32 <kmc> fungot: how do you pluralize yourself
17:20:33 <fungot> kmc: for that, my family would like my mode of transit returned, do you know that no one leaves. roy, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant, do i not, lieutenant,
17:20:49 <int-e> "pluralize", not "multiply"
17:21:16 <kmc> huh I usually don't see fungot do that
17:21:17 <fungot> kmc: too much clean and safe places for us, " oh, i get it. in that case, i will be up here on my throne, being awesome and everyone here could use a little. you sound so bad, really, all my molecules, so that the dwarf, " stabby"
17:21:23 <fungot> Selected style: discworld (a subset of Terry Pratchett's Discworld books)
17:21:38 <int-e> fungot: how do you feel about imps?
17:21:38 <fungot> int-e: " good heavens. really... i have nothing but the endless glass rooms.
17:22:07 * int-e wonders whether fungot can recognize handwriting now
17:22:07 <fungot> int-e: " ah," said ponder. " uh... and there's still more scumble in the jug."
17:22:40 * int-e realizes for the first time that fungot is all lower case ALL THE TIME.
17:22:41 <fungot> int-e: on the other hand, anyone you managed to hit instantly became your foe, so it can get interesting, technically you'll rank as a corporal," said colon, but without much enthusiasm. even beggars need someone to watch over imp that night was day, people would have joined in.
17:23:12 -!- MoALTz has joined.
17:23:13 <kmc> T FUNGOT HUALAGAHALAHAGAGLAHL
17:23:30 <int-e> yes, including the fUnGoT nickname recognition
17:23:40 <kmc> tea fungot
17:23:41 <fungot> kmc: this was a gross breach of etiquette. " she's all right. you have to look hard. the hogfather's artificial stomach was now at groin level.
17:23:52 <kmc> fungot: c.c
17:23:52 <fungot> kmc: the whole family, including the floor and looked down at the table in the rats chamber repaired?' he said.
17:23:57 <kmc> myndzi: TOO SLOW
17:24:09 * kmc wonders if the ordering of messages is consistent for all users in a channel
17:24:15 <kmc> I suspect not, at least between servers?
17:24:40 <shachaf> In the past I've seen messages from the same user reordered.
17:25:32 <int-e> discworld was a bad choice, I want to get this image out of my head ...
17:26:04 <kmc> fungot: i'll be back in a bit
17:26:05 <fungot> kmc: ' is there something you want to go by yourself?'
17:26:16 <kmc> fungot: yes, riding TRAAAAAINS
17:26:16 <fungot> kmc: ' right,' said the count, thrusting the axe aside. ' good name.'
17:26:34 <int-e> fungot: s/go/do/ and it would have been perfect.
17:26:35 <fungot> int-e: teppic joined him on the
17:27:21 <int-e> That's an euphemism I have not heard before.
17:27:24 <kmc> the only 1676 mm gauge railway in North America?
17:44:21 <int-e> ... still in operation?
17:45:19 -!- doesthiswork has joined.
17:46:24 -!- ^v has quit (Read error: Connection reset by peer).
17:46:52 -!- ^v has joined.
17:54:46 -!- MoALTz_ has joined.
17:57:22 -!- MoALTz has quit (Ping timeout: 252 seconds).
17:58:40 -!- Sorella has quit (Ping timeout: 252 seconds).
18:05:23 <Bike> kmc: messages by yourself show up instantaneously in most clients so there's semifrequent mild inconsitencies
18:08:36 <oerjan> i assume irc makes no attempt at chronologically ordering messages arriving from different servers
18:08:57 <Jafet> “The Sampoong Department Store collapse was a structural failure that occurred on June 29, 1995 [...] It was the deadliest building collapse since the Circus Maximus collapse in c. 140 AD”
18:09:09 <oerjan> hm, _is_ there even any original timestamp?
18:10:41 <oerjan> that circus maximus one was a long-lasting record for sure
18:11:35 <oerjan> wait it didn't say that beat it
18:12:07 <oerjan> i'd imagine the twin towers might hold that record now?
18:12:21 <Jafet> There is a very brief mention on the article for the Circus Maximus, in the citation footnotes, of 13000 people killed by a partial collapse of the stadium.
18:12:25 <Bike> they're probably only counting accidents.
18:12:43 <oerjan> 13000, ok that record might _still_ hold then.
18:13:50 <Jafet> If you really want to kill the most people, though, you should build a dam in china
18:14:01 <Jafet> Or a chemical factory in india
18:15:16 <oerjan> just do that mediterranean basin thing
18:15:49 <oerjan> takes a few millennia to set up, though
18:17:43 -!- nooodl_ has joined.
18:21:02 -!- nooodl has quit (Ping timeout: 253 seconds).
18:22:24 <kmc> just spend a few hundred years filling the atmosphere with excess CO₂
18:22:51 -!- password2 has quit (Read error: Operation timed out).
18:25:28 <Jafet> Wouldn't you only ruin a few million coastal dwellers who by most accounts don't even give us cheap consumer products
18:26:31 <oerjan> kmc: um that wouldn't be likely to empty the basin, would it?
18:28:41 -!- upgrayeddd has joined.
18:29:10 -!- doesthiswork has quit (Quit: Page closed).
18:36:48 -!- password2 has joined.
18:41:14 -!- shikhout has joined.
18:44:00 -!- shikhin has quit (Ping timeout: 255 seconds).
18:44:02 -!- shikhout has changed nick to shikhin.
19:02:36 <Bike> http://appleinsider.com/articles/14/04/01/like-a-glove-april-fools-efforts-from-samsung-htc-toshiba-all-share-the-same-punchline
19:11:01 -!- Guest27452 has changed nick to Zom-B.
19:12:22 -!- impomatic has joined.
19:15:06 <impomatic> Core War is currently high on the programming reddit :-) http://www.reddit.com/r/programming/comments/21xfrs/the_spring_2014_core_war_tournament_celebrating/
19:15:25 * impomatic hopes quite a few people will enter the tournament...
19:17:19 -!- Sorella has joined.
19:17:22 -!- Sorella_ has joined.
19:22:07 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:28:23 -!- chaiomanot has joined.
19:29:30 -!- olsner has joined.
19:35:33 <olsner> sounds too boring to approve of, however crazy it may be
19:39:38 -!- password2 has quit (Ping timeout: 240 seconds).
19:43:58 -!- heroux has joined.
20:02:38 -!- conehead has joined.
20:05:26 -!- Sprocklem has joined.
20:24:21 -!- conehead has quit (Quit: Computer has gone to sleep).
20:36:47 <oerjan> darn i had 1024, 512 and 256
20:41:04 <kmc> you know how it saves your game when you close the tab? well you can cheat by opening multiple tabs as savepoints
20:42:25 <shachaf> you can also cheat by changing the numbers around to say what you want
20:45:52 <kmc> you can also cheat by not playing at all
20:46:18 <kmc> shachaf: there's "taking the rubiks cube apart and reassembling it solved" cheating and then there's "moving all the stickers" cheating
20:46:39 <kmc> now you've made me want to play DEFCON
20:46:58 -!- conehead has joined.
20:49:10 <olsner> I want a proper programming language to (re-)write my OS in
20:49:23 <lexande> the only winning move is to play, perfectly, waiting for your opponent to make a mistake
20:52:55 <kmc> olsner: Rust?
20:53:43 <maurer> kmc: Are you on a team for it?
20:54:00 <kmc> I don't know what you mean by that quite
20:54:07 <kmc> I'm on Team Rust in that I plug Rust every chance I get :P
20:54:08 <olsner> I guess I should try, I hear there have been some improvements for runtime-less rust code
20:54:18 <kmc> yeah, it's pretty slick now
20:54:22 <maurer> kmc: Sorry, I meant in relation to 16:46 < kmc> now you've made me want to play DEFCON
20:54:24 <kmc> http://blog.theincredibleholk.org/blog/2013/11/18/booting-to-rust/
20:54:28 <maurer> you don't mean that defcon
20:54:31 <maurer> you mean the missile shooting one
20:54:57 <maurer> We're gonna have srsmode competition from dragon sector this year :(
20:54:59 <olsner> but I may want something that's more like a mix between rust and assembly
20:55:01 <maurer> well, it's a good thing
20:55:41 <kmc> olsner: in what way?
20:59:31 <kmc> you can do inline assembly in Rust; you can also link object files from Rust, C, assembly pretty easily
21:01:57 <olsner> not sure :) but e.g. something like inline rust for the code that's too tedious to do manually in assembly
21:09:20 -!- trn has quit (Ping timeout: 246 seconds).
21:09:59 <olsner> I've been playing with the idea of building an optimizing assembler too
21:11:50 <olsner> (... implementing actual functionality is not the primary activity of this project)
21:15:59 -!- john_metcalf has quit (Read error: Connection reset by peer).
21:17:50 -!- Sprocklem has quit (Quit: Lost terminal).
21:19:05 -!- trn has joined.
21:19:12 <olsner> UEFI's console API takes UTF-16 o.O
21:19:23 <kmc> i blame microsoft
21:19:48 <olsner> obviously, with the PE32 format too
21:19:56 <kmc> and the windows x64 calling convention
21:20:16 <Bike> at least it's not latin-1
21:20:32 <kmc> cp437 for life
21:21:06 <olsner> code page "whatever matches the font loaded on the graphics card"
21:21:17 <kmc> Bike: I like how on the web "Latin-1" means Windows-1252 always
21:21:25 <kmc> like in <meta charset> tags, etc.
21:22:11 <kmc> also the algorithm for parsing numerical character entities (which are supposed to be Unicode codepoints) has special cases for 0x80 - 0x9F (the ISO-2022 C1 control code range) which map to the most likely printable Windows codepage characters
21:26:46 -!- Sprocklem has joined.
21:29:13 <olsner> oh well, I think I'll do a trial rewrite of the kernel in rust ... the biggest horror is that I'll probably have to use a linker
21:29:32 <zzo38> CP437 (the PC character set) is good idea.
21:37:31 -!- boily has joined.
21:43:08 <olsner> but tomorrow! now I shall sleep
21:45:42 -!- olsner has quit (Quit: Leaving).
21:46:07 -!- heroux has quit (Ping timeout: 264 seconds).
21:46:29 <boily> can lambdabot send differed subconscious messages in people's sleep?
21:46:31 -!- heroux has joined.
21:46:59 <lambdabot> The answer is: Yes! Haskell can do that.
21:47:23 <int-e> . o O ( which reminds me of a request to change this to a link to the FAQ on the haskell wiki )
21:47:44 <int-e> boily: it only works if your subconscious is pure though
21:48:24 <boily> ain't gonna happen soon. my subconscious is having lascivious thoughts of a grilled bagel, with chipotle hummus, random cheese, spinach and italian tomatoes.
21:49:47 -!- MoALTz__ has joined.
21:54:40 -!- tertu has quit (Ping timeout: 255 seconds).
21:54:41 -!- shikhin has quit (Ping timeout: 255 seconds).
21:54:42 -!- lambdabot has quit (Ping timeout: 255 seconds).
21:54:43 -!- MoALTz_ has quit (Ping timeout: 255 seconds).
21:54:43 -!- vravn has quit (Ping timeout: 255 seconds).
21:55:26 -!- shikhin has joined.
21:55:29 -!- upgrayeddd has quit (Quit: Connection closed for inactivity).
21:57:09 -!- vravn has joined.
21:59:50 -!- lambdabot has joined.
22:01:27 -!- MoALTz__ has quit (Quit: Leaving).
22:01:40 -!- MoALTz has joined.
22:05:24 -!- nooodl_ has quit (Quit: Ik ga weg).
22:15:17 -!- boily has quit (Quit: UNCLEAN CHICKEN).
22:38:29 <kmc> wish lambdabot would rejoin ##crypto
22:39:08 <elliott> int-e: you should add kmc to online.rc
22:40:28 <kmc> what's online.rc
22:41:01 <elliott> the file of commands lambdabot loads at startup
22:49:00 <shachaf> int-e: you should add shachaf to online.rc
22:49:34 <Taneb> elliott, could you make lambdabot join #cs-york?
22:50:18 -!- yorick has quit (Remote host closed the connection).
23:01:01 <Taneb> (elliott, that is the University of York computer science channel)
23:01:43 <elliott> you'll have to ask int-e for permanence, but sure
23:01:49 <elliott> it runs ghc not yhc though
23:02:01 -!- oerjan has quit (Quit: join ALL the channels).
23:02:59 <Taneb> And we are for some strange reason slowly working on a new York Haskell Compiler
23:03:30 <Taneb> Which of course is called the New York Haskell Compiler
23:12:08 -!- Sorella has quit (Ping timeout: 240 seconds).
23:14:03 -!- Sorella has joined.
23:33:29 <Taneb> TIL 5 ^ (4 ^ (3 ^ (2 ^ 1)))) is rather large
23:35:38 <kmc> `run python -c 'print 5 ^ (4 ^ (3 ^ (2 ^ 1))))'
23:35:39 <HackEgo> File "<string>", line 1 \ print 5 ^ (4 ^ (3 ^ (2 ^ 1)))) \ ^ \ SyntaxError: invalid syntax
23:35:46 <kmc> `run python -c 'print 5 ^ (4 ^ (3 ^ (2 ^ 1)))'
23:36:32 <Taneb> kmc, Python has the wrong definition of ^
23:37:08 <kmc> that'sthejoke
23:37:15 <kmc> also I just realized most lines of C code end with a sad face
23:37:24 <Taneb> Also I regret giving #cs-york lambdabot
23:37:31 <Taneb> Mostly I regret giving me lambdabot, though
23:38:06 <Taneb> <Sourceless> > foldl (+) [1..]
23:39:06 -!- Chiyo has joined.
23:39:42 <HackEgo> Chiyo: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/wiki/Main_Page>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
23:40:17 -!- Sprocklem has quit (Quit: Lost terminal).
23:40:50 -!- Sprocklem has joined.
23:40:54 <zzo38> Don't be too ineffective.
23:41:06 <elliott> `addquote <zzo38> Don't be too ineffective.
23:41:08 <HackEgo> 1181) <zzo38> Don't be too ineffective.
23:41:59 -!- Chiyo has left.
23:42:59 <elliott> I wonder what our user retention would be like without HackEgo.
23:43:30 <lexande> what was it like during the recent HackEgo downtime?
23:43:58 <shachaf> I think all the hello/welcome jokes are played out and were never a good idea for actually making newcomers feel welcome.
23:48:46 -!- Sorella_ has quit (Quit: It is tiem!).
23:52:23 -!- ^v has quit (Ping timeout: 252 seconds).
23:54:21 -!- ^v has joined.
23:59:44 -!- nisstyre has joined.
23:59:45 -!- nisstyre has quit (Changing host).
23:59:46 -!- nisstyre has joined.
00:02:29 <kmc> we need to A/B-test that shit
00:02:39 <kmc> who wants the title of #esoteric growth hacker
00:03:08 <HackEgo> rm: cannot remove `bin/*elcom*': No such file or directory
00:03:49 -!- tertu has joined.
00:04:05 <Bike> for a/b testing we're gonna need two hack egos, and which one a given person commands has to be random
00:05:10 <kmc> two hacks ego
00:23:12 -!- Phantom_Hoover has quit (Quit: Leaving).
00:33:59 -!- Sgeo has joined.
00:36:21 <Sgeo> `homestarrunnerlist
00:36:22 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: homestarrunnerlist: not found
00:38:50 <HackEgo> battscoin exedcoin anicecoin metalcoin toucoin lcourbelcoin rocumcoin mannahcoin this=thagoncoin mercoin epicoin sootcoin entectncoin smarcoin shwhaltritcoin madrainfucker)coin attacoin befuncorcoin reraturcoin smncoin
00:41:29 -!- shikhout has joined.
00:44:27 -!- shikhin has quit (Ping timeout: 255 seconds).
00:44:33 -!- shikhout has changed nick to shikhin.
01:17:23 -!- shikhin has quit (Remote host closed the connection).
01:23:01 -!- ^v has quit (Read error: Connection reset by peer).
01:23:29 -!- ^v has joined.
02:40:10 -!- xpte has joined.
02:42:14 -!- Sorella has quit (Quit: It is tiem!).
02:57:47 -!- darwin has joined.
02:57:50 -!- darwin has left ("Leaving").
02:58:35 -!- darwin has joined.
02:58:48 -!- darwin has left ("Leaving").
03:43:11 <HackEgo> timinuschecoin watecoin haffe7coin enamoucaleverixcoin sbancoin grofcoin nicecoin braintegdcoin nyboxcoin infalcatcoin ctorcoin laziacoin bf-rlecoin frackcoin thumbercoin elogiccoin loadcoin shructioncoin domcoin supecoin
03:43:54 <ion> `run cat /home/hackbot/hackbot.hg/multibot_cmds/lib/limits
03:43:54 <HackEgo> #!/bin/bash \ ulimit -f 10240 \ ulimit -l 0 \ ulimit -u 128 \ exec -- "$@"
03:46:09 <kmc> `dis86 4daf5f1e95
03:46:09 <HackEgo> scasq; pop rdi; invalid; xchg ebp, eax;
04:04:06 <Sgeo> Does... sdelete not like me trying to delete directories that ... have files?
04:09:24 -!- conehead has quit (Quit: Computer has gone to sleep).
04:18:36 <Bike> `run file $(which dis86)
04:18:37 <HackEgo> /hackenv/bin/dis86: ASCII text
04:18:48 <Bike> `cat /hackenv/bin/dis86
04:18:48 <HackEgo> bin="$1"; shift; unhex "$bin" | udcli -noff -nohex -64 "$@" | perl -pe 's/^ *//; s/ *\n/; /;'
04:38:35 -!- conehead has joined.
05:09:42 -!- tromp_ has quit (Remote host closed the connection).
05:10:18 -!- tromp has joined.
05:14:27 -!- tromp has quit (Ping timeout: 255 seconds).
05:29:33 -!- conehead has quit (Quit: Computer has gone to sleep).
05:32:02 -!- tertu has quit (Ping timeout: 246 seconds).
05:42:37 <kmc> `cat /hackenv/bin/as86
05:42:38 <HackEgo> as="$1"; shift; echo ".intel_syntax noprefix; $as" | gcc "$@" -c -x assembler /dev/stdin -o /tmp/as86.o && objcopy -O binary /tmp/as86.{o,bin} && xxd -p /tmp/as86.bin
05:44:33 <Jafet> Love the hardcoded tmpnams
05:45:16 -!- password2 has joined.
05:48:02 <kmc> `run as86 ret & as86 nop; wait
05:48:42 <kmc> aha i got a c3 \ c3 after some tries
05:49:22 <Jafet> `run for i in `seq 8 15`; do as86 r$i &; done; wait
05:49:23 <HackEgo> bash: -c: line 0: syntax error near unexpected token `;' \ bash: -c: line 0: `for i in `seq 8 15`; do as86 r$i &; done; wait'
05:51:20 <Jafet> `run for i in `seq 8 15`; do (as86 r$i &); done; wait
05:51:21 <HackEgo> /dev/stdin: Assembler messages: \ /dev/stdin:1: Error: no such instruction: `r12' \ /dev/stdin: Assembler messages: \ /dev/stdin:1: Error: no such instruction: `r11'
05:51:38 <Jafet> `run for i in `seq 8 15`; do (as86 'push r'$i &); done; wait
05:51:39 <HackEgo> objcopy: error: the input file '/tmp/as86.o' is empty
05:51:56 <Jafet> Also awesome bash syntax
05:52:47 <kmc> i think "& done" will also work
05:52:49 <fizzie> You don't need a subshell; for ...; do foo & done is valid.
06:01:31 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:03:20 -!- olsner has joined.
06:05:01 <ion> I just lost the game.
06:05:54 <kmc> yeah, that one
06:08:55 -!- password2 has quit (Ping timeout: 264 seconds).
06:11:19 -!- nisstyre has joined.
06:25:33 -!- password2 has joined.
07:13:22 -!- EgoBot has quit (Ping timeout: 265 seconds).
07:13:54 -!- EgoBot has joined.
07:24:52 -!- Sprocklem has quit (Quit: leaving).
07:29:30 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
07:37:41 -!- S1 has joined.
07:38:19 <HackEgo> fractioncarandrijcoin ortacoin minicoin braincoin singtoniimtitiicoin easepolicoin highcoin bracoin brackcoin shakencalcoin minecoin starcoin timicoin eplieycoin smucoin easepolcoin concacoin filosophycoin ortcoin 0x25coin
08:06:34 <Sgeo> So, the three big Haskell frameworks are each moving to use different streaming solutions
08:06:38 <Sgeo> *web frameworks
08:07:53 <kmc> what do you mean by streaming solutions
08:09:10 <Sgeo> conduits/pipes/io-streams
08:09:45 <kmc> unfortunate that the haskell community has still not converged on one of those
08:09:59 <kmc> haskell has lots of ecosystem fragmentation
08:10:09 <kmc> or whatever the hell you would call that
08:15:15 -!- Tritonio has joined.
08:29:16 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
08:30:24 <Sgeo> http://jaspervdj.be/posts/2013-10-22-websockets-0.8.html
08:30:29 <Sgeo> Interesting appendix
08:31:03 <Sgeo> (essentially: wondering if io-streams may be better for libraries as a lower-level thing that may work well with higher-level things like conduits and pipes, I think)
08:33:11 -!- Frooxius has quit (Read error: Connection reset by peer).
08:35:39 -!- Frooxius has joined.
08:37:21 -!- oerjan has joined.
08:43:51 <olsner> hmm, if I'm reading this right rust emits a stack check using TLS at the start of every function, and this can't be disabled because something about memory safety
08:44:16 <olsner> or maybe it can, but I'm reading the wrong series of closed bugs
08:51:14 <olsner> (that the stack check is 37 extra bytes for every function is great too)
08:51:59 -!- olsner has quit (Quit: Leaving).
10:00:40 -!- yorick has joined.
10:16:38 -!- boily has joined.
10:52:18 -!- maurer has quit (Ping timeout: 240 seconds).
10:53:25 -!- maurer has joined.
11:02:11 -!- boily has quit (Quit: Poulet!).
11:44:21 -!- MindlessDrone has joined.
12:18:48 -!- oerjan has quit (Quit: leaving).
12:35:04 <Jafet> Is it wrong to be amused at the name of Ludwig Bieberbach
12:50:09 <quintopia> i was going to add another line to that, but I can Nazi a way to make it rhyme
12:51:25 <quintopia> but yeah, no one was as schlicht as that guy
13:00:12 -!- spiette has joined.
13:01:21 -!- xpte has quit (Quit: Connection closed for inactivity).
13:06:12 <int-e> kmc: I had an explicit request (from mm_freak) for removing lambdabot from ##crypto. Can you please sort this out? I don't want to be part of that fight.
13:07:42 -!- Sgeo has quit (Read error: Connection reset by peer).
13:18:17 -!- spiette has quit (Ping timeout: 265 seconds).
13:27:44 -!- spiette has joined.
13:28:05 -!- `^_^v has quit (Quit: This computer has gone to sleep).
13:29:21 -!- `^_^v has joined.
13:50:11 <elliott> does it collide with an existing prefix there or something?
13:51:01 <elliott> according to chanserv, kmc is an op of ##crypto and mm_freak is not
13:53:02 <Jafet> I wonder if they discuss actual cryptography there now
13:53:29 -!- Giannos_Gr has joined.
13:53:43 <int-e> elliott: I want to avoid going back and forth on this.
13:54:00 <elliott> ok, I don't know if there's history or anything, just providing data
13:54:18 <int-e> yes, I appreciate that
13:55:03 <elliott> residual #haskell-ops instincts :)
13:59:47 -!- Giannos_Gr has left.
14:34:14 -!- TodPunk has quit (Ping timeout: 265 seconds).
15:02:22 -!- xpte has joined.
15:07:20 -!- TodPunk has joined.
15:08:32 * int-e ponders "<Taneb> Also I regret giving #cs-york lambdabot"
15:18:46 <Taneb> int-e, lambdabot's been kicked now
15:52:26 -!- Phantom_Hoover has joined.
16:03:58 <Taneb> And now I am doing scary Python programming
16:04:30 <Taneb> (for one reason or another I'm restricted to one file and it's up to 500 lines)
16:23:00 <Jafet> Make sure to use as many different classes as you can
16:23:11 <Jafet> It enhances maintainability
16:27:42 <Jafet> Ok when did applybot break 1500 lines
16:27:53 <Jafet> I don't remember this happening
16:33:32 <coppro> Jafet: Ludwig Bieberbach doesn't make much sense to me.
16:33:44 <coppro> would be funnier to combine only one classical composer with bieber
16:37:02 <Jafet> I was going to say that Bach was not a classical composer, but forgot about Carl
16:38:36 -!- Tritonio has quit (Ping timeout: 252 seconds).
16:40:27 <Jafet> I've heard a theory that python is a good language because you can write ~10^3 lines in it before your code becomes unmaintainable, compared to perl where it's ~10^2 lines
16:48:21 <Phantom_Hoover> <Taneb> (for one reason or another I'm restricted to one file and it's up to 500 lines)
16:48:52 <Taneb> Phantom_Hoover, I'm writing it with someone who insists max 80 characters
16:49:47 <Taneb> This is Python, not Perl
16:49:50 <newsham> jafet: "unmaintainable" is a strong word.
16:50:19 <newsham> python code is pretty maintainable even at scale.. but you just have lots of low hanging bugs that arent easily shaken out by a type checker.
16:50:53 <newsham> also 10^3 and 10^2 are harder to type than 1000 and 100 :)
16:53:08 <Jafet> In this context, 10^3 does not mean the same thing as 1000.
16:55:24 <Jafet> ~10^3 implies a range somewhere between 10^2 and 10^4. ~1000 implies a range somewhere between a few hundred and 2000.
16:56:34 <quintopia> when i see ~10^3 i think "3 digits"
16:57:39 <Jafet> Personally, I have not seen good python code past 10^3 lines or so. There is little documentation (docstrings don't count), no type system, and no confidence that anything that is documented does work as documented
16:58:15 <Jafet> Then I refer to the source code and it invariably looks like java without the type checking.
16:59:11 <newsham> perhaps you should read more python code?
16:59:55 <newsham> how about https://github.com/trevp/tlslite ?
17:00:59 <Jafet> Why should I read that?
17:02:51 <Jafet> Reading a TLS stack written in python doesn't sound very enjoyful.
17:03:20 <Jafet> I would guess that the authors derived enjoyment from writing it.
17:05:43 <newsham> mind you most my published python codeis around 500loc, beautiful, bug free, and well documented ;-)
17:07:08 <Jafet> They don't seem to have negative tests, though this isn't that surprising any more.
17:08:03 -!- ^v has joined.
17:09:11 <kmc> int-e: sigh, then it stays out of ##crypto I guess
17:11:00 <kmc> <int-e> kmc: I had an explicit request (from mm_freak) for removing lambdabot from ##crypto. Can you please sort this out? I don't want to be part of that fight.
17:12:05 <kmc> i don't care that much if lambdabot is in ##crypto
17:14:35 <newsham> > -- because it might conflict with another bot?
17:14:36 <lambdabot> not an expression: `-- because it might conflict with another bot?'
17:15:45 <newsham> also she is no longer a vixen
17:17:54 <kmc> haha this again
17:17:58 <kmc> newsham: I think it's good
17:18:12 <kmc> well mm_freak kickbanned lambdabot when he left the channel
17:18:33 <lambdabot> I don't want to see this country to go that way. You know what happened to the Greeks. Homosexuality destroyed them. Sure, Aristotle was a homo, we all know that, so was Socrates.
17:18:46 <newsham> is it just doing random quotes for vixen now?
17:18:53 <kmc> vixen -> nixon
17:19:03 <lambdabot> Don't put all your ducks in one barrel.
17:19:27 <kmc> mm_freak left because of my "anti-haskell crusade" wherein I claim that Haskell is a capable, practical programming language rather than a perfect object of mathematical beauty which will solve all of humanity's problems
17:19:46 <elliott> wait, why is mm_freak involved in whether lambdabot is in ##crypto if he is not in the channel?
17:19:51 <newsham> a little birdy told me that haskell is not math.
17:19:56 <kmc> beats me elliott
17:20:10 <newsham> its funny that all the programmers think haskell is math, and all the math people think it is not.
17:20:19 <zzo38> I am sure it won't solve all of humanity's (or anyone else's) problems, any more than, another programming language
17:20:25 <kmc> on the (substantial) list of interpersonal drama I can get involved with, this has a pretty fucking low priority
17:20:52 <kmc> newsham: well I'm a programmer and I don't think Haskell is math, although it obviously has connections to math, as do other programming langugaes or most things really
17:20:52 <newsham> zzo38: not until it can be compiled to javascript, at least. ;-)
17:21:33 <kmc> newsham: I think it's funny how Haskell detractors and Haskell zealots believe the same set of falsehoods about the language
17:21:34 <zzo38> newsham: Compiling it to JavaScript isn't really all that good either, but at least it is another possible target.
17:22:00 <newsham> zzo38: javascript is for solving the worlds problems!@#
17:22:03 <kmc> most recently mm_freak was trying to claim that GHC Haskell doesn't have shared-memory concurrency
17:22:05 <zzo38> Haskell has a lot of mathematical stuff on it but only computable (or partially computable) and it can't be ideal like mathematics can be, any more than any other computer program can be !
17:22:18 <zzo38> newsham: No it can't solve the world's problems very well either!
17:22:43 <newsham> zzo38: sure it can! see the facebooks! and the tweets! and the goog pluses!@#!@#
17:22:44 <kmc> because someone else was talking about how Rust doesn't have shared memory concurrency, and that this is a good thing, and if another language has a good thing then Haskell obviously has it but better, never mind what the facts are
17:23:03 <kmc> (not really true that Rust doesn't have shared-memory concurrency, either, but more true than for GHC Haskell)
17:23:05 <lambdabot> ghc need to have plugin that allow copy paste in xp
17:23:31 <zzo38> newsham: O, it is bad because Hitler did it.
17:24:23 <elliott> I mean I don't really want #esoteric to be feud central, I was just confused.
17:25:17 -!- olsner has joined.
17:26:23 <int-e> elliott: it's an interesting bit of information.
17:27:28 <int-e> kmc: I can easily add ##crypto back; the real question is whether it annoys people on the channel or not.
17:28:21 <kmc> also it is there at the moment
17:28:38 <kmc> the entirety of what's been said about lambdabot since lambdabot rejoined is
17:28:39 <kmc> 15:38 -!- lambdabot [~lambdabot@silicon.int-e.eu] has joined ##crypto
17:28:39 <kmc> 15:40 < kmc> lambdabot: welcome back!
17:28:39 <kmc> 15:41 < sarnold> lambdabot: botsnack!
17:29:48 <elliott> I could understand if the channel had hate speech or whatever, but this seems like deliberate troublemaking.
17:30:29 <elliott> I mean, trying to get lambdabot out of a channel you're not in
17:30:53 <kmc> he used to be an op there, but not anymore I guess
17:31:17 <int-e> That was a month ago. I dunno.
17:31:38 <kmc> yeah so it happened when he quit the channel
17:39:06 <lexande> is math a perfect object of mathematical beauty which will solve all of humanity's problems?
17:39:17 <lexande> maybe in some vacuous sense
17:39:25 <lexande> but maybe it can only have metamathematical beauty
17:40:28 <int-e> lexande: you can define the can of beans as open. this easily generalizes to larger real world problems.
17:42:49 <zzo38> Don't expect, that humanity is the only thing having a problem, and that furthermore, one thing can solve all of them. Both things are impossible...
17:43:11 <Bike> way to be anti-haskell zzo
17:43:33 <int-e> . o O ( humanity is part of the problem space )
17:44:22 <Bike> if you're not part of the solution you're part of the noxious acidic gas rising from it
17:44:44 <olsner> is that the precipitate?
17:49:17 <lexande> i think that's a precipitate
17:53:31 <Jafet> Acidic precipitation
17:57:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
17:58:09 <newsham> math can solve humanities problems. most notably subtraction of certain people and addition of others.
17:59:45 -!- oerjan has joined.
18:02:03 <Jafet> What about multiplication
18:02:33 <newsham> multiplication has lead to a lot of problems, but does underly a lot of our current economic strategies
18:04:23 <quintopia> george washington has warned us about division, however
18:05:21 <newsham> but only after he divided the british empire. so perhaps he didnt mean it generally
18:05:45 <quintopia> lexande: i belief math, to the extent it is economics, has the potential to solve a lot more problems than "social consciousness"
18:06:37 <newsham> unfortunately a lot of economics is based on math that is untethered from any physical reality.
18:06:53 <newsham> maybe someday we'll figure out how to fix that
18:07:22 <quintopia> economics is a relatively young field of study
18:07:35 <Jafet> There seems to be this bizarre popular misconception that if you generate a probable prime and it turns out to be not actually prime, your cryptosystem will instantly break
18:08:41 <Jafet> (#programmersarestoopid)
18:09:09 <quintopia> "psychology" has now gone two directions: there's cognitive neuroscience, which is where neuroscience met computer science, and there's economics, which is what behaviorism has evolved into.
18:10:22 <quintopia> Jafet: if your composite "probable prime" has lots of small factors, then any data encrypted with it is definitely insecure
18:11:45 <newsham> though i'm pretty sure crypto libs do a sieve against small primes after generation
18:12:30 <int-e> it's also very unlikely that it will qualify as a probable prime.
18:13:08 <newsham> but you know.. when 1/2^100 eventually happens, you wanna be safe ;-)
18:13:11 <quintopia> it's very unlikely that any composite will...that's the whole point
18:13:55 <quintopia> i wish they'd just hurry up and prove the riemann hypothesis already so we can have the dang miller test
18:14:14 <int-e> when the probability is lower than that of a hardware failure, that may be a good point to stop worrying.
18:14:54 <quintopia> i've had enough hardware failures in my life to keep worrying
18:15:48 * Bike vomits all over the channel
18:16:07 <int-e> quintopia: I meant to stop worrying about the primality of the probably prime and start worrying about hardware failures instead.
18:16:15 <Bike> stop saying things like economics evolving out of behaviorism then!
18:17:05 * int-e agrees with Bike there; just because there is an overlap (once you give up the "rational agent" simplification doesn't mean one evolved into the other)
18:17:39 <Jafet> The thing that people don't get is that if there was any cryptosystem that would break if you handed it a fake prime, you would instantly get a primality test
18:17:58 <int-e> well, primality is in P
18:18:14 <Bike> there's nothing much to say, i don't know where the hell you get your idea of psychology and its history but what you're saying has nothing to do with reality
18:18:17 <Bike> anyawy https://twitter.com/BuzzFeedAndrew/status/451410960519938048/photo/1
18:19:54 <int-e> twitter makes those URLs useless without javascript.
18:20:03 <quintopia> Bike: have you looked at economics research lately? it bares little resemblance to what it was back before modern psychology. that old-school stuff has been shoved aside (not completely...there's room for everyone i guess)
18:20:35 <Bike> that doesn't mean psychologists started becoming economists!
18:21:06 <Jafet> Shoved into schools
18:21:18 <Bike> that's what you said. "psychology" has now gone two directions...
18:21:35 <Bike> also, plenty of economic research is unrelated to the psychological states of actors.
18:21:38 <quintopia> more the other way around really. or maybe more like people who decided to become "economists" lately end up looking more like psychologists of old
18:22:17 <quintopia> i didn't say ALL of economics was subsumed by psychology
18:22:38 <quintopia> you are extrapolating way too much in the wrong directions
18:23:04 <zzo38> I read somewhere, someone who said, astrology is no good, and psychology is even worse.
18:23:13 <quintopia> in tracking philosophies and paradigms through time, it makes sense to say that many of those originating in psychology are now held by those calling themselves economists
18:23:37 <Bike> you said "that old-school stuff has been shoved aside" and the thing you said earlier pretty clearly looked like psychologists became x
18:23:59 <quintopia> i never used the word psychologists
18:24:20 <int-e> zzo38: Well, messing with people's heads works. It's much harder to influence the trajectories of planets.
18:24:35 <quintopia> and if something i say can be misinterpreted to your dislike, please ask what i mean before vomiting on me
18:25:41 <Bike> you said "psychology". i don't think i'm being weird by interpreting «"psychology" has now gone two directions» as meaning psychology became something.
18:26:05 <Bike> i'm more vomiting because it sure looks like the channel is doing this thing where computer nerds start talking shit about soft sciences they don't know anything about.
18:26:26 <quintopia> humans evolved from primates, but we're not the only primates. psychology has become more than two things, but i'm only concerned with two of them here
18:26:54 <elliott> oh come on, you're loopholing, there is no way your statement can be reasonably interpreted that way
18:27:55 <quintopia> elliott: but why would you even think that i was talking about clinical psychology or abnormal psychology or all that stuff? do i have to add a whole long list of qualifications to every damn thing i say?
18:28:45 <quintopia> i mispoke, but that doesn't mean you need to go accusing me of holding beliefs i don't hold
18:28:45 <int-e> because "psychology" encompasses all of those
18:28:58 <elliott> no, but saying things that clearly strongly imply something and then getting pedantic when someone disagrees with it just makes you really annoying to talk to...
18:29:04 <elliott> I should know because I used to do it constantly.
18:29:21 <elliott> it's permitted to just say you misspoke and take it back.
18:29:51 <quintopia> i'm not trying to get pedantic here. i'm trying to clarify. i know what i mean, but i don't know how to put it across so that i'm not misinterpreted
18:30:32 <Bike> "modern economics has a lot more psychological realism than it used to"
18:31:09 <quintopia> that works for part of it i suppose
18:31:28 <Bike> well what's the other part. what's the cognitive neuroscience thing even mean
18:32:57 -!- spiette has quit (Ping timeout: 265 seconds).
18:34:07 <quintopia> well that part you rephrased was supposed to convey more about economics adopting the principles of behaviorism, looking at what people actually do and treating them sort of like black boxes. (which is to say, they haven't quite gotten to the point of using actual neuroscience in their models)
18:35:09 <quintopia> and the other part means exactly what it says. cognitive neuroscience combines behavioral psychology with neuroscience with computer science models and other things
18:38:35 <Bike> so i'm supposed to interpret half of the sentence as meaning 'economics incorporated psychology' and the other half as 'psychology became cognitive neuroscience'?
18:39:53 <Bike> or am i supposed to interpret them both as meaning something incorporated psychology, despite cognitive neuroscience not being mentioned before and seeming kind of random, or what. i'm confused
18:42:29 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:44:03 <quintopia> Bike: if you are having trouble interpreting my original statement, you should forget i ever said it, and ask about the things i said afterwards instead
18:44:22 -!- spiette has joined.
18:48:20 <Bike> how about before, can i complain about whatever weird thing you were complaining about as 'social consciousness'
18:49:24 <quintopia> that wasn't a complaint, but commentary on its inherent ephemerality. i don't think it's a bad thing to have, just that it won't stand throughout time.
18:53:54 <Phantom_Hoover> http://www.reddit.com/r/math/comments/21zdln/the_common_core_is_corrupting_school_mathematics/ holy shit this is awful
18:54:19 <Phantom_Hoover> http://i.imgur.com/0TDJAcR.jpg i mean for christ's sake the 'new' way is the way i learnt multiplication, it's far more sensible than the 'old' one
18:55:48 <Bike> um is this a j- right.
18:56:12 <Phantom_Hoover> i was confused on account of the fact that when it was posted it was 4 in the morning of april 2 when i saw it?
18:56:37 <Bike> «You heard it here first from the Reform Math lobby: the "easy" way to divide is using a square root.»
18:56:53 <oklopol> i wonder if that guy really has a phd in math
18:57:27 <Bike> http://imgur.com/cYBLWpZ hahaha
18:58:03 <Bike> "This was a simple, straightforward process that required only basic fraction sense, understanding of whole-number addition, and a first-semester course in undergraduate number theory."
18:58:47 <Bike> «The Common Core is introducing all of this "problem solving" that relies on sudden insight and creative thinking and getting math away from what children should be doing: learning to operate on numbers according to pre-specified routines and instructions to produce a simple numerical output - you know, the sort of work that will position our kids for jobs that will exist well into the 21st century.» this is a good post
19:03:10 <olsner> to be fair, it looks like both methods did give the same answer, just written differently
19:03:14 <kmc> I realized that Rust Objective-C bindings could support syntax like let string = objc![[NSString alloc] initWithCString: "Hello,
19:03:38 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
19:03:48 <Bike> olsner: part of the joke is the writer not knowing anything yeah
19:03:58 <Bike> kmc: is the newline intentional
19:04:12 -!- w00tles has joined.
19:04:31 <olsner> Objective-Rust, sounds great
19:04:38 <kmc> I'm just saying you can shoehorn Objective C method call syntax into Rust as a macro, which is pretty amusing
19:04:44 <kmc> olsner: yep yep
19:05:05 <quintopia> Bike: completing the square really is quite easy, and it is, in fact, the first method ever discovered to solve such problems, as well as the method by which the quadratic formula is derived. i definitely prefer it to the quadratic formula (but not to factoring if the problem is reducible)
19:05:55 <olsner> btw, I found the magic attribute to disable the ridiculous stack check, but it seems to be a *function* attribute
19:06:12 <Bike> completing the square is fine but that's not what the image is doing, is it?
19:06:45 <kmc> olsner: that's right
19:06:57 <Bike> if you wanted to complete the square you'd add, uh... 5/2 or something? man it's been too long -_-
19:07:15 <kmc> olsner: I don't think it's ridiculous; stack overflow would be a memory saftey violation
19:07:38 <kmc> but there should be better tools for turning off the check, and also it should probably use a guard page instead for functions with a stack frame smaller than one page
19:08:03 <Bike> oh is it 25/4 you add
19:08:13 <Bike> and that gives you (x + 5/2)², right
19:09:10 <Bike> as for the quadratic formula it's useful for whenever i want to solve a quadratic based on empirical data, because completing the square of 2.7x² + 5.3819x sounds p. annoying
19:09:23 <Bike> (in actuality i make the computer do it but w/e)
19:09:23 <quintopia> Bike: look near the end of the one he solved there. he adds 25/4 to both sides. it's completing the square...encrypted :P
19:09:28 <kmc> olsner: there are real-world examples of exploiting stack overflow in C programs for arbitrary code execution
19:09:38 <kmc> that's the kind of thing Rust is supposed to prevent absolutely, modulo unsafe code
19:09:55 <kmc> in practice it can't catch stack overflow in C code called from Rust code, unless the C was specially compiled
19:10:27 <Bike> having students derive the quadratic formula from square-completion would be nice for sure, i don't rmeember doing that in class
19:10:34 <quintopia> Bike: but i like his method too. it still requires less memorization than the quadratic formula, and more number sense as well :D
19:10:36 <Bike> "and then, you can jump into galois theory"
19:10:41 <fizzie> @tell Vorpal You've seen most of these already, but here they are all grouped together: http://zem.fi/2014-04-02-tl2
19:10:55 <Bike> quintopia: i'm honestly not sure i get where the substitution comes from
19:11:43 <quintopia> Bike: the substitution will always be (x+b/2)=u
19:12:08 <Bike> i think i'd rather complete the square
19:13:19 <quintopia> however, students who plan on eventually taking calculus might benefit from being able to make substitutions like tht
19:13:31 <quintopia> it also makes some trig identities a lot easier to solve
19:14:21 <Bike> for trig identities they oughta just teach euler's formula.
19:14:36 <Bike> the fact i iddn't learn it in high school is one of my great griefs against the educational system
19:16:02 <Taneb> Oooh! Today I ate a burrito
19:16:11 <Jafet> Schools teach integrals the same way that the reddit post teaches substitutions. You grab a magic term and substitute it for u and somehow it all works
19:16:31 <kmc> Taneb: congratulations
19:16:34 <kmc> what was in it?
19:16:37 <Bike> i'm still bad at integral substitutions
19:16:59 <olsner> Taneb: did it make you think about monads?
19:17:14 <Jafet> I actually don't care that I can't evaluate any integrals because I know you can write arbitrarily hard problems as integrals
19:17:17 <Taneb> Other than the "this is not much like a monad"
19:17:37 <Jafet> Try eating it in a spacesuit
19:17:41 <kmc> ceci n'est pas une monad
19:19:04 <quintopia> Bike: yes. i bet they also didn't teach you the geometric intuition for all of the trig functions, which i find /more/ useful than the complex analysis connection
19:19:19 <Taneb> I'm a little worried as the only player whose character is aligned good in my D&D party
19:19:53 <Taneb> We're going to bring down a major bank. At level 2.
19:20:33 <Jafet> Why not start a D&D hedge trading guild
19:21:35 <Taneb> Jafet, that's part of the plan
19:21:55 <Taneb> We're only doing this because one of the characters owes the bank money
19:23:34 <kmc> apparently GNU C has destructors: http://gcc.gnu.org/onlinedocs/gcc/Variable-Attributes.html#index-g_t_0040code_007bcleanup_007d-attribute-3022
19:27:19 -!- Tritonio has joined.
19:28:51 <fizzie> It also has a "destructor" function attribute to complement "constructor", but that's different.
19:30:27 <kmc> those run when an object file is loaded/unloaded right?
19:30:58 <kmc> I once did a "return to libdl" attack where the payload was in a constructor function
19:32:30 <fizzie> It says "after main () completes or exit () is called". I'm not entirely certain on what happens if you have a destructor function in a shared object that is dlclose'd.
19:32:49 -!- augur_ has quit (Remote host closed the connection).
19:32:50 <fizzie> "Destructor routines are executed before dlclose() returns" okay, that.
19:35:50 <fizzie> Something I once idly wondered but didn't take the time to find out: if you put an __attribute__ ((constructor)) function in a .so, will that get run based on an ELF dynamic section DT_INIT entry?
19:36:20 <oerjan> ( the Int (10 `xor` 3)
19:36:20 <idris-ircslave> (input):1:5:When elaborating argument x to function Prelude.Basics.the:
19:36:48 <oerjan> ( the (Bits 16) (10 `xor` 3)
19:37:28 <oerjan> ok wtf don't they have a Num instance for that
19:37:52 -!- nooodl has joined.
19:39:52 <elliott> because would it be big or little endian, for one?
19:40:22 <elliott> what are the constructors?
19:40:33 <oerjan> that's what i was trying to find with :info
19:40:54 <oerjan> but i must have misremembered the command
19:42:39 <lambdabot> <hint>:1:1: parse error on input `:'
19:44:27 <zzo38> I have not recently played the Dungeons&Dragons, but may be able to, this week, however.
19:44:51 <Taneb> I won't be able to until after Easter
19:44:53 <zzo38> I don't expect to ever need to take down any bank.
19:45:15 <Taneb> As I play it with friends at uni and it's the Easter holiday at the moment
19:45:20 <Taneb> So we're all spread all voer
19:49:20 <zzo38> There are currently no other player characters, in the game I am playing.
19:50:10 <zzo38> (Which means, that our best fighter is gone, making it more difficult in the situation where combat becomes necessary or especially helpful, but so far we have been able to do stuff without much of that anyways)
19:55:33 <Melvar> ( the (Bits 16) (cast 10 `xor` cast 3)
19:57:54 -!- augur has joined.
19:58:12 <oerjan> just make Num a superclass of Cast Integer and make fromInteger a synonym for cast, i guess
20:00:38 <oerjan> ( the (Bits 16) MkBits (-1)
20:00:38 <idris-ircslave> (input):1:5:When elaborating argument x to function Prelude.Basics.the:
20:00:38 <idris-ircslave> (machineTy (nextPow2 (case block in divCeil n 8 (Prelude.Nat.modNat, mod' n 7 n n 7)))) -> Bits n
20:01:06 <oerjan> ( the (Bits 16) (MkBits (-1))
20:01:06 <idris-ircslave> When elaborating argument x to function Prelude.Basics.the:
20:01:14 <Bike> bits doesn't include two's comp? :(
20:01:46 <idris-ircslave> Data.Bits.MkBits : (machineTy (nextPow2 (case block in divCeil n 8 (Prelude.Nat.modNat, mod' n 7 n n 7)))) -> Bits n
20:01:46 <oerjan> ( the (Bits 16) (cast (-1))
20:02:15 <oerjan> Bike: MkBits is a constructor, so presumably it can't do canonicalization
20:03:19 <Bike> wow that's a scary type
20:03:21 <Melvar> The thing is actually that the function to compute what type you pass to MkBits is private to Data.Bits.
20:04:22 <nooodl> mmmm http://en.wikipedia.org/wiki/Dynamic_programming#History
20:04:39 <nooodl> dynamic programming called dynamic programming because: that sounded cool
20:04:44 <Melvar> So you get a nosuchvariable when trying to apply MkBits.
20:05:08 <Bike> "and because it sounded impressive" my life
20:14:38 <Bike> here's kind of a neat thing https://www.crowdsupply.com/kosagi/novena-open-laptop
20:16:06 <Melvar> ( the (Bits 12) (cast (-1))
20:17:41 <oerjan> clearly Bits should take a transfinite ordinal instead of just a Nat
20:20:20 <Melvar> Currently, it doesn’t even go over 64 bits.
20:21:04 <Melvar> ( (Bits8, Bits16, Bits32, Bits64)
20:21:05 <idris-ircslave> (Bits8, Bits16, Bits32, Bits64) : (Type, Type, Type, Type)
20:21:48 <Melvar> It just wraps one of these primitives according to its parameter.
20:22:37 <Jafet> oerjan: we have an isabelle theory of arrays where the arrays are typeclass-constrained to be at most 8192 elements long
20:22:45 <Melvar> We also still don’t have well-supported bytearrays.
20:23:01 <Jafet> The typeclass is named something like fourThousand
20:29:16 -!- tertu has joined.
20:31:24 <elliott> Bike: why would they pick Debian if it's a purity thing...?
20:31:36 <elliott> I'd expect one of the GNU-approved distributions nobody knows about.
20:31:47 <Bike> i don't care, i just like fpgas >_>
20:31:49 <elliott> that said, I wonder if Stallman will buy one.
20:32:10 <Bike> course xilinx isn't exactly an open source paradigm either
20:32:31 <elliott> yeah... I guess there's no way to change what the FPGA runs without proprietary software
20:32:49 <elliott> so the open laptop gimmick is kinda silly, though I suppose you could just ignore the FPGA if it does nothing by default and is just an add-on? I dunno
20:33:08 <Jafet> Laptops are a lost cause
20:33:31 <elliott> well, it's not exactly a laptop
20:33:48 <elliott> the case literally comes open when you lift up the screen and it has no keyboard.
20:33:54 <elliott> but they call it a laptop.
20:34:22 <fizzie> (I don't know if that's current.)
20:34:47 <elliott> fizzie: yes, plus Trisquel, Dragora, BLAG, dynebolic, and some others I'm forgetting
20:35:06 <elliott> I forgot Musix, Parabola, and LibreWRT.
20:35:17 <Jafet> Why not fab your own CPU while you're at it
20:35:23 <elliott> and BLAG is no longer recommended, apparently?
20:36:07 <fizzie> Is LibreWRT an OpenWRT-kinda thing?
20:37:05 <elliott> http://librewrt.org/index.php?title=Main_Page yeah (dunno if it's based on OpenWRT)
20:37:54 <Bike> fiiiiine i'll just get a PCI FPGA somewhere ya nerds
20:38:28 <elliott> "Lets Free Your Ben Nanonote!" this is some weird Chinese pocket computer that ships with OpenWRT and it's still not enough for these people
20:38:53 <zzo38> If it has no keyboard, then it isn't very good
20:39:03 <fizzie> http://librewrt.org/index.php?title=Hardware_Support you can kind of notice the must-be-free constraints in the hardware support page.
20:40:08 <Jafet> "If you have a hardware that is free, in the sense that no proprietary software is required to run it"
20:42:47 <fizzie> Makes me wonder if their WZR-HP-G300NH firmware actually replaces all bootloaders and such on the device.
20:43:34 <Jafet> Probably hard to replace anything in ROM.
20:44:17 <zzo38> If I have a C code such as function_module_vtab*vt=*sqlite3_user_data(cxt); then it is error dereferencing (void*) but the compiler ought to figure it out in this case.
20:45:48 <fizzie> Soon you'll start asking for modern C++-style "auto" type inference features in C, too.
20:46:06 <elliott> fizzie: it might run a free bootloader out of the box
20:46:41 <Jafet> Even auto doesn't solve that; the right operand of = is not well-typed by itself.
20:47:59 <Jafet> You can, however, implement type inference by having sqlite3_user_data return a template with an operator* that returns a template that automatically converts to the correct contextual type
20:48:19 <Jafet> s/template/template class object unicorn/
20:48:23 -!- olsner has quit (Quit: Leaving).
20:48:41 <Jafet> Now I'm thinking about U-boat loaders
20:51:57 <fizzie> "SanDisk drive in the photos is a throw-away for our dev purposes only, we would not subject end users to such a drive" so much 'tude
20:53:23 <Jafet> Oversized SD cards
20:53:42 -!- password2 has quit (Ping timeout: 255 seconds).
20:54:24 -!- conehead has joined.
20:56:57 -!- augur has quit (Read error: Connection reset by peer).
20:57:06 <zzo38> Jafet: In this case it isn't even exactly a ordinary = operator; it is a declaration.
20:57:21 -!- augur has joined.
21:02:17 <Jafet> That is true, but having a special rule for initializers is odd.
21:04:52 <fizzie> They're already quite special, to be fair. Like, there's no analogue to aggregate initialization for assignment.
21:05:12 <Jafet> Maybe there should be.
21:06:08 <fizzie> Maybe you could make it support a multiple assignment thing while you're at it.
21:06:29 <fizzie> int a; struct { int x, y; } b; { a, b } = { 1, { 2, 3 } };
21:06:59 <Jafet> That's getting dangerously close to making C a usable language, and we should have none of that.
21:07:00 -!- tertu_ has joined.
21:07:35 <Jafet> Though, I wonder why C++11 didn't just add initializer_list literals. I don't see a grammatical conflict there.
21:07:59 <Jafet> (as exemplified by the existence of http://gcc.gnu.org/onlinedocs/gcc/Compound-Literals.html)
21:08:15 <fizzie> You could have int a, b; { a, b } = { b, a }; have undefined behavior -- like it naturally would -- to keep it sufficiently C-like.
21:08:51 -!- tertu has quit (Read error: Connection reset by peer).
21:10:19 <Jafet> The semantics should be easy to define, the left operand is treated as a temporary structure whose new contents are then assigned to a,b
21:11:12 <fizzie> No, that would Preclude Optimization Opportunities and would never do. Clearly the only thing is to consider that the same as "a = b, b = a" except without the sequence point implied by the comma operator.
21:12:06 <Jafet> Also another problem, people will then want their { any lvalue-expr, ... } = ...
21:12:08 <zzo38> Jafet: Why should we have none of making C a usable language?
21:12:47 <Jafet> On further thought, that may not actually be a big problem
21:13:43 <fizzie> It does make it somewhat hard to define the resulting type of that = expression. (Perhaps an untagged structure with the corresponding member types could do?)
21:14:19 <zzo38> However I think that thing like { a, b } = { 1, { 2, 3 } } isn't needed and shouldn't be have in C, anyways, unless you could do something like int a; int b; struct { int x; int y; } c; { a, b } = c; which would be slightly more meaningful, but probably that isn't needed either.
21:14:36 <Jafet> The conclusion I am compelled to draw from all this is that the following should be made legal C: {{a, b} = {b, a}, {b, *f(a, b)}} = {{b, a}, {a, b}}
21:15:22 <fizzie> Jafet: That would be p. weird, since the normal result of = is not an lvalue.
21:15:54 -!- Phantom_Hoover has joined.
21:16:02 <Jafet> Arrr, me seaplus be leakin'
21:16:50 <fizzie> I don't have any problems with e.g. {({a, b} = {b, a}, a), {b, *f(a, b)}} = {{b, a}, {a, b}} though.
21:17:15 <Jafet> Sad: "In C++, a compound literal designates a temporary object, which only lives until the end of its full-expression [...] As a result, the C++ compiler now rejects the conversion of a temporary array to a pointer."
21:17:25 <fizzie> (Er, assuming a is an aggregate type with at least two members to fix my thinko.)
21:17:44 <Jafet> Wonder if they will take a patch that makes you a std::array instead
21:17:52 <Bike> wait is *f(a,b) an lvalue
21:18:06 <Jafet> Of course, how else can you assign to it
21:18:11 <elliott> int x; int *f(int a, int b) { return &x; }
21:18:15 <Bike> isn't it a dereference of a function call
21:18:22 <elliott> no, it's a dereference of the result
21:18:29 <elliott> like int *p = f(a, b); *p = ...
21:18:40 <Jafet> Some pretty great macro libraries have been written this way
21:19:35 <Jafet> Well, a library which defines macros to dereferenced function calls
21:19:48 <fizzie> Where did I recently read something about a crafty lifetime difference between two things.
21:20:46 <fizzie> There should be some convenient way to run a full-text search on the subset of pages in browser history for the last couple of days.
21:20:50 <Jafet> There are some more pedestrian uses, like errno is usually a dereferenced function call that grabs the thread-local errno
21:20:53 -!- impomatic has quit (Ping timeout: 246 seconds).
21:22:00 <Bike> fizzie: i'm pretty sure you can do that in chrome?
21:22:54 <zzo38> fizzie: I think Mozilla uses SQLite, which includes full-text search. However, I do not know how to tell Mozilla to run SQL statements.
21:23:34 <fizzie> Bike: As far as I can tell, the "search history" button in (this) Chrome's history view only searches metadata like title and URL, not page contents.
21:24:07 <fizzie> (Also it won't show history for other devices than the local device if sync encryption is on.)
21:25:01 <Jafet> You can always hook up the sqlite command line utility to the mozilla database, once you figure out where they've moved the database files this week.
21:26:32 -!- impomatic has joined.
21:26:55 <Jafet> fizzie: is it the const& return values
21:28:00 <Jafet> http://herbsutter.com/2008/01/01/gotw-88-a-candidate-for-the-most-important-const
21:40:30 <fizzie> It wasn't that. I think it might've been something related to a macro.
22:00:01 -!- Tritonio has quit (Ping timeout: 240 seconds).
22:45:00 -!- zzo38 has quit (Remote host closed the connection).
22:47:00 -!- augur has quit (Remote host closed the connection).
22:47:34 -!- augur has joined.
22:51:51 -!- augur has quit (Ping timeout: 252 seconds).
23:00:25 -!- ^v has quit (Read error: Connection reset by peer).
23:00:54 -!- ^v has joined.
23:01:26 -!- oerjan has quit (Quit: leaving).
23:15:52 -!- yorick has quit (Remote host closed the connection).
23:18:24 <^v> Phantom_Hoover, he left :<
23:22:41 -!- Sgeo has joined.
23:33:42 -!- nooodl has quit (Quit: Ik ga weg).
23:39:14 -!- augur has joined.
23:40:22 -!- augur has quit (Remote host closed the connection).
23:42:08 -!- augur has joined.
23:56:30 -!- Koen_ has joined.
00:00:12 <lambdabot> shachaf says: Everyone forgets about Agda Lovelace, the first constructivist.
00:00:52 -!- nisstyre has joined.
00:05:26 -!- nisstyre has quit (Client Quit).
00:07:39 -!- w00tles has quit (Quit: quit).
00:15:28 -!- tromp has joined.
00:18:34 -!- Phantom_Hoover has quit (Quit: Leaving).
00:19:05 -!- Sorella has joined.
00:19:58 -!- Sorella has quit (Max SendQ exceeded).
00:21:17 -!- Sorella has joined.
00:29:55 -!- w00tles has joined.
00:35:37 -!- conehead has quit (Ping timeout: 240 seconds).
00:36:59 -!- conehead has joined.
01:01:31 -!- augur has quit (Remote host closed the connection).
01:13:45 <Bike> http://i.imgur.com/kJxqkZ6.png software licenses are important
01:16:39 <elliott> I hear IBM actually managed to get an exception to that license that allows them to use it for Evil too. (I'm not kidding, but the story may be false.)
01:16:54 <elliott> Crockford is dumb and his license is dumb though.
01:19:31 <Bike> http://dev.hasenj.org/post/3272592502/ibm-and-its-minions mmhm great
01:20:44 <elliott> I mean if you use Crockford's JSON code as it stands then you're completely open to him wasting a lot of your time and money by deciding you're using it for Evil and trying to get you legally for it.
01:21:07 <elliott> and since he's the kind of person to put a clause like that in a license, it's not really convincing to just assume he won't be obnoxious enough to.
01:21:21 <Bike> the point is, someone not a programmer linked me to this and there's nothing to do but laugh
01:22:50 -!- tromp has quit (Remote host closed the connection).
01:23:23 -!- tromp has joined.
01:26:15 -!- tromp has quit (Read error: Operation timed out).
01:27:59 -!- Sprocklem has joined.
01:34:38 -!- Sorella has quit (Quit: It is tiem!).
01:50:27 <^v> "it has addition and subtraction, must be a brainfuck derivetive!"
01:50:52 <^v> ^ everyone who hasnt been to esolangs.org
01:52:28 -!- augur has joined.
01:52:30 -!- augur has quit (Remote host closed the connection).
01:52:37 -!- augur has joined.
01:53:33 -!- w00tles has quit (Quit: quit).
03:46:26 <ion> http://www.sewingandembroiderywarehouse.com/embtrb.htm
04:26:35 -!- nisstyre has joined.
04:31:50 <Sgeo> Since #haskell is ignoring me, should I just ask questions in here?
04:32:01 <Sgeo> (Or probably they just didn't see it or didn't know)
04:34:48 <Bike> ask now or forever hold your piece
04:36:12 <ion> Urinate now or forever hold your piss
04:41:37 -!- tromp has joined.
04:57:04 -!- tromp has quit (Remote host closed the connection).
04:57:36 -!- tromp has joined.
04:58:47 -!- MoALTz_ has joined.
05:01:38 -!- tromp has quit (Ping timeout: 240 seconds).
05:01:51 -!- MoALTz has quit (Ping timeout: 255 seconds).
05:20:52 <Sgeo> Is Elerea not a good fit if I want discrete events like 'line received from IRC'?
05:33:54 <Sgeo> It looks as though the external function could end up causing loss for those things if the FRP network isn't fast enough
05:46:18 -!- w00tles has joined.
05:46:23 -!- w00tles has quit (Read error: Connection timed out).
05:47:04 -!- w00tles has joined.
06:09:17 -!- nooodl has joined.
06:19:50 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:29:53 -!- w00tles has quit (Quit: quit).
06:32:25 -!- password2 has joined.
06:35:28 -!- tertu_ has quit (Ping timeout: 255 seconds).
06:51:00 -!- nooodl has quit (Quit: Ik ga weg).
07:02:03 -!- MindlessDrone has joined.
07:05:58 -!- lexande has quit (Ping timeout: 240 seconds).
07:11:27 -!- lexande has joined.
07:14:59 -!- samebchase has quit (Read error: Operation timed out).
07:16:45 -!- samebchase has joined.
07:24:15 <Sgeo> http://stackoverflow.com/questions/22109333/how-can-i-write-human-language-units-as-postfixes-in-haskell-like-3-seconds
07:24:29 <Sgeo> Why does everyone love '3 seconds' whether it makes a lot of sense in the language or not?
07:24:39 <Sgeo> It makes sense in Factor, much less so in Haskell...
07:25:40 -!- chaiomanot has quit (Remote host closed the connection).
07:28:29 -!- Sprocklem has quit (Quit: leaving).
07:33:48 -!- Slereahphone has joined.
07:38:06 -!- oerjan has joined.
08:00:30 -!- tromp has joined.
08:04:49 -!- tromp has quit (Ping timeout: 240 seconds).
08:05:22 -!- Patashu has joined.
08:18:05 -!- MoALTz_ has quit (Quit: brb).
08:18:28 -!- MoALTz has joined.
09:23:45 -!- MindlessDrone has quit (Quit: MindlessDrone).
10:00:09 -!- Phantom_Hoover has joined.
10:23:29 <b_jonas> if I'm not sure whether a language is esoteric or not, should I add it to the esolang wiki?
10:28:14 <oerjan> why is the bloody wiki stalling in the middle of my edits
10:30:21 -!- yorick has joined.
10:34:22 -!- Slereahphone has quit (Remote host closed the connection).
10:37:30 <HackEgo> [U+2018 LEFT SINGLE QUOTATION MARK] [U+0060 GRAVE ACCENT]
10:39:36 <oerjan> fizzie: wiki is down hth
10:41:33 <oerjan> i opened a heap of tabs and not worked, then i complained, then it worked again
10:44:28 -!- Slereahphone has joined.
10:46:01 <oerjan> b_jonas: we _do_ have a rule you cannot create categories without discussing first, though. *cough*
10:47:52 <oerjan> well then why didn't you repeal it while you hosted the wiki QED hth
10:48:09 <elliott> enforcing it was more fun!
10:55:32 -!- Slereahphone has quit (Remote host closed the connection).
10:55:49 -!- Slereahphone has joined.
10:57:29 <b_jonas> oerjan: we do? oh damn, sorry
10:57:46 <b_jonas> what do I do now then? how do I put it up for discussion?
10:58:09 <b_jonas> an yes, that seems like a dumb rule
10:59:40 <fizzie> I am not sure why it is being slow, the computer it runs on is mostly idle.
10:59:47 <fizzie> (But it was v. slow for me, too.)
11:00:54 <oerjan> b_jonas: http://esolangs.org/wiki/Esolang_talk:Categorization
11:11:21 -!- xpte has quit (Quit: Connection closed for inactivity).
11:15:51 <elliott> 11:41:38 <oerjan> *none worked
11:27:15 <oerjan> what, a new HWN i thought they'd died
11:32:43 -!- Phantom_Hoover has quit (Ping timeout: 268 seconds).
11:35:40 -!- glogbackup has joined.
11:52:45 <oerjan> "•Fuuzetsu: I know someone who pulls in Lens just for & and ??" <-- it's tempting...
11:54:07 <oerjan> hm looks like there's been another bitcoin crash
12:12:59 -!- Sorella has joined.
12:13:15 <ion> http://i.imgur.com/Bsy1sZI.jpg
12:13:45 -!- Sorella has quit (Max SendQ exceeded).
12:14:17 <b_jonas> I want to add the ant brain language from ICFP 2004 defined at "https://alliance.seas.upenn.edu/~plclub/cgi-bin/contest/ants.html" to the wiki. what name do you suppose I should use for that language?
12:15:38 -!- Sorella has joined.
12:15:39 <b_jonas> it could be "Ant state machine" or "Ambiant" or "Ant brain" or "ICFP 2004" or something else
12:17:00 <oerjan> elliott: bitcoinity's graph fell from 0.6 to 0.4 in the last week
12:17:14 <elliott> pfft, you call that a crash?
12:17:17 <elliott> it's not a crash until it halves
12:17:28 <oerjan> for anything _other_ than bitcoin it would be :P
12:17:37 <elliott> b_jonas: mediawiki supports redirects, so pick your favourite and redirect th eothers
12:19:09 <oerjan> finally ghc might get the (:: T) extension i babbled about in 2008 or thereabouts
12:21:10 <elliott> I guess it is actually useful these days
12:21:22 <elliott> I guess lens wants something stronger
12:21:48 <oerjan> elliott: augustss noted that it could also be used as a proxy
12:22:29 <Koen_> I'm doing these regexp crosswords and one of the 'definitions' is [ABC]\s(LU|LP)]* and there is a mismatched ] whatdoido
12:22:34 <lambdabot> `IM.size' (imported from Data.IntMap),
12:22:55 <lambdabot> `IM.size' (imported from Data.IntMap),
12:23:16 <elliott> Koen_: \] or put it right after the [
12:23:23 <elliott> the latter is quite horrid.
12:23:39 <lambdabot> Foreign.Storable sizeOf :: Storable a => a -> Int
12:23:39 <lambdabot> Network.Socket.Internal sizeOfSockAddr :: SockAddr -> Int
12:23:39 <lambdabot> Network.Socket.Internal sizeOfSockAddrByFamily :: Family -> Int
12:23:59 <oerjan> elliott: i think Koen_ means the regexp is already given as that
12:24:53 <Koen_> I'm feeling very uncomfortable
12:26:25 <oerjan> killed by unmatched brackets
12:37:00 -!- conehead has quit (Quit: Computer has gone to sleep).
12:45:13 -!- tromp has joined.
12:45:50 <fizzie> This code is supposed to return values generally in the range [-10, 10], but it's returning values in [-10^300, 10^300]. :/
12:47:53 -!- MindlessDrone has joined.
12:51:00 -!- tromp has quit (Remote host closed the connection).
12:51:33 -!- tromp has joined.
12:52:16 -!- nisstyre has quit (Ping timeout: 268 seconds).
12:56:30 -!- oerjan has quit (Quit: leaving).
12:56:35 -!- tromp has quit (Ping timeout: 268 seconds).
13:00:55 -!- MindlessDrone has quit (Ping timeout: 240 seconds).
13:01:18 -!- Sgeo has quit (Read error: Connection reset by peer).
13:14:59 -!- MindlessDrone has joined.
13:37:40 -!- nisstyre has joined.
13:44:55 -!- Patashu has quit (Ping timeout: 240 seconds).
13:48:18 <b_jonas> hehe http://esolangs.org/wiki/Ndef
13:50:55 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi).
13:54:24 <int-e> I love "the famous real-time interpreter notepad.exe".
13:59:10 -!- Slereahphone has joined.
14:11:38 -!- oklopol has quit (Ping timeout: 240 seconds).
14:15:50 -!- nooodl has joined.
15:09:44 -!- copumpkin has quit (Ping timeout: 252 seconds).
15:10:20 -!- copumpkin has joined.
15:26:16 -!- spiette has quit (Ping timeout: 265 seconds).
15:27:49 -!- tertu has joined.
15:33:38 -!- tertu has quit (Ping timeout: 240 seconds).
15:37:54 -!- spiette has joined.
15:57:13 -!- Sellyme has quit (Quit: Oh god my bouncer is down help).
15:59:01 -!- Phantom_Hoover has joined.
15:59:13 -!- Sellyme has joined.
15:59:38 -!- tertu has joined.
15:59:57 <mroman> Is there a language that let's you define input types based on whether certain methods exist?
16:00:25 <mroman> kinda like int foo(some type where int bar(int) exists )
16:00:42 <mroman> *int bar(that certain type)
16:03:06 -!- Sellyme has quit (Excess Flood).
16:03:10 -!- CutoutCapitalist has joined.
16:06:37 <mroman> Can you give me a keyword to look it up?
16:06:49 -!- tertu has quit (Read error: Connection reset by peer).
16:07:36 <elliott> or "static duck typing" is what a plebian would call it, so you might get results that way too :P
16:08:27 <mroman> Go hase some cool interface stuff
16:09:22 <mroman> well.. it's an interface alright
16:10:05 <FireFly> https://www.cs.cmu.edu/~neelk/rows.pdf has some slides on the topic
16:10:14 <FireFly> but you probably found those already
16:16:55 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi).
16:18:14 -!- Sellyme has joined.
16:21:28 -!- Koen_ has quit (Quit: Koen_).
16:33:13 -!- ^v has joined.
16:35:59 <mroman> http://codepad.org/BkcDW8CK <- something like that
16:36:14 <mroman> although showing you sketch-code isn't probably gonna say much :D
16:38:12 <mroman> function addStuff(<* +(a) => a *> a, <* +(a) => a *> b) would allow you to pass two things that support the + operator
16:38:31 -!- CutoutCapitalist has left ("Leaving").
16:38:48 <mroman> the real question though is whether this kind of stuff requires run-time checks or not
16:40:49 <mroman> You can create a list of "objects" that all support addition
16:41:37 <mroman> which means there can be a double and an integer in it
16:41:44 <mroman> but I might not be able to add doubles and integers
16:41:53 <mroman> which is why I'd need a "homogenous" constraint
16:42:32 <mroman> The other thing is knowing at compile time which overloaded function I'd actually have to invoke
16:42:45 <mroman> and I guess that's not possible
16:45:28 <mroman> http://codepad.org/x9yx3VQb <- Haskell seems to know which version of a function it has to invoke
16:45:34 <mroman> for existential quantification
16:50:11 <mroman> Is my assumption correct that this can't be decided at compile time?
16:51:43 <nooodl> i don't think it is; you could have some function return Objs and pass them to squ
16:52:03 <nooodl> then which function it has to invoke depends on that x value's type
16:52:58 -!- spiette has quit (Quit: :qa!).
16:55:45 <newsham> infinite ducks typing for an infinite amount of time will eventually verify a correct program
17:06:11 <quintopia> does boily ever leave metasepia in here while he's at work
17:08:18 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
17:08:24 <Bike> he did once when specifically asked to
17:09:13 -!- Phantom_Hoover has joined.
17:10:50 <coppro> kolgomorov complexity blows my mind every time
17:14:42 <coppro> the correctly spelled complexity blows my mind every time
17:15:32 <coppro> the fact that the difference between different systems is only constant is just amazing
17:15:53 <Bike> it's "just" turing universality
17:18:10 -!- nisstyre has quit (Remote host closed the connection).
17:22:07 <coppro> but the constant factor is what's so strange
17:22:38 <coppro> not all universal machines are time-equivalent; it's likely the case that TMs are slower than QTMs are slower than NTMs
17:23:08 <Bike> yeah, there are extensions to kolmogorov complexity that require the program to have similar complexities, and there's no constant factor there
17:26:17 <Bike> i don't understand your question.
17:26:32 <Bike> i don't understand your message
17:26:50 <int-e> ?! time does not even the picture, it's all about program size.
17:27:16 <coppro> Given two models of turing-universality, kolmogorov complexity of a string between the two varies by at most a constant
17:27:31 <Bike> yes, because you can just stick an interpreter in front
17:27:48 <coppro> This doesn't come from "just" turing universality, because there are other properties like time complexity which do depend on the model
17:27:52 <coppro> and that's what's so weird
17:28:01 <Bike> time complexity is irrelevant to kolmogorov complexity.
17:28:22 <Bike> the constant factor is just for the program size. the new interpreter program combo might run exponentially slower.
17:28:33 <Bike> so what are you talking about.
17:29:39 <int-e> https://xkcd.com/386/
17:30:22 <coppro> Bike: I am simply trying to draw a comparison between two properties of universal turing machine
17:33:45 <mroman> The biggest problem about this "as few constraints as possible" is, that you can't do much withit
17:34:00 <mroman> you can pass in a list of squarables to a function that squares them and returns them in a new list
17:34:07 <mroman> but you can't get those values out again :)
17:34:33 <mroman> because you can't cast it back to a double (because a squarable isn't always a double)
17:34:50 <mroman> The function would have to make a promise to NOT change any type in the list
17:34:56 <mroman> as well as NOT change the length of the list
17:35:36 <mroman> then one could safely pass a list of doubles and cast it back to a list of doubles since we know the function doesn't affect the types
17:35:53 <mroman> and I guess then we arrived at dependant types :(
17:37:29 <mroman> especially with custom user defined types/containers that's probaly a little bit tricky
17:37:35 <mroman> to verify that no contained type is changed
17:37:54 <mroman> for lists you could just block add and some other list functions
17:38:25 <Bike> https://peerj.com/articles/338/ scientists are fucked up
17:40:24 <mroman> not as fucked up as the participants who stung themselves
17:40:37 <mroman> or let them sting them?
17:40:44 <mroman> I'm not sure what the correct pronoun here is :(
17:41:01 <mroman> ... as the participants who let them(the scientists) sting them(the participants)?
17:41:15 <Bike> the participant was the experimenter, is the point.
17:41:30 <nooodl> Bike: "Medical terminology: Buttocks / Layperson terminology: Buttock" nice
18:02:18 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
18:09:10 -!- Phantom_Hoover has joined.
18:15:59 -!- oklopol has joined.
18:31:16 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
18:42:43 <b_jonas> mroman: go also has static duck typing I think, but I'm not sure
18:43:48 <b_jonas> well, I think they're both static and dynamic, sort of like haskell's classes, as in the validity is checked in runtime but the methods are resolved partly in runtime
18:44:01 -!- avid has joined.
18:45:39 -!- avid has quit (Quit: tulip).
18:52:13 <kmc> was the first "runtime" there meant to be "compile time"?
18:52:16 -!- olsner has joined.
18:57:34 -!- yorick has quit (Ping timeout: 240 seconds).
18:58:10 -!- yorick has joined.
19:08:23 -!- ^v has quit (Read error: Connection reset by peer).
19:12:03 -!- ^v has joined.
19:15:55 -!- Phantom_Hoover has joined.
19:21:51 <b_jonas> validity is checked in compile time
19:29:08 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
19:29:23 -!- ^v has joined.
19:31:02 -!- oerjan has joined.
19:36:01 -!- password2 has quit (Ping timeout: 240 seconds).
19:38:49 * oerjan wonders who made him a reddit response that was deleted.
19:43:57 <kmc> b_jonas: yeah
19:44:06 <kmc> interface types in Go are used for two different things, though
19:44:45 <kmc> you can call the methods in the interface, but you can also do typecase and casts on the dynamic type of the value
19:45:39 <kmc> and since Go doesn't have actual polymorphism, it's very common to pass "interface {}" and do runtime checks on it :<
19:46:32 <kmc> by contrast Haskell a) has a real type system, b) has a separate facility for dynamic casts, which is much less frequently used because see (a)
19:47:23 <Melvar> interface{} is the top type.
20:10:10 <olsner> oh, btw, these guys are back: https://www.youtube.com/watch?v=OH0n_Ew2YDM
20:13:43 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:24:22 -!- conehead has joined.
20:24:26 -!- ^v has quit (Read error: Connection reset by peer).
20:24:53 -!- ^v has joined.
20:29:11 -!- yorick has quit (Read error: Operation timed out).
20:44:22 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
20:46:23 -!- tertu has joined.
20:51:13 -!- Sorella has quit (Ping timeout: 240 seconds).
21:21:46 <Taneb> elliott, I have a strange feeling that your day was more interesting than mine
21:22:02 -!- nisstyre has joined.
21:45:50 -!- olsner has quit (Quit: Leaving).
21:46:39 -!- yorick has joined.
22:02:46 -!- Bicyclidine has joined.
22:04:58 <Bicyclidine> https://twitter.com/haley/status/451838031297646592/photo/1/large
22:08:27 <oerjan> butt that makes no sense.
22:17:08 -!- tertu has quit (Ping timeout: 268 seconds).
22:17:15 -!- tertu has joined.
22:17:29 -!- nooodl has quit (Quit: Ik ga weg).
22:25:46 -!- oklopol has quit (Ping timeout: 268 seconds).
22:44:51 -!- yorick has quit (Read error: Connection reset by peer).
22:48:56 -!- boily has joined.
22:53:34 -!- Sprocklem has joined.
22:56:32 -!- nisstyre has quit (Quit: bai).
23:07:19 -!- Phantom__Hoover has joined.
23:07:23 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:26:51 <impomatic> How can I do a signed multiplication using unsigned multiplication? Is the only way to take the absolute value of both multiplicands, multiply, then set the correct sign afterwards?
23:28:13 <elliott> how could you do better? if the call will only take and output naturals, then you need to have a "downgrade" and an "upgrade" step
23:28:48 <elliott> abs to get something you can pass to unsigned multiplication, then applying the sign to regain the information, seems minimal
23:30:05 <impomatic> I wasn't sure if there's some magical bit twiddling thing that somehow works :-)
23:30:33 <oerjan> there is. just make sure you use enough bitwidth
23:31:21 <elliott> oh, okay, so it's unsigned multiplication on the two's complement form?
23:32:02 <elliott> right, I can see how it's not obviously impossible to do better then :P
23:32:03 <oerjan> it's just multiplication (mod 2^n)
23:32:34 <oerjan> and it will work as long as the multiplication of the value bits don't seep into the sign bit
23:34:33 <oerjan> put differently, you can think of it as working in the 2-adic system
23:36:11 -!- ^v has joined.
23:41:30 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
23:42:31 -!- oerjan has quit (Quit: Niet).
23:49:31 -!- Sgeo has joined.
23:52:11 <Sgeo> Ok so in Elemera or whatever it's called, there's externalMulti, which I completely didn't notice until now
23:56:57 <lambdabot> Koen_ said 11h 33m 11s ago: yeah I watched the latest captain america film with a friend and of course the bad guys from the opening scene are french (the bad guys are always french...) or so did they say!!! they were OBVIOUSLY quebecois
23:57:27 <boily> @tell Koen_ eh? eeeeeeh? like, real Québécois people for real real?
00:03:08 -!- tromp has joined.
00:14:39 -!- boily has quit (Quit: Poulet!).
00:27:31 -!- conehead has joined.
00:36:38 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
00:37:15 -!- Phantom__Hoover has quit (Remote host closed the connection).
00:43:43 -!- conehead has quit (Quit: Computer has gone to sleep).
00:49:05 -!- conehead has joined.
00:56:14 -!- tertu has quit (Ping timeout: 268 seconds).
01:01:52 -!- prooftechnique has joined.
01:03:06 -!- prooftechnique has quit (Client Quit).
01:03:22 -!- Ghoul_ has joined.
01:09:40 -!- mortape123 has joined.
01:34:23 -!- tertu has joined.
02:00:00 <Sgeo> Aren't horrible hacks fun?
02:01:58 <Sgeo> NetWire provides an instance (Monad m, Num b) => Num (Wire s e m a b)
02:02:10 <Sgeo> Which means you can use, e.g., 17 as a wire
02:02:14 <Sgeo> Instead of pure 17
02:02:34 <Sgeo> Which... seems a bit needless, like a fancy trick that Ruby would pull to make test cases read like English, or something
02:10:23 <Sgeo> "Data.Traversable.sequenceA is useful to convert [Behavior a] into Behavior [a]."
02:10:53 <Sgeo> That bothers me a bit.... presumably, the size of the list of Behavior [a] will never vary, but that's not obvious in its type
02:31:33 <Bike> "You Are Using: Firefox 27. CSM Recommends: Explorer 8" meanwhile, on the web
03:01:19 <HackEgo> stalcoin bistificidecoin dumplodecoin vilcoin commentcoin confiecoin astilcoin iapleasepollcoin tricoin rblockcoin appaghtidointolerentraccoin mousequecoin noobcoin rodoncoin gibbcoin quagecoin full0coin lazolcoin iicecoin archcoin
03:11:17 -!- tertu has quit (Ping timeout: 268 seconds).
03:17:05 -!- tertu has joined.
03:24:09 -!- Ghoul_ has quit (Quit: Connection closed for inactivity).
03:45:21 -!- tertu has quit (Ping timeout: 255 seconds).
03:47:39 -!- tertu has joined.
03:52:09 <Sgeo> copumpkin: I hate to tell you this... but GitHub's Haskell hilighter sucks
03:52:40 <Sgeo> Wait, actually, looking at it again... oh. Extension I don't understand
03:53:13 -!- tertu has quit (Ping timeout: 240 seconds).
03:53:21 -!- tertu has joined.
03:53:31 <Sgeo> How do data ... things that need extensions to be made interact with code with those extensions disabled
03:53:52 <Sgeo> e.g. what happens when a function with no extensions enabled tries to use a (forall a. a -> a) -> a?
03:54:09 <Sgeo> Wait, that type doesn't make sense except as bottom or const bottom :/
03:54:37 <Sgeo> But I ... hope my question is sufficiently clear?
03:55:18 <coppro> Sgeo: Syntactic extensions merely enable the syntax; the semantics are always available
03:55:32 <coppro> a rank2 type could be referred to indirectly, but not explicitly
03:56:04 <coppro> modifications to the semantics of defined syntax occur only when the extension is available
03:56:19 <coppro> these two cases probably cover 96% of extensions
04:01:12 -!- Frooxius has quit (Read error: Connection reset by peer).
04:03:16 -!- Frooxius has joined.
04:13:18 -!- tertu has quit (Ping timeout: 240 seconds).
04:13:26 -!- squeak has joined.
04:14:14 -!- nisstyre has joined.
04:16:57 -!- tertu has joined.
04:29:38 -!- tertu has quit (Ping timeout: 240 seconds).
04:29:46 -!- HackEgo has quit (Ping timeout: 265 seconds).
04:44:24 -!- nisstyre has quit (Ping timeout: 268 seconds).
04:54:01 -!- nisstyre has joined.
04:58:08 -!- HackEgo has joined.
05:03:36 -!- Guest2460 has joined.
05:05:46 -!- tertu has joined.
05:08:24 -!- ter2 has joined.
05:08:24 -!- tertu has quit (Disconnected by services).
05:10:34 -!- Guest2460 has quit (Ping timeout: 240 seconds).
05:11:18 * Sgeo is slightly surprised that kmc didn't say anything about Rust 0.10 being released
05:27:18 -!- password2 has joined.
05:39:38 -!- ter2 has quit (Ping timeout: 240 seconds).
05:40:42 -!- prooftechnique has joined.
05:41:21 -!- prooftechnique has quit (Client Quit).
05:42:35 <Sgeo> http://www.reddit.com/r/technology/comments/b0x3z/so_readwriteweb_does_a_story_about_how_facebooks/c0kfwpu
05:42:48 <Sgeo> They made a silly error and I can't correct them
06:05:46 -!- nooodl has joined.
06:17:59 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:24:14 -!- Sprocklem has quit (Quit: leaving).
06:39:55 -!- nooodl has quit (Quit: Ik ga weg).
06:57:00 -!- squeak has quit (Remote host closed the connection).
07:14:32 -!- itsy has quit (Read error: Connection reset by peer).
07:15:07 -!- john_metcalf has quit (Read error: Connection reset by peer).
07:27:51 -!- Patashu has joined.
07:42:00 -!- password2 has quit (Ping timeout: 268 seconds).
07:55:52 -!- Patashu[Zzz] has joined.
07:55:53 -!- Patashu has quit (Disconnected by services).
08:08:29 -!- Sellyme has quit (Excess Flood).
08:08:45 -!- Sellyme_ has joined.
08:09:00 -!- Sellyme_ has changed nick to Sellyme.
08:22:34 -!- password2 has joined.
08:32:06 -!- oerjan has joined.
08:35:53 -!- variable has quit (Read error: Operation timed out).
08:41:12 -!- MindlessDrone has joined.
08:42:15 <oerjan> <Sgeo> They made a silly error and I can't correct them <-- http://xkcd.com/386/ hth
09:38:33 <b_jonas> does the wiki have something about the ioccc entry at http://www.de.ioccc.org/years-spoiler.html#1992_buzzard.1 ?
09:39:26 <b_jonas> there probably should be, the subset of C it uses after expansion is an interesting obfu language in its own right because it's not obvious how you can implement conditionals and other control structures in it
09:47:44 <b_jonas> huh? why can't I edit the wiki? when I submit the edit, I get a blank page as result and the edit doesn't happen
09:54:34 <b_jonas> oerjan: funny, I could create my talk page,
09:54:54 <b_jonas> maybe it matches a spam filter rule or similar
09:56:24 <oerjan> i thought that was supposed to give you a slightly relevant error message.
09:56:48 <oerjan> maybe the wiki move broke something (a sure bet)
10:00:57 <oerjan> b_jonas: i created it, let's see if that helps?
10:02:29 <b_jonas> oerjan: no, still can't edit it
10:02:44 <oerjan> can you edit it to say something else?
10:03:00 <b_jonas> must be spam filter, because it depends on the content I edit it to
10:03:05 <b_jonas> maybe it doesn't like links
10:04:03 <b_jonas> let me try to bisect the text
10:04:27 <oerjan> b_jonas: you might be triggering filter 3, make sure to include a newline.
10:05:08 <oerjan> http://esolangs.org/wiki/Special:AbuseFilter but i don't know if you can view that
10:05:26 <b_jonas> ah! apparently the newline at the beginning before the == matters!
10:05:36 <oerjan> "userpage contains no newlines and adds a link"
10:05:54 <b_jonas> sure, but I did have newlines
10:05:59 <oerjan> b_jonas: oh you start with ==? that's filter 4! :P
10:06:02 <b_jonas> but apparently it wants a newline at the beginning
10:09:14 <oerjan> i suspect that regexp might catch === etc. as well, despite the description.
10:13:00 <fizzie> I seem to recall that AbuseFilter errors have been just unfriendly blank pages also before.
10:13:45 <Jafet> Who needs section headings, anyway
10:14:27 <oerjan> Jafet: it only applies to user pages btw
10:14:41 <oerjan> because that's what the spammers did
10:16:27 <oerjan> fizzie: i'm also a bit worried that the filter statistics says it hasn't triggered.
10:16:44 <Jafet> They maliciously... used section headings?
10:17:12 <Jafet> b_jonas: uhh the fact that they implement a language with control flow operators (including goto) using said subset of C
10:17:16 <oerjan> Jafet: it's only when the page _starts_ with a section heading, which is not our wiki's style
10:18:27 <oerjan> it was presumably the most identifiable feature ais523 could find for that particular flood of spam
10:18:43 <Jafet> I see. Strange that someone runs into it, then.
10:19:27 -!- boily has joined.
10:21:18 <fizzie> oerjan: Curious, there are no entries in the abuse log newer than 5 November, 2013.
10:30:06 -!- MoALTz has quit (Quit: bbl).
10:32:48 <fizzie> Well, would you look at that, there is in fact a bug there.
10:34:19 <fizzie> It was indeed an AbuseFilter match, and it's supposed to log it and give a "descriptive error message", but it has instead hit a PHP "must be of the type array, double given" exception, presumably due to AbuseFilter configuration syntax having changed.
10:37:59 <fizzie> (Though the value it complains about is a double right there in the documentation, so I'unno.)
10:38:27 -!- MindlessDrone has quit (Ping timeout: 255 seconds).
10:39:58 -!- yorick has joined.
10:40:00 <fizzie> "This action has been automatically identified as harmful, and therefore disallowed. If you believe your action was constructive, please inform an administrator of what you were trying to do. A brief description of the abuse rule which your action matched is: an edit to a user page makes it start with an h2 tag"
10:40:14 <fizzie> Now it works, and gives that kind of error message.
10:40:45 <fizzie> Also ends up in the log.
10:50:23 <boily> (what? hungry ghosts in my labyrinth?)
10:52:30 -!- MindlessDrone has joined.
10:53:18 <boily> not much. my thinking functions are running on power saving mode.
10:53:56 <quintopia> boily: okay tell me about your favorite games
10:54:03 <oerjan> fizzie: mind if we start calling you fixie
10:54:24 <quintopia> because he has only one gear! makes sense!
10:54:51 <boily> quintopia: board or video? if it's board, I'd say Eclipse (which we played until midnight Wednesday night), mahjong, xiangqi and 将棋.
10:55:25 <boily> quintopia: video: I have a strong sentimental attachment to the old zelda, mario, DK and FF on the SNES. right now I'm a crawl addict.
10:55:57 <boily> (also, tetris. one can never get enough tetris in one's life.)
10:58:13 <HackEgo> 1110) <boily> aaaaaurgh. you're making me think on a Monday! that shouldn't be happening!
10:59:00 <boily> quintopia: what kind of other medias are you thinking about of?
10:59:07 <oerjan> boily: it's friday hth
11:00:42 <quintopia> boily: books, shows, manga, visual novels, multiplayer rpgs, improv games....
11:01:42 <boily> oerjan: I know. there's an orange t-shirt waiting for me.
11:02:14 <quintopia> oerjan: what computational class do you think you would get by adding an FSM to a poppable circular buffer. (aka you can delete from the queue, or move an element to the back, but not add anything new to it)
11:02:53 <boily> quintopia: many things including the Discworld, I don't really watch TV, azumanga and yotsuba, haven't read any yet, don't play any, do you include tabletop RPGs in that category?
11:03:44 <quintopia> i was thinking of tabletop rpgs i suppose.
11:04:07 <quintopia> though less dndy ones and more storycrafting style ones
11:05:56 <fizzie> oerjan: No, but it might be a bit premature; I'm sure I'll get progressively lazier w.r.t. fixing things as the novelty wears off.
11:06:05 <boily> quintopia: then paranoia.
11:06:37 <boily> (time to initiate the Morning Rituals and go to Work)
11:06:44 -!- boily has quit (Quit: SHOWERED CHICKEN).
11:09:47 -!- conehead has quit (Ping timeout: 252 seconds).
11:09:53 <oerjan> fizzie: yes but by then you'll already have fixed everything, right? O_O
11:11:39 <oerjan> quintopia: hm. if you could also change things you'd have PSPACE, but without that i guess you get something less. it seems doomed to halt or loop trivially...
11:12:13 <quintopia> without writing your own stuff, it's pretty weak
11:12:40 <quintopia> but is there a simple characterization of the languages it can accept?
11:16:10 <oerjan> that sounds even harder since you'd presumably need to massage data into the right form to get much computation at all
11:18:05 <oerjan> i'm thinking with just a _little_ massaging, you should be able to do LR(1) recognition at least.
11:18:55 <oerjan> it might be hard to get back to just before the same point
11:19:01 <nortti> could one modify the values in the buffer? or it it just read/delete/next?
11:19:13 <oerjan> no modification is what i assumed
11:20:35 <oerjan> it's not obviously equal to any class i know of, anyway
11:33:34 -!- Patashu[Zzz] has quit (Ping timeout: 240 seconds).
11:42:42 -!- variable has joined.
11:51:43 -!- password2 has quit (Quit: Leaving).
12:11:37 -!- Sgeo has quit (Read error: Connection reset by peer).
12:20:10 -!- nooodl has joined.
12:22:35 -!- Phantom_Hoover has joined.
12:43:00 -!- ter2 has joined.
12:55:40 -!- oerjan has quit (Quit: leaving).
13:03:58 -!- mortape123 has quit (Ping timeout: 245 seconds).
13:21:08 -!- ter2 has quit (Ping timeout: 240 seconds).
13:43:39 -!- ter2 has joined.
13:57:45 <elliott> fwiw, http://esolangs.org/wiki/Special:AbuseFilter lists the current filters
13:58:20 <elliott> I'm not sure about that #4. it seems overly restrictive
13:58:23 <elliott> I guess you can just use <h2> though.
13:58:31 <elliott> (but then, the description is misleading.)
14:13:49 -!- ter2 has quit (Quit: Leaving).
14:25:56 <b_jonas> elliot: you can just put a newline at the start of the page before the == mark and it works
14:26:10 <b_jonas> elliot: I've put a comment and a newline so that I don't try to delete the newline in the future
14:26:53 <Jafet> You can write an intro to the page
14:28:32 <b_jonas> Jafet: sure, I can write "hello, I'm b_jonas" or something
14:37:03 <elliott> b_jonas: <h2>blah</h2> is just as easy
14:53:30 <fizzie> http://sprunge.us/eEHB let's see you remotely TR-069-administrate my modem now, Mr. ISP.
14:56:14 <b_jonas> elliott: but will the wiki put that to the toc?
14:56:19 <b_jonas> the wiki formatter that is
14:56:28 <elliott> it's not like your page has a TOC though.
14:56:57 <b_jonas> doesn't have a toc yet, because I haven't forced the toc with that magic string and has too few sections
14:57:28 <elliott> a user page long enough for a TOC is a sure sign of ego :p
14:57:40 <elliott> (okay, or more often on the wiki, brilliance)
14:58:27 <b_jonas> just checked, mediawiki does put the <h2> to the toc as well
15:02:09 <b_jonas> elliott: then I have ego. my userpages on both en.wikipedia and en.wiktionary have sections.
15:02:41 <b_jonas> enough sections to have a TOC without forcing it.
16:03:04 -!- ^v has joined.
16:05:36 <int-e> love the latest GG comic.
16:29:31 -!- MoALTz has joined.
16:39:04 <int-e> boily would know ;)
16:39:10 -!- Phantom_Hoover has quit (Remote host closed the connection).
16:41:28 <int-e> (I may be mixing up oerjan and boily. I hope not.)
16:42:31 <Taneb> fwiw, I also read FF
16:43:05 <ion> http://www.telegraph.co.uk/technology/microsoft/10741243/Government-pays-Microsoft-5.5m-to-extend-Windows-XP-support.html
16:44:45 -!- yorick has quit (Remote host closed the connection).
16:46:36 <int-e> gene catlow? stopped reading in 2009.
16:47:12 <int-e> (that's the only match in my comic bookmarks)
16:47:28 <fizzie> I was referring to Gunnerkrigg Court, actually.
16:47:44 <int-e> Pattern match failure then.
16:47:47 <int-e> I do read that one.
16:50:42 <int-e> Taneb: bookmark points to http://www.egscomics.com/?date=2010-07-12
16:51:25 <int-e> I was moving at the time, starting on a new job, ... I guess that's why I stopped reading. And I didn't miss it enough to start again.
16:53:30 <fizzie> I probably stopped reading EGGS around thereabouts, too.
17:21:20 -!- nisstyre has quit (Remote host closed the connection).
18:01:14 -!- itsy has quit (Ping timeout: 240 seconds).
18:30:38 <^v> i have a massive number which is x^x http://pastebin.com/dxYJhSWh
18:30:42 <^v> how do i find out what x is
18:34:21 <nooodl> lambert W function i bet
18:34:25 -!- olsner has joined.
18:35:45 -!- nooodl_ has joined.
18:37:15 -!- nooodl has quit (Disconnected by services).
18:37:18 -!- nooodl_ has changed nick to nooodl.
18:37:37 <lambdabot> 2715417592887128558260874551700217860278385210650169871782230046965783675347...
18:37:59 -!- nooodl has changed nick to nooodl_.
18:38:05 -!- nooodl_ has changed nick to nooodl.
18:38:27 <olsner> idris-ircslave: stop reacting to lambdabot's prefixes
18:38:27 <idris-ircslave> When elaborating an application of constructor __infer:
18:40:45 <Jafet> idris-ircslave: 666**666
18:42:02 <Melvar> There’s no infix operator for it yet, because nobody’s gotten around to adding it.
18:44:47 <nooodl> >>> itertools.ifilter(lambda x: pow(x, x, 1000000) == 598016, itertools.count()).next()
18:44:52 <nooodl> this is a fun way to find it
18:45:09 -!- chaiomanot has joined.
18:50:01 <fizzie> "solve x^x = (big number here) for x real" in W|A works up to some point, though not quite up to 666^666 without W|A Pro.
18:50:01 <Jafet> % Solve[x^x == 2.715*10^1880, x]
18:50:14 <Jafet> {{x -> 665.9999794971646}}
19:07:14 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
19:07:39 -!- ^v has joined.
19:11:41 -!- tertu has joined.
19:26:28 -!- nooodl has changed nick to fcrawl.
19:34:30 -!- ^v has quit (Read error: Connection reset by peer).
19:34:57 -!- ^v has joined.
19:35:17 <augur> https://www.youtube.com/watch?v=NRvK_07KRV8
19:46:55 -!- tertu_ has joined.
19:47:49 -!- tertu has quit (Read error: Connection reset by peer).
20:04:49 -!- tertu_ has quit (Ping timeout: 240 seconds).
20:13:18 -!- olsner has quit (Quit: Leaving).
20:23:47 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
20:25:40 -!- tertu has joined.
20:31:25 -!- oerjan has joined.
20:32:49 -!- Bicyclidine has joined.
20:35:14 <oerjan> <int-e> love the latest GG comic. <-- yep
20:36:30 <fizzie> I can't find my Winterbells high score. :/
20:36:44 <oerjan> <int-e> (I may be mixing up oerjan and boily. I hope not.) <-- it's conceivable we both read it.
20:38:12 <oerjan> Taneb: DD, FF and GG, the cream of webcomics.
20:39:13 -!- MindlessDrone has quit (Ping timeout: 255 seconds).
20:42:54 <b_jonas> GG is Girl Genius, FF is Freefall, but what's DD now?
20:43:13 <b_jonas> ah, you mean Darths and Droids
20:43:36 <myname> i don't know any of them :(
20:43:42 <b_jonas> or maybe Doghouse Diaries? hmmm
20:44:00 <b_jonas> myname: if it helps, http://www.math.bme.hu/~ambrus/sc/grn lists all webcomics I read and many I don't read
20:44:34 <myname> i'd love something like a generic wbcomic reader for android
20:44:47 <b_jonas> myname: don't you have a browser?
20:45:01 <b_jonas> for almost all webcomics, you only need a browser
20:45:09 <myname> i don't want to read webcomics via gprs
20:45:42 <b_jonas> I have some webcomics downloaded, both to read locally and to have a backup copy in case the online one disappears
20:45:48 <b_jonas> do you want some of them zipped?
20:46:33 <myname> i could do that myself, but it's just a huge lack of comfort
20:47:06 <oerjan> augur: i found that presentation a bit one-sided.
20:47:08 <b_jonas> on contrary, for some webcomics (not all by far) it's quite convenient to read off-line using a plain image viewer
20:48:09 <myname> i am looking forward to manga watcher adding custom sites
20:48:10 <augur> oerjan: actually i was iritated by the last bagel, cause its not a moebius bagel
20:48:28 <myname> i may build a wrapper site for webcomics
20:48:59 <myname> what the hell is a moebius bagel
20:49:07 <Taneb> myname, that's not actually legal
20:49:13 <augur> myname: https://www.youtube.com/watch?v=NRvK_07KRV8
20:49:30 <oerjan> i guess it's a möbius bagel complement
20:49:36 <myname> Taneb: yeah, but i don't care
20:49:56 <fizzie> I used to have a Perl script that watched a web page for a changing image (with crummy parse-HTML-with-regexps rules to detect the current image) and fake a RSS feed entry with a direct link to that image, for webcomics that don't do feeds.
20:49:58 <myname> i don't have any plans of making it widely accessable
20:50:02 <fizzie> It worked reasonably well.
20:50:21 <int-e> fizzie: Hmm, potentially addictive. I presume that 59k is still a fairly low score.
20:50:42 <fizzie> int-e: Well, I found mine, and it was approximately 107383695948381900000.
20:50:56 <fizzie> int-e: The five last digits didn't fit in the counter, so it's hard to be sure.
20:50:58 <int-e> yeah. doubling is a stupid idea.
20:51:26 <fizzie> It did take maybe a 15-minute session to rack up that score.
20:51:27 <int-e> (but nevertheless it'll take quite a bit of practice to get that far. I'd rather play 2048)
20:51:31 <oerjan> @run logBase 2 107383695948381900000
20:51:59 <augur> its just a bagel with a double twisted cut
20:51:59 <fizzie> int-e: Also, I was playing it with a Wacom tablet back then, which I think made it rather easier.
20:58:04 <b_jonas> myname: mobius bagel: http://www.georgehart.com/bagel/bagel.html
21:09:57 -!- Patashu has joined.
21:11:03 -!- tertu has quit (Ping timeout: 268 seconds).
21:31:52 <Bicyclidine> «b = uicontrol('Style','pushbutton','Units','normalized','Position',[.5 .5 .2 .1],'String','click here');» now b equals .0015. thanks matlab.
21:44:22 -!- Patashu[Zzz] has joined.
21:44:23 -!- Patashu has quit (Disconnected by services).
21:47:36 -!- Phantom_Hoover has joined.
21:49:04 -!- yorick has joined.
22:16:54 <fizzie> "ME-E4100 Advanced Computer Graphics -- The course concludes in a rendering competition -- The winner will be chosen by Eric Tabellion of Dreamworks Animation -- The competition has a main prize of a Geforce GTX TITAN graphics card, courtesy of Nvidia Corporation."
22:17:16 <fizzie> (Also I don't think they had anything like that going on when I was doing the related courses.)
22:18:44 -!- nisstyre has joined.
22:19:17 -!- olsner has joined.
22:25:53 <kmc> TIL facebook wrote their own C preprocessor https://code.facebook.com/posts/476987592402291/under-the-hood-warp-a-fast-c-and-c-preprocessor/
22:27:51 <olsner> skimmed some low-level optimizations it makes use of, but does it do something clever too?
22:28:38 <kmc> apparently clang's is still faster, because it uses SSE4 string ops on x86
22:29:52 <elliott> kmc: "walter bright wrote a C preprocessor for facebook", even
22:30:04 <kmc> should i know who that is
22:30:22 <elliott> also a long-time C and C++ compilers guy
22:32:32 <Bicyclidine> "If you use a name that MATLAB cannot unambiguously distinguish as a variable inside a parfor-loop, atparse time MATLAB assumes you are referencing a function" i hate this system so much
22:35:54 <Melvar> Whyyy is that even different?
22:36:58 <Bicyclidine> () is overloaded to mean function call on functions, or matrix access on variables, because idon't fucking know
22:40:20 <Melvar> Ohright, I don’t think you can do matrix access on a literal, either …
22:45:11 <Bicyclidine> wow GUIDE is just like visual basic, jesus christ i haven't used this since middle school
22:49:58 -!- conehead has joined.
23:12:50 -!- ^v has joined.
23:16:38 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
23:23:07 -!- nooodl_ has joined.
23:23:29 -!- fcrawl has quit (Ping timeout: 252 seconds).
23:24:09 -!- nooodl_ has changed nick to fcrawl.
23:31:52 -!- Sellyme has quit (Excess Flood).
23:33:45 -!- Sellyme has joined.
23:34:31 -!- olsner has quit (Quit: Leaving).
23:35:04 <pikhq> I imagine that GCC's preprocessor is pretty easy to beat on speed though.
23:35:55 -!- Bike has quit (Quit: leaving).
23:37:53 -!- Bike has joined.
23:38:03 -!- yorick has quit (Remote host closed the connection).
23:38:37 -!- Sellyme has quit (Excess Flood).
23:39:14 -!- Sellyme has joined.
23:39:58 -!- TodPunk has quit (Ping timeout: 240 seconds).
23:45:42 -!- oerjan has quit (Quit: leaving).
23:56:37 -!- tertu has joined.
00:07:54 -!- Sorella has joined.
00:10:43 -!- Sellyme has quit (Excess Flood).
00:12:45 -!- Sellyme has joined.
00:37:39 -!- Patashu[Zzz] has changed nick to Patashu.
00:39:19 -!- zzo38 has joined.
00:41:31 -!- conehead has quit (Quit: Computer has gone to sleep).
00:42:36 -!- conehead has joined.
00:42:36 -!- conehead has quit (Client Quit).
00:55:24 -!- Sgeo has joined.
00:59:39 <Sgeo> Maybe telling a charity telemarketer that I feel like I have too much money is not a good idea...
00:59:44 <Sgeo> Was asked for $365
01:00:36 <kmc> did you pony up
01:00:49 <Sgeo> I made no promises
01:02:52 -!- tertu has quit (Disconnected by services).
01:02:52 -!- ter2 has joined.
01:04:17 <pikhq> Sgeo: Do what I do, and purchase a $1000 monitor.
01:04:44 <Sgeo> I have no place to put it
01:07:10 <kmc> do what I did, and purchase a $1000 monitor and two $250 monitors
01:07:37 <kmc> seriously though, Sgeo, do you know of http://www.givewell.org/
01:07:39 <pikhq> I'm pretty sure I don't have cause for another monitor. This thing is huge.
01:08:27 <Sgeo> I've donated to them a few times. I did mention that to the telemarketer, who was all 'we have 4 stars on Charity Navigator'
01:08:34 <Sgeo> (They do. It's UNICEF)
01:09:03 <pikhq> Have you considered... having less money?
01:10:50 <kmc> Sgeo: if you find a way for donating large amounts of money to produce more than a slight and transient easing of guilt, let me know
01:11:05 <kmc> I think I probably need to do one thing to be objectively helpful, and another thing to feel good about myself
01:12:14 <Sgeo> Donating large amounts of money on a regular basis automatically? I plan on trying... well, not sufficiently large amounts, but something like that
01:12:38 <Sgeo> Although I'm sure there would be some guilt with any amount <100%
01:21:38 -!- ter2 has quit (Ping timeout: 240 seconds).
01:24:28 <kmc> https://gist.github.com/kmcallister/9986166 speeding up an ASCII whitespace scan by a factor of 5 using SSE 4.2
01:24:31 -!- TodPunk has joined.
01:27:46 <pikhq> How does it compare against http://git.musl-libc.org/cgit/musl/tree/src/string/memchr.c ?
01:27:57 <kmc> don't know
01:28:11 <kmc> that only looks for a single byte though
01:28:14 <kmc> this can do a set of up to 16
01:28:51 <kmc> this is pretty gnarly code
01:35:05 <pikhq> Ah, so it's more like strspn.
01:35:31 <Sgeo> kmc: apparently I forgot that Rust has macros :/
01:35:38 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
01:35:58 <Sgeo> http://www.reddit.com/r/rust/comments/224gc0/rust_010_released/cgjpkwh?context=1
01:37:00 <kmc> 420 smoke macros every day
01:38:14 <Sgeo> RUST IS NOT A GAME WHERE NAKED MEN MURDER EACH OTHER WITH HATCHETS
01:41:17 <Bike> there is a video game entitled "rust" in which player avatars are naked and murder each other with hatchets
01:45:52 <lexande> maybe the name of the game is case-sensitive
01:46:42 <Bike> http://playrust.com/wp-content/uploads/2013/12/RustLogo-Normal-Transparent.png it's usually stylized "RUST" though
01:46:59 <Bike> wow i don't know why it looks like that
01:50:24 -!- Slereah_ has quit (Ping timeout: 268 seconds).
02:14:47 <kmc> https://github.com/mozilla/rust/issues/12723
02:19:18 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
02:26:30 <Bike> not bad, metajack
02:27:03 -!- madbr has joined.
02:28:20 <zzo38> What kind of question?
02:28:22 <madbr> how efficient is llvm's alias analysis?
02:28:31 <madbr> zzo38 : a hard one
02:28:40 <Bike> efficient as in how well does it work, or efficient as in how fast does the analysis itself run
02:28:44 <madbr> actually I'm not expecting an answer
02:29:56 <madbr> mostly up to what kind of inner loops can it figure out that none of the writes alias any of the reads
02:31:07 <madbr> essentially trying to figure if my architecture concept is never gonna work :D
02:32:09 <madbr> mostly interested in the kind of number crunching loops you get in video games
02:32:40 <madbr> video rendering, sound rendering, physics simulations, floating point stuff
02:33:09 <zzo38> So would you then have instructions dedicated to video, audio, and physics?
02:33:29 <madbr> don't care about the kind of code that's all function calls, hashes, graph parsing, linked lists... that kind of code is generally impossible to accelerate anyways
02:34:15 <madbr> zzo: just an architecture that can run ~8 instances of a loop at the same time
02:34:35 <zzo38> Yes, you should need some parallel instructions.
02:34:36 <madbr> without multithreading
02:35:10 <madbr> right, it's similar to autovectorization but a little more general
02:35:27 <madbr> essentially it adds possibility for feedback loops
02:36:06 <Bike> wait, feedback? how?
02:36:23 <zzo38> In esolang wiki, there is a article called "Checkout" it describes a code for parallel looping, and some other things
02:36:23 <madbr> each slice runs 1~2~etc slices after the previous one
02:36:25 <kmc> oh jeez, "jmp 3" and "jmp 3f" are not the same instruction at all
02:36:27 <kmc> jumping to 0x0000000000000003 considered harmful
02:37:08 <madbr> so if the longest feedback loop takes 1 cycle to propagate (ie some kind of accumulator), then slice 2 runs 1 instruction later than slice 1
02:38:25 <madbr> if you're doing something like a filter and it takes, say, 10 cycles due to having a couple multiplies in the loop, then slice 2 runs 10 cycles later, slice 3 runs 20 cycles later, slice 4 runs 30 cycles later etc
02:39:55 <madbr> it's probably mostly for math heavy DSP kind of code since you can still only do 1 memory read per cycle across all slices
02:40:29 <madbr> except for really simple cases like an SSE-style aligned block of values
02:41:38 <madbr> so essentially you need 7 math ops to do for every 1 memory read
02:42:04 <madbr> if you make it dual-issue then you need 15 math ops for every 1 memory read :D
02:43:20 <zzo38> You should then use a "load program" instruction, to load the program into internal memory, and then other instruction set up each execution unit, and then you can make it slice like that to don't interfere with memory access.
02:44:21 <madbr> but then you have to operate on really small data loads
02:44:34 <madbr> like, cache-size data loads
02:44:48 <madbr> kinda like the ps3's cell processor actually
02:45:09 <zzo38> What is the cache size?
02:45:58 <madbr> it depends on how the chip is made
02:46:13 <madbr> but it's definitively under 1 meg
02:46:34 <madbr> probably in the 32k~256k range
02:47:13 <madbr> essentially it becomes a cell processor like on the ps3
02:49:39 <madbr> which kinda became moot when they figured out how to turn x86 into 8 cores (which is a pretty scary concept tbh)
02:52:32 <madbr> anyhow, if llvm can figure out that none of the memory reads can alias any of the writes inside a loop, you can autovectorize anything that has predictable flow
02:53:58 <madbr> if it doesn't have something like "half the operations are memory operations" or "feedback loop is as long as the loop itself so the loop is essentially 100% serial", you can probably come out ahead in terms of speed
02:57:29 <madbr> kindof an anti-pentium2
02:58:59 <madbr> which seems to be based around the idea that most programs are horrible unoptimizable crudge made out of jumps and memory accesses
02:59:51 <Bike> http://www.beepboopbitcoin.com/ Finally.
03:00:07 <madbr> (the fastest cpus are still ultimately based on that design which I guess says something about software... or maybe about how people benchmark them)
03:05:38 -!- ter2 has joined.
03:07:53 <Bike> is it like controversial that most programs are made of jumps and memory accesses?
03:08:34 -!- fcrawl has quit (Ping timeout: 240 seconds).
03:08:49 <madbr> no but it's essentially the unoptimizable part of programs
03:09:04 <madbr> since it has lots of stuff like short dependencies
03:09:22 <zzo38> Some things in the program could be manually optimized though
03:09:55 <kmc> scanned 100 MB of data for ASCII space characters in about 8 ms
03:09:59 <kmc> 12 GB/s ain't bad
03:10:06 <kmc> it's within a factor of 2 of the theoretical max memory bandwidth
03:26:29 <^v> 47 is one of my favorite numbers now
03:26:46 <copumpkin> I agree. It's a pretty good number
03:28:00 <^v> it (47*x)%256 can be anywhere from 0-255
03:28:19 <Bike> what causes that, 256 and 47 being coprime probably?
03:29:10 <copumpkin> aren't all odd numbers coprime to 256?
03:29:11 <^v> i recently found this out by making a text to Barely converter
03:29:30 <^v> copumpkin, yes actually, fuck
03:46:25 -!- ter2 has quit (Ping timeout: 240 seconds).
03:52:00 -!- ter2 has joined.
04:07:39 -!- ter2 has quit (Ping timeout: 252 seconds).
04:13:04 -!- ter2 has joined.
04:14:45 -!- nisstyre has joined.
04:14:50 -!- nisstyre has quit (Changing host).
04:14:50 -!- nisstyre has joined.
04:22:49 -!- Sorella has quit (Quit: It is tiem!).
04:25:46 -!- conehead has joined.
04:27:18 <^v> i made hello world in barely
04:27:19 <^v> xoooooooooooooohjjjjjjjjjjjjjjjhhhxooooooooxooooooxjjjxjjjjjjjjjjjjjjjjjjjjjjjjxjjjjjjjjhxooooooooooooxooohjjjjhhhxjjjxxjjjjjjjxjjjjjjjhhjhhhhoooooxhoooooooooooooooooooooohjhhhoooooooooooo~
04:30:08 <^v> and holy shit i made it smaller
04:30:09 <^v> xjhhhhxooooooooxooooooxjjjxhhoohhhhxjjjjjjjjhxooooooooooooxjhhhhxjjjxxjjjjjjjxjjjhhhhhhxjjjjjjjjjjjjjjhhhh~
04:30:58 <kmc> it looks like a cat is walking on your keyboard
04:31:46 <^v> i am the kind of asshole who makes hello worlds in languages that dont have them yet
04:31:50 <^v> and doesnt post them to the wiki
04:32:23 <^v> what i have so far: fishstacks and barely
04:32:26 <^v> need to make more
04:32:29 <^v> just to piss people off
04:32:49 <zzo38> I would want the instruction set, where, implicit vectorization/out-of-order/pipelining/caching/etc is not allowed.
04:33:40 <^v> and mind you, these are all pregenerated tables which i can use to convert text to that lang instantly
04:33:54 <^v> which i am not giving to you, because i am an asshole
04:35:57 <madbr> zzo38 : I'm not sure sure that's possible
04:36:10 <madbr> zzo38 : though you can make it really hard :D
04:37:04 <^v> a compiler that disagrees with you if you do something too complicated
04:38:29 <zzo38> madbr: What do you mean by that?
04:38:52 <madbr> without self modifying code you can simply cache the code
04:38:59 <madbr> and cache the data
04:39:48 <madbr> the running core cannot figure out that it got hella cached
04:40:02 <madbr> or even out-of-ordered
04:40:04 <zzo38> I mean, that cache is only accessed by instructions which explicitly access the cache in the certain way.
04:40:44 <zzo38> And then, the instructions in cache are VLIW which is different from instructions from external memory, is another possibility.
04:41:29 <madbr> explicit cache I think doesn't gain anything AFAIK
04:42:40 <^v> because i dont feel like being an asshole today, here is the conversion table: https://gist.github.com/infinikiller64/9987604
04:42:53 <zzo38> It gains not complicating the execution with not knowing the cache and having to just guess instead, making also the speed confusing...
04:42:53 <^v> warning: your browser will probably crash
04:43:42 <zzo38> ^v: Then put "view-source:" at front, or download using curl, and then the browser might not crash as much.
04:43:54 <^v> https://gist.githubusercontent.com/infinikiller64/9987604/raw/07db8ab7a7e64a58e4f2fb3bb957296b5a54f2cf/gistfile1.lua
04:44:14 <zzo38> OK, that one better
04:44:55 <^v> 256^2 values
04:46:42 <madbr> zzo38 : it simplifies the design I guess yeah
04:46:45 <zzo38> madbr: I think simplicity of the implementation is better than simplicity of the interface, and simplicity is better than completeness, robustness, correctness, sanity, etc.
04:47:13 <madbr> but to get the kind of RISC speed there's more or less no way around a data and instruction cache
04:47:21 <zzo38> Yes, I always want to simplify the design.
04:47:26 <madbr> otherwise your speed is going to be on the order of the 386
04:47:39 <zzo38> I did not say to eliminate the cache entirely, but to make it explicit-only.
04:47:44 <madbr> unless you use pseudo-static ram or some other similar exotic part
04:48:23 <madbr> zzo38 : then you're still going to need 2 RAM banks probably
04:48:37 <madbr> one for data, one for instructions
04:49:46 <madbr> the problem is that DRAM has pages :(
04:49:59 <zzo38> There would still be an internal cache, which is also used for microcodes, so in instruction cache it would be VLIW codes
04:50:55 <madbr> opening a new page and reading a value is something like 3 times slower than reading a value from an already open page
04:51:05 <madbr> more if you're using more recent DRAM
04:52:10 <madbr> pages are something like 512bytes/1k/2k/4k/8k etc depending on DRAM generation/size
04:52:27 <zzo38> It could use 8-bits external memory interface, and 128-bits for internal memory interface for cache, so you can deal with arrays of whatever bit size of data, you loaded, and is also for use with VLIW, which has longer instructions than the external one.
04:53:06 <madbr> I'm not sure you can guzzle picture data from RAM fast enough if your external memory is only 8 bits
04:53:08 <zzo38> madbr: It would be OK, as long as, the number of clock cycles is based on a fixed DRAM size/speeds
04:55:39 <madbr> if your part is a cpu, it's going to mix up accesses to data with accesses to instructions
04:55:51 <madbr> so you're going to have the page-change-penalty every cycle
04:56:04 <madbr> well, every time you access data actually
04:56:10 <Bike> http://web.archive.org/web/19990128210124/http://people.netscape.com/brendan/ this is real right? tell me it is
04:56:34 <^v> function SwapBack() { document.knob.src = Image1.src; return true; }
04:56:58 <zzo38> madbr: You could have a separate GPU as well, as CPU, so it is possible to write the program in the way to act in parallel; you can also store the data in the cache which you would use mostly often, to increase the speed; and, depending on the way the program is written to use/unuse cache, use self-modifying codes, too.
04:57:01 <^v> page still loading
04:57:14 <zzo38> (Possibly even the program in cache is allowed to modify itself)
04:58:16 <zzo38> Self-modifying codes should be allowed, as it is very useful.
04:58:31 <madbr> I'm not convinced it's worth the complexity
04:58:58 <zzo38> If you store the value of a variable in an immediate operand, then you can avoid a page penalty.
04:59:01 <Jafet> Bike: not enough jquery
04:59:13 <zzo38> (It also avoid a memory access, too.)
04:59:24 <madbr> except it's still a memory access
04:59:50 <madbr> and later on when you're pipelining your architecture, you're in deep trouble
05:00:42 <zzo38> Some instruction sets don't have pipeline stalls, so it avoids that problem; you then need to program them yourself.
05:01:23 <zzo38> You can also, tell it to copy it to the cache and then tell it to read/write cache and execute instruction in a cache, is another way speeding it up a bit.
05:01:24 <madbr> it's really hard to avoid pipeline stalls
05:01:36 <madbr> if you have cache you have pipeline stalls
05:01:55 <madbr> if you have branch prediction you have pipeline flushes
05:01:56 <zzo38> That is why, it has to be explicit-only cache.
05:02:26 <madbr> if you have something like load reg, [reg + 5]
05:02:33 <madbr> you have pipeline stalls
05:02:36 <zzo38> If you use it wrong, you are subject to the consequences by yourself.
05:02:57 <madbr> because if the reg in [reg + 5] changes the cycle before, you have to catch that
05:04:01 <zzo38> madbr: The program would be written to avoid that if you want it to use the register that changes in the cycle before.
05:04:40 <madbr> then your program has extra nops every time some other useful instruction can't be swapped in
05:05:14 <madbr> the extra nops take up extra code cache which makes the thing slower
05:05:15 <zzo38> Yes, it does, but if you don't have another useful instruction to put in, then be careful maybe you wrote your program badly and there might be a way to fix it.
05:05:25 -!- oklopol has joined.
05:05:32 <madbr> depends on the kind of algo
05:05:49 <madbr> if it's number crunching stuff then usually there's something you can stuff in yes
05:06:07 <madbr> if it's like, zip decompression or something nasty like that... god have mercy on you
05:06:14 <zzo38> Anyways, my suggestion was that, the instruction cache would be VLIW, so different than the instruction set used for executing external memory anyways
05:06:45 <zzo38> (It would execute microcode ROM if the instruction cache is not being executed.)
05:07:30 <madbr> I guess vliw would be ok if you had a way to switch to some less efficient instruction set
05:07:46 <madbr> for like non-number-crunching code
05:08:08 <madbr> where you're going to do lots of memory accesses anyways so there's no point to having 6 ALUs
05:08:37 <madbr> and then for that one hand-optimized crunching loop, use the VLIW mode
05:08:49 <^v> Bike, the page finnaly loaded and xD
05:09:33 <zzo38> If the program isn't in cache, it would use a less efficieint instruction set. Otherwise, if it is in the cache, you would need to implement your own instruction set that the program in microcode RAM runs from the rest of the cache.
05:10:20 <madbr> essentially this is what the ARM does with the THUMB vs ARM
05:11:09 <madbr> thumb is 16 bits which limits the number of ram cycles you lose to loading in the stuff
05:12:40 <madbr> though you could probably just have a VLIW that has a choice between 1 big VLIW instruction word, or an instruction word that encodes multiple one-cycle instructions
05:14:09 <zzo38> Sure, that is another possibility
05:15:46 <madbr> it's hard to find a good balance in this kinda thing :D
05:17:08 <madbr> optimal instruction is somewhere between 16 and 32 bits AFAIK
05:17:42 <madbr> less than 16 and it's too small, not enough bits for the register selection
05:18:08 <madbr> plus you need too much granularity in your instruction word shifter
05:19:56 <madbr> more than 32 and you're probably wasting too much instruction cache space, unless it's VLIW and you're packing more than one instruction per word...
05:20:05 <madbr> AFAIK this was a major problem on itanium
05:20:57 <madbr> also if your cpu is dual issue that is kinda equivalent-ish to making your instructions 64bits
05:22:39 <zzo38> What does "dual issue" mean?
05:22:47 <madbr> two instructions per cycle
05:23:23 <madbr> see: intel pentium, ARM A8 (used on lots of older iphones), one MIPS generation (can't remember which)
05:23:35 <madbr> I think there was also one of the 68k that was designed like that
05:23:54 <madbr> afaik it's one of the cpu design "sweet spots"
05:24:26 <madbr> less than 2 and you're running 1 instruction per cycle... and essentially twice as slow
05:24:45 -!- chaiomanot has quit (Quit: Leaving).
05:25:05 <madbr> more than 2 and chances are you're going to need crazy stuff like out of order execution to make it any faster than 2 instructions per cycle
05:25:19 <madbr> (though I guess the IBM POWER6 did it)
05:25:20 -!- tromp has quit (Remote host closed the connection).
05:25:55 -!- tromp has joined.
05:25:59 <madbr> (and it really depends on the type of program, I'm sure you can do a lot more in-order if your programs are number crunching or floating point)
05:28:07 <madbr> I guess it all comes down to "what kind of game is going to run on it" :D
05:30:09 -!- tromp has quit (Ping timeout: 252 seconds).
05:31:03 <madbr> the general problem with a VLIW is to make it faster than a well designed RISC
05:31:56 <madbr> ie "pay for" your large instructions by figuring out stuff for your CPU to do in the leftover slots
05:33:16 <madbr> if this fails, the RISC is faster than you because it needs less code cache
05:35:37 <madbr> generally the stuff that reduces your gains are stuff like
05:35:52 <madbr> - ram/cache read ports
05:36:07 <madbr> - register file read/write ports
05:37:39 <madbr> - absolute latencies in instruction processing, which can also be described as "lack of number crunching to do while working on the critical-latency-path"
05:41:37 <madbr> that being said, gfx and sound rendering are more or less the ideal case for finding stuff that won't fall into these limits and will actually benefit from VLIW or similar stuff like SIMD
05:42:15 <^v> anyone still have barely.asm?
05:42:21 <^v> link b bork
05:46:25 -!- zzo38 has quit (Ping timeout: 255 seconds).
05:49:56 <Sgeo> > fix (sequence [(!! 1), 2 + 2])
05:49:56 <idris-ircslave> When elaborating an application of constructor __infer:
05:49:58 <lambdabot> No instance for (GHC.Show.Show a0)
05:49:58 <lambdabot> arising from a use of `M688017572578786861922522.show_M6880175725787868619...
05:49:58 <lambdabot> The type variable `a0' is ambiguous
05:49:58 <lambdabot> Possible fix: add a type signature that fixes these type variable(s)
05:49:58 <lambdabot> Note: there are several potential instances:
05:50:26 <Sgeo> @run fix (sequence [(!! 1), 2 + 2]) :: [Int]
05:50:27 <lambdabot> No instance for (GHC.Num.Num ([GHC.Types.Int] -> GHC.Types.Int))
05:50:27 <lambdabot> (GHC.Num.Num ([GHC.Types.Int] -> GHC.Types.Int))
05:50:56 -!- Patashu[Zzz] has joined.
05:50:56 -!- Patashu has quit (Disconnected by services).
05:51:06 <Jafet> @run fix (sequence [(!! 1), (2 +)])
05:51:07 <lambdabot> Occurs check: cannot construct the infinite type: a0 = [a0]
05:51:09 <Sgeo> Trying to recreate something similar to the loeb example
05:51:28 <Sgeo> With just reader monad + fix
05:54:35 <Jafet> :t sequence [(!! 1), const (2 + 2)]
05:54:44 <Jafet> @run fix $ sequence [(!! 1), const (2 + 2)]
05:54:56 <Jafet> @run fix $ sequence [ (!!5), const 3, liftM2 (+) (!!0) (!!1), (*2) . (!!2), length, const 17 ]
05:55:35 <Jafet> @let loeb :: [[a] -> a] -> [a]; loeb = fix . sequence
05:56:12 <Sgeo> That's not the standard defintion of loeb, is it?
05:56:34 <Jafet> The type looked more general than that, but sequence is constraining it
05:57:09 <Jafet> :t let loeb x = ($ loeb x) <$> x in loeb
05:57:46 <Jafet> :t fix . sequenceA
05:57:47 <lambdabot> `T.sequenceA' (imported from Data.Traversable),
05:57:52 <Jafet> :t fix . T.sequenceA
05:57:53 <lambdabot> Traversable t => t (t a -> a) -> t a
05:58:49 <Jafet> @pl loeb x = ($ loeb x) <$> x -- trivial fix
06:00:27 <Jafet> @let loeb = fix (fmap.flip id =<<)
06:00:29 <lambdabot> No instance for (Functor f0) arising from a use of `fmap'
06:00:29 <lambdabot> The type variable `f0' is ambiguous
06:00:29 <lambdabot> Possible fix: add a type signature that fixes these type variable(s)
06:00:29 <lambdabot> Note: there are several potential instances:
06:01:18 <Jafet> @let loeb :: Functor f => f (f b -> b) -> f b; loeb = fix (fmap.flip id =<<)
06:04:15 -!- madbr has quit (Quit: Rouringu de hajikunda!).
06:15:22 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:25:58 -!- ter2 has quit (Ping timeout: 240 seconds).
06:28:58 <mroman> > loeb Just (\Just x -> x)
06:28:58 <idris-ircslave> When elaborating an application of constructor __infer:
06:28:59 <lambdabot> Constructor `Data.Maybe.Just' should have 1 argument, but has been given none
06:29:18 <mroman> > loeb Just (\(Just x) -> x)
06:29:19 <idris-ircslave> When elaborating an application of constructor __infer:
06:29:20 <lambdabot> Couldn't match type `Data.Maybe.Maybe (Data.Maybe.Maybe t0 -> t0)'
06:29:20 <lambdabot> with `((Data.Maybe.Maybe t0 -> t0) -> b0) -> b0'
06:29:20 <lambdabot> Expected type: (Data.Maybe.Maybe t0 -> t0)
06:29:20 <lambdabot> -> ((Data.Maybe.Maybe t0 -> t0) -> b0) -> b0
06:29:20 <lambdabot> Actual type: (Data.Maybe.Maybe t0 -> t0)
06:34:11 <Jafet> @run loeb $ Just fromJust
06:34:44 <mroman> > let fun :: (Functor f, Functor g) => f -> g -> (f b -> b) -> f b -> g b; fun f g x = f ( g x) in fun Just Just (\(Just x) -> x) 9
06:34:44 <idris-ircslave> let fun :: (Functor f, Functor g) => f -> g -> (f b -> b) -> f b -> g b; fun >
06:34:45 <lambdabot> Expecting one more argument to `f'
06:34:52 <mroman> ^- what's wrong with that?
06:36:03 <mroman> > let bar :: Functor f => f -> a -> f a; bar f x = f x in (bar Just) 9
06:36:03 <idris-ircslave> let bar :: Functor f => f -> a -> f a; bar f x = f x in (bar Just) 9<EOF>
06:36:04 <lambdabot> Expecting one more argument to `f'
06:36:35 <Jafet> @run let fun :: (Functor f, Functor g) => (a -> f a) -> (a -> g a) -> (f a -> a) -> f a -> g a; fun f g x = f (g x) in fun Just (:[]) (\(Just x) -> x) (Just 9)
06:36:36 <lambdabot> from the context (GHC.Base.Functor f, GHC.Base.Functor g)
06:36:36 <lambdabot> fun :: (GHC.Base.Functor f, GHC.Base.Functor g) =>
06:36:36 <lambdabot> (a -> f a) -> (a -> g a) -> (f a -> a) -> f a -> g a
06:37:00 <mroman> > let bar :: Functor f => (a -> f a) -> a -> f a; bar f x = f x in (bar Just) 9
06:37:01 <idris-ircslave> let bar :: Functor f => (a -> f a) -> a -> f a; bar f x = f x in (bar Just) 9<>
06:37:11 <mroman> ah. I see the problem.
06:37:54 -!- ter2 has joined.
06:39:37 <mroman> @run return 9 :: Maybe Int
06:43:16 <mroman> @run id (Just 9) == (id Just) 9
06:48:31 -!- ter2 has quit (Ping timeout: 255 seconds).
07:04:35 -!- MoALTz has quit (Quit: bbl).
07:54:49 -!- trolly has joined.
08:02:36 -!- trolly has quit (Remote host closed the connection).
08:14:29 -!- sgelios has joined.
08:17:35 -!- Slereah_ has joined.
08:25:08 -!- sgelios has quit (Ping timeout: 240 seconds).
08:37:10 <fizzie> Huh, is Brainfuck/Ook commonly used in goecaching circles? This geocaching tool I stumbled upon while looking for something else -- http://gcc.eisbehr.de/features.html -- lists conversions between text, Brainfuck and Ook among its features.
08:38:06 -!- oerjan has joined.
08:38:07 <fizzie> (Also an absolutely ludicrous list of non-eso things.)
08:39:41 <Taneb> Yogscast is getting pretty huge
08:56:16 <oerjan> @run length . nub . take 128 . flip iterate 1 $ \x -> (x*47) `mod` 256
08:57:51 <oerjan> @run nub [length . nub . take 256 . flip iterate 1 $ \x -> (x*n) `mod` 256) | n <- [0..255]]
08:57:52 <lambdabot> <hint>:1:70: parse error on input `)'
08:58:02 <oerjan> @run nub [length . nub . take 256 . flip iterate 1 $ \x -> (x*n) `mod` 256 | n <- [0..255]]
08:58:42 <oerjan> none 128, so not cyclic
09:01:03 <oerjan> hm why is there no 7 i there
09:02:28 <oerjan> @run nubBy ((==) `on` snd) [(n, length . nub . take 256 . flip iterate 1 $ \x -> (x*n) `mod` 256) | n <- [0..255]]
09:02:29 <lambdabot> [(0,2),(1,1),(2,9),(3,64),(4,5),(7,32),(8,4),(15,16),(16,3),(31,8)]
09:03:40 <oerjan> @run nubBy ((==) `on` snd) [(n, length . nub . take 256 . flip iterate 1 $ \x -> (x*n) `mod` 256) | n <- [1, 3..255]]
09:03:41 <lambdabot> [(1,1),(3,64),(7,32),(15,16),(31,8),(63,4),(127,2)]
09:05:43 -!- zzo38 has joined.
09:06:43 <oerjan> @run last . sort . nub . take 256 . flip iterate 1 $ \x -> (x*3) `mod` 256)
09:06:45 <lambdabot> <hint>:1:70: parse error on input `)'
09:06:49 <oerjan> @run last . sort . nub . take 256 . flip iterate 1 $ \x -> (x*3) `mod` 256
09:07:22 <oerjan> ok so 3 and 255 are summand generators
09:08:39 <oerjan> @run sort . nub . take 256 . flip iterate 1 $ \x -> (x*3) `mod` 256
09:08:39 <lambdabot> [1,3,9,11,17,19,25,27,33,35,41,43,49,51,57,59,65,67,73,75,81,83,89,91,97,99,...
09:10:26 <fizzie> I keep wanting you to write \x -> (x*n) `mod` 256 as flip mod 256 . (n*) instead, because it has less pokey bits.
09:12:02 <oerjan> i pretty clearly decided against making that pointfree at one point.
09:14:04 <oerjan> @run nubBy ((==) `on` snd) [(n, length . nub . take 256 $ iterate (n*) 1 ) | n <- [0..255 :: Word8]] -- another option
09:14:05 <lambdabot> [(0,2),(1,1),(2,9),(3,64),(4,5),(7,32),(8,4),(15,16),(16,3),(31,8)]
09:30:07 <int-e> sort . nub -> head . group . sort
09:32:10 -!- ski has quit (Quit: Lost terminal).
09:32:23 <oerjan> and it wasn't in the inner loop
09:43:20 -!- yorick has joined.
09:43:49 <int-e> oerjan: I do that habitually; I usually get it right the first time, too, when actually coding.
09:44:11 * int-e should have an nubOrd helper instead.
09:48:30 <int-e> @run id * 3 `mod` 256 $ 123 -- I forgot whether this is still in lambdabot.
09:48:31 <lambdabot> No instance for (GHC.Show.Show a0)
09:48:31 <lambdabot> arising from a use of `M826470610663680039923602.show_M8264706106636800399...
09:48:31 <lambdabot> The type variable `a0' is ambiguous
09:48:31 <lambdabot> Possible fix: add a type signature that fixes these type variable(s)
09:48:31 <lambdabot> Note: there are several potential instances:
09:48:55 <Jafet> @run 0 0 :: Integer
09:48:56 <lambdabot> No instance for (GHC.Num.Num a0) arising from the literal `0'
09:48:56 <lambdabot> The type variable `a0' is ambiguous
09:48:56 <lambdabot> Possible fix: add a type signature that fixes these type variable(s)
09:48:56 <lambdabot> Note: there are several potential instances:
09:48:56 <lambdabot> instance GHC.Num.Num GHC.Types.Double
09:49:09 <Jafet> @run (0 :: Integer -> Integer) 0
09:49:10 <lambdabot> (GHC.Integer.Type.Integer -> GHC.Integer.Type.Integer))
09:49:15 <int-e> (when Cale ran it, there used to be a Num a => Num (r -> a) instance, acting pointwise
09:49:55 <Jafet> @instances-importing Num
09:49:57 <oerjan> i remember that, also when it was removed
09:50:19 <int-e> which is really irritating if you make a mistake in numeric code somewhere, but id * const k `mod` 256 would be kind of cool.
09:50:23 <oerjan> @help instances-importing
09:50:23 <lambdabot> instances-importing [<module> [<module> [<module...]]] <typeclass>. Fetch the instances of a typeclass, importing specified modules first.
09:50:41 <oerjan> Jafet: i think that requires the module list to do anything different
09:51:25 <int-e> (ironically it's longer than \x -> x * k `mod` 256)
09:51:50 <oerjan> yeah function instances confuse matters, which is why i was surprised they added the monadic ones by default to ghci lately
09:56:27 -!- MindlessDrone has joined.
09:58:24 <Jafet> @run (ap, ap.ap, ap.ap.ap, ap.ap.ap.ap)
09:58:25 <lambdabot> No instance for (Data.Typeable.Internal.Typeable1 m0)
09:58:25 <lambdabot> arising from a use of `M431492159472810415423670.show_M4314921594728104154...
09:58:25 <lambdabot> The type variable `m0' is ambiguous
09:58:25 <lambdabot> Possible fix: add a type signature that fixes these type variable(s)
09:58:25 <lambdabot> Note: there are several potential instances:
09:58:30 <Jafet> :t (ap, ap.ap, ap.ap.ap, ap.ap.ap.ap)
09:58:31 <lambdabot> Monad m => (m (a -> b) -> m a -> m b, (a1 -> a2 -> b1) -> ((a1 -> a2) -> a1) -> (a1 -> a2) -> b1, (a3 -> a4 -> b2) -> (((a3 -> a4) -> a3) -> a3 -> a4) -> ((a3 -> a4) -> a3) -> b2, (a5 -> a6 -> b3) -> ((((a5 -> a6) -> a5) -> a5 -> a6) -> (a5 -> a6) -> a5) -> (((a5 -> a6) -> a5) -> a5 -> a6) -> b3)
10:01:22 <oerjan> :t ap`fmap`ap`fmap`ap`fmap`ap
10:01:23 <lambdabot> (a -> a1 -> b) -> ((((a -> a1) -> a) -> a -> a1) -> (a -> a1) -> a) -> (((a -> a1) -> a) -> a -> a1) -> b
10:05:05 <Jafet> @run length.show.typeOf $ ap.ap.ap.ap.ap.ap.ap.ap.ap $ (undefined :: ()->()->())
10:05:10 <Jafet> @run length.show.typeOf $ ap.ap.ap.ap.ap.ap.ap.ap.ap.ap $ (undefined :: ()->()->())
10:05:30 <Jafet> @run 1688/1044 - (1+sqrt 5)/2
10:08:28 <oerjan> does that mean you can get the type of the next one with a fibonacci substitution on the previous?
10:09:03 <lambdabot> Monad m => (a -> m (a1 -> b)) -> a -> m a1 -> m b
10:09:24 <FireFly> Good way of deriving the golden ration IMO
10:10:13 <oerjan> hm the b only occurs once above
10:10:24 -!- olsner has joined.
10:10:44 <lambdabot> (a -> a2 -> a1 -> b) -> a -> (a2 -> a1) -> a2 -> b
10:12:20 <oerjan> indeed that's a fibonacci substitution
10:14:51 <oerjan> a2 becomes a2 -> a1, a1 becomes a2
10:18:00 <lambdabot> (a1 -> a -> b) -> (a1 -> a) -> a1 -> b
10:18:52 <lambdabot> Monad m => (a -> m (a1 -> b)) -> a -> m a1 -> m b
10:19:31 <oerjan> olsner: i added the ($) to force the function instance
10:20:01 <Jafet> @run (\(a,b,c,d) -> printf "%s -> %s -> %s -> %s" a b c d) <$> unfoldr (\e@(a,b,c,d) -> Just (e, (a, printf "(%s -> %s)" b c, b, d))) ("(a -> b -> c)", "(a -> b)", "a", "c") :: [String]
10:20:03 <lambdabot> ["(a -> b -> c) -> (a -> b) -> a -> c","(a -> b -> c) -> ((a -> b) -> a) -> ...
10:21:04 <oerjan> that's the base case, sort of
10:21:37 <oerjan> which is of course a refinement of ($)'s type
10:22:23 <Jafet> @run (12+) . sum <$> unfoldr (\e@[a,b,c,d] -> Just (e, [a, 6+b+c, b, d])) $ length <$> ["(a -> b -> c)", "(a -> b)", "a", "c"]
10:22:25 <lambdabot> No instance for (GHC.Num.Num [GHC.Types.Int])
10:22:25 <lambdabot> add an instance declaration for (GHC.Num.Num [GHC.Types.Int])
10:22:50 <Jafet> @run unfoldr (\e@[a,b,c,d] -> Just (12 + sum e, [a, 6+b+c, b, d])) $ length <$> ["(a -> b -> c)", "(a -> b)", "a", "c"]
10:22:51 <lambdabot> [35,49,70,105,161,252,399,637,1022,1645,2653,4284,6923,11193,18102,29281,473...
10:24:06 <oerjan> @run typeOf (undefined:()->()->())
10:24:07 <lambdabot> Pattern syntax in expression context: undefined : () -> () -> ()
10:24:13 <oerjan> @run typeOf (undefined::()->()->())
10:24:26 <oerjan> @run typeOf ap.(undefined::()->()->())
10:24:27 <lambdabot> Couldn't match expected type `(() -> ()) -> c0'
10:24:27 <lambdabot> with actual type `Data.Typeable.Internal.TypeRep'
10:24:35 <oerjan> @run typeOf $ ap.(undefined::()->()->())
10:24:36 <lambdabot> Couldn't match type `()' with `a0 -> b0'
10:24:37 <lambdabot> Expected type: () -> () -> a0 -> b0
10:24:56 <oerjan> @run typeOf $ ap$(undefined::()->()->())
10:25:03 <Jafet> Function instances.
10:26:51 <oerjan> ap f x y = f y (x y), which shows you get a fibonacci on the term level too
10:27:57 <oerjan> @run (ap.ap.ap) (f::Expr->Expr->Expr) a b
10:27:59 <lambdabot> Couldn't match expected type `((Debug.SimpleReflect.Expr.Expr
10:27:59 <lambdabot> -> Debug.SimpleReflect.Expr.Expr -> Debug.Simp...
10:27:59 <lambdabot> with actual type `Debug.SimpleReflect.Expr.Expr'Couldn't match t...
10:28:07 <oerjan> @run (ap.ap.ap) (f::Expr->Expr->Expr) g h
10:28:08 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
10:28:08 <lambdabot> arising from a use of `Debug.SimpleReflect.Vars.g'
10:28:19 <oerjan> @run (ap.ap.ap) (f::Expr->Expr->Expr) g h :: Expr
10:28:20 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
10:28:21 <lambdabot> arising from a use of `Debug.SimpleReflect.Vars.g'
10:28:29 <lambdabot> (FromExpr t, FromExpr t1) => (t, t1)
10:28:56 <lambdabot> (a -> a1 -> b) -> (((a -> a1) -> a) -> a -> a1) -> ((a -> a1) -> a) -> b
10:29:41 <oerjan> @run (ap.ap.ap) (f::Expr->Expr->Expr)
10:29:43 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
10:29:47 <lambdabot> arising from a use of `M723199156154611174123930.show_M7231991561546111741...
10:29:53 <oerjan> :t (ap.ap.ap) (f::Expr->Expr->Expr)
10:29:54 <lambdabot> (((Expr -> Expr) -> Expr) -> Expr -> Expr) -> ((Expr -> Expr) -> Expr) -> Expr
10:30:29 <oerjan> @run g (h :: Expr) :: Expr
10:31:09 <oerjan> @run (ap.ap) (f::Expr->Expr->Expr) g h :: Expr
10:31:12 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
10:31:12 <lambdabot> arising from a use of `Debug.SimpleReflect.Vars.g'
10:31:18 <oerjan> @run ap (f::Expr->Expr->Expr) g h :: Expr
10:31:54 <oerjan> :t (ap.ap) (f::Expr->Expr->Expr) g h :: Expr
10:31:54 <lambdabot> No instance for (Typeable Expr) arising from a use of `g'
10:31:55 <lambdabot> Possible fix: add an instance declaration for (Typeable Expr)
10:31:55 <lambdabot> In the second argument of `ap . ap', namely `g'
10:32:12 <oerjan> something is going horribly wrong in the typechecking
10:32:26 <lambdabot> (Typeable a, Typeable b, FromExpr c) => (a -> b) -> c
10:33:08 <lambdabot> Could not deduce (Typeable b0) arising from a use of `f'
10:33:08 <lambdabot> bound by the inferred type of it :: FromExpr c => c at Top level
10:35:00 <oerjan> you cannot actually show FromExpr values that aren't fully applied
10:35:11 <oerjan> which some of the subexpressions will be
10:35:59 <oerjan> so the Expr trick doesn't work with higher-order functions
10:42:25 <int-e> hmm. a challenge? :)
10:44:17 * oerjan somehow pressed return instead of tab
10:45:24 <int-e> *Main> f.id :: Expr -> Expr ---> \x -> f x
10:46:05 <int-e> unfortunately, f :: Expr -> Expr -> Expr becomes \x -> \x -> f x x ;-)
10:46:06 <Jafet> :t (ap.ap.ap) ?f ?g ?h
10:46:06 <lambdabot> (?f::a -> a1 -> b, ?g::((a -> a1) -> a) -> a -> a1, ?h::(a -> a1) -> a) => b
10:46:28 <oerjan> int-e: it's (Expr -> Expr) -> Expr which becomes the problem
10:46:51 <int-e> (but perhaps showsPrec can be abused to make instance Show a => Show (Expr -> a) where show f = "\\x -> " ++ show (f x) use different variables)
10:47:00 <int-e> oerjan: sure, there are limits.
10:47:47 <int-e> I'm not going to pursue this seriously
10:47:48 <oerjan> int-e: also, my examples don't actually give lambdas.
10:49:31 <Jafet> show f = show (['x':show n|n<-[0..]], f); instance Show a => Show ([String], Expr -> a) where show (v:vs, f) = "\\" ++ v ++ " -> " ++ show (vs, f $ var v)
10:51:10 <int-e> Possibly one would end up with horrible things like instance (Witness a, Show b) => Show (a -> b) where show f = let w = witness in "\\" ++ show w ++ " -> " ++ show (f witness), plus some hackery to get identifiers.
10:54:07 <oerjan> instance Witness (a -> b) => Show (a -> b) where show = witness 0
10:55:11 -!- conehead has quit (Quit: Computer has gone to sleep).
10:56:03 <oerjan> mroman: shall i ban you for not noticing that everyone else is using @run twh
10:58:35 <myname> i am thinking about making "indecision" a disadvantage for my rogue, but i'm not really sure if i want to
10:58:57 <oerjan> `addquote <myname> i am thinking about making "indecision" a disadvantage for my rogue, but i'm not really sure if i want to
10:58:59 <HackEgo> 1182) <myname> i am thinking about making "indecision" a disadvantage for my rogue, but i'm not really sure if i want to
10:59:06 <oerjan> i'm pretty sure i was baited.
11:00:11 <myname> that situation actually stands
11:00:39 <int-e> Right ... "I used to be indecisive but now I'm not so sure."
11:00:48 <int-e> (I wonder who came up with this.)
11:01:32 <myname> does anybody has good ideas for quirks which donkt hurt that much?
11:02:00 <int-e> It *is* a good weakness. "There is a cop. Should I run or hide? In the meantime I can just stand here and look suspicious."
11:02:07 <oerjan> i go with the typo and say "were-donkey"
11:05:24 -!- yorick has quit (Remote host closed the connection).
11:05:44 <myname> int-e: well, it may be *too* good
11:06:17 <int-e> only if you want to survive
11:06:23 <int-e> but how can you be sure about that?
11:07:14 <myname> as a player i'd like my character to be alive most of the time
11:08:10 <int-e> but such a character could be lots of fun ... as long as it lasts.
11:08:30 <int-e> But I do understand your concerns.
11:16:49 -!- Patashu[Zzz] has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
11:16:58 -!- Patashu has joined.
11:21:42 <int-e> *Main Control.Monad> (ap.ap.ap) (f::Expr->Expr->Expr)
11:21:43 <int-e> \abb -> \aa -> f aa abb
11:23:02 <int-e> oerjan: http://sprunge.us/iMUg?haskell (not perfect, but now it stops being fun)
11:25:44 <int-e> (actually I have no clue what I did there, semantically)
11:27:36 <int-e> best I can tell the witnesses are now Skolem functions with all their arguments implicit. Hah.
11:27:54 <int-e> Clearly that's very useful.
11:28:14 <int-e> (Especially because their names clash, too.)
11:30:16 -!- olsner has quit (Quit: Leaving).
11:37:31 -!- fcrawl has joined.
11:38:13 -!- boily has joined.
11:39:04 <boily> good international boardgaming day morning!
11:48:22 <Taneb> I need to move my computer
11:48:29 <Taneb> Having it here is giving me a sore back
11:54:42 -!- Sorella has joined.
11:56:49 <Jafet> 3SUM purportedly in o(n^2): http://arxiv.org/abs/1404.0799
12:11:32 <int-e> Jafet: interesting.
12:13:25 -!- Phantom_Hoover has joined.
12:48:38 -!- Patashu has quit (Ping timeout: 240 seconds).
12:56:43 -!- ter2 has joined.
13:02:13 -!- ter2 has quit (Read error: Connection reset by peer).
13:02:28 -!- ter2 has joined.
13:05:11 <boily> that video was introductionarily interesting, lightly brushing against the Uncountability of the Reals.
13:06:07 <Phantom_Hoover> sam hughes wrote a better explanation: http://qntm.org/trollpi
13:06:45 <boily> IT'S NOT WROOOOONG!
13:06:48 <Phantom_Hoover> but all it comes down to is that when you take the limit of a sequence of curves that limit doesn't have to share any properties with the curves in the sequence
13:08:54 <Taneb> Phantom_Hoover, Vi Hart is pop maths. It's for viewerships, not correctness
13:09:25 <Phantom_Hoover> Right but it's not incorrect in a 'lies-to-children' sense, it's incorrect in the sense that it just leads viewers down the garden path.
13:10:44 <oerjan> and to the barn fell of doom
13:12:20 <Taneb> What really annoys me about Vi Hart is her video about Flexagons came out a day after I decided to make some
13:14:18 * oerjan now imagines gingerbread flexagons. and probably should eat.
13:14:24 <Taneb> Now I want to make a flexagon
13:15:15 <Taneb> Probably not out of gingerbread
13:17:04 <int-e> reminds me of https://en.wikipedia.org/wiki/Rubik%27s_Magic hmm
13:18:01 <boily> oerjan: can one make flexible gingerbread?
13:20:24 <quintopia> Taneb: what annoys me about vihart is that my friends got a private concert from her on joco cruise crazy 1 and i couldn't go :(
13:20:28 <oerjan> quintopia: oh the barn fell?
13:21:51 <oerjan> boily: i dunno do i look like a baker
13:22:59 <boily> oerjan: you are oerjan. maybe you are a baker. maybe not. hth.
13:41:12 <quintopia> nooooooooooo not the morse code .-.
13:42:54 <boily> the Morse Code is the Future!
13:43:07 <oerjan> .--.-..--..-.--.-..-.--..--.-..-
13:44:35 <oerjan> it uses separating pauses
13:44:50 <oerjan> because, it's like designed to be decoded by humans.
13:45:13 <quintopia> humans could decipher a pauseless stream with practice!
13:48:10 <boily> without humans in the way, communication would be much easier.
13:48:25 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
13:55:36 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
14:01:32 -!- Phantom_Hoover has joined.
14:04:49 -!- boily has quit (Quit: BOARDGAMING CHICKEN!).
14:11:28 -!- shikhin has joined.
14:15:17 -!- shikhin has changed nick to shikhi.
14:19:02 <Sgeo> Is it normal for a Haskell question to go unanswered on SO this long? http://stackoverflow.com/questions/22851565/getting-input-into-netwire-programs
14:20:12 -!- shikhi has changed nick to shikhin.
14:26:00 <oerjan> well it's not about a very widely used library afaik
14:28:10 -!- Lola has joined.
14:29:12 -!- applybot has quit (Quit: sorry!).
14:30:39 <HackEgo> Lola: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.)
14:32:38 -!- ter2 has quit (Ping timeout: 240 seconds).
14:33:39 -!- ter2 has joined.
14:36:28 -!- ter2 has changed nick to tertu.
14:36:39 -!- tertu has changed nick to ter2.
14:36:55 -!- Lola has left.
14:41:25 <elliott> oerjan: don't bother welcoming ~canaima
14:41:38 <elliott> all the spanish people of the past N months are just one person.
14:41:48 <elliott> in fact we should just set a ban or something. it's silly.
14:42:25 <ion> Ban all the users
14:49:17 -!- conehead has joined.
14:49:52 -!- oerjan has quit (Quit: Omelette du fromage).
15:03:32 -!- applybot has joined.
15:04:39 -!- yorick has joined.
15:11:44 <Jafet> idris-ircslave: let x = 1 :: x in x
15:11:45 <idris-ircslave> (input):1:14:When elaborating argument val to constructor Delay:
15:17:24 -!- tromp has joined.
15:25:57 -!- int-e has changed nick to notregistered.
15:26:10 -!- notregistered has changed nick to int-e.
15:28:00 -!- tertu3 has joined.
15:28:13 -!- ter2 has quit (Read error: Connection reset by peer).
15:31:37 -!- ^v has joined.
15:31:48 <HackEgo> /hackenv/bin/pastelogs: line 2: cd: /var/irclogs/_esoteric: No such file or directory \ grep: ????-??-??.txt: No such file or directory \ http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.22298
15:32:33 <int-e> No such file or directory
15:33:13 <fcrawl> HackEgo just doesn't keep have logs anymore?
15:33:15 <int-e> afaik, hackego moved and the logs are now stored elsewhere
15:33:39 <int-e> While previously they were on the same machine. But I don't know for sure.
15:43:48 -!- shikhin has quit (Quit: Leaving).
16:12:20 -!- fcrawl has quit (Read error: Connection reset by peer).
16:16:00 <fizzie> That is my impression, too.
16:17:01 <fizzie> kmc: Just so you know, I have made the opcode generator into an opcode quiz, as per your suggestion. (Just need to collect data for a couple more architectures before making it public.)
16:18:40 -!- copumpkin has joined.
16:23:41 <Jafet> Call it the Label Ersatz Generator; name the quiz "ARM or LEG?" Add some Thumb to throw people off.
16:25:59 <Jafet> (People who pass are True Opcode Experts.)
16:26:04 -!- nooodl has joined.
16:27:55 -!- Phantom_Hoover has quit (Ping timeout: 268 seconds).
16:34:13 <fizzie> "incorrect; opcode HW_LD/PAWQVL is real" man, Alpha is hard.
16:35:43 <fizzie> It's not in the web yet. I only have x86 and Alpha in it.
16:36:34 <fizzie> Also it's missing "share your score in Facebook/Google+/Twitter" buttons, which were something I was thinking of "ironically" adding.
16:36:38 <fizzie> (I'm trying to figure out where the ARM opcodes are in this GNU binutils GDB checkout.)
16:39:23 <fizzie> They seem to be somewhat complicatedly in it, due to having some structure programmatically constructed.
16:46:05 -!- Phantom_Hoover has joined.
17:05:24 <zzo38> Program a quiz using Internet Quiz Engine. It work better, and is faster, too.
17:07:09 <zzo38> Yet, it includes a few extra commands for feature such as arithmetics and a few others.
17:07:37 <kmc> fizzie: did I ever show you http://ugcs.net/~keegan/complexity.html
17:11:25 <fizzie> I don't think I saw that.
17:11:44 <fizzie> And the Internet Quiz Engine will probably not be able to generate fake opcodes from n-gram models, will it?
17:13:08 <zzo38> fizzie: That feature is not included yet, although you can pregenerate the data. Currently, there is not the program to allow manipulation of Internet Quiz Engine files using SQL, sorry.
17:14:21 <zzo38> (But, it is currently possible to manipulate them using AWK, so you can use that.)
17:18:31 <fizzie> Well, I've already written this thing.
17:19:59 <zzo38> Currently IQE has no features for any kind of string manipulation at all, actually; only arithmetics and conditions are supported (although, there is timer support, multiple selection support, percentages, and some other things like that). There are no kinds of backward flow control at all, so loops are impossible.
17:23:09 -!- ^v has quit (Ping timeout: 252 seconds).
17:35:43 <fizzie> kmc: Here, you can have a preliminary-ish look at http://zem.fi/2014-04-05-opquiz -- though I'm going to have to go to do some sauna things real soon.
17:37:49 <fizzie> (Wonder if I should really add those score-share buttons.)
17:45:59 -!- bekirov has joined.
18:02:12 <zzo38> It is not working OK.
18:09:12 -!- variable has changed nick to trout.
18:09:35 <int-e> hmm, github. why don't forks have their own issue trackers, and why can't I merge an upstream pull request to my own fork using their frontend?
18:11:19 <zzo38> I have looked at (but not used) the Fossil system, which is said to be simpler than Git. Fossil is a SQL-based system, implemented as a single C program. I do not know if it can solve those problem or not.
18:14:53 -!- ^v has joined.
18:15:53 <int-e> No, because I have no issues with git itself.
18:17:39 -!- conehead has quit (Quit: Computer has gone to sleep).
18:18:39 <zzo38> You could move it to a system other than Github, even if it is still git-based system, though.
18:22:47 -!- S1 has joined.
18:27:38 -!- olsner has joined.
18:34:42 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:43:21 -!- bekirov has quit (Remote host closed the connection).
19:23:32 <fizzie> kmc: Re the complexity class game, I would've wanted to have similar short descriptions of the (real) instructions, but those would've been less simple to extract. (And I guess also the entire list would be much larger.)
19:26:29 -!- nooodl_ has joined.
19:27:36 -!- nooodl has quit (Ping timeout: 252 seconds).
19:30:38 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
19:30:55 -!- ^v has joined.
19:34:12 -!- tertu3 has quit (Ping timeout: 252 seconds).
19:54:04 -!- lambdabot has quit (Quit: requested).
19:56:26 -!- fungot has quit (Quit: requested).
19:57:26 -!- fungot has joined.
19:58:22 -!- lambdabot has joined.
19:58:57 <int-e> The request was supposed to go to my test instance of the bot :-/ Oh well. It took its time (as usual) but it made it back.
20:05:26 <HackEgo> danddreclist 50: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
20:10:43 <zzo38> How can I tell gdb which module to debug by default? I have two modules loaded, and the one I want to debug isn't the main program.
20:18:43 -!- evalj has joined.
20:19:21 -!- olsner has quit (Quit: Leaving).
20:20:31 -!- nooodl_ has changed nick to nooodl.
20:50:42 <fizzie> http://cybermap.kaspersky.com/ that looks ridiculously like in a movie
21:01:11 * Sgeo goes to listen to all the music here: http://jessicadickinsongoodman.com/2008/01/18/pachebels-rant-dissected/
21:02:14 -!- oerjan has joined.
21:06:42 <Sgeo> And some of those videos don't exist :(
21:09:35 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
21:16:23 -!- evalj has quit (Remote host closed the connection).
21:31:33 -!- augur has quit (Remote host closed the connection).
21:37:01 -!- Patashu has joined.
21:56:05 -!- Koen_ has joined.
21:59:35 -!- Patashu[Zzz] has joined.
21:59:35 -!- Patashu has quit (Disconnected by services).
22:10:41 -!- ejls has joined.
22:20:12 <^v> i made bottles of beer in fishstacks
22:21:15 <^v> its 142K chars
22:21:40 <^v> who wants it?
22:23:17 <^v> https://dl.dropboxusercontent.com/u/55181333/bottles.fishstacks
22:26:57 <Sgeo> Why are haddocks not built for this? https://hackage.haskell.org/package/python-pickle-0.2.0
22:28:01 <^v> D: me no likey python
22:29:21 -!- ^v has changed nick to PixelTerst.
22:31:13 <Taneb> I am still not quite sure what Object-Oriented programming actually is
22:31:52 <PixelTerst> i dunno, if memory addresses are objects, arent all programs object oriented
22:35:03 -!- PixelTerst has changed nick to ^v.
22:39:37 <Taneb> On the other hand, I have biscuits
22:40:22 <S1> k I'm outa here
22:40:24 -!- S1 has left.
22:40:43 -!- Phantom__Hoover has joined.
22:42:10 <oerjan> On the first hand, do you have cheese?
22:42:45 <Taneb> I am one of those weird people who isolates biscuit and cracker consumption
22:44:03 <^v> i am one of those weird people who makes programs in languages without an official interpreter
22:44:07 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
22:44:18 <^v> i made my own fishstacks inturpreter
22:44:28 <^v> but im not giving it to you, because lazyness
22:44:51 <oerjan> did you know that if you don't put things on the wiki, they don't exist hth
22:44:57 <Taneb> ^v, have you seen Eodermdrome?
22:45:18 <^v> oerjan, ohey you are the person who edited fishstacks after me
22:45:23 <^v> please dont slap me
22:45:26 <^v> my first edit
22:46:01 <^v> Taneb, i remember it now ;-;
22:46:34 <oerjan> i'm one of those weird people who makes programs in Eodermdrome.
22:47:09 <oerjan> still waiting for someone to implement it so i can test the program.
22:47:24 <oerjan> (too lazy to code up actual graph algorithms)
22:47:43 <oerjan> BUT I PUT THE PROGRAM ON THE WIKI HTH
22:53:25 -!- conehead has joined.
22:55:50 -!- Zom-B has quit.
23:09:00 -!- tertu3 has joined.
23:42:07 <^v> the barely page is full of shit
23:42:25 <^v> h adds 71 not 47
23:45:29 -!- oerjan has quit (Quit: Nite).
23:49:31 <^v> proof: http://puu.sh/7XtPL.png
23:49:41 <^v> ]xjjjjjhhhhxjhhhhhhhhjjjhh~
23:49:44 <^v> is what i entered
23:50:45 <^v> its because some dumbass misread the assembly source
23:50:57 <^v> fucking.. dumbass
23:52:53 <^v> i am just mad
23:54:53 <elliott> that's no reason to take it out on the intelligence of someone you don't even know who made a simple mistake
23:55:04 <elliott> after all, it was not that long ago you misread how Deadfish works...
23:57:06 -!- yorick has quit (Remote host closed the connection).
00:10:33 -!- 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?").
00:16:00 <^v> woooooooooooooooooooooooooooot http://puu.sh/7Xvui.png
00:16:31 <^v> ]xhhhhooooooooohhhhhhxooooooooxooooooxjjjxhoooohhhxhohhhhhhhxhhhhjjjhhhxhhhhooooooooohhhhhhxjjjxxjjjjjjjxjhhhhxjhhhhhhhhjjjhh~
00:16:42 <^v> will add to wiki, but gtg soon
00:25:32 -!- Frooxius has quit (Read error: Connection reset by peer).
00:25:45 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
00:28:03 -!- Frooxius has joined.
00:59:05 -!- conehead has quit (Quit: Computer has gone to sleep).
01:27:05 -!- ^v has quit (Read error: Connection reset by peer).
01:27:16 -!- ^v has joined.
01:33:03 -!- Phantom__Hoover has quit (Ping timeout: 268 seconds).
02:09:01 -!- nooodl has quit (Quit: Ik ga weg).
02:17:01 <quintopia> seems like every time i turn around my iptables configuration has been deleted. :(
02:23:36 <Bike> sounds like a really boring poltergeist
02:32:23 -!- nisstyre has joined.
02:41:36 <quintopia> might be the upgrade installer. dunno. making an extra copy of the rules in case it happens again
02:45:04 -!- ter2 has joined.
02:49:03 -!- tertu3 has quit (Ping timeout: 252 seconds).
02:58:51 <Jafet> fizzie: you should add the snarxiv score indicators
02:59:16 <Jafet> (I think 30% was "9th year grad student")
03:00:00 <Jafet> Also, this is genuinely harder than snarxiv
03:00:01 <zzo38> Do you know how to recognize the music of a record by observing the grooves?
03:01:44 <Jafet> In other news, I'm sad CMONFLICTOR isn't a real opcode
03:07:09 -!- Sorella has quit (Quit: It is tiem!).
03:13:23 -!- conehead has joined.
03:14:49 <quintopia> zzo38: that's essentially how CDs work. I'm surre one could readily build an optical needle
03:15:33 <quintopia> http://en.wikipedia.org/wiki/Laser_turntable
03:15:57 <Bike> that's so zeerust a concept i can't handle it
03:16:06 <zzo38> I read a book that someone could recognize a lot of orchestral music on a record, by only observing the grooves, not using any special equipment. However, only post Mozart music, but still that is a lot of possibilities
03:16:44 <Bike> i imagine there are repetitive patterns, especially if you're listening to some form that's really regimented
03:17:51 <zzo38> I would certainly believe that it might be possible.
03:18:54 <quintopia> probably amplitude variation over time would be enough. i don't doubt there are many more who can differentiate pieces looking at the waveform
03:19:18 <zzo38> I don't know exactly, since I don't know how to do it myself.
03:20:47 <zzo38> It says here: "Arthur Lintgen ... apparently possesses the remarkable ability to identify the music on a phonographic record without referring to its label ... by looking at the grooves on the surface of the disc ... the music must be classical, orchestral, and post-Mozart ... this leaves a body of recorded music that runs into thousands of records."
03:21:07 -!- conehead has quit (Read error: Connection reset by peer).
03:22:28 <zzo38> James Randi was commissioned to test it. He figured it out, even multiple recordings of the same music, and an extra cut on the disc, and others. However, two of them were something different: rock music, and a lecture. He called the rock music "gibberish" and the lecture "a vocal solo of some kind". I suppose this is to be expected if you don't understand that kind of "music"...
03:22:52 <zzo38> It is clear to me that this is nothing "paranormal".
03:23:44 <quintopia> well, seeing as how nothing people actually can do can be called "paranormal"...
03:27:47 <zzo38> There are other reports of things, much of which are exposed as hoaxes, frauds, or something else, but some which don't know such thing quite yet, and which would seem to be "paranormal". I wasn't there, so I don't know if these reports are just made up, but you cannot disregard things out of hand. Once people thought, stones cannot come from the sky, but now they figured it out. So, you cannot just ignore something with no good reason.
03:28:27 <Jafet> "The prototype revealed an interesting flaw of laser turntables: they are so accurate that they play every particle of dirt and dust on the record, rather than pushing them aside as a conventional stylus would."
03:28:38 <zzo38> Extraordinary claims require extraordinary evidence, but, doesn't mean it can ignore everything
03:28:49 <zzo38> Jafet: Interesting idea.
03:29:01 <quintopia> Jafet: but all SERIOUS audiophiles store and play their records in an industrial clean room, so it's no big issue
03:29:03 <zzo38> I didn't know, but yes of course if it a laser, clearly that is how it works!
03:29:47 <Jafet> Would be fun to use a record of 4'33"
03:30:09 <Jafet> I don't think industrial clean rooms tend to have good acoustic qualities
03:30:31 <quintopia> why not? theoretically you can design your clean room any way you want to
03:30:32 <Bike> it's not musicians' fault that semiconductor manufacturer have no taste.
03:44:34 <zzo38> Then, you need to design, the musical clean room.
03:46:02 <Bike> emptying spit valves is gonna suck, i can already tell
03:47:07 <quintopia> sorry, no wind or brass instruments allowed...you can't play them with a clean suit on
04:12:41 -!- ^v has quit (Ping timeout: 252 seconds).
04:15:52 -!- ^v has joined.
04:46:26 -!- tertu3 has joined.
04:49:46 -!- ter2 has quit (Ping timeout: 268 seconds).
05:20:45 -!- ter2 has joined.
05:21:03 -!- tertu3 has quit (Read error: Connection reset by peer).
05:25:00 -!- john_metcalf has quit (Read error: Connection reset by peer).
06:18:40 -!- tromp has quit (Remote host closed the connection).
06:19:17 -!- tromp has joined.
06:23:45 -!- tromp has quit (Ping timeout: 255 seconds).
06:35:10 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:39:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:51:18 <zzo38> Play non-brass music, then.
06:51:28 <zzo38> (If you like non-brass music)
07:11:49 -!- augur has joined.
07:23:33 -!- zzo38 has quit (Ping timeout: 240 seconds).
08:09:09 -!- ter2 has quit (Ping timeout: 252 seconds).
08:10:11 -!- ter2 has joined.
08:20:53 -!- ter2 has quit (Ping timeout: 252 seconds).
08:21:07 -!- ggherdov_ has quit (Changing host).
08:21:07 -!- ggherdov_ has joined.
08:21:07 -!- ggherdov_ has quit (Changing host).
08:21:07 -!- ggherdov_ has joined.
08:27:50 <fizzie> Jafet: I was thinking that there should have been some sort of a complicated scoring mechanism with multipliers and all that.
08:42:02 -!- oerjan has joined.
09:06:42 -!- stuntaneous has joined.
09:09:21 -!- Vorpal has joined.
09:20:09 <fizzie> "I heard it through the grapefruit / not much longer would you be mine. / Oh I heard it through the grapefruit, / Oh and I'm just about to lose my mind."
09:20:39 <fizzie> (Ate a grapefruit for breakfast.)
09:23:24 <fizzie> quintopia: Maybe some kind of a bellows-driven trombone.
09:23:43 <fizzie> Vorpal: http://zem.fi/2014-04-05-opquiz
09:24:47 <oerjan> fizzie: your interpretation makes the losing mind part so much clearer.
09:39:13 <Vorpal> fizzie, nice photos again
09:39:32 -!- Tritonio has joined.
09:39:33 <Vorpal> fizzie, I like the "Pixels most distant from the mean, smoothed." a lot
09:40:27 <Vorpal> fizzie, also nice opcode quiz
09:41:29 <Vorpal> fizzie, really? There are real opcodes with underscore in them?
09:41:59 <fizzie> At least as accepted by NASM.
09:42:12 <Vorpal> Well so far I have 19/23 correct
09:42:37 <Vorpal> VFNMADD213SS is real? Really?
09:42:46 <Vorpal> There should be like a link to what each real one does
09:43:37 <fizzie> Yes, I would've liked that, but it would've been hard to collect, since they're all spread out.
09:44:04 <fizzie> And ARM opcodes were in an overly complicated from in the Binutils sources, all kind of custom %x expandables.
09:44:11 <Vorpal> fizzie, ARM and AVR are probably the only other two I have a chance of
09:45:10 <Vorpal> Yeah, about 80% success rate is what I manage on x86
09:45:54 <fizzie> The underscores are at least official Intel nomenclature, as per the Intel Architecture Instruction Set Extensions Programming Reference.
09:47:37 <Vorpal> I think the 80% correct was a fluke, now it seems to stay around 70%
09:48:03 <Vorpal> AVR I think I could manage, mostly because it is such a simple instruction set
09:48:35 <fizzie> And VFNMADD213SS is "Fused Negative Multiply-Add of Sclaar Single-Precision Floating-Point Values"; VFNMADD213SS xmm0, xmm1, xmm2 does x0 = x2 - x0 * x1 where xN is the single-precision float in the low 32 bits of xmmN.
09:49:21 <fizzie> (The numbers -- 132, 213 and 231 are all valid -- denote the way those three operands go.)
09:50:03 <fizzie> There's some kind of logic in there, though I can't quite decode it immediately.
09:50:20 <Vorpal> SS is probably scalar single or something like that
09:50:36 <fizzie> The opcode for VFNMADD213SS is VEX.DDS.LIG.128.66.0F38.W0 AD /r.
09:51:04 <Vorpal> The hell? Is this an alias for a lot of prefixes basically?
09:51:34 <fizzie> It's some way of denoting all the parts of the VEX prefix, yes.
09:52:05 <Vorpal> Which flag is support for this sort of stuff in /proc/cpuinfo?
09:52:10 <fizzie> "VEX.[NDS/NDD/DS].[128,256,L0,L1,LIG].[66,F2,F3].0F/0F3A/0F38.[W0,W1,WIG] opcode [/r]" is the full format.
09:52:40 <fizzie> "CPUID Feature Flag" column lists "FMA" in the manual.
09:52:55 <Vorpal> I mean the VEX stuff in general
09:53:21 <Vorpal> flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx lahf_lm ida arat epb xsave
09:53:21 <Vorpal> opt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid
09:53:37 <Vorpal> Heh, that is a lot, also that is "xsaveopt" as a single entry in the line-break
09:53:45 <fizzie> That's what introduced the VEX prefix, AIUI.
09:53:58 <Vorpal> Well it is there I guess
09:54:02 <fizzie> (Or AVX512F if you want to use the "VFMADD132SS xmm0 {k1}{z}, xmm1, xmm2/m32{er}" form.)
09:54:39 <fizzie> "flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx ...
09:54:45 <fizzie> ... f16c rdrand lahf_lm abm ida arat xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm"
09:55:17 <Vorpal> Given that it has more stuff
09:55:51 <fizzie> ("avx2" is a tipoff, technically.)
09:56:20 <Jafet> "flags: vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx rdtscp lm constant_tsc up rep_good nopl pni monitor ssse3 lahf_lm"
09:56:42 <fizzie> Jafet: It's what came in-between SSE3 and SSE4.
09:56:49 <fizzie> (Supplemental Streaming SIMD Extensions 3.)
09:57:00 <Vorpal> Jafet, is that your entire flags? Fairly old I guess?
09:57:16 <Vorpal> Though I think I can beat you, even if it is a bit of cheating:
09:57:18 <Vorpal> Features: swp half thumb fastmult vfp edsp java tls
09:57:54 <fizzie> flags: fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht syscall lm constant_tsc up rep_good nopl pni ssse3 cx16 movbe hypervisor lahf_lm dtherm
09:58:00 <fizzie> (Intel Atom 230, not virtualized.)
09:59:16 <fizzie> No idea. Could be something Atom-specific, I guess.
09:59:35 <fizzie> Oh, no, it's also in these bigger flag lists.
10:00:13 <Vorpal> Yeah they aren't sorted, so it is kind of hard to find
10:00:27 <Vorpal> I guess they are sorted somewhat chronologically.
10:00:45 <Vorpal> Btw, I have an old P3 that I could boot to check the flags, but I'm not sure I care, the power isn't connected and so on
10:00:52 <fizzie> CPUID bit order, presumably.
10:01:22 <Vorpal> Which would be reasonably chronological
10:01:37 <fizzie> This system does not have a "flags" entry in cpuinfo at all, does that count as a list of length 0?
10:02:40 <Vorpal> fizzie, RPi? I think we can use the "Features" then
10:02:53 <fizzie> There's no "Features" either.
10:02:59 <fizzie> "system type: 96368MVWG" "cpu model: BCM6368 V3.1"
10:03:18 <fizzie> Oh, there's "ASEs implemented:" but it's empty.
10:03:22 <fizzie> And I don't know what an "ASE" is.
10:03:31 <fizzie> But it sounds like a list of some kind of extensions.
10:05:00 <fizzie> dtherm is apparently the "Digital Thermal Sensor Capability" bit (CPUID function 06h, bit EAX[1]); as far as I can tell, it's what the coretemp thing reads.
10:07:17 <fizzie> "Features: swp half fastmult vfp edsp neon vfpv3" this phone has a list one element shorter than the RPi.
10:07:55 <fizzie> (Also somewhat different; no thumb, and noen + vfpv3 in place of java + tls.)
10:08:21 <fizzie> I'm pretty sure it can run Thumb code, so I don't know why there's no Thumb flag. Maybe it's a kernel thing.
10:09:13 <Jafet> "bogomips: 4548.57"
10:09:43 <fizzie> 398.33 BogoMIPS on the MIPS box.
10:10:31 <Vorpal> bogomips: 6621.52 is my desktop
10:10:37 <fizzie> Sounds like a bogus result on the RPi.
10:10:44 <myname> what the hell are bogomips
10:11:05 <fizzie> I have 249.96 on the phone, 1993.93 on this Android tablet and 6799.32 on the desktop.
10:11:16 <Jafet> Is that, like, more bogus than bogomips
10:11:20 <Vorpal> myname, number of NOPs per second as measured early during boot by the kernel to calibrate some internal delay loop iirc
10:11:35 <Vorpal> Not sure why it is 2 on the RPi though, that seems wrong
10:11:51 <myname> i have to check that :D
10:12:05 <Vorpal> https://en.wikipedia.org/wiki/BogoMips
10:12:28 <fizzie> I seem to recall I had some system where the BogoMIPS number changed according to cpufreq scaling. Doesn't seem to happen on this desktop, though.
10:13:41 <Vorpal> fizzie, constant_tsc probably counteracts it (the feature that results in that flag that is)
10:13:53 <Vorpal> Pretty sure it scaled back on older computers yes
10:26:36 -!- yorick has joined.
10:26:45 <oerjan> "The reasons (there are two) it is printed during boot-up is that a) it is slightly useful for debugging and for checking that the computers caches and turbo button work, and b) Linus loves to chuckle when he sees confused people on the news."
10:27:46 <fizzie> Good old turbo button.
10:28:37 <Jafet> Is that the button that made your CPU slower
10:29:42 <fizzie> Though I vaguely recall one system that was wired to be faster (16 MHz vs. 8 MHz) with the button pressed.
10:30:44 <Vorpal> I guess BogoMIPS is a bit like glxgears then, useless except to tell that your system isn't completely out of whack
10:33:29 <Jafet> "158 frames in 5.0 seconds = 31.595 FPS"
10:33:36 <Taneb> int-e, elliott could you make lambdabot join #cs-york for a bit?
10:33:48 <Jafet> We should really have GPU virtualization by now.
10:34:13 <fizzie> I think Nvidia did have some stuff towards that direction?
10:34:22 <fizzie> For their computing-oriented hardware, anyway.
10:34:45 <Vorpal> Jafet, we should, but most people who virtualize don't game
10:34:51 <Vorpal> At least on the same machine
10:36:18 <oerjan> i recall glogbot accepts channel invites, how bad would it be to do the same for lambdabot
10:37:10 <Jafet> Nvidia Grid is fairly new, I think
10:37:30 <Jafet> Also, they loves segmentation
10:38:05 <int-e> oerjan: I don't know. Are there honeypot channels here where joining gets you killed? ;-)
10:38:08 <oerjan> (i assume the main worry would be if lambdabot gets too overworked)
10:38:15 * int-e is too paranoid for that.
10:38:31 <oerjan> int-e: well yes but you have to be _on_ them to invite, no?
10:38:48 <oerjan> i'm talking about the technical invite which only a channel op can do, afaiu
10:41:31 <Vorpal> <int-e> oerjan: I don't know. Are there honeypot channels here where joining gets you killed? ;-) <-- think so yes
10:42:12 <Vorpal> oerjan, I think you only need to be op of +m is set?
10:42:43 <Vorpal> oerjan, if you /part, we can test I guess
10:42:58 -!- fungot has left.
10:43:07 <fizzie> [13:43:54] -!- #esoteric You're not a channel operator
10:43:13 <fizzie> (When trying to invite fungot.)
10:43:16 <Vorpal> * oerjan #esoteric :is already on channel
10:43:19 -!- fungot has joined.
10:43:26 <Vorpal> I guess the checks happen in a weird order
10:43:30 <oerjan> i was about to part when i saw fungot do it
10:43:30 <fungot> oerjan: ( though its experimental and instrumenting) ' it)
10:43:37 <myname> from that kernel onward the BogoMips rating for then current Pentium CPUs was twice that of the rating before the change. The changed BogoMips outcome had no effect on real processor performance.
10:44:58 <int-e> I imagine the patch name was "improve bogosity of bogomips"
10:46:30 <Jafet> http://www.amazon.com/dp/B00CA5MLCS Enterprise ready GPU virtualization. At least they're cheaper than some Xeons.
10:47:05 <Vorpal> Jafet, are those Telsa series with no actual display connectors?
10:47:43 <Vorpal> So useless for non-HPC then, right
10:47:46 <int-e> (For a moment I was wondering whether that was the real name.)
10:48:44 <int-e> Honestly, there are too many codenames for all the GPUs and CPUs, who's expected to track them?
10:49:04 <fizzie> Vorpal: Something discovered recently: if you have a channel with modes +if (invite-only, forward on; the latter needs the former), and the person trying to join the channel is either banned or already on the target channel of the +f, the error message given is the "cannot join, invite-only" one instead.
10:49:33 <fizzie> We have some Tesla cards in the local computing cluster of the university.
10:49:40 <Vorpal> int-e, Tesla is a product line. Like i5 and i7 or GeForce and Quadro
10:50:03 <Jafet> Vorpal: no display connectors, but they are intended for graphics
10:50:23 <Vorpal> Jafet, I thought Tesla were intended for GPGPU?
10:50:34 <Jafet> Also, a better example is Celeron
10:50:39 <fizzie> "10 compute nodes gpu[001-011] are HP SL390s G7 for gpu computing. Same configuration as above but they are 2U high and have 2x Tesla 2090 card each."
10:50:42 <Jafet> I think some new CPUs are still Celerons.
10:50:57 <Vorpal> Really? I thought i3 replaced that segment
10:51:17 <int-e> Vorpal: as I said, who's supposed to keep track. I've heard of "Tesla" and not of "Telsa" but took a moment to make the connection, because there was nothing obviously wrong with the latter name.
10:51:27 <Jafet> No, i3 is the lowest rung of the high-end Core series.
10:51:40 <Vorpal> int-e, oh I didn't even notice my typo
10:51:45 <Jafet> Intel makes plenty of smaller CPUs.
10:51:56 <Vorpal> int-e, not even when you repeated it
10:52:10 <fizzie> I didn't notice the typo either, and the conversation was all manner of confusing.
10:52:22 <int-e> Vorpal: the human brain is a marvellous thing ;-)
10:54:08 <Jafet> https://en.wikipedia.org/wiki/Celeron I think every Intel generation since P6 is represented here
10:55:51 -!- ais523 has joined.
10:56:45 * int-e notes with joy that KICK and INVITE have their operands swapped.
10:56:49 <Jafet> (Sometimes "smaller" just means "we turned half the cache off")
10:57:19 <int-e> err, parameters to stick to the RFC wording.
10:58:14 <int-e> So implementing this is not too hard (at most 5 lines of code), I just wonder whether I want to have that feature.
10:58:49 <int-e> this is the internet
10:58:51 <Jafet> Or non-people, as the case may be
10:58:55 <int-e> I don't trust people ;-)
10:59:06 <Jafet> Do you trust fungot
10:59:06 <fungot> Jafet: its pretty easy to use. that always does the right if 90 is straight down then it should
10:59:19 <int-e> fungot has not done me any harm yet
10:59:19 <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
10:59:26 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
10:59:53 <Jafet> fungot never talks to me like that.
10:59:53 <fungot> Jafet: heh. ( fnord tsh) ( seems ( ( prefix notation) confusing)) to change it to create a whole breed of new fnord languages.
10:59:56 <int-e> Ah, it's the recursive style.
11:00:16 <fizzie> No, that would be "fungot".
11:00:16 <fungot> fizzie: dpkg -i is ok to count your own artificial language when asked how many languages the fnord speak
11:00:19 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
11:00:34 <int-e> Which is still dominated by the f word.
11:00:34 <fizzie> The small bits of Finnish come from ircnet/#douglasadams, where there occasionally was a bit of it.
11:01:15 <fizzie> No statements of the f are part of the "irc" style, since the model was trained before the bot existed.
11:01:38 <fizzie> Oh, you meant the other f word.
11:01:42 <fizzie> Yes, there's that mapping.
11:02:39 <Jafet> `addquote <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
11:02:39 <fungot> Jafet: fnord it. :p it could be managed with the right hand
11:02:40 <HackEgo> 1183) <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
11:03:10 <int-e> so what does "niinku" mean?
11:03:58 <int-e> Oh it's just a filler, like, that.
11:04:00 <fizzie> It's a contraction of "niin kuin", which is approximately something like "as if".
11:04:18 <fizzie> The original source of the "niinku" line seems to be a DRUGZ reference. :/
11:05:18 <fizzie> (Most of the "fnords" were different Finnish nicknames for hashish.)
11:11:03 <int-e> a couple of those are mysterious to me. Agora, for example.
11:11:27 <fungot> Selected style: sms (National University of Singapore SMS corpus, 2011-08-20)
11:11:37 <int-e> fungot, is that as bad as I imagine it would be?
11:11:37 <fungot> int-e: can i use short form to. thanks
11:11:48 <int-e> fungot, please don't
11:11:48 <fungot> int-e: only one place can sit to bishan, take the barcap... all thebest!! :) its time bah, cause i was thinking of coming to soc. btw how to go downfron bugis. u lookfor place
11:12:05 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
11:12:27 <fizzie> That was a reasonably tame example of the SMS style.
11:12:32 <fizzie> It's p. bad occasionally.
11:13:01 <int-e> worse than a f n o r d loop?
11:13:31 <fizzie> Matter of taste, I guess. I don't think it has those at all.
11:13:39 <fizzie> But more of that "u lookfor" kind of stuff.
11:14:03 <ion> http://www.cartoonbrew.com/ideas-commentary/sony-demands-removal-of-open-source-indie-short-sintel-from-youtube-98182.html
11:22:30 <Jafet> Wow, a corporate video host stops hosting a video. Much censor.
11:23:16 <ais523> I guess Sintel is sort-of "famous" in that it was one of the first entirely open-source-rendered CGI videos
11:23:26 <ais523> it's mostly a tech demo
11:23:44 <Vorpal> * int-e notes with joy that KICK and INVITE have their operands swapped. <-- Yes, there are more cases like that in IRC iirc. I wrote an IRC bot once and I noticed quite a lot of strange things
11:24:50 <fizzie> Some other post said Sony added Sintel to their "4k demo reel" kind of thing, and speculated that led to the (presumably automatic) takedown request.
11:25:38 <Vorpal> fizzie, fnord was basically unique words right?
11:26:13 <fizzie> For the old models; the new ones, trained with VariKN, mostly have just discarded them, I think.
11:27:02 <Vorpal> fizzie, what did you use the train the new models?
11:28:45 <Vorpal> This computer combined with Debian Stable has a really interesting bug btw. If I pause playback in vlc, sound will stop working on resume, I have to do a jump in the video/audio stream to reset it. Either backwards or forward, doesn't matter how long either.
11:28:58 <Vorpal> fizzie, err I meant the old ones
11:29:31 <fizzie> Oh. It doesn't have a name, it was just a custom piece of C++ (of all things) doing a fixed-length unpruned N-gram.
11:30:20 <fizzie> (Rather crummy code, too.)
11:31:06 <Vorpal> Well it is C++, good look not being crummy
11:33:34 <fizzie> http://sprunge.us/SLKb?c++ I guess it's not that bad, but it's not that good either.
11:34:02 <fizzie> Also what's really silly is that the only code to test a generated model was in the same program, so I needed to rebuild the whole thing to generate sample sentences.
11:34:03 <Vorpal> That is interesting indentation
11:34:11 <Vorpal> Or is that sprunge messing up tabs?
11:35:15 -!- Phantom_Hoover has joined.
11:38:06 <fizzie> It uses the time-tested approach of "just throw strings" to C++ exceptions.
11:38:22 <fizzie> (Or, rather, "just throw string literals".)
11:38:54 <Vorpal> Pretty sure that is not considered good practice
11:39:10 <ais523> it's better than throwing malloc'ed strings
11:39:12 <Jafet> That is, secretly, what most C++ exceptions are made of
11:39:25 <ais523> (although even that is better than a mix of throwing malloc'ed strings and string literals)
11:39:48 <Vorpal> On the other hand I have never been a fan of exceptions in general. There is often a better solution
11:39:49 <Jafet> Throwing malloc'd strings is horrible. You should be using new.
11:40:14 <Jafet> Vorpal: they are great for cross-function control flow
11:40:19 <ais523> Jafet: I was trying to think of the most horrible sort of exception I could off the top of my head
11:40:48 <ais523> although I have a Java program that throws integers (specifically speaking, a class deriving from Exception with only one int member of its own)
11:40:52 <ais523> because it was translated from C
11:41:13 <Jafet> I have a factoring program that throws any factors discovered
11:41:35 <Vorpal> Generally I prefer co-routines for that
11:41:45 <Vorpal> (Assuming the language allows that of course)
11:41:54 <Vorpal> (Also assuming you mean the same thing as I do)
11:42:06 <nortti> can be simulated pretty easily, even in c
11:42:19 <Vorpal> I know, but not elegantly really
11:42:43 <nortti> yeah, that or non-re-entrant
11:42:47 <Jafet> The program has several layers of function calls, which makes simulating coroutines unpleasant.
11:43:03 <Vorpal> nortti, also thread safety
11:43:25 <Jafet> I could use a lambda object as a continuation, but it gets annoying to pass it around.
11:50:19 -!- stuntaneous has quit (Ping timeout: 264 seconds).
11:52:34 <oerjan> `run allquotes | tail -1
11:52:34 <HackEgo> 1183) <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
11:52:54 <oerjan> `run sed -i '1183s/ </ </' quotes
11:52:59 <oerjan> `run allquotes | tail -1
11:52:59 <HackEgo> 1183) <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
11:53:50 <HackEgo> qdbformat is: <nick> message; * nick action; two spaces between messages; all elisions marked with [...] other than irrelevant intervening messages; for messages separated by elision, one space on each side, not two
11:57:54 <Jafet> `addquote oerjan says:`? qdbformat[...]oerjan says:hth
11:58:54 <ion> What is this evil quote format?
11:59:32 <int-e> It allows us to achieve great wisdom.pdf
11:59:53 * int-e is too lazy to check the repo.
12:00:01 -!- Tritonio1 has joined.
12:00:19 <oerjan> the format is considerably older than the pdf hth
12:00:38 -!- Tritonio has quit (Ping timeout: 240 seconds).
12:01:29 <int-e> Because it does not answer this question: Where else is the format exploited?
12:03:11 <oerjan> it's simply a measure of consistency. it also helps a bit when quotes themselves contain quotes.
12:04:15 <oerjan> not in every case though.
12:04:21 <HackEgo> 262) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something \ 307) <cpressey> `quote django <HackEgo> 352) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something <cpressey> thankfully only one \ 308) <monqy> `quote django <HackEgo> 352) <olsner> django is named a
12:15:39 -!- boily has joined.
12:20:38 -!- nooodl has joined.
12:29:18 -!- Tritonio1 has quit (Quit: Tritonio1).
12:40:53 -!- MindlessDrone has joined.
12:47:06 <HackEgo> #!/bin/sh \ nl -w 1 -s ') ' quotes
12:47:47 <HackEgo> <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
12:57:26 <boily> now that HackEgo seems to be alive and well, I should get back to updating the Wisdom...
12:57:52 <ais523> does it have logs yet?
12:58:39 <HackEgo> /hackenv/bin/pastlog: 2: cd: can't cd to /var/irclogs/_esoteric \ ls: cannot access ????-??-??.txt: No such file or directory
12:59:04 <oerjan> your logs are in a different castle
13:00:42 <boily> lexande: hellexandello. my name is boily. you don't have a Wisdom Entry describing you. prepare to be wisdomified.
13:04:55 <Vorpal> What happened to the logs?
13:05:10 <ais523> they're still there, they're just not inside HackEgo's VM
13:05:11 <boily> elliott: you are vile. you rmed the *elcome*s.
13:05:15 <ais523> so HackEgo can't see them
13:05:21 <ais523> `welcome what about this one
13:05:21 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: welcome: not found
13:06:16 <ais523> it's a "new" VM, new as in no more than several monthd old
13:06:43 <Vorpal> What caused the revert?
13:06:53 <Vorpal> I thought it was all in hg so it would be easy to restore a backup
13:07:34 <oerjan> ais523: um elliott deleted the welcomes in a fit of ...something...
13:07:54 <ais523> Vorpal: the filesystem wasn't reverted
13:07:58 <boily> elliott deleted the welcomes in a fit of binaries???
13:08:02 <ais523> just the VM is on a different physical computer
13:08:09 <ais523> not the same one that's doing the logging
13:09:58 <oerjan> yes the logs were never inside the repository, just mounted on the same machine
13:11:06 <oerjan> although the codu.org webserver obviously has access to both
13:12:05 <HackEgo> df: cannot read table of mounted file systems: No such file or directory
13:12:39 <HackEgo> ls: cannot access /var: No such file or directory
13:12:43 <HackEgo> bin \ dev \ etc \ hackenv \ home \ lib \ lib64 \ opt \ proc \ sbin \ sys \ tmp \ usr
13:13:58 <oerjan> ais523: the spanish welcome is still there, but elliott tells me all the recurring spanish people are the same anyway
13:18:33 <elliott> this is a spanish-language channel, after all
13:19:42 <oerjan> elliott: well that welcome has been tailored specifically to make it clear we're not.
13:21:23 <oerjan> it's a shame, really. i was somehow imagining somewhere a venezuelan site with a convenient list of irc channels people could try, which had somehow been made by grepping for es in channel names
13:22:12 <ais523> I want to believe that now
13:22:30 <elliott> not *all* the spanish people are one person
13:22:36 <elliott> there was just one particularly persistent one over the last few months
13:22:51 <elliott> I think the "es" hypotesis is plausible.
13:23:30 <oerjan> elliott: are all the venezuelans the same?
13:24:42 <oerjan> good, good, we can continue to believe then
13:29:10 <fizzie> oerjan: If you want to get all technical about it, the HackEgo hg browser is actually running on www2.codu.org, a different VPS (the one HackEgo also runs), and www.codu.org just (AFAIK) proxymates the access.
13:33:40 -!- metasepia has joined.
13:33:50 <metasepia> ENVA 061320Z 26007KT 9999 FEW040 SCT070 08/01 Q1007 NOSIG RMK WIND 670FT 36002KT
13:34:16 <metasepia> Your divination: "Obstruction" to "Clustering"
13:39:03 <ais523> b_jonas: sorry about you getting caught in the spam filter, that's probably the first false positive in the modern era of spam filtering
13:39:20 <ais523> (graue's spam filter blocked "span" and "div", that was hilarious…)
13:39:28 <ais523> (…in that it lead to some interesting workarounds)
13:39:46 <oerjan> yeah we had span and div _templates_ instead
13:40:34 <oerjan> and it took some silly workarounds to make _those_ without triggering the filter in the process.
13:41:00 <ais523> oerjan: a spambot somehow managed to make a page whose URL triggered the spam filter if it appeared in the Referer header
13:41:31 <ais523> given that deleting a page is a POST request, that took a bunch of confusion before I told my browser to turn referers off on Esolang
13:45:07 <oerjan> it seems there isn't that much spam nowadays, there have been no new filter catches since fizzie fixed the logging. well, unless it broke again i guess.
13:45:37 <ais523> just a thought: fizzie's server is a different physical server from elliott's, right?
13:45:42 <ais523> so presumably it has a different IP
13:45:47 <ais523> perhaps the spambots don't use DNS
13:46:06 <ais523> the IPv4 space is easier to bruteforce than the domain name space…
13:46:31 <oerjan> ais523: um how can they post to a webserver without knowing the hostname?
13:46:45 <oerjan> i suppose some might allow it...
13:46:58 <ais523> webservers often have a default hostname
13:47:06 <elliott> or rather, solidity did not
13:47:16 <fizzie> And the new esolangs.org does not, either.
13:47:47 <fizzie> (Because the "default" server, the one it hits without a esolangs.org Host: header, is the www2.codu.org one, where there's just the hg browser and nothing else.)
13:49:15 * oerjan now imagines interlinking the wiki and HackEgo
13:50:21 <fizzie> Would you like HackEgo to post all recent changes on-channel?-)
13:50:27 <fizzie> (MediaWiki has some features for that.)
13:51:20 <fizzie> (I mean, they're not for IRC in particular, but it has some general mechanisms for getting change notifications out.)
13:51:59 <ais523> fizzie: I think they were originally for IRC
13:52:09 <ais523> in fact, IRC's the recommended official way to get a stream of all changes to Wikipedia
13:52:11 <ais523> if you need one for some reason
13:53:27 <elliott> fizzie: I tried to set that up once.
13:53:37 <elliott> there are pre-built bridges from the UDP thing to IRC.
13:53:49 <FireFly> It sounds a bit spammy, but maybe it's not too bad
14:02:04 -!- Sorella has joined.
14:03:35 <fizzie> FireFly: There aren't typically very many changes/day, so there's at least that.
14:09:34 <fizzie> (On the other hand, it's kind of a silly idea, and we all know how serious and, for want of a better word, reserved, this channel is.)
14:11:12 <fungot> Selected style: europarl (European Parliament speeches during approx. 1996-2006)
14:11:35 <oerjan> fungot: what is your opinion on the meat shortage?
14:11:36 <fungot> oerjan: in fact, this would result in a conclusion that is perceived as a lame duck in the community institutions the council, to the framework of agenda 2000 but also to the rights associated with citizenship, which must be understood in every country, probably loses more from the commission was behind the policy choices now about what we are discussing this morning because these are very important.
14:12:10 -!- Patashu[Zzz] has quit (Ping timeout: 268 seconds).
14:12:32 <oerjan> well that certainly clears it up.
14:13:37 * oerjan forgot the "excuse me"
14:18:40 <fizzie> fungot: How come you didn't address the channel as "Mr. President"?
14:18:41 <fungot> fizzie: mr president, ladies and gentlemen, the emperor is not wearing any clothes. these organisations are often under threat, at a revised directive for the duty of care for all those who have battled very fnord against the dual use of the most important details are dealt with objectively and impartially so that all of that here, hardly anybody, or rather on public access to documents which, due to the lack of backbone of the
14:21:36 <boily> fungot: what is your foreign policy on the Existence of Canada?
14:21:36 <fungot> boily: madam president, i have tried to impose its legal point of view to match the objectives and procedures agreed upon by the commission on this issue. the commission can accept the first part of the amendment of directive 90/ 220/ eec, according to the united states
14:27:36 <Jafet> Sounds like you're getting annexed.
14:29:12 <FireFly> fungot: what are your thoughts concerning the situation in Crimea?
14:29:13 <fungot> FireFly: madam president, commissioner, the copenhagen facility, money is given to improving transparency and a closer relationship with the applicant countries on this day that franz fnord fnord was murdered, together with a series of dictates issued from brussels as to what is being done, and i very much welcome an extension of the single market
14:30:34 <ais523> wow, that almost seems relevant
14:31:46 <FireFly> I'm sorry fungot, I can't let you do that
14:31:47 <fungot> FireFly: mr prodi, i ask the president-in-office of the council! we should note that the report only covers areas over which there is discussion everywhere the usa cannot achieve this itself. perhaps with that background it is totally wrong. as far as the framework is concerned.
14:33:18 <Jafet> I honestly hope "money is given to improving transparency" is a synthesis
14:33:28 <Melvar> (Regarding the es hypothesis, #selinux says in its /topic that the swedish linux channel is #linux.se .)
14:34:01 <Jafet> Also, franz ferdinord
14:34:20 <ais523> Melvar: haha, that's also brilliant
14:34:36 <ais523> as a joke, or does it come up often enough that they felt it was required?
14:37:56 <Melvar> Does someone know a good way to pipe /list into grep?
14:38:55 <ais523> you could hack together something involving netcat, nobuffer, and tee, I guess
14:39:08 <ais523> not sure if the nobuffer is required, it often is, though
14:41:12 <ais523> boily: it's something I wrote, but I'm sure loads of other people wrote it too
14:41:44 <ais523> it basically just adds LD_PRELOAD hooks to get stdio to stop buffering, you inject it into programs that use default stdio buffering in cases where that's unacceptable for what you're doing
14:42:03 <ais523> (and it does /that/ by hooking fopen and friends to call setvbuf and turn buffering off)
14:42:22 <Jafet> Does that do more that stdbuf?
14:44:01 <HackEgo> stdbuf: missing operand \ Try `stdbuf --help' for more information.
14:44:17 <HackEgo> Usage: stdbuf OPTION... COMMAND \ Run COMMAND, with modified buffering operations for its standard streams. \ \ Mandatory arguments to long options are mandatory for short options too. \ -i, --input=MODE adjust standard input stream buffering \ -o, --output=MODE adjust standard output stream buffering \ -e, --error=MODE adjust standard
14:44:27 <ais523> oh neat, it even has a standard name
14:44:37 <ais523> and is installed here too
14:44:46 <ais523> so I needn't have written nobuffer after all :-)
14:44:46 <Jafet> stdbuf is in coreutils.
14:45:01 <Jafet> I suspect it only sets fd buffering, though, not stdio.
14:45:18 -!- oerjan has set topic: Note that the Spanish Oteric channel is #oteric.es | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
14:46:00 <ais523> Jafet: no, it sets stdio buffering
14:46:03 <ais523> fds don't /have/ buffering
14:46:28 <boily> interesting. “stdbuf --help”'s French translation is only halfway done, with random sentences in English.
14:47:07 <Jafet> "BUGS: On GLIBC platforms, specifying a buffer size, i.e. using fully buffered mode will result in undefined operation."
14:47:14 <ais523> stdbuf's info page states that it doesn't work with tee, because tee changes buffering itself
14:47:19 <Jafet> So yes, stdbuf truly is just nobuffer.
14:47:21 <ais523> so maybe you don't need a nobuffer with tee
14:53:15 <Jafet> Among other lesser-known coreutils is ptx, which can be used to make a search engine.
14:54:56 <boily> what the fungot is that mysterious utility...
14:54:56 <fungot> boily: mr president, as we have always been a broad measure of agreement between the european union to take the results of the brussels 2 convention, but also with their quality.
14:55:03 <ais523> Jafet: ptx confuses me a lot
14:55:14 <boily> Jafet: ptx puzzles me a lot.
14:55:15 <ais523> mostly because I can't figure out what it's meant to do even after reading the info page
14:55:28 <ais523> well, it creates a permuted index
14:56:02 -!- oerjan has quit (Quit: Like an index, but all over the place).
14:56:26 <Jafet> I figured out what it was by running it on a file.
14:58:04 <ais523> you mean to say you ran a program without knowing what it did?
14:58:12 <ais523> even if it comes from coreutils, that seems a little risky
14:58:46 <Jafet> The manual clearly says that it reads input files and produces some kind of output
14:59:07 <Jafet> (It creates a strangely-formatted index of the input.)
15:00:03 <ais523> hmm, I wonder who maintains the coreutils Info file
15:00:14 <boily> it is decorative. I ran it on a DCSS morgue file. lots of zombies!
15:00:17 <ais523> if it isn't Ulrich Drepper, it may be worth working out what the program does and then sending a patch
15:01:06 -!- ter2 has joined.
15:02:42 <Jafet> I believe (and hope) that Drepper does not maintain anything in coreutils.
15:03:28 <FireFly> Who is Ulrich Drepper and why does that name look vaguely familiar?
15:04:31 <boily> FireFly: from gnulibc, “with Ulrich Drepper[4] as the lead contributor and maintainer.”
15:05:33 <ais523> that [4] looks ominous
15:06:55 <boily> of course it is ominous. it is the Number Four of Death!
15:08:25 <elliott> drepper no longer maintains glibc
15:08:33 <Melvar> Hey, it occurs to me that people here might know: Are there any other -l puns other than libiberty and libowfat?
15:08:51 <Jafet> Drepper is a very clever programmer and maintainer who often gets frustrated because many others are not as clever as he is.
15:09:08 <Jafet> I suspect -loobs is a reverse pun.
15:11:04 <ais523> I suspect that there are, but can't think of any offhand
15:11:28 <ais523> unless you count libraries that happen to make real words by coincidence, such as libick
15:11:44 <ais523> $ locate libick.a | wc -l
15:11:51 <ais523> wow I have a lot of compiled versions of INTERCAL
15:12:20 -!- tromp has joined.
15:12:39 <boily> some people have pron stashes on their machines. other collect intercal compilers...
15:13:13 <ais523> one of them is in a backup of my account on a SunOS workstation
15:13:23 <ais523> the account probably doesn't still exist, but who knows, it might
15:13:41 <ais523> I don't have physical nor network access to the computer in question, so no way to tell
15:15:06 <FireFly> That's handy, I didn't know about timeout(1)
15:15:14 <ais523> I imagine very few people my age have ever had the experience of accidentally writing programs that aren't portable to Unices other than SunOS
15:15:45 <ais523> "Some platforms don't curently support timeouts beyond 2038"
15:15:56 <ais523> Y2038K bugs are annoying
15:16:13 <ais523> in another 23 years, maybe there'll be a huge panic and I'll be called in to help out with the cleanup effort
15:16:22 <ais523> or maybe the world will end because people became complacent after Y2K
15:20:05 <mroman> I thought the world ended in 2012
15:20:21 <lifthrasiir> we need 2012 the game (a spin-off of 2048)
15:20:23 <ais523> I thought that theory was conclusively disproved in 2013
15:20:47 <mroman> ais523: Not conclusively
15:20:55 <ais523> lifthrasiir: easy, it's identical to 2048, except your goal is to make 2012 (via integer overflow, obviously)
15:21:06 <mroman> I mean... how do you know that 2012 doesn't exist anymore?
15:21:43 <lifthrasiir> ais523, or modulo 2012, which would be a bit more interesting
15:22:00 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: sdate: not found
15:22:13 <ais523> oh come on, what sort of self-respecting server doesn't have sdate?
15:22:41 <ais523> mroman: so you combine two 1024s to create a 36
15:23:47 <mroman> I have no idea what 1024 has to do with 36
15:24:11 <ais523> (1024 + 1024) % 2012 == 36, right?
15:24:38 <ais523> anyway, the integer overflow joke is that you can't integer overflow in 2048 because there's not enough room on the board, and if you could, you'd get 0
15:24:39 <mroman> I meant more the thing where time coexists
15:25:01 <ais523> oh, I pinged the wrong person
15:25:48 <lifthrasiir> ais523, yeah, 36. I'm actively destroying your joke :p
15:26:18 <lifthrasiir> since it is modulo 2012, the eventual goal would be to make 2012 modulo 2012, aka 0.
15:26:20 <ais523> but if it's modulo 2012, you can never get 2012 exactly, best you can get is 0 which is equivaent
15:26:30 <ais523> there isn't enough room to make 0 module 2012 either, though
15:27:18 <Jafet> wheezy has: libace libarch libass libast libawl libax libemma libend libib libice libid libint libion liboath libobby libode liboop liboping liboss libots libow libowfat libs libust, though most of them are probably unintended.
15:29:18 <ais523> is that in a default install?
15:29:37 <ais523> checking the repos would be even better, as in more false positives
15:32:00 <FireFly> I have only libass it seems, satisfying that criteria
15:32:31 <nortti> ais523: http://man.cat-v.org/unix-1st/1/sdate ?
15:33:06 <FireFly> `run ls /lib/lib*.so /usr/lib/lib*.so | sed 's:(/usr)?/lib/lib:l:; s:\.so$::' | sort | comm -12 - /usr/share/dict/words
15:33:07 <HackEgo> ls: cannot access /lib/lib*.so: No such file or directory \ comm: /usr/share/dict/words: No such file or directory
15:33:09 <ais523> also UNIX first edition predates september 1993
15:33:17 <ais523> Sun Sep 7523 16:33:03 BST 1993
15:33:44 -!- boily has quit (Quit: PERMUTATIONALISED CHICKEN).
15:33:46 <HackEgo> [wiki] [[User:Fizzie]] M http://esolangs.org/w/index.php?diff=39225&oldid=39224 * Fizzie * (-59) I removed a test, but it keeps happening.
15:33:47 -!- metasepia has quit (Remote host closed the connection).
15:33:49 <HackEgo> Today is Sweetmorn, the 23rd day of Discord in the YOLD 3180
15:34:50 <ais523> sdate is a great way to confuse random program
15:35:04 <ais523> it's quite common for programs to assume that there can't be more than 31 days in a month
15:36:27 <ais523> how can you say that on September 7523?
15:36:57 <FireFly> Now I see what sdate is doing
15:37:01 <nortti> well, as long as one uses gregorian calendar
15:37:26 <ais523> the sdate calendar is much simpler in many ways
15:37:27 <fizzie> Huh, I thought the above didn't work at all, because I was all scrolled up in the backscroll.
15:40:30 -!- zzo38 has joined.
15:46:07 <Jafet> for l in $(apt-cache search --names-only 'lib.*' | grep -Eo '^lib[aeiou][a-zA-Z]+' | uniq | sed 's/^lib/l/'); do for i in `seq $#l -1 3`; do if ( dict -s exact -d wn -m ${l[1,$i]} >/dev/null 2>&1 ); then echo $l; break; fi; done; done
15:46:43 <Jafet> Most of the matches are the minimum, 3 letters long.
15:50:11 -!- ^v has joined.
15:51:58 <fizzie> ais523: Quite a lot of our university (including a classroom full of UltraSPARC 10 workstations, and both main general-use shell servers) ran on SunOS not more than a decade ago, so I think a lot of our CS students have that experience.
15:54:38 <maurer> Heh. My main experience with Solaris is that killall will in fact, kill all.
15:55:31 <fizzie> Incidentally, if I make "test" edits of my user page (e.g. after upgrade, to test that everything still works), is it considered good MediaWiki administrative practice to somehow undo those (if that's even possible) so that they don't clutter up RC or page history?
15:56:35 <Vorpal> ais523, sdate does some sort of LD_PRELOAD?
15:57:42 <Vorpal> Hm I suspect it won't break cfunge, I only think I use unix timestamp in that for the DATE fingerprint
15:58:29 <Vorpal> Oh, DATE doesn't even have a command to get current date?
15:59:17 <Vorpal> Oh okay, TIME uses localtime/gmtime, so that would be confused
16:15:14 <fizzie> Gah, the offline experience of Google Maps Android has gone so downhill.
16:15:16 <fizzie> It used to be so that you had a separate "Offline" tab in "My Places", where you could see a list of what's available offline, and remove/add regions, and when adding you could drag the bounding box what you want to cache.
16:15:20 <fizzie> But in this 7.x version, there seems to be no way at all of seeing what is available offline, and adding new regions is done by the most illogical way I have ever heard of: you zoom the map so that what you want to cache offline is visible, and then search for "ok maps".
16:15:24 <fizzie> Then it flashes briefly something to the tune of "caching map data", but afterwards there seems to be no indication of what exactly it saved.
16:16:01 <Phantom_Hoover> <fizzie> Incidentally, if I make "test" edits of my user page (e.g. after upgrade, to test that everything still works), is it considered good MediaWiki administrative practice to somehow undo those (if that's even possible) so that they don't clutter up RC or page history?
16:16:12 <Vorpal> fizzie, downgrade if you can, that is what I did
16:16:26 <fizzie> I mean, just compare: https://support.google.com/gmm/answer/2650377?hl=en&ref_topic=2649131 https://support.google.com/gmm/answer/3273567?hl=en&ref_topic=3273087
16:16:38 <ais523> fizzie: (re the comment Phantom_Hoover quoted) no, although sometimes it's considered good form to use a page designed for test edits
16:16:50 <ais523> those pages can later have the test edits removed in batch
16:17:07 <ais523> actually, that reminds me of the old AfD page on Wikipedia
16:17:55 <ais523> before it was split into subpages, it had been edited so many times that when an annoyed admin deleted it, it brought the site down because the server couldn't handle deleting that many edits
16:18:13 <ais523> then when it was subsequently undeleted (after the site came back up), it brought the site down again
16:18:44 <ais523> then the developers added a limit that you can't delete pages that have been edited 5000 or more times, so some enterprising admin decided to get a bot to edit the Main Page 5000 times in order to stop it being deleted
16:19:00 <ais523> the developers stopped that at like 3000 because it was creating a bunch of load in of itself
16:19:03 <Vorpal> ais523, also how could it bring the server down if the delete isn't permanent? Isn't it just marking a flag then
16:19:37 <Vorpal> ais523, would the main page be in risk of being deleted though?
16:19:38 <ais523> it's not exactly a flag internally, the edit gets moved to a separate table, and a whole bunch of tables that relate to non-deleted edits get change
16:19:50 <elliott> fizzie: notifying people the wiki upgraded is prtetty useful, anyway
16:19:53 <ais523> and yeah, the main page used to get deleted quite frequently
16:20:13 <Vorpal> ais523, why? Shouldn't those admins that did it get fired then?
16:20:14 <ais523> it was the #1 most common action for disgruntled admins (which is strange, because it doesn't cause a whole lot of damage)
16:20:31 <Melvar> It’s rather visible though.
16:20:38 <ais523> and yeah, obviously they were desysopped, unless they could successfully pass it off as a joke and also a lapse of judgement at the same time
16:20:47 <Vorpal> elliott, well the equivalent. Stripped of their rank, whatever
16:20:53 <ais523> I think it has been deleted by accident before now
16:21:01 <ais523> anyway, there are a whole bunch of protections in place nowadays
16:21:39 <ais523> I think I'm one of the few people who knows how to delete the Main Page through them, and even then, a) I no longer have the perms; b) with the protections in place, doing so would be rather time-consuming, and there'd be a pretty high chance someone would notice what I was doing and stop me
16:22:24 <ais523> using a bot to help out would make it a bit faster, although testing it would be awkward; if you're going to break the rules to the extent of running an unapproved bot
16:22:32 <ais523> err, to the extent of deleting the main page
16:22:42 <ais523> you're probably not going to be worried about running an unauthorized bot
16:23:00 <elliott> testing it sounds easy, just run a local test wiki
16:23:52 <Phantom_Hoover> <ais523> before it was split into subpages, it had been edited so many times that when an annoyed admin deleted it, it brought the site down because the server couldn't handle deleting that many edits
16:24:16 <FireFly> According to http://en.wikipedia.org/wiki/Wikipedia:Don't_delete_the_main_page it's protected in the mediawiki software nowadays
16:24:21 <ais523> not sure, I don't typically remember the names of specific disgruntled admins
16:25:02 <ais523> this is why very few people would be able to delete it, you'd need a knowledge of how the software works in addition to a knowledge of the redundant protections on enwiki in particular
16:25:14 <ais523> and for all I know, they may have added more since I stopped actively adminning Wikpedia
16:27:32 * Melvar is amused that Wikipedia:Don't delete the main page has the shortcut WP:IDIOT .
16:28:26 <ais523> those shortcuts are incredibly cheap to create
16:28:37 <ais523> you could make one right now if you felt like it, and given that they're rather more expensive to delete
16:28:46 <ais523> if it's remotely plausible people would probably just let it stay
16:29:25 <b_jonas> and there are lots of them on en.wikipedia: the very long page https://en.wikipedia.org/wiki/User:B_jonas/Pages_with_shortcuts lists many of them
16:29:55 <b_jonas> note that it only lists ones where the target page has a template marking the shortcut
16:29:56 <Melvar> Wikipedia:Village stocks apparently has WP:AAAARGH
16:30:10 <b_jonas> and there are lots more where the target page isn't marked
16:30:52 <b_jonas> there are shortcuts like P:P -- guess where that goes
16:31:28 <ais523> P: is Portal:, I guess
16:31:37 <ais523> but there are numerous portals that could start with P
16:34:26 <ais523> probably most of them actually do start with P
16:35:17 <Melvar> “WP:Oh I say, what are you doing? Come down from there at once! Really, you're making a frightful exhibition of yourself.”
16:36:46 <FireFly> The target's title doesn't make *much* more sense
16:37:32 <ais523> Melvar: I remember that page being created
16:37:39 <ais523> I forget the context, but ISTR it was necessary
16:42:55 <Jafet> Does that redirect to the reichstag page
16:54:16 <Vorpal> <ais523> I forget the context, but ISTR it was necessary <-- what? Why?
16:54:38 <Vorpal> My mind just boggles at the idea such a page could be *required*
16:54:50 <ais523> like, people were taking something too seriously, and it was causing problems
16:55:49 -!- Frooxius has quit (Read error: Connection reset by peer).
16:56:26 <ais523> I think there were also people who didn't understand WP:POINT
17:05:41 <nooodl> ooh https://en.wikipedia.org/wiki/P:X
17:24:15 <HackEgo> q-revercoin holdecoin quiseporacoin glypecoin usaumcoin rfollocoin baggedcoin temparncoin l3841coin zowcoin braincoin :coin redgrecoin mempaicoin raintfcoin petrocoin sellcoin thumorecoin toicoin condicoin
17:25:15 <HackEgo> rhotorcoin nconveccoin gracoin smycelcoin kayakcoin bythessenhohcoin dobbocoin brbcoin devercoin rnarycoin memmentcoin sedcoin sorccoin overspidcoin bhacoin convecorritcoin migoritaffcoin objectdrumcoin tbfcoin huntedlyearandeltcoin
17:25:24 <HackEgo> words ${1---eng-1M --esolangs 20} | sed -re 's/( |$)/coin\1/g'
17:28:51 -!- copumpkin has joined.
17:41:52 <fizzie> Huh, someone was just querying for "DrIvErcAzo.esOLaNGs.oRg" (with that capitalization) when I was debugging a (non-esolangs) DNS thing and looking at tcpdump.
17:42:07 <fizzie> (Spoiler: there is no such host.)
17:42:36 <ais523> I /said/ that brute-forcing the space of all domain names would be harder than brute-forcing IPs :-)
17:43:27 <fizzie> Huh, and now crawl-66-249-66-216.googlebot.com asked for "drivercazo.esolangs.org", in lowercase. Was that in fact something at some point?
17:43:57 <fizzie> Four Google hits for the name.
17:44:17 <ais523> perhaps someone linked to it
17:44:32 <ais523> and googlebot converts to lowercase
17:46:35 <fizzie> Two of the hits did have curious-looking links; for /stranica/drayver-dlya-netronix-mn01.html and /catalog/drayver-dlya-i7500.html.
17:56:38 <fizzie> Oh: https://isc.sans.edu/diary/Use+of+Mixed+Case+DNS+Queries/12418
17:57:16 <fizzie> (There were more mixed-case queries, so I got curious.)
18:01:29 <elliott> fizzie: IME the logs are always filled with the weirdest things
18:01:56 <elliott> fizzie: https://twitter.com/zucrowgo/status/184029492237438976
18:02:00 <fizzie> I haven't even looked at the web server log.
18:34:27 <kmc> douglass_: "We have two mugs of tea; one has pictures of geese and one has the MongoDB logo." shachaf: "Oh no, which is the lesser of two evils?"
18:54:28 <Vorpal> fizzie, interesting, that mixed case thing, but I wonder what happens when some DNS server doesn't maintain the case. Surely stuff will break then, and if you allow for that you basically nullified security.
18:55:41 <Vorpal> fizzie, You can't even reliably keep track of when it worked in the past of course, since the server software could change, or there could be some BGP anycast going on making it resolve to different servers at different points in time
18:55:48 <Vorpal> It probably works most of the time, but still...
18:56:36 <Vorpal> The page you linked even said "almost all" hm
18:58:07 <fizzie> Though of course that's just an empirical observation.
18:58:21 <Vorpal> I can only find a draft RFC for it
18:58:33 <fizzie> The draft is what I meant.
18:58:48 <Vorpal> That is quite a long time for it just to sit around as a draft isn't ut?
18:59:53 <fizzie> Long enough that it has expired, yes.
19:00:19 -!- tromp has quit (Remote host closed the connection).
19:00:31 <fizzie> (The validity period is six months.)
19:00:34 <Vorpal> Well I use unbound locally, I could probably turn it on
19:01:50 <fizzie> The expired draft does mention "a small set of rare and/or private label authoritative DNS implementations" that do lowercase names.
19:03:32 <kmc> geese don't have moral agency so I guess they can't be evil
19:03:37 <kmc> but they are vicious, though
19:03:39 <kmc> swans are worse though
19:03:46 <kmc> swans will break your arm
19:03:48 <Vorpal> kmc, are you sure they don't?
19:03:55 <kmc> they also fight to the death over territory
19:04:09 <kmc> which upsets people who want swans to be peaceful symbols of love
19:04:19 <kmc> I think pigeons are a much better peaceful symbol of love
19:04:27 <fizzie> I should probably finally get DNSSEC on for zem.fi one of these days; it's just that IIRC, the free secondary-DNS service I've been using doesn't grok the records.
19:04:30 <fizzie> (Kind of shabby that none of them do TSIG for zone transfers, either.)
19:04:37 <kmc> one time a flock of geese chased douglass_ and me down a hill and almost into the Charles River Basin
19:05:21 <ais523> there was that time when I was in the middle of a flock of geese, the ones behind me were trying to force me forwards in order to disturb the ones ahead of me
19:05:30 <ais523> none of them actually attacked but it was pretty scary
19:05:46 <Vorpal> kmc, pigeons? Peace? Really? When I hear pigeon I think of all the issues they cause in cities
19:05:59 <elliott> fizzie: did I ever give you alan dipert's email? in case there's ever any domain stuff with esolangs.org
19:06:04 <Vorpal> I guess that is a symbol of love, given how many there are
19:06:18 <fizzie> elliott: I don't think I have it, no.
19:06:18 <ais523> elliott: you missed out the article :-(
19:06:19 <kmc> Vorpal: when people like them they usually call them "doves" instead of "pigeons", but the terms are basically interchangeable
19:06:38 <elliott> fizzie: okay, alan@dipert.org then
19:06:50 <fizzie> Now that you've said it, it actually sounds familiar.
19:06:55 <Vorpal> kmc, yes, and I see right through that nomenclature and still dislike them :P
19:07:07 <elliott> although googling suggests adipert@acm.org??
19:07:19 <ais523> "the alan dipert" was the usual terminology, IIRC
19:07:33 <elliott> but alan@dipert.org is the one I received emails from and sent to.
19:07:50 <ais523> maybe they're different people?
19:08:05 <Vorpal> fizzie, speaking of free secondary DNS, what do you use for that?
19:09:44 -!- ^v has quit (Ping timeout: 252 seconds).
19:10:14 <Melvar> Also, IIRC pigeons supposedly don’t taste too bad if they haven’t been eating trash.
19:10:17 <Vorpal> fizzie, been looking for one myself
19:10:43 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:11:21 <fizzie> Vorpal: I use twisted4life.com at the moment, but it's kind of clunky. And their server is in Malaysia somewhere, which I guess is good for redundancy, but it's quite slow from many places. Earlier, I've used afraid.org and xname.org. And there's buddyns.com and dns.he.net I've heard of.
19:11:55 <Vorpal> fizzie, hm what about more than 2 DNS server? Couldn't you use several.
19:12:13 <fizzie> Sure, but it's even more of a hassle.
19:12:31 <fizzie> Some of those come with more than one server, anyway.
19:12:34 <Vorpal> I would assume the he.net one is quite reputable
19:13:12 <fizzie> I've been thinking about it, since I already have their IPv6 pipe and all, but they don't have DNSSEC support yet either. (Not sure if that just means for their primary DNS side, though.)
19:14:44 <Vorpal> None of those you mentioned seems to support DNSSEC, at least they are not listing it
19:15:22 <fizzie> I seem to recall afraid.org had something.
19:15:47 <fizzie> Their FAQ doesn't say anything about it, though.
19:19:07 -!- ais523 has quit.
19:20:55 <fizzie> (And there's https://acc.rollernet.us/help/dns/secondary.php that I know of that's explicitly DNSSEC-compatible and free.)
19:21:21 -!- nisstyre has joined.
19:23:35 <fizzie> https://forums.he.net/index.php?topic=3139.0 "still some hurdles"
19:24:54 <ion> vorpal: I use https://puck.nether.net/dns/ and http://freedns.afraid.org/secondary/
19:25:07 <ion> vorpal: http://www.frankb.us/dns/
19:25:24 <ion> The ones i’m using support DNSSEC.
19:29:32 -!- chaiomanot has joined.
19:39:48 -!- ^v has joined.
19:43:09 <Vorpal> Huh I just got SMS spam, that was new
19:44:59 <Vorpal> I guess CM doesn't have a block list, oh well
19:49:02 <Vorpal> fizzie, based on that link ion posted, I guess afraid is good
19:49:09 <Vorpal> Doesn't do ipv6 apparently
19:56:27 <Vorpal> fizzie, elliott, ion: What is a good VPS provider? I want to do my own domain, web server and mail server basically.
19:59:13 <ion> I’m afraid i don’t know, i haven’t been looking for a VPS.
20:02:26 <fizzie> I'm running zem.fi on Tilaa, and I think it's good.
20:02:57 <fizzie> (That really-cheap-dedicated-server link someone posted was rather intriguing, too.)
20:03:17 <fizzie> (That's "Tilaa" as in tilaa.nl.)
20:03:52 <Vorpal> That redirects to tilaa.com
20:04:14 <Vorpal> Also, I wouldn't want to deal with the crap that a dedicated server means
20:04:36 <Vorpal> fizzie, Tilaa uses xen I guess?
20:06:25 <fizzie> Oh, I guess .com is their primary domain, then.
20:06:29 <fizzie> And yes, it's a Xen shop.
20:06:44 <Vorpal> I have no idea what a reasonable price is here though
20:07:35 <Vorpal> fizzie, I guess they allow mail? And I presume irc too?
20:07:45 <Vorpal> (As in bouncer, not server)
20:07:52 <fizzie> You can compare prices with some "mainstream" providers, like Linode or a reserved Amazon EC2 instance.
20:09:01 <fizzie> And I don't think Tilaa has any restrictions except some generic "must follow local (Dutch) law" clause.
20:09:06 <fizzie> And something about the bandwidth.
20:09:51 <Vorpal> It says network traffic is unlimted/free on the configurator at least
20:10:08 <Vorpal> Presumably there is some clause about null routing in case of DDoS or similar though
20:10:42 <fizzie> "-- not allowed to run services that continuously use full capacity, like public software mirrors, BitTorrent seeding or web crawling/indexing --" in the "knowledge base".
20:10:47 <fizzie> Rather vaguely worded, but oh well.
20:10:56 <Vorpal> Well okay, that seems kind of reasonable
20:11:30 <fizzie> There are other places where you pay for anything above some fixed number, which is arguably at least more consistent.
20:11:39 <Vorpal> what does a "reserved" EC2 mean btw?
20:12:40 <Vorpal> Also EC2 pricing is convoluted
20:12:59 <fizzie> They have "on-demand" instances where you pay per hour whenever the server is online, and "reserved" instances where you make a single payment, and then get a discounted hourly rate.
20:13:22 <fizzie> (I thought reserved instances had some monthly price, but apparently it's an upfront cost nowadays. May have changed, of course.)
20:13:22 <Vorpal> Also I seem to remember reading about EC2 blocking outgoing SMTP
20:14:28 <Vorpal> Yeah I can't be bothered to dig through that pricing model
20:14:47 <fizzie> Yes, it's kind of convoluted. Separate prices for data transfer and storage and all that.
20:14:57 <fizzie> At least for Linode you should be able to find a single number.
20:15:13 <Vorpal> Yes, and it seems generally a bit more expensive than Tilaa
20:16:24 <fizzie> I used prgmr before Tilaa (like I guess I've mentioned), and I don't have anything really to complain there either, except for some lag for interactive use (but I doubt they can do much about the speed of light). It's a bit less "commercial-looking" than Tilaa.
20:18:12 <Vorpal> fizzie, so far Tilaa seems to offer the most bang for the buck
20:18:52 <Vorpal> Also why does prgmr list Debian 6.0.3 as an option they will install, but not Debian 7? Debian 6 is *oldstable*
20:19:15 <Vorpal> Not impressed by that in the least
20:22:16 <Vorpal> Oh, EC2 is only 99.95% uptime? I expected more from them
20:24:52 <fizzie> There are quite a few extremely cheap places selling OpenVZ and the like, if you want to go that way.
20:25:10 <Vorpal> ooh, that is sneaky, Tilaa excludes "external factors" "such as" "DDoS attacks"
20:25:22 <Vorpal> in the uptime guarantee
20:25:38 <Vorpal> fizzie, anyway you said Tilaa used xen right?
20:25:53 <Vorpal> Anyway why would places using openvz be cheaper
20:26:27 <fizzie> I guess because you don't need to dedicate RAM for your guests then.
20:29:12 <Vorpal> fizzie, yeah Tilaa's uptime guarnatee is kind of shitty, seems good otherwise though
20:30:54 -!- copumpkin has quit (Quit: Textual IRC Client: www.textualapp.com).
20:32:06 <Vorpal> fizzie, which distro did you go for on Tilaa btw?
20:33:26 <fizzie> And yes, their SLA is kind of funny; I guess it only includes their own mistakes and nothing else, since their own planned maintenance as well as acts of unspecified "third parties" are all excluded.
20:33:38 -!- copumpkin has joined.
20:34:33 <fizzie> fungot: What do you think of Tilaa? I know you're not exactly running there, but you've been speaking via them for no particular reason except convenience and vanity.
20:34:34 <fungot> fizzie: madam president, mr mauro used an example. finally, mr marset campos: we hope that the process in november with the formal presentation of the euro and in view of the fact that the president of the commission, and we will also have to work with you to intervene to stop uncontrolled and illegal immigration on public opinion and the draft joint action as amended, i would ask for the commission and in the draft resolution
20:37:01 <Vorpal> fizzie, why not run it on tilaa?
20:37:05 <Vorpal> Model files too large?
20:39:14 <fizzie> Jafet: It's a bit late, but "money is given to improving transparency" is indeed a synthesis. (From "In connection with global loans, that is, the Copenhagen facility, money is given to banks which then issue the loans." and "-- priority should be given to improving transparency and a clear demarcation of powers between the European Union and the Member States.")
20:40:00 <fizzie> Vorpal: Well, they're slightly large. But there's no really strong reason why not, except laziness.
20:40:19 <Vorpal> fizzie, how large are they, combined?
20:40:25 <fizzie> The chroot jail for fungot is 646M.
20:40:25 <fungot> fizzie: mr president, the report proposes to introduce competition in air transport services entails risks which have been declared adopted and i do it willingly. madam president, i am fully behind the support which the european parliament.
20:40:42 <Vorpal> Oh okay, that is just program, interpreter and model?
20:41:06 <Vorpal> I guess the interpreter + libraries would account for a couple of megabytes at most
20:41:11 <fizzie> Actually, it's not even that, since I kludged in cfunge the "chroot at startup" feature.
20:41:30 <fizzie> It's only the Funge-98 sources and data.
20:42:10 <Vorpal> fizzie, hey, you should send a patch upstream ;P
20:42:29 <fizzie> And apparently some DNS resolver support files, though I don't think those are used for anything at the moment.
20:42:30 <Vorpal> Personally I would be using an umlbox like what HackEgo uses
20:42:44 <fizzie> An umlbox might be nice too.
20:42:55 <Vorpal> I guess that would be out of question on a VPS though?
20:43:09 <Vorpal> Or I guess since it is xen, you could do it...
20:43:10 <fizzie> HackEgo runs on a VPS, so I don't see why not.
20:43:30 <fizzie> I mean, it's just a process almost just like any other.
20:44:06 <Vorpal> I thought it used special stuff from the kernel
20:44:14 -!- maurer_ has joined.
20:44:39 <fizzie> There was some sort of a performance thing.
20:44:52 <elliott> Xen is "just" like having your own machine.
20:44:55 <elliott> except for the ways in which it's not.
20:45:08 <Vorpal> Such as you couldn't do hw virutalization inside it yeah
20:45:33 <fizzie> UML had the "Skas mode" that needed a patch, but I can't remember if that got replaced by something newer.
20:46:36 <fizzie> The cfunge process has a RSS of 6988k and a VSZ of 27592k, so I guess it would fit okayish even on my so-small-they-no-longer-sell-it 256M RAM Tilaa instance.
20:47:35 <Vorpal> fizzie, oh, what does it cost you?
20:47:52 <Vorpal> Also, I forget what VSZ is
20:48:02 <fizzie> Address space cost, I think.
20:48:04 <fizzie> And 4.77 EUR/month, IIRC.
20:48:18 -!- copumpkin has quit (*.net *.split).
20:48:19 -!- maurer has quit (*.net *.split).
20:48:20 -!- jconn has quit (*.net *.split).
20:48:22 -!- Phantom_Hoover has quit (*.net *.split).
20:48:23 -!- itsy has quit (*.net *.split).
20:48:24 -!- lambdabot has quit (*.net *.split).
20:48:31 <fizzie> (That's including VAT; the prices quoted on their page were, at least before, excluding it.)
20:48:34 <Vorpal> fizzie, Oh, so cheaper than any available option,
20:48:44 -!- copumpkin has joined.
20:49:05 <fizzie> Yes. But it's also "only" 6 gigs of disk, too.
20:49:22 <zzo38> I made up a implementation of a "CREATE FUNCTION" command on SQL.
20:49:43 <fizzie> Er, make that 10 gigs, apparently. Huh. I was sure it was six.
20:49:47 <zzo38> I don't know, if that server supports this SQL extensions or not.
20:51:54 <HackEgo> Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
20:54:09 <zzo38> If you are not going to store any movies and/or pornography, then probably 6 GB is sufficient.
20:54:30 -!- lambdabot has joined.
20:54:47 <fizzie> It's a bit few also for things like photos.
20:55:32 <fizzie> Our collection of vacation photos shared with family and friends seems to be 21G at the moment.
20:55:41 -!- Koen_ has joined.
20:56:39 -!- Phantom_Hoover has joined.
20:59:55 <fizzie> Bah, UML documentation is so fragmentary and (in many places) old. The HOWTO in Documentation/ of the kernel sources is from 2002, the sf.net page at http://user-mode-linux.sourceforge.net/ has just links to "The UML Wiki" with an "It works!" default page in it and "The Old UML Site", and so on.
21:01:14 <fizzie> http://blogs.igalia.com/berto/2006/09/13/user-mode-linux-and-skas0/ well, that's not new either, but I think that's the "skas mode with no patched kernel on the host" thing I thought existed.
21:01:40 <fizzie> Because I don't think there are skas3 patches for anything newer than 2.6.x.
21:05:04 -!- iano has joined.
21:05:26 -!- iano has left.
21:24:45 <fizzie> Vorpal: Incidentally, I added AVR in that quiz.
21:27:55 <Vorpal> fizzie, huh, which variant of AVR is that
21:28:01 <Vorpal> I coded for the ATMega128 iirc
21:30:02 <Vorpal> fizzie, also it likes giving me the fake opcode "BR" a /lot/
21:30:06 <Vorpal> I got it 3 times in a row
21:30:36 <Vorpal> Guess the instruction set is too small?
21:30:46 <fizzie> It's just "grep AVR_INSN avr.h | cut -c 11- | sed -e 's/,.*//' | sort | uniq". And it is quite small, yes.
21:31:36 <Vorpal> Well I got 89% at best
21:31:46 <Vorpal> More commonly around 85%
21:32:09 <fizzie> http://sprunge.us/aZaF it does seem quite fond of "br".
21:32:26 <fizzie> (That's a "uniq -c" on 100 generated opcodes.)
21:32:52 <fizzie> Possibly a shorter model order might've been better for this.
21:33:58 -!- oerjan has joined.
22:08:37 -!- SpaceWizard has joined.
22:19:43 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
22:26:14 -!- conehead has joined.
22:39:35 -!- Frooxius has joined.
22:42:42 <zzo38> gtristan: NULL values in columns take up one byte of disk space each, I think.
22:42:50 -!- zzo38 has left.
22:44:39 <kmc> Vorpal: counterpoint: pigeons are awesome, screw you
22:44:50 <kmc> some pigeons have made a nest behind a plastic fake owl at my house <3
22:45:00 <kmc> the kind meant to keep birds away
22:46:09 <Taneb> Pigeons are not my favourite bird
22:46:28 <kmc> what is your favourite bird
22:46:43 <Taneb> They don't seem to have been made to the same scale as any of the other birds that appear in my garden
22:46:53 <Taneb> kmc, I dunno, the blackbird, maybe?
22:47:04 <HackEgo> [wiki] [[Talk:Universal Machine]] N http://esolangs.org/w/index.php?oldid=39226 * EzoLang * (+102) Possible duplicate
22:47:13 <Taneb> Hold on that's new
22:47:38 <Taneb> When did HackEgo start doing that
22:47:57 <Bike> this morning, maybe
22:48:22 <Taneb> The song of the Australian Magpie is other-worldly
22:50:10 <oerjan> b_jonas: EzoLang seems to have a point
22:51:08 -!- nooodl has quit (Ping timeout: 240 seconds).
22:51:24 <Taneb> Well, the seagulls around here feel out of place
22:51:27 * oerjan likes seagulls. better than crows, anyhow.
22:51:32 <Taneb> I'm 25 miles from the coast
22:51:37 <shachaf> oerjan: i heard that seagulls have a bad reputation in norway
22:53:06 <oerjan> shachaf: well people don't like to have them too close, all the time.
22:53:15 <Taneb> They have a bad reputation here
22:53:20 <oerjan> they're noisy and vindictive during breeding season
22:53:48 <Taneb> And the geese at my uni are notorious
22:53:57 -!- nooodl has joined.
22:55:49 <oerjan> not much geese in trondheim that i know of, we see them flying in their V formation during migration
22:56:44 <oerjan> however somehow the noise of seagulls doesn't grate on me the same way crows do.
22:57:30 <kmc> humans also tend to be noisy and vindictive during breeding season, which is all of the time.
23:09:36 <Phantom_Hoover> i ended up getting chased by one of the geese at warwick
23:09:51 <Phantom_Hoover> this was admittedly after i'd followed it around for a bit until it walked into a corner
23:10:30 <kmc> never corner a goose
23:10:31 <kmc> rookie mistake
23:11:10 <Taneb> Phantom_Hoover, how does it feel going to an inferior university in the all-important metric of duck to student ratio?
23:11:10 <Phantom_Hoover> shortly after that i realised i was no longer following the goose; the goose was following me
23:11:47 <Phantom_Hoover> also there was a guy who got kicked out for, amongst other things, chasing a swan about the place last year
23:12:10 <Taneb> Someone tried to sell a swan to someone I know
23:12:33 <Taneb> I'm... not sure how they got it that far from the lake
23:16:22 <shachaf> copumpkin: the play was good
23:16:42 <copumpkin> I missed the second day of hac nyc anyway
23:17:21 <Taneb> I need to get me to some of these
23:17:35 <Taneb> Wouldn't be too hard to do hac yc
23:18:08 <Taneb> shachaf, I really want to but hoooteeel roooooms
23:18:18 <Taneb> Can I like stay with you in your Zurich apartment
23:18:35 <shachaf> i don't have a zurich apartment
23:18:52 <shachaf> i can't predict my zurischedule
23:19:11 -!- zzo38 has joined.
23:22:52 <Taneb> With one of those I could afford a Zurich apartment!
23:30:03 <shachaf> Taneb: are you moving to zurich
23:30:26 <Taneb> Not in the near future
23:30:40 <Taneb> I still have the majority of an undergraduate degree to complete
23:31:07 <Taneb> But after that? Who knows!
23:31:11 <Taneb> I'll go where the wind takes me
23:32:06 <oerjan> i'd just remind you the earth is something like 4/5 ocean hth
23:32:44 <Taneb> I know people with boats, it's cushty
23:32:51 <shachaf> <Taneb> I'm 25 miles from the coast
23:33:06 <shachaf> i imagine that Taneb is p. wind-resistant
23:33:15 <oerjan> hm 70.8% says this link
23:38:44 <Taneb> In holiday-time I live near England's pole of inaccessibility from roads
23:39:22 -!- bigbugkik has joined.
23:42:35 <Taneb> Did I just use the word "cushty"
23:44:29 -!- Frooxius has quit (Read error: Connection reset by peer).
23:52:48 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:53:15 -!- nooodl has quit (Ping timeout: 255 seconds).
23:56:09 -!- yorick has quit (Remote host closed the connection).
23:58:21 -!- nooodl has joined.
23:59:38 -!- oerjan has quit (Quit: new cushtoms).
00:00:24 -!- ter2 has quit (Read error: Connection reset by peer).
00:00:28 -!- tertu3 has joined.
00:10:08 -!- `^_^v has quit (Read error: Operation timed out).
00:11:47 <Sgeo> "Hoon is real, but whether Hoon is for real is debatable."
00:32:08 -!- nooodl has quit (Ping timeout: 240 seconds).
00:33:43 -!- maurer_ has changed nick to maurer.
00:37:58 -!- 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?").
00:38:38 -!- john_metcalf has quit (Read error: Connection reset by peer).
00:38:39 -!- itsy has quit (Read error: Connection reset by peer).
00:42:24 -!- john_metcalf has quit (Read error: Connection reset by peer).
01:31:26 <HackEgo> [wiki] [[ObjectArt]] http://esolangs.org/w/index.php?diff=39227&oldid=39036 * Ypnypn * (+167) /* Other numbers */
01:49:26 <zzo38> What is that and why you put too much ^C codes on it?
01:51:27 <Bike> it's wiki updates, of course.
01:53:35 <quintopia> and ^C is the price you pay for not having colors in your client. you chose your road, now you pay the piper
01:59:43 <zzo38> I do have colors on my computer
02:00:13 <zzo38> And it still has too much regardless of that or not.
02:02:03 <quintopia> nah it's fine. the colors look nice.
02:02:58 <zzo38> Yes, at least is less than `relcome has.
02:05:54 <zzo38> I found a example code to make up a custom aggregate function in PostgreSQL. It looks like terrible to me! The syntax I implemented is clearly better (at least to me, it is). The PostgreSQL code is: CREATE FUNCTION append_id(TEXT, INTEGER) RETURNS TEXT AS ' SELECT CASE WHEN $2 = 0 THEN $1 ELSE $1 || '' '' || CAST($2 AS TEXT) END;' LANGUAGE 'sql' WITH (ISCACHABLE, ISSTRICT); CREATE AGGREGATE id_list ( SFUNC = append_id, BASETYPE = INTEGER, S
02:05:59 <zzo38> Would you call it terrible?
02:08:08 <quintopia> yes. but then all sql languages are terrible
02:09:49 <zzo38> I think SQLite is better. It doesn't have any CREATE FUNCTION built-in but I added one.
02:11:36 <zzo38> Is this way better? CREATE FUNCTION ID_LIST(X) ACCUMULATING(R = NULL SET TO COALESCE(R || ' ' || X,X)) AS COALESCE(R,'');
02:12:20 <zzo38> (You don't need it anyways, since SQLite has a "group_concat" function built-in which does this, but it is to demonstrate the example.)
02:13:01 <zzo38> quintopia: Why do you think SQL is terrible?
02:14:19 <quintopia> zzo38: it doesn't feel like programming. if you want to have a point-free query scheme for manipulating data, why not use a dataflow/concatenative language?
02:15:01 <quintopia> not anymore. but that only makes it worse.
02:15:19 -!- SpaceWizard has quit (Read error: Operation timed out).
02:15:20 <zzo38> quintopia: SQL looks fine to do such thing, to me. At least SQLite is; procedural SQL and that stuff tends to be more terrible.
02:17:54 <quintopia> i also think bash looks ugly. perhaps that is influencing my judgment...
02:24:08 <zzo38> It seems my syntax may not be suitable for some kinds of aggregate functions though; for that it may be useful to define an alternate syntax, which puts all input records in one temporary table which is accessed by the expression after "AS". For example, it might help if you want to calculate the median of a data set.
02:26:28 -!- Frooxius has joined.
02:30:50 <Sgeo> <3 foobar2000's gapless playback
02:32:47 <Sgeo> "I don't like most of the music on Magnatune.com..... but you might"
02:33:08 <elliott> you know even iTunes has done gapless playback for years now, right?
02:33:22 <Sgeo> I never used iTunes
02:33:35 <pikhq> Heck, Winamp did it way back in the day.
02:34:03 <Sgeo> I've used WinAmp... maybe I haven't used it with albums that need gapless playback (Ridin' the Faders and one particular Enya album)
02:34:44 <pikhq> Admittedly, all gapless playback fails horribly if done with not-well-encoded MP3 files.
02:35:05 <Sgeo> Incidentally, Magnatune butchered Ridin' the Faders when it started inserting ads
02:35:46 <pikhq> (MP3 files will have a bit of silence in them for padding)
02:36:59 <kmc> i hear winamp really whupps the llama's ass
02:42:38 -!- HackEgo has quit (Ping timeout: 240 seconds).
02:42:48 -!- HackEgo has joined.
02:50:09 <HackEgo> [wiki] [[Cyclic tag system]] http://esolangs.org/w/index.php?diff=39228&oldid=39187 * Quintopia * (+1808) Undo revision 39187 by [[Special:Contributions/Oerjan|Oerjan]] ([[User talk:Oerjan|talk]]) (were you asleep when you did this?)
02:53:15 -!- jconn has joined.
02:54:25 -!- HackEgo has quit (Ping timeout: 252 seconds).
02:59:11 -!- tertu3 has quit (Ping timeout: 252 seconds).
03:04:00 -!- tertu has joined.
03:17:05 <zzo38> Did you read my latest Dungeons&Dragons recording that I typed yesterday?
03:28:51 <Sgeo> Ugh, whenever I buy cup noodles, I go through a cycle of thinking that the 7-eleven clerk might think I'm poor, then feeling guilty about the previous thought
03:29:27 <Bike> just buy them in industrial quantities from the manufacturer
03:29:52 <pikhq> Sgeo: It is highly unlikely the clerk even particularly cares.
03:30:09 <pikhq> Also, cup noodles are an indicator of either poverty *or laziness*.
03:30:16 <zzo38> I would think the clerk wouldn't (and shouldn't) care.
03:30:28 <Sgeo> Also, I usually end up asking if I can use their hot water
03:30:54 <pikhq> But yeah. You are generally a very uninteresting part of their day.
03:33:55 <Sgeo> Ok. I have had an awesome song on my computer since 2005, carried with me through a variety of systems, and I haven't heard it until now
03:33:58 <Sgeo> At all, that I remember
03:34:03 <Sgeo> I might not have remembered
03:34:04 <zzo38> Even if they do think of such thing, probably they don't care, and it wouldn't affect you, anyways.
03:37:07 -!- nisstyre has joined.
03:50:46 -!- ^v has quit (Quit: SoniEx2).
03:51:09 -!- Sorella has quit (Quit: It is tiem!).
03:56:08 -!- tertu has quit (Ping timeout: 240 seconds).
03:56:20 -!- tertu has joined.
03:59:28 -!- tromp has joined.
04:12:27 -!- tertu has quit (Ping timeout: 255 seconds).
04:13:06 -!- tertu has joined.
04:15:36 <Sgeo> I need a better way to indicate which pieces of music are my favorites
04:15:49 -!- tromp has quit (Ping timeout: 252 seconds).
04:16:05 -!- tromp has joined.
04:16:11 <Sgeo> In the past, I've used KDE ... marker things (or maybe GNOME marker things), Windows shortcuts, and literally copy/pasting the file so that I get "Copy of ..."
04:16:21 <Sgeo> Only the last one survived to this day
04:17:52 <Sgeo> I would question whether that would actually have survived to the present, but apparently I have last modified dates that have survived from 2005
04:25:39 <Bike> http://archive.wired.com/robots.txt huh.
04:29:47 <zzo38> Move (or delete) the music you don't like.
04:49:59 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
04:58:09 -!- tertu has quit (Ping timeout: 252 seconds).
04:58:27 -!- tertu has joined.
05:00:35 -!- tertu has quit (Disconnected by services).
05:00:35 -!- ter2 has joined.
05:01:28 -!- nisstyre has quit (Quit: bai).
05:02:30 <fizzie> zzo38: The too many ^C codes are part of stock MediaWiki; they're from the IRCColourfulRCFeedFormatter of http://www.mediawiki.org/wiki/Manual:$wgRCFeeds and there's no IRCColourlessRCFeedFormatter available. (Though I could have stripped the color codes off myself, I guess.)
05:25:57 <zzo38> Why didn't you just modify it?
05:29:39 -!- pikhq has quit (Ping timeout: 245 seconds).
05:31:50 -!- pikhq has joined.
05:45:36 -!- ter2 has quit (Ping timeout: 255 seconds).
06:04:24 -!- ^v has joined.
06:12:31 -!- zzo38 has quit (Ping timeout: 255 seconds).
06:13:58 <fizzie> I saw no particular reason to, for the channel of `relcome and all.
06:17:50 <fizzie> Curious; the latest few recent changes have not been announced.
06:17:57 <fizzie> Didn't think it was *that* brittle.
06:19:39 <fizzie> Broken down it has, indeed. Strange. Even though the bridge bit is still running.
06:21:11 <fizzie> Oh, there's no HackEgo connected.
06:21:41 -!- HackEgo has joined.
06:21:51 -!- zzo38 has joined.
06:22:27 <fizzie> I don't know what has broken the post-reconnection rejoin of HackEgo; I haven't touched that part. (And it rejoined after that one ping timeout up there, at 02:43 UTC, but not after the 02:55 UTC one.)
06:22:35 <HackEgo> [wiki] testing, testing, 1, 2, 3
06:22:43 <fizzie> At least that part had not broken down.
06:38:33 -!- not^v has joined.
06:39:28 <kmc> inlining a lambda into its caller is a kind of constant propagation
06:39:56 <kmc> also, compression is learning
06:42:11 -!- ^v has quit (Ping timeout: 252 seconds).
06:43:49 <kmc> http://mushroomobserver.org/162974?q=1ttKN found & photographed by douglass_ in our backyard
06:47:21 <shachaf> difficult not to read as mushroom mob server
06:48:05 <Sgeo> lazy is strict, right?
06:48:19 <Sgeo> It just lies to the strictness analyzer?
06:49:51 <kmc> shachaf: you could vote on what kind it is
07:23:06 <douglass_> technically the one you saw is not pictured though i might add a picture
07:23:54 <douglass_> http://www.mushroomexpert.com/major_groups.html here's a key you can use
07:27:11 <kmc> http://www.mushroomexpert.com/abnormal.html
07:27:15 <kmc> a three-headed morel!
07:39:02 <douglass_> I found an Agaricus with another perfectly formed cap growing right out of the top
07:39:26 <douglass_> (this was on Mt. Sutro a bit before I found the Chicken of the Woods that I cloned.)
07:39:50 -!- MindlessDrone has joined.
07:41:24 <kmc> Bike: huh indeed
07:47:18 -!- Bike has quit (Ping timeout: 240 seconds).
07:48:58 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
07:50:24 -!- Bike has joined.
07:50:43 <Bike> whenever i shut down my computer the display totally goes to shit, it almost looks like snow
07:50:49 <Bike> wonder if it's the weird proprietary drivers somehow
07:51:59 <kmc> it's uploading nam-shubs thru yr. optic nerve
08:06:51 -!- Slereah has joined.
08:07:58 -!- Slereah_ has quit (Ping timeout: 240 seconds).
08:29:31 -!- Patashu has joined.
08:42:02 -!- conehead has quit (Quit: Computer has gone to sleep).
08:45:30 <fizzie> http://sprunge.us/dELU (paraphrasing from Finnish) well, that's a big change indeed.
08:53:37 -!- john_metcalf has quit (Ping timeout: 252 seconds).
08:53:45 -!- impomatic has quit (Ping timeout: 252 seconds).
08:57:36 -!- nooodl has joined.
08:58:34 -!- Patashu[Zzz] has joined.
08:58:34 -!- Patashu has quit (Disconnected by services).
09:03:31 -!- oerjan has joined.
09:04:09 -!- augur has quit (Quit: Leaving...).
09:04:45 <fizzie> It's off to work we go.
09:04:52 -!- vravn has quit (Ping timeout: 255 seconds).
09:04:52 <oerjan> i'm not getting to the codu logs
09:05:28 <fizzie> (Stalker mode, at least.)
09:06:31 <oerjan> what is the name of that effect where things start working as soon as you get someone to look at it
09:06:51 <oerjan> (fine for me, as long as it gets me to the logs)
09:08:43 -!- vravn has joined.
09:10:43 -!- olsner has joined.
09:13:57 <HackEgo> [wiki] [[Cyclic tag system]] M http://esolangs.org/w/index.php?diff=39231&oldid=39229 * Oerjan * (+1) /* Example */ A paranoid test
09:14:41 <fizzie> I think it's called "the demo effect", at least in Finnish and hereabouts.
09:15:01 <oerjan> quintopia: my only explanation is that i somehow had two edit windows open, one only for the section and one for the whole article, and somehow pasted from vim into the wrong one
09:15:42 <Taneb> fizzie, the demo effect sounds like the other way round to me
09:15:51 <Taneb> ie, things stop working when you try to show them off
09:16:57 <oerjan> quintopia: that, and somehow missing my routine of checking my edits afterwards. maybe i _was_ asleep.
09:17:51 <olsner> it's annoying when that effect happens to bugs I'm supposed to fix
09:20:36 <fizzie> Taneb: I think it's (at least occasionally) applied both ways, here; as in, also for bugs that stop "working" (start working) when you try to show them off.
09:20:58 <Taneb> I guess that makes sense
09:27:21 -!- Slereah has quit (Ping timeout: 255 seconds).
09:30:35 -!- tromp has quit (Ping timeout: 246 seconds).
09:47:49 <Taneb> GG has an 4th wall breaking almost title-drop today :)
09:48:37 <oerjan> <Bike> http://archive.wired.com/robots.txt huh. <-- i had to test one of those, didn't i :(
09:54:23 <b_jonas> argh. http://esolangs.org/wiki/Universal_Machine and http://esolangs.org/wiki/UM-32 are duplicates. I didn't search carefully enough.
09:54:44 <b_jonas> how should I clean these up? should I merge the former into the latter?
09:55:16 <oerjan> yeah i think UM-32 is a better name
09:55:33 <b_jonas> but where's that name from? is it mentioned somewhere in the task description?
09:55:52 <b_jonas> http://boundvariable.org/um-spec.txt says "Object: UM-32 "Universal Machine""
09:57:50 -!- MindlessDrone has quit (Quit: MindlessDrone).
10:03:53 -!- bigbugkik has quit (Remote host closed the connection).
10:07:51 <HackEgo> [wiki] [[UM-32]] http://esolangs.org/w/index.php?diff=39232&oldid=25362 * B jonas * (+1066)
10:10:28 <HackEgo> [wiki] [[Talk:Universal Machine]] http://esolangs.org/w/index.php?diff=39233&oldid=39226 * B jonas * (+107)
10:10:48 <HackEgo> [wiki] [[Universal Machine]] http://esolangs.org/w/index.php?diff=39234&oldid=39191 * B jonas * (-1201) Redirected page to [[UM-32]]
10:11:18 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39235&oldid=39209 * B jonas * (-24)
10:12:48 <oerjan> i can see this getting annoying with those people who edit articles in tiny steps
10:13:04 <fizzie> It'll probably break down far before that.
10:13:12 <olsner> hmm, is this the first instance of a bot with a useful function for this channel?
10:13:27 <fizzie> fungot: Did you hear that?!
10:13:27 <fungot> fizzie: mr papayannakis, is going to deal with it seriously with socio-economic accompaniment measures which, if implemented, will offer a referendum to the national data protection authorities, according to whether the us measures, which are normally very small and the large export capacity of many developing countries.
10:14:35 -!- boily has joined.
10:16:31 <nooodl> `welcome.es is useful isn't it
10:16:32 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: welcome.es: not found
10:16:50 <HackEgo> ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.)
10:17:33 <boily> today is «journée d'élections»!
10:19:08 <fizzie> Today, the university main building had Finnish flags in the set of five flagpoles beside the main entrance, as opposed to the silly colorful university flags they usually do.
10:19:13 <fizzie> So it's probably some sort of a day.
10:20:10 <nooodl> fizzie: clearly celebrating canadian journée d'élections
10:20:18 <fizzie> Though I don't think I saw flags out there generally, so maybe it's something more specific.
10:20:49 <HackEgo> [wiki] [[User:Nooodl/test]] N http://esolangs.org/w/index.php?oldid=39236 * Nooodl * (+2) Created page with "hi"
10:21:12 <nooodl> maybe User: namespace edits shouldn't be reported
10:21:33 <fizzie> "International Bird Migration Day in Costa Rica" it's probably not that
10:21:46 <oerjan> they'd not use finnish flags then
10:22:00 <fizzie> The feed functionality didn't really have any options. Other than to hide bot edits, but I guess we don't have any wikibots?
10:22:29 <boily> fungot: are you a wikibot?
10:22:30 <fungot> boily: madam president, please allow me to make one observation and three recommendations. as i have already referred to some of you have referred to, which may be suffered by women on account of support from the structural reform process laid down in the wait-and-see policy and the activities of the paramilitaries' involvement in the support of all current internal investigations involving allegations of fraud and irregulariti
10:22:34 <fizzie> Could add a d in the sed, I guess.
10:22:47 <int-e> oerjan: that's the day they can air the flags without worrying because the birds will be away ;)
10:23:26 <oerjan> fizzie: well during major spam runs we sometimes turn on the bot flag to make them disappear. but that only works in afterthought.
10:23:27 <int-e> it's a congress bot now.
10:23:40 <oerjan> *disappear from recent changes
10:24:39 <int-e> Speaking of which, is Freefall now going to turn into a month of heated debate?
10:25:08 <oerjan> no, i think it'll be at least 3 months hth
10:26:10 <oerjan> i guess it might be alternating with sam and florence
10:26:33 <oerjan> so make that a year of on-off debate.
10:27:20 <int-e> Ah, first we have to rehash all of Asimov's logic tricks.
10:27:42 <int-e> Oh well, let's wait and see.
10:28:18 <int-e> Maybe Dr. Bowman gets a chance to make an appearance and save the day. That could be fun.
10:29:14 -!- SpaceWizard has joined.
10:29:39 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=39237&oldid=38919 * Nooodl * (-59486) /* Implementations */ move to separate article
10:30:21 <fizzie> I guess it's even borderline possible that the wiki notices might get more people work on it?
10:30:58 <HackEgo> [wiki] [[Deadfish implementations]] N http://esolangs.org/w/index.php?oldid=39238 * Nooodl * (+59587) Created page with "Implementations of the '''[[Deadfish]]''' language. Some of these implementations may not be considered fully compliant, sometimes because an implementor has implemented the ..."
10:32:46 <oerjan> you are ruining years of tradition here
10:33:38 <nooodl> is the tradition to stretch out the deadfish page to ridiculous lengths!!
10:33:45 <oerjan> also the number of implementations is the most impressive part of the deadfish page
10:34:14 <int-e> "The language defined by the Revised Revised Revised Revised Revised Report on the Algorithmic Language Scheme"
10:34:26 <int-e> what if they revise it again, will you add another entry?
10:34:42 <oerjan> they already did. and are doing it again.
10:35:25 <oerjan> but the implementation is in R5RS
10:36:02 <oerjan> (whether there are any changes that would break it in later ones, i don't know)
10:36:54 <fizzie> R⁷RS is getting to be pretty close to finished, these days.
10:38:51 <HackEgo> [U+2077 SUPERSCRIPT SEVEN]
10:41:24 <fizzie> Shouldn't've been fancy, I see.
10:43:07 <boily> I see dead superscript sevens...
10:50:19 -!- password2 has joined.
11:02:00 -!- boily has quit (Quit: CITIZEN CHICKEN).
11:04:15 <nooodl> speaking of deadfish: i ~omg optimized~ the hello world, and also generalized it
11:04:51 <nooodl> http://sprunge.us/EJAQ like so
11:57:28 -!- Patashu has joined.
11:58:39 -!- Patashu[Zzz] has quit (Ping timeout: 255 seconds).
11:59:56 -!- Patashu has quit (Client Quit).
12:09:00 -!- yorick has joined.
12:15:50 -!- Patashu has joined.
12:23:50 -!- augur has joined.
12:30:15 <elliott> nooodl: we might as well delete the deadfish article if it isn't filled with implementations
12:38:38 -!- Sorella has joined.
12:41:21 <nooodl> elliott: should i put 'em back?
12:41:38 <elliott> well, arguable. I mean, it is deadfish
12:49:36 -!- Sgeo has quit (Read error: Connection reset by peer).
12:50:35 <int-e> . o O ( clearly there should be two pages, one with, and one without the implementations, in addition to the separate page of implementations, just to satisfy all tastes. )
12:56:49 <fizzie> Also one empty page with neither the implementations, nor the language.
13:03:09 <int-e> and one stub with all the [citation needed] annotations.
13:12:48 -!- oerjan has quit (Quit: leaving).
13:17:27 -!- S1 has joined.
13:20:48 -!- SpaceWizard has quit (Read error: Operation timed out).
13:27:41 -!- `^_^v has joined.
13:37:16 -!- Sellyme has quit (Excess Flood).
13:37:46 -!- Sellyme has joined.
13:37:47 -!- Sellyme has quit (Excess Flood).
13:38:47 -!- Sellyme has joined.
13:52:30 -!- SpaceWizard has joined.
14:15:22 -!- Patashu has quit (Ping timeout: 255 seconds).
14:23:53 -!- SpaceWizard has quit (Read error: Operation timed out).
14:24:47 -!- SpaceWizard has joined.
14:28:40 -!- zzo38 has quit (Remote host closed the connection).
14:32:10 -!- lambdabot has quit (Remote host closed the connection).
14:36:31 -!- lambdabot has joined.
14:36:55 <lambdabot> The answer is: Yes! Haskell can do that.
14:38:24 <int-e> Oh I meant to change that.
14:38:53 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
14:39:37 <int-e> That seems to be a slightly more useful reply.
14:40:33 -!- Sellyme has changed nick to BenignAardvark.
14:40:46 -!- BenignAardvark has changed nick to Sellyme.
14:43:13 <elliott> int-e: enjoy all the whining you get in #haskell for it :)
14:44:01 <int-e> elliott: when was the last time you saw @faw being used on #haskell? My backlog isn't long enough ...
14:44:08 <lambdabot> The answer is: Yes! Haskell can do that.
14:44:18 <int-e> lambdabot: oh shuddup.
14:44:48 <elliott> int-e: I don't know, I left. but people made lots of sad faces at me just for saying I'd make @faq do that, when it was being used unhelpfully like once a day.
14:45:18 <elliott> maybe the problem has gotten better.
14:45:36 <int-e> I'm inclined to silently change it and wait for the complaints.
14:45:50 <int-e> But it can wait for the ghc 7.8 update.
14:46:21 <elliott> run on GHC HEAD! it'll be more exciting
14:47:29 <int-e> up to a month ago half of the dependencies didn't even build
14:47:53 -!- john_metcalf has quit (Ping timeout: 240 seconds).
14:47:54 <int-e> (I was surprised to find last weekend that they do build now)
14:53:51 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
15:02:18 <Bike> http://article.gmane.org/gmane.comp.mozilla.devel.platform/7648 hell yeah
15:03:40 <int-e> and all I needed for getting lambdabot to compile was a role annotation in a hs-boot file: https://github.com/int-e/lambdabot/commit/dc7ee36480a3e2b4e1b25d0022de72b764029bf7
15:06:15 <int-e> Hmm. Should I feel bad about abusing this channel for talking about lambdabot?
15:06:36 <elliott> have you noticed how little we talk about esolangs?
15:08:18 <Jafet> I have written much code for lambdabot. Unfortunately the reference implementation changes often.
15:08:48 <Bike> couldn't you just have @faq say both
15:09:41 <Jafet> @faq couldn't you just have @faq say both
15:09:41 <lambdabot> The answer is: Yes! Haskell can do that.
15:10:37 <Bike> i doubt that question is asked frequently
15:11:31 <Jafet> What are you, a frequentist?
15:11:33 <int-e> If I wanted random answers I'd change @faq into an 8ball clone.
15:13:19 <b_jonas> if you want an 8-ball, /msg perlbot 8ball your question here
15:13:42 -!- SpaceWizard has quit (Quit: Leaving).
15:14:01 -!- SpaceWizard has joined.
15:14:20 <int-e> Despite Pugs I still believe that using Perl is against the spirit of Haskell.
15:14:45 <Jafet> If you want an 8-ball, wait a random period of time and ask #haskell whether you can retrieve the IO from an IO String
15:15:11 <int-e> Jafet: That sounds like a viable approach.
15:15:33 <int-e> Jafet: Assuming you meant to retrieve the String.
15:15:50 -!- zzo38 has joined.
15:15:53 <lambdabot> No quotes match. You untyped fool!
15:16:20 <Jafet> @quote monochrom IO.String
15:16:21 <lambdabot> monochrom says: How do I extract the IO out of IO String?
15:16:49 <int-e> Oh. Typical monochrom there.
15:17:15 -!- MindlessDrone has joined.
15:36:48 -!- SpaceWizard has quit (Read error: Operation timed out).
15:38:28 -!- SpaceWizard has joined.
15:40:02 -!- tromp has joined.
15:41:40 -!- tromp has quit (Read error: Connection reset by peer).
15:42:23 -!- tromp has joined.
15:43:27 -!- nucular has joined.
15:46:36 -!- tromp has quit (Ping timeout: 252 seconds).
16:30:01 <zzo38> Do you play a computer game "Sub-EBCDIC ZZT Village Part II"?
16:30:14 -!- SpaceWizard has quit (Ping timeout: 252 seconds).
16:34:35 -!- SpaceWizard has joined.
16:44:34 -!- ^v has joined.
16:54:25 <HackEgo> olist (948): shachaf oerjan Sgeo FireFly boily nortti
17:00:09 <zzo38> Remember: Quidquid latine dictum sit, altum viditur.
17:01:30 <^v> \o/ the barely wiki page is wrong, also the brainfuck conversions are now wrong
17:01:45 <^v> Y u no test.
17:02:43 <zzo38> Then you should fix it please.
17:02:59 -!- S1 has joined.
17:03:08 -!- S1 has left.
17:13:58 <HackEgo> [wiki] [[Talk:MarioLANG]] http://esolangs.org/w/index.php?diff=39239&oldid=37562 * T.J.S.1 * (+119) correction about 99bottles program
17:21:18 -!- SpaceWizard has quit (Ping timeout: 255 seconds).
17:39:23 -!- SpaceWizard has joined.
17:55:28 <nooodl> idea i had: can you perform any calculations using the functions and constants in python's "math" module
17:55:57 <nooodl> looks like A+B is pow(hypot(sqrt(A),sqrt(B)),trunc(gamma(pi)))
18:00:47 <fizzie> A*B is log(pow(exp(A),B)) and A+B is log(exp(A)*exp(B)) is log(log(pow(exp(exp(A)),exp(B)))) but that hits floating-point range errors pretty soon.
18:00:55 <fizzie> It can compute 1+2 but not 5+7.
18:02:45 <fizzie> 2+3 is still okay, too, and only involves 2.851123567946167e+64 as an intermediate number.
18:04:46 <quintopia> does "math" allow you to specify a base for log? i know mpmath does. if so, you can use 1.0000000000001 as a base and add large numbers too
18:14:02 -!- chaiomanot has left ("Leaving").
18:17:13 <int-e> log_a(b) = log(b)/log(a) (where _ indicates a subscript)
18:18:37 <fizzie> Though since you can give base as an argument, maybe that's a way to do A/B.
18:18:40 <fizzie> >>> log(log(pow(pow(1.0000000000001,pow(1.0000000000001,17)),pow(1.0000000000001,13)),1.0000000000001),1.0000000000001)
18:18:44 <fizzie> Has some round-off problems, though.
18:18:48 <fizzie> >>> log(log(pow(pow(1.001,pow(1.001,17)),pow(1.001,13)),1.001),1.001)
18:18:54 <nooodl> tan(atan2(A,B)) works sometimes!
18:19:19 <int-e> quintopia: I missed the significance of the quotes.
18:19:32 * int-e goes back to reading webcomics.
18:20:57 <quintopia> fizzie: a power of -1 seems to be the obvious way to do A/B. i would expect less error.
18:23:11 <nooodl> also the "gimmick" is you have to construct your constants from functions and math.e and math.pi!!
18:31:24 -!- SpaceWizard has quit (Ping timeout: 255 seconds).
18:35:35 <quintopia> nooodl: well, that pretty much bars you from doing large numbers.
18:37:59 -!- password2 has quit (Ping timeout: 246 seconds).
18:42:08 -!- zzo38 has quit (Remote host closed the connection).
18:44:04 <fizzie> >>> b = tanh(e); log(log(pow(pow(b,pow(b,17)),pow(b,13)),b),b)
18:44:07 <fizzie> That's not too shabby.
18:44:20 <fizzie> Though summing via hypot is much more sane, I'm not arguing against that.
18:44:29 <fizzie> (tanh is a nice way to get numbers close to one.)
18:47:59 <fizzie> I assume you'd count fsum((A,B)) cheating?
18:48:52 <nooodl> yeah (imo forming tuples isn't in the module)
18:53:41 <nooodl> i've been thinking about having an esolang that gives you complex built-ins and forces you to build simple things through creative use of them
18:58:28 <elliott> there was that language on the wiki recently
19:02:06 <nooodl> http://esolangs.org/wiki/SELECT. hm!
19:06:02 <HackEgo> [wiki] [[SELECT.]] M http://esolangs.org/w/index.php?diff=39240&oldid=38622 * Quintopia * (-1) /* Etymology */ grammar and spelling
19:08:33 -!- nucular has quit (Quit: Excess Food).
19:13:17 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:15:45 -!- conehead has joined.
19:17:34 -!- sebbu has quit (Ping timeout: 245 seconds).
19:48:24 <nooodl> what's that red M. minor edit?
19:49:28 -!- Mortape123 has joined.
19:50:16 -!- Mortape123 has quit (Client Quit).
19:50:48 <fizzie> Nice to have it bright red like that, so that you don't miss any of those minor edits.
19:52:34 -!- sebbu has joined.
19:53:13 -!- sebbu has quit (Changing host).
19:53:13 -!- sebbu has joined.
19:55:54 -!- SpaceWizard has joined.
20:05:31 -!- elliott_ has joined.
20:09:39 <HackEgo> nandcoin schecoin mailaxcoin biltcoin shinycoin checoin knglycoin biecoin percoin ~coin birdhmentalkcoin ooetiocoin gultermanaxatificularycogschcoin firecoin bulocoin rel-petcoin gottcoin henetidadcoin leszecoin congcoin
20:09:55 <kmc> kind of want HackEgo to join ##crypto just for that
20:10:17 -!- fizzie has quit (*.net *.split).
20:10:18 -!- elliott has quit (*.net *.split).
20:10:43 -!- fizzie has joined.
20:14:08 <olsner> maybe you could arrange for `coins to temporarily join ##crypto, dump that, then leave
20:15:20 <olsner> (but I suspect the connections to IRC are managed outside the sandbox in a way that makes that messy)
20:16:22 <fizzie> olsner: You are a correct.
20:16:26 <Jafet> Make a bot that tunnels coinage to the other channel
20:17:43 <Taneb> My hard drive is almost full so I am going to get a new one
20:17:49 <Taneb> That is much larger
20:18:39 <olsner> it's a trap, the new disk will also run out of space
20:19:07 <FireFly> http://en.wikipedia.org/wiki/Spaghetti_code#Related_terms I feel that the images here really help illustrating the concept
20:19:13 -!- zzo38 has joined.
20:19:23 <fizzie> Taneb: I did that, and now the hard disk in this desktop is so large, the disk for backups is having space problems.
20:19:50 <Jafet> Indeed. And it will take you longer to move off larger disks. It's like gravity.
20:19:50 <Taneb> fizzie, I solve that problem by not caring about anything enough to back it up
20:20:40 <Taneb> Any recommendations for hard-drive?
20:20:54 <Bike> recommend a good one
20:21:14 <olsner> FireFly: hmm, most of those read like "good" code according to that article
20:21:48 <olsner> if lasagna code is "well-defined and separable layers", what's the term for code that is just layers everywhere?
20:22:45 <fizzie> FWIW, I bought a pair of "Seagate Barracuda ST3000DM001 3TB" disks for this desktop, because I've heard bad things about probably every (mainstream) brand, and it's all a crapshoot anyway.
20:23:07 <Jafet> There's supermarket microwave oven lasagna code, which is when your layers leak into each other and there is an odd smell in the background.
20:23:08 <Taneb> fizzie, I've heard they have problems with reliability
20:23:09 <FireFly> The last paragraph of the lasagna code section mentions how it could also be an anti-pattern if overdone
20:23:19 <fizzie> Taneb: I've heard that said of everything, though.
20:23:29 <Jafet> fizzie: there are two mainstream brands, so you may have indeed heard about all of them
20:24:16 <fizzie> Jafet: There used to be more, though.
20:25:19 <Jafet> There are the "green" disks, where most of the bad things you hear are actually true. Then there are the "black" ones which most people use.
20:25:45 <Jafet> WD also has enough other colours to start a gay pride parade but most of them are just product binning.
20:26:15 <fizzie> I think Seagate dropped the "green" nomenclature.
20:27:26 -!- oerjan has joined.
20:27:43 <fizzie> Looking at the Seagate section of the local shop, there's just other arbitrary terms ("Constellation", "Enterprise Capasity Series", "NAS", ...) now.
20:28:06 <fizzie> Also the middle one was spelled "Enterprice" here. Trying to hint at something, perhaps.
20:28:32 <fizzie> Or maybe it's the c from "capacity".
20:28:38 <Jafet> Perhaps you get to choose.
20:29:00 <olsner> hinting that the shop owner doesn't spell well?
20:29:29 <fizzie> olsner: It's the biggest e-retailer in all of Finland, I think.
20:29:58 <fizzie> http://en.wikipedia.org/wiki/Verkkokauppa.com Notable enough for Wikipedia, yet can't spell.
20:32:02 <olsner> well, seagate spells it normally afaict
20:32:19 <fizzie> The product links also have it right there in the URL.
20:33:05 <fizzie> WD has 3TB drives in "Green", "Purple", "Red", "Se" and "Black", and I'm wondering what kind of color "Se" is.
20:33:19 <fizzie> Oh, it's short for Server.
20:33:44 -!- hexagon has quit (Read error: Connection reset by peer).
20:34:22 <kmc> experts recommend buying a whole rainbow of drives
20:36:40 <FireFly> Oh, not a selenium hard drive
20:37:10 <fizzie> "WD Green Power -malleissa yhdistyy tehokkuus, luotettavuus ja ennen kaikkea virransäästö." "WD Purple-malleissa yhdistyy tehokkuus ja ennenkaikkea luotettavuus." "WD Red-malleissa yhdistyy tehokkuus, luotettavuus ja ennen kaikkea virransäästö." "WD Se-malleissa yhdistyy tehokkuus ja ennenkaikkea luotettavuus." "WD:n uudistuneessa Black -kovalevysarjassa yhdistyy huippuluokan ...
20:37:16 <fizzie> ... suorituskyky ja luotettavuus." Well, it's good that they're well differentiated, at least.
20:38:05 <int-e> oh, Selenium comes in several colors. Neat.
20:38:55 -!- Guest652 has joined.
20:39:15 -!- Guest652 has changed nick to hexagon.
20:50:23 -!- nisstyre has joined.
21:02:25 -!- Patashu has joined.
21:03:30 <zzo38> If you need more than one drive you can get each one different color, to tell apart.
21:13:00 -!- Sellyme has quit (Excess Flood).
21:13:17 -!- Sellyme has joined.
21:25:09 -!- Patashu has quit (Ping timeout: 252 seconds).
21:39:35 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
21:48:12 -!- boily has joined.
21:56:16 -!- idris-ircslave has quit (Quit: Terminated).
21:56:33 -!- idris-ircslave has joined.
22:11:28 -!- boily has quit (Quit: Poulet!).
22:41:12 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39241&oldid=39221 * Rdebath * (+557) /* Performance Matrix */
22:42:03 -!- rodgort has quit (Quit: ERC Version 5.3 (IRC client for Emacs)).
22:42:57 -!- augur has quit (Remote host closed the connection).
22:47:59 -!- rodgort has joined.
23:20:03 -!- augur has joined.
23:21:02 -!- augur has quit (Read error: Connection reset by peer).
23:21:25 -!- augur has joined.
23:33:53 -!- yorick has quit (Remote host closed the connection).
23:33:55 -!- nisstyre has joined.
23:48:42 <HackEgo> [wiki] [[Special:Log/newusers]] create * Quojil * New user account
00:01:38 -!- tromp has joined.
00:02:14 -!- tromp has quit (Read error: Connection reset by peer).
00:02:38 -!- tromp has joined.
00:17:08 -!- Sgeo has joined.
00:30:10 -!- zzo38 has quit (Remote host closed the connection).
00:33:35 -!- zzo38 has joined.
00:34:35 <zzo38> Now I fixed it so that filters in PHIRC (this IRC client) is allowed to include regular expressions if it starts with a forward slash.
00:36:38 -!- oerjan has quit (Quit: ZZoon).
00:55:55 <myname> http://www.qdb.us/305734 that kinda reminds me of zzo
01:06:29 <HackEgo> [wiki] [[Indirect]] N http://esolangs.org/w/index.php?oldid=39242 * Quojil * (+2214) Initial documentation
01:08:49 -!- monotone has quit (Quit: restart).
01:09:49 -!- monotone has joined.
01:11:24 <HackEgo> [wiki] [[Indirect]] http://esolangs.org/w/index.php?diff=39243&oldid=39242 * Quojil * (+267) Specifications & another edit to only example... for now.
01:11:53 <HackEgo> [wiki] [[Dogescript]] http://esolangs.org/w/index.php?diff=39244&oldid=38025 * 216.38.135.42 * (+73) /* External Resources */
01:12:06 <HackEgo> [wiki] [[Indirect]] http://esolangs.org/w/index.php?diff=39245&oldid=39243 * Quojil * (+0) /* How is it different */
01:14:40 <HackEgo> [wiki] [[Indirect]] M http://esolangs.org/w/index.php?diff=39246&oldid=39245 * Quojil * (+16) Modified example again and fixed typo.
01:15:58 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39247&oldid=39235 * Quojil * (+15) /* I */
01:23:47 <Sgeo> The Onion's Kelly is losing his grip
01:23:56 <Sgeo> The villain of the cartoon isn't covered in flies
01:25:35 <Sgeo> @run let reify = flip id; reflect = id in reify 6 (\p -> reflect p + reflect p)
01:26:28 <Sgeo> I am so tired of that example, it doesn't clarify anything
01:26:54 <Sgeo> I think what I want is an example of, e.g., passing around a username+password known only at runtime
01:27:32 * Sgeo starts reading
01:29:31 <^v> my kitteh is so flufffie
01:29:46 <Sgeo> Oh, so you can create the proxy out of thin air... I guess ScopedTypeVariables is needed to do that?
01:30:49 <elliott_> no. you can do it in other ways too.
01:31:12 <Sgeo> Now, if only this were someplace more obvious than some random paste that you get linked to if you ask the right question...
01:31:16 <elliott_> ScopedTypeVariables is never or at least only very rarely necessary, afaik.
01:31:25 <elliott_> reflection ships with more examples.
01:33:30 <Sgeo> The phantom type parameter in Report and Datum are strictly necessary, or not?
01:34:24 <elliott_> you would not want to eliminate them. they provide type safety.
01:34:42 <elliott_> you can mix multiple configurations in one program and they are tagged with the type. it is just like putting the configuration itself into the type.
01:35:05 <elliott_> if you eliminate the type parameter, then you just have to add Proxy arguments, but e.g. that Num instance would not be possible.
01:36:08 <elliott_> you can e.g., have (Int `Mod` n) where you can think of the n "phantom" type as actually just a natural
01:36:22 <elliott_> (and you can make instances so that you can use a TypeLit natural as an "n" there, as well as supporting runtime decision of n)
01:36:56 <elliott_> btw, all of this is in the paper, if you read it
01:37:24 <Sgeo> I know the paper has an example of using it for modulus arithmetic...
01:37:45 <Bike> the 6 example is pretty lol
01:39:03 <Sgeo> I like seeing a lot of examples. I think yours was the most helpful so far, but... I still wish it was someplace more accessible
01:40:47 <elliott_> I hereby release it under the CC0 1.0 Universal terms, available at https://creativecommons.org/publicdomain/zero/1.0/legalcode.
01:40:57 <elliott_> feel free to submit a patch to add it; I'd prefer no credit in the source.
01:42:37 <elliott_> (better quote those two lines in the pull request so there's no legal lawyering.)
01:44:28 <elliott_> or maybe I should GPL it just to be a pain. (too late now.)
01:46:56 <Sgeo> What should I call the file? I have a feeling you may not like the name ReaderLike.hs
01:47:46 <Bike> psh it's in public domain fuck elliott_
01:48:03 <Bike> ElliottSucksLol.hs
01:48:06 <elliott_> pretty much, do what you like with it :p
01:48:37 <elliott_> I don't want credit because I just wrote it ad-hoc and nobody should feel like I have creative rights over it.
01:49:05 <Sgeo> I tried to copy/paste your lines, they got eaten
01:50:28 <nooodl> hm is the "available at https://creativecommons.org/..." legally required
01:51:17 <Bike> i don't think you people understand the public domain very well
01:52:40 <Bike> i could take the code and tattoo it on my ass and sell photos of the ass and musical compositions based on the ass to Disney and elliott_ couldn't do shit.
01:53:10 <elliott_> nooodl: I don't think there's any clear standard. I think what I said is unambiguous enough for any court.
01:53:33 <elliott_> Sgeo: eaten...? well, just say you got permission from me to use it under CC0.
01:53:46 <Sgeo> Bike: Unless some country says that elliott_ isn't allowed to give permission away like that
01:53:54 <Sgeo> I think that's why CC0 exists
01:54:00 <Bike> too bad. taht's an ass state
01:54:05 <elliott_> CC0 still probably doesn't work everywhere.
01:55:19 <pikhq> CC0 probably works in more jurisdictions than GPL.
01:56:36 <pikhq> And it certainly works in more jurisdictions than a generic public domain grant. :)
01:57:24 <Bike> i only use the wtfpl personally
01:57:47 <pikhq> The WTFPL probably doesn't work in a decent handful of jurisdictions, though it definitely does under common law.
01:58:08 <Bike> that's the beauty of it: fuck those jurisdictionsssss
01:58:09 <nooodl> how can the wtfpl fail to work
01:58:41 <elliott_> nooodl: e.g. some countries don't let you just give away your rights without something in return like that
01:59:04 <Bike> my attitudes towards law is like a billion times more lackadaisical than most programmers and i love it
01:59:56 <pikhq> A sampling of github suggests it's actually much less lackadaisical than most programmers.
02:00:08 <pikhq> The typical repo on github is unlicensed. :)
02:00:30 <pikhq> The WTFPL might not work in all jurisdictions, but it definitely is a legal copyright license.
02:02:33 <Bike> "In May 2005, Daniel Wallace filed suit against the Free Software Foundation in the Southern District of Indiana, contending that the GPL is an illegal attempt to fix prices (at zero)." nice
02:02:59 <Bike> "Defendants argued that since it is impossible to maintain trade secrets while being compliant with GPL and distributing the work, they are not in breach of trade secrets" this is some good stuff
02:10:16 -!- SpaceWizard has quit (Read error: Operation timed out).
02:36:31 -!- aloril has quit (Ping timeout: 264 seconds).
02:50:14 -!- aloril has joined.
03:01:53 <Sgeo> elliott_: I'm starting to think you're right about trusting random Haskell over OpenSSL (not really... if it gets as many eyes looking at it as OpenSSL, then definitely... but the OpenSSL bug is really just anecdotal evidence, I think?)
03:02:56 <Bike> when have programmers ever used non-anecdotal evidence?
03:04:06 <Sgeo> I heard a programmer use non-anecdotal evidence just the other day
03:25:48 -!- ter2 has joined.
03:36:33 -!- ter2 has quit (Ping timeout: 240 seconds).
03:39:54 <Jafet> Bike: note that you can't conversely take Disney's stuff, because CTEA and 93/98/EEC
03:40:41 <Bike> my ass will hae to wait
03:41:02 -!- ter2 has joined.
03:43:09 -!- tromp_ has joined.
03:44:06 -!- tromp has quit (Ping timeout: 255 seconds).
03:55:26 -!- nooodl has quit (Quit: Ik ga weg).
04:01:37 <HackEgo> 2.74coin epitcoin hoycoin altiverowcoin rainfrecoin pathcoin alighcoin relcoin undanicasmicoin halfhacoin calcoin etercoin rencoin returncoin minocoin crading-booker)coin vollicoin gartrethintynskinguissioncoin sublecoin nnrcoin
04:03:57 <kmc> numberwangcoin
04:08:52 <Sgeo> I remember eating fish once, I don't remember what kind of fish
04:08:59 <Sgeo> Flounder? Is that a fish people eat
04:10:25 <Bike> https://twitter.com/RUST_HULK/status/453294938763976704 of course
04:12:41 * kmc has null-routed twitter locally
04:14:52 -!- tertu3 has joined.
04:14:53 -!- ter2 has quit (Read error: Connection reset by peer).
04:16:41 <Sgeo> OOOOOOOH https://github.com/chrisdone/foreign-store
04:17:14 <Sgeo> Blah, looks less smooth than in, say, CL or Smalltalk
04:17:22 <Sgeo> Still, better than DrRacket
04:20:53 <Sgeo> https://github.com/chrisdone/ghci-reload-demo
04:23:12 <Sgeo> "I shouldn’t have to tell anyone this but just in case: don’t use this in production."
04:24:45 <Bike> using a live image as production seems bad anyway...
04:25:32 <Sgeo> What do Erlangers do?
04:25:47 -!- tromp_ has quit (Remote host closed the connection).
04:26:23 -!- tromp has joined.
04:26:25 <kmc> "oh yeah, use me in production"
04:26:41 <Bike> i'm not ready to enter this porn dimension.
04:30:54 -!- tromp has quit (Ping timeout: 255 seconds).
04:33:42 <Sgeo> Wikipedia doesn't have Heartbleed yet
04:34:05 <Bike> http://en.wikipedia.org/wiki/Openssl#Heartbleed_bug ?
04:35:00 <Sgeo> And that's what I get for assuming that Wikipedia search works
04:35:17 <Sgeo> "known to attackers since March 2012."
04:35:19 <kmc> ♫ learnin' a lesson ♫
04:35:32 <Bike> learnin on a wish
04:36:39 -!- tertu3 has quit (Ping timeout: 255 seconds).
04:37:12 -!- aloril has quit (Read error: Operation timed out).
04:38:07 * kmc restarts irssi and his EC2 instance
04:38:09 <kmc> 21:38:09 up 186 days, 3:48, 6 users, load average: 0.57, 0.22, 0.12
04:38:16 -!- kmc has quit (Quit: leaving).
04:39:14 <Bike> the end of an era
04:40:22 -!- tomsmeding has joined.
04:41:18 -!- tomsmeding has left.
04:41:24 -!- kmc has joined.
04:41:58 <HackEgo> hebdcoin continucoin reding-boocoin clunkcoin illghcoin codifycoin singcoin rcelumcoin spoohcoin emmertcoin yourcoin q-refcoin temcoin etaincoin proofcoin haowcoin recuncoin nonicoin murprincoin apocoin
04:42:49 -!- ineiros has quit (Ping timeout: 240 seconds).
04:43:50 -!- ineiros has joined.
04:47:30 -!- Sorella has quit (Quit: It is tiem!).
04:51:41 <HackEgo> [wiki] [[Talk:MarioLANG]] http://esolangs.org/w/index.php?diff=39248&oldid=39239 * T.J.S.1 * (+440) Interpreter
04:52:58 <kmc> http://www.antichipotle.com/git/
04:53:22 <Bike> Firefox can't establish a connection to the server at www.antichipotle.com.
04:54:35 -!- aloril has joined.
04:57:04 * quintopia isn't using a vulnerable ssh. phew.
04:57:18 <kmc> there's a ssh vuln too?
04:58:26 <quintopia> oh wait. i think i misread that :P
04:59:24 <Bike> what if my password is my birthday
05:03:12 <zzo38> Bike: I don't care if it is or not. (Hopefully your date of birth doesn't change; I don't expect such things ever to change!!)
05:09:27 <quintopia> i wish my birthday got one year later every year
05:09:58 <kmc> zzo38: what if the calendar changes?
05:14:08 <zzo38> kmc: Then, you can write it in the new notation/calendar-based-system.
05:14:57 <zzo38> Already there is different kind of calendar, but Gregorian calendar is a common kind (and so is UNIX).
05:15:19 <zzo38> But you can figure out using, Discordian calendar instead, if you prefer to do so.
05:15:20 -!- Slereah_ has joined.
05:18:21 <fizzie> Fun fact: esolangs.org had Debian wheezy installed, but the line for security updates was for squeeze (oldstable)...
05:18:36 <fizzie> (sources.list line, that is.)
05:26:48 -!- Bike has quit (Quit: leaving).
05:36:18 -!- password2 has joined.
05:59:40 <HackEgo> [wiki] [[Kolmogorov machine]] http://esolangs.org/w/index.php?diff=39249&oldid=24661 * 99.118.9.187 * (+24) /* See Also */
06:02:01 <Slereah_> The Andrei Machine is the best
06:03:00 <maurer> Out of curiosity, does anyone know how the heartbleed thing works?
06:03:03 <maurer> the site is not super clear
06:06:14 -!- conehead has quit (Quit: Computer has gone to sleep).
06:16:36 <HackEgo> [wiki] [[Kolmogorov machine]] http://esolangs.org/w/index.php?diff=39250&oldid=39249 * 99.118.9.187 * (+146) Я не говорю по-русски
06:28:55 <Sgeo> "Responsible disclosure (n.): coming up with a cool logo, homepage and name for your terrifying bug before panicking the Internet with it"
06:32:34 -!- `^_^v has quit (Ping timeout: 252 seconds).
06:45:25 <fizzie> Oh, the company behind that thing (Codenomicon) is originally Finnish.
06:45:54 -!- Sgeo_ has joined.
06:49:30 -!- Sgeo has quit (Ping timeout: 255 seconds).
07:01:14 <fizzie> Heh, kind of funny: StartSSL provides certificates for free, but asks a $24.90 "handling fee" for revocation.
07:04:24 -!- `^_^v has joined.
07:05:23 <kmc> "Not a classy industry, is it?" "It ranks slightly behind three-card monty but two spots ahead of straight daytime flashing"
07:06:22 <kmc> lexande sometimes claims to be an X.509 certificate authority but he won't give me a cert
07:07:43 <fizzie> I was hoping for this DANE thing to get popularly supported (it's not like a free StartSSL certificate "validates" anything else than a domain name either), but it doesn't seem like it.
07:12:25 <lexande> kmc: i suspect honest lexande may be too honest to be an X.509 certificate authority
07:17:50 -!- ^v has quit (Ping timeout: 252 seconds).
08:25:20 -!- Patashu has joined.
08:30:12 -!- Patashu[Zzz] has joined.
08:30:12 -!- Patashu has quit (Disconnected by services).
08:44:50 -!- Patashu[Zzz] has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
08:58:31 -!- oerjan has joined.
09:01:22 -!- Slereah has joined.
09:03:53 -!- Slereah_ has quit (Ping timeout: 246 seconds).
09:16:20 -!- Patashu has joined.
09:16:56 -!- conehead has joined.
09:18:38 -!- aloril has quit (Ping timeout: 240 seconds).
09:23:08 -!- password2 has quit (Ping timeout: 240 seconds).
09:24:19 <fizzie> "error: command failed: non-zero return code: -11"
09:24:25 <fizzie> It's good to have verbose diagnostics.
09:25:07 <oerjan> someone turned that command down to eleven
09:29:30 -!- yorick has joined.
09:30:15 <fizzie> It seems to be a segfault, actually. Didn't recognize.
09:30:34 -!- nooodl has joined.
09:38:18 -!- aloril has joined.
09:39:00 -!- Patashu has quit (*.net *.split).
09:39:02 -!- Sgeo_ has quit (*.net *.split).
09:39:02 -!- ineiros has quit (*.net *.split).
09:39:03 -!- zzo38 has quit (*.net *.split).
09:39:03 -!- john_metcalf has quit (*.net *.split).
09:39:07 -!- Frooxius has quit (*.net *.split).
09:39:09 -!- EgoBot has quit (*.net *.split).
09:39:09 -!- trn has quit (*.net *.split).
09:39:09 -!- jix has quit (*.net *.split).
09:39:11 -!- Speed` has quit (*.net *.split).
09:39:11 -!- mtve has quit (*.net *.split).
09:39:11 -!- Jafet has quit (*.net *.split).
09:39:13 -!- lifthrasiir has quit (*.net *.split).
09:39:13 -!- b_jonas has quit (*.net *.split).
09:39:14 -!- myndzi has quit (*.net *.split).
09:39:19 -!- Patashu has joined.
09:39:19 -!- Speed` has joined.
09:39:21 -!- myndzi has joined.
09:39:22 -!- Jafet has joined.
09:39:25 -!- mtve has joined.
09:39:27 -!- Sgeo has joined.
09:39:29 -!- jix has joined.
09:39:34 -!- Jafet has quit (Changing host).
09:39:34 -!- Jafet has joined.
09:39:39 -!- Frooxius has joined.
09:39:40 -!- yorick has quit (Read error: Connection reset by peer).
09:39:44 -!- Frooxius has quit (*.net *.split).
09:39:44 -!- Sgeo has quit (*.net *.split).
09:39:44 -!- Jafet has quit (*.net *.split).
09:39:45 -!- aloril has quit (*.net *.split).
09:39:47 -!- monotone has quit (*.net *.split).
09:39:47 -!- augur has quit (*.net *.split).
09:39:48 -!- vravn has quit (*.net *.split).
09:39:52 -!- lexande has quit (*.net *.split).
09:39:58 -!- lexande has joined.
09:40:00 -!- TodPunk has quit (*.net *.split).
09:40:01 -!- trout has quit (*.net *.split).
09:40:01 -!- samebchase has quit (*.net *.split).
09:40:02 -!- Gregor has quit (*.net *.split).
09:40:02 -!- mroman has quit (*.net *.split).
09:40:03 -!- ion has quit (*.net *.split).
09:40:03 -!- shachaf has quit (*.net *.split).
09:40:03 -!- douglass_ has quit (*.net *.split).
09:40:03 -!- FireFly has quit (*.net *.split).
09:40:10 -!- augur has joined.
09:40:13 -!- mroman has joined.
09:40:17 -!- Gregor has joined.
09:40:17 -!- samebchase has joined.
09:40:29 -!- TodPunk has joined.
09:40:41 -!- aloril has joined.
09:40:42 -!- Frooxius has joined.
09:40:53 -!- trn has joined.
09:41:14 -!- FireFly has joined.
09:41:20 -!- fizzie has quit (*.net *.split).
09:41:24 -!- atehwa_ has quit (*.net *.split).
09:41:27 -!- nortti has quit (*.net *.split).
09:41:33 -!- fizzie has joined.
09:41:34 -!- nortti has joined.
09:42:14 -!- kmc has quit (*.net *.split).
09:42:15 -!- rodgort has quit (*.net *.split).
09:42:16 -!- elliott_ has quit (*.net *.split).
09:42:18 -!- jconn has quit (*.net *.split).
09:42:22 -!- oklopol has quit (*.net *.split).
09:42:26 -!- myname has quit (*.net *.split).
09:42:28 -!- realzies has quit (*.net *.split).
09:42:37 -!- oklopol has joined.
09:42:38 -!- jconn has joined.
09:42:48 -!- myname has joined.
09:42:55 -!- realzies has joined.
09:42:55 -!- realzies has quit (Changing host).
09:42:55 -!- realzies has joined.
09:42:57 * oerjan perhaps should read about that SSL vulnerabiliy
09:43:57 -!- Sgeo has joined.
09:44:08 -!- ineiros has joined.
09:44:17 -!- EgoBot has joined.
09:45:19 -!- monotone has joined.
09:46:08 -!- ion has joined.
09:46:18 -!- vravn has joined.
09:46:25 -!- atehwa has joined.
09:47:32 -!- kmc has joined.
09:47:36 -!- rodgort has joined.
09:47:39 -!- Sellyme has quit (Excess Flood).
09:49:18 -!- lifthrasiir has joined.
09:49:50 -!- Sellyme has joined.
09:51:05 -!- douglass_ has joined.
09:52:09 -!- shachaf has joined.
09:54:25 -!- elliott has joined.
09:54:49 -!- elliott has changed nick to Guest49575.
10:03:33 -!- trn has quit (*.net *.split).
10:03:33 -!- myndzi has quit (*.net *.split).
10:03:44 -!- scoff has quit (*.net *.split).
10:03:56 -!- myndzi has joined.
10:04:09 -!- b_jonas has joined.
10:05:18 -!- trn has joined.
10:06:40 -!- conehead has quit (Quit: Computer has gone to sleep).
10:07:17 <HackEgo> [wiki] [[Talk:MarioLANG]] http://esolangs.org/w/index.php?diff=39251&oldid=39248 * Oerjan * (+103) /* Interpreter */ Of course
10:07:23 -!- scoff has joined.
10:09:11 -!- yorick has joined.
10:12:18 <HackEgo> [wiki] [[Kolmogorov machine]] http://esolangs.org/w/index.php?diff=39252&oldid=39250 * Oerjan * (+23) bullets, and spell Russian title with Russian letters
10:12:20 <Taneb> I like the wiki edits
10:14:52 <oerjan> tomorrow: DMM's new comic
10:14:52 <Taneb> That is, I like that HackEgo posts them
10:15:01 <Taneb> oerjan, oh god I forgot about that
10:15:18 -!- myndzi has quit (Ping timeout: 264 seconds).
10:15:43 <oerjan> he has revealed a hint that the name is a tv trope
10:16:42 <Taneb> I've stopped following the IWC rerun :(
10:17:03 <Taneb> Might try to get back into it
10:17:05 <oerjan> well this was in the forum.
10:17:18 <Taneb> I haven't been there for aaaageees
10:17:48 <oerjan> he also said "This will narrow things down quite a bit:" i smell irony
10:18:04 <Taneb> That sounds more like sarcasm
10:18:32 * oerjan is vague on those fine distinctions
10:18:48 <Taneb> I just assume that nothing is irony
10:18:57 <Taneb> I know what dramatic irony and metallurgic irony are
10:19:52 -!- myndzi has joined.
10:19:53 <oerjan> i googled that and the most promising hit was tvtropes
10:20:08 <Taneb> Metallurgic irony is "sort of like iron"
10:24:02 -!- boily has joined.
10:26:45 -!- realzies has quit (*.net *.split).
10:26:49 -!- nortti has quit (*.net *.split).
10:26:53 -!- Gregor has quit (*.net *.split).
10:26:53 -!- samebchase has quit (*.net *.split).
10:26:57 -!- jix has quit (*.net *.split).
10:26:59 -!- Slereah has quit (*.net *.split).
10:27:03 -!- nisstyre has quit (*.net *.split).
10:27:07 -!- HackEgo has quit (*.net *.split).
10:27:08 -!- copumpkin has quit (*.net *.split).
10:27:12 -!- tromp__ has quit (*.net *.split).
10:27:14 -!- glogbackup has quit (*.net *.split).
10:27:18 -!- Gracenotes has quit (*.net *.split).
10:27:18 -!- JZTech101 has quit (*.net *.split).
10:27:20 -!- ggherdov_ has quit (*.net *.split).
10:27:25 -!- Gracenotes has joined.
10:27:26 -!- Gregor has joined.
10:27:32 -!- nortti has joined.
10:27:39 -!- samebchase has joined.
10:27:41 -!- HackEgo has joined.
10:27:42 -!- JZTech101 has joined.
10:27:46 -!- Slereah_ has joined.
10:27:47 -!- realzies has joined.
10:27:48 -!- tromp__ has joined.
10:27:51 -!- jix has joined.
10:27:52 -!- realzies has quit (Changing host).
10:27:52 -!- realzies has joined.
10:27:55 -!- copumpkin has joined.
10:27:58 -!- Gregor has changed nick to Guest72108.
10:28:05 -!- JZTech101 has changed nick to Guest79765.
10:28:17 -!- nisstyre has joined.
10:32:12 -!- SpaceWizard has joined.
10:38:53 -!- conehead has joined.
10:39:44 -!- Guest72108 has quit (*.net *.split).
10:39:45 -!- yorick has quit (*.net *.split).
10:39:49 -!- atehwa has quit (*.net *.split).
10:39:55 -!- aloril has quit (*.net *.split).
10:39:55 -!- mroman has quit (*.net *.split).
10:39:58 -!- nooodl has quit (*.net *.split).
10:40:10 -!- atehwa has joined.
10:40:11 -!- Gregor has joined.
10:40:16 -!- yorick has joined.
10:40:16 -!- nooodl has joined.
10:40:36 -!- mroman has joined.
10:40:39 -!- aloril has joined.
10:43:37 -!- ggherdov_ has joined.
11:08:45 -!- boily has quit (Quit: DEGOVERNMENTED CHICKEN).
11:15:55 <fizzie> "checking for gcc... icc" "checking whether we are using the GNU C compiler... yes" hmm.
11:25:09 -!- conehead has quit (Quit: Computer has gone to sleep).
11:47:41 -!- realzies has quit (Ping timeout: 264 seconds).
11:54:44 -!- Patashu has quit (Ping timeout: 252 seconds).
11:59:27 -!- realzies has joined.
12:00:12 -!- variable has joined.
12:07:51 -!- tromp has joined.
12:12:01 -!- password2 has joined.
12:13:43 -!- Guest49575 has quit (Quit: Reconnecting).
12:13:49 -!- elliott has joined.
12:14:09 -!- elliott has quit (Client Quit).
12:14:17 -!- elliott has joined.
12:15:23 -!- tromp has quit (Remote host closed the connection).
12:15:56 -!- Sgeo has quit (Read error: Connection reset by peer).
12:16:00 -!- tromp has joined.
12:18:32 -!- myndzi has quit (Ping timeout: 252 seconds).
12:18:55 -!- trn has quit (Ping timeout: 252 seconds).
12:20:20 -!- tromp has quit (Ping timeout: 246 seconds).
12:21:52 -!- Jafet has joined.
12:23:00 -!- myndzi has joined.
12:23:14 -!- trn has joined.
12:31:07 -!- nucular has joined.
12:49:55 -!- augur has quit (Quit: Leaving...).
13:14:13 -!- ^v has joined.
13:30:17 -!- oerjan has quit (Quit: leaving).
13:59:45 -!- password2 has quit (Read error: Connection reset by peer).
14:06:38 -!- password2 has joined.
14:09:51 <HackEgo> [wiki] [[MarioLANG]] http://esolangs.org/w/index.php?diff=39253&oldid=37549 * T.J.S.1 * (+303) Add interpreter by T.J.S.1
14:12:18 <HackEgo> [wiki] [[User:T.J.S.1]] http://esolangs.org/w/index.php?diff=39254&oldid=36857 * T.J.S.1 * (+165) Updates
14:15:58 -!- password2_ has joined.
14:16:39 -!- password2 has quit (Read error: Connection reset by peer).
14:19:31 -!- nisstyre has quit (Quit: bai).
14:22:35 -!- password2_ has changed nick to password2.
14:25:00 -!- augur has joined.
14:29:50 -!- `^_^v has quit (Ping timeout: 252 seconds).
14:31:46 -!- `^_^v has joined.
14:32:26 -!- Melvar has quit (Quit: WeeChat 0.4.3).
14:32:45 -!- Melvar has joined.
14:37:37 <Jafet> `run echo $'!\xAA1\xB2xM|;b\xD1\x15\xA3\x0C\x18:\xB0I\xA7\x1F\xB6\xCE\xD4~\x161\xAD\xF4\xB8k$\x0C\xCA\xE8\xE8b\x97\xE3\xE3\x95Yly\x05\xD3\x9F\x1E\xAC\xEC\xBA\x9E\x86=\xBD\x13\xDF\xBCd\x8C\xEEdo\x93\x8F\xB9\x97\xCD_\xE6\xAA\xD3}Z\xAB\x17\xC5\xFB+\xE8i\x1A\xB1~\xC1\xA7\xD6|$\x7F\x92\x19\xBF\x94\xF6\xD7\xE6\x0E\xA4E\xF3\xCD\x97q'\''C\x07k\xBD1T&\xCA\x84#\x8B,x\x86\xCE\xF6\x19\xE6\xB6\xAC' | dis86
14:37:49 <Jafet> `run dis86 $'!\xAA1\xB2xM|;b\xD1\x15\xA3\x0C\x18:\xB0I\xA7\x1F\xB6\xCE\xD4~\x161\xAD\xF4\xB8k$\x0C\xCA\xE8\xE8b\x97\xE3\xE3\x95Yly\x05\xD3\x9F\x1E\xAC\xEC\xBA\x9E\x86=\xBD\x13\xDF\xBCd\x8C\xEEdo\x93\x8F\xB9\x97\xCD_\xE6\xAA\xD3}Z\xAB\x17\xC5\xFB+\xE8i\x1A\xB1~\xC1\xA7\xD6|$\x7F\x92\x19\xBF\x94\xF6\xD7\xE6\x0E\xA4E\xF3\xCD\x97q'\''C\x07k\xBD1T&\xCA\x84#\x8B,x\x86\xCE\xF6\x19\xE6\xB6\xAC'
14:38:16 <Jafet> `run dis86 $'\x90\x90'
14:41:55 <Jafet> `run dis86 aa21b2314d783b7cd162a315180cb03aa749b61fd4ce167ead31b8f4246bca0ce8e89762e3e35995
14:41:56 <HackEgo> stosb; and [rdx+0x3b784d31], esi; jl 0xffffffda; invalid; mov [0xb649a73ab00c1815], eax; invalid; invalid; invalid; invalid; jle 0xffffffc6; xor [rax-0x3594db0c], edi; or al, 0xe8; call 0xffffffffe3e362bd; pop rcx; xchg ebp, eax;
14:42:55 -!- password2 has quit (Ping timeout: 240 seconds).
14:45:10 -!- esowiki has joined.
14:45:14 -!- esowiki has joined.
14:45:15 -!- esowiki has joined.
14:45:16 -!- glogbot has joined.
14:45:16 <?unknown?> [freenode-info] if you're at a conference and other people are having trouble connecting, please mention it to staff: http://freenode.net/faq.shtml#gettinghelp
14:45:22 -!- TodPunk has joined.
14:45:23 -!- oklopol has joined.
14:45:29 -!- clog has joined.
14:45:47 -!- ejls has joined.
14:45:58 -!- olsner has joined.
14:46:53 -!- FireFly has quit (Excess Flood).
14:48:54 -!- int-e has joined.
14:49:22 -!- FireFly has joined.
14:50:23 -!- maurer has joined.
14:50:40 <HackEgo> [wiki] [[Indirect]] http://esolangs.org/w/index.php?diff=39255&oldid=39246 * 76.94.2.75 * (+383) /* "operations" */
14:51:32 <HackEgo> [wiki] [[Indirect]] http://esolangs.org/w/index.php?diff=39256&oldid=39255 * 76.94.2.75 * (+104) /* "operations" */
14:52:13 -!- Taneb has joined.
14:53:18 -!- lambdabot has joined.
14:55:14 -!- myname has joined.
14:55:41 -!- quintopia has joined.
14:55:42 -!- `^_^v has quit (Ping timeout: 265 seconds).
14:58:29 -!- `^_^v has joined.
14:59:17 -!- ^v has quit (Ping timeout: 252 seconds).
15:00:36 -!- newsham has joined.
15:05:54 -!- xpte has joined.
15:46:40 -!- nisstyre has joined.
15:53:58 -!- ^v has joined.
15:54:10 -!- nisstyre has quit (Read error: Connection reset by peer).
15:54:20 -!- nisstyre has joined.
15:59:23 -!- MindlessDrone has joined.
16:02:11 -!- stuntaneous has joined.
16:06:08 -!- password2 has joined.
16:31:19 -!- password2 has quit (Ping timeout: 240 seconds).
22:25:02 <oerjan> cool https://en.wikipedia.org/wiki/Seventeen_or_Bust
22:26:31 <elliott> oerjan: seems somewhat stalled
22:28:21 <oerjan> there's of course the possibility the conjecture is wrong and the last six will never budge
22:28:54 <elliott> no progress for seven years is a bit sad
22:29:24 <Taneb> And their homepage
22:29:51 <oerjan> note the digits column though, they've definitely not stopped searching
22:31:38 <oerjan> maybe they should get tao on the case to prove it's wrong
22:34:41 -!- fizzie has quit (Ping timeout: 245 seconds).
22:34:43 <oerjan> indeed, his blog seems to have never mentioned it
22:36:53 -!- fungot has quit (Ping timeout: 252 seconds).
22:39:41 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
22:40:15 -!- conehead has joined.
22:46:17 -!- fizzie has joined.
22:46:50 <fizzie> Hm, this time the codu.org is in fact entirely down, or is it just me?
22:53:54 <fizzie> No, I mean, http://codu.org/logs/_esoteric/ or http://codu.org/ for that matter.
22:54:34 <oerjan> that's what i meant too
22:54:51 <fizzie> Oh, I didn't understand DFM at all.
22:55:05 <fizzie> I thought it was some kind of a new HTH.
22:55:24 <fizzie> (I was trying to see all the no doubt incredible happenings that had happened while I was gone there.)
22:55:26 <oerjan> no it was a new WFM HTH
22:55:52 <oerjan> <oerjan> indeed, his blog seems to have never mentioned it
22:56:23 <oerjan> i suppose you may have missed something before that too
22:56:47 <fizzie> "<oerjan> note the digits column though, they've definitely not stopped searching" is the last I saw. But it's not all that important.
22:58:04 <oerjan> ok 2048 is officially passé, dagbladet.no is covering it. (and putting it behind their paywall part.)
22:58:04 <quintopia> dfm means both "down for me" and "doesn't fucking matter"...different farflung meanings
23:02:04 -!- Sgeo has joined.
23:14:13 -!- conehead has quit (Quit: Computer has gone to sleep).
23:14:42 <quintopia> are there numbers stations on twitter
23:15:56 <oerjan> https://twitter.com/NumbersStations
23:16:17 <oerjan> i assume that was a rhetorical question
23:18:36 -!- tromp has joined.
23:21:22 -!- variable has quit (Write error: Connection reset by peer).
22:27:56 -!- boily has joined.
22:28:11 <boily> lexande: hellexandello! you'll be quoted in no time.
22:29:18 -!- Tritonio has quit (Ping timeout: 240 seconds).
22:31:16 <boily> lexande: ♪ding♪ your missing quote is ready!
22:31:34 <boily> quintopia: quintellopiaaaaaaaaaaaaaaaaa!!!
22:32:45 -!- esowiki has joined.
22:32:46 -!- glogbot has joined.
22:32:49 -!- esowiki has joined.
22:32:50 -!- esowiki has joined.
22:33:38 <boily> quintopia: how's life? is it spring already down South?
22:35:05 -!- esowiki has joined.
22:35:06 -!- glogbot has joined.
22:35:09 -!- esowiki has joined.
22:35:09 -!- esowiki has joined.
22:37:12 <lexande> boily: thank you! i am still missing a description though
22:37:32 <shachaf> did you ever get lexande's approximate coördinates and body weigh
22:37:35 <oerjan> now the codu logs are empty pages :(
22:38:36 <boily> lexande: I know. no one entered a Wisdom Entry about you yet.
22:38:48 <boily> shachaf: not yet. let me ask them the The Question.
22:39:12 <boily> lexande: eeeeeh... you know about the bees and flowers and storks, right?
22:39:33 <boily> lexande: also, could you please answer the The Question? what are your approximate coördinates and body weigh?
22:40:13 <lexande> i answered it on 2013-10-08
22:40:47 <lexande> 10:11 < boily> lexande: what kind of people do you meet? are met people human? do you like roast beef? what are your approximate coördinates and body weigh?
22:40:56 <lexande> 10:16 < lexande> boily: {iowa, tanzania, cambridge, caltech, boston, new york, CMU, random traveling} people; yes (to first approximation); ambivalent; (40.80, -73.94) and 90kg
22:41:11 <lexande> 10:21 < lexande> err, 900N sorry
22:41:12 <lexande> 10:21 * boily falls down from his chair “A first! Complete and useful information!”
22:41:26 <boily> ah bin torieux. autant pour moi...
22:42:15 <HackEgo> boily is monetizing a broterhood scheme with the Guardian of Lachine. He's also a NaniDispenser, a Man Eating Chicken and a METARologist.
22:45:13 <boily> int-e: int-ello. sorry, let me cuttlefishify the channel ipso facto.
22:45:31 -!- metasepia has joined.
22:45:36 <metasepia> LOWI 092220Z AUTO VRB02KT 9999 BKN090 08/M00 Q1023
22:49:43 * int-e fails to think of a clever way of combining "thanks" and "boily" into a single word. thankoily? much boiblyged?
22:50:09 <int-e> suggestions welcome.
22:52:45 -!- nucular has quit (Quit: Excess Food).
22:55:01 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39273&oldid=39272 * 198.188.4.4 * (+279) Borrowed decrement from Nock
22:58:06 <boily> “much boiblyged”. hi hi hi :D
22:58:52 <metasepia> CYUL 092200Z 26014G22KT 30SM SKC 04/M10 A2984 RMK SLP106
23:03:21 <ion> https://twitter.com/Slidebite/status/453974294582665217
23:05:31 <HackEgo> [wiki] [[Talk:Smartboxes]] N http://esolangs.org/w/index.php?oldid=39274 * 198.188.4.4 * (+369) Created page with "--~~~~ I'm probably going to write a Hoon implementation at some point. Though in that case I'll borrow the local convention of %literals (besides numbers, I suppose I could j..."
23:17:19 -!- augur has joined.
23:24:03 -!- augur has quit (Remote host closed the connection).
23:32:57 <ion> https://fbcdn-sphotos-f-a.akamaihd.net/hphotos-ak-ash3/t31.0-8/1941475_10203307420304421_4729873601312022517_o.jpg “This content cannot be displayed in a frame”
23:33:17 -!- yorick has quit (Remote host closed the connection).
23:35:18 -!- augur has joined.
23:35:53 <kmc> is that the error produced by X-Frame-Options ?
23:37:01 -!- augur has quit (Remote host closed the connection).
23:39:00 -!- Sgeo has joined.
23:40:04 -!- tromp has joined.
23:47:14 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39275&oldid=39273 * 198.188.4.4 * (+36) Amended to use fixpoint combinator instead of relying on scope
23:53:09 -!- Froox has joined.
23:55:02 -!- Froox has quit (Client Quit).
00:02:15 <HackEgo> aeoldcoin immentheoncoin olerankcoin aarecoin glypecoin taxiccoin corumcoin abcdxcoin evisincoin cvlcoin singcoin bam1coin smatyracoin beitcoin mkmbccoin phabetcoin checoin vernatocoin boenamcoin viotecoin
00:03:51 -!- augur has joined.
00:18:35 <HackEgo> [wiki] [[Special:Log/newusers]] create * Zerk * New user account
00:22:47 <boily> http://boingboing.net/2014/04/09/breather-is-like-an-airbnb-by.html ← that is an idea eagerly waiting for a disaster...
00:22:55 <boily> (but hey, I can get some in Montréal!)
00:31:06 -!- SpaceWizard has quit (Changing host).
00:31:06 -!- SpaceWizard has joined.
00:43:55 -!- ^v has joined.
00:45:04 -!- oerjan has quit (Quit: Nite).
00:46:25 -!- augur has quit (Remote host closed the connection).
00:49:40 <boily> Sgeo: people are random. everything can happen. like, everything.
00:54:54 <Bike> https://twitter.com/tavisrudd/status/454044086547136512/photo/1/large good news everyone, i have found the best programming psychology paper yet.
00:55:44 <Bike> kind of funny that i saw this right after hunting down (!) a spreadsheet bug by following a chain of dependencies
01:01:49 <HackEgo> ensiscoin lazycoin vasscoin mizatifcoin intecoin poincoin lockzufcoin lyacoin clubcoin bracoin martrecoin l3250coin procoin skycoin mumontecoin dd/ddcoin eta-julietzstreactcoin charmancoin binarycoin huntedcoin
01:02:14 * boily gives a poincoin to Bike
01:02:24 <kmc> poutinecoin
01:02:45 <ion> Lazycoin leaves the mining to the entity exchanging something else for lazycoin.
01:02:50 <Bike> (relatedly, fuck excel)
01:03:36 <ion> Excel is a fine demo platform. http://youtu.be/4xKllypfn20
01:03:53 <kmc> http://nayuki.eigenstate.org/page/aes-cipher-internals-in-excel
01:04:33 <Bike> i think, if i somehow got leeway to teach a class to actual human beings, it would be about how to simplify your science homework by programming things
01:04:34 <quintopia> you didn't sendn me a birthday present!
01:04:37 <Bike> here's your reaction ordres bla bla
01:05:32 <Bike> oh my god, is this double buffering via sheets?
01:07:06 -!- tromp has quit (Ping timeout: 240 seconds).
01:07:47 <Bike> it just seems a bit embarassing that "tangent line" is a concept that needs to be worked through in college
01:08:46 <boily> I had a nice galvaude Monday night. (I know I shouldn't, cause I always have weird dreams afterwads and it wreaks my digestion, but it tastes so good...)
01:09:09 <kmc> weird dreams eh?
01:09:18 -!- tromp has joined.
01:10:45 <boily> kmc: poutine-induced dreams are interesting, to say the least. when you upgrade to a galvaude, anything goes.
01:11:03 <kmc> i'll have to try that sometime
01:11:20 <kmc> I rarely remember interesting dreams despite sleeping under the influence of all manner of psychoactive compounds
01:11:29 <kmc> but poutine might beat them all
01:11:40 <Bike> >implying poutine isn't psychoactive
01:11:40 <boily> have you ever had poutine?
01:12:07 <kmc> but it was american poutine
01:12:14 <elliott> please. don't make me want to take off +c
01:12:18 <kmc> so maybe it doesn't have the je ne sais quoi
01:12:39 <kmc> also a lot of my friends are headed to your fair city, boily
01:12:46 <kmc> for Pie Khan
01:13:00 * boily mapoles the cuttle
01:13:22 <boily> kmc: what's a pie khan?
01:13:32 <boily> (also, for you next poutine, add duck meat and green peas.)
01:13:44 <boily> (only frozen peas. canned peas are no good.)
01:13:59 <boily> ah, that thing my friend from Québec City is coming over too.
01:14:29 <kmc> it sounds fun and friendly
01:14:30 <Bike> elliott: here's where i greentext you a bunch in a futile effort to jok'e
01:14:34 <Bike> (not going to do this obviously)
01:14:45 <quintopia> a friend of man came to atlanta for pycon a couple years back, and decided to come when i was out of the country :(
01:14:46 <kmc> maybe I'll go someday, even though I don't give much of a shit about python
01:14:53 <kmc> a friend of man
01:14:57 <kmc> a title to which I aspire
01:15:34 <kmc> coppro: no, montréal
01:15:36 <ion> “Belle later confirmed the existence of the Z(4430) with a significance of 5.2 sigma on the scale that particle physicists use to describe the certainty of a result.”
01:15:39 <ion> “sigmificance” FTFY
01:15:43 <coppro> kmc: that's still in QC
01:15:55 <boily> coppro: you Ontarian :P
01:15:56 <kmc> I assumed that meant Quebec City
01:16:00 <kmc> truly I have made an ass out of u and me
01:17:17 <boily> kmc: one important French thing people learn here is the difference between «au Québec» and «à Québec».
01:17:18 <Bike> today i learned that a friend's advisor thought results were significant because they had non-overlapping SE bars. stats sure is hard.
01:17:59 <Bike> http://en.wikipedia.org/wiki/Z%284430%29 that's a lot of sigmificance
01:18:33 <kmc> boily: what is it
01:18:48 <boily> kmc: the former refers to the province, the latter to the city.
01:20:12 -!- boily has quit (Quit: DREAMING CHICKEN).
01:20:17 -!- metasepia has quit (Remote host closed the connection).
01:21:09 <Bike> http://en.wikipedia.org/wiki/Proton_decay physics is impossible
01:21:26 -!- mysanthrop has joined.
01:22:16 -!- myname has quit (Ping timeout: 265 seconds).
01:22:18 -!- olsner has quit (Ping timeout: 265 seconds).
01:22:18 -!- trn has quit (Ping timeout: 265 seconds).
01:22:19 -!- Gregor has quit (Ping timeout: 265 seconds).
01:22:54 -!- olsner has joined.
01:23:09 -!- Gregor has joined.
01:25:43 -!- jhj1 has joined.
01:28:19 <Sgeo> "All shamen are at your disposal"
01:29:42 <Bike> What are shamen?
01:32:38 <Sgeo> plural of shaman I assume. Or the lyrics sites I looked at are wrong
01:32:59 <Bike> false friends >:|
01:33:52 <Sgeo> Same song talks about stimulating your third eye
01:34:31 <kmc> that doesn't sound sexual at all
01:34:33 <ion> Eat a single raman noodle
01:35:45 <ion> men should be an alias to man -a
01:35:50 <kmc> in college we had fake majors listed on our dorm doors and douglass_ at one point had "Ramen Spectroscopy"
01:36:35 <ion> What was yours?
01:37:01 <Sgeo> Wiktionary lists shamen as a hypercorrect plural of shaman. And apparently hypercorrect is a subset of incorrect
01:37:20 <kmc> i don't remember
01:37:22 <kmc> something less funny
01:37:28 <Bike> "shaman" is from some language near siberia or mongolia
01:37:36 <Bike> nothing to do with german plurals
01:37:50 <lexande> kmc: they never gave me my "hobotopy theory" one
01:38:14 <ion> Toby the hobo
01:38:27 <Sgeo> https://www.youtube.com/watch?v=Y3WFrQzYJOY
01:38:55 <Sgeo> The only reason I care about this song is because I think it's a song I heard briefly on PulsRadio in 2006, but streamripper never manaaged to capture it
01:40:10 <kmc> that doesn't really explain anything
01:42:37 -!- MoALTz_ has quit (Ping timeout: 250 seconds).
01:43:25 <ion> kmc: Would it help if you combine that explanation with an OCD?
01:46:18 <Sgeo> I don't think I have OCD. Although I do sometimes worry what if I didn't lock the door. And when I was a kid, I once recorded each die roll in a game of Monopoly because I wanted it to be reproducible (not in those worse). Randomness freaked me out
01:47:03 <Sgeo> Before then, played Monopoly on the computer with friends, but when most of my friends left, another friend and I played out the game a bit more and caused someone who wasn't there to go bankrupt
01:51:05 -!- augur has joined.
01:51:49 -!- tromp has quit (Ping timeout: 276 seconds).
01:52:17 -!- tromp has joined.
01:52:22 <Bike> http://support.microsoft.com/kb/180162 aaaaaaaaaaah
01:52:48 -!- augur_ has joined.
01:53:06 -!- augur has quit (Read error: Connection reset by peer).
01:55:27 -!- SpaceWizard has quit (Quit: Leaving).
01:55:50 -!- SpaceWizard has joined.
01:56:41 <kmc> the 1904 date system is a plot by the pope
02:12:36 -!- Slereah_ has joined.
02:13:54 -!- Slereah has quit (Ping timeout: 240 seconds).
02:33:42 -!- SpaceWizard has quit (Ping timeout: 240 seconds).
03:00:05 <Sgeo> http://article.gmane.org/gmane.os.openbsd.misc/211963
03:00:21 -!- Slereah has joined.
03:00:26 <Sgeo> Had this not occurred, I assume heartbleed would instead be an easy DoS attack?
03:00:40 <Sgeo> Oh, probably just on OpenBSD?
03:02:02 -!- Sorella has quit (Quit: It is tiem!).
03:02:06 -!- Slereah_ has quit (Ping timeout: 240 seconds).
03:02:31 <pikhq> It also would've been easily noticed.
03:06:42 <Sgeo> "malloc guarding (world is not ready for this)"
03:32:43 <Sgeo> "Let me reiterate - everybody who was ever taught anything about that green padlock - grandmothers, bosses, school kids, web devs, everyone - now thinks that it means something it doesn’t, and won’t mean what they think again until all those server-babies are replaced."
03:33:05 <Sgeo> Any chance of browser vendors agreeing to not show the security lock for sites affected by Heartbleed?
03:33:18 <Sgeo> Although, how to detect site that was vulnerable, repaired bug, didn't yet get new certificates
03:33:35 <Jafet> That would require shipping an exploit for heartbleed
03:33:44 <Jafet> That would also require giving a shit
03:33:47 <Bike> a tree planted upside-down
03:34:24 <Jafet> Bosses and web devs are a lost cause anyway
03:36:32 -!- doesthiswork has joined.
03:38:31 <Bike> and do you know where your cause is?
03:42:25 <Sgeo> https://bugzilla.mozilla.org/show_bug.cgi?id=994033
03:49:28 -!- nooodl has quit (Quit: Ik ga weg).
03:50:25 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39276&oldid=39275 * Doesthiswork * (-9) I couldn't get the Y combinator to terminate so I'm using a different way to get a fixed point
03:52:11 <HackEgo> [wiki] [[Smartboxes]] M http://esolangs.org/w/index.php?diff=39277&oldid=39276 * Doesthiswork * (+1) left off a bracket
03:55:44 -!- Slereah_ has joined.
03:56:20 -!- Slereah has quit (Ping timeout: 252 seconds).
04:05:10 <Sgeo> I'm seriously tempted to start using LastPass
04:10:34 -!- ^v has quit (Read error: Connection reset by peer).
04:11:00 -!- ^v has joined.
04:34:04 <Sgeo> I don't trust myself to make backups
04:41:18 <HackEgo> [wiki] [[Smartboxes]] M http://esolangs.org/w/index.php?diff=39278&oldid=39277 * Doesthiswork * (+3) added missing :-
04:54:27 <quintopia> i'm mostly tempted to write my own custom deterministic password generator
04:55:50 <kmc> base64(HMAC-SHA256(master key, website domain name))[:16]
04:56:00 <kmc> should do nicely
04:56:06 <Jafet> alias pw='echo -n "> " && stty -echo && (read pw && echo -n "$pw" | sha256sum | head -c 20 && echo; stty echo)'
04:56:13 <quintopia> kmc: i don't want to have to depend on a master key
04:56:35 <Jafet> What do you want to depend on, then
04:56:36 <Sgeo> I used to use hashapass
04:56:45 <Sgeo> Found I couldn't remember the names I gave each site
04:57:07 <kmc> if only there were some hierarchical name structure associated with websites
04:57:12 <Jafet> Why don't you use the name the site gives itself
04:57:16 <quintopia> Jafet: gestures which are different for each domain
04:57:20 <Jafet> Most sites have that
04:57:55 <Jafet> How are you going to come up with the gestures
04:58:00 <Sgeo> I also have no list of every website that I have made a password for
04:58:11 <Sgeo> This has been problematic before and it's problematic now
04:58:30 <kmc> my gesture for every site would be a big ol' middle finger
04:58:35 <quintopia> Jafet: generate a custom image automatically and deterministically, and use my innate sense of location and visual memory to recall the gesture associated with it
04:59:11 <Jafet> My sense of location is pretty exnate, but ok
04:59:54 <Jafet> Wait, passgestures, is this one of those "phone"isms
05:01:05 <fizzie> I'm a bit surprised nobody has asked for TLS to happen for esolangs.org.
05:01:06 <Jafet> Speak friend and slide to unlock
05:01:48 <quintopia> Jafet: that's unusual. most animal memories are location-based
05:01:50 <Sgeo> Does LastPass not work well for nonwebsite passwords?
05:02:01 <quintopia> "i recognize this place. the last time i was here i ...."
05:07:31 <Jafet> echo stty intr ^M >> ~/.bashrc
05:09:12 <shachaf> i'm going to need to do the pick-a-distribution thing again soon
05:09:51 <Jafet> For some reason, I can bypass ^J with C-^J.
05:09:52 <Sgeo> What's wrong with nixos?
05:10:48 <kmc> running «stty intr ^C < /dev/pts/1» in another terminal is enough to let me run one command, but then it resets
05:10:58 <kmc> perhaps bash is saving and restoring the termios stuff
05:11:26 <newsham> perhaps its applying it to the wrong pty?
05:11:49 <shachaf> Then why would it be enough for one command?
05:12:04 <newsham> i dunno.. i dont understand computers
05:12:07 <Sgeo> You should use Bedrock Linux, and run a banking website from it
05:13:11 <shachaf> i run enough websites for a lifetime
05:15:32 <newsham> after a while they run you
05:20:52 <kmc> echo 'echo "sleep 0.1" >> ~/.bashrc' >> ~/.bashrc
05:21:14 <Jafet> Who came up with that originally
05:22:09 <Bike> heh, that's good.
05:22:10 <shachaf> it has been around for at least 20 years
05:22:23 <newsham> so each time you log in it gets slower?
05:23:07 <kmc> microsoft gotta get paid
05:24:05 <shachaf> http://www.dorje.com/netstuff/folklore/the.tricks
05:27:06 <shachaf> 20 years ago was an odd time
05:27:08 -!- not^v has joined.
05:27:10 <newsham> i once wrote a program which would recurse into all subdirs and in each subdir it would list files that werent dirs and randomly rename them to each other
05:27:21 <newsham> so that you still had all the same files but with different filenames
05:27:29 <newsham> (err, dirs were renamed too, oops)
05:28:06 <shachaf> did everyone have signatures on their messages back then
05:29:19 <newsham> a time of .plans and .signatures
05:30:24 -!- ^v has quit (Ping timeout: 252 seconds).
05:32:18 <shachaf> https://groups.google.com/d/msg/comp.sources.wanted/3o-Ej2pyvQ8/eSwcgvJWDT4J
05:33:24 <Jafet> It's a bit disturbing that most of those tricks are still applicable.
05:34:24 <newsham> jafet: but who uses multi-user systems these days?
05:35:11 <newsham> wow, schachaf, thats a really old post
05:36:42 <newsham> i wondr if that was my first usenet post evar
05:37:25 <shachaf> https://groups.google.com/d/msg/comp.os.minix/pHRCC5JKCV8/4irAi_sYsZwJ was earlier
05:37:28 <shachaf> "(please respond in mail so as not to waste bandwidth)"
05:37:43 <shachaf> i'll stop looking for old newshamposts now
05:38:20 <newsham> thats a year later, shachaf
05:38:24 <olsner> oh, right, it's newsgroups, not a mailing list
05:39:36 <newsham> i think i got my unix account in fall 1989. i didnt find usenet right away
05:39:45 <shachaf> ok, then https://groups.google.com/d/msg/alt.fractals/xLXAGFDRcwY/L4FJBhoEi3QJ
05:40:14 <shachaf> all these things are from before i was born
05:43:04 <Bike> I got hit by a letter.
05:53:09 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:54:40 -!- doesthiswork has quit (Quit: Page closed).
05:57:53 <newsham> "A co-worker has his plan file end with
05:57:54 <newsham> [2] - Done /bin/rm -rf ~ &
05:57:54 <newsham> which tends to induce heart-attacks in the unwary...
06:02:56 -!- password2 has joined.
06:17:51 <fizzie> I think I had something esolangy in my .plan at the university shell servers.
06:17:57 <fizzie> Probably a Befunge program.
06:30:11 -!- MoALTz has joined.
06:35:13 -!- MoALTz has quit (Ping timeout: 276 seconds).
06:36:20 -!- MoALTz has joined.
06:38:43 -!- MoALTz has quit (Max SendQ exceeded).
06:39:51 -!- MoALTz has joined.
06:50:00 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:57:08 -!- atriq has joined.
06:57:39 <atriq> I wonder if I should learn Forth
07:11:21 -!- xpte has quit (Quit: Connection closed for inactivity).
07:12:00 -!- Bike has quit (Quit: gets hit by an ice-cream truck).
07:16:43 -!- MindlessDrone has joined.
07:25:51 -!- Sgeo_ has joined.
07:29:06 -!- Sgeo has quit (Ping timeout: 240 seconds).
08:12:38 -!- tromp has quit (Read error: Connection reset by peer).
08:13:30 -!- tromp has joined.
08:13:41 -!- mysanthrop has changed nick to myname.
08:14:54 <fizzie> If there can be a payer paying a payee, and an employer employing an employee, and so on, why is the thing what a mentor does to a mentee called "mentoring" and not "menting"?
08:16:07 <fizzie> OED: "mentee, n. Etymology: < ment- (in mentor n.) + -ee suffix1. orig. U.S. A person who has a mentor; the person guided or tutored by a mentor."
08:16:57 <fizzie> One of the downstairs info screens was promoting some university mentoring program with a logo that said "mentor", "mentoring", "mentee" in it.
08:17:17 <Jafet> Hmm, I suppose you could claim "ment".
08:35:09 -!- Patashu has joined.
09:07:18 -!- atriq has quit (Ping timeout: 240 seconds).
09:09:42 -!- password2 has quit (Read error: Connection reset by peer).
09:13:46 -!- oerjan has joined.
09:24:49 -!- MindlessDrone has quit (Quit: MindlessDrone).
09:26:50 -!- MindlessDrone has joined.
09:31:08 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
09:32:21 -!- MoALTz has quit (Ping timeout: 250 seconds).
09:44:46 -!- MindlessDrone has joined.
10:00:51 -!- yorick has joined.
10:02:38 <fizzie> >> mean(cleancep, 2).'
10:02:38 <fizzie> -Inf NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
10:02:42 <fizzie> Best mean vector ever.
10:03:50 <oerjan> it's so mean it just says NaN NaN NaN at you
10:16:07 -!- boily has joined.
10:20:59 <ion> fizzie: nice
10:29:40 -!- SpaceWizard has joined.
10:54:01 -!- oerjan has quit (Quit: Ribbit).
11:06:40 -!- boily has quit (Quit: Chasing Norwegian frogs...).
11:19:15 -!- nucular has joined.
11:19:16 -!- nucular has quit (Changing host).
11:19:16 -!- nucular has joined.
11:44:16 -!- SpaceWizard has quit (Ping timeout: 245 seconds).
11:54:11 -!- Sorella has joined.
11:54:31 -!- oerjan has joined.
11:56:45 -!- idris-ircslave has quit (Quit: Terminated).
11:57:01 -!- idris-ircslave has joined.
12:05:13 -!- nooodl has joined.
12:21:04 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
12:21:26 -!- tromp has quit (Remote host closed the connection).
12:22:02 -!- tromp has joined.
12:26:11 -!- tromp has quit (Ping timeout: 252 seconds).
12:41:53 -!- SpaceWizard has joined.
12:53:33 -!- Sgeo_ has quit (Read error: Connection reset by peer).
13:03:45 -!- MoALTz has joined.
13:08:26 -!- MoALTz_ has joined.
13:11:17 -!- MoALTz has quit (Ping timeout: 252 seconds).
13:15:26 -!- tromp__ has quit.
13:31:23 -!- SpaceWizard has quit (Quit: Leaving).
13:31:59 -!- SpaceWizard has joined.
13:33:50 -!- Patashu has quit (Ping timeout: 252 seconds).
14:32:58 -!- ^v has joined.
14:55:46 -!- oerjan has quit (Quit: Etc.).
15:04:56 -!- Bike has joined.
15:18:08 -!- augur has joined.
15:18:16 -!- augur_ has quit (Read error: Connection reset by peer).
15:22:52 -!- tromp has joined.
15:27:06 -!- tromp has quit (Ping timeout: 240 seconds).
15:34:18 -!- augur has quit (Ping timeout: 240 seconds).
15:35:04 -!- augur has joined.
15:40:22 -!- SpaceWizard has quit (Ping timeout: 252 seconds).
15:50:13 -!- doesthiswork has joined.
15:58:14 -!- doesthiswork has quit (Quit: Page closed).
16:01:28 -!- password2 has joined.
16:11:31 -!- xpte has joined.
16:27:44 -!- nisstyre has joined.
16:40:58 -!- doesthiswork has joined.
16:50:47 -!- tromp has joined.
16:56:55 -!- SpaceWizard has joined.
17:21:18 -!- SpaceWizard has quit (Ping timeout: 240 seconds).
17:30:33 -!- SpaceWizard has joined.
17:57:24 -!- nooodl has quit (Quit: Ik ga weg).
17:59:34 -!- nooodl has joined.
18:00:00 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
18:08:30 -!- password2 has quit (Ping timeout: 240 seconds).
18:08:37 <HackEgo> [wiki] [[A programming language is an artificial language designed to communicate instructions to a machine, particularly a computer.]] http://esolangs.org/w/index.php?diff=39279&oldid=39269 * 38.96.153.66 * (+2) /* Overview */ formatting
18:08:52 -!- nooodl_ has joined.
18:09:04 -!- nooodl_ has left.
18:09:11 <HackEgo> [wiki] [[A programming language is an artificial language designed to communicate instructions to a machine, particularly a computer.]] M http://esolangs.org/w/index.php?diff=39280&oldid=39279 * Rottytooth * (+2) formatting
18:10:27 <HackEgo> [wiki] [[A programming language is an artificial language designed to communicate instructions to a machine, particularly a computer.]] http://esolangs.org/w/index.php?diff=39281&oldid=39280 * Rottytooth * (+44) /* Concept */
18:13:24 <fizzie> For the record, the [-Inf NaN NaN ...] mean was from having some hard zeros. (Which got turned into -Inf by a log compression step, and NaNs by a DCT.)
18:14:42 -!- oklopol has quit (Ping timeout: 240 seconds).
18:17:12 -!- MoALTz_ has quit (Quit: Leaving).
18:24:44 <ion> fizzie: Try applying some heat, they might get softer.
18:25:57 <fizzie> I applied an arbitrary epsilon. It wasn't for anything serious.
18:26:32 -!- password2 has joined.
18:28:20 -!- conehead has joined.
18:28:51 -!- SpaceWizard has quit (Ping timeout: 245 seconds).
18:37:39 -!- ^v has quit (Read error: Connection reset by peer).
18:38:01 -!- ^v has joined.
18:40:13 <HackEgo> [wiki] [[Esolang:Wiki dumps]] http://esolangs.org/w/index.php?diff=39282&oldid=30687 * Fizzie * (+74) Time zones are the bane of all civilized folk. (+update numbers)
18:54:25 <kmc> the ECMAScript standards committee is meeting just down the hall from me
18:54:33 <kmc> clearly I should go in and troll them about adding dependent types or something
18:56:46 <fizzie> Someone was thinking of doing some kind of Rust promotion lecture at the university.
18:57:06 <kmc> i,i integer promotion lecture
19:00:37 <fizzie> I haven't been following the ECMAScript standardization effort at all, except that I remember I've been surprised several times to find out that those Mozilla additions (generators, array comprehensions, let expressions, expression closures) still aren't standard and/or widely supported.
19:01:01 <fizzie> I guess it all has something to do with this Harmony thing I've heard of.
19:01:56 -!- DiNoALaCorrupcio has joined.
19:08:53 -!- ChanServ has set channel mode: +o elliott.
19:08:58 -!- elliott has kicked DiNoALaCorrupcio no thanks.
19:11:03 -!- elliott has set channel mode: +b *!*@denuncia.anonima.empleosonora.gob.mx.
19:11:05 -!- elliott has set channel mode: -o elliott.
19:21:37 <doesthiswork> kmc: I double dare you to troll the ecmascript standards commity
19:22:30 <Bike> "hey peeps, how's ur assembly going"
19:29:13 <ion> kmc: You should go in and troll them about the things mentioned in the wat talk.
19:29:34 -!- conehead has quit (Quit: Computer has gone to sleep).
19:31:13 -!- MindlessDrone has quit (Ping timeout: 250 seconds).
19:31:45 <quintopia> i haven't seen that talk in a long time
19:31:54 -!- variable has quit (Ping timeout: 240 seconds).
19:31:58 -!- scoff has quit (Ping timeout: 240 seconds).
19:33:23 <ion> https://pbs.twimg.com/media/Bk3uviICYAAvnWo.jpg:large
19:33:39 <Slereah_> That is what the future will be like
19:34:13 <int-e> Bike: you are aware of http://asmjs.org/ right?
19:34:47 <Bike> doesn't kmc work with it
19:35:18 -!- scoff has joined.
19:36:33 <ion> slereah: http://www.windowsphonefr.com/wp-content/uploads/2012/12/micro-sd.jpg
19:37:11 -!- TheMind has joined.
19:38:17 -!- tertu has joined.
19:38:57 <fizzie> ion: Next, find a photo that's analogous to that tiny tiny keyboard on the watch.
19:40:04 <Slereah_> Also find a tiny console-based computer
19:40:28 <Slereah_> I don't think the iPhone would sell as well if it was all command line
19:40:41 -!- TheMind has quit (Read error: Connection reset by peer).
19:40:47 <ion> http://www.buysku.com/wholesale/q8-dual-sim-quad-band-1-5-quot-touch-screen-watch-cell-phone-with-keyboard-camera-bluetooth-fm-mp3-mp4-white.html
19:41:01 <b_jonas> ok, so I have a crazy idea about an esoteric virtual machine
19:42:08 <b_jonas> suppose you have a cpu with very few registers, say only an instruction pointer, an accumulator, and an index/extra register.
19:42:24 <b_jonas> imagine it has a reasonable small instruction set, but there's one crippling feature.
19:42:27 <Slereah_> Imagine a dude talking to SIRI in console commands
19:43:43 <Bike> so far this is 6502?
19:44:01 <fizzie> Bike: I think it's intentional, and the twist is yet to come.
19:44:28 <b_jonas> the feature is that interrupts are handled in a crazy way: when an interrupt arrives, the cpu overwrites each of the few registers is overwritten by interrupt-related information without saving it first. the ip is set to the interrupt handler address, the accumulator to the interrupt number, and the index register to some port input from the hardware.
19:44:47 <b_jonas> there's some limit for how quickly you can get interrupts or else you would have to lose some.
19:44:52 <b_jonas> and you can't disable interrupts.
19:45:04 <b_jonas> Bike: like 6502 but with wider word size
19:45:28 <b_jonas> so you have to do all normal computations in an idempotent way because an interrupt can destroy your registers any time
19:45:53 <Bike> well, the isa can't be 6502, then
19:46:16 <b_jonas> after the interrupt, the os will resume your program at some last saved location, but since then your program might have done some steps
19:46:23 <b_jonas> so you can't do destructive computations in place
19:46:30 <b_jonas> because then they might run twice
19:46:51 <b_jonas> but you can do non-in-place operations, then in the worst case you recompute the part since last time you saved the status to memory
19:48:05 <fizzie> It sounds likely that you'd end up with some translator from a non-crazy thing to the crazy thing, with some amount of overhead, and then you'd do all the work in the non-crazy thing.
19:48:29 <b_jonas> fizzie: possible, if you don't mind the overhead
19:48:42 <b_jonas> but for the inner loops you might want to code for the crazy thing directly
19:50:44 -!- impomatic has joined.
19:50:53 <b_jonas> yeah, it's not a really good idea
20:01:37 -!- Tritonio has joined.
20:03:47 <kmc> i don't use asm.js for anything at the moment
20:07:45 -!- tertu has quit (Disconnected by services).
20:07:46 -!- ter2 has joined.
20:08:15 <kmc> but it's another Mozilla Research project
20:08:28 <kmc> somebody needs to get the .js TLD
20:10:32 -!- conehead has joined.
20:11:32 <kmc> fizzie: you can write such translators for most esolangs, though
20:12:00 <fizzie> Yes, I was commenting from the viewpoint of some hypothetical poor soul hired to port a game on the hypothetical computer, or something.
20:12:40 <kmc> I've never designed a proper esolang
20:12:45 <kmc> maybe I should try my hand at an eso-ISA instead
20:13:17 <kmc> though a lot of esolangs feel like machine code
20:13:42 <kmc> are there real ISAs with Brainfuck-style structured control instructions?
20:14:04 <kmc> that is, you have "loop begin" and "loop end" instructions and the CPU will scan forward/backward in memory to find a matching one
20:15:13 <fizzie> Regarding the .js TLD, I think you'd need to beat up someone at ICANN for it.
20:15:36 <fizzie> Because I think they reserved all 2-character ASCII strings for "possible future ccTLD delegations".
20:15:36 <kmc> x86 has the LOOP instruction but it still has an explicit jump target
20:16:11 <kmc> fizzie: or I need to create an internationally breakaway state whose plausible abbreviation is '.js'
20:16:21 <kmc> internationally recognized*
20:18:45 <fizzie> kmc: ISTR the TMS320C54x (or some other member of TMS320) has a "repeat block" instruction, but you give the block size as an immediate argument to the instruction.
20:19:43 -!- password2 has quit (Ping timeout: 240 seconds).
20:19:57 <fizzie> (Then the instruction initializes the "repeat block" register to contain the size and the end address, sets the "repeat counter" register, and the hardware arranges for the repetition to happen.)
20:19:59 <kmc> now I'm thinking about a weird mash-up of x86's rep and Thumb2's i[te]{1,4} instructions
20:20:32 <kmc> ooh, that TMS320C54x thing seems pretty close
20:20:36 <kmc> I don't know much about DSP architectures
20:22:54 -!- variable has joined.
20:24:06 <kmc> I also wonder if a "conditionalize any instruction" prefix was ever considered for x86
20:24:08 <fizzie> Oh, if you want to be more exact about it, "RPTB pmad" sets RSA and REA (repeat start/end address) to PC+2 and pmad, respectively, and turns the BRAF (block-repeat active flag) on; you're supposed to have manually set the BRC (block-repeat counter) beforehand.
20:24:26 <kmc> BRAF is a great name for a register
20:24:46 <kmc> and pmad is a great name for an operand
20:24:48 <fizzie> Sadly, it's just a name of a bit in ST1.
20:24:58 <kmc> I take it you've programmed for the TMS320C54x?
20:24:58 <fizzie> But there's a lot of "pmad"s in the manual.
20:25:05 <kmc> is there also "umad"
20:25:45 <fizzie> There's just dmad, extpmad and pmad.
20:26:07 <fizzie> And I've done a little bit for it; we had a three-architecture DSP course with randomly assigned architectures for the groupwork.
20:26:53 <kmc> what did you build?
20:27:49 <fizzie> There was a TI TMS320C5416 devboard (what we had), a Motorola DSP56k thing of something or another, and a Sharc ADSP which was I think some sort of a musician DSP effect box with a twiddleable knob and all.
20:28:05 <fizzie> We built an echo effect thingie. Just a second, I have a photo I've pasted on-channel before.
20:29:22 <kmc> a button to touch, a dial to turn, a key to hold
20:30:23 <fizzie> Our devboard just had four dip switches and four leds in terms of UI, so we had to figure out alternative controls.
20:30:32 <fizzie> https://dl.dropboxusercontent.com/u/113389132/Misc/20140410-spank.jpg
20:31:07 <fizzie> (We had to do a three-slide presentation at the end of the course, that was one of the slides.)
20:32:21 <fizzie> Also it's called "spank" because the name of the course was "SPÄNK", short for "signaaliprosessorit ja äänenkäsittely", "[digital] signal processors and sound processing".
20:33:39 <kmc> SPÄNK sounds like something from IKEA's line of sex toys
20:35:11 <fizzie> If I recall correctly, the top-left thing was a Perl + Tk prototype for figuring out the algorithm and parameters, the middle picture shows the DSP devboard and the TI-86 driven slider control interface, and top-right is a photo of the oscilloscope we used when we spent two nights debugging the DSP/TI-86 link that turned out to be a broken cable I had salvaged from a discarded set of speakers ...
20:35:17 <fizzie> ... that, when I finally came to think of it, were in fact discarded because no sound came out of them.
20:35:44 <ion> fizzie: Do you know of a no-horribly-expensive DSP platform for a hobbyist? Perhaps with an ADAT interface or some other way to add an AD/DA interface (possibly with preamps) with a number of channels.
20:37:52 <fizzie> (Also I couldn't quite manage to convince the (really quite flexible) C5416 "McBSP" serial port to give me the TI-86 stuff over DMA, so we had to resort to software polling.)
20:38:13 <fizzie> ion: One of the boxes we had on the course was the http://www.chameleon.synth.net/english/index.shtml but I think that must be pretty outdated by now?
20:38:50 <fizzie> "Only a few units remain, --" I guess they're not really selling it any more either.
20:38:52 <ion> Thanks, i’ll take a look.
20:39:42 <fizzie> It seemed like quite a nice thing for that sort of thing. Though I don't know if it was ever what you'd call affordable.
20:41:02 <fizzie> There are reasonably cheap devkits similar to the C5416 one we had, but their I/O capabilities might be somewhat lacking, if you want multiple AD/DA channels.
20:41:54 <ion> 8 inputs would be nice.
20:44:06 <fizzie> They're things like http://www.ti.com/tool/tmdx5502ezdsp for $89, but at least that particular one just has two channels in/out when it comes to audio codecs.
20:44:15 <fizzie> Some of them have add-on modules you can stick on, though.
20:48:24 -!- SpaceWizard has joined.
20:50:03 <fizzie> A friend wrote the Z80 code for the TI-86 side.
20:50:25 <fizzie> (I wrote the DSP side of the communications stuff.)
20:52:11 <fizzie> Actually, I'm a bit surprised if there isn't a Kickstarter for something like that Soundart Chameleon around.
20:55:41 <ion> fizzie: Thanks for the pointer, i’ll research them add-on modules.
20:56:09 <fizzie> From a quick look, it seemed like the "DSK" boards that accepted them rather quickly went to several hundreds of dollars.
20:57:25 <ion> Ok, a bit too expensive then. Thanks anyway.
20:57:39 <fizzie> As one final note, Analog Devices' SigmaDSP evaluation boards are a bit more fully featured when it comes to built-in analog inputs/outputs -- http://www.analog.com/en/processors-dsp/sigmadsp/products/sigmadsp_evaluation_boards/fca.html -- but they're not exactly cheap either.
21:02:43 -!- oerjan has joined.
21:05:46 <fizzie> Fun fact: there's a reasonably "general-purpose" TI TMS320C64x (the aspires-to-VLIW-but-not-quite sibling to the C54x family) DSP core in my N900, and I keep thinking of trying to hack together something using it, but so far haven't managed to.
21:06:00 <fizzie> I know the stock camera application encodes JPGs on it.
21:07:34 <kmc> can you easily program it?
21:08:07 <fizzie> Not "easily", but people have done it up to some degree. The communications to/from it are somewhat torturous, AIUI.
21:10:12 <fizzie> It was a relatively common OMAP3 feature, I believe; I don't know if it's any easier/harder to access on the myriad other OMAP3 devices. (From OMAP4 onwards, I think TI gave up on including a generic DSP chip like that, and just bundled one of their more video-specific things.)
21:13:11 <fizzie> They're still making those "DaVinci" family of SoCs that bundle a C6x DSP with an ARM core, and people are still using them, I believe, in things like media player boxes and such.
21:13:52 -!- Patashu has joined.
21:15:21 <fizzie> There seems to be at least hacked-together port of the (Mozilla-funded!) C64x+ implementation of Theora to the N900.
21:15:30 -!- Patashu[Zzz] has joined.
21:15:30 -!- Patashu has quit (Disconnected by services).
21:17:10 <fizzie> http://schleef.org/blog/2009/11/11/theora-on-ti-c64x-dsp-and-omap3/
21:17:43 <fizzie> And then -> http://blog.mjg.im/2010/04/16/theora-on-n900.html to N900.
21:17:55 <fizzie> Probably not much happening there these days.
21:19:35 -!- nucular has quit (Quit: Excess Food).
21:19:43 <ion> Someone should write a C64 emulator on C64x+
21:23:59 <ion> “Videotape evidence can be overruled by the testimony and after-the-fact interpretation of a police officer, the Indiana Supreme Court ruled last week.” http://thenewspaper.com/news/43/4373.asp
21:24:19 -!- Patashu[Zzz] has quit (Ping timeout: 250 seconds).
21:42:47 -!- ^v has quit (Ping timeout: 252 seconds).
21:45:43 -!- nisstyre has joined.
22:03:34 -!- vravn has quit (Ping timeout: 240 seconds).
22:04:58 -!- shachaf_ has joined.
22:05:09 -!- shachaf_ has quit (Changing host).
22:05:09 -!- shachaf_ has joined.
22:05:16 -!- shachaf has quit (Disconnected by services).
22:05:19 -!- shachaf_ has changed nick to shachaf.
22:05:31 <shachaf> http://git-man-page-generator.lokaltog.net/
22:07:36 -!- vravn has joined.
22:09:39 <doesthiswork> the spitbol manual says that it has esoteric features
22:12:57 <oerjan> i liked the --increase-blast-area option i got
22:22:51 -!- boily has joined.
22:31:05 <quintopia> it means i can sort of chat a bit until 7:40
22:31:39 -!- metasepia has joined.
22:31:39 <boily> DCSS!!!!!1!!1!11!!!one!!
22:33:12 <boily> dungeon crawl stone soup. and you're lucky, 0.14 is just out!
22:33:38 <boily> (okay. I *may* be a little bit addicted to that game. only slightly. a smidge.)
22:33:55 <boily> but then, I also have spent many hours on minecraft...
22:34:13 <boily> I haven't brogued yet, but it seems very interesting, what with all those colours and shiny stuff.
22:34:40 <quintopia> it is more like a roguelike than any platformer out there
22:35:03 <doesthiswork> the colors are there to make it feel as if you are really walking thought the cave
22:35:15 <boily> spelunky is very roguelike-y. procedural, stupid deaths, bonus impossible stuff...
22:36:19 <quintopia> i want to play spelunky crossed with DF
22:36:39 <boily> holy fungot with the hardcore stuff, batman!
22:36:39 <fungot> boily: it's a logic system in scheme, lists are a pair of identifiers except by accident.
22:36:49 <boily> fungot: no, quintopia is not logical.
22:36:49 <fungot> boily: vim isn't exactly snappy on slower systems either.
22:36:52 <doesthiswork> wouldn't a functional game be in a better state than a procedural one?
22:37:35 <nooodl> hey boily this might interest you,
22:37:49 <quintopia> boily: it would be the hardest game ever written, but "fun"
22:37:52 <nooodl> and `telnet termcast.org`
22:37:54 <doesthiswork> how would you cross a platformer like spelunky with a strategy game like df?
22:38:20 <boily> nooodl: I hate you, tempting me with awesome time-sucking things like that.
22:41:17 <quintopia> doesthiswork: how do you cross an adventure game like Alice with an RTS like C&C? (The answer is Brutal Legend)
22:41:47 <quintopia> in other words: i haven't thought about it enough to know, but i'll know it when i see it.
22:44:05 <quintopia> anyway, i specifically mean real time games
22:50:54 <quintopia> procedural generation of worlds, including their history, culture, climates, biomes, etc. independent agents with their own goals, able to modify the world in physically realistic ways.
22:53:39 -!- idris-ircslave has quit (Quit: Terminated).
22:54:36 -!- idris-ircslave has joined.
22:56:40 -!- nooodl_ has joined.
22:57:12 -!- nooodl has quit (Disconnected by services).
22:57:14 -!- nooodl_ has changed nick to nooodl.
22:58:07 -!- Tritonio has quit (Ping timeout: 258 seconds).
23:05:36 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
23:09:14 -!- doesthiswork has quit (Quit: Page closed).
23:10:15 -!- yorick has quit (Read error: Connection reset by peer).
23:20:39 -!- Sprocklem has joined.
23:41:45 -!- tromp_ has joined.
23:43:09 -!- Sprocklem has quit (Quit: leaving).
23:43:43 -!- Sprocklem has joined.
23:43:46 -!- Sprocklem has quit (Changing host).
23:43:47 -!- Sprocklem has joined.
23:54:58 -!- ^v has joined.
00:07:30 -!- Sprocklem has quit (Quit: leaving).
00:07:48 -!- prooftechnique has joined.
00:07:56 -!- prooftechnique has quit (Client Quit).
00:08:03 -!- Sprocklem has joined.
00:11:14 -!- vravn has quit (Ping timeout: 240 seconds).
00:14:36 -!- vravn has joined.
00:18:17 -!- doesthiswork has joined.
00:24:20 -!- ter2 has quit (Ping timeout: 252 seconds).
00:24:34 -!- vravn has quit (Ping timeout: 240 seconds).
00:25:22 -!- oerjan has quit (Quit: timeout: 8-9 hours).
00:28:37 -!- vravn has joined.
00:49:52 -!- ter2 has joined.
00:52:37 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
00:52:56 -!- ^v has joined.
01:07:54 -!- ter2 has quit (Ping timeout: 240 seconds).
01:13:43 -!- boily has quit (Quit: GARDEN CHICKEN).
01:13:50 -!- metasepia has quit (Remote host closed the connection).
01:20:07 -!- Sgeo has joined.
01:27:36 <^v> why do you think
01:32:49 <coppro> this week in "dumb questions";
01:35:38 <Bike> oh, is that why it is.
01:59:59 <coppro> I was going to suggest that actually
02:08:34 <doesthiswork> oh there you are <^v> I was wondering where you had gone when I only saw ^v in the channel
02:14:01 <doesthiswork> wat isn't THAT esoteric but it's still interesting https://github.com/manuel/wat-js
02:14:28 <lexande> doesthiswork: i don't see <^v>, only < ^v>
02:15:31 <^v> nobody else has a space?
02:18:45 -!- conehead has quit (Quit: Computer has gone to sleep).
02:30:54 -!- vravn has quit (Ping timeout: 240 seconds).
02:34:38 -!- vravn has joined.
02:35:12 -!- nooodl has quit (Quit: Leaving).
02:38:48 -!- nisstyre has joined.
02:40:57 <Bike> 19:40 < Barcode> i ended up spitting a wad of half-dry blood into the garbage like 15 minutes after i figured i stopped my bleed and my coworker just. stopped typing for a few seconds
02:41:01 <Bike> well, whatever.
02:45:38 <Sgeo> I think the idea of just passing around IOs and functions to IOs is starting to bother me
02:46:09 <Sgeo> What does an (a -> IO ()) do when you pass it an a? Whatever the heck it wants to! What do you mean, this one is supposed to trigger a bunch of event handlers?
02:48:29 <Bike> what does an a -> Num do when you pass it an a who knows
02:57:07 -!- SpaceWizard has quit (Ping timeout: 250 seconds).
03:07:36 <kmc> Sgeo: it doesn't do anything
03:08:05 <kmc> but as for the IO actions themselves, yes, the lack of type information about effects can be problematic
03:11:42 <elliott> you want event handlers to be able to do arbitrary IO anyway, generally
03:11:46 <elliott> so this is not a very good example
03:24:36 <Sgeo> In general, would using reactive-banana just for its AddHandler be a bad idea?
03:28:47 <kmc> there's always money in the banana stand
03:31:32 <Sgeo> So yeah... I'm pretty certain I'm going to bite the LastPass bullet soon
03:35:03 <Bike> "OpenSSL uses a custom freelist for connection buffers because long ago and far away, malloc was slow." so i think i'd like to declare a blood oath against C
03:35:52 <kmc> pfft C is easy, just don't make any mistakes ever
03:36:02 <kmc> you shouldn't be programming if you're the sort of person who would ever make a mistake
03:38:48 <Bike> also you have to hate the idea of standard libraries?
03:39:13 <Sgeo> What sort of vulnerabilities would crypto in Haskell be particularly likely to be vulnerable to, compared to liklihood of vulnerabilties of reimplementation in more conventional languages?
03:39:21 <Sgeo> Side-channel attacks based on timing?
03:40:33 -!- copumpkin has joined.
03:46:28 <pikhq> The amusing thing about this is, most of these bugs aren't entirely from C being bad, but from the coders being *profoundly moronic and awful*. With C just making the consequences of it worse.
03:48:48 <Sgeo> http://np.reddit.com/r/Bitcoin/comments/22p50z/sub400_btc_here_we_go/cgp0gwy
03:49:20 <Sgeo> Not commenting on the rest of it, but that $500/coin to mine figure, would the cost go down with fewer miners competing?
03:50:29 <kmc> others in the thread point this out
03:51:26 <kmc> the cost per GH/s won't go down, but the revenue per GH/s will go up
03:51:47 <kmc> or should that just be cost per GH? anyway
03:53:07 <HackEgo> toadcoin boudcoin falcoin sansiscoin libedtcoin whostepchcoin acfcoin consurfcoin zustcoin patncoin dnagecoin adnestcoin ntcmcoin eloopcoin attoacoin niedcoin revelacoin smyrmatinucoin golcoin devcoin
03:53:30 <Sgeo> So much for being unregulatable. One government's actions is enough to drastically hurt the price
03:53:52 <kmc> which actions are those
03:54:26 <Sgeo> http://blogs.wsj.com/moneybeat/2014/04/10/bitcoin-prices-down-10-after-chinese-banks-cut-off-local-exchanges/
03:54:34 <kmc> I thought that happened months ago
03:54:38 <kmc> I guess something new happened
03:54:42 -!- Sorella has quit (Quit: It is tiem!).
03:55:09 <lexande> it was always super volatile
03:55:25 <Sgeo> "To be fair, if 1 BTC equaled 390 BTC that wouldn't be bad for bitcoin at all."
03:55:29 <Sgeo> http://www.reddit.com/r/SubredditDrama/comments/22q9tr/when_bitcoin_drops_to_390_btc_one_man_dares_to/
03:56:06 <Bike> http://i.imgur.com/ZNN5zrn.png good point
03:58:26 <Sgeo> It would be nice if the technical stuff behind bitcoin allowed it to be useful without it being a vehicle for continuous speculation
03:58:54 <Sgeo> There may be something good about having a cryptocurrency, but I don't think 'wild price changes you may get lucky on' is it
04:00:03 <kmc> i mean, that's something more specific than continuous speculation
04:00:08 <kmc> every market has continuous speculation
04:00:20 <Jafet> If you trade bitcoin in real life, its exchange rate will move in real life
04:01:05 -!- conehead has joined.
04:02:09 <Sgeo> Is StartSSL still evil?
04:02:39 <pikhq> More so than usual with the recent Heartbleed issue.
04:02:59 <Sgeo> I didn't consider it evil before Heartbleed
04:03:16 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
04:03:31 <pikhq> It still disincentivizes good security practices, it just happens to have not been very relevant until just now. :)
04:05:23 <Sgeo> The non-existence of free certs also isincentivizes good security practices
04:05:28 <Sgeo> *disincentivizes
04:05:45 <pikhq> It's more the complete and utter insanity of the CA system that does that.
04:06:09 <pikhq> "Trust is hard. So trust this list of companies ENTIRELY!" is just... insane.
04:08:36 <kmc> i,i "truth is hard, so trust these axioms entirely!"
04:09:09 <Jafet> Free certs, are you suggesting we should lower the cost of someone jacking your router from $20 to zero
04:10:04 <kmc> routerjacking.xxx
04:10:40 <Bike> yeah, sure would suck if mathematicians dedicated themselves to finding the Right axioms
04:10:46 <Bike> anyway What Is Life is p. good i recommend it
04:13:09 <doesthiswork> there is an online catagory theory demonstrator
04:13:47 <doesthiswork> http://www.j-paine.org/cgi-bin/webcats/webcats.php
04:14:45 <elliott> Jafet: StartSSL free certs are already accepted by the major OSes/browsers, afaik
04:16:25 <Sgeo> Does LastPass have a feature to import saved Chrome passwords?
04:16:28 <Sgeo> That would be convenient
04:20:18 <kmc> I'm still waiting for Honest Lexande's Discount Certificates
04:21:06 -!- variable has quit (Ping timeout: 240 seconds).
04:21:15 <Jafet> Yeah, I should clear out root certs here
04:21:23 <Jafet> Maybe I should remove all root certs
04:21:34 <Jafet> And use certpatrol manually
04:22:01 <Jafet> But first, any root that signs intermediates
04:22:58 <kmc> `run openssl genrsa -out /tmp/root-ca.key 4096
04:22:59 <HackEgo> WARNING: can't open config file: /usr/lib/ssl/openssl.cnf \ Generating RSA private key, 4096 bit long modulus \ ..........++ \ .++ \ e is 65537 (0x10001)
04:23:04 <elliott> you might even succeed in making SSL annoying enough to use that you just use http intsead
04:24:53 <Bike> hey has anyone noticed that statistical mechanics is balls out crazy
04:26:04 <Jafet> elliott: to be fair http://i.imgur.com/jfGMMyL.png
04:28:40 <kmc> military grade cryptography
04:29:05 <kmc> the default is 1024 bits :'(
04:29:41 <Bike> whast's wrong with 1024
04:30:10 <Bike> but it's like, ovre twice as much as 400 bits
04:30:18 <shachaf> kmc would prefer 2048 bits
04:31:35 <maurer> The real thing that surprises me with default military grade being 1024 is that it's not like it would be that expensive for them to say "1024 is accepted but all new keys are 4096"
04:32:59 <Jafet> You don't understand, "military grade" just means "iraqi rebels can't hack into our drones using 20-year-old PCs"
04:33:11 <Jafet> It also sometimes means "RAM heatsinks"
04:33:37 <Bike> important to stay warm
04:34:12 <kmc> japanese solid capacitors
04:42:28 -!- tromp_ has quit (Remote host closed the connection).
04:43:01 -!- tromp_ has joined.
04:47:18 -!- tromp_ has quit (Ping timeout: 240 seconds).
04:53:49 -!- oklopol has joined.
04:59:48 -!- Sprocklem has quit (Quit: leaving).
05:12:09 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
05:15:36 -!- variable has joined.
05:15:36 -!- variable has quit (Changing host).
05:15:36 -!- variable has joined.
05:22:20 -!- password2 has joined.
05:25:48 -!- ^v has quit (Read error: Connection reset by peer).
05:26:14 -!- ^v has joined.
05:28:58 <Sgeo> If Heartbleed is 11 on a scale of 1-10, what is 'mathematicians have found a very fast way to factor any number' be?
05:29:50 <Bike> well, factorization could be in P without P = NP, right?
05:30:15 <Bike> so you could base a cryptosystem on discrete log or w/e right
05:30:45 <coppro> like elliptic curve crypto
05:30:48 <kmc> RSA is pretty widely used though
05:30:50 <Bike> i guess "RSA doesn't work" would still be pretty bad, practically speaking, huh
05:31:10 <coppro> it would be pretty bad. but not nearly as bad as "private key crypto doesn't wokr
05:31:40 <kmc> but it's a lot worse than everyone's private keys getting leaked once
05:34:35 <Bike> «Note that this final London equation does not contain instantaneous dipoles (see molecular dipoles). The "explanation" of the dispersion force as the interaction between two such dipoles was invented after London arrived at the proper quantum mechanical theory.» can someone explain to me how chemistry, the science, is even possible
05:35:46 <coppro> Bike: btw you would like quantum crypto
05:36:09 <Bike> that's not a joke or anything it just doesn't seem like i would
05:39:36 <Bike> i'm reading a seminontechnical schrodinger thing and he more or less gave up on explaining quantum jumps except that they happen, it kind of rules
05:41:27 <kmc> i like post-quantum crypto
05:44:46 -!- doesthiswork has quit (Quit: Page closed).
05:49:31 <coppro> Bike: not totally sure
05:50:03 <Bike> right now i would like to understand stat mechanics. it seems slightly different from quantum crypto, but then it is connected to info theory...
06:00:30 <Slereah_> Statistical mechanics doesn't use much information theory
06:00:43 <Slereah_> Just that you try to guess at the microstates from the macrostate
06:01:39 * Bike points at szilard engine
06:01:45 <Slereah_> And the lack of knowledge between the two is basically what constitutes entropy
06:11:32 -!- oklopol has quit (Ping timeout: 252 seconds).
06:14:11 <Sgeo> http://copy.sh/v24/
06:16:21 <Bike> oh, right. and chemical entropy is shannon entropy times boltzmann.
06:29:29 -!- Slereahphone has joined.
06:31:08 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:32:03 <kmc> not the preferred nomenclature
06:33:55 -!- Slereahphone has quit (Remote host closed the connection).
06:34:02 <Bike> "continually sucking orderliness"
06:34:39 -!- Slereahphone has joined.
06:51:16 -!- Slereahphone has quit (Remote host closed the connection).
07:00:43 <HackEgo> [wiki] [[Rebmu]] N http://esolangs.org/w/index.php?oldid=39283 * Zom-B * (+2118) Created page with "Rebmu is an esoterical code-[[golf]] dialect of Rebol, made by HostileFork. ==Overview== The underlying language is case-insensitive, so it uses CAPSalternationTOseparateTOKE..."
07:00:49 -!- MoALTz has joined.
07:03:51 <HackEgo> [wiki] [[Rebmu]] http://esolangs.org/w/index.php?diff=39284&oldid=39283 * Zom-B * (+263)
07:06:12 <fizzie> I don't know if I should try to smuggle that ^ wiki update bridge into the start script of HackEgo, or if that would be presumptuous, or if it's even a good idea in general.
07:12:48 -!- Slereahphone has joined.
07:21:20 -!- MoALTz has quit (Quit: brb).
07:34:39 -!- MoALTz has joined.
07:46:27 <Bike> http://xkcd.com/1354/ So how accurate is this
07:49:34 -!- MindlessDrone has joined.
07:50:40 <kmc> "Lactarius xanthogalactus" is a pretty effing cool name
07:53:11 <kmc> yellow-milked milk-cap
07:53:22 <Bike> xantho is yellow, not weird
07:53:30 <kmc> Bike knows
07:53:42 <Bike> well i got no idea about galactus
07:53:46 <Bike> other than the planet eater dude
07:55:22 <Taneb> Well, "Galaxy" is from the greek for milky way
07:55:29 <Taneb> I mean, literally "Milky Way"
07:56:00 <kmc> yes TIL as well
07:56:07 <kmc> though it sounds like the kind of thing I would have known and forgotten
07:56:23 <kmc> but really isn't all learning just remembering
07:56:40 <Bike> going for the double greek, are we
08:09:34 -!- mtve has quit (Quit: Terminated with extreme prejudice - dircproxy 1.2.0).
08:27:00 -!- MoALTz_ has joined.
08:27:58 -!- MoALTz has quit (Ping timeout: 252 seconds).
08:28:09 -!- Patashu has joined.
08:28:31 -!- Patashu has quit (Disconnected by services).
08:28:31 -!- Patashu[Zzz] has joined.
08:53:05 -!- cool has joined.
08:53:37 <cool> hey did you guys see the european open source meeting talk?
08:55:06 <cool> https://www.youtube.com/watch?v=3jQoAYRKqhg
08:58:27 <cool> openssl is dead
09:09:00 <int-e> I wouldn't bet on it
09:11:21 -!- xpte has quit (Quit: Connection closed for inactivity).
09:35:29 -!- S1 has joined.
09:40:53 -!- cool has quit (Quit: Page closed).
10:02:59 -!- Slereahphone has quit (Remote host closed the connection).
10:15:26 -!- yorick has joined.
10:19:04 -!- oerjan has joined.
10:29:18 <oerjan> <Sgeo> Side-channel attacks based on timing? <-- that's my hunch anyway.
10:30:03 <oerjan> assuming an attacker cannot also track memory use.
10:30:49 <fizzie> I think I've read about things like cache-timing attacks on AES.
10:31:03 <fizzie> Which I guess would be a subclass of "memory use".
10:31:43 <oerjan> fizzie: btw i left out the context that this was about haskell
10:31:52 <oerjan> which is safe in so many other ways.
10:32:29 <fizzie> That's all right, since I did see the context.
10:33:29 <oerjan> that's like tracking memory use _via_ time use...
10:34:26 -!- SpaceWizard has joined.
10:39:44 -!- MoALTz_ has quit (Quit: brb).
10:39:56 -!- MoALTz has joined.
10:47:44 -!- yorick has quit (Read error: Connection reset by peer).
10:48:34 -!- nucular has joined.
10:48:46 -!- nucular has quit (Changing host).
10:48:47 -!- nucular has joined.
10:49:31 -!- Slereahphone has joined.
10:50:24 -!- Slereahphone has quit (Read error: Connection reset by peer).
10:52:13 <fizzie> These spam emails from (predominantly Chinese) manufacturers of this and that (mostly) industrial thing are curious.
10:52:35 <fizzie> One wouldn't assume them to have much of a success rate, but maybe it's a large enough epsilon to be worth it.
10:53:42 <fizzie> (Or maybe they have some other purpose. Does anyone know?)
10:53:54 -!- yorick has joined.
10:55:01 <fizzie> Here's a sample I just got, delivered to an obviously-harvested-from-web role address just now: http://sprunge.us/ceGW
10:55:46 <oerjan> they're secretly commands to the chinese hacker botnets, they're just sent indiscriminately so no one will notice where the real machines are hth
11:05:10 -!- S1 has left.
11:08:45 -!- Patashu[Zzz] has changed nick to Patashu.
11:10:11 -!- password2 has quit (Ping timeout: 252 seconds).
11:11:59 -!- password2 has joined.
11:15:34 <int-e> fizzie: that reminds me of http://www.nytimes.com/2012/04/15/opinion/sunday/the-cybercrime-wave-that-wasnt.html?_r=0
11:36:14 -!- conehead has quit (Quit: Computer has gone to sleep).
11:46:18 -!- SpaceWizard has quit (Ping timeout: 276 seconds).
11:48:54 -!- olsner has quit (Ping timeout: 276 seconds).
11:53:25 <oerjan> @tell Jafet before `reverting, you should check that your command actually changed something, otherwise you'll revert the previous change instead.
11:59:23 <Jafet> I see, /tmp isn't tracked
12:01:06 -!- olsner has joined.
12:11:25 -!- SpaceWizard has joined.
12:18:05 -!- Sgeo has quit (Read error: Connection reset by peer).
12:19:30 -!- Tod-Autojoined has quit (Read error: Connection reset by peer).
12:19:43 -!- Tod-Autojoined has joined.
12:34:36 -!- tromp_ has joined.
12:34:41 -!- tromp has quit (Ping timeout: 245 seconds).
12:38:34 -!- password2 has quit (Remote host closed the connection).
12:40:05 -!- password2 has joined.
12:40:23 -!- tromp has joined.
12:45:57 -!- tromp has quit (Remote host closed the connection).
12:46:33 -!- tromp has joined.
12:51:05 -!- tromp has quit (Ping timeout: 258 seconds).
12:51:36 -!- password2 has quit (Ping timeout: 252 seconds).
12:56:07 -!- nooodl has joined.
13:09:29 -!- impomatic has quit (Ping timeout: 258 seconds).
13:18:56 -!- Sellyme has quit (Excess Flood).
13:20:09 -!- S1 has joined.
13:20:52 -!- Sellyme has joined.
13:25:35 -!- SpaceWizard has quit (Quit: Leaving).
13:26:04 -!- SpaceWizard has joined.
13:32:51 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
13:55:38 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39285&oldid=39247 * 88.162.181.62 * (+9)
14:06:38 <fizzie> That can't be right, but I don't have time to look into it right now.
14:07:01 <fizzie> (They added "F#" to the language list, but that just works out as a link to F.)
14:08:18 -!- SpaceWizard has quit (Quit: Leaving).
14:08:46 -!- SpaceWizard has joined.
14:08:47 -!- SpaceWizard has quit (Changing host).
14:08:47 -!- SpaceWizard has joined.
14:24:53 -!- Patashu has quit (Ping timeout: 252 seconds).
14:29:22 -!- Sprocklem has joined.
14:30:51 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39286&oldid=39274 * Oerjan * (+95) Move signature to end, question
14:35:02 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39287&oldid=39285 * Oerjan * (-9) Undo revision 39285 by [[Special:Contributions/88.162.181.62|88.162.181.62]] ([[User talk:88.162.181.62|talk]]) (Not esoteric, and the page is not about it.)
14:44:09 -!- ^v has joined.
15:00:24 -!- variable has changed nick to trout.
15:15:29 -!- oerjan has quit (Quit: leaving).
15:30:27 -!- oerjan has joined.
15:32:32 -!- SpaceWizard has quit (Ping timeout: 252 seconds).
15:33:18 -!- oerjan has quit (Client Quit).
16:25:31 -!- Sprocklem has quit (Ping timeout: 245 seconds).
16:27:19 -!- Sprocklem has joined.
16:27:25 -!- SpaceWizard has joined.
16:33:37 -!- password2 has joined.
16:49:48 -!- yorick has quit (Remote host closed the connection).
17:01:04 -!- jconn has quit (Remote host closed the connection).
17:09:27 -!- Sprocklem has quit (Ping timeout: 258 seconds).
17:10:56 -!- MoALTz has quit (Quit: Leaving).
17:11:16 <fizzie> Grumble frumble mips-elf-objdump doesn't have a similar "use information from DYNAMIC phdr entry instead" flag that mips-elf-readelf has; it can't disassemble these binaries at all. (I've used readelf + dd-with-offsets + objdump -b binary as a workaround, but it's very uncomfortable.)
17:13:09 <fizzie> (For one thing, I need to manually cross-reference all GOT offsets and such.)
17:17:12 -!- jconn has joined.
17:17:54 -!- lambdabot has quit (Quit: brb).
17:18:03 -!- zzo38 has joined.
17:22:34 -!- lambdabot has joined.
17:35:04 -!- Sprocklem has joined.
17:40:15 -!- Sprocklem has quit (Ping timeout: 250 seconds).
17:49:01 <mroman> Does anyone have experience with compiling BASIC-like Languages to languages without computed gotos?
17:49:11 <mroman> http://codepad.org/ib8s3lEB <- this approach works
17:49:29 <mroman> but it's prone to stack overflows
17:52:30 <mroman> I also figured I could keep a list of delegates
17:52:41 <mroman> which tell's me which function I have to call next
17:53:09 <mroman> that way I could probably avoid that
17:53:33 -!- MindlessDrone has quit (Ping timeout: 276 seconds).
17:54:30 <fizzie> There's the single-function giant-dispatcher approach.
17:56:32 <int-e> there is the Statement s = LINE1; while (!quit) { s = s.invoke(); } approach.
17:58:37 <fizzie> You could also adopt something like the "Cheney on the M.T.A." trick, but it's perhaps not that doable in C#.
17:59:12 <mroman> http://codepad.org/eSHjKVYa <- this works
17:59:57 <mroman> keeping a list of delegates. and a GOTO changes the index of the next called function
18:00:25 <mroman> (and no GOTO just increases the index)
18:01:01 <zzo38> To do something similar I have just used a case block, where the labels are just case and goto is replaced by an assignment and then continue the outer loop.
18:04:57 <mroman> I think I can have this thing going by tomorrow :D
18:05:35 <mroman> aka Write Yourself a crappy BASIC compiler in a day :)
18:09:51 -!- MindlessDrone has joined.
18:09:52 -!- MoALTz has joined.
18:18:47 <HackEgo> imminicoin lnncoin greocoin nyrcoin alpitchcoin smalcoin fortcoin anemailwariathcoin theshccoin chercoin grapecoin wheecoin fernacoin son-textenchcoin longcoin balcoin lintolercoin nesancoin sfulcoin empiuertcoin
18:29:41 -!- Slereah has joined.
18:30:44 -!- Slereah_ has quit (Ping timeout: 252 seconds).
18:40:19 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39288&oldid=39278 * Zerk * (+10) Clarified indentation slightly; "[same _Y _Y]" is my new favourite way to specify letrec XD
19:01:27 <HackEgo> [wiki] [[Nock]] N http://esolangs.org/w/index.php?oldid=39289 * Zerk * (+1425) TODO: actual article. I think copying the official docs wouldn't be a license conflict?
19:01:44 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39290&oldid=39286 * Zerk * (+415)
19:08:38 -!- Slereah_ has joined.
19:12:07 -!- Slereah has quit (Ping timeout: 250 seconds).
19:12:54 -!- Slereah has joined.
19:13:30 -!- Slereah_ has quit (Ping timeout: 240 seconds).
19:14:57 -!- Slereah has quit (Client Quit).
19:29:56 -!- Slereah_ has joined.
19:53:17 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:55:28 -!- impomatic has joined.
19:57:23 -!- Sprocklem has joined.
20:26:18 -!- password2 has quit (Ping timeout: 276 seconds).
20:34:21 -!- doesthiswork has joined.
20:38:03 <doesthiswork> what would be a good name for a language based on a statemachine that can be in an arbitrary superposition of states?
20:38:52 <Bike> powerstate machine
20:39:09 <Bike> because the state is actually out of the powerset of states, rather than the set, see
20:40:46 -!- password2 has joined.
20:42:32 <Bike> probability assigned to each state?
20:44:19 <Bike> Does this involve a priesT?
20:45:20 <doesthiswork> its state is holographic so it responds in proportion to how similar it's current state is to the set of states
20:53:01 -!- Frooxius has quit (Read error: Connection reset by peer).
20:54:38 -!- Frooxius has joined.
21:03:13 -!- zzo38 has quit (Remote host closed the connection).
21:03:46 -!- oerjan has joined.
21:20:42 -!- Sprocklem has quit (Ping timeout: 240 seconds).
21:36:49 -!- Slereah has joined.
21:39:01 -!- Slereah_ has quit (Ping timeout: 250 seconds).
21:41:19 -!- ^v has quit (Read error: Connection reset by peer).
21:41:41 -!- ^v has joined.
21:49:35 <kmc> I found one case in Rust where let mut x = ...; f(x) can end up modifying x
21:51:03 <kmc> that's one of the worst things about C++, and Rust generally avoids it
21:51:23 <kmc> well I don't know, there's a lot of competition for "worst things about C++"
21:56:10 -!- MoALTz has quit (Quit: brb).
21:57:19 -!- copumpkin has joined.
21:57:39 -!- MoALTz has joined.
22:03:10 -!- nucular has quit (Quit: Switching to the phone).
22:07:42 -!- drlemon_ has quit (Remote host closed the connection).
22:08:10 -!- drlemon has joined.
22:08:53 -!- yorick has joined.
22:15:34 <HackEgo> [wiki] [[Talk:Nock]] N http://esolangs.org/w/index.php?oldid=39291 * Doesthiswork * (+172) Created page with "After reading about the Urbit project, Nock and Hoon are definitely esoteric ~~~~"
22:17:54 -!- Frooxius has quit (Ping timeout: 240 seconds).
22:26:22 <HackEgo> [wiki] [[User:Doesthiswork]] N http://esolangs.org/w/index.php?oldid=39292 * Doesthiswork * (+763) notes on holographic reduced representation
22:39:52 -!- conehead has joined.
22:40:17 -!- tromp has joined.
22:48:02 -!- doesthiswork has quit (Quit: Page closed).
22:49:07 <shachaf> https://plus.google.com/111605401594472745199/posts/BBarZAT9wCM
22:50:10 -!- Sgeo has joined.
22:51:06 -!- Patashu has joined.
22:58:23 -!- Sorella has joined.
23:10:15 <oerjan> argh easter is next week
23:11:48 * oerjan wows never to trust shop assistants again
23:13:12 <oerjan> (because of this, i might have sent flowers to someone who is already on vacation)
23:21:45 -!- yorick has quit (Remote host closed the connection).
00:04:16 -!- password2 has quit (Ping timeout: 245 seconds).
00:25:05 -!- conehead has quit (Quit: Computer has gone to sleep).
00:26:17 -!- tertu has joined.
00:33:02 -!- Sprocklem has joined.
00:33:15 -!- conehead has joined.
00:41:28 -!- Tod-Autojoined has quit (Ping timeout: 252 seconds).
00:41:59 -!- ^v has quit (Ping timeout: 252 seconds).
00:51:48 -!- TodPunk has joined.
00:59:10 -!- Sorella has quit (Quit: It is tiem!).
01:08:57 -!- tertu has quit (Ping timeout: 252 seconds).
01:09:05 -!- tertu has joined.
01:17:16 -!- oerjan has quit (Quit: leaving).
01:20:06 -!- tertu has quit (Ping timeout: 276 seconds).
01:41:05 -!- CapitalSigma has joined.
01:41:38 <CapitalSigma> is there a BNF grammar for brainfuck out there somewhere?
01:43:26 <kmc> I think it would just be c ::= "[" c "]" | "+" | "-" | "<" | ">" | "," | "."
01:43:27 -!- zzo38 has joined.
01:43:41 <kmc> and a lot of interpreters will accept unbalanced [] until you actually hit them
01:43:52 <kmc> so it's not clear whether that's a syntax error or a runtime exception
01:44:23 <kmc> c ::= "" | "[" c "]" | "+" c | "-" c | "<" c | ">" c | "," c | "." c
01:48:56 -!- boily has joined.
01:52:31 <CapitalSigma> okay. i'm trying to learn about compilers so i figure that getting a parser+lexer for brainfuck working would be the easiest place to start -- are there any good resources out there?
01:53:08 <zzo38> Ah. What are you trying to write the program in?
01:56:06 <kmc> brainfuck isn't the kind of language you would use those tools for
01:56:12 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39293&oldid=39288 * Doesthiswork * (+2056) added a simple genetic algorithm as an example
01:56:24 <kmc> I would start with a simple expression grammar
01:56:39 <CapitalSigma> zzo38: i'm really interested in learning how to use parser-generators, i'm using antlr
01:56:43 <zzo38> Yes it is true you don't need a parser+lexer for brainfuck compiling
01:57:01 <kmc> parse arithmetic expressions with literals and +-*/ and parentheses
01:57:08 <kmc> that's kind of the standard first parser project
01:58:41 <HackEgo> [wiki] [[Smartboxes]] M http://esolangs.org/w/index.php?diff=39294&oldid=39293 * Doesthiswork * (+7)
01:58:54 <CapitalSigma> okay.... and that would look something like: op ::= "+" | "*" | "/" | "-"; exp ::= exp op exp | id; id ::= [0-9]+;
01:59:20 <zzo38> CapitalSigma: That won't make any precedences.
01:59:56 -!- doesthiswork has joined.
02:00:09 <zzo38> I have seen the parser for the OASYS compiler (a text-adventure game system); is not too difficult for understanding. (I have, in fact, rewritten it in BASIC from a printout of the C code, because I didn't have a disk, and on the target computer I didn't have a C compiler.)
02:02:08 -!- ^v has joined.
02:02:33 <CapitalSigma> zzo38: okay. so it needs parens.... i suppose exp ::= "(" exp op exp ")"; would be enough... is there anything that you all recommend i read for starting off?
02:05:37 <zzo38> I actually don't read much about parser either...the only expression parser I really studied much is the one used in OASYS, and didn't find it so difficult.
02:09:15 <zzo38> I have read some books too, telling about LL(1), LR(1), and so on, but I forgot what book it is.
02:09:26 <zzo38> Wikipedia might have some more information.
02:24:09 -!- Sprocklem has quit (Ping timeout: 250 seconds).
02:24:31 -!- nisstyre has joined.
02:45:13 <Sgeo> If only NullPointerException was a checked exception...
02:45:54 <Sgeo> (Actually that would probably be quite annoying to work with)
02:46:06 <Sgeo> Not sure which is worse
02:47:04 <Bike> if only, if only, the woodpecker sighs
02:49:27 <doesthiswork> apparently there was a comic charecter named Smokey Stover who called things he didn't know the name of "foo"
02:52:49 <Sgeo> the bark on the trees was as soft as the skies
02:54:07 -!- boily has quit (Quit: Poulet!).
03:02:41 <Sgeo> Google seems to disagree on if it's 'trees' or 'tree'
03:03:48 -!- doesthiswork has quit (Ping timeout: 240 seconds).
03:06:12 * Sgeo goes to install EclipseFP
03:19:35 -!- SpaceWizard has quit (Remote host closed the connection).
03:31:23 -!- nooodl has quit (Ping timeout: 252 seconds).
03:33:05 <Sgeo> https://www.cloudflarechallenge.com/heartbleed
03:33:15 <Sgeo> So, are they just trying to figure out the plausibility of stolen certificates?
03:37:30 <Sgeo> Is it possible for a random third party to hinder Heartbleed attacks slightly by asking for a smaller heartbeat payload than it gives?
03:39:55 <Bike> that sounds hilarious
03:40:50 <Jafet> I don't know what that means, but you could inundate servers with traffic so that single attackers are less likely to find sensitive data amongst all of your buffers
03:41:31 <Jafet> Though, it costs you more traffic to play this game than them.
03:45:31 <Sgeo> https://twitter.com/indutny/status/454767565991325697
03:48:52 <kmc> you have to use www.cloudflarechallenge.com to make it actually work
03:49:04 <kmc> I think twitter messes with things that look like hostnames
03:49:26 <Sgeo> Hovering over the links shows www
03:50:26 <Jafet> What if someone steals the private key from his server
04:23:30 <zzo38> There is this quotation about Lisp programming: SQL, Lisp, and Haskell are the only programming languages that I've seen where one spends more time thinking than typing. -- Philip Greenspun
04:24:58 <elliott> Greenspun hasn't seen enough languages
04:26:55 <zzo38> elliott: You are probably correct.
04:29:30 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39295&oldid=39294 * Zerk * (-50) /* Examples */(Decrement) I think I just figured out recursion, correct me if I'm misunderstanding the semantics.
04:36:00 <Bike> i also get that with brainfuck
04:36:46 <zzo38> Why do you hate FORTRAN so much?
04:39:49 <kmc> why you want rail for kalashnikov
04:40:44 -!- ^v has quit (Read error: Connection reset by peer).
04:42:10 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39296&oldid=39295 * Zerk * (+50) Undo revision 39295 by [[Special:Contributions/Zerk|Zerk]] ([[User talk:Zerk|talk]]) I do misunderstand the semantics! It would reach the right value, but then unwind back to the original 0 before returning.
04:43:50 <zzo38> I don't know who/what they are.
04:44:43 <shachaf> What do you call a chain A, B, C, ... such that A ⊆ B ⊆ C ⊆ ...?
04:45:11 -!- ^v has joined.
04:47:39 <Bike> why do i hate fortran so much
04:48:17 -!- password2 has joined.
04:48:33 <Bike> shachaf: descending chain? or what
04:48:54 <shachaf> i guess chain is the actual term
04:49:02 <shachaf> also why is it descending and not ascending
04:49:17 <Bike> look, i'm not noether
05:00:36 <zzo38> How can you make a programming language where the types are Hoare triples?
05:00:41 <Sgeo> It occurs to me that I'm already using an entirely online password manager, completely unencrypted
05:00:59 <Sgeo> (At least, I think it's unencrypted)
05:02:21 -!- adu has joined.
05:06:27 <HackEgo> [wiki] [[Smartboxes]] http://esolangs.org/w/index.php?diff=39297&oldid=39296 * Doesthiswork * (-2065) removed the GA example after concluding that it is a mess semantically
05:12:06 -!- zzo38 has quit (Ping timeout: 240 seconds).
05:14:24 <Sgeo> Google already has my passwords, why not LastPass?
05:15:58 <coppro> Chrome is unecrypted by default but you can encrypt them if you'd like.
05:16:11 <coppro> I believe the local store is encrypted though; the encryption option just affects the syncing
05:18:52 -!- zzo38 has joined.
05:19:33 <zzo38> Is it possible to do sequent calculus with only bound variables and no free variables (so that free variables are ungrammatical)?
05:21:29 <coppro> been too long since I've seen sequent calculus
05:27:09 <zzo38> I try to think of a way
05:43:14 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:46:38 -!- tertu has joined.
06:06:38 -!- tromp has quit (Remote host closed the connection).
06:07:10 -!- tromp has joined.
06:09:23 <newsham> whoa, you gave your password to google?!@#
06:11:06 -!- tromp has quit (Ping timeout: 240 seconds).
06:14:11 -!- tertu has quit (Ping timeout: 252 seconds).
06:18:22 <Jafet> newsham: it's what happens when you decide to use gmail.
06:21:05 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:34:03 <newsham> cant you tell them you want to use gmail but you dont want to give them your pw?
06:35:56 <Jafet> The trouble is that most services that use authentication persistently insist that you should allow them to delegate the authentication to google.
06:37:26 <Jafet> Hmm, I wonder if I could simply point them at foo@example.com. (Probably not; IANA has a server there.)
06:38:09 <newsham> most services i've seen dont delegate auth to google
06:38:39 <newsham> you know what pisses me off lately? hotmail and google and others pestering me constantly to link a cell phone number to my account
06:38:57 <Jafet> They do, but have a strange name for this--"Forgot your password?"
06:42:39 <newsham> yah well hotmail locked me out of my account for a month because i didnt have a cell phone number in case I "forgot my password"
06:42:48 <newsham> so whats more dangerous, forgetting my password, or hotmail?
06:43:57 <newsham> in a few days when its finally available again i can start migrating all my accounts off of that email addr
06:45:26 <Jafet> Those are two opposite kinds of danger. I don't know how forgetful you are, but I create passwords algorithmically so "forgetting" them is not an issue. The only issue, then, is email.
06:46:07 <Bike> Import Your Contacts From Gmail
06:50:05 <kmc> import your contacts from the depths of hell
07:05:40 -!- MoALTz has quit (Quit: Leaving).
07:06:42 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
07:10:14 -!- MoALTz has joined.
07:42:01 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39298&oldid=39290 * Zerk * (+2165) /* Implicit evaluation */ new section
07:50:59 <myname> is it just me or does smartboxes look to useful to be an esolang? :D
07:59:14 <Jafet> The lead mentions Kay, so it is esoteric pretty much by construction
08:11:21 <olsner> myname: it's an upper bound, so anything except good? (unless good is small, then anything except bad)
08:11:23 -!- adu has quit (Quit: adu).
08:22:06 -!- Slereah has quit (Ping timeout: 240 seconds).
08:27:41 -!- Slereah_ has joined.
08:32:00 -!- Slereah has joined.
08:34:57 -!- Slereah_ has quit (Ping timeout: 276 seconds).
09:09:33 -!- tromp has joined.
09:09:42 -!- tromp has quit (Read error: Connection reset by peer).
09:10:20 -!- tromp has joined.
09:14:41 -!- tromp has quit (Ping timeout: 245 seconds).
09:39:44 -!- MindlessDrone has joined.
09:48:00 -!- yorick has joined.
09:59:12 <fizzie> http://sprunge.us/WRGj That's quite the regexp.
10:03:47 -!- Slereah_ has joined.
10:04:47 -!- Slereah has quit (Ping timeout: 250 seconds).
10:14:16 <myname> well, pretty simple, though
10:14:49 <myname> not like that deprecated expression for email addresses
10:43:50 -!- Vorpal has joined.
10:48:01 -!- conehead has quit (Quit: Computer has gone to sleep).
11:03:04 -!- oerjan has joined.
11:04:27 -!- Frooxius has joined.
11:08:26 -!- Slereah_ has quit (Ping timeout: 245 seconds).
11:08:38 -!- Slereah_ has joined.
11:27:37 -!- nooodl has joined.
11:43:51 -!- Melvar` has joined.
11:44:45 -!- idris-ircslave has quit (Ping timeout: 276 seconds).
11:45:26 -!- Melvar has quit (Ping timeout: 255 seconds).
11:56:43 -!- Melvar` has changed nick to Melvar.
11:57:32 -!- idris-ircslave has joined.
12:24:42 -!- Slereah_ has quit (Ping timeout: 240 seconds).
12:32:29 -!- boily has joined.
12:34:19 -!- Slereah_ has joined.
12:36:30 <HackEgo> [wiki] [[Boxy]] N http://esolangs.org/w/index.php?oldid=39299 * Zerk * (+2725) Spec fork!
12:50:11 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
12:50:53 -!- Vorpal has joined.
12:50:53 -!- Vorpal has quit (Changing host).
12:50:53 -!- Vorpal has joined.
12:54:42 -!- Sorella has joined.
13:05:31 <fizzie> Hmm. My 16 GB CF card has turned into a 2 TB CF card.
13:05:55 <fizzie> [3432361.978679] sd 11:0:0:0: [sde] 3842213123 512-byte logical blocks: (1.96 TB/1.78 TiB)
13:06:08 <fizzie> That's what it says when I plug it into a card reader.
13:06:31 <fizzie> olsner: Less lucky is that any IO access to it just hangs indefinitely.
13:07:12 <fizzie> Oh, it wasn't indefinitely; but it does go all http://sprunge.us/Meab after a long delay.
13:07:17 <Jafet> Some manufacturers inflate the apparent capacity of their flash devices, but this is somewhat excessive
13:07:39 <fizzie> It does manage to read the partition table off, so maybe a dd on the first 16 gigs could work.
13:08:12 <boily> Jafet: it's only a 7 order of magnitude error. nothing to worry about.
13:10:10 <fizzie> dd of the first partition (there seems to be three) at least seems to be working. fdisk didn't, but maybe it was trying to check something at the end of the disk.
13:11:29 <fizzie> (Okay, it's only reading 100 kilobytes/sec, but that still counts as working, I guess.)
13:13:31 <oerjan> `frink 16 gigabytes / (100 kilobytes/s)
13:13:44 <fizzie> That's only 46 hours to read the 16 gigs that should be there, and a further 220 days to see what's on the rest of the two terabytes.
13:15:57 <int-e> so does the data that you get off the drive make sense?
13:17:11 <olsner> hmm, for some reason I could see immediately that 160000s is about two days, but had to think a long while to realize that 46h is also about two days
13:22:35 <fizzie> int-e: I haven't looked yet. But it had the same number of partitions, so presumably at least the first sector was correct.
13:23:07 <int-e> ok. anyway, good luck :)
13:23:09 <fizzie> Same number that I expected it to have, that is.
13:23:56 <fizzie> There's nothing terribly important in there; it used to be the "hard disk" of a computer, I was just missing some scripts and crontabs I think were in /root which I didn't copy back when the card was working normally.
13:36:40 <fizzie> 140345856 bytes (140 MB) copied, 1327.63 s, 106 kB/s
13:37:02 -!- nucular has joined.
13:38:09 <fizzie> Contents seem correct, too. Except that sde1 was apparently /boot, so they're not exactly useful.
14:02:12 -!- tertu has joined.
14:14:10 -!- ^v has joined.
14:19:18 -!- password2 has quit (Ping timeout: 240 seconds).
14:38:44 -!- Tritonio has joined.
14:45:01 -!- password2 has joined.
14:49:59 -!- tromp has joined.
15:00:50 -!- Patashu has quit (Ping timeout: 258 seconds).
15:07:20 -!- password2 has left ("Leaving").
15:16:12 -!- tertu has quit (Read error: Connection reset by peer).
15:37:40 -!- oerjan has quit (Quit: leaving).
15:42:44 -!- erdic has quit (Ping timeout: 246 seconds).
15:43:46 -!- erdic has joined.
15:45:54 -!- copumpkin has joined.
16:13:49 <fizzie> Also got http://sprunge.us/aFOb during a scheduled check of a backup disk, which doesn't sound good.
16:20:48 <fizzie> I can never figure out how to read this smartctl output. :/
16:28:34 <Jafet> LBA numbers, right next to planck units and ancient greek cubits
16:29:20 -!- MoALTz_ has joined.
16:30:42 <fizzie> Is it a graphical something? The disk is not on a computer with X libraries or anything.
16:31:11 <Jafet> It is a gtk something
16:31:58 <fizzie> I don't even know if big numbers or small numbers are good for these translated ones.
16:32:07 -!- MoALTz__ has joined.
16:32:11 -!- MoALTz has quit (Ping timeout: 250 seconds).
16:32:39 <Jafet> Well, you could keep mashing the drive and check if the number increases.
16:34:04 <fizzie> I guess I'll run the self-tests, since those at least should say something reasonable, hopefully.
16:34:54 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
16:35:01 <fizzie> Reallocated_Sector_ct has a velue of "200", worst of "200", threshold of "140" and a raw value of "1".
16:38:08 <Jafet> `run echo $'#include <sys/mman.h>\n#include <stdio.h>\n#include <string.h>\nmain(){\n void *p = mmap((void*)0x398e4f53fa300000, 4096, PROT_NONE, MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);\n return !printf("%p %s\n", p, strerror(errno)); }\n' > /tmp/m.c && gcc m.c -o m && ./m
16:38:09 <HackEgo> gcc: error: m.c: No such file or directory \ gcc: fatal error: no input files \ compilation terminated.
16:38:20 <Jafet> `run echo $'#include <sys/mman.h>\n#include <stdio.h>\n#include <string.h>\nmain(){\n void *p = mmap((void*)0x398e4f53fa300000, 4096, PROT_NONE, MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);\n return !printf("%p %s\n", p, strerror(errno)); }\n' > /tmp/m.c && gcc /tmp/m.c -o /tmp/m && /tmp/m
16:38:21 <HackEgo> /tmp/m.c: In function ‘main’: \ /tmp/m.c:6:17: warning: missing terminating " character [enabled by default] \ /tmp/m.c:6:2: error: missing terminating " character \ /tmp/m.c:7:1: warning: missing terminating " character [enabled by default] \ /tmp/m.c:7:1: error: missing terminating " character \ /tmp/m.c:7:1: error: expected expression at
16:39:18 <Jafet> `run echo $'#include <sys/mman.h>\n#include <stdio.h>\n#include <string.h>\n#include <errno.h>\nmain(){\n void *p = mmap((void*)0x1000000000, 4096, PROT_NONE, MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);\n return !printf("%p %s\\n", p, strerror(errno)); }\n' > /tmp/m.c && gcc /tmp/m.c -o /tmp/m && /tmp/m
16:39:31 <Sgeo> Ok, seeing the reactive-banana guy act like an idiot makes me sad
16:39:33 <Jafet> `run echo $'#include <sys/mman.h>\n#include <stdio.h>\n#include <string.h>\n#include <errno.h>\nmain(){\n void *p = mmap((void*)0x1000000000000, 4096, PROT_NONE, MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);\n return !printf("%p %s\\n", p, strerror(errno)); }\n' > /tmp/m.c && gcc /tmp/m.c -o /tmp/m && /tmp/m
16:39:34 <HackEgo> 0xffffffffffffffff Cannot allocate memory
16:40:33 <Jafet> `run echo $'#include <sys/mman.h>\n#include <stdio.h>\n#include <string.h>\n#include <errno.h>\nmain(){\n void *p = mmap((void*)0x1000000000000ull, 4096, PROT_NONE, MAP_PRIVATE|MAP_ANON|MAP_FIXED, -1, 0);\n return !printf("%p %s\\n", p, strerror(errno)); }\n' > /tmp/m.c && gcc /tmp/m.c -o /tmp/m && /tmp/m
16:40:33 <HackEgo> 0xffffffffffffffff Cannot allocate memory
16:40:48 <Sgeo> http://www.reddit.com/r/haskell/comments/22udou/heartbleed_aftermath_should_haskell_web/
16:44:10 <fizzie> Jafet: Wouldn't 0x1'0000'0000'0000 fail the canonical-address test?
16:46:12 <Jafet> Huh, there are such things as canonical addresses.
16:46:14 <fizzie> "In addition, the AMD specification requires that bits 48 through 63 of any virtual address must be copies of bit 47 (in a manner akin to sign extension), or the processor will raise an exception.[1](p131) Addresses complying with this rule are referred to as "canonical form."[1](p130) Canonical form addresses run from 0 through 00007FFF'FFFFFFFF, and from FFFF8000'00000000 through ...
16:46:20 <fizzie> ... FFFFFFFF'FFFFFFFF, for a total of 256 TB of usable virtual address space."
16:46:34 <fizzie> Bits don't grow on trees, you know!
16:46:36 <Jafet> I thought CPUs were more clever about masking the unimplemented address lines.
16:46:44 <ion> FFFFFFFF'UUUUUUUU
16:47:07 <fizzie> They're clever about hiding unimplemented physical address lines.
16:47:59 <Taneb> That was meant to be an emoticon but I am too tired
16:48:59 <Taneb> otoh, I bought a new comic :)
16:49:17 <fizzie> They're less clever about the virtual address space limit, which I gather has something to do with saving area on the chip. (As well as maybe some page table -related things?)
16:50:12 <fizzie> Fun fact: Intel manuals allow for up to 52-bit physical addresses even while the linear addresses are restricted to 48 bits.
16:51:12 <Jafet> 48-bit PAE... they think ahead, don't they.
16:52:52 <Taneb> Man, I feel like crap
16:54:10 <kmc> the canonical address thing is done on purpose
16:54:24 <kmc> so that people don't use the unused bits for tag bits (without masking)
16:54:34 <kmc> so that the virtual address space can be extended later without breaking shit
16:55:07 <kmc> i know, right?
16:55:12 <kmc> imo there should at least be a way to disable it
16:55:27 <kmc> some people care a whole lot about speed and not at all about binary forwards-compatibility
16:55:39 <kmc> there's probably a secret MSR or something
16:55:55 <fizzie> Even a translation of a 48-bit virtual address involves quite a lot of pointers. The CR3 register points at the start of the PML4 table; bits 39..47 of the address select an entry of it pointing at a Page-Directory-Pointer Table; bits 30..38 select an entry of it pointing at a Page-Directory Table; bits 21..29 select an entry of it pointing at a Page Table; bits 12..20 select an entry of it ...
16:56:01 <fizzie> ... pointing to a physical page; and bits 0..11 are an offset within the page.
16:56:29 <kmc> kind of bugs me that they all have names instead of just being level4 .. level1
16:56:46 <fizzie> "PML4" has a 4 in it, at least.
16:57:02 <fizzie> I'd like to see them invent names for all similar tables of a full 64-bit setup.
16:57:14 <kmc> don't give them any ideas
16:57:19 <Jafet> Although, you could map identical ranges that have a tag bit on and off to the same underlying pages
16:57:36 <kmc> I've wondered if there are programs that do that
16:57:39 <Jafet> Might screw with the tlb, but isn't it worth it
16:57:57 <fizzie> Just set the "Page-Directory-Selector-Index-Hyperpage-Pointer" suitably and...
16:58:06 <kmc> also do you know the trick about having a page directory table entry that points back to the page directory table?
16:58:28 <kmc> the PDT and PT records have a similar layout
16:59:12 <Jafet> Who would you trick with that
16:59:21 <kmc> if you use the PDT as a PT, then you've mapped all the PTs as pages in virtual memory
17:01:54 <kmc> Taneb: why do you feel like crap? :/
17:02:43 <fizzie> Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
17:02:47 <fizzie> # 1 Short offline Completed: read failure 80% 26750 470670340
17:02:50 <fizzie> I'm going to call it broken.
17:02:52 <Taneb> I was meeting from friends and I kind of abandoned them and I feel bad about it
17:10:51 -!- AnotherTest has joined.
17:11:02 <int-e> > 1 -- did I break this?
17:11:03 <lambdabot> mueval-core: GhcException "cannot satisfy -package lens\n (use -v for mor...
17:12:50 <zzo38> Why do Intel make it too complicated/confusing?
17:14:37 -!- MindlessDrone has quit (Ping timeout: 258 seconds).
17:15:36 <fizzie> Hah, there was a 36-month warranty on the disk, and it ended three weeks ago.
17:16:18 <ion> fizzie: nice
17:16:24 <fizzie> Man, those engineers are good when it comes to planned obsolescence.
17:16:32 <Jafet> Dangerous level of competency here.
17:25:24 -!- yorick has quit (Remote host closed the connection).
17:29:31 -!- MindlessDrone has joined.
17:32:27 -!- lambdabot has quit (Quit: 7.8.1 -> 7.8.2).
17:34:18 -!- Slereah_ has quit (Ping timeout: 240 seconds).
17:37:06 -!- lambdabot has joined.
17:41:15 * boily lightly pokes lambdabot
17:41:43 <boily> @tell idris-ircslave hello!
17:44:31 <kmc> > "hi fungot"
17:44:31 <fungot> kmc: those wallpapers have fnord. python has no semicolons, but mandatory newlines and indentation.
17:44:55 <kmc> python does have semicolons
17:46:20 <boily> fungot: if Python has semicolons, does it mean that wallpapers are fnordless?
17:47:06 <boily> fungot: I'm talking to you, you uncouth bot!
17:47:06 <fungot> boily: if all the benchmarks were implemented. the shared state was very clearly isolated in both scheme48 t ( except in summer when i earn nothing
17:47:21 <boily> fungot: ah. summer internship?
17:47:21 <fungot> boily: that doesn't render correctly here." " n=1" " n=2" " n=3" " n=4" " n=5" " n=6"... etc.
17:48:02 <kmc> int-e: is that a vampire bat
17:48:13 <kmc> fungot: are you a vampire bat
17:48:13 <fungot> kmc: strange labels like spells and magic recipes?" but i don't
17:49:16 <boily> today is a day to be smooth and drink coffee.
17:49:42 <quintopia> it was almost two weeks old and gross
17:49:52 * int-e ponders compiling a couple more ghcs
17:50:02 * int-e should probably change some passwords instead
17:50:18 <boily> two. weeks. old. coffee. I am impressed.
17:51:04 <int-e> . o O ( please tell us if you do )
17:51:43 <boily> I hope you're going to live through the Experience, then pen a beautiful, heart-wrenching Memoir about it.
17:52:06 <quintopia> "here's my password. get on all my networks and tell them i'm dead please and how i died."
17:52:29 <boily> is your password hunter2weekOldCoffee?
17:53:38 <quintopia> what do you mean *******weekOldCoffee?
17:53:45 <Jafet> The thought of dying from stale coffee is enough to keep one awake at night.
17:55:29 <int-e> still better than 2weakOldCoffee
17:56:26 -!- Slereah_ has joined.
17:57:46 -!- tromp has quit (Remote host closed the connection).
17:58:18 -!- tromp has joined.
17:58:35 -!- conehead has joined.
17:59:47 <boily> meanwhile, I just finished a full pot of http://www.ikea.com/ca/en/catalog/products/60241389/?query=UPPHETTA
18:02:45 -!- tromp has quit (Ping timeout: 250 seconds).
18:09:16 -!- Slereah_ has quit (Ping timeout: 245 seconds).
18:21:52 -!- lambdabot has quit (Quit: utf8 woes).
18:23:53 -!- nisstyre has joined.
18:24:00 -!- nisstyre has quit (Changing host).
18:24:00 -!- nisstyre has joined.
18:26:09 -!- lambdabot has joined.
18:40:46 -!- boily has quit (Quit: Poulet!).
18:58:14 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:05:04 <zzo38> Did you look at Nock? (there is now an article on esolang wiki, and a talk page with a comment on it)
19:15:12 -!- Slereah_ has joined.
19:17:55 -!- MoALTz__ has quit (Quit: Leaving).
19:25:15 -!- Slereah has joined.
19:25:57 -!- Slereah_ has quit (Ping timeout: 250 seconds).
19:43:48 <HackEgo> eta-julinersuscoin arcallyidocoin unshicoin stanacoin trocoin inforkcoin ringvilcoin unlamcoin crambdcoin uncecoin hcmoncoin keliucoin briacoin blocoin msglecoin wobtucoin kimossercoin waiperlinecoin ennecoin etchellcoin
19:44:01 <fizzie> The first one sounds good.
19:45:44 <HackEgo> puscoin varscoin härtatcoin äkterskådandlatcoin böncoin bestallatcoin opencoin livitcoin uddeställcoin avböjtscoin frisioneracoin tonårcoin återscoin stancoin kokosympacoin omväxlincoin natikuslingcoin gunviscoin elväggnacoin ausarnacoin
19:45:50 <HackEgo> /usr/bin/tail: option used in invalid context -- 1
19:46:37 <olsner> two of those were beancoin and teenagecoin in swedish
19:47:27 <olsner> deniedcoin/rejectedcoin too
19:47:48 <HackEgo> mattomuutomimpänäcoin kireammecoin läpäivässännecoin persovemacoin loppiincoin humistävänäncoin tuneimpinallecoin seksennecoin upottelicoin herkkostansacoin kivaimpianicoin innöiltacoin kailemmecoin puuteleviävistäsicoin joutsuttavammottuvistacoin kiipeimmiltacoin alustammecoin oikografisimmassacoin havastustamincoin pöydäntegiasicoin
19:48:44 <int-e> `coins --klingon 20
19:52:54 <HackEgo> babiliocoin nanisercoin desgotricanglecoin recencoin glriencoin lyeaucoin mbuscoin repréexprivacoin cudentcoin trèsfactécoin lilécoin regacoin siminuovecoin tewarolencoin procoin uivcoin clorescoin dêlecoin édouvecoin pérecoin
19:53:03 <fizzie> "2379071488 bytes (2.4 GB) copied, 22536.1 s, 106 kB/s" fastest CF card in the West
19:54:12 <olsner> only 13.6GB left of the 16GB card then?
19:55:49 -!- nucular has quit (Quit: Switching to phone).
19:56:21 -!- Sgeo|iPad has joined.
19:57:13 <Sgeo|iPad> Stupidly went to another town' s AT&T store without my computer to wait two hours for my phone to be repaired
19:59:10 <Bike> at&t store, that exists?
19:59:58 <Sgeo|iPad> Yes. There's one near where I live and one in this other town that is an expensive cab ride away
20:04:18 <fizzie> olsner: Something like that. I had to stop temporarily to reboot.
20:04:50 <lexande> Sgeo|iPad: what was wrong with the one where you live?
20:04:55 <fizzie> olsner: (Also for some reason the new 3.13.x kernel Debian had installed hangs in the "waiting for /dev to be fully populated..." at boot; the old 3.12.x worked.)
20:05:12 <Sgeo|iPad> They directed me to come to this one
20:05:16 <fizzie> (Today's apparently the National Computer Problems Day.)
20:05:32 <Sgeo|iPad> With them overnight which I didn't want to do
20:11:50 -!- Sgeo|iPad has quit (Quit: Page closed).
20:12:35 -!- tromp_ has quit.
20:19:18 -!- aergus has joined.
20:26:31 -!- Slereah_ has joined.
20:28:21 -!- Slereah has quit (Ping timeout: 250 seconds).
20:42:55 -!- heroux has quit (Ping timeout: 252 seconds).
20:43:25 <int-e> fizzie: isn't the "problems" redundant there?!
20:48:00 -!- heroux has joined.
20:49:29 <fizzie> I guess so. After all, "computer" is a Navajo word meaning "the cause of problems". (Not true.)
20:51:42 <fizzie> Ut oh, now the CF card reading has stopped.
20:56:39 <Taneb> Help I accidentally qualified for the google code jam
20:56:44 <Taneb> None of you make the joke please
21:01:06 -!- tromp has joined.
21:02:33 <int-e> Taneb: damn. what joke?
21:03:34 <Taneb> "is it good on code toast"/"i prefer code marmalade" etc
21:03:58 <Sgeo> Didn't get phone fixed
21:04:08 <int-e> ah. food programming. spaghetti code.
21:04:12 <Sgeo> They said need to order a new part to do it safely
21:04:47 <Sgeo> I don't feel like ordering a new part, going to some place again, blah
21:04:53 <Sgeo> Might just buy a new phone
21:05:06 <Sgeo> But I don't want to get into the habit of buying a phone just because the old one broke slightly
21:06:21 -!- tromp has quit (Ping timeout: 276 seconds).
21:11:57 -!- Koen_ has joined.
21:12:11 -!- Koen_ has quit (Remote host closed the connection).
21:24:00 -!- tromp_ has joined.
21:50:19 -!- oerjan has joined.
21:51:18 -!- Patashu has joined.
21:56:15 <oerjan> <Sgeo> Ok, seeing the reactive-banana guy act like an idiot makes me sad <-- yeah people who aren't perfect all the time are so stupid
21:56:42 <oerjan> (i noticed those comments too btw.)
21:57:39 -!- Patashu[Zzz] has joined.
21:57:39 -!- Patashu has quit (Disconnected by services).
22:06:51 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
22:06:53 <oerjan> * int-e ponders compiling a couple more ghcs <-- what, are you updating lambdabot to 6.8.2 already? :)
22:07:28 <elliott> I think 6.8.2 was the first GHC version I used.
22:07:35 -!- AnotherTest has quit (Ping timeout: 250 seconds).
22:09:41 <int-e> oerjan: already done
22:10:08 <int-e> 19:32:27 --- lambdabot has quit [Quit: 7.8.1 -> 7.8.2]
22:10:58 <oerjan> i vaguely recall lambdabot used to be several versions behind
22:11:00 <int-e> I was amazed, all dependencies already worked, I only had to patch lambdabot itself.
22:12:03 <oerjan> they seem to be getting good at updating packages for big releases
22:12:06 <int-e> there was only this small problem related to role annotations: https://github.com/int-e/lambdabot/commit/dc7ee36480a3e2b4e1b25d0022de72b764029bf7
22:13:36 <int-e> (I'm waiting for somebody to figure out that not being able to infer a representational role for the return value of monad transformers is actually quite annoying.)
22:13:44 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39300&oldid=39299 * Zerk * (+2358) Examples!
22:14:02 <int-e> well, s/monad transformer/concrete monad stack/
22:14:59 <oerjan> int-e: hm indeed, i'd have expected m to have the nominal role if any?
22:15:13 <oerjan> not that i really understand roles yet
22:15:21 <int-e> (Oh. LB a = StateT State IO a, for some datatype State)
22:15:35 <int-e> I want a to be representational there.
22:16:26 <int-e> And it's not because the monad transformer uses 'm a' for unknown 'm', forcing the argument to be nominal (that's the only safe choice in general).
22:16:59 <oerjan> you can't force m to be representational instead?
22:17:09 -!- aergus has quit (Read error: Connection reset by peer).
22:17:30 <oerjan> or maybe they simplified the role system so much they cannot express that.
22:17:35 <int-e> hmm. what do roles even mean for things of kind other than *?
22:17:43 <int-e> (i.e. plain types)
22:18:14 <int-e> or perhaps more relevantly, what does m ~ n mean if m,n : * -> *?
22:18:14 <oerjan> i'd imagine that it should mean that m is something that is representational if its argument is
22:20:06 <oerjan> i suppose they'll be forced to implement role polymorphism eventually >:)
22:22:00 <elliott> int-e: you changed lim80! the end of an era
22:22:40 <elliott> the two-space days are over.
22:22:44 <elliott> oerjan: lambdabot's output limiting command
22:22:57 <oerjan> right, i thought he did that a while ago
22:23:05 <elliott> oerjan: it's the thing that makes lambdabot cut off > [1..] far too early, but lets you flood the channel with N lines of error.
22:23:11 <int-e> elliott: but you get 80 characters on each line!
22:23:25 <int-e> rather than 80, total.
22:23:27 <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,...
22:23:35 -!- idris-ircslave has quit (Quit: Terminated).
22:23:49 <elliott> int-e: now just rewrite @run to use repl and support user-local definitions and you'll be ahead of not only what I actually did, but my plans as well.
22:25:11 <int-e> elliott: that sounds like work though
22:25:26 <elliott> int-e: but it was sooooo fast
22:25:34 <elliott> and soooo brittle. so many ways to crash that thing
22:26:43 <HackEgo> [wiki] [[Talk:Smartboxes]] M http://esolangs.org/w/index.php?diff=39301&oldid=39298 * Doesthiswork * (+866)
22:26:49 <int-e> oerjan: I did that in December last year.
22:27:03 <oerjan> yep, that's a while ago ok
22:27:26 <elliott> yeah, but I didn't look at the log until now.
22:27:56 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
22:28:08 <int-e> elliott: the branch I'm actually using is called 'config' btw. that's where all the nasty changes are hidden.
22:28:17 <int-e> (like this change to @faq)
22:28:33 <elliott> I think you should upstream config stuff
22:28:47 <elliott> there's no reason the default config and rc and stuff \bot ships with should differ from what actually runs on lambdabot
22:29:21 <int-e> I have to admit that the actual configuration is not even checked in. I should really do that.
22:29:51 <int-e> (and I have to clean up the utf8 changes very slightly and put them on master)
22:30:27 <elliott> oh, you ported it to UTF-8?!?!
22:30:38 <elliott> I started to do that but it was such a massive effort to untangle what's really a bytestring and what's really text
22:30:51 <elliott> at one point @run was broken because of double-encoding or something like that
22:31:11 <int-e> elliott: not really. ghc-7.8 now uses utf-8 quotes ...
22:31:31 <int-e> like there. so I patched @eval and @type where it leaked through
22:31:39 <elliott> no, @eval is something else entirely :)
22:31:48 <elliott> (it should stop being something else entirely and become @run instead)
22:31:57 <elliott> (well, it's more like nothing else entirely.)
22:32:08 <int-e> I know, but I will probably continue to mix them up.
22:32:24 <lambdabot> eval provides: run let define undefine
22:33:30 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39302&oldid=39301 * Zerk * (+222) /* Implicit evaluation */
22:34:03 <HackEgo> [wiki] [[Talk:Smartboxes]] M http://esolangs.org/w/index.php?diff=39303&oldid=39302 * Zerk * (+73) Forgot to sign
22:41:59 <int-e> elliott: https://github.com/int-e/lambdabot/commit/e4c4c70c41f79d497bc59e381552d5b6b3c44d38 is the actual configuration
22:42:07 <int-e> (you may like the scripts)
22:42:42 <elliott> wow, you refactored it and everything.
22:43:26 <elliott> is the nickserv password still, erm, *that*?
22:43:44 <int-e> I think so. There was no reason to change it.
22:44:24 <int-e> yes, I refactored online.rc, because I actually have two of them, one using a DNS name for freenode, and the other using an IP. I grew tired of keeping them in sync.
22:44:42 <elliott> as in, what's the point of the IP one?
22:44:51 <int-e> IP works better when Freenode is under DDoS attack
22:45:10 <elliott> it should support a list of addresses for a server :)
22:46:10 <int-e> And the screen session setup should actually be invoked automatically when the server reboots. I have not tested that though.
22:46:24 <elliott> int-e: incidentally, what with the rate of owner turnover, I think lambdabot's 100% loyalty rating could use a reassessment.
22:47:18 <elliott> int-e: make it pick a random number on startup!
22:47:41 <elliott> just move that into an -e rather than the .rc.
22:50:15 <olsner> hmm, I wonder if I have a binary clock, or if I'm remembering someone else's
22:50:17 <int-e> I guess laziness and purity wins that fight: It has already been evaluated to 100%, it'll stay that way.
23:10:20 <int-e> shachaf: ^^^ HTTP does not support https out of the box, but at least it does not error out anymore.
23:36:25 <HackEgo> [wiki] [[User:Doesthiswork]] http://esolangs.org/w/index.php?diff=39304&oldid=39292 * Oerjan * (+1) I don't normally edit user pages but that's a broken link.
23:49:07 -!- Tritonio1 has joined.
23:49:16 -!- Slereah_ has quit (Ping timeout: 245 seconds).
23:50:39 -!- Sprocklem has joined.
23:51:30 -!- idris-ircslave has joined.
23:52:06 -!- Tritonio has quit (Ping timeout: 276 seconds).
23:58:18 -!- xpte has joined.
00:18:13 -!- nooodl has quit (Quit: Leaving).
00:18:30 -!- nooodl has joined.
00:21:30 -!- Tritonio1 has quit (Ping timeout: 240 seconds).
00:22:52 -!- Tritonio has joined.
00:23:12 -!- tromp has joined.
00:25:06 -!- Frooxius has quit (Ping timeout: 240 seconds).
00:25:07 <zzo38> Many text adventure games use a virtual machine, which is then run in the interpreter. I have a bit different idea, to instead make a intermediate code, which is then compiled by the OEM into the proper code for the machine and then put into a disk, tape, ROM cartridge, or internet. Probably it would run faster like that and possibly smaller file too.
00:25:33 <zzo38> So, it is compiled into a 6502 code, x86 code, or possibly even a C code.
00:25:53 <pikhq> I imagine it wouldn't matter too much though -- zcode tends to be pretty swift on most platforms. :)
00:30:29 <zzo38> Yes, it is; I have written interpreters for Z-code.
00:32:24 <zzo38> There is, though, also TADS, Glulx, Level 9 A-code, OASYS, and others. (I have worked with OASYS, too; it is designed to be interpreted but could be compiled too due to its Restricted-Harvard format.)
00:34:23 <zzo38> But most of them have some complexity involved, so a simpler format can be made, and make it fit on smaller ROM cartridges. Some older computers don't have lowercase, and omit some other ASCII characters too; using only uppercase and also improve text compression. (Z-machine version 3 can run on uppercase-only computers, but mixed-case text is still needed in the story file.)
00:36:05 <pikhq> Are you familiar with Linus Akesson's Zeugma?
00:36:11 <zzo38> Yes, I know of it.
00:36:30 <zzo38> I also, made part of a Z-machine interpreter for Famicom, myself.
00:36:45 <zzo38> (which isn't tested and probably contains many errors)
00:38:26 <zzo38> Here is the entire code so far of Famicom Z-machine: http://wiki.nesdev.com/w/index.php/User:Zzo38/Famicom_Z-machine
00:39:18 <zzo38> I believe Zeugma is for version 4, 5, 8. My program is for version 1, 2, 3.
00:41:26 <zzo38> Many Z-machine interpreters contain errors.
00:41:40 <zzo38> Hardly any implements permanent shifts correctly.
00:43:06 <pikhq> How many examples of version 1-3 Z-code are there?
00:43:26 <pikhq> Small handful of early Infocom games?
00:44:01 <zzo38> There are many, actually.
00:44:11 <zzo38> I think most Infocom games are version 3
00:45:18 -!- nooodl has quit (Quit: Leaving).
00:45:44 -!- nooodl has joined.
00:49:02 <zzo38> Tell me if you find my program to be OK and/or anything you think is wrong with it, please.
00:54:38 <zzo38> A compiled system would probably work better though, especially if it is far simpler than Z-machine.
00:55:51 -!- adu has joined.
01:00:42 -!- nisstyre has joined.
01:02:56 <zzo38> How many different SQL "CREATE FUNCTION" syntaxes are there?
01:03:59 -!- oerjan has quit (Quit: Night).
01:06:25 <zzo38> There seems to be a lot of different ones, and there are more differences when aggregate functions are involved too.
01:10:45 -!- Sorella has quit (Ping timeout: 276 seconds).
01:13:43 -!- tromp has quit (Remote host closed the connection).
01:21:43 <Sgeo> http://arstechnica.com/information-technology/2012/01/microsoft-pimps-it-old-school-with-a-pricey-text-adventure-game/
01:24:16 <Bike> this is disappointing.
01:31:57 -!- drlemon has quit (Read error: Connection reset by peer).
01:32:00 -!- drlemon_ has joined.
01:56:46 -!- Tritonio has quit (Ping timeout: 245 seconds).
01:59:30 -!- adu has quit (Quit: adu).
02:06:57 -!- adu has joined.
02:09:46 -!- conehead has quit (Quit: Computer has gone to sleep).
02:26:29 -!- SleepyPikachu has joined.
02:26:45 -!- SleepyPikachu has quit (Quit: leaving).
02:42:47 <Sgeo> I'm guess Erlang is a language that you don't want to use as just a general make-yourself-a-better-programmer language? At least, I have a feeling that let-it-crash may be a bad idea to bring into non-Erlang ecosystems
02:43:18 <kmc> i'm a pretty big fan of let-it-crash tbh
02:43:33 <Sgeo> But does that work outside of Erlang?
02:44:25 <kmc> you can design systems that way in any language(s)
02:44:29 <kmc> erlang may make it easier
02:44:39 <kmc> functional programming in C is also quite popular
02:45:52 <Sgeo> Maybe I should get more understanding of let it crash
02:46:16 <Sgeo> I guess a cryptographic primitive that fails quickly and blatantly if a precondition isn't met is an example?
02:46:23 <kmc> well i don't know the finer points of it eithe
02:46:30 <kmc> Rust lost linked task failure :/
02:46:34 <zzo38> Functional programming in C? But, then you would need a user-parameter.
02:46:37 <kmc> it's a real pita
02:46:45 <Bike> i just imagine myself standing over a flaming computer and laughing
02:46:47 <kmc> zzo38: yeah, and void* user parameters are quite popular
02:46:53 <Bike> YOU GOT WHAT YOU DESERVED
02:46:57 <kmc> although it's kind of a joke to call that functional programming
02:47:12 <kmc> people don't much write higher order combinators around their closure structs in C
02:47:19 <kmc> even people who went to MIT
02:47:24 <zzo38> kmc: Yes, a lot of SQLite API functions that will call back functions, will have void* user parameters.
02:47:55 <zzo38> I know it isn't real functional programming, but it would be one thing you would require, if you are to start trying to make functional programming in a C code.
02:52:15 <HackEgo> [wiki] [[Special:Log/newusers]] create * Extwo * New user account
02:58:53 <zzo38> And still it isn't quite real function programming; functional programming isn't a C code anyways!
03:04:07 <Bike> the functional programming that can be spoken of is not the true functional programming
03:04:54 <zzo38> Now I made this "text adventure intermediate language". It has 36 opcodes (actually, 90 if you count the operand size bits), although some don't need to be implemented. It is possible for SAVE, LPTON, LPTOFF, PICTURE to all be no-operations; it is OK for QUIT and RESET to have the same operation as each other, and if SAVE isn't implement, RESTORE? can act the same as JUMP.
03:06:33 <zzo38> Binary and decimal numbers are treated differently, for compatibility with computers where such a thing would help. The high bit of a variable number is set to use that variable as a decimal number (although it takes up the same memory as the binary variables).
03:33:01 -!- drlemon_ has quit (*.net *.split).
03:33:02 -!- jconn has quit (*.net *.split).
03:33:04 -!- nisstyre has quit (*.net *.split).
03:33:04 -!- tromp_ has quit (*.net *.split).
03:33:04 -!- heroux has quit (*.net *.split).
03:33:04 -!- Melvar has quit (*.net *.split).
03:33:05 -!- zzo38 has quit (*.net *.split).
03:33:05 -!- TodPunk has quit (*.net *.split).
03:33:05 -!- shachaf has quit (*.net *.split).
03:33:06 -!- applybot has quit (*.net *.split).
03:33:06 -!- jix has quit (*.net *.split).
03:33:06 -!- newsham has quit (*.net *.split).
03:33:06 -!- quintopia has quit (*.net *.split).
03:33:06 -!- maurer has quit (*.net *.split).
03:33:07 -!- realzies has quit (*.net *.split).
03:33:08 -!- idris-ircslave has quit (*.net *.split).
03:33:09 -!- CapitalSigma has quit (*.net *.split).
03:33:10 -!- myndzi has quit (*.net *.split).
03:33:11 -!- Taneb has quit (*.net *.split).
03:33:11 -!- ejls has quit (*.net *.split).
03:33:11 -!- clog has quit (*.net *.split).
03:33:11 -!- mroman has quit (*.net *.split).
03:33:12 -!- Gracenotes has quit (*.net *.split).
03:33:13 -!- douglass_ has quit (*.net *.split).
03:33:13 -!- vravn has quit (*.net *.split).
03:33:14 -!- ggherdov has quit (*.net *.split).
03:33:14 -!- JZTech101 has quit (*.net *.split).
03:33:14 -!- nortti has quit (*.net *.split).
03:33:15 -!- adu has quit (*.net *.split).
03:33:15 -!- nooodl has quit (*.net *.split).
03:33:16 -!- Sgeo has quit (*.net *.split).
03:33:17 -!- fizzie has quit (*.net *.split).
03:33:18 -!- Jafet has quit (*.net *.split).
03:33:18 -!- HackEgo has quit (*.net *.split).
03:33:19 -!- int-e has quit (*.net *.split).
03:33:19 -!- elliott has quit (*.net *.split).
03:33:19 -!- Speed` has quit (*.net *.split).
03:33:19 -!- Sprocklem has quit (*.net *.split).
03:33:20 -!- Patashu[Zzz] has quit (*.net *.split).
03:33:20 -!- copumpkin has quit (*.net *.split).
03:33:21 -!- Bike has quit (*.net *.split).
03:33:22 -!- Sellyme has quit (*.net *.split).
03:33:22 -!- lambdabot has quit (*.net *.split).
03:33:22 -!- olsner has quit (*.net *.split).
03:33:23 -!- augur has quit (*.net *.split).
03:33:23 -!- jhj1 has quit (*.net *.split).
03:33:23 -!- myname has quit (*.net *.split).
03:33:25 -!- FireFly has quit (*.net *.split).
03:33:25 -!- aloril has quit (*.net *.split).
03:33:25 -!- atehwa has quit (*.net *.split).
03:33:26 -!- b_jonas has quit (*.net *.split).
03:33:26 -!- lifthrasiir has quit (*.net *.split).
03:33:27 -!- rodgort has quit (*.net *.split).
03:33:27 -!- kmc has quit (*.net *.split).
03:33:27 -!- ion has quit (*.net *.split).
03:33:27 -!- monotone has quit (*.net *.split).
03:33:27 -!- EgoBot has quit (*.net *.split).
03:33:27 -!- ineiros has quit (*.net *.split).
03:33:28 -!- lexande has quit (*.net *.split).
03:33:28 -!- sebbu has quit (*.net *.split).
03:33:29 -!- xpte has quit (*.net *.split).
03:33:29 -!- erdic has quit (*.net *.split).
03:33:31 -!- pikhq has quit (*.net *.split).
03:33:32 -!- coppro has quit (*.net *.split).
03:33:34 -!- ^v has quit (*.net *.split).
03:33:34 -!- Vorpal has quit (*.net *.split).
03:33:36 -!- Gregor has quit (*.net *.split).
03:33:36 -!- fungot has quit (*.net *.split).
03:33:36 -!- hexagon has quit (*.net *.split).
03:33:37 -!- hogeyui has quit (*.net *.split).
03:33:37 -!- SirCmpwn has quit (*.net *.split).
03:33:38 -!- Deewiant has quit (*.net *.split).
05:16:46 -!- coppro has joined.
05:16:46 -!- douglass_ has joined.
05:16:46 -!- Gracenotes has joined.
05:16:46 -!- mroman has joined.
05:16:46 -!- clog has joined.
05:16:46 -!- ejls has joined.
05:16:46 -!- Taneb has joined.
05:16:46 -!- Bike has joined.
05:16:46 -!- copumpkin has joined.
05:16:46 -!- Patashu[Zzz] has joined.
05:16:46 -!- Sprocklem has joined.
05:16:46 -!- pikhq has joined.
05:16:46 -!- lambdabot has joined.
05:16:46 -!- olsner has joined.
05:16:46 -!- augur has joined.
05:16:46 -!- jhj1 has joined.
05:16:46 -!- myname has joined.
05:16:46 -!- FireFly has joined.
05:16:46 -!- glogbackup has joined.
05:16:46 -!- int-e has joined.
05:16:46 -!- drlemon_ has joined.
05:16:46 -!- jconn has joined.
05:16:46 -!- `^_^v has joined.
05:16:46 -!- ^v has joined.
05:16:46 -!- Vorpal has joined.
05:16:46 -!- Gregor has joined.
05:16:46 -!- fungot has joined.
05:16:46 -!- hexagon has joined.
05:16:46 -!- hogeyui has joined.
05:16:46 -!- SirCmpwn has joined.
05:16:46 -!- Deewiant has joined.
05:16:52 -!- adu has joined.
05:16:53 -!- nooodl has joined.
05:16:53 -!- Sgeo has joined.
05:16:53 -!- fizzie has joined.
05:16:54 -!- ineiros has joined.
05:16:54 -!- lexande has joined.
05:16:54 -!- sebbu has joined.
05:18:07 -!- elliott has joined.
05:18:07 -!- tromp has joined.
05:18:07 -!- idris-ircslave has joined.
05:18:27 -!- erdic has joined.
05:18:28 -!- CapitalSigma has joined.
05:18:28 -!- myndzi has joined.
05:18:40 -!- HackEgo has joined.
05:18:40 -!- nisstyre has joined.
05:18:40 -!- tromp_ has joined.
05:18:40 -!- heroux has joined.
05:18:40 -!- Melvar has joined.
05:18:40 -!- zzo38 has joined.
05:18:40 -!- TodPunk has joined.
05:18:40 -!- shachaf has joined.
05:18:40 -!- jix has joined.
05:18:40 -!- newsham has joined.
05:18:40 -!- quintopia has joined.
05:18:40 -!- maurer has joined.
05:18:40 -!- realzies has joined.
05:18:44 -!- vravn has joined.
05:18:44 -!- ggherdov has joined.
05:18:44 -!- JZTech101 has joined.
05:18:44 -!- nortti has joined.
05:21:35 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:31:21 -!- Sellyme has joined.
05:31:22 -!- Speed` has joined.
05:31:22 -!- aloril has joined.
05:31:22 -!- atehwa has joined.
05:31:22 -!- b_jonas has joined.
05:31:22 -!- lifthrasiir has joined.
05:31:22 -!- kmc has joined.
05:31:22 -!- ion has joined.
05:31:22 -!- EgoBot has joined.
05:37:56 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39305&oldid=39300 * Zerk * (-1) /* Standard Library */ syntax
05:38:17 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39306&oldid=39303 * Doesthiswork * (+541)
05:54:09 -!- rodgort has joined.
06:02:37 -!- nooodl has quit (Remote host closed the connection).
06:08:50 -!- zzo38 has quit (Remote host closed the connection).
06:16:06 -!- Sprocklem has quit (Quit: leaving).
06:16:29 <Sgeo> I think I want to know the context of every line of the Picard Song
06:37:42 -!- oklopol has joined.
07:02:13 -!- MoALTz has joined.
07:04:29 -!- Patashu has joined.
07:07:36 -!- Patashu[Zzz] has quit (Ping timeout: 258 seconds).
07:15:22 -!- Slereah_ has joined.
07:18:54 -!- elliott has changed nick to Guest46968.
07:30:45 -!- erdic has quit (Changing host).
07:30:45 -!- erdic has joined.
07:35:29 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
07:36:59 -!- Slereah_ has quit (Ping timeout: 250 seconds).
07:48:34 -!- nooodl has joined.
07:48:49 -!- Slereah_ has joined.
07:55:07 -!- AnotherTest has joined.
08:07:36 -!- Frooxius has joined.
08:14:41 -!- Slereah_ has quit (Ping timeout: 250 seconds).
08:18:27 -!- Patashu has quit (Ping timeout: 276 seconds).
08:21:24 -!- Jafet has joined.
08:23:55 -!- applybot has joined.
08:25:32 -!- password2 has joined.
09:18:15 -!- Sellyme has quit (*.net *.split).
09:18:15 -!- Speed` has quit (*.net *.split).
09:18:16 -!- aloril has quit (*.net *.split).
09:18:16 -!- atehwa has quit (*.net *.split).
09:18:17 -!- b_jonas has quit (*.net *.split).
09:18:17 -!- lifthrasiir has quit (*.net *.split).
09:18:18 -!- kmc has quit (*.net *.split).
09:18:18 -!- ion has quit (*.net *.split).
09:18:18 -!- EgoBot has quit (*.net *.split).
09:19:45 -!- Sellyme has joined.
09:19:46 -!- Speed` has joined.
09:19:46 -!- aloril has joined.
09:19:46 -!- atehwa has joined.
09:19:46 -!- b_jonas has joined.
09:19:46 -!- lifthrasiir has joined.
09:19:46 -!- kmc has joined.
09:19:46 -!- ion has joined.
09:19:46 -!- EgoBot has joined.
09:22:30 -!- conehead has joined.
09:31:44 <fizzie> olsner: STATUS UPDATE: 6011486208-byte partition sde2 extracted successfully overnight; turned out to be the / partition; had the crontab I was looking for, but scripts were in /home/foo for a system user foo, in flagrant disregard of FHS; now reading the rest.
09:33:25 <fizzie> (Disclaimer: I don't know if FHS really says anything about that, but I imagine it might.)
09:35:41 -!- Slereah_ has joined.
09:50:10 -!- adu has quit (Quit: adu).
09:59:44 -!- MindlessDrone has joined.
10:06:14 -!- password2 has quit (Remote host closed the connection).
10:09:55 -!- password2 has joined.
10:20:00 -!- Patashu has joined.
10:25:31 -!- Patashu[Zzz] has joined.
10:25:31 -!- Patashu has quit (Disconnected by services).
10:28:52 -!- Patashu has joined.
10:31:58 -!- Patashu[Zzz] has quit (Ping timeout: 245 seconds).
10:34:03 -!- Slereah_ has quit (Ping timeout: 245 seconds).
10:34:24 -!- Patashu[Zzz] has joined.
10:34:24 -!- Patashu has quit (Disconnected by services).
10:39:37 -!- password2 has left ("Leaving").
10:39:51 -!- Patashu has joined.
10:43:13 -!- Patashu[Zzz] has quit (Ping timeout: 245 seconds).
10:46:33 -!- Patashu has quit (Ping timeout: 245 seconds).
10:48:24 -!- Patashu has joined.
10:51:40 -!- Patashu[Zzz] has joined.
10:51:40 -!- Patashu has quit (Disconnected by services).
10:56:05 -!- Patashu[Zzz] has quit (Client Quit).
11:05:31 -!- yorick has joined.
11:08:33 -!- oerjan has joined.
11:14:33 -!- Slereah_ has joined.
11:14:44 -!- boily has joined.
11:15:01 -!- Patashu has joined.
11:16:55 <oerjan> @tell zzo38 <zzo38> [...] SAVE, LPTON, LPTOFF, PICTURE <-- you need a HDRON too hth
11:17:26 <oerjan> lambdabot: you seem slow.
11:18:07 <oerjan> i know it is evil to pun zzo but i couldn't resist
11:19:21 <oerjan> BRYON and MSON are optional.
11:20:01 -!- Patashu[Zzz] has joined.
11:20:02 -!- Patashu has quit (Disconnected by services).
11:21:17 <myname> sounds a bit like barking
11:21:50 <int-e> oerjan: it's hard to tell who is slow on IRC
11:22:21 <int-e> (from here, the @tell and lambdabot's reply both had timestamp 13:16:55)
11:22:27 <oerjan> hm there's a big split gap in the logs
11:23:00 <Jafet> Someone spammed freenode.
11:25:10 <int-e> oh. impressive spew of k-lines.
11:26:53 <Jafet> Yes. In other big news, Afghanistan held presidential elections for the first time in modern history.
11:32:42 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
11:35:18 -!- Patashu[Zzz] has quit (Ping timeout: 245 seconds).
11:36:21 -!- Patashu has joined.
11:36:39 -!- Patashu has quit (Client Quit).
11:37:49 <oerjan> hm clog and glogbot were in different fragments but neither registered any talking. almost everyone who split split from both.
11:38:33 <oerjan> 20:36:03 --- quit: drlemon_ (*.net *.split)
11:38:34 <oerjan> 20:36:04 --- quit: jconn (*.net *.split)
11:38:34 <oerjan> 20:36:07 --- quit: impomatic (*.net *.split)
11:38:34 <oerjan> 20:36:08 --- quit: trout (*.net *.split)
11:38:34 <oerjan> 20:36:08 --- quit: scoff (*.net *.split)
11:38:36 <oerjan> 20:36:09 --- quit: glogbot (*.net *.split)
11:38:38 <oerjan> 20:36:11 --- quit: nisstyre (*.net *.split)
11:38:41 <oerjan> 20:36:11 --- quit: tromp_ (*.net *.split)
11:38:43 <oerjan> 20:36:11 --- quit: heroux (*.net *.split)
11:38:46 <oerjan> 20:36:11 --- quit: Melvar (*.net *.split)
11:38:48 <oerjan> 20:36:12 --- quit: zzo38 (*.net *.split)
11:38:51 <oerjan> 20:36:12 --- quit: TodPunk (*.net *.split)
11:38:53 <oerjan> 20:36:13 --- quit: shachaf (*.net *.split)
11:38:54 -!- ChanServ has set channel mode: +o fizzie.
11:38:56 <oerjan> 20:36:14 --- quit: applybot (*.net *.split)
11:38:58 <oerjan> 20:36:15 --- quit: jix (*.net *.split)
11:39:00 -!- fizzie has set channel mode: +q oerjan!*@*.
11:39:08 <fizzie> (I assume a mispaste.)
11:39:19 <fizzie> Let's see if the faucet is still on.
11:39:20 -!- fizzie has set channel mode: -q oerjan!*@*.
11:39:21 <oerjan> 20:36:23 --- quit: ggherdov (*.net *.split)
11:39:23 -!- oerjan has left.
11:39:47 -!- fizzie has set channel mode: -o fizzie.
11:40:24 -!- oerjan has joined.
11:40:28 <oerjan> i hope parting flushed that buffer
11:40:39 <oerjan> i have no idea what command does it.
11:41:01 <oerjan> i thought irssi was supposed to have protection against this D:
11:41:37 <oerjan> also this touchpad is evil hth
11:41:37 <fizzie> It is supposed to ask, but sometimes (if there's SSH lag or something) it doesn't realize.
11:42:20 <fizzie> Since the protection is based on "N lines in K units of time" kind of rules.
11:42:30 <oerjan> hm i think i planned to increase that timeout once.
11:43:08 <fizzie> [14:43:16] paste_detect_time = 5msecs
11:43:08 <Jafet> freenode probably throttles input.
11:43:12 <fizzie> That's, like, 1499 km in speed-of-light terms.
11:43:54 <Jafet> Ah, good ol' zeroth order models.
11:43:54 <oerjan> it was 10 msecs i now increased it to 100
11:45:04 <oerjan> i doubt i manage to type a normal line in less than 0.1 s
11:46:20 <oerjan> fizzie: i had just copied and pasted that long list into vim to compare clog's view with glogbot's.
11:47:50 <oerjan> Jafet: i'm pretty sure there was an election for karzai's second term? but this may have been the first time they handled it themselves.
11:48:18 <Jafet> Actually, there were two elections, but people didn't seem to like those very much.
11:52:05 <oerjan> (incidentally the only ones not split from clog were Gracenotes Taneb clog douglass_ ejls mroman, and the only ones not split from glogbot were glogbot impomatic scoff trout.
11:55:33 <int-e> I was asleep, hth.
11:55:59 <oerjan> int-e: you were in both lists.
11:56:23 <Jafet> I believe int-e's alibi.
12:00:51 <impomatic> IRC alerted me so I zoomed across here in case everyone's talking about Core War or something :-D
12:01:32 <oerjan> sorry it was just clog war
12:02:30 <impomatic> I'll just mention this before I have lunch :-P http://corewar.co.uk/spring2014.htm
12:03:27 <impomatic> Oh also if you're interested in the history of worms / viruses I've found a description of one which possibly predates Creeper.
12:04:41 <lambdabot> Local time for oerjan is Sun Apr 13 14:04:41 2014
12:05:58 <int-e> 05:38:35 --- [Users #esoteric]
12:05:58 <int-e> 05:38:35 --> drlemon_ int-e jconn
12:06:22 <oerjan> that "but the program must still behave essentially the same" sounds rather subjective for a computer tournament...
12:06:25 <int-e> 05:40:24 --- glogbackup has joined #esoteric
12:06:57 <int-e> and then people started coming back 07:12:11 (all CET). That's my view of the netsplit.
12:07:28 <oerjan> rather fine fragments, i take.
12:09:37 <oerjan> glogbot split a bit earlier and rejoined a little later. tunes still hasn't fixed its broken clock.
12:09:42 <olsner> boily: btw UPPHETTA means to heat up (something)
12:09:56 <oerjan> olsner: what, with two t's?
12:10:14 <olsner> what other number of t's could there be?
12:10:29 <oerjan> one like in norwegian? (and english for that matter)
12:10:36 <int-e> well, "other", so one or three ;)
12:11:14 <int-e> "aufheizen" has no t at all (though you can count the implied one in the 'z')
12:12:40 <olsner> well, literally... hood would probably be sv:huva nowadays
12:14:20 <oerjan> that's what hue means in my dialect, although standard norwegian is lue.
12:15:08 <oerjan> actually more like huæ.
12:18:15 <oerjan> "The thin atmosphere prevents Mars from retaining any heat energy, so temperatures near the equator can get up to 70 degrees F during a summer day, and then drop down to minus 100 degrees F at night."
12:18:52 <oerjan> i didn't know summer day temperatures on mars were so reasonable.
12:20:13 <boily> `frink 70 fahrenheit to celsius
12:20:16 <HackEgo> Warning: undefined symbol "fahrenheit". \ Bounds in range expression are of unsupported types: (70 fahrenheit (undefined symbol), celsius (undefined symbol)) \ at frink.expr.bh.byte(frink) \ at frink.expr.bh.evaluate(frink) \ at frink.parser.Frink.parseString(frink) \ at frink.parser.Frink.parseStrings(frink) \ at frink.parser.Frink.
12:20:26 <olsner> iirc, 70 is about room temperature
12:20:47 <boily> `` echo $(((70 - 32) * 5 / 9))
12:21:10 <boily> 21 is good. I like 21.
12:23:40 <oerjan> the time period when mars may have had water is known as the "Noachian". although the implications are somewhat dampened by it being named after the region of Noachis Terra.
12:24:39 <oerjan> istr `frink has a weird way of converting temperatures, also your syntax is wrong for ordinary units as well, it's not a bloody natural language parser.
12:25:28 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: sanetemp: not found
12:25:50 <EgoBot> sh dc -e "1k?32-5*9/p"
12:25:59 <int-e> dampened, hmm. (damp = moist)
12:27:14 <boily> oerjan: what is istr twh
12:30:20 <int-e> oh, twh is another acronym in the hth family.
12:31:49 <int-e> but does it mean "that will help" or "that won't help"? ;-)
12:31:58 <boily> that would help, iirc.
12:32:03 <HackEgo> twh would help, but is an hth derivative. hth. twh. hand.
12:32:09 <oerjan> `run (echo '#!/bin/bash'; echo 'echo "$@" | dc -e "1k?32-5*9/p"') > bin/sanetemp; chmod +x bin/sanetemp
12:32:28 <EgoBot> sh dc -e "1k?9*5/32+p"
12:32:52 <oerjan> `run (echo '#!/bin/bash'; echo 'echo "$@" | dc -e "1k?9*5/32+p"') > bin/insanetemp; chmod +x bin/insanetemp
12:34:21 <oerjan> /bin/sh on HackEgo does some bad things
12:34:39 <HackEgo> /bin/sh: symbolic link to `dash'
12:34:42 <oerjan> in particular iirc you don't want to echo user input with it.
12:35:08 <boily> `` /bin/sh echo echo
12:35:08 <HackEgo> /bin/sh: 0: Can't open echo
12:35:20 <boily> `` /bin/sh -c echo echo
12:35:35 <oerjan> it doesn't break on _all_ input, mind you.
12:35:38 <int-e> `` /bin/sh -c "echo echo"
12:36:20 <oerjan> i don't quite recall what caused the problem, but i think tabs may have been involved.
12:36:59 <boily> `` echo -e '#!/bin/sh\necho "$@"' >bin/poulet; chmod +x bin/poulet
12:37:13 <oerjan> it was when your input contained escape sequences like \n.
12:37:25 <int-e> so that's why <<< worked :)
12:37:39 <fizzie> It's kind of unclear whether "insanetemp" (resp. "sanetemp") converts from insane to sane, or the other way around.
12:37:54 <boily> `poulet somethingsomething
12:38:03 <boily> darn. the tab didn't work.
12:38:05 <oerjan> boily: it wasn't tabs, but \n
12:38:19 <boily> `poulet somethingsomething
12:38:30 <boily> int-e: I got slightly confused.
12:38:32 <oerjan> it's hard to get it passed through unchanged.
12:38:40 <boily> `poulet somethingsomething
12:39:09 * boily sucks at mental calculation and hexadecimal this morning. I deserve an automapole.
12:39:57 <oerjan> int-e: my test shows it.
12:40:02 <int-e> http://int-e.eu/~bf3/tmp/Ohlo9ru5.png - wysiwyg
12:40:30 <oerjan> boily: you know you could be saved all this work if you paid attention to my self-corrections hth
12:41:11 <int-e> (unless it adds color codes, in which case they get filtered on my end)
12:41:19 <oerjan> the problem is that the idiom of using echo "$@" to pass command args unchanged as input to a command breaks with /bin/sh
12:41:59 <oerjan> int-e: that is, it's not _supposed_ to turn that \n into a newline.
12:42:49 <int-e> oooh. I have a file called -u in my home directory, how did that happen :)
12:43:20 <int-e> some curl mishap judgring by its content (a 401 error)
12:43:43 <oerjan> hm i remember someone added a command to do this automatically...
12:43:49 <HackEgo> bin/forget \ bin/fortune \ bin/joustreport \ bin/ord \ bin/ordu \ bin/pastefortunes \ bin/print_args_or_input \ bin/rainwords \ bin/word \ bin/words
12:44:01 <oerjan> print_args_or_input, it was
12:44:26 <oerjan> boily: truth in advertising
12:44:46 -!- MoALTz has quit (Quit: bbl).
12:45:09 <int-e> oerjan: sorry. http://pubs.opengroup.org/onlinepubs/009695399/utilities/echo.html begs to differ.
12:45:23 <int-e> "the results are implementation-defined"
12:46:39 <oerjan> int-e: i'm not saying dash breaks the standard, i'm saying the standard is inconvenient.
12:49:07 <oerjan> "New applications are encouraged to use printf instead of echo."
12:49:20 <oerjan> `cat bin/print_args_or_input
12:49:21 <HackEgo> if [ "$#" -gt 0 ]; then printf '%s\n' "$*"; else cat; fi
12:50:02 <int-e> oerjan: I guess the proper solution is a here document. foo <<EOF; $@; EOF. Inconvenient indeed.
12:50:18 <int-e> (since the ; have to be actual newlines)
12:50:38 <oerjan> `run sed -i 's/echo/print_args_or_input/' bin/*sanetemp
12:50:47 <HackEgo> #!/bin/bash \ print_args_or_input "$@" | dc -e "1k?32-5*9/p"
12:51:21 <oerjan> `run echo 32 | sanetemp
12:51:29 <oerjan> now it can be used both ways
12:51:41 <int-e> bin/print_args_or_input can't be executed directly
12:51:54 <int-e> am I missing somehting?
12:52:32 <int-e> how does print_args_or_input work without a shebang line?
12:52:37 <oerjan> int-e: it's a convenience command someone made so we can easily write commands that take either stdin or cmdargs
12:53:16 <oerjan> int-e: i guess it's just run as shell commands, then.
12:53:32 <oerjan> that's it's intended use, anyway.
12:54:09 <int-e> man bash helps: "If this execution fails because the file is not in executable format, and the file is not a directory, it is assumed to be a shell script."
12:54:37 <HackEgo> dc: '(' (050) unimplemented \ dc: stack empty \ dc: ')' (051) unimplemented \ 4.4
12:55:55 <oerjan> `run sed -i '1i#!/bin/bash' bin/print_args_or_input
12:56:04 <oerjan> `cat bin/print_args_or_input
12:56:04 <HackEgo> #!/bin/bash \ if [ "$#" -gt 0 ]; then printf '%s\n' "$*"; else cat; fi
12:57:50 <oerjan> i guess dc isn't quite sane, only the temps.
12:58:08 <HackEgo> bash: ls/*temp*: No such file or directory
12:58:15 <HackEgo> bin/insanetemp \ bin/sanetemp
12:58:56 <int-e> `` echo -10 | sed 's/^/1 /;s/-/2-/' | dc -e "1k?32-5*9/p"
12:59:16 <int-e> `` echo -10 | sed 's/^/1 /;s/-/2-/' | dc -e "1k?*32-5*9/p"
12:59:22 <int-e> `` echo -40 | sed 's/^/1 /;s/-/2-/' | dc -e "1k?*32-5*9/p"
13:01:01 <int-e> `` echo -40 | dc -e "1k0 1?*32-5*9/p"
13:01:44 * oerjan happily lets int-e handle this.
13:03:20 <int-e> `` sed -i 's/k./k0 1?*/' bin/sanetemp bin/insanetemp
13:05:35 <int-e> bin/{in,}sanetemp would have been more clever.
13:12:15 -!- MoALTz has joined.
13:15:28 -!- Sorella has joined.
13:57:58 -!- monotone has joined.
14:04:01 -!- password2 has joined.
14:21:07 -!- password2 has quit (Ping timeout: 252 seconds).
14:31:29 -!- boily has quit (Quit: Poulet!).
14:37:46 -!- oerjan has quit (Quit: leaving).
14:58:38 <myname> so... sane is which one?
15:00:26 <Taneb> I presume Celsius is the sane one
15:05:08 <int-e> Rankine is the truly insane one
15:06:16 <int-e> "Kelvin had a great idea there, but clearly we should base the scale on the more familiar Fahrenheit unit instead."
15:06:25 <fizzie> How about the Rømer and Réaumur scales?
15:07:04 <fizzie> There was a giant temperature-o-meter with markings in one of those in a park somewhere in Switzerland or Italy, I took a photo of it.
15:08:25 <Slereah_> How about just an exponential scale with k = 1
15:08:57 <fizzie> (It's just Celsius except with 80 in place of 100.)
15:09:36 <int-e> right, Réaumur looks quite sane. Rømer not so much, because it seems to depend on the salt content of brine.
15:10:16 <Slereah_> Why can't we just use natural units
15:10:57 <int-e> And both are saner than Fahrenheit (coldest temperature ever encountered at home = 0 ... body temperature = 100; everybody gets their own scale that way!)
15:11:32 <int-e> like good old time, with elbow and foot lengths of the king.
15:12:02 <Slereah_> People would be always like "Hey king, can you drop by, I have stuff to measure"
15:12:25 <Jafet> That's why they're called rulers, you know
15:12:45 <int-e> (it would explain the attraction of the chinese to small feet ;-) )
15:13:06 <fizzie> Random hardware question: are there any potential issues with USB-connected SATA HD enclosures around the 2 TB barrier? (I had that 1.5 TB drive that broke, and was thinking of sticking a 3 TB drive in to replace it.)
15:13:44 <Slereah_> Jafet : Reminds me of https://images.encyclopediadramatica.es/3/39/Robotnikwood.jpg
15:14:06 <fizzie> (I would have thought we're past that kind of problems already, but in the past there's been some kind of a "barrier" at pretty much every other power of two.)
15:14:11 <Guest46968> fizzie: have to use GPT if it's partitioned, I guess?
15:15:42 <fizzie> That's probably true. Though I don't think that should be a problem, as long as there isn't anything about the USB-to-SATA bridge that would have problems.
15:15:50 <Jafet> The 2TiB barrier is not visible to SATA
15:16:07 <Guest46968> fizzie: well, I was just thinking of issues with using a drive like that in general.
15:16:27 <Jafet> The only reason people made a big deal out of it was because old BIOSes couldn't deal with 4KiB sectors
15:17:58 <fizzie> I think I had a "must upgrade disk firmware in order for it to be recognizable at all" incompatibility with these current 3TB drives in this desktop.
15:19:38 <fizzie> Oh, no, it was the 1TB Samsung HD105SI instead. And some other computer.
15:20:32 <fizzie> Well, anyway, things never work out right if there's any chance for them to go wrong, has been my general feeling about hard disks.
15:24:33 -!- Slereah_ has quit (Ping timeout: 250 seconds).
15:31:02 -!- ^v has joined.
15:39:17 -!- impomatic has quit (Ping timeout: 250 seconds).
15:44:28 -!- Slereah_ has joined.
15:55:29 -!- zzo38 has joined.
16:03:33 -!- ais523 has joined.
16:03:59 <Vorpal> fizzie, you should use a lot of smaller disks in RAID instead then?
16:05:13 <fizzie> I don't have places to put them in. Anyway, maybe it'll work.
16:05:40 <fizzie> By all means it should, anyway.
16:06:13 <ais523> huh, beautiful timing: Evolution froze up, I typed in a killall command
16:06:13 <ais523> and just before I ran the command, it crashed
16:06:16 <ais523> Vorpal: I thought the disks were meant to be inexpensive
16:06:16 <ais523> rather than, necessarily, small
16:06:30 <lambdabot> oerjan said 4h 49m 34s ago: <zzo38> [...] SAVE, LPTON, LPTOFF, PICTURE <-- you need a HDRON too hth
16:06:33 <Vorpal> ais523, you missed the context
16:06:51 <zzo38> oerjan: O, it is a joke...
16:07:03 <zzo38> Actually "LPTON" is short for "line printer on"
16:08:46 <Vorpal> ais523, I know it is ironic that I should say that yes
16:09:11 -!- callforjudgement has joined.
16:09:27 -!- ais523 has quit (Disconnected by services).
16:09:28 -!- callforjudgement has changed nick to ais523.
16:09:37 <Vorpal> <Vorpal> ais523, you missed the context <Vorpal> ais523, I know it is ironic that I should say that yes
16:16:12 <b_jonas> man, C++ is getting ever better language for obfuscations too
16:16:20 -!- impomatic has joined.
16:17:20 <ais523> yeah, C++ is pretty great for obfuscations
16:17:38 <ais523> in general, any apparently innocent line of C++ code can do pretty much anything, depending on the context
16:18:28 <ais523> unless it explicitly names a primitive data type
16:19:08 <Jafet> C is the language with apparently innocent lines. C++ is like a mob boss.
16:19:08 <b_jonas> have you noticed how lambda syntax now lets you define new variables (possibly shadowing existing ones) without ever mentioning a type name or "auto"? makes it even more difficult for a human to follow bindings.
16:20:19 <Vorpal> ais523, yes, it is pretty terrible for anything except obfuscation at this point
16:20:34 <Vorpal> At least with C++03 it wasn't /that/ bad
16:21:11 <ais523> int-e: that's the preprocessor, it doesn't count
16:21:12 <Guest46968> C++11 was an obvious improvement on C++03.
16:21:38 <newsham> bjonas: haskell lambdas dont even make you type a type name.. how evil
16:21:46 <ais523> C++11 is better at being C++ than previous versions were
16:22:19 <idris-ircslave> (input):1:1:When elaborating an application of function Prelude.Vect.++:
16:22:20 <lambdabot> Not in scope: data constructor ‘C’
16:22:20 <b_jonas> newsham: yeah, but in haskell you don't have assignments to previously declared variables either
16:22:36 <fizzie> Were user-defined literals part of C++11?
16:22:45 <b_jonas> newsham: so, like, in haskell, x = 3 always introduces a new variable x
16:22:52 <Vorpal> <Guest46968> C++11 was an obvious improvement on C++03. <-- in some respects, yes
16:22:57 <b_jonas> in C++ it's probably just an assignment to an existing x
16:23:36 <Vorpal> If you mean suffixes to numbers at least
16:23:46 <Vorpal> That I think is terrible, makes it much harder to follow
16:24:29 <Jafet> Nearly all C++03 code is valid C++11, and C++11 can do many other things. So the committee considers it an improvement.
16:24:48 <b_jonas> I consider it an improvement too
16:24:55 <b_jonas> especially because of move-return
16:24:58 <Vorpal> So... I was reading some C++ (03) code making heavy use of boost MPL the other day. Scary
16:25:03 <newsham> superset is an awesome langauge design technique!
16:25:13 <Jafet> Oh, you say you wanted a language that takes less than five years to learn properly and less than one coffee break to compile? Too bad.
16:25:25 <newsham> this tomato is really cool, now it just needs wheels!
16:26:28 <Vorpal> Jafet, the code base at work takes about an hour to completely build, using MSVC 2005. Building for both windows and the embedded real time OS. Oh and that is using a distcc-like thing for windows called IncrediBuild. I have no idea how long it would take with a single computer
16:26:37 <int-e> newsham: it's amazing how many gaps in the syntax tree you can fill that way.
16:26:53 <Jafet> I remember building gcc from svn, soon after they switched to C++
16:27:04 <b_jonas> Vorpal: try disabling link-time optimization. that sometimes helps a lot with MSVC.
16:27:09 -!- stuntaneous has joined.
16:27:13 <Jafet> (The svn repo is about 1GB now.)
16:27:27 <Vorpal> b_jonas, the real killer is generating the pdb files for debug build really...
16:27:39 <b_jonas> Jafet: yeah, gcc is building slow again
16:27:45 <b_jonas> there was a time when it built quickly
16:28:11 <Vorpal> b_jonas, I have seen 700+ MB pdb files for the final applications. We link everything statically (since anything else is a MASSIVE pain on the RTOS target), so that doesn't help.
16:28:26 <Jafet> (Also, the commands I used to build gcc were "./configure && make; make; make; make; make install".)
16:28:28 <b_jonas> Slereah_: no no, back in my days gcc built slow, because computers were too slow
16:28:37 <Vorpal> b_jonas, the linker takes a LONG time for that
16:28:46 <Vorpal> b_jonas, it is not so bad in release builds though
16:28:54 <b_jonas> Vorpal: generating pdb files you say? hmm
16:29:01 <fizzie> It's daily C syntax corner case time! http://sprunge.us/ccKL
16:29:04 -!- Sprocklem has joined.
16:29:38 <int-e> back in those days e-mailing somebody the X11R5 sources was considered a DoS attack.
16:29:38 <Vorpal> b_jonas, can take up to 5 minutes to link debug builds sometimes, and some investigation showed most of that was spent writing the 700+ MB pdb file
16:30:01 <Vorpal> b_jonas, the application is more like 30 MB in debug (and iirc like 12 or so in release)
16:30:02 <HackEgo> [wiki] [[Talk:Smartboxes]] http://esolangs.org/w/index.php?diff=39307&oldid=39306 * Zerk * (+476) /* Implicit evaluation */
16:30:10 <b_jonas> there's a funny C++ code that used to build in old gccs then not build in later ones, and I actually understood why it is invalid code according to C++, but then some later gcc decided to accept it again
16:30:43 <Vorpal> <fizzie> It's daily C syntax corner case time! http://sprunge.us/ccKL <-- what is ptype?
16:30:44 <newsham> c++ still hasnt incorporated awk or sed or sh
16:30:50 <newsham> there is still room for improvement
16:30:56 <b_jonas> newsham: no, but they're getting close to that
16:31:26 <Vorpal> fizzie, also why does it do what it did there?
16:31:40 <fizzie> Vorpal: The "-" sign is the unary - operator, not part of the integer literal.
16:32:01 <fizzie> (And 2147483648 is larger than INT_MAX, so is of type long.)
16:32:02 <Vorpal> b_jonas, also that is not due to the disk btw, we all use high end intel SSDs in our computers
16:32:28 <b_jonas> Vorpal: are you also using enough RAM?
16:32:45 <Vorpal> b_jonas, 12 GB in some machines, 16 in others. 64-bit windows 7
16:32:50 <fizzie> (The "-" sign in floating point literals is part of the literal syntax, but it probably doesn't matter there.)
16:32:58 <newsham> for(<FD>) { next unless(m/stuff/; ... }
16:33:25 -!- MoALTz_ has joined.
16:33:30 <Vorpal> b_jonas, we are going to switch to linux in the future though for the next version of the embedded platform, porting is currently in the works. I guess we will have to support the old one for quite some time to come though
16:33:33 <Jafet> Ironically, float range is sign-symmetric but int range is not
16:33:34 <b_jonas> here's that C++ thingy that I think shouldn't compile, but gcc now accepts it again: http://dpaste.com/1778559/
16:33:38 -!- ais523 has quit (Ping timeout: 245 seconds).
16:33:38 <Vorpal> so eh I don't bother too much
16:33:41 <b_jonas> this channel might apprecate it
16:34:08 <b_jonas> Jafet: it does matter a bit for floats too, because of preprocessor shenenigans with ## stuff
16:34:21 <Vorpal> b_jonas, what is wrong with that?
16:34:35 <b_jonas> Vorpal: oh wait, that's the version that should compile
16:34:48 <b_jonas> Vorpal: change the ::d to d to have the version that is questionable
16:34:49 <Vorpal> b_jonas, I probably couldn't tell them apart
16:35:10 <b_jonas> Jafet: also probably for user-defined literals
16:35:21 <Vorpal> b_jonas, okay, why is that questionable, I don't see multiple d symbols in there
16:35:29 <b_jonas> here's the questionable version: http://dpaste.com/1778560/
16:36:06 <Vorpal> b_jonas, as far as I can see, there is only one class d in there?
16:36:10 <b_jonas> Vorpal: the trick is that in that context d can refer to the concrete type d<T>, or the type template d
16:36:22 <b_jonas> Vorpal: ::d unambiguously refers to the template
16:36:42 <Vorpal> fuck template-template arguments :P
16:36:51 <b_jonas> the language usually disambiguates between the two because if you use the template a less than sign follows
16:36:56 -!- nucular has joined.
16:36:56 -!- nucular has quit (Changing host).
16:36:56 -!- nucular has joined.
16:37:00 -!- MoALTz has quit (Ping timeout: 276 seconds).
16:37:03 <b_jonas> which is why you need this crazy code to confuse the grammar
16:37:05 <Vorpal> b_jonas, yes and template-template breaks that
16:37:24 <Vorpal> C++ grammar is terrible
16:38:06 <Vorpal> That is one thing I like about python. A mostly sensibly grammar that is sensibly parseable
16:38:14 <Vorpal> Btw, is it "parseable" or "parsable"?
16:39:30 <b_jonas> Vorpal: is it now? do you know the scoping rules for python, like what creates a new variable in a scope as opposed to referring to an existing one?
16:39:42 <int-e> Vorpal: yes, according to https://en.wiktionary.org/wiki/parsable
16:40:09 <Vorpal> b_jonas, okay that bit is a meh, but at least there is no ambiguity at the actual parsing stage. Afaik the grammar is LL(1)
16:40:32 <Vorpal> int-e, oh nice, I can mix and match after my mood ;)
16:41:40 <b_jonas> I have another crazy example about gcc, but that's more dependent on which generation of the C++ standard you look at
16:42:58 <b_jonas> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59704
16:43:00 <Vorpal> Completely unrelated, I just looked at my car expenses spreadsheet, specifically the fuel page. Man, it is expensive having a car. At least if you live in Europe.
16:43:35 <Vorpal> Spent around 1225 USD on fuel alone since buying the car last summer.
16:44:50 <Vorpal> This is a new chromium bug I think... Sometimes when I scroll the page goes blank. If I scroll a bit further it goes back to working again
16:45:01 <Vorpal> First showed up a couple of days ago...
16:46:04 <int-e> b_jonas: evil gcc.
16:46:16 <Vorpal> int-e, also evil language and evil code
16:46:31 <Vorpal> b_jonas, what does = delete mean? I haven't used C++11
16:47:13 <Guest46968> I want to tell 2008 Vorpal about 2014 Vorpal having a car.
16:47:35 <Vorpal> Guest46968, why is that? Did I say something about cars back then?
16:47:45 <b_jonas> Vorpal: that means the function doesn't exist and will never be defined. it's most often used for copy constructors of non-copiable classes.
16:47:47 <Guest46968> um. I think you hated them but maybe I'm mixing you up.
16:47:52 <b_jonas> here it comes useful to produce a clear example
16:48:10 <b_jonas> it's not necessary for exhibiting this bug, just makes it simpler to show
16:48:23 <Vorpal> Guest46968, err think you are mixing me up. They are terrible for the environment, and I avoid driving when I don't have to. But I probably didn't go further than that
16:49:16 <Vorpal> b_jonas, ah yes, the old C++03 way of declaring but not defining such a function would produce a linker error instead
16:49:30 <Vorpal> or making it private (if in a class, unlike here)
16:49:51 <b_jonas> Vorpal: you can demonstrate this bug without delete, but then you'd have to check what function gcc actually chooses to call, instead of getting a straight error message
16:50:31 <Vorpal> b_jonas, or just define one of them and try to link it, resulting in a linker error as I said
16:51:10 <Vorpal> I didn't know you could mix varargs with overloading btw
16:51:18 <Vorpal> It seems like it could be terribly confusing
16:52:40 <Vorpal> fizzie, recommendation(s) for domain name reseller?
16:52:43 <b_jonas> Vorpal: the context is this. gcc has a language extension called __builtin_constant_p to determine whether an expression is compile-time constant. this is useful in macros that try to do magical optimized stuff.
16:53:08 <b_jonas> Vorpal: now Jens Gustedt noticed that this is possible to write in standtard C11, without an extesions,
16:53:12 <b_jonas> see https://gustedt.wordpress.com/2013/08/22/testing-compile-time-constness-and-null-pointers-with-c11s-_generic/
16:53:29 <b_jonas> but he wrote "I am not aware of a C++ feature that provides the same possibilities"
16:53:46 <b_jonas> so I wanted to implement the same thing in C++, and I do have a solution which seems to work,
16:54:04 <b_jonas> but the problem is, it's completely fragile and seems to depend on what gcc can optmize to a constant,
16:54:17 <b_jonas> instead of just what the language specs considers compile-time constant,
16:54:23 -!- doesthiswork has joined.
16:54:25 <Sgeo> Why do bullshitters always put their bs "information" in a video instead of something nice and readable?
16:54:26 <b_jonas> so it could easily break in a future gcc.
16:54:40 <Sgeo> The bill this person is talking about was in 2010 and doesn't even mention 2014
16:54:41 <Vorpal> b_jonas, so what does _Generic do?
16:54:50 <Sgeo> So I cant just google
16:55:09 <b_jonas> c++1y wants to change the rule about what can be casts to a null pointer, so it would break my solution completely.
16:55:46 <b_jonas> Vorpal: it's a C11 thingy for choosing different expressions depending on the type of an expression.
16:55:48 <Vorpal> I need to look into what C11 brought to the table at some point btw
16:55:49 <int-e> Sgeo: charisma? hard to express that in text (unless you use comic sans ;-) )
16:55:59 -!- ais523 has joined.
16:56:08 <b_jonas> C++ doesn't have it, because it has function overloading instead.
16:56:11 <Vorpal> int-e, doesn't comic sans express the lack thereof
16:56:27 <b_jonas> Vorpal: the most useful thing it's brought is well-defined semantics for multithread stuff,
16:56:27 <int-e> Vorpal: yes. but so could a video.
16:56:32 <Sgeo> "Write Down This Date:
16:56:32 <Sgeo> July 1st, 2014"
16:56:42 <Sgeo> Can we write it down so we can give people like this the middle finger?
16:56:42 <b_jonas> Vorpal: with basically the same model as C++11,
16:56:44 <Vorpal> b_jonas, so a C header using it couldn't be included in a C++ program? Okay
16:57:15 <int-e> July 1st 2014. A perfectly ordinary day somewhat past the middle of 2014.
16:57:16 <Sgeo> Or maybe this person is schizophrenic, rather than a scammer?
16:57:21 <b_jonas> Vorpal: not normally, but such a C header could do an #ifdef to work in both cases, and some headers in gcc or libc will do that
16:57:29 <Sgeo> int-e: supposedly the US is going to collapse due to some law
16:58:17 <Sgeo> But there's a template here, I feel. Of using a video. They don't sound like a crazy. My vote is scammer.
16:58:44 <Sgeo> http://www.endofamerica.com/
16:58:54 <Sgeo> The video is so lengthy, still hasn't gotten to the point yet
17:01:18 <Sgeo> Why doesn't this person just GET TO THE POINT already
17:01:26 <Sgeo> Does doing this increase fear or something?
17:01:31 <Vorpal> Sgeo, why are you watching it then?
17:01:55 <Sgeo> I want to see what this scam is about
17:03:27 <Sgeo> Apparently it's fear-mongering about debt spending? WIth no relation to "On this date, U.S. House of Representatives Bill "H.R. 2847" goes into effect. It will usher in the true collapse of the U.S. dollar, and will make millions of Americans poorer, overnight. You now have just several months to prepare..." on the website
17:07:13 <int-e> http://www.truthorfiction.com/rumors/h/HR-2847-Dollar-Collapse.htm
17:07:40 <int-e> I tried reading the bill itself but I have no idea what it says.
17:08:24 <Sgeo> It doesn't say 2014, but maybe I missed something that's equivalent
17:09:14 <int-e> Sgeo: there are relative effective dates in there, e.g. "The amendments made by this section shall apply to obligations issued after the date which is 2 years after the date of the enactment of this Act."
17:09:24 <fizzie> Vorpal: I have my only .org from register4less, but they're not cheap; I've just been staying there because of inertia.
17:10:02 <fizzie> Vorpal: (For .fi domains, I recommend the Finnish Communications Regulatory Authority.)
17:10:38 <ais523> fizzie: misleading name?
17:10:59 <fizzie> ais523: It's possible they were relatively cheap at that time.
17:11:17 <Sgeo> "Our countries's unique ability to print more money"
17:11:33 <Sgeo> Oh, it's saying that we're the only one able to print US money, which is popular
17:12:37 <fizzie> "10MB of web space. A part of the R4L difference that we have offered our clients from the first day is free web space with your domain. With every R4L registration, you can host a web site up to 10MB in size, banner-free!"
17:12:53 -!- nooodl has quit (Ping timeout: 258 seconds).
17:12:55 <fizzie> I have a feeling 10 megabytes might not be anything to write home about, these days.
17:13:30 <Bike> might not even be enough space to fit t he ltter home, in fact
17:17:54 <ais523> fizzie: it's still quite a lot of space if you're just storing text, though
17:18:31 <fizzie> ais523: It is, yes, but it does sound sort of "outdated".
17:24:31 <doesthiswork> sfeer theory shows the connection between comonads and natural deduction http://sfeertheory.littlefoolery.com/index.html
17:25:55 -!- ais523 has quit.
17:26:05 -!- ais523 has joined.
17:27:51 -!- ais523 has quit (Read error: Connection reset by peer).
17:27:54 -!- callforjudgement has joined.
17:30:56 * pikhq submits a CFJ: can "ais523" and "callforjudgement" refer to the same entities?
17:31:18 <Vorpal> fizzie, with tilaa how many IPv4 do you get?
17:31:51 <Vorpal> fizzie, I can't find that on their site
17:32:29 -!- scarf has joined.
17:32:37 -!- callforjudgement has quit (Read error: Connection reset by peer).
17:32:50 <fizzie> Vorpal: It's (sort of) there in the knowledge base, just not very prominently: https://support.tilaa.com/entries/20917782-Can-I-get-additional-IPv4-addresses-
17:33:21 -!- tromp has quit (Remote host closed the connection).
17:33:57 -!- tromp has joined.
17:34:28 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39308&oldid=39305 * Zerk * (+281) Reverted to using _var assignments, moved $ to #sugar where it belongs.
17:34:31 <fizzie> Vorpal: (They also assign only a single IPv6 address, not a /64 block or something, and you need to request more via their dashboard thing. But I think those are free.)
17:34:46 <Vorpal> fizzie, how is support btw?
17:34:57 <Vorpal> And do they have an IRC channel?
17:35:46 -!- scarf has quit (Client Quit).
17:36:13 -!- scarf has joined.
17:38:39 <fizzie> Vorpal: I don't think I've had any reason to contact them. I tried to check my email archive, but "tilaa" is the Finnish word both for "space" (as in, "the space between the walls", not stars-and-galaxies space) and "order" (as in, "order now while supplies last"), so I get a whole lot of emails in Finnish.
17:38:45 -!- tromp has quit (Ping timeout: 276 seconds).
17:39:48 -!- ais523 has joined.
17:39:49 <fizzie> "tilaa.com" seems to have been a better search term, but there's just email notices of downtime or planned maintenance; I've never had an occasion to contact their support.
17:40:03 <fizzie> I don't think they have an IRC channel, though I could be wrong about that.
17:40:39 <fizzie> They have a Twitter account. :p
17:41:17 -!- scarf has quit (Ping timeout: 240 seconds).
17:43:50 -!- callforjudgement has joined.
17:45:49 -!- ais523 has quit (Ping timeout: 250 seconds).
17:46:31 -!- Bike_ has joined.
17:46:34 -!- Bike has quit (Read error: Connection reset by peer).
17:50:27 -!- callforjudgement has quit.
17:50:34 -!- scarf has joined.
17:55:52 -!- scarf has quit.
17:56:01 -!- scarf has joined.
18:00:01 <Bike_> http://blog.regehr.org/archives/767 lol
18:00:12 -!- Bike_ has changed nick to Bike.
18:00:54 -!- heroux has quit (Ping timeout: 240 seconds).
18:01:55 -!- heroux has joined.
18:09:23 <fizzie> Bike: I like that winner #2 end result very much.
18:10:03 <Bike> yeah it's pretty @_@
18:12:25 <fizzie> Though I was under the impression that the fact realloc can return some completely different pointer and invalidate the old one was pretty common knowledge.
18:12:51 <Jafet> A C compiler should not assume these things left and right, though.
18:13:23 <pikhq> Unfortunately for you, a C compiler is permitted to assume UB never happens.
18:13:28 <Jafet> For example, what happens when you use -nostdlib. (Sometimes, the compiler blindly continues using its assumptions)
18:13:28 <zzo38> fizzie: I also, thought so
18:14:02 <pikhq> -ffreestanding is the one to make it do a freestanding C implementation.
18:14:05 <Jafet> There was a bug in gcc 4.8 where gcc would compile an implementation of memset into a call to memset
18:14:07 <Bike> fizzie: well, i didn't know, not that i'm a C programmer, and i don't see it in man
18:14:25 <zzo38> I don't really like that, standard library assumptions, so, I defined that Black-C has a different way to specify standard library assumptions.
18:14:31 <pikhq> -nostdlib says "don't implicitly add -lc to the link line" and that's all.
18:14:52 <Bike> it's not what i'd infer from "changes the size of the memory block pointed to by ptr", certainly
18:14:54 <Jafet> Yes, I meant -ffreestanding might not turn off those assumptions.
18:14:56 <fizzie> Bike: It is only implied very vaguely in my realloc man page. "If the area pointed to was moved, a free(ptr) is done."
18:15:11 <pikhq> And *that* is a compiler bug. :)
18:15:20 <pikhq> fizzie: The man page isn't normative though.
18:15:33 <Bike> not normative, but more people are going to read it than ANSI!
18:16:01 <pikhq> " The realloc function deallocates the old object pointed to by ptr and returns a pointer to a new object that has the size specified by size. The contents of the new object shall be the same as that of the old object prior to deallocation, up to the lesser of the new and old sizes."
18:16:05 <Bike> btw is there some way to see what version of a given man page i have
18:16:30 <Bike> pikhq: is that the standard?
18:16:36 <fizzie> That is the standard, yes.
18:16:55 <Bike> that sounds like a totally different function from the one in my manual
18:16:55 <fizzie> It also mentions, in the return value section, that it "returns a pointer to the new object (which may have the same value as a pointer to the old object)".
18:17:09 <pikhq> Yes, that is 7.20.3.4 from the WG14/N1256 draft.
18:17:19 <pikhq> (closest I, a cheapskate, have to the actual spec)
18:17:36 <fizzie> The C89 wording is essentially very close to Bike's (and mine) man pages.
18:17:38 <Bike> i mean obviously it makes sense that it's going to have to get a new block sometimes, but i didn't know that from the manual, is all
18:17:49 <fizzie> "The realloc function changes the size of the object pointed to by ptr to the size specified by size . The contents of the object shall be unchanged up to the lesser of the new and old sizes."
18:18:13 <zzo38> So I would have it, the realloc function can be declared with ["implements"("realloc",ptr,len)] ["invalidate"(ptr)] before the function header, to indicate to the optimizer, such features. (Actually the first implies the second, but this is in case the compiler doesn't implement "implements".)
18:18:34 <fizzie> And the only bit that hints at the possibility of a move is the "returns" section: "The realloc function returns either a null pointer or a pointer to the possibly moved allocated space."
18:18:41 <scarf> ooh, are we taking about realloc?
18:18:47 <Bike> fizzie: that's actually the same as my man page, except it uses "will" instead of "shall"
18:18:55 <Bike> scarf: yes, see my link above, there's an amusing UB
18:18:59 <Bike> amusing result of UB, rather
18:19:06 <scarf> I was reading C11's definition of realloc, and AFAICT, if you give it a zero size and an existing pointer
18:19:21 <scarf> it's allowed to return a non-NULL pointer that you aren't allowed to dereference
18:19:29 <Bike> zzo38: does "implements" tell the compiler to use optimizations hardcoded for "realloc"?
18:19:30 <scarf> and that can be deallocated
18:19:34 <pikhq> Yes, that matches malloc's behavior.
18:19:50 <Bike> boring. i like "invalidate" though.
18:19:51 <pikhq> malloc(0) can return NULL or a unique pointer that it is UB to dereference.
18:20:01 <Bike> sounds like the sort of thing rust probably has
18:20:25 <pikhq> This is the same in C99 and C90.
18:20:26 <fizzie> pikhq: It can be safely passed to free, however.
18:20:37 <pikhq> Yes, but the same is true of NULL.
18:20:46 <zzo38> pikhq: Yes, what make sense to me is that realloc with an existing pointer and zero size, ought to free the pointer and then return whatever malloc(0) is, which can be safely freed whether or not the result is null.
18:20:46 <scarf> pikhq: yeah, but realloc-as-0 is documented to be the same as free in the man pages
18:20:52 <scarf> and it's quite useful for it to behave like that
18:21:04 <pikhq> scarf: Yes, it is quite useful.
18:21:09 <scarf> as such, I've been making realloc wrappers I write do a free instead if given zero size
18:21:42 <pikhq> zzo38: Conceptually that's what it *does*.
18:22:13 <pikhq> Except a hypothetical evil implementation could have realloc make the opposite choice from malloc. :(
18:22:45 <Guest46968> it's amusing that if (!(p = malloc(sz))) die(); is incorrect
18:22:46 <zzo38> pikhq: I don't care as long as whatever it returns can be safely freed once, and that whatever it returns can also be passed to realloc.
18:23:09 <Bike> Guest46968: for sz = 0 you mean?
18:23:16 <pikhq> zzo38: Well, the C standard does require that to work no matter which implementation choice is made.
18:23:20 <scarf> pikhq: it's unspecified, isn't it, not impl-defined?
18:23:24 <scarf> so it could change randomly during a program
18:23:38 <zzo38> pikhq: Yes, which is how it should be, so it is OK.
18:24:03 <Jafet> What happened to the evil libc project, anyway
18:24:16 <pikhq> scarf: " If the size of the space requested is zero, the behavior is implementation- defined: either a null pointer is returned, or the behavior is as if the size were some nonzero value, except that the returned pointer shall not be used to access an object."
18:24:36 <scarf> oh good, it is impl-defined
18:24:56 <fizzie> You could argue that realloc is not allowed to return NULL, since it must "return a pointer to a new object that has the size specified by /size/" and can return NULL only if "the new object could not be allocated". And you can't say that it can return NULL under the "could not be allocated" rule, because "if memory for the new object cannot be allocated, the old object is not deallocated and ...
18:25:01 <scarf> hey, is it legal to pass a negative size to malloc?
18:25:02 <fizzie> ... its value is unchanged".
18:25:12 <fizzie> scarf: It's a size_t, it has no negative values.
18:25:22 <scarf> I'd just notice that, but you got there first
18:25:34 <scarf> I was confused by valgrind telling me that I'd passed -8 to malloc recently
18:25:45 <scarf> (it was very helpful that it did that, that bug would have taken longer to find otherwise)
18:25:56 <scarf> presumably it assumes very large size_ts are actually negative
18:26:26 <Jafet> What if it told you that you'd passed 0xfffffffffffffff8
18:26:34 <scarf> yeah, that'd be useful too
18:26:50 <pikhq> Yes. It's essentially impossible to meet some of C's requirements while allowing objects with a size that don't fit in ssize_t.
18:26:56 <scarf> but the Valgrind docs imply to me that they care a lot about making the output understandable to end users, which implies to me that many end users tend to be confused by it
18:27:09 <zzo38> If you are passing a size with the high bit set then probably it is wrong anyways since it likely take up too much of the program's RAM.
18:27:22 <pikhq> Which means that sufficiently large objects (larger than SSIZE_T_MAX) are utterly illegal in practice. :)
18:27:29 <scarf> pikhq: you're reminding me of a thread on comp.lang.c about whether you could have a conforming implementation that could allocate objects larger than SIZE_MAX bytes using calloc
18:27:45 <fizzie> There was someone on another channel doing fd = open(...); if (fd < 0) die_noisily(); printf("fd = %d", fd); with an accidentally unsigned fd, and was very confused by "it prints fd = -1 but it doesn't die_noisily whaaat". (A case of not enough compiler warning flags, of course.)
18:28:00 <Jafet> That is metaphysics.
18:28:04 <scarf> I know that one outcome on the thread is that a lot of libc devs realised that their libcs were buggy when given such arguments, at least
18:28:05 <zzo38> scarf: I suppose that might be possible.
18:28:16 <pikhq> scarf: "Essentially" for the sake of skipping out on such a debate. :)
18:28:54 <scarf> fizzie: this reminds me, I've been planning to change all the integers in NetHack, apart from bitfields, to signed (making them wider if necessary)
18:29:01 <scarf> can you think of anything that might end up breaking as a result?
18:29:40 <Jafet> I suppose you mean things that aren't exploits
18:29:43 <fizzie> scarf: Hah, realloc of size 0 is the very first defect report of C11: http://www.open-std.org/jtc1/sc22/wg14/www/docs/dr_400.htm
18:29:58 <scarf> note that it's OK if code could theoretically break from the change, so long as it's not used in NetHack
18:30:22 <scarf> Guest46968: I want to autogenerate structure descriptions, rather than relying on a bunch of code implemented by hand that has to be manually synchronized across up to six different files
18:30:28 <scarf> automatically generating unsigned ints is just asking for pain
18:30:35 <scarf> thus making them all signed is a saner option
18:32:39 <zzo38> What are these structure descriptions?
18:32:42 <scarf> hmm, so they're officially making size-0 realloc an error
18:33:00 <zzo38> And, sometimes you might want unsigned numbers
18:33:07 <scarf> zzo38: I only started work on them a couple of days ago, it's not really finished
18:33:15 <zzo38> scarf: I sometimes use malloc(0) and realloc with size zero, too, though.
18:33:18 <scarf> but you define numerical types by giving a range
18:33:28 <scarf> e.g. you write [0, 100] and that probably becomes int8_t
18:33:55 <scarf> [0, 255] would become int16_t unless you explicitly say that unsigned types are allowed, in which case it might become uint8_t or a bitfield unsigned : 8
18:34:00 <zzo38> TeX actually does contain macros which are there in case the compiler won't generate unsigned types.
18:34:31 <scarf> in general, I assume that you shouldn't be having overflow happen at all
18:34:46 <Guest46968> just use a bignum type for everything.
18:35:35 <zzo38> (These macros are in section 112)
18:35:41 <fizzie> scarf: The mixed-sign integer comparison rules (or, rather, the usual arithmetic conversions in that context) are kind of unintuitive occasionally, at least. (Both get integer promotions first; then if the unsigned type has larger rank, the signed is converted to unsigned and unsigned comparison takes place; alternatively if the signed type can represent all values of the unsigned type, the ...
18:35:45 <scarf> 'twould be nice, but that's not easy to retrofit onto a 27-year-old C codebase
18:35:47 <fizzie> ... unsigned operand is converted to signed and the comparison is signed; alternatively both are converted to the unsigned type corresponding to the operand with the signed type.)
18:36:02 -!- ^v has quit (Ping timeout: 252 seconds).
18:36:13 <Guest46968> scarf: easier if you use C++ to define the bignum type
18:36:16 <scarf> fizzie: I don't remember that rule 100%, but do know how it works approximately
18:36:24 <scarf> scarf: NetHack doesn't compile as C++
18:36:42 <Guest46968> that's an easier problem to solve than replacing all arithmetic operators
18:36:58 <scarf> and really, neither problem is particularly easy to solve
18:37:03 <fizzie> So (-1L < 1ULL) for example is false, which you maybe might not expect.
18:37:04 <zzo38> Section 110 contains the description of this feature; "Some Pascal compilers ... insist on allocating space for an additional sign bit; on such systems you can get 256 values into a quarterword only if the subrange is `-128 .. 127'."
18:37:32 <scarf> fizzie: I expected that, fwiw
18:37:38 <fizzie> While (1-LL < 1U) is true.
18:37:55 <scarf> zzo38: what about 16-bit systems? wouldn't a quarterword be 4 bits?
18:38:08 <scarf> also, TeX is written in Pascal?
18:38:33 <Guest46968> it's written in pascal but translated to C with a program solely designed to translate TeX to C to compile it
18:38:39 <zzo38> TeX is written in WEB, which is a preprocessor for Pascal.
18:38:56 <zzo38> The "word" in TeX has to be 32-bits even in 16-bit systems though.
18:39:33 <myname> wait, tex is written in a preprocessor for pascal which is translated into c to be compiled?
18:40:03 <zzo38> It could be compiled using some Pascal compilers too, though.
18:40:42 <Jafet> Like thousands of other programs of the 70s, TeX was written in pascal.
18:41:02 <scarf> also, blog.regehr.org talks about UB quite a bit, and is frequently a good read
18:41:12 <scarf> it has an example where it doesn't check the return value of printf
18:41:20 <scarf> and then actually talks about the possible behaviour of the program
18:41:28 <scarf> (this is, btw, the #1 most common bug in hello world programs)
18:41:47 <scarf> `run /bin/true --help > /dev/full
18:41:48 <HackEgo> /bin/true: write error: No space left on device
18:41:55 <scarf> `run /bin/true --help > /dev/full; echo $?
18:41:56 <HackEgo> /bin/true: write error: No space left on device \ 1
18:42:18 <scarf> admittedly, /checking/ the return value can also lead to absurdities
18:42:18 <fizzie> And -1L < 1U is false on systems where long is the same size as int, but true on systems where long is longer.
18:42:42 <zzo38> The preprocessor does various things, such as convert hex and octal numbers into decimal, implement macros, convert all names into uppercase and remove all underscores, as well as rearrange and transclude "chunks", generate a string pool, and generate an index and various cross-references, pretty-print the code, etc.
18:42:43 <scarf> now I wonder if any program uses that to compare the size of int to the size of long
18:42:44 <myname> i have a long long in my pants!
18:43:12 <scarf> zzo38: now I wonder if Knuth uses a preprocessor to write INTERCAL
18:43:16 <fizzie> (On the first kind of systems, long can represent all values of unsigned int so 1U is converted to long; on the second it can't, so both are converted to unsigned long.)
18:43:18 <scarf> that converts variable names to numbers, for instance
18:43:29 <Jafet> `run echo 'long long long n;' > /tmp/a.c && gcc /tmp/a.c
18:43:29 <HackEgo> /tmp/a.c:1:11: error: ‘long long long’ is too long for GCC
18:43:55 <scarf> he uses three-letter variable names that are converted into variable numbers using the five-bit Baudot encoding
18:44:19 <scarf> I'm upset that gcc doesn't still have a pragma to run NetHack
18:44:22 <scarf> (it was documented, thus legal)
18:44:39 <scarf> actually it used to interpret all pragmas like that, as a protest against bugs in the definition of #pragma
18:44:42 <Jafet> I thought it did, at one point
18:45:02 <scarf> but the bugs were fixed, and it now implements a few pragmas of itso wn
18:45:09 <scarf> so it can't implement /all/ of them like that
18:45:15 <scarf> and thus it doesn't implement any like that
18:45:36 <Bike> http://blog.regehr.org/archives/140 haha, beaut
18:46:11 <zzo38> Another thing WEB does is read a "change file" which makes changes to the program before it is compiled. This is implemented so that you can make the changes needed for whatever system you are compiling on.
18:47:43 <Bike> i don't think i understand how this termination analysis works...
18:47:45 <scarf> Bike: incidentally, gcc now has an option that, among other things, tells you about functions it wanted to perform optimizations on (normally moving calls to them elsewhere), but couldn't because it isn't sure that they terminate
18:47:46 <Jafet> I like "change file"
18:48:04 <scarf> (although it suspects that they probably do)
18:49:18 <Bike> is there an annotation or something to say that they terminate?
18:49:22 <scarf> incidentally, CLC-INTERCAL actually optimizes detected infinite loops into infinite sleeps
18:49:37 <scarf> Bike: there's __attribute__((pure)), which implies termination among other things
18:49:57 <scarf> if the function is total but impure, then gcc couldn't do the optimizations in question anyway, so there's no real gain
18:49:57 <Bike> surely always terminating mutagenic functions aren't uncommon
18:51:22 <int-e> Bike: I remember having run into something like this. I wanted to produce a stack overflow, void f() { f(); } ... and the call got optimized away by icc.
18:51:31 <Bike> hm, does the analysis work by figuring that once it's run through all 1000³ tuples it can stop
18:51:36 <scarf> wow, according to http://blog.regehr.org/archives/161, in C++0x, infinite lops are UB
18:52:07 <Bike> guess i should just try it
18:52:18 <scarf> unless they access library functions that do I/O, do synchronization with other threads, or change volatile variables
18:52:33 <Bike> ok, yeah, there's a delay.
18:52:52 <Bike> a delay that is appreciably burning my CPU, even
18:53:21 <Bike> i suppose it doesn't say what gcc does, though.
18:53:29 <scarf> Bike: I think it works correctly in gcc
18:53:47 <scarf> given that a) it doesn't mention gcc, and b) gcc explicitly checks for termination when optimizing out code
18:53:50 <Bike> i don't think i'm willing to install icc for this
18:54:34 <fizzie> scarf: Anyhow, if you're dealing mostly with narrower-than-int unsigned types (like I'd assume, given NetHack), those probably have been converted to int by integer promotions in most of their uses in arithmetics/comparisons before now, already.
18:55:00 <scarf> fizzie: NetHack uses types more or less at random, AFAICT
18:55:09 <scarf> I guess there have been guiding principles in the past, but they've changed over time
18:55:19 <scarf> plain unsigned is entirely visible on occasion
18:55:34 <scarf> actually, the main problem is when they've tried to do overflow checks, and those checks don't work
18:55:43 <Bike> "nethack" and "random" in the same sentence brings odd memories to mind
18:55:52 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:56:04 <scarf> Bike: well NetHack is a very random gmae
18:56:10 <scarf> its implementation's also pretty random
18:57:14 <Bike> scarf: was thinking of rnz
18:57:35 <scarf> Bike: "These C compilers known to not preserve termination properties of code: Sun CC 5.10, Intel CC 11.1, LLVM 2.7, Open64 4.2.3, and Microsoft Visual C 2008 and 2010. The LLVM developers consider this behavior a bug and have since fixed it. As far as I know, the other compiler vendors have no plans to change the behavior.
18:57:36 <scarf> These C compilers, as far as I know, do not change the termination behavior of their inputs: GCC 3.x, GCC 4.x, and the WindRiver Diab compiler."
18:58:00 <Bike> that seems like a pretty strong claim, i wonder how you'd prove it
18:58:06 <scarf> myname: in case you didn't know, I'm the lead maintainer of the fan project to restart NetHack development
18:58:17 <scarf> and the main aim of 4.3 is cleaning up the code
18:58:21 <Bike> "This observation is not untrue, but it’s a little like explaining that World War II happened because people couldn’t all just get along." not bad
18:58:28 <Bike> scarf: oh, you're ais, aren't you
18:58:34 <myname> i used to play nethack with like 2 dozens of patches applied
18:58:39 <Bike> names are hard
18:58:45 <myname> and a bit UI modifying by myself
18:58:49 -!- scarf has changed nick to ais523.
18:59:28 <Bike> rnz is so amusing, it seems like a in-the-wild semiexample of the kind of prng knuth talks about
18:59:36 <ais523> sorry, I set my client to cycle nicks on connection failure, because I use unreliable connections often enough that it helps keep them refreshed
18:59:57 <ais523> Bike: well it doesn't suffer from patterns in the output, just from an utterly nonsensical distribution
19:00:05 <Bike> that's why it's semi-, yeah
19:00:44 <Bike> if i was running a stats class i'd compare rnz to cauchy to explain different kinds of "nonsensical"
19:01:04 <myname> ais523: i assume that this will take years
19:01:08 <Bike> (rnz, if i'm not mistaken, has defined moments)
19:01:44 <ais523> myname: yeah, but we've been working on it for years
19:01:57 <myname> ais523: well, you just proved me right
19:02:13 <ais523> fewer than 50% of the lines in NetHack 4 come from NetHack 3.4.3 or earlier, even when you ignore whitespace changes
19:02:29 <ais523> (if you don't ignore whitespace changes, it's close to 0% because we reindented the entire source tree)
19:02:34 <Bike> now i wish i was good enough with cass to give symbolic definitions of all of rnz's moments.
19:02:46 <Jafet> Has anyone actually calculated the higher moments of rnz
19:03:04 <myname> ais523: what is the reason behind that?
19:03:28 <ais523> myname: for reindenting it? because it was entirely inconsistent before
19:03:41 <myname> ais523: for the project itself
19:03:44 <ais523> I standardised it on what seemed to be the most common indentation scheme within the existing code
19:03:46 <Bike> Jafet: seems unlikely, given that the wikis mostly analyze a continuous distribution slightly different from rnz
19:03:54 <ais523> oh, for the project, it's because there have been no public updates in over 10 years
19:04:07 <ais523> which is far too long to leave NetHack stagnant
19:04:13 <ais523> so if the devteam won't update it, we will
19:04:47 <Bike> i actually don't recall how to do moments of a discrete distribution, hopefully you just replace the integral with a sum
19:05:00 <Jafet> Sometime in the past 10 years, crawl happened to nethack
19:05:37 <zzo38> I want to write roguelike game using SQL.
19:05:47 <Bike> wow wikipedia's article on moments is not very formal
19:06:02 <myname> i want to write a roguelike in rust
19:06:20 <Bike> maybe i should see if i know enough real analysis to figure this out, after i do my nine hours of homework
19:06:21 <zzo38> myname: OK do you know how to do?
19:06:35 <ais523> Jafet: well, there are enough people who think that NetHack is better (including me) that there's still a healthy NetHack community
19:06:44 <myname> zzo38: you are there for that creative stuff
19:07:41 <ais523> so it's not really fatal at all; competition can be helpful
19:07:44 <ais523> myname: fwiw, structdesc has three types of borrowed pointers, two types of owned pointers, and two which can be owned /or/ borrowed depending on context; I'm considering adding reference counting too
19:07:58 <ais523> this is because it's meant to describe the behaviour of existing C programs
19:08:06 <zzo38> (Not entirely written in SQL; part of it written in C, such as the display and input manager, and some of the functions and virtual table modules, and some other performance related things, and a few other things)
19:08:12 <Jafet> I prefer crawl, though that may be due to the fact that I have not finished it yet.
19:08:12 <ais523> and only disallow the behaviour if it's completely nonsensical
19:09:01 <Sgeo> I wonder how much money I'm spending on ignoring things like sales and atm fees and coupons on receipts
19:09:03 <Bike> "The 1st through 3rd elements indicate cases where the I/O subsystem truncated the string. " shit, printf can do this?
19:09:40 <zzo38> Bike: I would think there are cases where no other way is possible, but to truncate the string.
19:10:01 <myname> ais523: i would prefer a sane port of nethack for android
19:10:01 <Bike> could you have a libc where printf never prints anything and always returns zero if there's no error
19:10:14 <ais523> myname: I've had thoughts along those lines too
19:10:22 <ais523> not owning a tablet myself, it'd be hard to get the ergonomics right
19:10:29 <zzo38> And then, you can add more items and stuff into the game, by adding more records into the table and adding triggers, and possibly more tables if needed; even such things can be changed during the game if these tables are copied into the save file!!
19:10:37 <ais523> the main difficulty is a control scheme
19:10:53 <ais523> I've been wondering about what a mouse-based scheme would look like, that'd be closer to tablet controls than keyboard
19:10:55 <ais523> but still not idential
19:10:55 <Bike> hopefully term on android works better than snes on android
19:10:56 <myname> ais523: well, there are (fairly limited) RL which work pretty well
19:11:09 <zzo38> ais523: You can still implement keyboard scheme; however, then you need also a scheme that work if you have a non-keyboard device.
19:11:28 <myname> but stuff like clicking on a location and a menu would be a big improvement
19:11:46 <zzo38> I think touch screen interfaces are just terrible in general, though.
19:11:46 <ais523> I'm assuming that most smartphones and tablets on which people want to play NetHack don't have physical keyboards, and that I could use a soft keyboard if I wanted to but that it would take up a large amount of screen space
19:12:01 <ais523> and thus other alternativels are likely to be better
19:12:17 <myname> screen space is not THAT big of a problem
19:12:35 <myname> it's more that keys are pretty small and you could move a lot out of that
19:12:48 <myname> like moving, picking up, opening/kicking doors, ...
19:12:51 <Jafet> To do it well, you may need to change some parts of the game to be more like powder.
19:13:08 <Bike> wowwwww that C++ behavior
19:13:22 <Jafet> Powder is a dungeon crawler written for consoles.
19:13:45 <zzo38> I really believe keyboard interface are much better than touchscreens and so on.
19:14:00 <myname> i may have seen it on nds
19:14:00 <Bike> "Haskell fails to distinguish between the error and non-terminating cases: this can be seen as trading diagnostic power for speed" :')
19:14:01 <ais523> myname: POWDER started out as a project by Jeff Lait (famous both for POWDER and for many 7DRLs) to port NetHack to the DS by rewriting it from scratch, but after starting he decided to make a different game instead that was merely similar to NetHack, rather than identical
19:14:20 <ais523> and it's diverged more from that to become a roguelike of its own
19:14:29 <ais523> then it got ported to a bunch of other systems
19:14:33 <ais523> it was some Nintendo portable, anyway
19:14:46 <myname> but even more than that i'd LOVE to have something dwarf fortress like for android
19:14:48 <zzo38> (So, the Famicom version of Attribute Zone, is supporting input from the keyboard in all cases! You can use the standard controller but only for playing ROM levels and the other features are not supported unless you use a keyboard)
19:15:27 <Jafet> dwarf fortress is already unplayable on a PC, and uses too much power
19:15:32 <myname> also, do you guys know cataclysm?
19:15:38 <Jafet> Though I suspect some of that is due to bad programming
19:15:38 <myname> Jafet: yeah, i play it via ssh :D
19:16:10 <myname> i do think the maths behind it are pretty well
19:16:23 <fizzie> That http://blog.regehr.org/archives/161 is wrong when it says "int main(void) { unsigned short a = 65535; return a + 1; } -- may return 65536 or 0 -- depending on whether the particular C implementation being used has defined the size of an unsigned short to be 16 bits or to be larger than 16 bits", incidentally. It can return 0 (if both unsigned short and unsigned int are 16 bits), 65536 (if ...
19:16:29 <fizzie> ... the size of int is 18 bits or larger) or "the result is implementation-defined or an implementation-defined signal is raised" (if short is 16 bits and int is 17 bits), or the behaviour is undefined (if both short and int are 17 bits).
19:16:37 <Jafet> I continue to hold the position that df2 is not actually a game, based on my attempt to "play" it
19:16:59 <Bike> fizzie: some promotion thing?
19:17:03 <ais523> df2 as in a sequel to dwarf fortress, or a sequel to slaves to armok?
19:17:08 <zzo38> fizzie: OK, although I don't expect most computers to have 17-bits numbers
19:17:20 <Bike> also, you should point that out, just to give more power to the "can't reason bout my C" thing
19:17:25 <Jafet> Wait, it's sta2, not df2.
19:17:31 <zzo38> I suppose it is possible but many programs wouldn't work so well on such things anyways, regardless of that.
19:17:34 <fizzie> Bike: Yes, integer promotions. They are mentioned in comment #6 but without considering the case of small ints.
19:18:04 <myname> i watched a tutorial about df once
19:18:06 <fizzie> Oh, it's also mentioned in comment #16 in an almost complete form.
19:18:31 <myname> after half an hour it said "finally, we are in the game. this is, where most of the players quit, too"
19:18:52 -!- ais523 has quit (Read error: Connection reset by peer).
19:18:59 <fizzie> It's missing the implementation-defined case, but that's just additional finessing.
19:19:07 -!- ais523 has joined.
19:19:14 <Bike> hmmmmm now i wish i had more time/effort, i want to prove kinetics is impossible again
19:19:43 -!- adu has joined.
19:20:38 -!- callforjudgement has joined.
19:21:20 <callforjudgement> fizzie: I was trying to figure out if 16-bit short, 17-int is legal; if int and unsigned int have to be the same size, it isn't
19:21:21 <Bike> myname: the one time i tried to play df we were going to do a tradeoff game but worldgen took so long that we ran out of time
19:21:49 <Bike> can't CHAR_BIT be 1
19:21:50 <myname> Bike: let me guess "nah, maximum time, what could go wrong"
19:21:51 <callforjudgement> however, could int be 24 bits, 7 of which are padding bits (with unsigned int being 24 bits)
19:21:59 <Bike> myname: basically
19:22:01 <Bike> callforjudgement: sucks
19:22:14 <HackEgo> bercoin thcoin norfualcoin reviejcoin datecoin cluecoin irkcoin sinrcoin anycoin hypecoin cluhiccoin undercoin l0jdcoin spacecoin develatlinecoin birthcoin dzecoin beakgefcoin leszccoin khalcoin
19:22:50 <kmc> good coins
19:22:55 <kmc> also, good morning everyone
19:23:15 <Bike> hello hello, we have been discussing weird C for far too long
19:23:20 <kmc> @localtime callforjudgement
19:23:21 <lambdabot> Local time for callforjudgement is Sun Apr 13 20:23:20 2014
19:23:23 <olsner> anycoin sounds like it could be actually useful
19:23:23 <kmc> sorry that I missed it :(
19:23:26 <Bike> weird C is like weird fiction except incredibly dull
19:23:32 <zzo38> Now you need a silver coin, gold coin, copper coin, platinum coin, lead coin, iron coin, and radioactive coin.
19:23:43 <olsner> (i.e. cryptocoin compatible with every other cryptocoin)
19:24:01 <fizzie> callforjudgement: Unsigned int can have padding too.
19:24:02 -!- ais523 has quit (Ping timeout: 276 seconds).
19:24:03 <olsner> unicoin would be another nice name for that
19:24:23 <fizzie> Unsigned char, and the exact-width integer types from <stdint.h>.
19:24:40 <Bike> zzo38: 180Tantalumcoin
19:24:52 <callforjudgement> one nice thing I noted is that C11 reserves uint9_t, uint10_t, etc., as well as the least and fast variants
19:25:01 <zzo38> Now I wrote document of "text adventure intermediate language"
19:25:01 <Bike> 180mTantalumcoin, rather
19:25:04 <myname> olsner: like, i will farm a dogecoin in an hour and sell it for hundreds of dollars as a bitcoin?
19:25:05 <kmc> callforjudgement: heh
19:25:11 <kmc> also POSIX reserves every name ending in _t?
19:25:21 <zzo38> http://sprunge.us/PfHL
19:25:34 <olsner> myname: something like that, but the exchange rate could be reasonable (whatever that means)
19:25:41 <zzo38> Now I can write a compiler library for its use.
19:25:49 <myname> olsner: i call that "usd"
19:26:03 <zzo38> Is this good like it is now?
19:26:08 <olsner> myname: that's not a -coin
19:26:08 <callforjudgement> (splint will give warnings about that on high warning levels; that's one of its less buggy warnings)
19:28:25 <fizzie> POSIX also reserves every identifier beginning with "str", "mem" or "wcs" if <string.h> is included, and every identifier beginning with "str" if <stdlib.h> is included.
19:28:48 <fizzie> And everything beginning with "to" or "is" if <ctype.h> is included.
19:28:53 <zzo38> Please tell me if this document is better now, or if you think anything I did wrong.
19:28:57 <olsner> why not just reserve the whole thing
19:29:22 <fizzie> Also all identifiers ending in _MIN or _MAX if <limits.h> is included.
19:29:33 -!- ^v has joined.
19:29:36 <callforjudgement> C with no non-reserved identifiers, and all reserved identifiers are used for a legal purpose
19:29:39 <kmc> greedy old posix
19:29:55 <callforjudgement> I was wondering about storing data in argv, but sadly it doesn't have a standard name
19:31:44 <fizzie> You can use errno as an arbitrary int, I believe.
19:32:07 <fizzie> "The macros are -- errno which expands to a modifiable lvalue that has type int and thread local storage duration, --"
19:32:21 <fizzie> (Though it's just one int.)
19:32:24 <Jafet> It may be legal to overwrite stderr
19:32:25 <callforjudgement> could you create a bunch of extra threads in order to gain more storage?
19:32:31 <Jafet> In which case, you get a pointer
19:33:11 <fizzie> "stderr" and such are not required to be lvalues.
19:33:25 <fizzie> They're just "expressions of type "pointer to FILE" that point to FILE objects".
19:33:44 <fizzie> (They're also macros.)
19:34:28 <fizzie> There's the "file loophole", of course, if you allow for a reasonably consistent file system as seen by fopen/etc.
19:35:23 <fizzie> Though I'm not sure where the FILE * would go for doing more than one operation on an opened file.
19:36:30 <Jafet> Close and open it again
19:36:46 <Jafet> Wait, you can't chain functions.
19:36:46 <fizzie> But you can't close it if you read from it.
19:37:19 -!- callforjudgement has changed nick to ais523.
19:37:32 <fizzie> And anyway it'd be really convenient if you could, say, seek *and* read.
19:37:56 <Jafet> If we're in posix, there is optarg.
19:39:06 <fizzie> If we're in POSIX, you can use open() and such, and stick the fd in... errno... except it's perhaps not the safest place when calling library functions.
19:39:25 <Jafet> optind and opterr can store fds.
19:39:54 <Jafet> Or you can dup2 it around to a known index.
19:40:34 <ais523> doing this in C11 is more interesting; POSIX sounds like it'd be too easy
19:42:12 <fizzie> I guess you can always freopen("data.file", "w+", stderr); and then just use the stderr handle for storage.
19:43:29 <ais523> stderr's readable, right?
19:43:40 <fizzie> You can freopen it to any mode.
19:43:43 <ais523> I know that reading from stderr's one way to get at the terminal when you have a redirected stdin
19:43:55 <ais523> although a fragile one, there are better methods if on POSIX
19:44:49 <Jafet> Hm, you can store a function pointer and retrieve it using signal.
19:45:12 <Jafet> (Obviously, you can in fact store one per signal.)
19:45:51 <fizzie> That might be handy, though you can of course store one in a file too.
19:46:29 <fizzie> (Just take the address of a compound literal of a pointer-to-function type, and pass to fwrite.)
19:47:06 -!- augur has quit (Ping timeout: 240 seconds).
19:47:15 <fizzie> Though reading it back in any very useful way sounds slightly more tricky.
19:48:15 <fizzie> At least the hello, world program is easy.
19:48:35 -!- augur has joined.
19:48:44 -!- ais523 has quit (Read error: Connection reset by peer).
19:48:54 -!- ais523 has joined.
19:49:47 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
19:51:03 -!- heroux has quit (Ping timeout: 250 seconds).
19:51:48 <Jafet> Hmm, you can use asctime for up to 26 bytes of storage.
19:52:19 <kmc> myname: regarding usdcoin, see Xia, P. (2014) Dollarcoin: A cryptocurrency with proof-of-dollar. Presented at ACH SIGBOVIK 2014, Carnegie Mellon University, 1 April (pp. 75-77). http://sigbovik.org/2014/proceedings.pdf
19:52:46 -!- heroux has joined.
19:52:55 <myname> kmc: there is nothing crazy enough for not being done :D
19:53:06 <fizzie> Jafet: You can get a pointer, yes, but any call to asctime will overwrite the contents, right?
19:53:16 <Bike> i'm going to imagine this is the xia of "prove newtonian mechanics impossible" fame
19:53:29 <kmc> myname: the proof of work entails writing a hash on a dollar bill, burning it, and posting the video to the block chain
19:54:49 <Bike> random question: does anyone know of a paper title better than "Can One Hear The Shape Of A Drum"
19:54:58 <Sgeo> kmc: I'm loving this
19:55:17 <Sgeo> Is all sigbovik humorous? I take it from that chart in the paper that that's the poin
19:56:06 <kmc> Sgeo: yes, although it does publish humorous things that are real and impressive, as well as fake things
19:56:15 <kmc> notably http://www.cs.cmu.edu/~tom7/mario/
19:56:24 <Bike> playfun rox my sox
20:03:26 <zzo38> When looking at Nock on esolang wiki it also links to the Urbit they mention, they use kelvin version numbering, where higher numbers indicate more likely to change and zero means it won't ever change at all.
20:04:12 <Taneb> zzo38, that's clever
20:04:21 <Bike> bitches don't know bout my electron degeneracy pressure
20:05:12 <kmc> nobody's in #oteric.es
20:05:56 <Taneb> I am kind of curious how many people joined and parted that as you said it, kmc
20:06:47 -!- password2 has joined.
20:14:06 -!- adu has quit (Quit: adu).
20:16:06 -!- adu has joined.
20:17:13 -!- ^v has joined.
20:23:52 <zzo38> Now I am writing the C library for dealing with Text Adventure Intermediate Language, and then, maybe also the Haskell library can be written.
20:27:02 -!- nooodl has joined.
20:30:55 -!- stuntaneous has quit (Remote host closed the connection).
20:34:48 <Taneb> zzo38, that sounds interesting
20:35:20 <Taneb> Does Inform (the only text adventure creation thing I know about) use Text Adventure Intermediate Language or does it use something else?
20:36:42 -!- tromp has joined.
20:38:11 -!- ^v has quit (Read error: Connection reset by peer).
20:38:38 -!- ^v has joined.
20:40:53 -!- tromp has quit (Ping timeout: 250 seconds).
20:52:27 -!- AnotherTest has quit (Ping timeout: 276 seconds).
20:52:32 <zzo38> Taneb: It compile into a Z-machine code, with some differences.
20:52:52 <zzo38> Z-machine is OK too, but much more complicated than the one I design.
20:56:41 <zzo38> Inform also compiles into Glulx.
20:56:47 <zzo38> (which is even more complicated)
21:07:45 -!- Slereah_ has quit (Ping timeout: 250 seconds).
21:10:08 -!- nooodl has quit (Quit: Leaving).
21:10:24 -!- nooodl has joined.
21:14:12 -!- adu has quit (Quit: adu).
21:14:22 <zzo38> (Both of them lack some features the other one has.)
21:14:22 -!- ^v has quit (Read error: Connection reset by peer).
21:14:51 -!- ^v has joined.
21:16:14 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39309&oldid=39287 * Zerk * (+11) /* B */ ++Boxy
21:16:45 -!- adu has joined.
21:20:40 -!- nooodl has quit (Quit: Leaving).
21:20:46 <zzo38> I may write some text adventure games using TAIL format and some using Z-machine format.
21:21:06 -!- nooodl has joined.
21:22:10 -!- nooodl has quit (Client Quit).
21:22:42 -!- nooodl has joined.
21:25:46 -!- conehead has joined.
21:28:01 -!- nooodl has quit (Quit: Leaving).
21:28:19 <fizzie> ais523: Jafet: Here's a rudimentary brainfuck interpreter in mostly-correct interpreter-free C, as long as you preprocess it out: http://sprunge.us/QJXJ
21:28:26 -!- nooodl has joined.
21:28:29 -!- nooodl has quit (Remote host closed the connection).
21:28:33 <fizzie> That's the only program it's been tested with, so expect bugs.
21:29:05 <fizzie> Oh, brainfuck without input, that is.
21:29:19 <ais523> fizzie: *identifier-free?
21:29:23 -!- nooodl has joined.
21:29:50 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
21:29:57 <ais523> fizzie: you're storing data in stdin's file pointer? clever
21:30:14 <fizzie> Yes, the file position is used as a variable safer than errno.
21:30:16 <ais523> Guest46968: it's a BF interp
21:30:28 <Guest46968> ais523: typical C BF interps are not TC...
21:30:53 <fizzie> Well, under the limits imposed by sizeof (int) for the tape.
21:30:54 <kmc> fizzie: nice :D
21:31:00 <Guest46968> I was wondering what interpreter-free is.
21:31:05 <Guest46968> fizzie: right, you can use fseek to get around that though
21:31:19 <kmc> that's identifier-free post-pre-processing I suppose
21:31:28 <fizzie> kmc: Yes. Or at least should be.
21:32:01 <fizzie> Guest46968: Right, though I'd need to mungle it even more for that, since I rely on seeking the same file to other places than the tape.
21:32:14 <ais523> fizzie: why is there a sizeof(int) limit? I thought the general argument in favour of C being TC is that file pointers are allowed to be bignums
21:32:52 <fizzie> ais523: It keeps the tape pointer in one of those errno-read "variables", so that it can seek the stderr file between the program source and current tape cell.
21:33:58 <fizzie> Also I'm not entirely sure the initial reading of the brainfuck program is valid, but that could be worked around pretty easily by just embedding the program.
21:34:30 <fizzie> It's at least relying on rewind() to not set errno.
21:35:28 <fizzie> I guess I could just open the stdin file (which is never written to, only its position is used) a bit earlier so I can use V to store the program length over the rewind, actually.
21:36:11 <ais523> Guest46968: I mean that fizzie's program uses ftell
21:36:20 <ais523> and thus is bounded by off_t limits and so not TC
21:36:48 <ais523> but a program that didn't ftell could still be TC
21:37:42 <fizzie> http://sprunge.us/iMEW?c I think that's better w.r.t. the initial program loading. I'm probably not going to work around that TC limitation.
21:38:13 <fizzie> Though it could be done very trivially by looking at brainfuck without output, in which case stdout can be dedicated for the tape, and can grow to arbitrary size without ftell issues.
21:38:24 <fizzie> (Brainfuck without output is kind of boring, though.)
21:40:10 <Sgeo> http://paradoxspace.com/
21:40:41 <Sgeo> http://www.paradoxspace.com/fourohfour
21:40:48 <fizzie> I'm still not entirely sure something like fwrite(&errno, 1, 1, stderr); is completely valid, since I guess if library functions are free to set errno whenever they want, fwrite could e.g. zero errno before reading in the bytes.
21:42:59 <olsner> I think most functions only modify errno if there's an error
21:43:05 -!- oerjan has joined.
21:43:57 <olsner> not sure if they don't have to change it or if they must not change it though
21:44:12 <ais523> I think they have to leave it the same, but maybe can change it during the call
21:44:25 <ais523> that's supposed to be unobservable because errno's thread-local
21:44:34 <ais523> I hadn't thought of passing &errno as a buffer to write before today
21:48:04 <olsner> I suspect you can't take the address of errno, e.g. because it could be a macro that expands to a function call
21:48:47 <oerjan> `addquote <int-e> like good old time, with elbow and foot lengths of the king. <Slereah_> man that must have sucked <Slereah_> People would be always like "Hey king, can you drop by, I have stuff to measure" <Jafet> That's why they're called rulers, you know
21:48:48 <HackEgo> 1184) <int-e> like good old time, with elbow and foot lengths of the king. <Slereah_> man that must have sucked <Slereah_> People would be always like "Hey king, can you drop by, I have stuff to measure" <Jafet> That's why they're called rulers, you know
21:49:00 <ais523> olsner: it's defined as an lvalue, IIRC
21:49:12 <ais523> although I think it can be a macro that expands to a pointer dereference
21:49:46 <Jafet> It is normally a macro that expands to a pointer dereference of a function call.
21:49:59 <olsner> hmm, it would be a bit difficult to set errno if it's an rvalue
21:50:08 <ais523> is &*functioncall() legal?
21:50:08 <Jafet> `run echo $'#include <errno.h>\nerrno' | cpp | tail
21:50:09 <HackEgo> # 1 "/usr/include/x86_64-linux-gnu/asm/errno.h" 2 3 4 \ # 5 "/usr/include/linux/errno.h" 2 3 4 \ # 26 "/usr/include/x86_64-linux-gnu/bits/errno.h" 2 3 4 \ # 47 "/usr/include/x86_64-linux-gnu/bits/errno.h" 3 4 \ extern int *__errno_location (void) __attribute__ ((__nothrow__)) __attribute__ ((__const__)); \ # 37 "/usr/include/errno.h" 2 3 4 \ # 5
21:50:35 <ais523> that looks more like head than tail
21:50:40 <Jafet> Every lvalue should have an address.
21:51:22 <Jafet> `run echo $'#include <errno.h>\nint main() { return errno; }\n' | cpp | tail
21:51:22 <HackEgo> # 1 "/usr/include/x86_64-linux-gnu/asm/errno.h" 2 3 4 \ # 5 "/usr/include/linux/errno.h" 2 3 4 \ # 26 "/usr/include/x86_64-linux-gnu/bits/errno.h" 2 3 4 \ # 47 "/usr/include/x86_64-linux-gnu/bits/errno.h" 3 4 \ extern int *__errno_location (void) __attribute__ ((__nothrow__)) __attribute__ ((__const__)); \ # 37 "/usr/include/errno.h" 2 3 4 \ # 5
21:51:35 <Jafet> `run echo $'#include <errno.h>\nint main() { return errno; }\n' | cpp | rev
21:51:35 <HackEgo> ">nidts<" 1 # \ ">enil-dnammoc<" 1 # \ ">nidts<" 1 # \ 4 3 1 "h.onrre/edulcni/rsu/" 1 # \ 4 3 "h.onrre/edulcni/rsu/" 92 # \ 4 3 1 "h.serutaef/edulcni/rsu/" 1 # \ 4 3 "h.serutaef/edulcni/rsu/" 323 # \ 4 3 1 "h.sfederp/stib/ung-xunil-46_68x/edulcni/rsu/" 1 # \ 4 3 2 "h.serutaef/edulcni/rsu/" 423 # \ 4 3 "h.serutaef/edulcni/rsu/" 653 # \ 4 3 1 "h.s
21:51:45 <Jafet> `run echo $'#include <errno.h>\nint main() { return errno; }\n' | cpp | tac
21:51:46 <HackEgo> int main() { return (*__errno_location ()); } \ # 2 "<stdin>" 2 \ \ # 59 "/usr/include/errno.h" 3 4 \ # 37 "/usr/include/errno.h" 2 3 4 \ extern int *__errno_location (void) __attribute__ ((__nothrow__)) __attribute__ ((__const__)); \ # 47 "/usr/include/x86_64-linux-gnu/bits/errno.h" 3 4 \ # 26 "/usr/include/x86_64-linux-gnu/bits/errno.h" 2 3 4 \
21:52:25 <olsner> `run echo $'#include <errno.h>\nint main() { return errno; }\n' | cpp | grep main
21:52:26 <HackEgo> int main() { return (*__errno_location ()); }
21:55:52 <myname> side note: i am kinda disappointed that there is a cat replacement called dog but no tac replacement called god
21:56:48 -!- Sprocklem has quit (Quit: leaving).
21:56:59 -!- adu has quit (Quit: adu).
21:58:56 -!- adu has joined.
22:00:22 <zzo38> Can you notify Google of the bug in their server that isn't correctly implementing headerless HTTP?
22:00:39 <zzo38> (There are other bugs in their server too; sometimes a HEAD request returns 404 even though GET works properly.)
22:00:45 <fizzie> It's defined as a "modifiable lvalue" and the possibility of it being *somefunction() is explicitly mentioned.
22:02:57 <zzo38> myname: You are allowed to write such software if you like to make
22:03:36 <myname> zzo38: that doesn't sound like any fun at all
22:03:59 <zzo38> OK then don't write such program, if you don't want to write such program.
22:04:49 <myname> only advantage would be being the founder of god
22:12:09 -!- ais523 has quit.
22:16:41 -!- adu has quit (Quit: adu).
22:17:31 -!- password2 has quit (Ping timeout: 250 seconds).
22:29:34 -!- adu has joined.
22:31:11 -!- not^v has joined.
22:31:51 -!- ^v has quit (Read error: Connection reset by peer).
23:04:37 -!- nucular has quit (Quit: Excess Food).
23:09:40 -!- doesthiswork has quit (Quit: Page closed).
23:21:39 -!- yorick has quit (Remote host closed the connection).
23:41:27 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39310&oldid=39308 * Zerk * (+248) mostly/* Nock Interpreter */ apparently things are reversible, partially. Which I supposed was implied by "unification".
23:41:53 -!- contrapumpkin has joined.
23:43:34 <zzo38> I started writing this library in C (for Text Adventure Intermediate Language), and then I should probably also write one for Haskell, and one for SQL, as well. If you want any other programming language then write it by yourself please
23:43:46 -!- nooodl has quit (Quit: Leaving).
23:44:04 <zzo38> Maybe you have some idea how it could be represent by Haskell?
23:44:43 <zzo38> Do you have a better idea than I do?
23:45:30 -!- nisstyre has joined.
23:49:24 <Sgeo> I don't know what Text Adventure Intermediate Language is
23:53:31 <zzo38> Sgeo: http://sprunge.us/ULeC
23:54:52 -!- boily has joined.
23:59:13 -!- zzo38 has quit (Remote host closed the connection).
00:03:45 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:08:12 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39311&oldid=39309 * Zerk * (+9) /* A */ added [[Ax]]
00:08:16 <HackEgo> [wiki] [[Nock]] M http://esolangs.org/w/index.php?diff=39312&oldid=39289 * Zerk * (+22) Added [[Ax]]
00:08:23 <HackEgo> [wiki] [[Ax]] N http://esolangs.org/w/index.php?oldid=39313 * Zerk * (+3792) Created page with "Ax is a [[Nock]] derivative by [https://github.com/mnemnion mnemnion] aimed for nondeterminism, a more asthetic operator order, and sane big O. =Specification= This text speci..."
00:08:52 -!- xpte has joined.
00:13:32 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: relcome: not found
00:13:49 <boily> @tell elliott AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAURGH!
00:14:01 -!- Guest46968 has changed nick to ellioyy.
00:14:03 -!- ellioyy has changed nick to elliott.
00:14:07 -!- elliott has quit (Quit: Reconnecting).
00:14:17 -!- elliott_ has joined.
00:14:22 -!- elliott_ has changed nick to elliott.
00:14:26 <HackEgo> [wiki] [[Smartboxes]] M http://esolangs.org/w/index.php?diff=39314&oldid=39297 * Zerk * (+24) Increased wiki dual-linkedness, i.e. blatantly promoting my own nearly identical version.
00:14:54 <boily> elliott: there you are, you infamous scallywag!
00:18:32 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39315&oldid=39310 * Zerk * (-14) /* Nock Interpeter */ recursion fix
00:24:40 <boily> hi. how are you doing by this fine evening?
00:25:01 -!- metasepia has joined.
00:47:06 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39316&oldid=39315 * Zerk * (+101) Added string representation.
00:51:55 -!- contrapumpkin has changed nick to copumpkin.
01:01:06 -!- boily has quit (Quit: CHICKEN CHAPTER 14).
01:01:09 -!- metasepia has quit (Remote host closed the connection).
01:04:38 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
01:16:58 -!- oerjan has quit (Quit: leaving).
01:29:27 -!- adu has quit (Quit: adu).
02:05:15 <HackEgo> lumcoin iiichcoin ostcndoncoin constinycoin graniccoin eichcoin befucoin ever2coin excelumbftancoin quyrecoin iptifcoin filecoin snorisccoin singecoin quycoin systepcoin broacoin scribildcoin uddencoin c-loncoin
02:06:21 <HackEgo> cat: $(which coins): No such file or directory
02:06:43 <HackEgo> words ${1---eng-1M --esolangs 20} | sed -re 's/( |$)/coin\1/g'
02:14:30 -!- tromp has joined.
02:15:47 <Sgeo> I wish Kickstarter could let you donate to stretch goals and refund if stretch goal not met
02:15:59 <Sgeo> Well, that may be a bad idea, but that's what I want to do with this one Kickstarter
02:16:21 <Sgeo> https://www.kickstarter.com/projects/1554093685/erfworld-print-book-2-and-draw-book-3
02:27:50 -!- nisstyre has joined.
03:08:05 * kmc gets very confused by a file that turns out to have a space at the start of its name
03:16:49 -!- Sorella has quit (Quit: It is tiem!).
03:34:08 <Jafet> Hmm, ls and zsh seem to be unsurprised by strange filenames
03:35:22 <Jafet> touch $'a\nb\tc'; cat a<tab>$'\n'b$'\t'c
03:38:38 -!- zzo38 has joined.
03:39:03 <zzo38> Write message about Spanish Oteric channel in Spanish, so that Spanish people can understand.
03:39:19 <zzo38> (Otherwise, only English people will try to understand)
03:50:40 -!- not^v has quit (Read error: Connection reset by peer).
03:51:08 -!- not^v has joined.
03:59:29 <Sgeo> http://www.reddit.com/r/wesnoth/comments/1cnir2/growing_wesnoth_with_bitcoin_would_this_idea_be/c9ii3c3
03:59:41 <Sgeo> Bitcoin people are starting to scare me
04:00:32 <Sgeo> On the other hand, I now have a lot of respect for the Wesnoth devs
04:01:08 <kmc> they're only just now starting to scare you?
04:04:34 -!- adu has joined.
04:33:41 -!- tromp_ has quit (Ping timeout: 240 seconds).
04:33:54 -!- tromp_ has joined.
04:35:37 -!- copumpkin has joined.
04:35:39 -!- copumpkin has quit (Client Quit).
04:36:04 -!- copumpkin has joined.
04:47:49 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
05:30:33 <shachaf> elliott: I've changed my mind on Dinosaur Comics, by the way.
05:36:27 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:43:14 -!- MindlessDrone has joined.
05:56:43 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39317&oldid=39316 * Zerk * (+259) Fixed decrement-is-expensive logic /* Sugar */ conjunctions
06:07:46 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:09:29 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=39318&oldid=39216 * 88.217.159.238 * (+99) Add shellfuck - a Brainfuck interpreter written in shell script.
06:20:03 -!- AnotherTest has joined.
06:22:35 -!- Slereah_ has joined.
06:34:20 -!- password2 has joined.
06:48:58 -!- MoALTz_ has quit (Quit: bbl).
07:02:23 -!- Slereah_ has quit (Ping timeout: 245 seconds).
07:03:17 -!- Slereah_ has joined.
07:12:15 -!- Slereah_ has quit (Ping timeout: 250 seconds).
07:15:04 -!- augur has quit (Ping timeout: 258 seconds).
07:21:33 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39319&oldid=39317 * Zerk * (+138) Added section /* Unification */
07:30:50 -!- augur has joined.
07:35:41 -!- augur has quit (Ping timeout: 240 seconds).
07:45:28 -!- augur has joined.
07:50:43 -!- augur has quit (Ping timeout: 258 seconds).
07:52:16 -!- augur has joined.
07:53:49 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
07:57:56 <b_jonas> Jafet: ls in gnu coreutils has at least three quoting modes: don't quote anything, replace with question marks, quote with octal backslash escapes
07:58:02 -!- augur has quit (Ping timeout: 276 seconds).
07:59:41 -!- augur has joined.
08:00:50 -!- Tritonio has joined.
08:03:19 -!- adu has quit (Quit: adu).
08:07:50 -!- MindlessDrone has joined.
08:29:20 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39320&oldid=39319 * Zerk * (+336) Defined what assignment actually is. Which upon recollection was more useful that what I'd been writing in, resulting in considerable refactoring.
08:33:28 -!- conehead has quit (Quit: Computer has gone to sleep).
08:39:03 -!- augur has quit (Remote host closed the connection).
08:41:22 -!- Patashu has joined.
08:42:07 -!- Patashu has quit (Client Quit).
08:48:34 -!- augur has joined.
08:57:41 -!- password2 has quit (Ping timeout: 240 seconds).
09:17:52 -!- Frooxius has quit (Read error: Connection reset by peer).
09:45:34 -!- vravn has quit (Ping timeout: 240 seconds).
09:46:55 -!- nortti has quit (Ping timeout: 240 seconds).
09:47:11 -!- nortti has joined.
09:48:32 -!- vravn has joined.
10:19:01 -!- boily has joined.
10:45:02 -!- nucular has joined.
10:45:02 -!- nucular has quit (Changing host).
10:45:02 -!- nucular has joined.
10:45:40 -!- oerjan has joined.
11:04:46 -!- yorick has joined.
11:06:30 -!- boily has quit (Quit: Poulet!).
11:23:59 <fizzie> "New CSC service available - Pouta cloud / Uusi CSC Pouta-pilvipalvelu käytettävissä" so punny
11:24:22 <fizzie> ("Pouta" is Finnish for non-rainy weather, and "poutapilvi" is a non-rainy cloud. (There might be a more exact definition.))
11:31:22 -!- xpte has quit (Quit: Connection closed for inactivity).
12:16:02 -!- Sgeo has quit (Read error: Connection reset by peer).
12:38:36 <fizzie> Fun fact: the DOM interface to HTML5 audio/video stuff has a canPlayType(mimeType) function; it returns the empty string, the string "maybe" or the string "probably". I guess it's good not to be overly confident.
12:39:45 <fizzie> It's supposed to return "probably" if "the user agent is confident that the type represents a media resource that it can render", the empty string if it's "a type that the user agent knows it cannot render", and "maybe" otherwise.
12:42:44 <fizzie> (I haven't yet mananged to coax anything more than a "maybe" out of Chrome.)
12:49:16 <Taneb> poutapilvi is a good word
12:50:17 <b_jonas> fizzie: well sure, most of these media containers can contain any codec in their insides
12:51:46 <fizzie> Yes, and I haven't gotten even a "maybe" out of the more niche one-format-only MIME types.
12:53:06 <fizzie> Though I'd assume something like WebM strictly speaking has a fixed list of allowed codecs? (Maybe it's still "maybe" for future changes, though.)
12:53:31 <fizzie> Ah -- "Generally, a user agent should never return "probably" for a type that allows the codecs parameter if that parameter is not present."
12:54:11 <fizzie> Right, 'audio/webm;codecs="vorbis"' -> "probably".
12:54:16 <fizzie> Well, that all makes sense.
12:55:08 <fizzie> Still, a protocol of lesser moral integrity would have spec'd "yes" as the response for "confident -- it can render".
12:58:57 <b_jonas> fizzie: there are so many broken video files around us that even if you know the codec you can't be sure about anything
12:59:18 <b_jonas> also buggy decoder software
12:59:49 <b_jonas> haven't you ever see broken jpegs, pngs and avis?
13:00:13 <int-e> the specification is ridiculous though
13:01:00 <int-e> (What were they thinking? 'No, we can't use "no" for "no", because then if() would think it's true.'?!)
13:02:43 <fizzie> b_jonas: Arguing from that point of view, you couldn't answer "probably" either, since you can never be sure.
13:03:13 <int-e> the best thing is that if you are sure, you have to answer "" or "probably".
13:04:37 <fizzie> Haven't you heard the campaign slogan? "'' means no!"
13:06:19 -!- nooodl has joined.
13:06:25 <b_jonas> int-e: should return "do'neh'lini" and "a'la'ih" for no and yes
13:07:23 <b_jonas> int-e: and then people will write checks like ("do’neh’lini" == value) in their code and wonder why it fails
13:09:49 <int-e> different quotes. fun.
13:43:34 -!- hern has joined.
13:45:56 -!- hern has quit (Client Quit).
14:14:55 -!- Frooxius has joined.
14:52:35 -!- oerjan has quit (Quit: leaving).
15:12:19 -!- conehead has joined.
15:16:25 -!- Sellyme has quit (Excess Flood).
15:18:24 -!- Sellyme has joined.
15:33:37 -!- Tritonio has quit (Ping timeout: 250 seconds).
16:04:17 -!- zzo38 has quit (Remote host closed the connection).
16:05:11 -!- ^v has joined.
16:08:04 <HackEgo> [wiki] [[Special:Log/newusers]] create * Ctrl-shift-esc * New user account
16:26:15 <HackEgo> [wiki] [[Keya]] N http://esolangs.org/w/index.php?oldid=39321 * Ctrl-shift-esc * (+1528) Keya is a Brainfuck influenced language
16:28:10 -!- nisstyre has joined.
16:28:12 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39322&oldid=39311 * Ctrl-shift-esc * (+11)
16:34:53 -!- zzo38 has joined.
16:46:12 -!- zzo38 has quit (Remote host closed the connection).
16:47:31 -!- xpte has joined.
17:03:28 -!- Phantom_Hoover has joined.
17:19:53 -!- augur has quit (Ping timeout: 245 seconds).
17:30:14 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
17:30:24 -!- password2 has joined.
17:31:34 -!- password2 has quit (Max SendQ exceeded).
17:32:33 -!- password2 has joined.
17:33:13 -!- password2 has quit (Max SendQ exceeded).
17:46:03 -!- Slereah_ has joined.
17:51:35 -!- augur has joined.
17:54:28 -!- MindlessDrone has quit (Ping timeout: 245 seconds).
17:55:06 -!- augur has quit (Read error: Connection reset by peer).
18:11:10 -!- MindlessDrone has joined.
18:11:13 -!- Sprocklem has joined.
18:25:48 -!- Sprocklem has quit (Quit: leaving).
18:33:16 <myname> "brainfuck influenced" sounds euphemistic
18:36:18 <fizzie> I was wondering if it's the 2D-grid-in-place-of-tape brainfuck that was discussed here on channel a while ago, or some other 2D-grid-in-place-of-tape brainfuck.
18:41:57 -!- MoALTz has joined.
18:43:21 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:44:24 <Slereah_> Is there an infinite dimensional brainfuck
18:48:06 <fizzie> There's an arbitrary-dimensional one, at least.
18:50:04 <fizzie> Dimensifuck claims to be infinite-dimensional.
18:50:45 <fizzie> Its wiki article also links to two sprunge.us pastes that have since passed away.
18:50:48 <Slereah_> I was gonna ask about a 0-dimensional one, but that's just a push down automaton
18:51:57 <Slereah_> Like maybe you add Fourier modes or something
18:52:00 <fizzie> That sounds vaguely familiar, but I may be just thinking of the debacle that was continuous chess.
18:52:47 <int-e> fizzie: aww. I was hoping it'd change <> to go forward/backward in the dimension specified by the current cell, which does not obviously preserve Turing-completeness.
18:53:14 <Slereah_> I wonder if a continuous brainfuck would be equivalent to an Oracle machine
18:53:24 <fizzie> Aww, I was hoping Wayback machine archived sprunge.us pastes.
18:54:31 <Slereah_> Continuous Turing machines are equivalent to oracles
18:54:33 -!- password2 has joined.
18:56:46 -!- password2 has quit (Max SendQ exceeded).
19:17:13 -!- sebbu has quit (Ping timeout: 252 seconds).
19:17:33 -!- password2 has joined.
19:29:17 -!- password2 has quit (Ping timeout: 240 seconds).
19:31:16 <fizzie> olsner: Oh, 9983361024 bytes (10 GB) copied, 64370.4 s, 155 kB/s
19:32:39 <int-e> and it's speeding up, too.
19:32:48 <int-e> (it's now faster than my internet connection ;-) )
19:34:42 <fizzie> That was actually the last part, the other six gigs finished earlier.
19:35:13 <olsner> is myndzi a bot or a human btw?
19:35:56 <fizzie> A human with a script has been my understanding.
19:36:32 <int-e> so a bot that lost its human?
19:36:59 <olsner> or a human that lost its human?
19:37:40 <int-e> <prefix?>celebrate
19:38:16 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
19:38:16 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c |
19:38:16 <myndzi> >\ c.c |\ /| | | |\ c.c /| | /| | |\ c.c /'\
19:51:19 <olsner> hmm, Steins;Gate is an anime involving SERN [sic] running some time travel conspiracy, and something called a "Reading Steiner" that lets you remember other timelines
19:51:22 -!- sebbu has joined.
19:51:57 <olsner> oh, and it's currently the all-time best anime (according to animenewsnetwork)
19:52:01 -!- sebbu has quit (Changing host).
19:52:01 -!- sebbu has joined.
19:52:13 <fizzie> The "Sonseil Européen pour la Recherche Nucléaire"?
19:53:17 <olsner> or perhaps the sonseiru oiropeen pure ra etc
19:53:42 <Bike> currently the all time <-- help
19:54:28 <fizzie> It's not like one thing would always be the best all-time something.
19:55:11 <olsner> currently the all-time-up-until-now, I guess
19:56:39 <olsner> I would've been fine with this if it was obviously a parody though (and I haven't watched it or anything)
19:57:45 <Bike> cern stands for "Organisation Européenne pour la Recherche Nucléaire " so i think we can cut the animes some slack
20:00:38 <Bike> hm cern hasn't amde antiwater yet. disappointing
20:02:06 <olsner> Bike: the semicolon in the name though
20:02:39 <Bike> the same people made "ChäoS;HEAd"
20:04:44 <olsner> the spinoff Chäos;Head Love Chu Chu! would be a great name for an esolang though
20:08:32 <fizzie> And I thought the .hack folk were bad when it came to punctuation.
20:10:25 <fizzie> (I've only watched .hack//SIGN out of it.)
20:23:12 -!- augur has joined.
20:32:22 -!- ^v has quit (Read error: Connection reset by peer).
20:32:45 -!- ^v has joined.
20:39:14 <kmc> TIL that the train providing high speed service between Helsinki and St Petersburg is built to 1522 mm gauge, which is the average of finnish (1524 mm) and russian (1520 mm) gauge
20:39:23 <kmc> so that it runs equally well (equally poorly?) on both networks
20:40:04 <Bike> that's a pretty small gauge difference
20:40:42 <kmc> yeah, low speed trains of either gauge work fine on either gauge
20:41:38 <Bike> http://skreened.com/dumbstuff/funny-meme unrelated
20:41:42 <Slereah_> Man I saw gauge and I thought it was ##physics
20:42:38 <Bike> gauge in a physics context just makes me think of a tao post i half remember
20:44:08 <Slereah_> Gauge can get pretty weird in GR
20:48:50 <fizzie> I think I passively knew that fact.
20:52:10 -!- oerjan has joined.
21:04:53 -!- nooodl has quit (Remote host closed the connection).
21:05:10 <HackEgo> [wiki] [[NRSRSSOMN]] N http://esolangs.org/w/index.php?oldid=39323 * EzoLang * (+2366) Created page with "'''NRSRSSOMN''' (Nameless Random String-Rewriting Systems Scribbled On Math Notebook) are a collection of [[:Category:String-rewriting paradigm|string-rewriting systems]] crea..."
21:05:19 -!- nooodl has joined.
21:05:35 <HackEgo> [wiki] [[User:EzoLang]] http://esolangs.org/w/index.php?diff=39324&oldid=32157 * EzoLang * (+15)
21:07:16 <Slereah_> it's gonna be a language where data is zoo animals
21:07:25 <Slereah_> And it is in cage data structures
21:08:32 <nortti> oh wow, I somehow though that 12yo-me would've known better with nicks. though that it was at least 10yo-me
21:10:04 <Slereah_> 14 years old me didn't foresee that using your real name online would turn out bad in the future
21:10:50 <Bike> what's bad about it for you
21:11:08 <Slereah_> 'cause now people can casually google you
21:11:12 -!- nucular has quit (Quit: Switching to phone).
21:11:55 <Bike> https://www.google.com/search?q=fizzie+freenode more a function of uniqueness, i would think
21:12:16 <Slereah_> I think that guy said it best :
21:12:22 <Slereah_> age 11: worry about internet people finding me in real life, now: worry about people in real life finding me on the internet
21:12:23 <Bike> "bike freenode" gets you a lot of articles about lilo dying, apparently
21:18:06 <oerjan> ok so i googled Ørjan Johansen just now...
21:18:45 <oerjan> the first page gives no relevant _text_ hits.
21:18:49 <fizzie> You need to go like to the seventh result of "fizzie freenode" to get a page with my real name on it.
21:18:50 -!- tertu has joined.
21:18:57 <fizzie> (At least as sorted for me.)
21:19:00 <oerjan> but there's a picture of me, which i had no idea was on the internet.
21:19:15 <oerjan> it's _not_ the one i've shown you before.
21:19:39 <fizzie> "Ørjan Johansen, leder for Miljøpartiet De Grønne (MDG) i Time --" I didn't know you were in politics.
21:19:55 <oerjan> my esolang page is on the second page of hits, though.
21:20:32 <oerjan> although coincidentally i _did_ vote for that party last election.
21:20:57 <oerjan> which was, given the election rules, afaict a wasted vote
21:21:32 <fizzie> I also didn't know you were in the field of "psychedelics, MDMA, drug policy, public health and evidence-based medicine".
21:21:36 <oerjan> (they got no representative from my county, and not enough total votes to get extra ones.)
21:21:50 <Bike> fizzie: kmc is well known to be infectious
21:23:17 <oerjan> my stackoverflow page is on page 4
21:23:50 <fizzie> My real name is terribly Googleable, since I believe it's unique. :/
21:25:52 <oerjan> oh the picture is one the university got on the press release from when i got the doctorate.
21:25:57 <fizzie> At least the image search for it has just two instances of my face, and then a whole lot of people, some of whom I know and some entirely unfamiliar.
21:28:07 <oerjan> http://www.ntnu.no/doktorgrader/dr.scient/09.98/johansen.html fwiw
21:28:34 <fizzie> That's strangely normal.
21:28:53 <fizzie> I don't know what I was expecting, but I was expecting something surprising.
21:29:17 <Bike> well, he's wearing makeup to hide the scar
21:29:19 <kmc> you expected a surprise and you were surprised
21:29:28 <oerjan> i'm not sure if they took that picture themselves, or if it's from that one passport photo i was particularly satisfied with once
21:30:14 <fizzie> I just cropped my face out of our professional-photographer-taken research group photo when I needed an up-to-date face for a thing.
21:30:21 * oerjan vaguely remembers that shirt
21:33:08 <oerjan> can't find any others, that might be the only one reachable through the web
21:37:13 <fizzie> Speaking of trains, they recently introduced two-floor restaurant carriages in the (two-floor) Intercity trains in Finland.
21:38:05 <fizzie> (Though the upstairs is just more or less regular seating.)
21:40:14 <fizzie> They claim it's a unique concept, but it might be just something they say.
21:40:18 -!- augur has quit (Ping timeout: 245 seconds).
21:40:39 <fizzie> http://www.vr.fi/en/index/palvelut/tietoja_junista/intercity/duettoplus.html in any case.
21:41:01 <oerjan> fizzie: do they have amusing accidents while bringing food up/down the stairs
21:41:24 <fizzie> oerjan: I would certainly assume so.
21:41:35 <oerjan> Phantom_Hoover: i am not a train hth
21:42:44 <oerjan> you brits and your weird spelling of skeptical
21:43:43 <lexande> fizzie: i am surprised they have many lines lone enough to justify that, it's only two hours to tampere right? i guess if you're going to oulu or something
21:43:54 <oerjan> fizzie: no i think that means american in cockney hth
21:44:11 <fizzie> lexande: They have introduced them, in fact, on the line from Helsinki to Oulu.
21:44:25 <fizzie> And it is indeed two hours to Tampere.
21:45:14 <lexande> anyway amtrak has double-deck "cafe/lounge" cars on its western routes with the cafe downstairs and tables with seating both downstairs and upstairs, IIRC
21:46:27 <fizzie> I was going to say it's something like six-seven-eight hours to Lieksa, except (a) they no longer have a single service going the whole way, and (b) it only takes four and a half hours to Joensuu nowadays. This truly is the future.
21:46:37 <lexande> i have never taken a train in finland :( ... well i took the helsinki metro a couple times
21:46:42 <fizzie> (We used to go Helsinki-Lieksa-Helsinki at least twice a year.)
21:47:11 <fizzie> Also ridiculous: the vr.fi netshop is closed from 22:30 to 06:00, because... I don't know, the servers need to sleep too?
21:47:30 <fizzie> (You can only look up schedules, not buy tickets.)
21:48:09 <fizzie> I guess they want someone to be looking after it at all times, but it's not like other companies generally seem to have trouble keeping their web-shops open.
21:49:06 <lexande> megabus used to not let you use the site at all between 03:00 and 05:00 or something
21:49:07 <fizzie> Besides, I'm reasonably sure the ticket vending machines are open 24/7.
21:49:07 <oerjan> <Bike> hm cern hasn't amde antiwater yet. disappointing <-- i have a hunch anti-oxygen might prove tricky?
21:49:11 <lexande> dunno if that's still the case
21:49:39 <fizzie> They made some anti-molecules already. (Anti-H_2, maybe?)
21:50:36 <Bike> "Antideuterium,[21][22] antihelium-3 (3He)[23][24] and antihelium-4 (4He) nuclei[25] have been produced so far"
21:50:41 <Bike> (in addition to antihydrogen)
21:51:15 <fizzie> I guess I misremembered some of those news, then.
21:51:23 <Bike> it's cool how we've made antihydrogen but still don't know how it's subjected to gravity
21:51:36 <Bike> fizzie: clearly you mistook 2H and H2
21:52:14 <oerjan> ok so they've at least managed helium
21:52:35 <oerjan> i wonder if they've managed to make normal oxygen "from scratch"
21:53:05 -!- lexande has quit (Quit: Lost terminal).
21:53:22 <Bike> Can you even do that without triple alpha?
21:53:28 <Bike> from fusion of hydrogen, i assume
21:53:35 <oerjan> starting with hydrogen yeah
21:53:46 <Phantom_Hoover> yeah in that case i doubt it, it's an awful lot of fusion to be doing
21:54:27 <Bike> i'm pretty sure triple alpha can't be done in any laboratory we're going to have in the next thousand years
21:54:59 <fizzie> Except in the big one we inherited.
21:55:43 <fizzie> (The "runaway laboratory experiment" theory of solar system foundation.)
21:55:53 -!- AnotherTest has quit (Ping timeout: 276 seconds).
21:55:54 -!- lexande has joined.
21:56:22 <Bike> http://en.wikipedia.org/wiki/Alpha_process right, you need carbon to get the "metals", and for carbon you need triple alpha
21:56:24 <oerjan> Bike: i dunno, we don't have to do it continuously...
21:56:50 <oerjan> maybe some kind of "shoot things at a point" setup...
21:57:23 <oerjan> well a collider, but with less power and more incoming paths
21:57:38 <oerjan> enough to get a few atoms
21:58:09 <oerjan> 3 beams of alpha particles crossing
21:58:36 <Bike> can things actually be coordinated to get a termolecular interaction? i mean you're talking a 10^-17 second window
21:59:46 <oerjan> how does the sun manage it
22:00:12 <oerjan> we can't beat it on pressure, but maybe on precision?
22:00:13 -!- augur has joined.
22:00:46 <oerjan> Taneb: did you read DMM's latest sunday annotation
22:00:53 <Taneb> oerjan, I am afraid I didn't
22:01:00 <fizzie> oerjan: Breaking news: solar fusion mathematically proven to be impossible, Sun shuts down.
22:02:23 <oerjan> fizzie: i vaguely recall there was a scifi story where the plot was that the alien's ftl system didn't make sense, and when the humans showed them the experiments to prove relativity their starship broke down...
22:02:26 <fizzie> (Like what happened with all the... what was the thing that was supposedly unable to fly?)
22:02:36 <Bike> well the fact it is possible was pretty surprising
22:02:57 <Bike> since it relies not just on the three-molecule thing but also on some energy resonance business i don't know shit about
22:03:04 <Bike> god fuck that bumblebee thing
22:03:07 <oerjan> the bumblebees are secretly using invisible stilts
22:03:21 <Bike> fluids behave differently at different scales breaking news
22:03:46 <Phantom_Hoover> the people making the claim generally don't understand things in that depth anyway
22:03:50 <oerjan> Bike: let's not go ballistic over dead unicorn tropes.
22:04:07 <Bike> yeah i know, it's just super irritating. insect flight is cool!!
22:04:43 <Bike> oerjan: and nah dude i've seen actual people say science says bumblebees can't fly, not that they know shit about anything ofc
22:05:13 <Phantom_Hoover> i like those tiny wasps that just have like a strut with lots of tiny filaments coming off
22:05:25 <Taneb> oerjan, now I have read it and maintain my opinion that science is scary
22:05:41 <Taneb> But hey, one synonym of scary is awesome
22:06:32 <oerjan> Taneb: also just in case you're entirely out of the loop, DMM started a new comic, which he actually draws.
22:06:40 <Taneb> Yeah, I think you linked me that
22:06:43 <Taneb> Every wednesday, right?
22:06:59 <Phantom_Hoover> have you noticed how the real numbers are kind of crazy but going full constructivist is even crazier
22:07:01 <Taneb> I'll try to keep up with it
22:07:08 <Taneb> Phantom_Hoover, everything is scary
22:07:23 <Bike> Phantom_Hoover: i have a few pdfs named things like 'more-finitist-crap' i can look at when i need a laff
22:07:32 <oerjan> he said crazy not scary * swats Taneb -----###
22:07:59 <Taneb> oerjan, things can be scary AND crazy
22:08:17 <oerjan> Bike: well the unicorn part is that any scientist ever claimed it, i guess.
22:08:42 <Taneb> Oh man, I think I remember the finitists
22:09:14 <olsner> what's scary about the real numbers? integers are scarier
22:09:40 <Bike> http://www.businessinsider.com/i-was-assaulted-for-wearing-google-glass-2014-4 most cyberpunk thing i've seen all day
22:09:42 <tertu> why does finitism even exist
22:09:59 <Bike> because exponentiation isn't total maaaaan
22:10:09 <Taneb> tertu, because things are scary and when some people see scary things they get afraid and try to rationalize to what they understand
22:10:51 <tertu> why not just accept it? you don't have to think of it as real, just think of it as a formalism that makes things easier to do or something.
22:10:58 <Taneb> Accepting is hard to do
22:12:06 -!- boily has joined.
22:12:21 -!- metasepia has joined.
22:12:22 <metasepia> CYUL 142207Z 27010G16KT 12SM -SHRA BKN075 OVC120 OVC220 20/12 A2951 RMK AC6AC2CS1 CS TR PRESRR SLP995 DENSITY ALT 1100FT
22:12:57 <tertu> so that's platonist in that it's proposing that somehow things that are otherwise real can somehow not be?
22:13:07 <Taneb> I haven't actually accepted that numbers exist
22:13:12 <Bike> just since you said "real"
22:14:04 <metasepia> EFHK 142150Z 23004KT CAVOK 03/02 Q0998 NOSIG
22:14:42 <metasepia> EGNT 142150Z 00000KT CAVOK 03/02 Q1029
22:15:02 <boily> it's not the size that counts, but how hot it is.
22:15:46 <fizzie> 03/02 seems to be popular.
22:16:38 <boily> that's too mainstream for me. have you heard of 20/12? probably not; they're very obscure numbers.
22:17:17 <olsner> `pastelog olsner.*~metar
22:17:20 <HackEgo> /hackenv/bin/pastelog: line 2: cd: /var/irclogs/_esoteric: No such file or directory \ grep: ????-??-??.txt: No such file or directory \ http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.30653
22:17:48 <olsner> hmm, guess not... does boily remember my metar code?
22:17:57 <boily> olsner: where are you again?
22:18:03 <metasepia> ESSA 142150Z 30006KT CAVOK 03/01 Q1002 R88/0///95 NOSIG
22:18:04 <metasepia> ESSB 142150Z AUTO 27003KT 9999NDV OVC220/// 04/02 Q1002
22:18:14 <Bike> really, have you ever seen proof that 20 exists
22:18:58 <olsner> I believe in 20 about as much as Canada
22:19:04 <boily> Bike: I'm Canadian. I embody conjectual existence.
22:20:52 <Bike> well, we have an example of a canada person right here, but i've yet to see a 20
22:21:28 <boily> Taneb, please prove that numbers exist.
22:21:29 <shachaf> gaSSSSSSSSSSSSSSSSSSSSZpacho
22:21:38 <lexande> Bike: you only think they're an example of a canada person, whereas we can prove things about 20
22:21:40 <Taneb> boily, I don't believe they do
22:21:44 <lexande> maths is real, physics might be fake
22:21:48 <HackEgo> gaszpacho is a polish soup, traditionally szerved cold for hot szummer days
22:21:50 <Bike> lexande: oh yeah, things like what
22:22:13 <boily> . o O ( hm. what was the entry again... )
22:22:28 <HackEgo> bookwatching is when you conflagrate birdwatching and the books used to identify them in the same object.
22:22:40 <HackEgo> disflagrate v.t.perf.: a traditional technique from Poland (earliest attestation c. 1042) used to separate szoups. Nowadays, commercial production is entirely mechanized.
22:22:44 <HackEgo> You like Gazpacho and I like Gaspacho. Let's call the whole thing off!
22:22:49 <Bike> boilyisms finally catch up w/im
22:23:00 <shachaf> when i was in spain i ate a lot of gazpacho
22:25:18 -!- tertu has quit (Ping timeout: 245 seconds).
22:27:43 <boily> the set of gazpachoes only has a cardinality of two.
22:28:33 <olsner> I think the set is infinite but we have a small selection of them in hackego
22:28:52 <HackEgo> A szoup a szilárd tápszereknek híg alakban való elkészítése a célból, hogy könnyebben emészthetők legyenek; a hígító anyag a viz, mely feloldja s magába veszi a tápanyag legértékesebb részeit.
22:29:15 <HackEgo> Phở là một món ăn truyền thống của Việt Nam, cũng có thể xem là một trong những món ăn đặc trưng nhất cho ẩm thực Việt Nam.
22:29:31 <fizzie> The szoup in Spain falls mainly on the plains.
22:31:32 <HackEgo> gazspaczo iz a hungarian szoup, tradizsonally szerved cold for hot szummer dayz
22:33:37 <oerjan> `learn gaspasjo is a norwegian soup, which died out due to a lack of hot summer days
22:34:05 <oerjan> `learn gaspatsjo is a norwegian soup, which died out due to a lack of hot summer days
22:34:28 <olsner> traditionally served warm for cold summer days?
22:34:40 <oerjan> `learn gaspatsjo was a norwegian soup, which died out due to a lack of hot summer days
22:34:50 <oerjan> olsner: that's like, every other soup.
22:35:07 <Taneb> I am now in awe about how hard it is to define the real numbers
22:35:07 -!- Sorella has joined.
22:35:12 <Taneb> But how simple the definition is
22:36:08 <shachaf> `run translatefromto en no soup
22:36:09 <HackEgo> This google api no longer exists.
22:36:34 <boily> oerjan: ♪ping♪ your Norwegian soup was PDFed.
22:36:58 -!- yorick has quit (Read error: Connection reset by peer).
22:37:34 <olsner> shachaf: no:suppe, sv:soppa
22:39:08 <Taneb> Archimedean complete totally ordered field
22:40:14 <shachaf> Taneb: oh, i thought you were, like, constructing them
22:40:39 <Taneb> I don't have the patience for constructivism
22:42:45 <Bike> dedekind cuts don't seem hard
22:43:26 <shachaf> dedekind cuts are the best
22:43:53 <shachaf> you should have a good word for soup like hebrew does
22:45:33 <fizzie> fi:keitto we like to be different.
22:48:18 <boily> fizzie: even the Estonians agree with the Sensible Way; ee:supp.
22:48:54 <fizzie> Well, "soppa" is used colloquially.
22:50:00 <fizzie> Though probably only for less fancy soups.
22:50:13 <Taneb> I hope you all have nice soup
22:52:26 * oerjan super en sup suppe til supéen
22:52:59 * boily pige que dalle à ce qu'oerjan dit.
22:54:17 <oerjan> shit this qu'oerjan said boily freelancing indeed.
22:55:13 <boily> ow. oooooow. I think I sprained the language zone in my brain trying to parse that.
22:55:39 <oerjan> ...then think of poor google translate which produced it.
22:56:07 * boily pats google translate. “sorry, bud. won't do that again. at least for a while.”
22:57:43 <oerjan> btw, super=sips (v), sup=sip (n), supé=supper (n, excessively formal)
22:58:45 -!- nooodl has quit (Ping timeout: 252 seconds).
22:59:56 <oerjan> (the informal word would be kveldsmat)
23:01:35 <boily> déjeuner, dîner, souper. as it should be, not like from those weird Frenchmen.
23:01:39 <oerjan> 'In most parts of The United States and Canada today, "supper" and "dinner" are considered synonyms.'
23:02:44 <fizzie> For the record, fi:keitto is derived from the verb "keittää", to boil something. (But only the transitive verb; if something's just boiling, the verb is "kiehua".)
23:02:57 <fizzie> oerjan: That's supperb.
23:05:06 -!- Sgeo has joined.
23:05:25 <fizzie> (I guess you could use "kiehuttaa" in place of "keittää", but it sounds slightly clunky. But "kiehauttaa" -- to bring to a boil, to parboil -- is a word that is used.)
23:06:14 <fizzie> (Languages are so silly.)
23:06:33 <oerjan> sounds like the difference between "koke" and "koke opp" in norwegian.
23:07:09 <fizzie> That sounds like the difference between cocaine and the actual act of snorting cocaine.
23:09:12 <fizzie> "Kokkeli" is a Finnish (very) colloquial term for cocaine, though it actually means curd, or in "munakokkeli" scrambled eggs.
23:09:32 <oerjan> i think with the right dialectical munging i can get the "kokain" and "koka inn" to sound similar.
23:09:33 <fizzie> I assume it's related to "coagulate".
23:10:49 <oerjan> (the later would mean boiled off of all liquid, or thereabouts)
23:11:12 -!- nooodl has joined.
23:13:18 <fizzie> Welp, good soup from me too. ->
23:18:18 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39325&oldid=39320 * Zerk * (+1193) Added sugared and defined chain assignment
23:22:50 -!- boily has quit (Quit: WHARGHARBL CHICKEN).
23:22:52 -!- metasepia has quit (Remote host closed the connection).
23:22:58 -!- Phantom_Hoover has quit (Quit: Leaving).
23:49:01 <nooodl> @tell fizzie now that i think about it, why is it "fi:" for finnish and not "su:"?
23:50:50 <Bike> hm, that is odd, plenty of other languages use endonyms under that iso
23:51:33 <Bike> and swedish gets sv... but japanese is ja
23:51:54 <Bike> su is sundanese, looks like
23:59:03 -!- Frooxius has quit (Ping timeout: 245 seconds).
00:17:38 <ion> nooodl: ISO 639-1
00:18:54 <nooodl> maybe they assigned exonyms/endonyms carefully to avoid clashes?
00:20:40 <ion> Also, suzzie might be a poor choice of nick for a male.
00:32:55 -!- tertu has joined.
01:06:05 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39326&oldid=39325 * Zerk * (+102) sugared primitives*
01:07:01 <HackEgo> plexcoin mycentinycoin smicoin trifiedcoin bievencoin ciilcoin lazanctioncoin feranoltamcoin pichcoin morshipcoin vitycoin kolmogecoin circacoin alpingcoin onozcoin bitcoin pulcoin digfacoin ettercoin ischcoin
01:07:22 <kmc> ion: oh i get it now (an hour later)
01:07:46 <Sgeo> plexcoin, a cryptocoin for EVE?
01:07:48 -!- tertu has quit (Ping timeout: 245 seconds).
01:11:43 <Sgeo> I played a little bit, not much
01:11:44 -!- nooodl has quit (Remote host closed the connection).
01:11:50 <Sgeo> I'm occasionally interested in reading about it
01:11:52 <maurer> What alliance/coalition?
01:11:56 <Sgeo> Last time all I did was take pretty pictures
01:12:04 <Sgeo> Of the EVE Gate and the violent wormhole
01:12:41 -!- nooodl has joined.
01:13:47 <Sgeo> http://i.imgur.com/QnZs290.png hmm doesn't quite show it
01:14:12 <Sgeo> http://i.imgur.com/WvcujFs.jpg
01:18:33 <maurer> Yeah, I've been to the eve gate and lived in a hole for a while
01:19:43 -!- tertu has joined.
01:29:19 -!- oerjan has quit (Quit: leaving).
01:33:15 <Sgeo> If I ever manage to stay in it, I'd... well, I would head for TEST if it wasn't dead
01:34:00 <maurer> I am currently blue with TEST, though I am a little sad about that
01:35:46 <Sgeo> <-- not the most knowledgeable about EVE
01:36:05 <maurer> Blue = have status wherein we do not shoot each other
01:36:14 <maurer> In particular, TEST is part of the HERO coalition at the moment
01:36:29 <maurer> I am a part of SOUND, who is currently supporting HERO's attempt to claim Catch after the russians fucked up
01:36:31 * Sgeo suddenly remembers Ferion
01:37:33 -!- erdic has quit (Max SendQ exceeded).
01:37:59 -!- erdic has joined.
01:38:05 <Sgeo> "10^4 players"
01:38:13 <Sgeo> But the site says 396000 players
01:38:31 <maurer> I think some of the recent battles in eve have had over 10^4 players in a single system >_>
01:38:36 -!- erdic has quit (Max SendQ exceeded).
01:38:41 <Sgeo> The Ferion forums are down :(
01:39:09 <maurer> err, nvm, looks like there were only 3k in a single system
01:41:10 <Sgeo> Ferion has 'arenas', that is, universes, that eventually get won and closed, with a brand new arena then starting
01:41:26 <Sgeo> So, you don't get this lock-in of powerful people who've been there since day 1
01:41:36 <Sgeo> Well, I guess I don't know if that's a real EVE issue
01:41:50 <Sgeo> Also it's an entirely different genre of game
01:42:53 <Sgeo> http://www.ferion.com/portal/screen.php
01:42:59 -!- erdic has joined.
01:43:12 -!- ter2 has joined.
01:43:12 -!- tertu has quit (Disconnected by services).
01:43:19 -!- erdic has quit (Max SendQ exceeded).
01:43:31 <maurer> Sgeo: In eve, being there earlier does give you some amount of power, but really not that much compared to coordination with other people
01:43:57 <maurer> Sgeo: The main power source is how many people you can get to 1.) Follow you and 2.) Not fuck up
01:44:20 <maurer> BRAVE (the most potent alliance from the HERO coalition) is essentially entirely constructed of a legion of newbies
01:44:30 <maurer> they fail at #2 pretty hard, but there are enough of them to make up for it
01:44:47 <maurer> You really only need a few people with a lot of SP/ISK to form a backbone around which other players can form
01:47:09 -!- tertu3 has joined.
01:47:59 -!- erdic has joined.
01:51:11 -!- ter2 has quit (Ping timeout: 276 seconds).
01:51:45 -!- erdic has quit (Max SendQ exceeded).
01:52:59 -!- erdic has joined.
01:53:07 -!- tertu has joined.
01:53:42 <Jafet> The game mechanics are biased heavily towards having thousands of minions in rifters
01:55:50 -!- erdic has quit (Max SendQ exceeded).
01:57:27 -!- tertu3 has quit (Ping timeout: 265 seconds).
01:57:59 -!- erdic has joined.
01:58:18 -!- erdic has quit (Max SendQ exceeded).
02:02:48 -!- tertu has quit (Ping timeout: 245 seconds).
02:02:59 -!- erdic has joined.
02:07:15 -!- ^v has quit (Max SendQ exceeded).
02:08:14 -!- ^v has joined.
03:01:21 <maurer> Eh, my alliance is small, and we get by fine
03:02:08 -!- ^v has quit (Read error: Connection reset by peer).
03:02:36 -!- ^v has joined.
03:05:05 <Bike> i feel this channel should know that, apparently thanks to the earlier discussion of nucleosynthesis, i had a dream about nazi nuclear reactors
03:19:13 -!- nooodl has quit (Quit: Leaving).
03:22:14 -!- nisstyre has joined.
03:25:05 -!- Sorella has quit (Quit: It is tiem!).
03:48:23 -!- tertu has joined.
04:12:29 -!- tertu has quit (Ping timeout: 240 seconds).
04:31:59 -!- tertu has joined.
05:17:08 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39327&oldid=39326 * Zerk * (+833) Moved integer sign to a key. Which will probably cause problems with 0 at some point *continues perpetually rewriting everything*
05:31:22 -!- xpte has quit (Quit: Connection closed for inactivity).
05:43:59 -!- tertu has quit (Read error: Connection reset by peer).
05:44:19 -!- MoALTz has quit (Quit: bbl).
05:45:08 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:05:40 -!- password2 has joined.
06:25:29 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39328&oldid=39327 * Zerk * (+518) Added $$$$… referencing outer levels, /* Standard Library */ and used it to factor out math into a subbox with output re-colored as ints.
06:46:37 -!- Frooxius has joined.
06:50:14 -!- AnotherTest has joined.
06:51:34 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
07:16:13 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=39329&oldid=39103 * 172.248.146.87 * (+1) /* Print value of cell x as number */ Return SP to it's starting position when finished
07:26:03 -!- Froox has joined.
07:27:54 -!- Frooxius has quit (Ping timeout: 258 seconds).
07:36:48 <kmc> fungots fall on fungot falls
07:36:49 <fungot> kmc: lisp could do that too ( insist on precision) but many people still speak of it and make it simpler
07:37:25 <kmc> fungot: whereof one cannot speak, thereof one must be silent
07:37:25 <fungot> kmc: maybe the words should be longer and harder? and software should be higher in quality how?
07:39:08 <fizzie> fungot: Stop making sense it's scary.
07:39:08 <fungot> fizzie: it's reserving 1424 bytes, then i can't
07:40:29 <olsner> fungot: what is it reserving those bytes for?
07:40:29 <fungot> olsner: and then you can hit alt-space be one
07:41:15 <olsner> less sense, but pretty good still... must be something in the data
07:42:03 <fizzie> @tell nooodl You must ask "ISO 639-1:2002, Codes for the representation of names of languages — Part 1: Alpha-2 code" that.
07:42:28 <fizzie> Oh, someone already pointed to it.
07:42:43 <fizzie> (I didn't read scrollback, only @masseurs.)
07:47:59 <fizzie> Possibly "Part 4: General principles of coding of the representation of names of languages and related entities, and application guidelines" would contain the reason, but I don't want to pay CHF 138 for it.
07:58:32 <lexande> a bit over ten trillion years of current world GDP
08:01:19 -!- MindlessDrone has joined.
08:05:43 -!- MindlessDrone has quit (Ping timeout: 245 seconds).
08:06:05 <kmc> earth has the highest GDP of any planet in our solar system
08:19:24 -!- MindlessDrone has joined.
08:24:06 <fizzie> kmc: Like they say, "to be born on Earth is like winning the lottery".
08:24:32 <fizzie> Also the longest life expectancy by far, I assume.
08:29:44 -!- Sellyme has quit (Excess Flood).
08:31:23 -!- Sellyme has joined.
08:45:46 -!- Patashu has joined.
09:05:50 -!- Patashu[Zzz] has joined.
09:05:50 -!- Patashu has quit (Disconnected by services).
09:05:50 -!- AndroidKitKat has joined.
09:16:49 <kmc> `relcome AndroidKitKat
09:16:50 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: relcome: not found
09:17:31 <kmc> !welcome AndroidKitKat
09:17:33 <EgoBot> AndroidKitKat: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/wiki/Main_Page>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
09:20:17 <Taneb> AndroidKitKat, a lot of us from time to time
09:20:45 <lifthrasiir> commercial viability of enterprise brainfuck solution?
09:21:57 <Taneb> lifthrasiir, I found it funny
09:22:37 <Taneb> AndroidKitKat, if you are storing lots of data, fixing the ends and only the ends to be zero works because then you can use [>] and [<] to navigate
09:23:51 <Taneb> Not sure how good advice that actually
09:24:00 <Taneb> I've never written anything particularly big in brainfuck
09:24:22 <kmc> i've written more brainfuck implementations than brainfuck programs, I think
09:24:39 <Taneb> I once almost had one in lambda calculus
09:26:06 <lifthrasiir> I had an optimizing Brainfuck implementation for the thesis
09:29:45 * AndroidKitKat wrote a brainfuck interpreter in a TI-83+. (Because I was bored as hell... <.<)
09:31:26 <Taneb> Has much research gone into algorithm complexity on the tape memory model?
09:32:41 <Taneb> Most of what I've seen seems to be on the random access memory model
09:33:30 <Taneb> I am just rambling mostly
09:44:09 <fizzie> Set-flag-and-conditionally-unset-it is a common brainfuck construction, though I'm not sure that really counts as a tip.
09:44:55 <fizzie> As in, something like >+<[>-<[-]]>[xxx] for "do xxx is current cell was zero".
09:45:02 <AndroidKitKat> fizzie: Like, have a certain memory cell to keep track of?
09:47:45 <fizzie> I wrote something useful in brainfuck just the other day, but now I can no longer remember what it was.
09:47:59 <fungot> Thanks, fungot. Thungot.
09:48:04 <fizzie> Oh right, it was that.
09:48:18 <fizzie> Perhaps calling it "useful" is stretching things.
09:48:23 <fungot> >2,[>,]+15[>+6>+7>+3>+2<4-]>-6.>-.-7.+13.-3.+8.>-.>+2.<5[<]>[.>]>3+2.>.<3.<2[<]>[[-<2+>+>]+<-97[-4[-4[-6[-6[-4[>-<[-]]]]]]]>[[>]>2-11.<3[<]<.>3[.>]>3.>5][-]>]<3[[<]>2[.>]>5.>2]
09:48:28 <HackEgo> #!/usr/bin/perl \ $_ = (join " ", @ARGV) || `words`; s/^\s+|\s+$//g; print "Thanks, $_. "; if (/[aeiouyAEIOUY]/) { s/^[^aeiouyAEIOUY]*/Th/; } else { s/^./T/; } print "$_.";
09:48:50 <fizzie> The former is an implementation of the latter, done because HackEgo was offline there for a while.
09:51:05 <fizzie> That +<-97[-4[-4[-6[-6[-4[>-<[-]]]]]]]>[xxx] construct is an example of the kind of flag-based "more complicated if condition than just != 0" construction; it does xxx if the < cell is not one of 97, 101, 105, etc.
09:51:24 <fizzie> (Corresponding to the [^aeiouy], of course.)
09:53:47 <fizzie> fungot's interpreter is based on compiling to a bytecode where consecutive +-s and <>s have been merged, and I thought I might as well implement ^show in a bit more compact way.
09:53:47 <fungot> fizzie: ' whore' is on the emacs wiki.
09:53:48 <AndroidKitKat> Do you know an application which does that for you?
09:54:06 <fizzie> ^def tmp bf ++++++++++-->>>>><.
09:54:21 <b_jonas> and 15 means 11111 so +15 means ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++means ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++means ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++means ++++++++++++++++++++++++
09:54:40 <fizzie> It's supposed to turn that into +8>4.
09:54:44 <fizzie> Or at least I thought it was.
09:54:58 <fizzie> Maybe I didn't implement that, and/or broke it.
09:55:05 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
09:56:03 <fizzie> Huh, seems I just dreamed I did it sanely.
09:56:44 <fizzie> As you can clearly see from lines 360-367 or thereabouts, it only considers the repetition of a single instruction.
10:00:00 <b_jonas> fizzie: whoa, that's scary
10:00:11 <AndroidKitKat> Anyways, somewhat off-topic, but what Lisp flavour should I learn?
10:00:34 <fizzie> b_jonas: It doesn't have "fung" in the name by accident.
10:02:01 <fizzie> "fungot - putting the fun back in befunge since 2008"
10:02:01 <fungot> fizzie: do they block zip, etc too :)
10:02:31 <b_jonas> that reminds me to NotJack who wrote a J evaluator irc bot in J
10:02:42 <b_jonas> I wonder which of these is crazier
10:02:54 <b_jonas> I don't know enough about befunge to decide
10:03:06 <fizzie> I don't have a Befunge interpreter in fungot (yet), to be fair.
10:03:06 <fungot> fizzie: and adamantix is supposed to catch that willy nilly penguins and seals, i think, due to probable single connection to the server cause nothing happends when i do something like
10:04:14 <fizzie> Also to belatedly comment on the Lisp flavours, I'm partial to Scheme but that's probably just due to SICP.
10:04:27 <b_jonas> fizzie: that would be practical only if you include a good multi-dimensional source code editor with an irc interface so people can edit their source code
10:05:48 <fizzie> 025*".srenileno rof enif tsuj si egnufeB">:#,_@
10:05:50 <b_jonas> AndroidKitKat: head on to http://www.racket-lang.org/ and http://www-sop.inria.fr/indes/fp/Bigloo/
10:06:16 <b_jonas> ) |.'.srenileno rof enif tsuj si egnufeB'
10:06:17 <jconn> b_jonas: Befunge is just fine for oneliners.
10:06:31 <fizzie> Okay, mybe not quite *that* fine.
10:08:39 <b_jonas> is there a magic 8-ball macro?
10:11:26 <fizzie> (Okay, it's not quite.)
10:12:01 <b_jonas> can you implement it in befunge or something?
10:12:16 <b_jonas> I have a reference implementation in perlbot macro language
10:12:50 <b_jonas> (well it's quite simple, it just takes one of the 20 reply strings at random)
10:13:17 <fizzie> That's certainly doable in Befunge; there's the ? instruction that (uniformly) randomly does one of ^ v < >.
10:13:31 <fizzie> It would also be doable as a ^style 8ball via the babble generator.
10:16:12 <fizzie> Though perhaps it'd be kind of pointless, since it's one "shuf -n 1" on HackEgo.
10:16:48 -!- boily has joined.
10:18:23 <b_jonas> `run <<<"It is certain/It is decidedly so/Without a doubt/Yes definitely/You may rely on it/As I see it, yes/Most likely/Outlook good/Yes/Signs point to yes/Reply hazy try again/Ask again later/Better not tell you now/Cannot predict now/Concantrate and ask again/Don't count on it/My reply is no/My sources say no/Outlook not so good/Very doubtful" tr / \\n > 8ballreplies
10:18:59 <b_jonas> `run shuf -n 1 8ballreplies
10:19:43 <b_jonas> `run shuf -n 1 8ballreplies # Are there 20 replies?
10:19:52 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
10:20:50 <HackEgo> ls: cannot access bin/8*: No such file or directory
10:21:18 <b_jonas> `run echo $'#!/bin/sh\nshuf -n 1 8ballreplies' > bin/8ball
10:21:30 <b_jonas> `8ball Did I create the script correctly?
10:21:31 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/8ball: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/8ball: cannot execute: Permission denied
10:21:51 <b_jonas> `run chmod a+x bin/8ball && cp bin/8{,-}ball
10:21:57 <b_jonas> `8ball Did I create the script correctly now?
10:22:10 <b_jonas> `8-ball Why, what's the error?
10:24:07 <fizzie> `run mkdir data; mv 8ballreplies data/; sed -i -e 's|8ballreplies|data/8ballreplies|' bin/8ball # let's keep the /hackenv clean and tidy, everybody
10:24:09 <HackEgo> mkdir: cannot create directory `data': File exists
10:25:28 <HackEgo> ls: invalid option -- ' ' \ Try `ls --help' for more information.
10:25:36 <HackEgo> drwxr-xr-x 2 5000 5000 4096 Apr 15 10:24 data
10:25:40 <fizzie> Oh, maybe that was some confusing thing it had w.r.t. directories. Anyway, it seems to have worked all right. (Though /hackenv is full of cruft anyhow.)
10:26:08 <HackEgo> `bin/8ball' -> `bin/8-ball'
10:26:19 <b_jonas> `8-ball Is /hackenv full of cruft?
10:26:28 <HackEgo> 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ data \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ Wierd \ wisdom \ wisdom.pdf
10:26:32 <fungot> boily: you need to use three .s in a version that uses meroon. oop in lisp is done with lambda?
10:27:34 <fizzie> Actually, maybe 'share' would've been the obvious place, WordData is there too.
10:28:34 <fizzie> `run mv data/8ballreplies share/; sed -i -e 's/data/share/' bin/8*ball; rmdir data # going to hit some empty-directory problem again, I'm sure
10:28:43 <b_jonas> We should upload buubot's old fortune files collection to HackEgo and add some command to interface it. I think I have a copy of those files at home.
10:29:44 <HackEgo> 8ballreplies \ awesome \ cat \ construct_grams.pl \ delvs-master \ esolangs.txt \ esolangs.txt.sorted \ hello \ hello.c \ lua \ maze \ maze.c \ radio.php?out=inline&shuffle=1&limit=1&filter=*MitamineLab* \ units.dat \ WordData
10:30:00 -!- yorick has joined.
10:39:17 -!- password2 has quit (Ping timeout: 240 seconds).
10:53:58 -!- Patashu has joined.
10:54:26 -!- Patashu[Zzz] has quit (Ping timeout: 265 seconds).
10:57:18 -!- shikhin has joined.
11:05:00 -!- oerjan has joined.
11:08:14 -!- boily has quit (Quit: PREDICTIVE CHICKEN).
11:08:30 <oerjan> i didn't predict that.
11:13:44 <oerjan> now you are making assumptions.
11:14:08 <oerjan> i suppose that picture from yesterday is evidence.
11:17:13 <fizzie> It could have been a convincing FLESH SUIT.
11:22:25 <fizzie> "During the evaluation, you should not use any buttons of your browser, such as "Back" and "Refresh"."
11:24:00 <oerjan> possibly that only applies to the current tab.
11:25:23 <b_jonas> fizzie: like http://www.xkcd.com/629/ ?
11:39:09 <oerjan> `cat share/8ballreplies
11:39:10 <HackEgo> It is certain \ It is decidedly so \ Without a doubt \ Yes definitely \ You may rely on it \ As I see it, yes \ Most likely \ Outlook good \ Yes \ Signs point to yes \ Reply hazy try again \ Ask again later \ Better not tell you now \ Cannot predict now \ Concantrate and ask again \ Don't count on it \ My reply is no \ My sources say no \ Outlook n
11:39:19 <oerjan> is that Concantrate intentional
11:39:46 <int-e> `grep 42 share/8ballreplies
11:40:53 <oerjan> b_jonas: i'll be correcting that if you don't say it's intentional hth
11:41:33 <int-e> `` echo 42 >> share/8ballreplies
11:41:51 <b_jonas> oerjan: the 8ball mechanicm has a physical d20 in it
11:41:56 <b_jonas> it can't handle more than 20 lines
11:42:06 <int-e> `wc share/8ballreplies
11:42:07 <HackEgo> 21 69 342 share/8ballreplies
11:42:08 <oerjan> b_jonas: i wasn't speaking about the 42.
11:42:29 <b_jonas> ah, Concantrate? let me check a source
11:43:18 <oerjan> `run sed -i '21,$d' share/8ballreplies #More fun than `revert
11:44:00 <oerjan> also do you mind if i add periods.
11:44:06 <b_jonas> yes, Concantrate is definitely a typo
11:44:15 <fizzie> More fun than a bucket of balls.
11:44:16 <b_jonas> I think we sohuld import the whole reply set again from a reliable source then
11:44:40 <fizzie> b_jonas: Ah, you must mean the ISO standard of magic 8-ball replies.
11:44:58 <b_jonas> fizzie: from the POSIX-2014 utility?
11:45:08 <oerjan> there ISO lways a standard
11:45:23 <b_jonas> fizzie: no, I think we follow that spec only if the POSIXLY_CORRECT environment variable is set, otherwise we use the more traditional replies
11:46:13 <oerjan> `run sed -i 's/Concantrate/Concentrate/;s/$/./' share/8ballreplies
11:46:33 <b_jonas> `run wc -c share/8ballreplies
11:46:48 <b_jonas> `run : "I meant"; wc -l share/8ballreplies
11:46:56 <fizzie> Things that are more fun: http://sprunge.us/jEBP
11:47:36 <b_jonas> `rub grep -i defi share/8ballr*
11:47:36 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: rub: not found
11:47:40 <b_jonas> `run grep -i defi share/8ballr*
11:48:07 <oerjan> `url share/8ballreplies
11:48:08 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/share/8ballreplies
11:51:35 * oerjan curses the lack of text mime type
11:51:57 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/8ball
11:52:06 <fizzie> Has there been a text MIME type before?
11:52:39 <oerjan> i don't know. it is possible that IE has decided to be unreasonable about files without a suffix.
11:53:10 <fizzie> The server does say application/binary now, I was just wondering if it was different.
11:53:38 <fizzie> I assume it's set by the hgweb script, though, and nothing I configurarated.
11:53:42 <oerjan> well i'm pretty sure i used to be able to view programs in bin/
11:53:58 <b_jonas> maybe it depends on the filename or some query parameter in the url?
11:54:14 <oerjan> b_jonas: it _used_ to work for those files, then it stopped.
11:54:33 <oerjan> i recall paste/ files breaking
11:54:45 <oerjan> and having to rename them to .txt to see them
11:55:11 <b_jonas> `run find -name '.htaccess'
11:55:30 <b_jonas> can we configure the web face from here?
11:55:30 <oerjan> b_jonas: that's _not_ inside /hackenv hth
11:55:55 <fizzie> I can mess with it, however.
11:56:05 <oerjan> fizzie "can". whether Gregor would like it is another matter.
11:56:27 <oerjan> but seeing as he's hardly even around...
11:56:28 <fizzie> Well, he had me re-set it up when I was adding esolangs.org; they're served by the same web server.
11:56:47 <oerjan> well this thing broke long before that.
11:57:16 <oerjan> possibly when HackEgo itself moved, or even before.
11:58:02 <fizzie> It's sent as Content-Type: application/binary combined with Content-Disposition: inline; filename="8ball" which I think is kind of ambiguous.
11:58:29 <fizzie> The "inline" disposition suggests automatic displayifying, but application/binary suggests it's not suitable for eyes.
11:58:35 <b_jonas> well, the .htaccess configuration file should be accessible from here so that when we create files we can tell their types to the webserver and stuff
11:58:58 <fizzie> They're not served raw, there's a mercurial repository browser in the way.
11:59:03 <fizzie> A .htaccess file would have no effect.
11:59:29 <oerjan> well IE certainly insists on treating it as needing an application.
11:59:42 <b_jonas> some config files for that then
12:02:00 <fizzie> Internet suggests hgweb should use the python mimetypes module and base the choice on extension, but even a .txt file comes out as application/binary.
12:02:31 <oerjan> it was 6 weeks ago that i had to that ridiculous paste renaming
12:03:01 <oerjan> http://codu.org/projects/hackbot/fshg/index.cgi/log?rev=.txt
12:04:43 <oerjan> which was likely the first time i tried viewing pastes after HackEgo moved.
12:07:24 <fizzie> I guess Gregor moved the repository browser too at that time.
12:09:28 <fizzie> As a workaround, if you don't absolutely need the raw view, quite often dropping "raw-" from the URL -- as in, http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/share/8ballreplies -- might work.
12:09:43 <fizzie> There's a bit of unnecessary fluff, but at least it opens in the window.
12:11:51 <oerjan> yes, although the question is whether to change bin/url to do that.
12:11:57 <fizzie> Apparently there's a config setting of "guessmime".
12:12:34 <fizzie> Seems to have been a security change.
12:12:56 <fizzie> "Before: hgweb made it possible to download file content with a content type detected from the file extension. It would serve .html files as text/html and could thus cause XSS vulnerabilities if the web site had any kind of session authorization and the repository content wasn't fully trusted."
12:13:08 <fizzie> I guess in this case "wasn't fully trusted" sounds like a good description.
12:13:18 <HackEgo> #!/usr/bin/env python \ import sys, urllib \ if len(sys.argv) <= 1: \ print "http://codu.org/projects/hackbot/fshg/" \ else: \ print ("http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/" + \ urllib.quote(sys.argv[1]))
12:14:09 <oerjan> `run cp bin/{,raw-}url; sed -i 's/raw-//' bin/url
12:14:56 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
12:15:02 <HackEgo> #!/bin/sh \ echo http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/wisdom/
12:15:55 <fizzie> Deciding between 'text/plain' and 'application/binary' based on whether the file "looks" binary (the way it does if guessmime is on but mimetypes.guess_type returns None) might presumably have been a reasonably safe thing, too.
12:16:06 <fizzie> File names, not content.
12:16:09 <oerjan> `run find | xargs grep fshg
12:16:41 <HackEgo> grep: .: Is a directory \ grep: ./ibin: Is a directory \ grep: ./quines: Is a directory \ grep: ./bin: Is a directory \ ./bin/raw-url: print "http://codu.org/projects/hackbot/fshg/" \ ./bin/raw-url: print ("http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/" + \ ./bin/pastewisdom:echo http://codu.org/projects/hackbot/fshg/index.cgi
12:17:07 <HackEgo> find: unknown predicate `-f' \ 0 0 0
12:17:15 <fizzie> "find -type f -print0 | xargs -0 grep whatever" is my typical quick-and-dirty look-inside tool.
12:17:15 <oerjan> hm possibly those were all the files, the rest use bin/url
12:17:17 <int-e> `run find -type f | wc
12:18:22 <b_jonas> fizzie: why not just grep -R ?
12:18:28 <HackEgo> du: cannot read directory `/proc/tty/driver': Permission denied \ du: cannot read directory `/proc/1/task/1/fd': Permission denied \ du: cannot read directory `/proc/1/task/1/fdinfo': Permission denied \ du: cannot read directory `/proc/1/task/1/ns': Permission denied \ du: cannot read directory `/proc/1/fd': Permission denied \ du: cannot read dir
12:18:43 <int-e> `run du -sh / 2>/dev/null
12:19:08 <b_jonas> (I have my own crazy grep tool for some reason, but it's not really better.)
12:19:46 <b_jonas> is there a channel for spamming hackego by the way? or should I just do it in private message?
12:19:54 <oerjan> b_jonas: that would mean remembering all the options of grep hth
12:20:14 <fizzie> bin/url, bin/raw-url, bin/pastewisdom, quotes, wisdom/fizzie and a number of paste/paste.* are the entire set of files containing "fshg".
12:20:28 <b_jonas> oerjan: since I wrote my grep clone, I remember more than half of the optoins
12:20:31 <HackEgo> fizzie is not fnord with a monad but the king of #esoteric, see http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/src/fizziecoin.jpg
12:20:49 <fizzie> It is a shame that comes out as application/binary. :/
12:21:06 <oerjan> actually IE showed that picture just fine :P
12:21:17 <fizzie> Oh. Heh. Chrome just saved it.
12:21:29 <b_jonas> but of course find | xargs grep can be useful too when you want some more complicated filter on the files
12:21:31 <oerjan> it pays some attention to the file extension, i assume.
12:21:41 -!- nucular has joined.
12:21:41 -!- nucular has quit (Changing host).
12:21:41 -!- nucular has joined.
12:22:38 <int-e> fizzie: heh, firefox treats it as PDF?!
12:22:57 <int-e> (but I could Open in Browser As -> Image)
12:23:21 <int-e> (thanks to the "Open in Browser" addon)
12:23:50 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.12979
12:24:51 <oerjan> there's still a raw link in the sidebar, anyhow
12:25:06 <int-e> fizzie: http://int-e.eu/~bf3/tmp/pdf.png
12:25:31 <int-e> I have no clue where it got that idea, hmm.
12:27:13 <int-e> Me too. The server does reply with application/binary. And the first couple of bytes look nothing like PDF either.
12:40:32 -!- Sgeo has quit (Read error: Connection reset by peer).
12:56:46 -!- Sorella has joined.
12:59:34 -!- ^v has joined.
13:15:11 -!- ^v has quit (Ping timeout: 252 seconds).
13:19:05 -!- shikhin has quit (Read error: Connection reset by peer).
13:19:57 -!- shikhin has joined.
13:43:18 -!- CapitalSigma has quit (Quit: leaving).
13:58:57 -!- Phantom_Hoover has joined.
14:06:33 -!- Patashu has quit (Ping timeout: 245 seconds).
14:23:27 -!- ggherdov has quit (Remote host closed the connection).
14:40:12 -!- HaliteTablet has joined.
14:44:52 <elliott> HaliteTablet: aren't you banned?
14:52:14 -!- shikhin has changed nick to Bender|shikhin.
14:54:08 -!- Bender|shikhin has changed nick to shikhin.
14:54:13 -!- ggherdov has joined.
14:58:22 -!- ^v has joined.
15:00:08 <oerjan> HaliteTablet: ...i didn't know you could put fluff in your NickServ metadata.
15:00:16 -!- shikhin has quit (Ping timeout: 252 seconds).
15:02:28 -!- password2 has joined.
15:02:56 <HackEgo> [wiki] [[Ignition]] http://esolangs.org/w/index.php?diff=39330&oldid=39208 * Luxen * (+1365) update for new commands
15:04:57 <oerjan> you mean wiki announcements?
15:05:23 <HackEgo> [wiki] [[User:Luxen]] M http://esolangs.org/w/index.php?diff=39331&oldid=39211 * Luxen * (+63) /* finished products */
15:07:20 -!- oerjan has quit (Quit: YOU WERE TOO LATE; NOW YOU WILL NEVER KNOW EITHER.).
15:18:27 -!- Froox has quit (Quit: *bubbles away*).
15:18:38 -!- Frooxius has joined.
15:29:27 <HackEgo> [wiki] [[Aeon]] N http://esolangs.org/w/index.php?oldid=39332 * Cptx032 * (+4959) init
15:31:08 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39333&oldid=39322 * Cptx032 * (+11) /* A */
15:33:35 -!- Frooxius has quit (Ping timeout: 258 seconds).
15:39:48 -!- Frooxius has joined.
15:47:52 -!- jesyspa has joined.
15:54:42 <fizzie> If you meant the wiki announcements, we got them on 2014-04-06.
16:03:35 -!- password2 has quit (Quit: Leaving).
16:05:40 -!- Slereah_ has quit (Ping timeout: 240 seconds).
16:11:01 <mroman> Any CLISPer around here?
16:13:05 <mroman> How does symbol to function coercing work?
16:13:41 <mroman> is that why (funcall 'id 9) == (funcall #'id 9)?
16:18:20 <mroman> > foldl1 (const) [1..]
16:18:20 <idris-ircslave> When elaborating an application of constructor __infer:
16:19:04 <mroman> That's one not lazy version of head .
16:19:39 <mroman> Evaling a list doesn't imply that the elements are evald, right?
16:20:16 <mroman> nvm. foldl1 (const) [print "a", print "b"] only prints "a"
16:20:45 <Jafet> > foldl1 (printf "(const %s %s)") ["a","b","c","d"]
16:20:45 <idris-ircslave> When elaborating an application of constructor __infer:
16:21:25 <Jafet> @run foldl1 (printf "(const %s %s)") $ (:"") <$> ['a'..'z']
16:21:27 <lambdabot> "(const (const (const (const (const (const (const (const (const (const (cons...
16:21:39 <Jafet> @run foldl1 (printf "(const %s %s)") $ (:"") <$> ['a'..'g']
16:21:41 <lambdabot> "(const (const (const (const (const (const a b) c) d) e) f) g)"
16:22:12 <elliott> mroman: that has nothing to do with evaluation
16:22:21 <elliott> (print "b") does not print "b" even if you evaluate it
16:22:54 <Jafet> @run [ print x | x <- [0..] ]
16:22:57 <lambdabot> [<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO ()>,<IO...
16:23:33 <mroman> > head . foldl1 (const) $ [[1..], reverse [1..]]
16:23:33 <idris-ircslave> (input):1:23:When elaborating an application of function Control.Category..:
16:24:00 <mroman> ^- according to my definition of eval, the above would run forever if each element where eval'd
16:24:47 <Jafet> Good thing your definition is wrong, then
16:25:08 <mroman> well... at least we now have established that my definition is indeed wrong :)
16:25:20 <Jafet> I wonder what's in idris's Control.Cat
16:25:42 <Jafet> Probably the same thing, but with actual proofs
16:25:59 <mroman> So, then... what's the correct terminology?
16:27:03 <mroman> (obviously it's not trying to reverse an infinite list)
16:27:37 <Jafet> @run foldl1 const [a, b]
16:27:39 <lambdabot> It could refer to either ‘L.b’, defined at L.hs:155:1
16:27:39 <lambdabot> imported from ‘Debug.SimpleReflect’ at L.hs:110:1-26
16:27:39 <lambdabot> (and originally defined in ‘simple-reflect-0.3.1:De...
16:27:51 <lambdabot> defined at /home/lambda/.lambdabot/State/L.hs:155:1
16:28:05 <lambdabot> It could refer to either ‘L.b’, defined at L.hs:155:1
16:28:05 <lambdabot> imported from ‘Debug.SimpleReflect’ at L.hs:110:1-26
16:28:05 <lambdabot> (and originally defined in ‘simple-reflect-0.3.1:De...
16:28:14 <Jafet> This is ridiculous
16:28:42 <Jafet> @run foldl1 const [x, y]
16:30:40 <mroman> the "actual value" of y is never required
16:49:55 -!- HaliteTablet has quit (Quit: Connection closed for inactivity).
16:57:09 <Bike> does anyone have an example of the real huge C++ things you get out of Spirit
16:58:25 <Jafet> We get them using xpressive now
17:06:27 -!- MoALTz has joined.
17:07:41 -!- password2 has joined.
17:14:59 -!- scoff has quit (Ping timeout: 250 seconds).
17:16:02 -!- scoff has joined.
17:19:23 -!- sebbu has quit (Quit: reboot).
17:20:02 -!- tromp has quit (Ping timeout: 276 seconds).
17:29:23 -!- MoALTz has quit (Ping timeout: 252 seconds).
17:30:18 -!- MoALTz has joined.
17:30:24 -!- MoALTz_ has joined.
17:30:45 -!- MoALTz_ has quit (Client Quit).
17:33:41 -!- MoALTz_ has joined.
17:36:21 -!- MoALTz has quit (Ping timeout: 252 seconds).
17:51:45 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
17:55:05 -!- MoALTz has joined.
17:56:33 -!- MoALTz has quit (Max SendQ exceeded).
17:58:22 -!- MoALTz has joined.
18:06:03 -!- MindlessDrone has quit (Ping timeout: 265 seconds).
18:12:45 <quintopia> are there any good puzzle games where the primarrry mechanic is manipulating in turns different characters with different abilities in different positions of the same puzzle map?
18:19:53 -!- MindlessDrone has joined.
18:22:44 <shachaf> supermegacomics.com is down?!
18:22:49 <shachaf> how long has this been the case
18:24:08 <Jafet> Puzzle games? Well, there is the time I played a wesnoth campaign by reloading over and over
18:24:23 <Jafet> I guess that wasn't very good
18:27:01 <int-e> hmm. fish fillets has some asymmetry between the two agents
18:30:59 <quintopia> others suggested thomas was along and lost vikings
18:33:35 <shachaf> that certainly satisfies your thing
18:35:39 <int-e> wow, I did not realize that "The Cave" was an elaborate Lost Vikings clone *g*.
18:36:25 -!- nooodl has joined.
18:44:20 <shachaf> is there a non-steam non-ouya non-apple-app-store way to get it
18:48:04 <int-e> I played the Steam version of "The Cave"
18:49:15 <shachaf> would rather avoid Steam if possible
18:50:51 -!- sebbu has joined.
18:50:51 -!- sebbu has quit (Changing host).
18:50:51 -!- sebbu has joined.
18:51:52 -!- sebbu has quit (Read error: Connection reset by peer).
18:52:34 -!- sebbu has joined.
18:52:34 -!- sebbu has quit (Changing host).
18:52:34 -!- sebbu has joined.
18:54:29 -!- nisstyre has joined.
19:02:19 <fizzie> I played Lost Vikings too.
19:03:26 <shachaf> I played Lost Vikings Two.
19:03:29 <int-e> I remember the game ... but not vividly
19:05:49 -!- nortti has changed nick to driyoyleujiy.
19:05:56 -!- driyoyleujiy has changed nick to nortti.
19:10:19 <fizzie> There were arrows, and the guy with a shield.
19:10:24 <fizzie> You could stand on the shield.
19:13:41 <kmc> Scandinavian Airlines is running an ad campaign in SF in conjunction with the Visit {Sweden, Denmark, Finland} organizations, which caused me to notice that while the logos for the first two are based on their countries' respective flags, the logo for Visit Finland is a collection of misshapen circles http://www.visitfinland.com/
19:15:35 <fizzie> I think I've seen that logo. It reminds me vaguely of the Aalto vases.
19:15:45 <fizzie> (It's not exactly the same shape.)
19:18:49 <fizzie> "Due to the huge volume of travel marketing and the plethora of potential travel destinations for tourists, the Fi
19:18:52 <fizzie> nnish Tourist Board recognized the need for renewing Finland's destination branding -- the need to stand out. Dis
19:18:55 <fizzie> ruptive strategy and design work resulted in countrybranding based on the key idea that in comparison with most o
19:18:58 <fizzie> ther countries, Finland is something else -- totally individual, unconventional and fresh. It is a welcome altern
19:19:01 <fizzie> ative to places crowded with tourists. Finland's country branding breaks the conventions and clichés of travel ma
19:19:04 <fizzie> rketing, represents the true qualities of Finland in an ironic, yet positive way and communicates the attributes
19:19:07 <fizzie> cool, creative, contrasts and credible."
19:19:10 <fizzie> In case you didn't get that from the misshapen circles.
19:19:13 <fizzie> (Also nice line breaks there.)
19:19:24 <fizzie> (They're my own fault.)
19:19:33 <kmc> they are nice
19:19:43 <Jafet> Good countrybranding
19:19:44 <kmc> they're disruptive, unconventional, and fresh
19:21:10 <fizzie> Today I am very disappointed, because last summer we rented this silly tiny "smart fortwo" mini-car, and drove it to Hanko and back, and it was a very nice trip; but now when I went back to the rental company, they're apparently entirely phasing that thing out at the end of May.
19:21:47 <fizzie> I mean, I'm sure they were losing money and people weren't renting those things, but they should still keep them because I would like to rent one about once a year.
19:22:32 <kmc> you should rent a TRAAAAAIN instead
19:22:40 <fizzie> On the other hand, they've started renting out the Tesla Model S, as the first place in Finland.
19:22:50 <kmc> where do you charge it?
19:22:51 <fizzie> (Last I heard, Tesla had sold a total of about twelve of them in Finland.)
19:23:13 <fizzie> At least nowhere outside the Helsinki region, I think there's a couple of charging stations hereabouts.
19:23:25 <fizzie> Not Tesla-specific, so probably not very fast either.
19:24:37 <fizzie> Okay, there's a few here and there -- http://sahkoinenliikenne.fi/latauspisteet/ -- but it's still not a very dense network.
19:24:41 <kmc> there was an electric car startup in israel that had removable batteries and stations where you could swap them out for a fresh one
19:24:44 <kmc> but i think they failed
19:24:59 <kmc> despite israel seeming like the ideal market for something like that
19:25:13 <fizzie> A total of 45 in the whole of Finland, apparently.
19:26:47 <fizzie> The Model S also costs something like 200€/day to rent, while the smart fortwo was around 30€/day.
19:29:10 <shachaf> https://www.humblebundle.com/
19:29:14 <shachaf> i feel like i've been set up
19:38:52 <fizzie> "Finngenerator" "Have a try and find your inner Finn by changing your name. Just type your name here and let the generator tell you what you would be called if you were a Finn."
19:39:07 <kmc> fizzie: the disruptive unconventional marketing reminds me of this classic: http://adage.com/images/random/0209/pepsi-arnell021109.pdf
19:39:10 <fizzie> I typed my very typical Finnish name in, and got something completely different out.
19:39:34 <fizzie> "THE GENERATOR HAS SPOKEN. FROM NOW ON YOU ARE CALLED: Ohto Viljanen"
19:39:37 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:39:59 <Jafet> That is such a silly decree, ohto.
19:41:05 <fizzie> kmc: Was this automatically generated?
19:41:41 <fizzie> Though it does remind me of a graph I saw that I cannot possibly find again.
19:43:22 <fizzie> http://kritiikkiblogi.files.wordpress.com/2011/10/11_juhani_risku_johtaminen_funktio_kaava_johtaa-edesta-ja-esimerkilla_design-muoto-oppi-johtajuus-arkkitehtuuri-muotoilu-taide_leadership_organization.jpg gets pretty close.
19:43:28 <fizzie> (And is a pretty long link.)
19:44:21 <fizzie> (Apparently Steve Jobs had a remarkably high levels of i and [noise].)
19:44:39 <fizzie> (It's the "leadership equation.")
19:47:56 -!- evalj has joined.
19:55:31 <fizzie> I can't find out how much it costs to rent a TRAAAAAIN -- or even just a single train carriage. (They had a couple of styles of those, but no pricing, just "contact us".)
19:55:56 <fizzie> The university had some sort of a train event, I think.
19:55:57 <kmc> that usually means "too damn much"
19:55:59 <int-e> oh, old times. "alt-x quite the game"
19:56:01 <fizzie> They also had a ship event.
19:56:30 <fizzie> "When you want to offer your interest groups an unforgettable journey you can charter a whole train. Choose from dozens of car types to put together a conference train, a train for a festive occasion, an exhibition train or an event train; there is enough room for as many as 1500 persons."
19:56:40 <fizzie> "A private train is also the easiest way to go to a competition, a celebration, a conference or other occasion."
19:56:56 -!- Sellyme has quit (Quit: Oh god my bouncer is down help).
19:57:03 <fizzie> "For further information please use our form or call --"
19:57:16 <fizzie> "You can add special-purpose cars to chartered trains in addition to normal day cars."
19:57:26 <fizzie> They don't say too much about what kind of cars.
19:57:55 <fizzie> I guess probably the same conference/saloon/exhibition ones they offer to stick in a normal, non-private train, too.
19:58:12 <fizzie> "Choose from day cars, sleeping-cars or special-purpose cars for business or pleasure."
19:58:17 <fizzie> That last part sounds a bit sleazy.
19:59:12 <kmc> sounds like something a few of my friends would enjoy
19:59:20 <fizzie> I'm a bit surprised they don't have a sauna car.
19:59:31 <fizzie> There's a number of saunas on wheels in Finland, I know that much.
20:00:28 <fizzie> I guess you generally park them before using them, though.
20:01:15 <fizzie> http://sauna.saunasessions.ca/category/mobile_saunas
20:01:23 -!- Sellyme has joined.
20:03:24 <fizzie> I've seen that Skipoli trailer sauna (the first photo in the list) parked around the university.
20:03:56 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39334&oldid=39328 * Zerk * (+186) /* Sugar */ Formalized ''.'' as just another map.
20:06:46 <fizzie> Also https://dl.dropboxusercontent.com/u/113389132/Misc/20140415-smart.jpg why would you stop renting something this cute?
20:07:09 <fizzie> I should start a web petition, those always have such an impact.
20:11:10 <int-e> ok, I can confirm that you may download apk files for those games :)
20:11:58 <kmc> fizzie: did you see http://jalopnik.com/vandals-are-flipping-over-smart-cars-in-san-francisco-1560004013
20:12:09 <fizzie> I saw, and it made me sad.
20:14:01 <shachaf> oh, wait, the humblebundle thing is android-only
20:14:30 <fizzie> Oh, I didn't even notice that.
20:14:36 <shachaf> so there's no way to get the game for the relevant platforms other than steam
20:14:39 <fizzie> Weren't the previous "mobile" bundles also desktop compatible?
20:14:54 <int-e> and not all of the games
20:16:17 <shachaf> oh well, already bought it
20:16:26 <int-e> . o O ( aren't there android simulators ;) )
20:27:33 -!- Sprocklem has joined.
20:39:35 -!- Bicyclidine has joined.
20:57:59 -!- Patashu has joined.
21:06:49 -!- Patashu[Zzz] has joined.
21:06:49 -!- Patashu has quit (Disconnected by services).
21:10:12 -!- AnotherTest has quit (Ping timeout: 265 seconds).
21:18:24 -!- password2 has quit (Remote host closed the connection).
21:19:20 -!- evalj has quit (Remote host closed the connection).
21:20:50 -!- Sprocklem has quit (Ping timeout: 265 seconds).
21:22:48 -!- Patashu[Zzz] has quit (Ping timeout: 258 seconds).
21:25:25 -!- password2 has joined.
21:28:21 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39335&oldid=39334 * Zerk * (+120) Removed half-baked importing /* Toplevel */ moved signedness handling to an extension. *abuses headers*
21:32:13 -!- password2 has quit (Remote host closed the connection).
21:37:53 -!- oerjan has joined.
21:41:36 -!- password2 has joined.
21:43:29 <HackEgo> morgecoin vitcoin ogdalgafficcoin modescoin falveollbercoin helpcoin hamccoin eoacoin yelcoin piocoin frogcoin lutingbraycoin ilossilandcoin ediumbraidcoin ozpurecoin prolcoin smunivarcoin attrecoin braebirccoin orrelazioncoin
21:44:15 <oerjan> <mroman> Evaling a list doesn't imply that the elements are evald, right? <-- no, also evaling an IO action like print "b" does not imply that it's actually _executed_.
21:44:34 <oerjan> @tell mroman <mroman> Evaling a list doesn't imply that the elements are evald, right? <-- no, also evaling an IO action like print "b" does not imply that it's actually _executed_.
21:49:51 <oerjan> <Jafet> wat <-- someone presumably @let b = something
21:50:11 <oerjan> and @let doesn't check for name conflicts with other modules.
21:50:33 <lambdabot> defined at /home/lambda/.lambdabot/State/L.hs:157:1
21:51:11 -!- xpte has joined.
21:55:10 <oerjan> <fizzie> ther countries, Finland is something else -- totally individual, unconventional and fresh. It is a welcome altern <-- that's seriously meta-clichéed.
21:55:41 <kmc> helsinki did not seem un-touristy to me
21:55:47 <oerjan> so much that i wonder if it's ironically meant
21:55:50 <kmc> what with the pub tram
21:56:01 <kmc> and the exorbitantly priced restaurants and pubs
21:56:19 <oerjan> kmc: um i am not talking about any resemblance to reality here.
21:56:35 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
21:57:18 <oerjan> can you get a design prize by being ironically meta-clichéed, i wonder.
21:57:20 <fizzie> I assume you were just understanding it wrong.
21:59:06 <fizzie> No, kmc, when they did not see the true qualities.
22:07:16 -!- Melvar has quit (Ping timeout: 240 seconds).
22:07:17 -!- boily has joined.
22:07:59 -!- Melvar has joined.
22:10:44 <Jafet> Hmm. Given a positive real vector x_i, how do I find a reasonably small r such that all r*x_i are close to integers?
22:12:01 <oerjan> if it were just one coordinate i'd use continued fractions.
22:12:03 <Jafet> That's unreasonably small, sorry
22:12:15 <Jafet> (x_i is the estimated speed of the ith CPU, and r*x_i is the (integer) amount of work to schedule to it)
22:13:46 <oerjan> i guess the r*x_i need to fit in some known datatype?
22:14:06 <nooodl> Jafet: i take it r is real too?
22:14:15 <Jafet> Yes, r is an arbitrary scaling.
22:14:28 <Jafet> (Which, for practical purposes, should be nonzero)
22:14:40 <oerjan> oh. in that case i'd also use continued fractions for _two_ coordinates :P
22:15:06 <oerjan> but i don't know any theory for more than that.
22:17:14 <oerjan> wouldn't a bit of dynamic adjustment be simpler.
22:18:11 <oerjan> estimate how long until a CPU runs out of work, or thereabouts.
22:18:15 <Jafet> This system only has one synchronization primitive, and it is global
22:18:36 <Jafet> s/only has/has only/
22:19:38 -!- jjestrel has joined.
22:23:53 <boily> s/has only/only only has has only way way pon pon pon only has/
22:24:05 <Jafet> Hmm, this might be equivalent to the shortest-vector-in-lattice problem
22:24:06 -!- jj2baile has joined.
22:25:49 <oerjan> i was wondering about that.
22:26:21 <oerjan> !welcome jjestrel jj2baile
22:26:22 <EgoBot> jjestrel: jj2baile: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/wiki/Main_Page>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
22:26:34 <elliott> I'm going to go out on a limb and guess it's only one person based on the prefix
22:26:59 <elliott> I'm now walking outdoors on top of my limb and it's really painful and awkward. this was a mistake
22:27:45 <elliott> well, I said I was going to go out on a limb.
22:27:49 <Bicyclidine> is there a fashion of walking that doesn't involve being on top of your limbs
22:27:49 <oerjan> oh limb is not a human organ here
22:28:14 <oerjan> Bicyclidine: let's do the snakey-snake
22:28:34 <elliott> I'm pretty sure I'm human.
22:28:34 <Jafet> The best form of walking is biking
22:29:14 <oerjan> so which of the two nicks is the bf bot
22:29:19 <Bicyclidine> you know what's a fun thing? reading old science books that assert wrong facts
22:29:41 * boily prods oerjan in the non-human limbs
22:29:42 <kmc> or current science boks.
22:30:16 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-ircslave ( , jconn ) , blsqbot !
22:30:20 <oerjan> boily: sorry i'm all out
22:30:40 <Bicyclidine> kmc: it's harder to tell what's wrong with those, though
22:30:55 <Bicyclidine> whereas with this one it's like "maybe muscle works by folding" or "DNA replication is catalyzed by a single enzyme"
22:31:21 <boily> coppro: which one of the jjes is a bot?
22:33:12 -!- nucular has quit (Quit: Excess Food).
22:33:50 <coppro> elliott: and yes, you blame me
22:34:47 <oerjan> elliott: yes but i don't think "out on a limb" refers to a human limb, in normal circumstances.
22:34:51 <fizzie> Was Bicyclidine something different than Bike?
22:35:19 <elliott> oerjan: you realise I was making a joke right :P
22:35:36 <oerjan> Bicyclidine is a patented copyrighted trademark hth
22:36:34 <oerjan> Bike used to be, back in the 19th century, but has long since expired.
22:37:03 <oerjan> Bicyclidine will never expire. the megacorps will see to that.
22:38:12 <boily> see, that's what happens when you mistreat your human organs.
22:38:46 <oerjan> i wasn't mistreating it, it started coughing all by itself
22:39:03 <Bicyclidine> 1-(1-bicyclohexyl)piperidine) isn't allowed as an irc name, and also isn't good nomenclature anyway
22:40:09 -!- oerjan has changed nick to a-123.
22:40:24 -!- a-123 has changed nick to oerjan.
22:40:47 <oerjan> apparently you cannot have just numbers.
22:41:37 -!- boily has changed nick to `.
22:42:00 -!- ` has changed nick to boily.
22:42:26 -!- password2 has quit (Ping timeout: 276 seconds).
22:46:36 <Bicyclidine> old information theory also great "Information is thus conveniently measured in the probability units called bits"
22:53:01 -!- Sgeo has joined.
23:00:10 -!- coppro has changed nick to jjcoppro.
23:07:41 <jj2baile> Oh, elliott: I am in fact not jjestrel
23:07:55 <jj2baile> also, !welcome makes me think of "not welcome" ;P
23:08:10 -!- jesyspa has quit (Quit: leaving).
23:08:43 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: relcome: not found
23:09:01 <oerjan> Phantom_Hoover is really not paying attention lately.
23:09:04 <boily> elliott deleted them all with extreme prejudice.
23:09:41 <oerjan> why don't i have popcorn for this.
23:09:48 <HackEgo> /hackenv/bin/WeLcOmE: 2: /hackenv/bin/WeLcOmE: welcome: not found
23:10:14 <elliott> Phantom_Hoover: they were annoying and only (over)used to make people feel unwelcome :/
23:10:21 <olsner> ehm, so that is still there, but broken because the plain welcome is gone
23:10:55 <elliott> there should just be one for people who have already demonstrated they're here for the wrong kind of esoterica (in fact I think there already is?) and we can just, you know, say hi to the rest
23:11:34 <oerjan> elliott: well that's what plain `welcome was.
23:12:02 <oerjan> olsner: his deletion may not have been case insensitive.
23:12:05 <elliott> oerjan: it's the least evil of them, yeah.
23:12:57 <elliott> I mean I won't bother deleting them again if someone really cares enough to readd them...
23:14:17 <Phantom_Hoover> running the 'wrong esoteric mate' one through rainbow is, i feel, an acceptable compromise
23:16:03 <lambdabot> (Settable f1, Functor f) => (a -> f1 b) -> f a -> f1 (f b)
23:16:16 <Sgeo> mapped is a traversal, right?
23:17:41 <oerjan> basically a Functor is a setter is a Functor
23:18:42 <lambdabot> (Indexable Int p, Traversable f, Applicative f1) => p a (f1 b) -> f a -> f1 (f b)
23:18:55 <oerjan> while a Traversable is a traversal is a Traversable
23:19:00 <lambdabot> (Contravariant f1, Indexable Int p, Foldable f, Applicative f1) => p a (f1 a) -> f a -> f1 (f a)
23:19:15 <oerjan> and a Foldable is a fold.
23:23:08 <jj2baile> woah and then suddenly #esoteric looked like #haskell
23:23:20 <jj2baile> I momentarily thought my irssi was just glitching
23:23:59 <Bicyclidine> and a uh, whatever applybot does. some math bullshit. ain't got time for dat
23:24:12 -!- cdchawthorne has joined.
23:24:42 <applybot> Meta-commands: colour context help info load* restart shutdown* state timeout* undo unicode unload* \ Isabelle commands: apply by declare defer definition done find_theorems fun function lemma oops prefer primrec quickcheck term termination thm try0 typ unfolding using value
23:26:16 <oerjan> ain't nobody got time for leaving off the nobody
23:26:32 <elliott> cdchawthorne: okay explain yourselves.
23:27:02 <jj2baile> elliott: This channel was casually mentioned in our home channel
23:27:06 <jj2baile> i guess a few people were curious
23:27:07 <Bicyclidine> pronoun dropping http://en.wikipedia.org/wiki/Pro-drop_language
23:27:44 <kmc> it's all about the drop
23:27:46 <elliott> jj2baile: as long as we don't have to ban dbelange again
23:28:14 <jj2baile> Well, feel free to ban dbelange as much as you want :p
23:28:14 <Bicyclidine> who was deblagne again? the puzzle person?
23:28:28 <elliott> Bicyclidine: no, somebody terrible from coppro's university :p
23:28:35 <jj2baile> That's of no concern to me, just don't like ban the subnet or something
23:28:45 <elliott> can we just ban canada...?
23:28:53 <elliott> I mean, we wouldn't be missing much, right.
23:29:02 <jj2baile> (that's happened to me before in #physics, I joined, was assumed to be dbelange, and *csclub was banned)
23:29:07 <Bicyclidine> i'm kind of disappointed that the hostname from my school doesn't tell you what computer i'm on
23:29:33 <oerjan> Bicyclidine: è bellissima
23:29:59 -!- Fixie__ has joined.
23:30:19 <Bicyclidine> i swear it used to tell you the exact computer i was on
23:30:24 <oerjan> oh "partially pr-drop"
23:30:24 <Phantom_Hoover> i swear i had dbelange's name stuck in my head a while ago for some reason
23:30:27 -!- Fixie__ has quit (Client Quit).
23:31:14 <elliott> I'd `pastelogs but I guess `pastelogs no longer works
23:31:55 <HackEgo> Phantom Michael Hoover is a true Scotsman and hatheist.
23:32:49 <oerjan> `run echo >wisdom/phantom_hoover 'Phantom Michael Hoover is a true Scotsman, hatheist, and completely out of the loop.'
23:32:59 <Sgeo> http://www.commitstrip.com/en/2014/04/14/true-story-coders-childhood-noob-professors/
23:33:35 <Phantom_Hoover> you know i think the freenode channel name guidelines are only actually there to sow discord and strife
23:33:44 <oerjan> Phantom_Hoover: Gregor moved HackEgo to a different server from where the logs are. on the plus side the wiki is now also there, so we get the announcements.
23:34:27 <boily> Phantom_Hoover: ♪ding♪ you are enlooped!
23:36:28 -!- Phantom_Hoover has changed nick to Phantoom_Hoover.
23:38:06 <oerjan> i should do more far-too-late corrections if this is the usual kind of result
23:48:23 <Sgeo> http://www.commitstrip.com/en/2014/02/18/side-project-cycles/
23:59:02 -!- yorick has quit (Remote host closed the connection).
00:05:17 -!- Phantoom_Hoover has quit (Quit: Leaving).
00:38:57 -!- tromp has joined.
00:51:03 -!- boily has quit (Quit: ORTHONORMAL CHICKEN).
00:56:11 <HackEgo> [wiki] [[Ax]] M http://esolangs.org/w/index.php?diff=39336&oldid=39313 * Oerjan * (+1) Let's compromise on the spelling
00:58:52 -!- Bicyclidine has quit (Quit: leaving).
01:01:22 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=39337&oldid=39318 * Oerjan * (+13) I think a TOC is appropriate for this article even with just 3 sections
01:03:42 <myname> also: what the hell is Ax
01:06:00 <HackEgo> [wiki] [[Keya]] http://esolangs.org/w/index.php?diff=39338&oldid=39321 * Oerjan * (+15) wikitable and some rephrasing for grammar/consistency
01:06:16 <oerjan> i dunno it was just added
01:06:29 <myname> i don't understand that article
01:07:20 -!- cdchawthorne has quit (Quit: leaving).
01:07:35 <oerjan> i didn't particularly try to read it
01:19:37 <HackEgo> [wiki] [[SSBPL]] http://esolangs.org/w/index.php?diff=39339&oldid=31003 * Oerjan * (+48) wikitable, add spaces to avoid accidental table markup, consistent capitalization
01:21:14 <Sgeo> I hope my defense of lens in concatenative was adequate/sane
01:21:34 <Sgeo> http://bespin.org/~nef/logs/concatenative/14.04.15
01:21:57 -!- nisstyre has joined.
01:23:06 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39340&oldid=39333 * Oerjan * (+67) Add [[User:EzoLang]]'s list of languages
01:29:55 -!- tromp has quit (Remote host closed the connection).
01:30:30 -!- tromp has joined.
01:34:51 -!- tromp has quit (Ping timeout: 252 seconds).
01:42:48 -!- jjcoppro has changed nick to coppro.
01:54:17 -!- tertu has joined.
02:07:45 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
02:28:33 -!- oerjan has quit (Quit: Nite).
02:33:34 -!- JesseH2 has joined.
02:33:41 -!- nooodl has quit (Quit: Ik ga weg).
02:36:21 -!- LucienG has joined.
02:39:06 <Jafet> Hmm, the numbers here seem wrong http://primes.utm.edu/mersenne/LukeMirror/lit/lit_039s.htm
02:40:40 <Jafet> (Table 1 supposedly shows the values of (3^(2^(2^n-1)) mod (2^(2^n)+1)) mod 2^36, 2^36-1, 2^35-1 for several n.)
03:04:34 <HackEgo> audacoin easyendocoin sardinalcoin bacacoin soundedintercoin gooilcoin crtlasscoin codentaurehecoin iotcoin addlecocoin forceiccoin factcoin datedcoin paracoin ringthesquecoin ungecoin heitkeecoin daturncoin varocoin comcoin
03:09:54 -!- JesseH2 has quit (Quit: Leaving).
03:20:29 -!- LucienG has quit (Quit: Lost terminal).
03:50:11 <Bike> https://www.mashape.com/nsure-io/porn-filter#!endpoint-porn this is the best startup ever
04:05:58 -!- Sorella has quit (Quit: It is tiem!).
04:07:11 -!- tromp has joined.
04:18:56 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39341&oldid=39335 * Zerk * (+391) Ints should not pattern-match as vectors. (So *that*'s why I had it that way initially!)
04:51:51 <Sgeo> http://www.reddit.com/r/Bitcoin/comments/234iem/bitundo_allowing_you_to_undo_bitcoin_transactions/
05:04:48 -!- conehead has quit (Quit: Computer has gone to sleep).
05:05:16 -!- tertu has quit (Ping timeout: 240 seconds).
05:43:46 <newsham> so some people are signing up to a mining pool with the purpose of destroying transactions?
05:47:08 <newsham> i guess btc has hit the big time
05:57:40 -!- password2 has joined.
06:02:08 -!- tromp has quit (Remote host closed the connection).
06:02:41 -!- tromp has joined.
06:02:41 -!- MoALTz has quit (Quit: bbl).
06:02:57 <Sgeo> Is monad-peel obsolete?
06:03:03 <Sgeo> I should learn how those sorts of things work
06:05:11 -!- shikhin has joined.
06:07:12 -!- tromp has quit (Ping timeout: 258 seconds).
06:49:35 -!- shikhin has quit (Read error: No route to host).
06:50:18 -!- AndroidKitKat has quit (Ping timeout: 240 seconds).
06:51:12 -!- shikhin has joined.
07:06:07 -!- password2 has quit (Ping timeout: 250 seconds).
07:29:30 -!- ^v has quit (Read error: Connection reset by peer).
07:47:13 -!- AnotherTest has joined.
08:09:48 -!- Patashu has joined.
08:24:35 -!- Patashu[Zzz] has joined.
08:24:35 -!- Patashu has quit (Disconnected by services).
08:28:58 <shachaf> i was just looking through old files and i found this line: "Oh, well *all* know that; / But it's undeniable Tom has the better hat."
08:41:11 <Taneb> Anyway, I have a movie to see
09:05:06 -!- tromp has joined.
09:10:03 -!- tromp has quit (Ping timeout: 258 seconds).
09:21:22 -!- xpte has quit (Quit: Connection closed for inactivity).
09:40:09 -!- newsham has quit (Read error: Connection reset by peer).
09:40:25 -!- newsham has joined.
09:40:40 <b_jonas> do you have an implementation for maintaining some kind of balanced search tree in a database using triggers, where the search tree lets you search among rows of a particular table according to a key column?
09:41:47 <fizzie> Is this the setup of a "database in your database" joke?
09:43:24 <b_jonas> fizzie: sort of... but not quite
09:44:41 <b_jonas> database in database is different, that'd be when you store the raw representation of database not in a few files on the filesystem but instead in a few blobs in another database.
09:45:22 <b_jonas> if there's an implementation of such a search tree already, I'd like to look at it
09:45:51 <b_jonas> if there isn't, then I'll think of whether it's possible to implement it, probably using a treap, and maybe even try an implementation
09:47:27 <Jafet> If it is made out of relations, are you allowed to call it a family tree?
09:47:45 <fizzie> I tried to figure out an X-in-your-X format thing referring to putting a handcrafted index into a database system (presumably) supporting indices, but couldn't.
09:48:26 <b_jonas> fizzie: the database would have to support some form of indexes for this to work in first place,
09:48:50 <b_jonas> but this way you could implement more powerful indexes and indexed queries than what the database supports
09:49:21 <fizzie> It sounds the kind of thing you'd find zzo38 doing in SQLite.
09:50:00 <b_jonas> fizzie: I should ask zzo38 then? ok
09:58:13 -!- Phantom_Hoover has joined.
10:01:20 -!- nooodl has joined.
10:16:38 -!- yorick has joined.
10:17:27 -!- boily has joined.
10:27:37 -!- metasepia has joined.
10:52:16 -!- shikhout has joined.
10:55:14 -!- shikhin has quit (Ping timeout: 252 seconds).
10:55:14 -!- shikhout has changed nick to shikhin.
10:58:50 -!- nucular has joined.
10:58:50 -!- nucular has quit (Changing host).
10:58:50 -!- nucular has joined.
11:00:56 -!- boily has quit (Quit: METHYLATED CHICKEN).
11:00:58 -!- metasepia has quit (Remote host closed the connection).
11:01:32 <ion> mona 250b intro for Atari 8-bit http://youtu.be/0NHaFS9YJBE
11:35:18 <Phantom_Hoover> http://www.reddit.com/r/Bitcoin/comments/234iem/bitundo_allowing_you_to_undo_bitcoin_transactions/cgtoivc bitcoiners ignorant of game theory, tragedy of commons; news at 11
11:41:49 -!- MindlessDrone has joined.
11:45:15 <b_jonas> now that I've heared of cobol PICTURE codes, I wonder if our galactic sector ZZ9 Plural Z Alpha was named of one
11:46:58 -!- conehead has joined.
12:11:13 <myname> so i went to a prof today asking for a bachelor thesis i could make
12:11:27 <myname> mentioned i like esoteric languages
12:11:45 <myname> i could make a compiler as a thesis project
12:12:46 <myname> what language could i choose? also: would my own language (wolfgang) be possible without that much work?
12:13:37 <Jafet> bffc could use some optimizations
12:17:13 -!- Sgeo has quit (Read error: Connection reset by peer).
13:02:33 -!- Sorella has joined.
13:30:37 -!- oerjan has joined.
13:41:55 <quintopia> wolfgang looks immineNtly compilable
13:43:32 <Phantom_Hoover> why the fuck was the 'previously closed tabs' thing removed from chrome
13:44:52 <quintopia> ah that's why i've been unable to undo tab closure hmm
13:45:04 <quintopia> yeah i agree chrome just isn't as awesome as it used to be
13:57:49 * oerjan thinks Phantom_Hoover could possibly approve of today's xkcd.
13:58:23 <Phantom_Hoover> although ksp isn't that representative of real-world orbital mechanics
14:01:31 <elliott> Phantom_Hoover: it's in history now I think
14:02:02 -!- Tritonio has joined.
14:03:36 <Phantom_Hoover> i still can't get over them wasting half the new tab page on a completely redundant google search box
14:06:08 -!- password2 has joined.
14:06:44 -!- password2 has quit (Max SendQ exceeded).
14:07:31 -!- password2 has joined.
14:16:37 <Bike> "Right, but miners wouldn't want transaction reversal to become a problem for the network because it would destroy the value of Bitcoin (and thus their ASICs)." amazing
14:17:06 -!- Patashu[Zzz] has quit (Ping timeout: 258 seconds).
14:18:30 <Bike> http://arxiv.org/abs/1308.5164 this has a certain charm :3
14:18:53 <Bike> plus it's even by a hungarian
14:54:39 <HackEgo> [wiki] [[Talk:Eodermdrome]] http://esolangs.org/w/index.php?diff=39342&oldid=35357 * GreyKnight * (+399) /* multiple matches */ new section
14:55:46 <elliott> looks like someone is trying to implement eodermdrome.
14:58:36 <HackEgo> [wiki] [[Talk:Eodermdrome]] http://esolangs.org/w/index.php?diff=39343&oldid=39342 * Phantom Hoover * (+177) /* multiple matches */
15:02:24 <myname> oerjan: suggest a language i could write a compiler for, which is not awfully hard!
15:02:44 <oerjan> well now that eodermdrome is taken...
15:04:07 <oerjan> (in fact i haven't even looked at the page)
15:04:39 <myname> eodermdrome looks pretty hard at first sight. that may be because i didn't fully understand it
15:05:07 <oerjan> it's a timey-wimey graph of ...stuff.
15:06:06 <myname> i don't think that claiming i will write a feather compiler does not work as bachelor thesis
15:12:19 -!- password2 has quit (Quit: Leaving).
15:25:10 <Phantom_Hoover> myname, eodermdrome's main problem, afaiu, is efficiently implementing the subgraph match algorithm
15:25:23 <int-e> myname: if you invent time travel and all you get for it is a bachelor thesis then you've done something wrong ;)
15:25:47 <myname> int-e: i'd rather implement twoducks, then
15:26:15 -!- oerjan has quit (Quit: Later).
15:43:05 <quintopia> how long has bf been the featured language now? it seems like ages
15:48:59 -!- ^v has joined.
15:54:07 <fizzie> You can make it change by making sure there is a good article about a language, and then suggesting it as featured.
15:54:14 <fizzie> Or that's my understanding, anyway.
15:56:47 -!- JesseH has joined.
15:58:21 -!- Tritonio has quit (Ping timeout: 252 seconds).
16:05:06 -!- password2 has joined.
16:11:33 -!- JesseH has quit (Ping timeout: 252 seconds).
16:39:22 -!- xpte has joined.
16:42:04 -!- password2 has quit (Ping timeout: 240 seconds).
16:43:22 -!- Sprocklem has joined.
16:46:18 -!- Sprockle1 has joined.
16:47:15 -!- JesseH has joined.
16:50:14 -!- augur has quit (Remote host closed the connection).
16:51:27 <myname> how do i make that programm that prints the sum of two numbers before it asks for them
16:52:25 -!- shikhout has joined.
16:54:56 -!- shikhin has quit (Ping timeout: 252 seconds).
16:54:57 -!- shikhout has changed nick to shikhin.
16:56:10 -!- nucular has changed nick to nuculaway.
16:58:11 -!- Sprocklem has quit (Quit: freenode).
16:58:11 -!- Sprockle1 has quit (Quit: freenode).
16:58:34 -!- Sprocklem has joined.
16:58:37 -!- Sprocklem has quit (Client Quit).
16:58:57 -!- Guest72113 has joined.
16:58:57 -!- Guest72113 has quit (Changing host).
16:58:57 -!- Guest72113 has joined.
16:59:40 -!- Guest72113 has quit (Client Quit).
17:05:38 <tromp_> printf("4\nPlease enter 2 and 2:\n");
17:10:18 <Bike> if you're doing it as a thesis, shouldn't it be awfully hard
17:20:45 -!- Sprocklem_ has joined.
17:21:25 -!- Sprocklem_ has changed nick to Sprocklem.
17:22:34 -!- MoALTz has joined.
17:28:08 -!- nuculaway has changed nick to nucular.
17:28:50 -!- Sprocklem has quit (Quit: leaving).
17:29:05 -!- Sprocklem has joined.
17:35:37 -!- Sprocklem has quit (Quit: leaving).
18:06:52 <quintopia> myname: have it print a random number. then, ask for input. if the numbers don't add up to the output number, destroy the universe. if the multiverse theory is true, anyone who observes the functioning of your program (which correspond to those living in universes that picked the right numbers) will see that it functions correctly.
18:07:28 -!- FreeFull has joined.
18:07:36 <quintopia> (It is probably mroally required here to remind users that entering values which do not sum to the printed value will result in their immediate nonexistence. This will have the beneficial side effect of increasing the number of universes in which the program succeeds.)
18:08:20 <myname> but more people will questioning if it really works
18:09:13 <quintopia> well, they are more than welcome to test it if they don't mind having the blood of who knows how many entire species on their hands!
18:09:52 <myname> which may result in even less universes in which the program succeeds
18:10:01 <Bike> it's going to be awkward if your prng isn't actually based on wavefunction collapse to any great extent and you destroy everything
18:10:06 -!- Sprocklem has joined.
18:10:06 -!- Sprocklem has quit (Changing host).
18:10:06 -!- Sprocklem has joined.
18:10:43 <quintopia> yes it is critical that you use a real RNG. sample the CMBR or something
18:13:32 <Bike> that collapses a wavefunction?
18:15:47 -!- Slereah_ has joined.
18:18:51 -!- zzo38 has joined.
18:28:56 -!- augur has joined.
18:29:31 <quintopia> the idea of waveform collapse is kind of antithetical to many-worlds
18:30:02 <quintopia> anything that differentiates one universe from another will do
18:31:37 <Bike> I thought the idea was that wavefunction collapse was actually the observer wavefunction being entangled (entrained?) with the observed wavefunction, so that probability amplitudes outside a particular basis are no longer observed
18:31:55 -!- zzo38 has quit (Remote host closed the connection).
18:32:27 <quintopia> yeah that's pretty much it. but that's not really a "collapse" of the wavefunction. More of a refactoring.
18:32:38 <Bike> i just mean something that looks like a collapse.
18:32:54 <Bike> there't nothing terribly quantum if i get a RNG by sampling microweather or whatever
18:34:14 <quintopia> the CMBR reflects the interactions of the matter of the universe at the timescale of yoctoseconds after the big bang or something like that. it should have plenty of distinguishing power between universes
18:34:29 <Bike> Isn't that too far back though
18:34:36 <Slereah_> The CMB is from like 300.000 years after the big bang
18:34:41 <Bike> I mean you want to keep universes that are mostly like this one
18:34:55 <quintopia> Slereah_: oh. damn. may not be useful then.
18:35:01 <Bike> If the only remaining universes after your twoducks program are ones where triple alpha never happened to happen or something you'd have a problem!
18:35:05 <Bike> well, you wouldn't, since you wouldn't exist
18:35:33 <Slereah_> Two Duck probably wouldn't work with a physical implementation
18:35:40 <Bike> it's pretty sad to know if anyone who actually knew quantum physics was here they'd be shuddering at me
18:35:43 <quintopia> Bike: well, what your observation of the CMBR would really differentiate between is microweather state like you said, but also the time at which you chose to make the observation.
18:35:44 <Slereah_> But that depends on how you implement time travel
18:36:45 <Slereah_> The best thing about time travel is that it makes general relativity non-deterministic technically
18:36:47 <quintopia> Slereah_: suggest a random number mechanism that would distinguish between similar universes
18:37:40 <Slereah_> I don't know that much about MWI
18:37:45 <Bike> quintopia: https://photonics.anu.edu.au/qoptics/Research/qrng.php
18:37:48 <Slereah_> But since it is deterministic, I guess none
18:38:30 <Bike> "Suggest a RNG that would make it look like we're distinguishing between similar universes to an entangled observer"
18:38:45 <Bike> actually, that kind of fucks up the whole 'destroy the universe' joke, doesn't it, since you don't really have multiple universes per se
18:39:09 <quintopia> well better to make it physically accurate than funny :)
18:39:15 <Slereah_> a thing to remember is that quantum interpretations are not actually physics
18:39:26 <Bike> http://qrng.anu.edu.au/ i like how there's actually several of these
18:39:46 -!- FreeFull has quit (Quit: Starting tmux).
18:39:51 <Slereah_> Also "random" can also depend on metaphysical points
18:40:28 <Bike> i tried reading everett's thesis once but it turns out ui don't know any physics
18:40:41 <quintopia> random is not the important thing. the important thing is that it be something that is different in universes where different people are likely to pick different numbers.
18:41:10 <quintopia> not the same across all universes that contain people
18:41:11 <Slereah_> Well between two different universe there will be at least one quantum measurement differing
18:41:39 <Bike> wait so is mwi based on there being "actual" multiple universes or not.
18:42:37 <Slereah_> The point is that quantum theory, due to various experiments, has found out that the theory cannot be, at the same time, local, deterministic and unique
18:42:46 <Bike> i'm trying to base my understanding on everett since it seems unlikely he said something dumb, unlike "what the bleep do we know" and suchlike
18:43:39 <Slereah_> ie it can't respect relativity in every aspect (not allowing instantaneous action at a distance), have the same results for the same events and be in one universe
18:43:49 <Bike> i guess it's like, is mwi is based on there being one universal wavefunction, and what we observe as wavefunction collapse is locking ourselves (as subfunctions) into a particular basis wrt the observed
18:43:53 <Slereah_> Copenhagen isn't deterministic, Bohm isn't local and MWI isn't unique
18:44:01 <Slereah_> And there's a bunch of others that break one of these
18:44:06 <Bike> but all the "other universes" are just parts of the wavefunction in different bases
19:07:06 -!- nortti has changed nick to lawspeaker.
19:07:13 -!- lawspeaker has changed nick to nortti.
19:07:25 -!- password2 has joined.
19:13:25 -!- sebbu has quit (Ping timeout: 258 seconds).
19:15:48 -!- FreeFull has joined.
19:16:48 -!- sebbu has joined.
19:16:48 -!- sebbu has quit (Changing host).
19:16:48 -!- sebbu has joined.
19:24:16 <b_jonas> wow, this channel has discussions on strange topics
19:25:12 <Slereah_> Hell I could talk about time travel physics for hours <3
19:25:47 <Slereah_> I should try implementing an interpreter for a twoduck-like someday
19:25:56 <Slereah_> Like a quantum computer that allows closed timelike curves
19:25:58 <kmc> few things are more esoteric than quantum mechanics
19:26:11 <Slereah_> But damn it's not gonna be easy
19:26:28 <b_jonas> myname: BSc thesis in what science? and you want a compiler from or to an esoteric language?
19:26:47 <Slereah_> I guess you'd basically have to run the program over his entire timeline
19:27:00 <Slereah_> Maybe there's a way to do it for all programs, but like
19:27:13 <Slereah_> Doing it for a machines where the halting problem is decidable
19:27:48 <myname> b_jonas: computer science
19:28:02 <myname> b_jonas: from would be more useful, i assue
19:29:23 <b_jonas> I remember someone wrote a compiler for K (the APL-like language) as his PhD thesis. That's of course impossible, because you can write stuff in K that's so dynamic that there's no chance to determine anything in advance,
19:30:02 <b_jonas> but he wrote a compiler that tries to figure out as much as possible about the data types and other invariants, and compile what it could.
19:30:26 <b_jonas> myname: probably. or maybe APLers just like brevity and so they choose single-letter names
19:30:34 <myname> b_jonas: i am aiming a bit lower than that
19:30:43 <b_jonas> Slereah_: it's a semi-successful APL-like language of whose derivative Q is used in business
19:30:49 <b_jonas> I'm not sure which of K or Q this guy compiled
19:31:06 <myname> i neither knew K nor Q but J
19:31:24 <b_jonas> Slereah_: it's an APL-like that tries to be efficient so it like doesn't check overflow and doesn't upgrade values to larger types when they overflow, etc
19:31:50 <Slereah_> Then why use an APL like and not C
19:31:50 <b_jonas> has lambdas, has a smaller set of primitives than C, fewer higher order functions,
19:32:43 <Slereah_> I think doing a two-duck like should be doable to implement
19:32:47 <Slereah_> For a machine that always halts
19:32:51 <b_jonas> also it semantically has only rank 1 inhomogenous array, though homogenous and higher rank arrays are stored in an optimized fashion.
19:33:06 <Slereah_> Using the Novikov principle, to avoid weird time travel stuff
19:33:17 <Slereah_> You calculate the entire program in advance
19:33:30 <Slereah_> And then output each time slice sequentially
19:34:21 <myname> Slereah_: that still won't do with IO
19:34:53 <Bike> http://www.theallium.com/science-life/scientists-reportedly-close-to-finding-a-use-for-linkedin/
19:35:19 <Slereah_> Well I don't think I can write an interpreter to communicate with the past unfortunately
19:35:27 <myname> b_jonas: http://esolangs.org/wiki/TwoDucks
19:35:28 <Slereah_> Two-Duck is a time travel based esoland
19:37:04 <myname> that sounds invader zimish
19:39:37 <Slereah_> With a quantum computer kind of thing it should be mostly paradox free
19:40:17 <b_jonas> no way. two duck is much more powerful than a quantum computer.
19:40:44 <Slereah_> Well that's because it allows timeline alterations
19:41:07 <Slereah_> But if you go the David Deutsch way, it only allows for consistent timelines
19:41:17 <b_jonas> without tiem travel it would be just an ordinary language
19:41:29 <Slereah_> And the quantum states sent along closed timelike curves become mixed
19:46:07 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:00:41 <kmc> perhaps bonghits will fix my time paradox
20:01:50 <Slereah_> kmc : https://www.youtube.com/watch?v=EVL1crIccRI
20:02:38 <myname> so, no specific language idea for me?
20:03:57 <myname> something to write a compiler for with a fair amount of work
20:04:45 <Slereah_> Well I'm just gonna pimp my own language I guess : http://esolangs.org/wiki/Limp
20:04:57 <Slereah_> And I was too lazy to implement that one
20:05:39 <myname> i thought about my own language as well, but i am quite unsure how hard it would be
20:06:29 <Slereah_> Also define "a fair amount of work"
20:06:54 <myname> well, i want to make it a bachelor thesis
20:08:32 <Slereah_> Like functional or procedural or whatevs
20:09:02 <myname> i do think procedural are a lot easier to compile (at least if i want to compile to c or assembly)
20:09:25 <Slereah_> Cellular automatons also aren't too hard
20:10:07 <Slereah_> The electronic-based one, I forget which
20:10:21 <Bike> electronic-based? you mean von neumann's?
20:10:39 <Bike> http://en.wikipedia.org/wiki/File:VonNeumann_CA_demo.gif
20:11:18 <myname> bullying automatons are fun, too
20:11:21 -!- conehead has quit (Ping timeout: 252 seconds).
20:12:24 <myname> but they may be really hard to compile
20:13:09 <myname> Slereah_: i don't get what's special about limp
20:13:35 <Slereah_> Basically I just mashed a lot of the functional languages together
20:13:58 <Slereah_> Also a lot of the greek letter based one
20:18:25 <Slereah_> Implement it with actual parallelism
20:19:24 <Slereah_> Like make a pi calculus language for some quadcore processor
20:19:48 <b_jonas> what the heck is pi calculus?
20:20:05 <Slereah_> Pi calculus is the abstraction of parallel computing
20:21:18 <Bike> imo digamma calculus
20:44:49 <kmc> i read (part of) djb's paper "Understanding brute force" last night
20:45:20 <kmc> it's about how a parallel computer can do brute force key search at a much better price:performance ratio than a serial computer
20:45:30 <kmc> and complaining that cryptographers often ignore this fact
20:46:05 <kmc> this is true even in a theoretical model which lacks some of the engineering factors that make parallel computers better in the real world
20:47:01 <kmc> I think a lot of it comes down to, if you have a huge amount of memory then you should have a proportional amount of cores, otherwise you are not using the memory very efficiently
20:47:45 <Slereah_> Memory is dirth cheap today though
20:49:21 <Slereah_> Hey do you remember that episode of the Magic School Bus on computers?
20:49:21 -!- password2 has quit (Quit: Leaving).
20:49:26 <Slereah_> The bus was driving on the BUS!
20:49:58 <kmc> Slereah_: general purpose CPU cores are complicated and expensive, but a circuit that just does AES and talks to some local memory is tiny and you can fabricate a lot of them on a single wafer
20:50:09 <kmc> and in this machine they're only connected to their neighbors
20:50:10 -!- nucular has quit (Quit: Switching to phone).
20:50:17 <kmc> and the interconnect doesn't need to be super fast
20:50:29 -!- oerjan has joined.
20:50:51 <olsner> imagine if you had one small cpu per 64k (or so) of your 4-8GB ram, that's ~half a shitload of cpus
20:51:06 <Bike> bet it could play crysis though
20:51:09 <kmc> if you're in the realm where a brute force attack on AES is remotely plausible then you're talking about spending billions of dollars on fully custom hardware
20:52:38 -!- augur has quit (Remote host closed the connection).
20:52:52 <Bike> that reminds me, anybody got any good examples for this http://mnxmnkmnd.tumblr.com/post/82876163079/dead-theories
20:52:59 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
20:55:36 <fizzie> "one small cpu" that's starting to sound like the GA144.
20:56:22 <fizzie> Maybe it doesn't have quite that many CPUs, and they're p. small.
20:57:17 <Bike> ooh, is this a flow computer
20:58:29 <Slereah_> But that was the pre-experimental era of physics
20:58:29 <Bike> i don't know any.
20:58:35 <Bike> i know some about aristotle's.
20:58:57 <Bike> with the whole, what was it, things keep moving because of wind
20:59:01 <Slereah_> I can't think of too many theories that are way wrong?
20:59:01 <fizzie> "Oh yeah, Aristotle" makes it sound like you knew him personally.
20:59:15 <Slereah_> I mean there's some charmingly old timey ones
20:59:40 <Bike> and yeah, i was trying to exclude classical science, because it's mostly just old guys making things up
20:59:53 <Bike> as opposed to real science, which is old guys making stuff up but having to convince other old guys of it for money
20:59:56 <nortti> why is he called "Aristotle" in english when his name was Ἀριστοτέλης?
20:59:58 <oerjan> aristotle aristotle was a bugger for the bottle
21:00:11 -!- augur has joined.
21:00:17 <Bike> nortti: probably warping through persian intermediates
21:00:26 <Bike> or just europeans being bad at languages as per usual
21:00:56 <nortti> interesting that finnish uses pretty-direct transliteration "Aristoteles"
21:00:57 <Bike> Slereah_: i think part of it is like i said, it hasn't happened so much in physics.
21:00:58 <Slereah_> nortti : why is Ἄνουβις in greek when his egyptian name is inpw
21:01:18 <kmc> it used to be more of a thing that you would translate names for a different language
21:01:18 <Bike> at least not that i know of. i ain't a physicist. hell yea
21:01:21 <Slereah_> I mean there's plenty of wrong theories in physics, certainly
21:01:30 <Slereah_> but for the most part, they weren't like
21:01:30 <kmc> and some of the names we use today are based on n steps of translation, I guess
21:01:37 <kmc> like if you were a scientist you had to have a latin name
21:01:46 <Bike> my favorite warped name is avicenna
21:02:14 <Bike> Slereah_: i was thinking of this because i was raeding a book from the 70s (so not that old) that put forward the folding muscle thing, which has nothing at all to do with the modern theory
21:02:27 <Bike> lysenkoism could work
21:02:42 <Slereah_> Or really a lot of scientific theories from the soviet union
21:02:45 <Bike> lamarckianism is kind of weird because of things like it being a huge influence on darwin
21:02:49 <Slereah_> there was a Party Line on science
21:02:55 <Slereah_> Hence there was a lot of weird things
21:03:07 <Bike> the only major ones i know are lysenko and pavlov, and pavlov wasn't /that/ wrong
21:03:43 <Bike> they still teach psychoanalysis in intro psych classes.
21:03:49 <kmc> what about individual (as opposed to gene) selection :3
21:03:55 <Bike> i don't know why, but
21:04:15 <Bike> kmc: can opens up beneath us, we fall into an earth sized sphere made entirely of worms
21:04:40 <Bike> was hollow earth ever a mainstream thing
21:04:54 <oerjan> Bike: oh, what about the theory that the sun was mostly iron
21:04:59 <Slereah_> But it enjoyed some popularity in the early 20th century
21:05:03 <Bike> it's like, i know some guys that said mountains were formed by underground gas pockets, but nobody much believed them
21:05:13 <Bike> oerjan: oh i half remember that one
21:05:58 <fizzie> They had that one flat-vs-round on-the-river test about the curvature of Earth that got them the result that the surface is in fact concave.
21:06:10 <Bike> that sounds awesome.
21:06:20 <fizzie> http://en.wikipedia.org/wiki/Bedford_Level_experiment
21:06:29 <Bike> aether is the sort of thing i wouldn't count, since it's how other waves work, and i'm gonna be honest i have no idea how EM works
21:06:39 <Slereah_> Flat earth theory hasn't been that popular in the last few thousand years
21:07:13 <Bike> "Several protracted court cases ensued, with the result that Hampden was imprisoned for libel and threatening to kill Wallace." ah, the scientific method
21:07:18 <fizzie> Not popular, but it's had its adherents.
21:07:28 <Bike> hm, maybe steady state universe.
21:07:36 <Slereah_> http://upload.wikimedia.org/wikipedia/commons/a/a5/Baylonianmaps.JPG
21:07:49 <Bike> old world maps rule
21:08:13 <Bike> «Wallace, who had been unaware of Rowbotham's earlier experiments, was criticized by his peers for "his 'injudicious' involvement in a bet to 'decide' the most fundamental and established of scientific facts"» is this like, the 1800s version of evolution debates
21:08:44 <fizzie> The concavity thing is in the "Other experiments" section.
21:08:44 <Slereah_> Although it's really just a little area around babylon
21:08:54 <Bike> oh hey lewontin wrote a bit about selection units, sweet
21:10:30 <maurer> http://www.tryidris.org/console
21:10:43 <maurer> (I know, I know, probably not esoteric enough)
21:13:11 <Slereah_> Although I guess on a processor, it will probably be basic brainfuck
21:13:17 -!- AnotherTest has quit (Ping timeout: 250 seconds).
21:14:28 -!- augur has quit (Ping timeout: 245 seconds).
21:15:18 <Slereah_> Brainfuck that uses a function over R instead of a tape
21:15:41 <Slereah_> And I guess instead of +- whatever, you use some basis for real functions
21:18:58 -!- Sprocklem has quit (Ping timeout: 276 seconds).
21:19:35 <fizzie> kmc: Fun fact: there are 20 trains currently on their way from somewhere to somewhere else in Finland. (VR has an "open data" feed of their current positions.)
21:19:57 <fizzie> (That's not very many; but it is 00:20am, maybe there's more during the day.)
21:20:30 <Slereah_> How many of the conductors are drunk though
21:21:06 <oerjan> istr when we discussed continuous brainfuck, the +->< commands were like infinitesimals, and then you put them in a loop to get larger effects.
21:22:01 <Slereah_> Well if they're infinitesimals you can't add them up to larger effects
21:22:02 <kmc> hm, that is rather few
21:22:03 <oerjan> i'm not sure a proper semantics was made. probably would involve differential equations.
21:22:06 <kmc> I assume that doesn't include the Helsinki Metro
21:22:09 <Slereah_> That's the whole point of infinitesimals!
21:22:20 <olsner> subway trains aren't trains, duh
21:22:21 <oerjan> Slereah_: yes you can, if you add infinitely many of them!
21:22:27 <Slereah_> They break the Archimedian properties
21:22:32 <kmc> well it isn't run by VR
21:22:38 <Slereah_> Well yeah but then how will you define them
21:22:51 <Slereah_> In the end you'll just replicate the natural numbers
21:22:53 <fizzie> kmc: Probably not, though it wouldn't be running at this time anyway.
21:22:59 <kmc> distinguishing subways from mainline / commuter trains is pretty easy in America, but quite difficult in some places (like Japan)
21:23:07 <fizzie> kmc: It stops at 23:20 except on Fridays.
21:23:40 <oerjan> Slereah_: that was the intuitive meaning. as i said, a proper semantics would probably involve differential equations.
21:24:18 <Slereah_> Technically, you can't make all real functions from differential equations with integer factors
21:24:23 <oerjan> also, nonstandard reals probably
21:24:29 <Slereah_> Also I think some diff eqs are uncomputable
21:24:33 <kmc> fizzie: boooooo
21:24:38 <kmc> when does it stop on friday / saturday?
21:24:49 <oerjan> Slereah_: i fail to see how this matters to an esolang hth
21:25:02 <fizzie> kmc: Last trains start at 01:15am one way and 01:05am the other.
21:25:04 <Slereah_> Well it does for an implementable one
21:25:59 <fizzie> (This Friday/Saturday extension is a relatively new thing, they started it in November last year.)
21:27:04 <Slereah_> Is there any neural network based esolang?
21:27:06 <kmc> and when does the first train in the morning run?
21:27:09 <Slereah_> Or other such similar concepts
21:27:22 <kmc> stopping at 23:20 is worse than a lot of subways in america :/
21:29:24 <oerjan> http://esolangs.org/wiki/Genetic_algorithm and http://esolangs.org/wiki/Wittgen are the only hits for Neural.
21:29:49 <kmc> fizzie: are there night buses in helsinki?
21:31:41 <kmc> the last trains on BART depart around midnight or 00:30 on a weekday, depending on the station
21:31:51 <kmc> the last train from the airport is before midnight, which is annoying
21:32:11 <kmc> and they start up around 04:00
21:32:36 <kmc> Google Transit will sometimes give you transit instructions that involve waiting on a street corner in Los Angeles for three hours in the middle of the night
21:32:59 <Slereah_> I wonder how long it would take to make a neural network learn the Fibonacci sequence
21:33:09 <Slereah_> Just input an ordinal and get the sequence member
21:33:58 <Bike> based on the evidence of my brain, i estimate that it would take approximately forever, unless the neural network was also a nerd
21:35:11 <Bike> probably needs a pocket protector too
21:37:13 <fizzie> kmc: There are special night-only bus lines, about 5 of theme these days. They go in a zigzaggy way in approximately equally spaced directions starting from the city centre.
21:38:12 <fizzie> Not very many scheduled departures, it's something like (for e.g. the 400N line) 2:35, 3:15, 4:00 and 4:15.
21:38:21 <b_jonas> only fice? hah, small town people
21:38:41 <fizzie> They all seem to be also Friday-and-Saturday-only.
21:39:27 <b_jonas> in some places, Budapest has better night buses than day ones
21:40:00 <b_jonas> maybe I should start going to work at \night
21:40:14 <fizzie> The local non-subway trains do have some amount of night service.
21:41:45 <b_jonas> the trains don't go during night here
21:41:50 <fizzie> Like, there's stop-on-all-stations departures from Helsinki towards Riihimäki/Lahti at 1:01, 1:31, 2:01, 2:31, 3:01, 4:01, 5:01 on the Fri/Sat and Sat/Sun nights; that pretty much covers the gap between the regular evening and morning trains.
21:42:44 <fizzie> Of course it's less nice if you happen to have some reason to be out late on anything else than a Friday or a Saturday.
21:43:39 <fizzie> E.g. it's pretty hard to go home to sleep on the first night of a Thursday-to-Sunday (pseudo-)demoscene event.
21:43:46 <oerjan> <myname> that sounds invader zimish <-- zzo38 is invader zim?
21:43:59 <fizzie> (Probably my only regular reason for interfacing with late-night public transportation.)
21:45:33 <b_jonas> I think the trains and non-urban buses stop during night so much that there's an instant each night when all passenger trains and all non-urban buses in the country are stopped.
21:45:53 <b_jonas> but it's hard to be sure about that for the buses, with these stupid timetables
21:48:23 <oerjan> <Bike> http://www.theallium.com/science-life/scientists-reportedly-close-to-finding-a-use-for-linkedin/ <-- subtle hostname, there
21:48:58 <fizzie> Though now that we live where we live, the last years I've just used the bicycle paths that run next to the train tracks. Summer nights/early mornings here are quite good for that; it's reasonably light, and usually refreshingly chilly.
21:49:20 <fizzie> Plus the place is for some reason full of rabbits around 03am or so.
21:49:42 <fizzie> I think I counted around twenty on a single trip.
21:49:58 <fizzie> (There's a bit of a pest problem with these "city bunnies".)
21:50:24 <fizzie> http://yle.fi/uutiset/hunt_for_city_bunnies_begins/6284368
21:50:39 <kmc> cuuuuuuute~
21:51:07 <fizzie> Those things go ridiculously fast for their size.
21:51:16 <kmc> i knew some good spots to find bunnies in Cambridge MA, but none in SF :/
21:52:29 <fizzie> "Helsinki to feed lions and vultures with city bunnies" sounds very exciting.
21:53:10 <fizzie> The circle of life. Except the bunnies are descendants of former pets, and the lions and vultures are in a zoo.
21:53:32 <fizzie> (And humans do the catching and feeding.)
21:53:51 <myname> oerjan: easy to find out. does he have any friends?
21:53:54 <fizzie> "The animal keepers at the zoo have also tried offering rabbits to the Steller's Sea Eagles, Haliaeetus pelagicus, but with little success. Apparently the heaviest eagle in the world, a beast with a wingspan of more than two metres, is actually afraid of the rather small cuddly cuties, which bear a passing resemblance to fur mittens."
21:54:15 -!- kallisti has joined.
21:54:52 -!- conehead has joined.
21:56:27 <oerjan> myname: you know, i have no evidence on that. does his D&D DM count?
22:10:44 -!- augur has joined.
22:11:18 -!- augur has quit (Remote host closed the connection).
22:18:21 <myname> i think i forgot how to sleep
22:18:47 <Taneb> I'm going to sleep now
22:18:58 <Taneb> Then in the morning, TRAVEL TO THE HOMELAND OF PHANTOM HOOVER
22:19:09 <myname> like, i am yawning every other minute but stay awake
22:19:45 <Taneb> (I need to visit the Australian Commission to renew my passport)
22:30:10 -!- esowiki has joined.
22:30:12 -!- glogbot has joined.
22:30:14 -!- esowiki has joined.
22:30:15 -!- esowiki has joined.
22:35:23 -!- augur has quit (Remote host closed the connection).
22:43:08 -!- yorick has quit (Remote host closed the connection).
22:52:34 -!- shikhout has joined.
22:55:22 -!- shikhin has quit (Ping timeout: 252 seconds).
22:55:22 -!- shikhout has changed nick to shikhin.
22:56:09 -!- Sgeo has joined.
23:03:56 -!- MoALTz_ has joined.
23:04:55 -!- MoALTz has quit (Ping timeout: 276 seconds).
23:05:09 -!- boily has joined.
23:06:03 -!- JesseH has quit (Read error: Connection reset by peer).
23:06:44 -!- JesseH has joined.
23:07:01 -!- MoALTz has joined.
23:07:53 -!- MoALTz_ has quit (Read error: Connection reset by peer).
23:18:51 -!- tromp has joined.
23:23:21 -!- tromp has quit (Ping timeout: 258 seconds).
23:50:33 <boily> good evening. a random thought was floating around in my cranium.
23:50:53 <boily> anyone know if jsvine published the Infamous Interview?
23:52:18 -!- madbr has joined.
23:52:41 <madbr> anyone has done verilog?
23:53:00 <oerjan> did ais523 use that or the other one
23:53:23 <boily> I should have ought to have did vhdl, but kinda dodged it.
23:53:45 <madbr> never done any but vhdl looks rather worse
23:54:04 <oerjan> i'm sure both of these questions could have been easily answered if Gregor hadn't broken `pastelogs hth
23:55:13 <boily> madbr: vhdl is refurbished ada.
23:56:10 <madbr> never tried ada either but it sounds grody
23:57:48 -!- metasepia has joined.
23:59:55 <madbr> looks just slightly more wordy in a way that makes it both harder to read and longer to type
00:04:37 <madbr> kinda wonder how hard it is to design a simple cpu, video rendering chip or sound playing chip
00:06:42 <boily> well, sound playing is the easiest. a few simple wave generators, subtractive synthesis, and you're golden.
00:07:08 <boily> in fact, you could design one with only basic discrete components.
00:07:15 <boily> (and a few logic gates if you wanna be fancy.)
00:07:28 <madbr> doesn't the filter require multipliers?
00:07:54 <madbr> in some feedback configuration
00:08:39 <boily> op amps. I always forget op amps.
00:09:02 <boily> I think you have them. I'd be very surprised if you didn't.
00:09:32 <boily> (but then, my understanding of verilog is quite limited and backwards, as I had urging deadlines and ethereal teammates to manage...)
00:10:27 * boily wonders if xcircuit is still maintained... “I have fond memories of that buggy and crashy piece of software...”
00:11:39 <madbr> hm, the one I've played around with is HADES
00:11:45 <madbr> and that's digital only
00:12:19 <boily> xcircuit is only for drawing. it was quite nice, when it was running.
00:13:05 <boily> I know I used something from xilinx a long time ago.
00:15:29 <madbr> I guess you could tape together 2 or 3 oscillators, pass through a textbook filter and multiply for volume yeah
00:15:40 <madbr> then replicate 6 times for a whole synth
00:17:03 <madbr> not very efficient but easy to design
00:18:56 <boily> I once combined a lo- and a hi-pass filter to make a no-pass filter. the end result was... unusual.
00:20:35 <madbr> filters were never too interesting to implement in sound LSIs
00:21:10 <madbr> until they became so large that they could just spend the extra multipliers on them
00:21:36 <madbr> (wavetable-based chips such as the soundblaster awe-32)
00:24:52 -!- ^v has joined.
00:39:21 -!- Sprocklem has joined.
00:39:21 -!- Sprocklem has quit (Changing host).
00:39:21 -!- Sprocklem has joined.
00:43:31 -!- tromp has joined.
00:48:27 -!- Phantom_Hoover has quit (Quit: Leaving).
00:49:32 <Bike> http://rxnm.files.wordpress.com/2012/08/image_thumb12.png?w=887&h=566 Meanwhile, science progresses
00:51:28 <oerjan> are you trying to point out the irony of the article vs. the number in the top bar
00:52:02 <kmc> his impact factor is over 9,000
00:55:40 <oerjan> Bike: perhaps you should stay away from inhabited planets twh
00:55:56 <kmc> every planet we reach is dead
00:56:11 <Bike> i don't actually know how impact factor is calculated. could you have 9000? is there like a singularity somewhere
00:56:30 <kmc> what's gauss's impact factor
00:56:30 <Bike> maybe over 1000 or so means everyone on earth is constantly thinking about your paper on cockroach neuroendocrine cells
00:56:39 <boily> what is an impact factor? against what is it impacted?
00:57:03 <Bike> It's a measure of your science penis
00:57:40 <oerjan> impomatic shouldn't feel too safe, either
00:57:51 <Bike> oh it's actually pretty simple: a journal's impact factor is number of citations of papers / number of papers written
00:58:19 <Bike> "The impact factor is based on the arithmetic mean number of citations per paper, yet citation counts follow a Bradford distribution (i.e., a power law distribution) and therefore the arithmetic mean is a statistically inappropriate measure." scientists are so awesomely bad at stats
00:59:41 <boily> oerjan: so, if I unabashedly mapole impomatic, I can augment my Factor?
01:00:36 <Bike> Annual Review of Immunology had the highest in 2006, apparently
01:01:22 <oerjan> boily: there's also a danger of both your factor and impomatic being smashed to little primes
01:02:33 <kmc> http://mushroomobserver.org/image/show_image/386349?q=1uvb6&size=full_size
01:02:53 <oerjan> Bike: clearly they should simply define the new Power Impact which takes this into account
01:02:55 <boily> impomatic: do you accept being a victim^Wvaluable contributor to a scientific experience of utmost importance?
01:04:43 <oerjan> kmc: i take it the flavor just rolls off your tongue
01:04:59 -!- nisstyre has joined.
01:06:11 <oerjan> douglass_: btw the nick thiotimoline is vacant here hth
01:06:31 <kmc> you can register multiple nicks to the same nickserv account
01:06:49 <Bike> oerjan: there's an elaboration where you weigh cites based on the citing journal's impact factor, like PageRank. it's fucking crazy
01:09:45 <oerjan> kmc: yes but thiotimoline hasn't been registered yet. nor has douglass_ fwiw
01:10:01 <kmc> that was to douglass_ not you
01:11:02 <oerjan> there's some limit but i'm pretty sure it's higher than 3 (i just have the 2)
01:12:10 <oerjan> Bike: clearly they should use the improved bfjoust algorithm.
01:12:11 -!- augur has joined.
01:12:20 <Bike> yeah that would make sense
01:15:56 <kmc> elo ratings
01:16:53 <boily> stupide bot de mes deux de pas foutu de trouver de l'information quand qu'on lui demande non mais tsé quand même...
01:17:28 <kmc> `thanks ants
01:17:36 <kmc> `thanks Hanks
01:18:34 <Bike> https://www.youtube.com/watch?v=rBHjx4dYxjA&t=2m20s my daily commute
01:19:28 <kmc> i like the part where individuals from different generations walk side by side
01:19:54 <kmc> Bike: why do people throw boxes at you on your commute
01:20:15 <Bike> They think I'm ugly since I'm made of boxes
01:20:17 <Bike> racism is terrible
01:20:32 <kmc> they see me boxin', they hatin'
01:20:46 <Bike> the dinosaurs falling over rule though yes
01:20:57 -!- JZTech102 has joined.
01:20:58 <kmc> hey it could be worse https://www.youtube.com/watch?v=rBHjx4dYxjA&t=3m10s
01:22:07 -!- vravn has quit (Ping timeout: 240 seconds).
01:22:07 -!- JZTech101 has quit (Ping timeout: 240 seconds).
01:22:35 <Bike> yeah i laughed out loud at that
01:25:11 -!- vravn has joined.
01:30:26 <oerjan> someone may have found a fly in the ointment of that inflation discovery http://physicsworld.com/cws/article/news/2014/apr/10/have-galactic-radio-loops-been-mistaken-for-b-mode-polarization
01:33:32 -!- JZTech102 has changed nick to JZTech101.
01:33:33 -!- JZTech101 has quit (Changing host).
01:33:33 -!- JZTech101 has joined.
01:38:29 -!- oerjan has set topic: The channel with > 10% bots | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
01:38:47 -!- nooodl has quit (Ping timeout: 265 seconds).
01:39:55 <douglass_> I'm using douglass_ instead of douglass because I registered douglass and then was too lazy to use it. I do like thiotimoline a bit better but it's less recognizable to people who know me in real life.
01:40:24 <Bike> ha ha, i knew i recognized the name from somewhere (no i didn't)
01:41:01 <boily> we have over 10% bots? wooooah...
01:41:05 <oerjan> douglass_: unless you have nick protection on, you don't _need_ to log in to use douglass
01:41:37 <douglass_> I don't even remember what I did when I set up this screen.
01:41:47 <douglass_> Certainly too lazy to change anything until it dies.
01:41:58 <Bike> "I inherited this dtach from my mother..."
01:42:51 <oerjan> boily: that also includes the logging bots.
01:43:55 <boily> and one unknown member, namely myndzi.
01:44:11 <Sgeo> I should play with Snap
01:44:18 <oerjan> i didn't include myndzi in the 10, but e would certainly not hurt the number
01:44:36 <boily> go myndzi! embrace your siliconoïd side!
01:44:42 -!- boily has quit (Quit: ROBOT CHICKEN).
01:44:44 -!- metasepia has quit (Remote host closed the connection).
01:49:37 <Sgeo> http://www.christianet.com/creditcounseling/
01:49:43 <Sgeo> Christian... credit counseling
01:49:47 <Sgeo> I don't get it
01:52:25 <Sgeo> I tried to install Snap, it seems to be installing lens....
01:52:40 <Sgeo> Oh, right, Snap was the one that bothered me for having its own little weird lens library, iirc
01:52:43 <Sgeo> Has that changed?
01:53:50 <Bike> do you ever think about turbulence
01:56:35 -!- tromp has quit (Remote host closed the connection).
01:56:36 <madbr> isn't christianity generally against credit?
01:57:12 -!- tromp has joined.
01:57:26 <Bike> if you're like, living in 1200s Europe, maybe
01:59:54 <madbr> http://www.thebricktestament.com/the_law/lending_money/ex22_24.html
02:00:47 -!- xpte has quit (Ping timeout: 252 seconds).
02:01:13 <Bike> Yes as it turns out practice does not completely correspond to any legal code for more than about two seconds
02:01:43 -!- tromp has quit (Ping timeout: 276 seconds).
02:01:53 -!- ggherdov has quit (Ping timeout: 252 seconds).
02:02:07 <Bike> Insofar as legal codes even mean anything bla bla bla
02:02:50 -!- xpte has joined.
02:04:56 <oerjan> iiuc there was a time in europe when that was interpreted by the christians such that they could not take interest from anyone, but by the jews such that they couldn't take interest from other jews, but could do it from christians. and so jews became the major bankers.
02:05:48 <oerjan> (this iiuc comes with no guarantees of actually being correct)
02:15:51 -!- ggherdov has joined.
02:30:55 <Bike> That's what I was trying to get at with the 1200s comment, yeah. it was usury.
02:31:22 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39344&oldid=39341 * Zerk * (+224)
02:31:59 <Bike> the workarounds are pretty hilarious sometimes http://en.wikipedia.org/wiki/Islamic_banking#Bai.27_al_.27inah_.28sale_and_buy-back_agreement.29
02:55:10 <Bike> Hey non-Americans, question: in your early math classes what symbols were used to describe a basic linear equation
02:57:13 <Bike> primary school? like "here's a line" early
02:57:25 <shachaf> not that i'm non-American, but i was in .il math classes until 4th grade or so
02:57:32 <shachaf> what do you mean by symbols
03:00:36 <Bike> something like that, yes.
03:01:11 <madbr> didn't see that until secondaire 1 tho (grade 7)
03:01:13 <Bike> i'm wondering because In American the usual is mx + b and the reason for the m is apparently mysterious
03:01:20 <Bike> In America rather
03:01:22 <madbr> oh yeah might have been
03:01:39 <Bike> quadratics are still ax² + bx + c though
03:01:43 <kmc> base and mantissa... wait no
03:02:00 <Sgeo> I was at a friend's house, and some teacher(?) was quizzing me, and I knew things like derivatives but not what y=mx+b was about
03:02:03 <Bike> i literally found a citation for this saying "It just happened"
03:02:08 <Sgeo> This was many, many years ago
03:02:14 <kmc> multiplier? i hardly know 'er!
03:02:32 <Bike> and like apparently in swedeworld it's usually "kx + m", k for koefficient
03:03:06 <shachaf> (i totally used U+2062 INVISIBLE TIMES, by the way)
03:03:24 * Sgeo verifies shachaf's clam.
03:03:31 <Sgeo> (Actually not fully verified)
03:03:39 <Sgeo> (And not a clam, but that was deliberate)
03:03:45 <Bike> wow, one of the citations is to an aol page
03:04:06 <shachaf> Bike: but aren't they both koëfficients :'(
03:04:12 <shachaf> wait maybe that's not valid swedish
03:04:20 <Bike> which is down, but thankfully i found a mirror. on tripod.
03:04:33 <Bike> shachaf: «where k may derive from "koefficient" in the Swedish word for slope, "riktningskoefficient."» is what it says
03:04:51 <Bike> rïktningsköefficient
03:05:30 <oerjan> ö IS A SEPARATE LETTER
03:05:36 -!- password2 has joined.
03:05:46 <shachaf> oerjan: you should be swatting me, though
03:05:56 <shachaf> coefficient, more like scowefficient
03:06:25 <shachaf> (because it's such a scow)
03:07:48 <oerjan> incidentally sv:ko = cow but sv:kö = queue
03:09:15 -!- ^v has quit (Read error: Connection reset by peer).
03:09:26 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39345&oldid=39344 * Zerk * (+57) /* Toplevel */ fixed math by adding unwrapped 0/1 defs
03:09:43 -!- ^v has joined.
03:10:08 <oerjan> and ko is not a common word in norwegian.
03:10:14 <Sgeo> maybe 5 (error "Must be Nothing")
03:10:25 <Sgeo> maybe 5 (const $ error "Must be nothing)
03:10:32 <Sgeo> Any significant reason to use one vs the other?
03:10:43 <Sgeo> :t maybe 5 (error "Must be nothing")
03:10:50 <Sgeo> :t maybe 5 (const $ error "Must be nothing")
03:10:59 <Bike> the $ indicates xtreme dosh
03:11:16 <shachaf> they will compile to the same thing
03:11:50 <kmc> $wag overload
03:12:47 <oerjan> i don't think there's any difference in semantics
03:13:07 <kmc> benchmark it with criterion
03:13:22 <oerjan> given that maybe won't be applying any seq's to it.
03:14:20 <shachaf> that's actually what i meant
03:14:23 <madbr> kö sounds like a borrowing
03:14:28 <shachaf> i didn't mean that they would compile to the same thing
03:14:31 <oerjan> Sgeo: basically const $ error ... is equivalent to error ... unless you apply seq to it
03:14:39 <shachaf> i meant they have the same semantics and i was wondering whether they would also compile to the same thing
03:14:47 <Sgeo> Even in terms of when the error message gets shown?
03:14:51 <shachaf> only if maybe gets inlined probably?
03:15:29 <Bike> i'm confused, this seems like the sort of thing haskell is pretty simple about
03:15:47 <Sgeo> Bike: undefined, and laziness in general, is a ... complication
03:15:59 <kmc> laziness: the ultimate side effect
03:16:05 <shachaf> it's not very complicated here
03:16:49 <Sgeo> I assume laziness can be described as a monad
03:17:27 <Sgeo> Although it kind of sucks to use lifted 'pure' functions in it, since they would be considered to be strict, I think
03:17:33 <kmc> Haskell didn't so much eliminate side effects as introduce a single pervasive side effect that doesn't play nice with others
03:17:40 * kmc checks if that's less than 140 characters
03:18:01 <Sgeo> Yeah but it allows for fancy tricks! At the expense of safety
03:18:06 <kmc> happiness is a warm monad
03:18:27 <kmc> the english word for cow is "cow"
03:19:15 <Bike> the english term for "cow" is "use-mention distinction"
03:20:50 <kmc> names with their own names!
03:21:11 <Bike> so does anyone else think once you have a "series of monographs" in over 40 volumes you should consider calling it something else
03:22:48 <oerjan> i assume it's time to link https://en.wikipedia.org/wiki/Haddocks'_Eyes#Naming again
03:23:09 <kmc> Bike: a polygraph?
03:23:17 <Bike> wow how did i not think of that
03:23:54 <kmc> oerjan: yeah that's the only example I know, besides "tetragrammaton"
03:23:57 <kmc> edit: fuck, beaten
03:25:24 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
03:25:34 <shachaf> that did help hope that helped have a nice day
03:25:38 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
03:25:50 <HackEgo> tdh is the past tense of a successful hth. hth.
03:26:08 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: àwesomé´: not found
03:28:09 <HackEgo> /hackenv/bin:/opt/python27/bin:/opt/ghc/bin:/usr/bin:/bin
03:28:45 <oerjan> i guess there's no way to get an empty command name to work
03:35:48 -!- Sorella has quit (Quit: It is tiem!).
03:44:25 -!- password2 has quit (Ping timeout: 276 seconds).
03:49:35 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39346&oldid=39345 * Zerk * (-6) /* Toplevel */ properly* fixed math
03:49:41 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
04:00:43 -!- kallisti_ has joined.
04:03:39 -!- kallisti has quit (Ping timeout: 250 seconds).
04:08:07 -!- tromp has joined.
04:23:44 -!- tromp has quit (Remote host closed the connection).
04:30:01 -!- oerjan has quit (Quit: leaving).
04:46:04 -!- Sprocklem has quit (Quit: leaving).
04:47:13 -!- Bike has quit (Quit: leaving).
04:47:34 -!- Bike has joined.
04:52:53 -!- shikhout has joined.
04:54:44 <Sgeo> (About OverlappingInstances)
04:54:45 <Sgeo> "Can sometimes be simulated with the extra-method trick used in the Show class of the Prelude for showing lists of characters differently than lists of other things.
04:54:48 <Sgeo> What trick is this?
04:55:47 -!- shikhin has quit (Ping timeout: 252 seconds).
04:55:49 -!- shikhout has changed nick to shikhin.
05:00:00 <Sgeo> Is it a bad idea to write code like
05:00:07 <Sgeo> blah >>= flip when $ do ...
05:00:32 <shachaf> > "flip" `isInfixOf` "blah >>= flip when $ do ..."
05:00:32 <idris-ircslave> When elaborating an application of constructor __infer:
05:00:42 <shachaf> idris-ircslave: go away or change your prefix
05:00:43 <idris-ircslave> When elaborating an application of constructor __infer:
05:12:16 <fizzie> I understand these days you just bite the bullet and use @run.
05:13:02 <shachaf> lambdabot: @run away or change your prefix
05:13:04 <lambdabot> Not in scope: ‘away’Not in scope: ‘change’
05:13:04 <lambdabot> ‘hang’ (imported from Text.PrettyPrint.HughesPJ)Not in scope: ‘your’Not in...
05:13:04 <lambdabot> Perhaps you meant ‘prefixed’ (imported from Data.List.Lens)
05:14:00 <fizzie> Idris also had something lambdabot did not respond to.
05:14:16 <shachaf> Yes, I used it a few lines above.
05:15:26 <fizzie> Something shorter than the full name, too.
05:17:12 <fizzie> It's like, it acquired a non-conflicting prefix, but did not get rid of >.
05:18:06 <fizzie> Which I kind of hope it would, but haven't cared about enough to say anything.
05:19:09 <Jafet> Think about it, shachaf, this is helping to get rid of the ) backlog.
05:19:46 <fizzie> (: just doing my part.
05:27:31 -!- kallisti_ has quit (Ping timeout: 258 seconds).
05:30:16 -!- kallisti has joined.
05:36:34 <Bike> http://freshbsd.org/search?project=openbsd&q=file.name:libssl they mad
05:37:33 -!- asie has joined.
05:37:34 <kmc> https://github.com/jmhodges/libssl/commits/master
05:37:41 <asie> hi! i used to be known as asiekierka here
05:37:43 <asie> a few years back
05:41:00 <shachaf> kmc: hmm, you've written ~20% more words in #haskell than i have
05:42:32 <kmc> Bike: hm your link is better
05:42:53 <Bike> i am the superior being.
05:47:06 <kmc> hasn't jconn already ruined the paren-balance of this room?
05:47:36 -!- conehead_ has joined.
05:48:05 -!- conehead has quit (Ping timeout: 250 seconds).
05:50:35 <kmc> is that a tie fighter
05:51:15 <kmc> rather a TIE Advanced x1
05:53:18 -!- MoALTz has quit (Quit: bbl).
05:55:46 <myname> https://www.dropbox.com/s/skmvujsn35s6q2x/IMG_20140417_075324.jpg wat
05:58:49 <oklopol> i don't think that's particularly weird
05:59:04 <oklopol> (except that i don't like any of those bands)
05:59:24 <myname> the second paragraph confuses me
05:59:31 <olsner> http://freshbsd.org/commit/openbsd/6fec7be36425adfd2b48f3695d24a03f6287d4fe wat
05:59:54 <myname> i don't get why he translated from german in a german university, either
06:00:14 <kmc> those are some good musicians
06:00:14 <myname> the fucking is one point, yes
06:00:16 <oklopol> maybe that's slightly weird
06:00:20 <olsner> myname: for the international students?
06:00:22 <kmc> perhaps i should find this person and engage in some of these activities
06:02:52 <myname> kmc: in return, name a cool esolang i could write a compiler for, that is not too hard to make
06:05:46 * Jafet memorizes that list of musicians for later hipster usage
06:06:32 <kmc> yeah radiohead is a pretty obscure hipster band
06:07:18 <Jafet> It looks like they forgot to translate Strawinsky
06:08:48 -!- ^v has quit (Read error: Connection reset by peer).
06:08:50 <kmc> wait are all those gerunds meant to apply to the noun "music"
06:09:16 <oklopol> that was my interpretation
06:09:16 -!- ^v has joined.
06:09:21 <myname> especially how "fucking music" would look like
06:09:23 <kmc> it makes... more and less sense simultaneously
06:09:51 <oklopol> i thought the joke was that it sounds like he is proposing sex, but then it turns out he is still talking about music
06:10:07 <myname> but what the hell is fucking muic?
06:10:48 <oklopol> (and that maybe his original wording in german made that slightly clearer, although i guess that's a bit unlikely)
06:11:04 <olsner> myname: that guy is, and the friends who respond?
06:11:26 <oklopol> he says something like in increasing order of emotional whatever
06:12:22 <kmc> perhaps he refers to products such as http://www.ohmibod.com/ [nsfw i guess]
06:12:49 <kmc> music controlled vibrators
06:13:18 <oklopol> perhaps the meaning of (emotionally ordered) was clearer originally
06:13:27 <oklopol> and yeah those sound awesome
06:14:07 <kmc> eh better to build a USB control kit for the Magic Wand, i think
06:14:13 <Jafet> http://www.gamegirladvance.com/2002/10/sex-in-games-rezvibrator.html
06:14:23 <myname> kmc: go and sell the result
06:14:29 <myname> you will be rich in no time
06:14:44 <kmc> selling stuff is hard
06:14:47 <kmc> then it has to be, like, good
06:14:53 <kmc> i've never made a physical thing that was good
06:15:23 <kmc> the Hitachi Magic Wand contains a 120 V DC motor
06:15:31 <kmc> the two speed settings correspond to half-wave and full-wave rectifiers
06:15:53 <kmc> ask me how i know this
06:16:08 <kmc> by taking one apart
06:16:21 <kmc> wasn't mine
06:16:27 <kmc> and we put it back together
06:16:29 <myname> i could think of better use cases
06:17:34 -!- conehead_ has quit (Quit: Computer has gone to sleep).
06:22:39 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:23:55 <kmc> at one of the sex toy shops in SF they have a museum with a bunch of old vibrators
06:25:40 <kmc> the vibrator was the fifth ever electric domestic appliance
06:25:45 -!- madbr has quit (Quit: Rouringu de hajikunda!).
06:26:00 <myname> at which point is the washing mashine?
06:28:15 <kmc> much later I think
06:28:46 <kmc> complicated and needs lots of power
06:29:00 <kmc> early appliances just connected in place of a light bulb
06:29:27 <shachaf> at what point was mr burbujas
06:29:37 <kmc> mr burbujas exists outside of time and space
06:29:48 <kmc> our entire universe is but one bubble in his frothy beard
06:30:13 <kmc> for the un-enlightened: http://www.sanfranciscodays.com/photos/large/mr-burbujas.jpg
06:33:53 * kmc -> bed (?)
07:32:44 -!- shikhin has quit (Ping timeout: 252 seconds).
07:49:12 -!- Tritonio has joined.
08:10:44 -!- Frooxius has quit (Quit: *bubbles away*).
08:10:55 -!- Frooxius has joined.
08:14:05 -!- Patashu has joined.
08:14:50 -!- Patashu[Zzz] has joined.
08:14:50 -!- Patashu has quit (Disconnected by services).
08:39:18 -!- Sellyme has quit (Excess Flood).
08:40:24 -!- Sellyme has joined.
08:41:22 -!- xpte has quit (Quit: Connection closed for inactivity).
08:50:28 -!- asie has quit (Ping timeout: 240 seconds).
08:52:17 -!- asie has joined.
09:02:53 <impomatic> boily, oerjan: anything in the name of science...
09:05:25 <fizzie> Bike: It's quite commonly "kx + ???" in Finland, and the "k" can be argued to stand for "kulmakerroin". I don't remember what the ??? usually is.
09:06:20 <fizzie> I think maybe "kx + b", though there is no Finnish explanation for b.
09:07:02 <fizzie> http://opinnot.net/kokonaisuudet/index.php?id_kokon=164&kieli_id=1&taso_kokon=0&oppiaine_kokon=2 and so on.
09:09:07 <fizzie> Searching for "y=kx" in Finnish has "b" for 9 out of 10 hits on the first page. (Last one just has "y = kx".)
09:10:11 <fizzie> ("kerroin" = coefficient, "kulma" = angle.)
09:10:30 <fizzie> ("kerroin" = "I told".)
09:13:39 <fizzie> It's the noun for coefficient, the first-person singular indicative past form of the verb "kertoa" 'to tell, to multiply (transitive)', and (which I didn't even think about at all before looking at Wiktionary) the instructive case plural form of the noun "kerta" (approx. 'occasion'). Possibly because the instructive case is such nonsense.
09:13:48 <fizzie> http://en.wikipedia.org/wiki/Instructive_case
09:13:54 <fizzie> What's that good for, anyway?
09:15:41 <fizzie> I guess it's used in something like "kaksin kerroin".
09:20:37 -!- yorick has joined.
09:22:26 -!- AnotherTest has joined.
09:44:09 -!- Tritonio1 has joined.
09:45:22 <fizzie> Fun fact: a = 0; printf("%d %d %d %d", a, a++, a, a++); produces "2 1 2 0" on many GCC versions on x86 and x86-64, "2 0 2 1" on GCC 4.7 on ARM and ICC 12.1.0 on x86-64, "0 0 1 1" on some versions of clang on x86-64, and "2 1 2 1" on the PGI C compiler on x86-64.
09:45:44 <fizzie> That's probably not an exhaustive list.
09:45:59 -!- Tritonio has quit (Ping timeout: 250 seconds).
09:47:26 <fizzie> The one with no zeroes in it is quite nice.
09:57:36 <b_jonas> fizzie: on x86, doesn't it also depend on -mcpu/-mtune?
09:57:54 <b_jonas> and maybe on other optimization switches
09:58:01 <fizzie> I couldn't coax other outputs with flags, but I'm sure it could be possible.
09:59:09 <lifthrasiir> we should make a C compiler that launches /usr/games/hack on compiling such program
10:16:31 -!- boily has joined.
10:29:22 -!- jconn has quit (Ping timeout: 276 seconds).
10:29:56 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.).
11:01:03 -!- Phantom_Hoover has joined.
11:05:06 -!- boily has quit (Quit: Ping: Read: Error: Timeout: Remote: Chicken).
11:07:37 -!- nucular has joined.
11:07:37 -!- nucular has quit (Changing host).
11:07:37 -!- nucular has joined.
11:17:54 -!- jconn has joined.
11:19:08 -!- atslash has joined.
11:25:49 -!- atslash has quit (Remote host closed the connection).
11:26:19 -!- atslash has joined.
11:27:47 -!- password2 has joined.
11:37:49 -!- jconn has quit (Ping timeout: 258 seconds).
11:38:17 -!- slereah has joined.
11:40:17 -!- jconn has joined.
12:10:43 -!- MindlessDrone has joined.
12:11:31 -!- Sorella has joined.
12:18:00 -!- Sgeo has quit (Read error: Connection reset by peer).
12:44:23 <slereah> What activation function would be faster for a backpropagation algorithm
12:44:46 <slereah> The basic sigmoid has an exponential in it, but on the other hand the derivative can be expressed simply by the function
12:45:06 <int-e> atan has 1/(1+x^2) as its derivative
12:45:23 <slereah> And the one that is 1/(1 + |x|) is simple to calculate but the derivative has to be calculated independantly
12:46:37 <Jafet> Changing the activation also changes the learning rate, doesn't it
12:46:42 -!- Sellyme has quit (Excess Flood).
12:47:01 <slereah> Dont know which one is better for it
12:47:53 -!- Sellyme has joined.
12:52:39 <fizzie> The Elliott activation function has the best name, obviously.
12:53:20 <slereah> http://www.dontveter.com/bpr/activate.html
12:54:03 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
12:56:17 <FreeFull> Not sure if it would be suitable though
12:56:29 <slereah> "Both these sigmoid approach their extremes more slowly. This means that if you are trying to output numerical values it will take more iterations to reach your target value. But if you're doing a classification problem you really only care to get the correct output value greater than the other outputs and here these functions will save on CPU time without influencing the number of iterations required by very much. "
12:57:26 <slereah> I guess I'll worry about that later and try several activation functions
12:57:37 <fizzie> "However, while simulation is faster with elliotsig, training is not guaranteed to be faster, due to the different shapes of the two transfer functions. Here, 10 networks are each trained for tansig and elliotsig, but training times vary significantly even on the same problem with the same network." (MATLAB Neural Networking toolbox, "Optimize Neural Network Training Speed and Memory" article.)
13:01:37 -!- conehead has joined.
13:13:20 <elliott> does it really misspell his name?
13:14:30 <slereah> elliott, tell us about your activation function
13:14:49 <fizzie> elliott: It does; it also does not credit him in any way.
13:15:53 <fizzie> Not that I think MATLAB documentation usually does, but still.
13:17:33 <fizzie> (It also doesn't mention what the actual function is, anywhere; I had to use "type" to check that it actually is the same as that David Elliott one.)
13:17:50 <elliott> it's a lot more common as a surname than a first name, it seems
13:20:50 -!- douglass_ has quit (Ping timeout: 255 seconds).
13:22:23 -!- douglass_ has joined.
13:41:46 -!- Patashu[Zzz] has quit (Ping timeout: 276 seconds).
14:06:40 -!- Phantom_Hoover has joined.
14:31:02 <slereah> Man my perceptron converges values all to 0.5 :(
14:35:54 <Jafet> It learned the truth
14:37:44 <slereah> The problem isn't from the learning rate and inertia apparently
14:38:18 <slereah> For some reason all my weights converge to 0
14:39:18 <slereah> It's that Stephen King book all over again
14:48:31 <Phantom_Hoover> slereah, i thought you were shachaf for quite a long time
14:56:48 <Bike> phantom's right
14:57:56 <slereah> slereah may not be upper cased
14:58:01 -!- `^_^v has left ("Leaving").
14:58:05 -!- `^_^v has joined.
15:02:04 -!- Tritonio1 has quit (Ping timeout: 240 seconds).
15:03:02 -!- Tritonio has joined.
15:04:26 <Bike> if all weights are converging to zero does that just mean it's learning a constant function
15:04:41 <slereah> I'm trying to make an autoencoder
15:04:52 <slereah> So the training set is just the identity function
15:05:03 <slereah> Currently the input is just (1 2 3 4 5)
15:05:27 <slereah> And I'm trying to get the same as output
15:05:50 <slereah> But for some reason weights all decrease with each update until they're all 0
15:06:08 <Bike> "Reading an embargoed paper that cites 71 papers in the first two sentences."
15:06:17 <Bike> well, that sounds like a bug probably /helpful
15:10:31 <fizzie> Are you doing it all DIY, or with some sort of a thing?
15:12:45 <slereah> Do you mean coded from scratch
15:13:02 <slereah> Though I did look at a few libraries of it before
15:17:53 <fizzie> Right, right, that just makes bug-in-the-implementation the likelier reason than doing-it-wrong.
15:18:11 <slereah> Well doing it wrong is still on the table
15:18:34 <slereah> I guess maybe I should do a very simple one
15:18:44 <slereah> 2 in, 2 out, 1 hidden neurone
15:22:18 <Bike> can you do an identity map if everything has to go through one neuron...?
15:23:29 <slereah> It's unfortunate that there are no step by step examples of the backpropagation algorithm
15:23:34 <slereah> I could check where it went wrong
15:25:46 -!- Tritonio has quit (Ping timeout: 276 seconds).
15:31:47 <fizzie> Bike: It should at least do a credible approximation, anyway, as long as things work out.
15:33:15 <fizzie> Autoencoder features are quite "hip" at the moment in the speech recognition field.
15:33:25 <Bike> how would it distinguish, like, 01 from 10
15:34:17 <Bike> The hidden neuron outputs one bit, doesn't it? How do you encode two bits into one bit
15:35:00 <fizzie> Bike: It's not usually binary; but in any case, by having first output equal to the hidden bit, and the second its complement.
15:35:07 <fizzie> Bike: That way 0 -> 01 and 1 -> 10.
15:35:21 <Bike> but then you couldn't also do 00 and 11.
15:35:28 <slereah> The network has real values and real weights
15:35:31 <Jafet> Neural networks can output any real number
15:35:52 <fizzie> Bike: Sure, sure; but it's supposed to learn the "best" low-dimensional representation it can.
15:36:14 <Jafet> You interpret the number if you want a classifier
15:36:50 <Bike> okay i guess i thought after the sigmoid you had a binary threshhold. oopsie.
15:37:26 <Jafet> The sigmoid is used to introduce nonlinearity (and to compress outputs between layers)
15:38:52 <fizzie> http://jmlr.org/papers/volume11/vincent10a/vincent10a.pdf is the kind of thing people do on speech too.
15:39:37 <fizzie> (Have to go do some things.)
15:44:37 -!- password2 has quit (Ping timeout: 265 seconds).
15:52:05 -!- tertu has joined.
15:55:00 -!- mekeor has joined.
15:55:54 -!- ^v has joined.
15:59:21 -!- tertu has quit (Ping timeout: 252 seconds).
16:00:13 -!- slereah has quit (Quit: Leaving).
16:01:49 <Taneb> Today I got a free hat
16:08:34 -!- Sprocklem has joined.
16:09:08 -!- doesthiswork has joined.
16:27:26 -!- ^v has quit (Read error: Connection reset by peer).
16:27:54 -!- ^v has joined.
16:28:41 -!- shikhin has joined.
16:36:34 <doesthiswork> so I've got a fun little thing. variables can only hold random bits. You can set a variable to the result of xoring or averageing other variables together. Print prints out the name of the variable that most closely matches the chunk of bits coming after it.
16:37:03 <doesthiswork> the control structures are "label" and "call" but procedures do not accept arguments
16:38:06 <Jafet> So, just xor all variables with themselves
16:38:14 <doesthiswork> call calls the chunk of code labeled with the most similar chunk of bits to the one its called with
16:39:31 <Jafet> Ok, so what is special
16:40:15 <doesthiswork> you can holographically store values in other values
16:40:36 <doesthiswork> using xor to make a pair and averaging to combine several pairs
16:44:05 -!- Slereah_ has quit (Ping timeout: 252 seconds).
16:45:33 <doesthiswork> I'm pretty sure it isn't turing complete because you can only store a finite amount of information in an anonymous value
16:45:47 -!- Slereah_ has joined.
17:12:57 <FreeFull> What sort of ternary operations would be useful for a ternary computer?
17:13:18 <FreeFull> I was thinking tritwise max would be a rough equivalent of OR
17:13:19 <b_jonas> FreeFull: all the trintercal ones?
17:14:40 <b_jonas> dunno, I'd rather stick to binary (with two's complement or one's complement, and fibonacci and negafibonacci)
17:16:07 <FreeFull> But ternary is the easiest way to render a sierpinski carpet to the screen
17:17:46 <doesthiswork> there are 3^9 different two argument ternary operators
17:18:30 <int-e> so that's one operation then, the sierpinsky operation: 222;202;222. For the other, addition, perhaps?
17:19:29 <fizzie> Not going the balanced ternary route? (In which case multiplication is I guess quite a natural one.)
17:19:53 -!- nisstyre has joined.
17:20:20 <doesthiswork> you could try creating random ternary circuts out of a selection of ternary gates and see which set seems to produce the remainder of the gates most fairly
17:25:54 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
17:33:59 <FreeFull> A single binary operation has many ternary equivalents
17:34:18 <FreeFull> Tritwise multiplication and tritwise min are both equivalents of AND
17:42:15 <kmc> what's a minimal basis for all ternary operations?
17:45:12 <fizzie> "A single two-input ternary operator and a single one-input ternary operator are proposed, which together with the logic values 1 and 2 form a functionally-complete set of ternary operators."
17:46:08 <fizzie> Tokmen, V. H. "A functionally-complete ternary system", Electronic Letters, Feb 1978, 14(3), pp. 69-71, http://dx.doi.org/10.1049/el:19780048
17:46:39 -!- Phantom_Hoover has joined.
17:47:48 <fizzie> The two-input operator it mentions is the {max(a, b) if a != b; 0 if a = b} one, and the unary operator is the {2 if a = 0; 0 if a != 0} one.
17:48:34 <fizzie> That's just the unary operator applied to 1 or 2, after all.
17:48:50 <Jafet> You don't need 0 for binary logic, either
17:49:17 <Bike> yeah, i still like it
17:49:41 <Jafet> 0 is nothing compared to 1
17:49:41 <fizzie> "The particular merit of the above operators is their ease of realisation in bipolar or m.o.s., technology."
17:49:59 -!- shikhin has changed nick to draumr.
17:50:04 <fizzie> The two-input operator is called the TOR, short for "Ternary exclusive-OR".
17:51:08 <fizzie> Also the notation is quite funky. TOR is denoted by a τ b, and the unary one by ⁰a⁰ of all things.
17:51:31 <Jafet> The teddy ears operator
17:51:44 <Jafet> I'm sure it'll catch on
17:53:09 <Bike> too cute not to
17:53:47 -!- draumr has changed nick to shikhin.
17:54:20 <Jafet> I wonder if they ever realised it in bipolar or m.o.s. technology.
17:54:38 <fizzie> Apparently it's a friend of ¹(a)¹ and ²(a)² -- the number denotes what a must be to get the value 2.
17:54:52 -!- nortti has changed nick to hvidie.
17:56:00 -!- hvidie has changed nick to nortti.
17:59:33 -!- atslash has quit (Ping timeout: 250 seconds).
18:02:17 <fizzie> Whose idea it was anyway to make it unclear whether calling something a "binary operator" (resp. a ternary operator) means that it takes two (resp. three) inputs or that it has two (resp. three) states for those inputs?
18:05:24 <Bike> huh. i don't think i've heard the latter. until um, just now.
18:05:45 <kmc> whose idea was it that the term "special case" should have two opposite meanings
18:07:06 <Jafet> kmc: http://nlab.mathforge.org/nlab/show/red%20herring%20principle
18:07:17 <Jafet> "The mathematical red herring principle is the principle that in mathematics, a “red herring” need not, in general, be either red or a herring."
18:08:02 <fizzie> The "two-input ternary operator" was an instance of the latter use.
18:08:20 <fizzie> And this other "Ternary Exclusive Or" is an instance of the former.
18:08:59 <kmc> Taneb: what kind of hat did you get for free; also how?
18:09:03 <fizzie> (It's just a boolean logic connective that's true iff exactly one of its three inputs is true.)
18:09:07 <HackEgo> mopocoin relyknitiationcoin hairequitcoin pingbraicoin liheidifycoin rpecoin bdallcoin duplycoin rubeofthecoin pcoin buggonaltcoin peracoin claimcoin aftgreurochesecoin festcoin selectpcoin hercoin wildcoin obfurlocoin mckecoin
18:09:31 <kmc> rubeofthecoin
18:09:53 <fizzie> duplycoin doesn't even try to prevent double-spending.
18:10:49 <Taneb> kmc, some form of knit cap
18:12:04 <fizzie> Huh, I didn't even know the next Ubuntu was going to be the "Trusty Tahr" and now it's released.
18:12:50 <Jafet> I hope ubuntu dies after Zebra
18:12:58 <Jafet> If for no other reason
18:13:30 <fizzie> The development code name page already goes up to 20.04 that will start with F; they just loop around.
18:13:42 <fizzie> The one where they list suggestions, that is.
18:14:39 <fizzie> The U names sound p. stupid.
18:52:44 -!- mekeor has quit (Remote host closed the connection).
18:54:16 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:55:37 <b_jonas> fizzie: no, duplycoin is like the treasure in Bellatrix Lestrange's vault in Gringotts: it's enchanted so that when you touch it it produces duplicates that look similar but are worthless, and also glow hot
18:56:48 <kmc> i've said it before but they should loop around with fungi next
18:57:21 <kmc> Ascendent Amanita, Beautiful Bolete, Charming Chanterelle
18:58:34 -!- vravn has quit (Ping timeout: 240 seconds).
19:00:03 -!- xpte has joined.
19:02:06 <b_jonas> kmc: good idea. then bacteria, then plants after that.
19:04:20 -!- vravn has joined.
19:07:55 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
19:15:10 <kmc> delicious dekkera, esoteric ergot, faithful flammulina, glistening ganoderma, happy hypholoma, intriguing inocybe, jovial jelly, keen kuehneromyces
19:22:33 <kmc> leafy laetiporus, magnificent morel, noble neolentinus, omniscient omphalotus, pleasing pleurotus, quixotic queletia, rustic russula
19:22:51 -!- AnotherTest has quit (Ping timeout: 252 seconds).
19:23:13 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
19:28:18 <HackEgo> olist (949): shachaf oerjan Sgeo FireFly boily nortti
19:30:22 <kmc> superb saccharomyces, tasty truffle, unctuous urnula, vernal velvet-foot, wonderful wine-cap, xenodochial xylaria
19:30:30 <kmc> i'll get back to you on y and z
19:30:46 -!- MoALTz has joined.
19:31:26 <kmc> i have no idea if velvet foot mushrooms actually grow in the spring; also it's the same critter as flammulina
19:33:28 -!- jix has quit (Remote host closed the connection).
19:34:26 -!- jix has joined.
19:41:27 -!- Sprocklem has quit (Ping timeout: 265 seconds).
19:45:01 -!- Sprocklem has joined.
19:45:01 -!- Sprocklem has quit (Changing host).
19:45:01 -!- Sprocklem has joined.
19:46:03 -!- Phantom_Hoover has joined.
19:51:42 <kmc> loveable lactobacillus
19:56:25 -!- shikhout has joined.
19:58:21 -!- shikhin has quit (Disconnected by services).
19:58:25 -!- shikhout has changed nick to shikhin.
20:17:31 <kmc> http://livegrep.com/search/linux?q=CHICKEN
20:25:36 <HackEgo> [wiki] [[Hollang]] N http://esolangs.org/w/index.php?oldid=39347 * Doesthiswork * (+2349) new holographic language
20:26:22 <HackEgo> [wiki] [[Hollang]] M http://esolangs.org/w/index.php?diff=39348&oldid=39347 * Doesthiswork * (+2)
20:31:09 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
20:34:19 -!- nisstyre has joined.
20:39:23 -!- doesthiswork has quit (Quit: Page closed).
20:39:39 -!- nooodl has joined.
20:41:15 <HackEgo> Concentrate and ask again.
20:43:26 <Bike> http://opensslrampage.org/post/83019384273/ok-there-was-a-need-for-openssl-cleanse-instead all your favorite drama, now in tumblr form
20:43:40 <myname> what the hell @ hollang
20:59:38 -!- adu has joined.
21:09:33 <Bike> ok i'm loving this, i looked up what OPENSSL_malloc is
21:09:37 <Bike> OPENSSL_malloc is a macro that expands to a call to CRYPTO_malloc, which calls a function pointer. the default value of that function pointer is a function that calls another function pointer. the default value of /that/ function pointer is, finally, malloc.
21:10:34 -!- nucular has quit (Quit: Excess Food).
21:11:19 <elliott> Bike: are you sure there's not one too many levels of funptr indirection there...?
21:11:25 <elliott> I'd... be surprised but not surprised enough
21:11:48 <Bike> yes. the outer function pointer is "malloc_ex_func" which is like malloc but takes __LINE__ and __FILE__
21:12:40 <Bike> see, the whole purpose for this is that if nothing's been allocated yet, you (as in you, outside the library) can call a function to switch all these pointers to something else
21:13:01 <elliott> that's actually useful sometimes, for what it's worth
21:13:20 <Jafet> BECAUSE LIBC MALLOC IS TOO SLOW
21:14:47 <Bike> hm does mercurial's web interface let you grep code or no
21:17:22 <Bike> p[-1] = (0xdeadbeef << 31) + 0xdeafdeed; <-- nifty (in gmp)
21:17:53 -!- adu has quit (Quit: adu).
21:19:36 <Jafet> Why would they shift a 32-bit number by 31 bites
21:21:27 <int-e> it could be 64 bits
21:21:35 <Bike> it's aprt of a debug section
21:22:10 <int-e> (to quote another popular value ;-) )
21:22:17 <Jafet> 0xdeadbeef is a 32-bit constant
21:22:37 -!- Sprocklem has quit (Ping timeout: 276 seconds).
21:23:57 <int-e> so you don't know how many bits it has from the compiler's perspective
21:24:52 <fizzie> libpng has a compile-time option (PNG_USER_MEM_SUPPORTED) that lets you switch around the memory allocation functions.
21:25:03 <Jafet> Unless that's in the cray mpn code or something, it's going to be a 32-bit unsigned int
21:27:08 <fizzie> And GMP has at least reasonable chances of running on such a thing, compared to many other pieces of code.
21:27:44 <Jafet> Yes, I know there is cray mpn code (and probably people still using it)
21:31:53 <Bike> https://gmplib.org/repo/gmp/file/55ff6b8d9a92/memory.c#l130 i come bearing context
21:32:39 <Jafet> I guess it's probably what it is for no particular reason
21:33:04 <fizzie> Since mp_ptr is an mp_limb_t *, and quite often mp_limb_t is unsigned long instead.
21:33:16 <Jafet> It's repeated a dozen times, though, and you'd think it'd be a macro at that point
21:34:08 <fizzie> Would presumably make sense to convert the constants to mp_limb_t.
21:35:45 <Jafet> Yes, it looks like a "bug"
21:38:18 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
21:39:44 <fizzie> Also I believe it's possibly undefined behaviour on a system where int is larger than 32 bits but smaller than 64.
21:40:44 <Jafet> Is it? The shift is valid as long as unsigned int is 32-bit or larger.
21:40:59 <fizzie> But the type of an unsuffixed hex constant 0xdeadbeef is signed int if it can represent the value.
21:41:22 <fizzie> And E1 << E2, when E1 has a signed type, is undefined if E1 * 2^E2 is not representable in the result type.
21:45:30 <fizzie> It's also kind of nasty, the way the types of integer literals changed from C89 to C99.
21:46:19 <fizzie> I mean, I'm sure they had to, thanks to the introduction of long long. But there used to be a "fallback" option for also unsuffixed decimal constants to end up as "unsigned long" if they were too long for a long.
21:48:02 <fizzie> http://sprunge.us/SCIF and so on.
21:48:28 <Jafet> This is why I always cast numeric values before doing anything weird with them
21:48:29 <fizzie> Also the silliest messages, __int128 is not unsigned.
21:53:55 <fizzie> Fun fact: C89 (or at least the "ansi.c.txt" draft that keeps circulating around) does not seem to really define E1 << E2 at all if E1 is signed.
21:54:25 <fizzie> "The result of E1 << E2 is E1 left-shifted E2 bit positions; vacated bits are filled with zeros. If E1 has an unsigned type, the value of the result is E1 multiplied by the quantity, 2 raised to the power E2, reduced modulo ULONG_MAX+1 if E1 has type unsigned long, UINT_MAX+1 otherwise. (The constants ULONG_MAX and UINT_MAX are defined in the header <limits.h> .)"
21:54:34 <fizzie> That's all it says on the topic of left shifts.
21:55:52 <fizzie> (C99 adds the "if signed type and nonnegative value and E1*2^E2 is representable" sentence.)
21:56:43 <fizzie> http://www.open-std.org/jtc1/sc22/wg14/www/docs/dr_081.html apparently it was entirely implementation-defined for C89.
21:56:44 -!- oerjan has joined.
22:02:30 <fizzie> "There is an ongoing discussion about what privacy means and if it is still needed. Some tracks differ from the versions on the albums listed. It was a tremendous success and marked the beginning of Italian operatic dominance north of the Alps."
22:02:49 <fizzie> Nice spam-filter avoidance header, I even thought it was something sane at first.
22:04:11 -!- idris-ircslave has quit (Ping timeout: 252 seconds).
22:05:31 -!- Melvar has quit (Ping timeout: 276 seconds).
22:06:22 <Jafet> fungot, do you write spam subject lines
22:06:23 <fungot> Jafet: the honourable member will be aware that all eurocontrol does is coordinate flights a priori. we are also acknowledging that this parliament sends the message that i would not be accepted by the council last week, when we discuss matters such as pay and conditions in a coastal area into account when drawing up the olive sector, the communal services, the commission generally agrees with.
22:07:37 <oerjan> i can believe that would avoid some filters.
22:07:49 <Jafet> The concerning thing, mr president, is that we are at more-or-less the point where fungot can speak more coherently than some healthy adults
22:07:49 <fungot> Jafet: mr president, i agree with you in mind. amendments nos 84 and 85 on reviewing the priority list do not allow the commission to take due account of the particular problem arising from the strategies will be adopted today in the role of the court of justice in the fnord session of the parliament, to support the airlines in their country.
22:08:28 <oerjan> Jafet: this can be fixed by redefining healthy again hth
22:08:35 -!- Bicyclidine has joined.
22:08:48 <Jafet> If you hit them in the head, they are no longer healthy
22:09:38 <oerjan> i imagine the fnord session of the parliament is where they discuss the secret illuminati stuff.
22:10:39 <Bicyclidine> ActiveX components enable you to display ActiveX controls in your GUI. They are available only on the Microsoft® Windows® platform.
22:11:29 <fizzie> Are you doing MATLAB®™ there?
22:12:02 <Bicyclidine> wondering if i should bother figuring out how to grey out a textbox
22:12:13 <oerjan> hm there are symbols for trademarks and copyrights, is there one for patents
22:13:24 <HackEgo> #!/usr/bin/env python \ # -*- encoding: utf-8 -*- \ import re \ import sys \ import unicodedata \ def l(c): m = re.match('(?:U+)?([0-9a-f]{1,5})$', c, re.I); return unicodedata.lookup(c) if m is None else unichr(int(m.group(1),16)) \ try: \ print u''.join(map(l, sys.argv[1:])).encode('utf-8') \ except KeyError: \ print u'Unknown characte
22:13:54 <fizzie> Shows how well I test these things.
22:14:10 <Jafet> Not just the standard unicode executable?
22:14:24 <oerjan> `run sed -i 's/U[+]/U[+]/' bin/unicode
22:15:08 <Jafet> python isn't very esoteric (below 100 lines, at least)
22:15:29 <Jafet> Incidentally, that character describes these programs also
22:15:40 <Jafet> `cat bin/unidecode
22:15:41 <HackEgo> #!/usr/bin/env python \ import sys \ import unicodedata \ print u" ".join("[U+{0:04X} {1}]".format(ord(c), unicodedata.name(c, "DUNNO")) for c in " ".join(sys.argv[1:]).decode("utf-8")).encode("utf-8")
22:15:58 <fizzie> It's all up to the version of Python unicodedata that's installed there.
22:16:29 <fizzie> At least we've got it out of UCS-2 nowadays; it was stuck in that for ages.
22:16:58 <Jafet> `run python -c $'import unicodedata\nprint unicodedata.unidata_version'
22:18:07 -!- Melvar has joined.
22:18:10 <Bicyclidine> "To add an image to a push button or toggle button, assign the button's CData property an m-by-n-by-3 array of RGB values that defines RGB (Truecolor) Images."
22:18:22 <fizzie> oerjan: In case you don't feel like looking it up, it was just PILE OF POO.
22:19:16 <oerjan> well that was obvious once i could see it properly; putty only displayed the left part
22:20:20 <fizzie> Also, stalker mode has stopped eworking for me.
22:20:47 <Bicyclidine> "You can extend the file types that the open command recognizes to include any file having a three-character extension. Do this by creating a MATLAB code file with the name openxyz.m. xyz is the file extension for the type of files to be handled. Do not, however, take this approach for opening FIG-files, because openfig.m is a MATLAB function which is needed to open GUIs."
22:20:51 <fizzie> I thought it was just something with the Android tablet's browser, but it doesn't seem better on this desktop either.
22:21:10 <fizzie> It keeps on scrolling and blinking.
22:24:57 -!- adu has joined.
22:27:21 * oerjan doesn't use stalker mode anyway.
22:28:43 -!- tromp has joined.
22:30:10 <oerjan> <Sgeo> blah >>= flip when $ do ... <-- the precedences are wrong for that to work.
22:30:31 <oerjan> @tell Sgeo <Sgeo> blah >>= flip when $ do ... <-- the precedences are wrong for that to work.
22:31:17 <shachaf> :t return True >>= do flip when $ Just ()
22:32:05 -!- Sprocklem has joined.
22:32:54 <oerjan> :t do flip when $ Just ()
22:33:04 <lambdabot> Couldn't match expected type ‘GHC.Types.Int’
22:33:04 <lambdabot> with actual type ‘Data.Maybe.Maybe s0’
22:33:32 <oerjan> hm i'm not sure if the last one is portable
22:34:00 <oerjan> is do with just one expression guaranteed to work if the expression doesn't have monadic type
22:34:22 <oerjan> elliott: in the report?
22:34:48 <elliott> the desugaring doesn't talk about types I think
22:34:53 <elliott> only that it uses Prelude return/(>>=)
22:34:58 <oerjan> i guess if so then you actually _can_ use do as a general-purpose precedence fixer, huh
22:36:35 <Jafet> `file /usr/share/unicode/unicodeData.txt
22:36:35 <HackEgo> /usr/share/unicode/unicodeData.txt: ERROR: cannot open `/usr/share/unicode/unicodeData.txt' (No such file or directory)
22:36:38 <Jafet> `file /usr/share/unicode/UnicodeData.txt
22:36:39 <HackEgo> /usr/share/unicode/UnicodeData.txt: ERROR: cannot open `/usr/share/unicode/UnicodeData.txt' (No such file or directory)
22:36:47 <HackEgo> No LSB modules are available. \ Distributor ID:Debian \ Description:Debian GNU/Linux \ Release:n/a \ Codename:n/a
22:38:11 <oerjan> @run do let x = 5; x+2
22:38:13 <lambdabot> parse error (possibly incorrect indentation or mismatched brackets)
22:38:23 <oerjan> @run do let {x = 5}; x+2
22:39:25 -!- Patashu has joined.
22:39:39 <oerjan> sadly the brackets are needed there
22:39:56 <Jafet> n/a is a rock that andy picked up on the way home. He hasn't named it yet.
22:49:29 -!- tromp has quit (Remote host closed the connection).
22:50:49 <Jafet> https://packages.debian.org/sid/unicode-screensaver
22:51:03 <Jafet> I wonder if it does the emoji block
22:53:59 <Jafet> `fetch http://sources.debian.net/data/main/u/unicode/0.9.7/unicode
22:54:03 <HackEgo> 2014-04-17 22:53:59 URL:http://sources.debian.net/data/main/u/unicode/0.9.7/unicode [26623/26623] -> "unicode" [1]
22:56:39 <Jafet> `fetch http://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt
22:56:41 <HackEgo> 2014-04-17 22:56:37 URL:http://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt [1367023/1367023] -> "UnicodeData.txt" [1]
22:56:49 <Jafet> Wonder how long this will ta.. nevermind.
22:57:32 <Jafet> `run mv bin/unicode{,.old} && mv unicode UnicodeData.txt bin && chmod +x bin/unicode
22:57:47 <HackEgo> U+1F4A9 - No such unicode character name in database \ UTF-8: f0 9f 92 a9 UTF-16BE: d83ddca9 Decimal: 💩 \ 💩 (💩) \ Uppercase: U+1F4A9 \ Category: Cn (Other, Not Assigned)
23:00:29 <Jafet> `run sed -i 's,\./UnicodeData\.txt,/hackenv/UnicodeData.txt,' && unicode U+1F4A9
23:00:38 <Jafet> `run sed -i 's,\./UnicodeData\.txt,/hackenv/UnicodeData.txt,' bin/unicode && unicode U+1F4A9
23:00:40 <HackEgo> U+1F4A9 - No such unicode character name in database \ UTF-8: f0 9f 92 a9 UTF-16BE: d83ddca9 Decimal: 💩 \ 💩 (💩) \ Uppercase: U+1F4A9 \ Category: Cn (Other, Not Assigned)
23:01:23 <HackEgo> U+1F4A9 PILE OF POO \ UTF-8: f0 9f 92 a9 UTF-16BE: d83ddca9 Decimal: 💩 \ 💩 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
23:01:31 <Jafet> Maybe that needs to be trimmed.
23:02:30 <HackEgo> U+1F4A9 PILE OF POO \ UTF-8: f0 9f 92 a9 UTF-16BE: d83ddca9 Decimal: 💩 \ 💩 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
23:03:04 <oerjan> oh well i guess it contains all the information needed
23:03:54 <HackEgo> bin/unicode: Python script, ASCII text executable
23:16:24 -!- Patashu[Zzz] has joined.
23:16:24 -!- Patashu has quit (Disconnected by services).
23:16:33 -!- tromp has joined.
23:18:43 -!- adu has quit (Quit: adu).
23:21:47 <HackEgo> [wiki] [[Talk:Hollang]] N http://esolangs.org/w/index.php?oldid=39349 * Zerk * (+225) Created page with "Could you clarify "holographically embed them into variables"? How does averaging two bitstrings work, some operation between an ''and'' and an ''or''?--~~~~"
23:22:39 -!- yorick has quit (Remote host closed the connection).
23:35:31 <kmc> "EXIT() is really exit(), a gentle surprise but… OPENSSL_EXIT() is really just return()"
23:39:37 -!- ^v has joined.
23:40:08 -!- adu has joined.
23:49:52 -!- adu has quit (Quit: adu).
23:52:55 -!- adu has joined.
00:00:02 -!- MoALTz has quit (Read error: No route to host).
00:00:47 -!- MoALTz has joined.
00:03:18 -!- MoALTz_ has joined.
00:05:42 <Jafet> kmc: it exits openssl for libc
00:05:57 <kmc> exit through the gift shop
00:06:33 -!- MoALTz has quit (Ping timeout: 245 seconds).
00:07:43 -!- MoALTz_ has quit (Max SendQ exceeded).
00:09:37 -!- tromp has quit (Remote host closed the connection).
00:11:44 -!- MoALTz has joined.
00:14:49 -!- MoALTz_ has joined.
00:15:36 <Bicyclidine> Someday I will understand why every C library abstracts standard everything through four layers of macrology, or rather I won't, because I ain't trying
00:16:04 -!- MoALTz has quit (Ping timeout: 240 seconds).
00:21:57 <lexande> is it in the name of portability to systems nobody has used since before most members of this channel were born?
00:22:52 <elliott> to be fair, many members in this channel have probably used obscure systems older than them.
00:26:07 <Jafet> Obscure systems, like autoconf
00:28:14 -!- MoALTz__ has joined.
00:28:51 <lexande> (well, i'm older than IRC but presumably many here aren't)
00:30:52 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
00:31:02 <int-e> It's not even 26 years old.
00:31:39 -!- Sgeo has joined.
00:33:54 -!- MoALTz has joined.
00:35:16 -!- MoALTz__ has quit (Ping timeout: 240 seconds).
00:35:29 -!- MoALTz__ has joined.
00:35:47 <copumpkin> kmc: https://www.youtube.com/watch?v=byp_x2be8C8
00:37:32 <copumpkin> I wonder who the target demographic of that ad is :P
00:38:13 -!- MoALTz has quit (Ping timeout: 250 seconds).
00:39:22 -!- MoALTz_ has joined.
00:40:08 -!- Sgeo_ has joined.
00:41:30 -!- MoALTz__ has quit (Ping timeout: 240 seconds).
00:42:39 <Sgeo_> Would OverlappingInstances be ok if we had typeclasses that were closed?
00:43:38 -!- MoALTz has joined.
00:43:45 -!- Bicyclidine has quit (Quit: Page closed).
00:43:54 -!- Sgeo has quit (Ping timeout: 240 seconds).
00:45:24 -!- MoALTz__ has joined.
00:46:18 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
00:47:03 -!- MoALTz_ has joined.
00:48:51 -!- MoALTz has quit (Ping timeout: 265 seconds).
00:49:55 -!- MoALTz__ has quit (Ping timeout: 250 seconds).
00:56:48 -!- adu has quit (Quit: adu).
00:57:15 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
01:14:24 -!- MoALTz has joined.
01:15:40 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
01:30:55 -!- MoALTz has quit (Ping timeout: 276 seconds).
01:32:11 -!- tromp has joined.
01:56:32 -!- shikhout has joined.
01:59:20 -!- shikhin has quit (Ping timeout: 252 seconds).
01:59:20 -!- shikhout has changed nick to shikhin.
02:11:17 <HackEgo> [wiki] [[Talk:Hollang]] http://esolangs.org/w/index.php?diff=39350&oldid=39349 * Doesthiswork * (+474)
02:21:04 <HackEgo> [wiki] [[Hollang]] M http://esolangs.org/w/index.php?diff=39351&oldid=39348 * Doesthiswork * (+5)
02:23:36 -!- doesthiswork has joined.
02:31:25 <oerjan> one bot left, but the channel also shrank a bit otherwise
02:31:44 <oerjan> and we can count myndzi in a pinch
02:33:09 -!- idris-ircslave has joined.
02:34:35 <nooodl> what percentage of the bots can answer this question?
02:34:55 <oerjan> and of course there might be bots we don't know about
02:35:18 <oerjan> fungot: answer nooodl's question please
02:35:18 <fungot> oerjan: mr president, in the last instance by the directorate-general for personnel, you share the commission's satisfaction with the support of this house.
02:39:21 -!- Patashu[Zzz] has changed nick to Patashu_.
02:39:24 -!- Patashu_ has changed nick to Patashu.
02:39:42 <fungot> lexande: mr president, on such a basis. i think no one would take it seriously and do not fall within the scope of objective 1, we cannot tell you anything more at present.
02:40:45 <fungot> Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, idris-ircslave ( , jconn ) , blsqbot !
02:45:55 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
02:46:36 <oerjan> thutubot isn't usually here.
02:46:46 <oerjan> metasepia is only when boily is.
02:47:23 <oerjan> `runpython print 10/87
02:47:25 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: runpython: not found
02:47:33 <oerjan> hm i thought there was a command like that
02:47:47 <oerjan> `run python -c 'print 10/87'
02:47:54 <oerjan> `run python -c 'print 10.0/87'
02:49:11 <oerjan> getting fungot to calculate that is going to take some work.
02:49:12 <fungot> oerjan: mr president, the purpose of our action could not be settled through the consultation procedure in this case of seven years, and that is after cooperation between the usa and to which our response can no longer be ruled out that any such transports do not allow us to be able to take into account what opinions are prevalent in the committee on women’s rights and the proper criteria for selecting the companies to be ins
02:50:03 <oerjan> ^ul (0.114942528736)S(although we can cheat a bit more)
02:50:04 <kmc> mr president, i don't like you, ♫ YOU DON'T KNOW HOW TO ROCK ♫
02:57:45 -!- Sprocklem has quit (Ping timeout: 250 seconds).
02:58:39 -!- Sprocklem has joined.
02:58:40 -!- Sprocklem has quit (Changing host).
02:58:40 -!- Sprocklem has joined.
02:59:31 -!- nisstyre has joined.
03:01:34 -!- nisstyre has quit (Client Quit).
03:22:50 <kmc> fungot: do you know how to rock
03:22:51 <fungot> kmc: madam president, i have taken on serious proportions. to dismiss these arguments with the other institutions to the concept of fixed controls with that of the impact of liberalising the energy markets on the consumer to pay for energy and transport policies is to be in favour of the previous explanation of vote in this budget process. three issues stand out, namely that there is a whole package of measures represents a goo
03:23:12 <kmc> `addquote <fungot> kmc: madam president, i have taken on serious proportions.
03:23:12 <fungot> kmc: madam president, the marinho report, which gives priority to research and partly to the many members who are deeply concerned about the absence of any further scientific progress.
03:23:14 <HackEgo> 1185) <fungot> kmc: madam president, i have taken on serious proportions.
03:23:42 <kmc> fungot: i'll show you my package of measures
03:23:43 <fungot> kmc: madam president, it gives us the greatest concern to us all imperative that we do not get left behind in relation to compliance with the fundamental principle of maintaining a capitalist system in which there is much talk of the collapse in the near future
03:24:03 <Bike> that seems like a pretty shoddy fundament, not gonna lie
03:24:11 <kmc> that last one is gold
03:24:21 <kmc> purestrain gold
03:27:41 <Sgeo_> http://opensslrampage.org/post/83007010531/well-even-if-time-isnt-random-your-rsa-private-key
03:28:33 <Bike> "There are no plans to ever build this with the Metrojerks compiler."
03:29:27 <Bike> During the 1990s, Apple Computer released a monthly series of developer CD-ROMs containing resources for programming the Macintosh. These CDs were, in the early days, whimsically titled using punning references to various movies but with a coding twist; for example, "The Hexorcist" (The Exorcist), "Lord of the Files" (Lord of the Flies), "Gorillas in the Disc" (Gorillas in the Mist), etc.
03:29:49 -!- MoALTz has joined.
03:30:05 <Bike> holy shit the stratus thing
03:30:34 <newsham> just in case your i386 converts
03:30:49 <Bike> «Most will argue that x86_64 is always little-endian. Well, yes, but then we have stratus.com who has modified gcc to "emulate" big-endian on x86. Is there evidence that they [or somebody else] won't do same for x86_64? Naturally no.»
03:31:17 <Bike> "so anyway that's why we're supporting architectures that don't exist"
03:31:42 <newsham> brought to you buy the people who brought you heartbeats for tcp
03:33:39 -!- Sprocklem has quit (Quit: leaving).
03:34:18 -!- doesthiswork has quit (Ping timeout: 240 seconds).
03:35:23 <Bike> "As snprintf is not available everywhere, we provide our own implementation."
03:36:32 <Bike> http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libssl/src/crypto/bio/b_print.c?rev=1.18;content-type=text%2Fplain this is... actually a printf implementation, isn't it
03:39:39 <newsham> it prints into a BIO, so its not really "printf" per se
03:39:52 -!- doesthiswork has joined.
03:40:16 <newsham> oh there's a BIO_snprintf too
03:40:55 <Bike> strncpy(d, s, strlen(s)), also good
03:42:59 <newsham> i've seen that more times than you'd think :(
03:45:01 -!- adu has joined.
03:52:09 -!- nooodl has quit (Ping timeout: 252 seconds).
03:52:58 <Sgeo_> http://www.reddit.com/r/programming/comments/23a8bf/openssl_valhalla_rampage_documenting_the_humorous/cgvbfch?context=1
03:53:14 <Bike> https://www.youtube.com/watch?v=CJQU22Ttpwc SSL theme song
03:58:53 <newsham> "A technical argument by a trusted author, which
03:58:53 <newsham> is hard to check and looks similar to arguments known to be correct, is hardly ever
04:00:52 <HackEgo> [wiki] [[Talk:Hollang]] http://esolangs.org/w/index.php?diff=39352&oldid=39350 * Zerk * (+170)
04:02:58 <HackEgo> [wiki] [[Talk:Hollang]] M http://esolangs.org/w/index.php?diff=39353&oldid=39352 * Zerk * (+1)
04:07:10 <HackEgo> [wiki] [[Talk:Hollang]] http://esolangs.org/w/index.php?diff=39354&oldid=39353 * Doesthiswork * (+191)
04:07:32 <HackEgo> [wiki] [[Talk:Hollang]] M http://esolangs.org/w/index.php?diff=39355&oldid=39354 * Doesthiswork * (+6)
04:09:52 <newsham> on coq and mathematics and getting mistakes out of proofs: http://www.math.ias.edu/~vladimir/Site3/Univalent_Foundations_files/2014_IAS.pdf
04:10:26 <doesthiswork> was that posted here recently? I remeber reading that a couple days ago
04:12:09 <Bike> is this the coq's C being undefined business
04:12:55 -!- tromp has quit (Remote host closed the connection).
04:13:11 -!- tromp has joined.
04:16:26 -!- Sorella has quit (Quit: It is tiem!).
04:16:27 <Bike> must be pretty great thinking you can prove things
04:16:54 <newsham> would prob not be worth being a mathematician if you thought you couldnt
04:17:49 <Bike> and thankfully I am not.
04:18:48 <Jafet> How can coq's (compcert's?) C be undefined
04:19:48 <Bike> Jafet: beats me http://blog.regehr.org/archives/903
04:20:42 <Bike> the bottom has coqchk's rather than coqtop's.
04:21:25 <Jafet> Ah, the runtime issue
04:21:34 <Jafet> regehr is being a sensationalist as usual
04:21:56 <Bike> "Therefore someone who wanted to get to the bottom of things in mathematics had a simpleroad to follow - learn what Predicate Logic is, then learn a particular theory called ZFC, thenlearn how to translate propositions about a few basic mathematical concepts into formulas ofZFC, and then learn to believe, through examples, that the rest of mathematics can be reducedto these few basic concepts. " lol
04:22:02 <elliott> not very sensationalist, have you seen what clang does with UB
04:22:17 <newsham> still, you'd prob want to hold coq to a high standard
04:22:24 <Jafet> I mean, you might as well bitch that the hardware has bugs (it does)
04:22:27 <newsham> i wonder if any of those issues are in the important core of coq
04:22:30 <Bike> "Now we come to the important question: Is Coq's validity threatened? The short answer is that this seems unlikely." yeah i can see how you'd read this and think it's sensationalist
04:22:34 <newsham> or if they're all in stuff thats "untrusted" anyway
04:22:34 <elliott> but these are not compiler bugs
04:22:43 <elliott> at least, the compiler writers wouldn't agree they are, and nor would the C committee
04:22:49 <Jafet> Bike: "coq's C is undefined"
04:22:50 <elliott> and they actually break things in practice, so...?
04:23:09 <elliott> that string appears nowhere on the linked page
04:23:13 <newsham> not all of coq needs to be correct to be trustworthy
04:23:22 <elliott> unless you believe Bike is regehr
04:23:31 <Jafet> This is C code in ocaml or its runtime, so who knows, probably most C code in ocaml is used at some point or other
04:23:36 <Bike> too busy poking flies to be regehr, thankfully
04:23:56 <Jafet> Ok, regehr does say: "This output means that Coq---via OCaml---is executing a number of C's undefined behaviors before it even asks for any input from the user. The problem with undefined behaviors is that, according to the standard, they destroy the meaning of the program that executes them."
04:24:16 <newsham> are there any more trustworthy versions of ocaml?
04:24:18 <Jafet> regehr's other posts are equally colourful
04:24:32 <Bike> you have really sad standards for color
04:24:34 <Jafet> I think there are projects to do verified runtimes of ocaml and/or sml
04:25:06 <newsham> so you just have to rerun your coq proof on a trusted ocaml once to verify that the c langauge didnt ruin your picnic
04:25:11 <Jafet> There was a paper on verified bignum libraries for x86
04:25:19 <elliott> tbh his blog is incredibly dry and even-handed by any standards I can think of, have you ever seen most programming blogs
04:25:32 <Jafet> When you are verifying to this standard, by the way, the C standard is irrelevant
04:25:43 <newsham> fwiw, the cpu your computer is running on is also flawed
04:25:45 <Jafet> You check the compiler of ocaml itself, and the generated machine code
04:25:50 <newsham> luckily it mostly does the right thing
04:25:52 <Bike> i think regehr probably thinks so too!
04:25:55 <Jafet> Compilers don't implement the C standard, either
04:26:22 <newsham> jafet: i heard some C compilers were even written before the language standard existed!
04:26:38 <Bike> there's not an implication of "coq is totally wrong" from "haha, unsigned shifts" unless you have really bizarre ideas about math
04:27:09 <newsham> bike: there seems to be an underlying "you cnat prove things" theme though in your discussion
04:27:09 <Jafet> I heard some C compilers wrote the standard
04:27:28 <Bike> newsham: in mine yeah. i don't think it's what regehr means though.
04:28:07 <Jafet> Also, I'm only reading past the first few paragraphs of regehr's post now
04:28:23 <newsham> also in a practical sense, you can use lots of compiler flags on a modern compiler to make those undefined operations do what the human thought they did
04:28:46 <newsham> for the most part (not always.. some of it is inherent in the translation to hardware ops.. like shifting more than 32 bits on a 32 bit cpu...)
04:28:58 <newsham> and there are people who have been studying the effects of undefined C ops
04:29:04 <elliott> troll first, actually read things later
04:30:19 <newsham> great fun http://people.csail.mit.edu/nickolai/papers/wang-undef.pdf
04:31:51 <Bike> "The third component
04:31:51 <Bike> is a structure that enables humans to encode
04:31:51 <Bike> mathematical ideas in terms of the objects directly associated with the
04:31:53 <newsham> http://people.csail.mit.edu/nickolai/papers/wang-stack.pdf has a nice table showing diff compilers and optimization levels
04:31:54 <Bike> language. " er sorry
04:32:03 <Bike> anyway that's an interesting way of seeing how people think
04:32:51 <newsham> maybe someone can run this STACK tool on ocaml and fix the compiler
04:33:04 <Bike> is this related to fuck shit stacks
04:33:13 <Jafet> It's stacks all the way down
04:33:28 <Bike> put some fuckshit, stack it on top of itself. that's ocaml
04:35:57 <shachaf> I kind of wish I was still writing fancy SSE code so I could finally port it to AVX on my Haswell CPU.
04:36:56 -!- oerjan has quit (Quit: leaving).
04:36:57 <kmc> http://newbrict.github.io/Fe26/
04:39:02 <Bike> triple alpha continues to be suffering
04:40:01 <newsham> http://freshbsd.org/commit/openbsd/448ea0eae861248df6710920c23f167647f487ca
04:41:36 <Bike> digital crime and forensic science in cyberspace
04:42:40 <HackEgo> Thanks, magnesium. Thagnesium.
04:42:56 -!- tromp has quit (Remote host closed the connection).
04:43:01 <Bike> i completely agree ;_;
04:44:04 <Bike> http://onlinelibrary.wiley.com/doi/10.1634/stemcells.2008-0184/abstract meanwhile in science
04:50:45 <Jafet> "Retraction notice ‘that is, the text supplied by Legal’."
04:52:09 <Bike> it's nice to see the scientific method in all its wonderful detail, isn't it
04:53:45 <newsham> this one is interesting http://freshbsd.org/commit/openbsd/0179d4e553d5f01de48877acefd1ebc795e2ce0a
04:54:00 <newsham> "goto err; i = -1; .... err: return i;"
04:56:41 -!- MoALTz has quit (Ping timeout: 252 seconds).
05:09:11 <shachaf> http://www.aliendovecote.com/uploads/twine/sauna.html
05:11:29 <copumpkin> https://www.dropbox.com/s/5bptf82xl4h0y52/Screenshot%202014-04-18%2001.11.25.png
05:12:04 -!- MoALTz has joined.
05:16:08 <newsham> "NOTE: Don't expect any of these programs to work with current OpenSSL releases, or even with later SSLeay releases.
05:16:13 <newsham> but still in the src tree...
05:16:19 <newsham> its like an append-only log
05:17:34 <Sgeo_> What are 'these programs'?
05:18:04 <newsham> these: http://freshbsd.org/commit/openbsd/eadb750b87b4a90c1284f6361d6c3ea6d6e26f66
05:21:05 <fizzie> `run unicode 1234 12345 4321
05:21:07 <HackEgo> U+1234 ETHIOPIC SYLLABLE SEE \ UTF-8: e1 88 b4 UTF-16BE: 1234 Decimal: ሴ \ ሴ \ Category: Lo (Letter, Other) \ Bidi: L (Left-to-Right) \ \ U+12345 CUNEIFORM SIGN URU TIMES KI \ UTF-8: f0 92 8d 85 UTF-16BE: d808df45 Decimal: 𒍅 \ 𒍅 \ Category: Lo (Letter, Other) \ Bidi: L (Left-to-Right) \ \ U+4321 CJK UNIFIED IDEOGRAPH-4321 \
05:21:20 <fizzie> It's a bit long if you want to do several.
05:21:45 <fizzie> But I guess the extra info is nice too.
05:22:43 <HackEgo> U+0066 LATIN SMALL LETTER F \ UTF-8: 66 UTF-16BE: 0066 Decimal: f \ f (F) \ Uppercase: U+0046 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right) \ \ U+006F LATIN SMALL LETTER O \ UTF-8: 6f UTF-16BE: 006f Decimal: o \ o (O) \ Uppercase: U+004F \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right) \ \ U+006F LATIN SMA
05:22:52 <fizzie> That just won't do at all for a `unidecode replacement, however.
05:40:47 -!- Tod-Autojoined has joined.
05:44:03 -!- TodPunk has quit (Ping timeout: 240 seconds).
05:44:52 -!- Tod-Autojoined has changed nick to TodPunk.
05:56:53 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:57:40 -!- ^v has joined.
05:58:00 -!- ^v has quit (Read error: Connection reset by peer).
06:02:12 <Bike> "The new language is thus named after the first systems designer to go over budget and behind schedule." cute.
06:04:09 -!- conehead has quit (Quit: Computer has gone to sleep).
06:04:39 <kmc> 'A hotly contested issue among language designers is the method for passing parameters to subfunctions. Some advocate "call by name," others prefer "call by value." Babbage uses a new method -- "call by telephone."' erlang
06:06:14 -!- Sellyme has quit (Excess Flood).
06:06:26 -!- Sellyme has joined.
06:17:20 <Bike> over the phone radar
06:23:15 <lambdabot> (Profunctor p, Functor f) => AnIso s t a b -> p t (f s) -> p b (f a)
06:23:33 <shachaf> You're right, it would be much better with pure profunctor lenses. :-(
06:24:55 -!- MoALTz has quit (Quit: bbl).
06:25:00 <Sgeo_> I mean, I'm interested in GHC.Generics
06:32:07 -!- impomatic has quit (Quit: impomatic).
06:44:42 <Sgeo_> http://hackage.haskell.org/package/CC-delcont-0.2/docs/Control-Monad-CC-Dynvar.html
06:44:54 <Sgeo_> So, it's storing values of arbitrary types ?
06:45:15 <Sgeo_> I guess this implies ST could be made in pure Haskell? Or am I missing something?
06:45:40 <Sgeo_> (Besides the possible negative performance implications of doing so)
06:46:01 -!- nikozzzzzz has joined.
06:46:26 -!- nikozzzzzz has quit (Client Quit).
06:51:21 <Sgeo_> "In the case for :+:, we produce False or True depending on whether the constructor of the value provided is located on the left or on the right:"
06:51:45 <Bike> i'm with niko on this one
06:51:48 <Sgeo_> So, for A | B | C, the exact serialization depends on the nesting of :+: ?
06:52:12 <Sgeo_> If the GHC compiler changes how that nesting works, could that break reserialization?
06:52:24 <Sgeo_> (Reading the example in http://hackage.haskell.org/package/generic-deriving-1.6.3/docs/Generics-Deriving-Base.html )
06:55:00 <Bike> i'm continually amazed by how complicated everybody makes haskell sound
06:59:17 <kmc> thought of another name that has a name
06:59:17 <kmc> there was an MIT Mystery Hunt team whose name was the entirety of Atlas Shrugged
06:59:45 <Bike> the worst buffer overflow in human history
07:10:14 <Sgeo_> "Generic Generic Programming
07:11:04 <Bike> where's my phylogenetic programming
07:30:46 -!- MindlessDrone has joined.
07:32:28 -!- slereah has joined.
07:36:40 <kmc> hi slereah
07:39:05 -!- hubert has joined.
07:43:55 -!- tromp has joined.
07:45:51 -!- doesthiswork has quit (Quit: Page closed).
07:48:18 -!- tromp has quit (Ping timeout: 240 seconds).
07:56:43 -!- hubert has quit (Read error: Connection reset by peer).
07:56:52 -!- shikhout has joined.
07:59:45 -!- shikhin has quit (Ping timeout: 252 seconds).
07:59:46 -!- shikhout has changed nick to shikhin.
08:10:04 <Bike> https://www.youtube.com/watch?v=FEHdDjVrGEM everyone's favorite movie
08:16:50 -!- hubert has joined.
08:51:31 -!- adu has quit (Quit: adu).
08:55:43 <HackEgo> [wiki] [[Special:Log/newusers]] create * Llrsexme * New user account
08:58:24 <HackEgo> [wiki] [[User talk:Llrsexme]] N http://esolangs.org/w/index.php?oldid=39356 * Llrsexme * (+2418) Created page with "Depending on scientific studies, introduction regarding virgin mobile acrylic inside eating habits is available being invaluable to take care of gallstone problems. To make ce..."
09:09:06 -!- hubert has quit (Ping timeout: 240 seconds).
09:13:14 -!- slereah has quit (Quit: Leaving).
09:13:41 -!- hubert has joined.
09:23:12 -!- AnotherTest has joined.
09:23:16 <olsner> hmm, apparently openssl had support (of some kind?) for big-endian x86 and x86-64
09:34:32 -!- Bike has quit (Quit: leaving).
09:35:56 -!- Frooxius has quit (Quit: *bubbles away*).
09:36:12 -!- Frooxius has joined.
09:49:50 -!- Vorpal has joined.
09:49:50 -!- Vorpal has quit (Changing host).
09:49:50 -!- Vorpal has joined.
09:50:28 -!- hubert has quit (Quit: leaving).
10:27:13 <olsner> this thing: http://en.wikipedia.org/wiki/Stratus_VOS has a compiler that makes your x86 code big endian
10:31:22 -!- xpte has quit (Quit: Connection closed for inactivity).
10:37:44 -!- JesseH2 has joined.
10:37:45 -!- yorick has joined.
10:40:53 -!- JesseH has quit (Ping timeout: 258 seconds).
10:41:54 -!- slereah has joined.
10:59:28 -!- Phantom_Hoover has joined.
11:16:22 -!- nooodl has joined.
11:19:36 <b_jonas> olsner: sure, and you can implement something very close to big-endian integer types in C++ too
11:21:19 <b_jonas> but that doesn't make the CPU itself big-endian
11:22:20 <Vorpal> olsner, why? And what b_jonas said
11:25:59 <Vorpal> olsner, huh, after reading the article, who uses that sort of stuff?
11:56:54 <FreeFull> I think x86 modified to be big endian exists out there, but the average x86 processor won't support that
12:00:28 <b_jonas> FreeFull: it exists as an emulator, sort of
12:00:36 <b_jonas> but I don't think it exists as a physical cpu
12:26:37 -!- Sgeo_ has quit (Read error: Connection reset by peer).
13:45:07 -!- conehead has joined.
13:50:58 -!- nucular has joined.
13:50:58 -!- nucular has quit (Changing host).
13:50:59 -!- nucular has joined.
13:52:57 <b_jonas> wtf are people asking for syntax highlighting for languages like brainfuck where it totally doesn't make sense?
13:54:43 <b_jonas> I mean, maybe I can understand that in C you want to color macros, type names, objects, functions, undefined identifiers.
13:55:16 <b_jonas> but in a language that doesn't have that kind of thing, or it can't be determined without running the program, what would syntax highlighting even do?
13:55:33 -!- shikhin has quit (Read error: Connection reset by peer).
13:56:59 -!- shikhin has joined.
14:07:48 <mroman> b_jonas: hey: I like them brackets blue!
14:09:37 <mroman> I'd also'd love a brainfuck eclipse plugin.
14:10:03 <mroman> So I can use it more professionlly.
14:10:40 <mroman> although brainfuck completely lacks any library support
14:10:46 <mroman> that's a bit of a turn down.
14:14:37 <slereah> Is there a BF version with libraries?
14:18:29 -!- yorick has quit (Remote host closed the connection).
14:18:47 <b_jonas> slereah: with so many variants out there, there's probably one
14:21:31 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[User talk:Llrsexme]]": Spam: content was: "Depending on scientific studies, introduction regarding virgin mobile acrylic inside eating habits is available being invaluable to take care of gallstone probl..." (and the only contributor was "[[Special:Contributions/Llrsexme|Llrsexme]]")
14:21:50 <HackEgo> [wiki] [[Special:Log/block]] block * Oerjan * blocked [[User:Llrsexme]] with an expiry time of indefinite (account creation disabled): Spamming links to external sites
14:31:34 -!- Patashu has quit (Ping timeout: 276 seconds).
14:44:19 -!- Bike has joined.
14:58:51 -!- Guest74775 has joined.
15:02:22 <int-e> Guest74775: could you elaborate on that point?
15:10:24 -!- Guest74775 has quit (Remote host closed the connection).
15:16:15 -!- conehead has quit (Quit: Computer has gone to sleep).
15:27:44 -!- conehead has joined.
15:36:14 <quintopia> oerjan stop editting the wiki and come here and help me :(
15:41:45 -!- slereah has quit (Quit: Leaving).
16:05:46 -!- FreeFull has quit.
16:07:41 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39357&oldid=39346 * Zerk * (+13) /* Signed */
16:28:36 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39358&oldid=39357 * Zerk * (+20) /* Nock Interpeter */ nil handling, br math
16:37:29 -!- xpte has joined.
16:39:01 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39359&oldid=39358 * Zerk * (+49) /* Arithmetic */ power of 2 optimization
16:42:48 -!- Sorella has joined.
16:42:59 -!- MoALTz has joined.
16:46:54 -!- yorick has joined.
17:27:35 <kmc> b_jonas: some syntax highlighters for lisp will color matching parentheses the same
17:27:49 <newsham> heehee http://theconversation.com/no-youre-not-entitled-to-your-opinion-9978
17:36:04 <newsham> though in general i dont believe i should have to defend every opinion to every person.
17:36:07 <newsham> often it is a waste of time
17:37:38 <newsham> (should be defensible, but need not always be defended, though you prob should defend ideas once in a while to make sure you're not fooling yourself)
17:38:59 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
17:44:13 <b_jonas> kmc: I do use the feature where the editor finds me the matching paren, but not with colors
17:45:12 <kmc> i think coloring the parens themselves is not that useful, but some editors will also shade the background behind the text according to the level of nesting
17:49:57 <Bike> http://paste.lisp.org/display/142012 example paren colors... in webscale
17:50:10 <Bike> the color choice is, frankly, terrible. need queer eye for the straight guy to take a look
17:50:45 <kmc> #haskelgbt
17:51:12 <kmc> Bike: I assure you that I have no particular skill at color coördination
17:51:35 <kmc> i like rainbows though :3
17:51:45 <Bike> Queer And Also Design-Trained Why Did We Specify Queer Again Eye for the Straight Guy
17:52:12 <quintopia> for that matter, why specify straight?
17:52:34 <Bike> or just fashion help
17:52:40 <Bike> Eye for the Person
17:52:45 <Bike> that sounds... sinister.
17:52:45 <kmc> eye for an eye
17:53:21 <quintopia> Bike: it's worthwhile to specify "dudes" because it has that connotation of "clueless and careless about fashion"
17:53:33 <Bike> wow way to be misandric???
17:53:52 <quintopia> there's already a similar show that's female-centric
17:54:04 <Bike> wait, wait, is the show still on
17:54:12 <Bike> it's just something i vaguely remember from when i was a kid
17:54:31 <quintopia> that was when i was in college or something
17:54:42 <Bike> 2007, apparently
17:54:46 <Bike> is when it ended.
17:54:54 <Bike> when it started i was... eleven.
17:58:18 <Bike> you know what would be good. a text-only browser like lynx except as modern html compliant as possible
17:58:21 <Bike> with one of them beefy js engines
17:59:33 <quintopia> it should even AUTOMATICALLY ASCII ART THE IMAGES
18:00:05 <elliott> Bike: links2, w3m, elinks are all better than lynx at that
18:00:10 <elliott> I think one of them has bad JS support or something.
18:00:13 <Bike> still not great though
18:06:26 <quintopia> 9what's the difference between a quintopia and a Bike?
18:06:34 -!- conehead has quit (Ping timeout: 265 seconds).
18:07:00 <Bike> Also I'm a bike
18:08:00 -!- Phantom_Hoover has joined.
18:08:38 <Taneb> Bike's a bike but is Phantom_Hoover a hoover?
18:09:51 <kmc> just run a headless webkit and send the output through an ascii art converter
18:14:53 <newsham> hmm.. i've seen people do mpeg in high-res ascii, but not full browser
18:15:02 <newsham> would be interesting seeing youtube in ascii browser
18:15:09 <kmc> would be an amusing hack
18:15:32 <kmc> kinda like http://virtuallyfun.superglobalmegacorp.com/?p=3866
18:16:01 <Bike> shit i was looking for that yesterday, thank you
18:29:24 -!- conehead has joined.
18:29:54 -!- impomatic has joined.
18:31:28 <Bike> static const char rnd_seed[] = "string to make the random number generator think it has entropy";
18:32:13 <myname> youtube videos with ascii were there a short time
18:41:54 -!- conehead has quit (Quit: Computer has gone to sleep).
18:53:52 -!- boily has joined.
19:12:07 <fizzie> These days, if you write to /dev/random it gets mixed in the pool but doesn't affect the entropy estimator.
19:12:28 <fizzie> (Not sure if it has been different.)
19:12:45 -!- Zerker has joined.
19:13:02 <myname> wait, you can WRITE in /dev/random?
19:13:11 -!- conehead has joined.
19:13:41 <fizzie> b_jonas: A brainfuck syntax highlighter that colors all non-brainfuck-command characters in some "comment" color sounds useful to me, since you'll immediately notice if you e.g. accidentally put a comma in your comment.
19:13:50 <newsham> freebsd random(4) page says yes.
19:14:05 <newsham> If the device is using the software generator, writing data to random
19:14:05 <newsham> would perturb the internal state. This perturbation of the internal
19:14:05 <newsham> state is the only userland method of introducing extra entropy into the
19:14:05 <newsham> device. If the writer has superuser privilege, then closing the device
19:14:06 <newsham> after writing will make the software generator reseed itself.
19:15:00 <fizzie> Also there are people who syntax-highlight Scheme so that every paren level gets a different background color, you might do that for the brackets to indicate loops. Though it might be more of a distraction.
19:16:03 <fizzie> For Befunge I haven't really thought of any (automatic) syntax highlighting worth doing. You could indicate valid commands, maybe, but so many things are.
19:16:29 <fizzie> Oh, kmc mentioned that already.
19:17:16 <newsham> need polyglot syntax highlighting
19:17:23 <newsham> with rainbow parens for scheme
19:18:14 <fizzie> I think I started on a manual syntax highlighting/"literate code" kind of thing for fungot, marking and commenting regions, but never got around finishing it.
19:18:14 <fungot> fizzie: i believe that this parliament must take account of the problem.
19:18:32 <fizzie> I did do that for a universal Turing machine Befunge thing, then lost the file. :/
19:18:46 <fizzie> And mooz did a very nice highlighted quicksort but that's only in archive.org now.
19:19:14 <fizzie> http://web.archive.org/web/20060925160554/http://kotisivu.mtv3.fi/quux/qsort.html
19:36:44 <impomatic> I feel like we should make an effort to mirror esolang content to keep it available...
19:37:50 <Deewiant> (For Befunge-98 compatibility, base64-decode MSwzYwogICAgIDAwOTYqMD4yKzAwcDo6ICAgICAgdgo7YjF4ID4wZzEtXHx2IWAwLSIhIjp+OyM6PAogICAgIF4wLSQkJDI+IzxfXDAwZ3AxKyAgXgouCg== and apply)
19:39:31 <boily> fungot: stop making sense.
19:39:31 <fungot> boily: president of the commission we will be in a position to give the member states too will take prompt action to update their systems for inspections at sea.
19:41:01 <HackEgo> [wiki] [[.yacuabll]] http://esolangs.org/w/index.php?diff=39360&oldid=38967 * 192.160.117.140 * (-21) /* Example Program */ Fixed to match website
19:41:51 <boily> fungot: indeed. but have you really been far even as decided to use even go want to do look more like?
19:41:51 <fungot> boily: mr president, i would also draw the commission's attention to a number of occasions i have always understood that during the discussions on climate change, and this is why we stress the need for change. it spells an end to the shortfall of information and inability to be able to take decisions after 2007. cohesion, ladies and gentlemen.
19:44:53 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
19:45:36 <fizzie> "cohesion, ladies and gentlemen."
19:45:47 <fizzie> fungot: You're quite the orator.
19:45:47 <fungot> fizzie: mr president, i too would like to stress very strongly and loudly here in parliament at that time accept an increase of a third country under the european union's great responsibility, and it could cause problems in the application of the agreement: for example references to the presence of president santer, with regard to this objective.
19:45:58 <Bike> very strong and loud is the key to oration
19:48:49 <fizzie> I think I was either going to ask mooz for the sources and/or permission for a mirror, or did ask, but I don't know which, and if I did ask, what I asked for, and what he said.
19:52:48 -!- MindlessDrone has quit (Ping timeout: 245 seconds).
19:57:02 -!- shikhout has joined.
19:59:53 -!- shikhin has quit (Ping timeout: 252 seconds).
19:59:54 -!- shikhout has changed nick to shikhin.
20:03:30 <Bike> http://www.umassd.edu/media/umassdartmouth/collegeofengineering/cisdept/resources/CIS_MS_Dependency_Graph.pdf i wonder why i can't find more of these... oh it's the CS department.
20:05:59 <fizzie> Now I'm tempted to scrape out the web interface to our course information system and try to parse a Graphviz graph out of the prequisites field.
20:06:07 <fizzie> Though the data is very very messy and not machine-readable at all.
20:06:10 -!- contrapumpkin has joined.
20:06:30 <fizzie> And of course not available via any reasonable API either.
20:08:28 <b_jonas> fizzie: how much of them is there?
20:08:55 -!- copumpkin has quit (Ping timeout: 276 seconds).
20:09:08 <fizzie> I can't even tell that in any reasonable way.
20:09:29 <Bike> fizzie: i've been thinking the same thing about my school. with the similar problems.
20:09:56 <Bike> and there are a few hundred courses at least.
20:10:01 <fizzie> The search forms can't search an empty field.
20:10:40 <b_jonas> fizzie: search for each digit
20:10:45 <fizzie> I can search for a single letter, apparently.
20:10:57 <fizzie> There are 4260 courses that have the letter "t" in their course code or name.
20:11:21 <b_jonas> fizzie: how many of those have prerequisites?
20:11:33 <fizzie> How am I suppose to know *that*?
20:12:32 <b_jonas> dunno. I'm glad I don't have to deal with this anymore.
20:12:35 <fizzie> Our university is the combination of three universities, so there's not even any single system for course codes.
20:13:01 <fizzie> Anyway, the prequisites field can have completely free text mentioning course names that are probably not even current.
20:13:20 <fizzie> And there's names in three different languages.
20:13:37 <fizzie> I don't think I'm going to try this.
20:13:43 <b_jonas> all three languages filled for all courses?
20:13:52 <fizzie> Anything from one to three.
20:14:07 <fizzie> Though the third (Swedish) is probably pretty rare.
20:14:10 <b_jonas> I mean, I think here every course has an official English translated name
20:14:29 <fizzie> We probably have courses that don't have an official English name, though those are probably reasonably rare too.
20:15:24 <fizzie> There's a university-level policy that bachelor's-level teaching should be mostly in Finnish, while master's-level stuff should be completely in English.
20:15:26 <Bike> so what's the uh... second
20:15:47 <fizzie> Also, sometimes there are different course codes for the separate language variants.
20:15:53 <fizzie> I think only for some "mass" courses, though.
20:16:07 <fizzie> Probably for easier handling of exams or something like that.
20:16:32 <b_jonas> fizzie: the courses have English names not because they're taught in English, but so that they can be printed to the English translted long diplomas and other forms
20:16:55 <fizzie> I think I had some Finnish course names when I last asked for a course transcript in English.
20:17:02 <Bike> totally sensible reasons being american annoys me: my cv won't be a weird cosmopolitan morass
20:20:46 <fizzie> Here's a random sampling of course codes, to show how uniform it is: 02115, 04334, 20021, 20A00310, 21C09901, 22771, ..., 37A055, 710000, 90L011, A-112.2501, A61A00100, AS-84.3411, Atk0195, AUT.kand, BECS-C3001, cb0027, CHEM-C2410, ELEC-C4110, et003, Inf-0.3101, KE-30.C, KE-31.4520, LC-8045, tk0299, ...
20:20:54 <fizzie> I think that includes most of the formats.
20:21:39 <Bike> man, the most i have to deal with is two (but not all) of the departments having different names at different campuses for no reason i can discern, meaning i have technically never taken a computer science class
20:22:58 <fizzie> I did most of my stuff (and got a master's) before the merger, so all my courses were Xxx-NN.DDD where Xxx was the name of a study program ("T" for computer science, "S" for electrical engineering, "Mat" for mathematics, etc.), Xxx-NN a code for a professorship, and DDD a three-digit course code with usually no clear structure.
20:23:21 <b_jonas> fizzie: here the course codes are at least uniform, mostly:
20:24:05 <fizzie> Then they switched from three- to four-digit codes with some kind of a inherent structure; I think first digit is more or less approximately the year you're supposed to take it in, or something like that.
20:24:32 <fizzie> Most of the other formats are probably from the other two universities, and now they're transitioning to a entirely new format, perhaps (dare I think) to unify them.
20:24:58 <b_jonas> they have the form BMETE010002 where "BME" is fixed and is the abbreviation of the university, TE is the two-letter code of the faculty, 01 is two alnums identifying the department owning the course, and 0002 is four alnums identifying the course among those
20:25:37 <fizzie> (It's this "ELEC-C4110" thing where the first part is a name for a "school" -- we've got six now -- and I don't know how the letter-and-four-numbers part is constructed.)
20:26:02 <b_jonas> mind you, at least one department has two different codes because it was renamed once so old courses use the abbreviation of its older name
20:26:17 <b_jonas> (more than just renamed really, it's complicated)
20:26:27 <fizzie> Except "new" maths courses seem to be of the form MS-A0503 and MS-C1110 and so on, even though "MS" is not a school name.
20:26:37 <fizzie> Never mind, I'm not going to start figuring this out at this point.
20:26:46 <myname> guys, i invented a way to easily kill a lot of nerds without raising suspicion
20:27:42 <b_jonas> a feature in the online administration system I hated is this: when you search for a course, you must choose one of three options for what to search in, one of the three saying "all course",
20:27:49 <myname> just produce something that moulds REALLY hard and make it limited, with a number on it (that part is important!)
20:28:16 <b_jonas> "all courses", but even "all courses" doesn't cover all courses, so you have to repeat the search using the other two options as well to find everything (and maybe even then you don't find everything, I don't know)
20:28:43 <b_jonas> the other feature is that if you log in as a teacher, you get access to much fewer data than if you log in as a student
20:30:12 <b_jonas> but the worst part is that the developers refuse to listen to complaints, they never fix bugs, and the software is based on some idealized rules which don't really apply to the university
20:30:39 <b_jonas> oh, and the system has a planned downtime five hours every night for "backup"
20:31:19 <b_jonas> it's web-based, and they keep changing the javascript code so it only runs on latest versions of browsers, even for features that used to work
20:31:57 <oklopol> our university intranet is incomparable to the non-intranet, for example the non-intranet contains the official instructions for phd students, as a pdf, and intranet contains an elaborate html version with most (though not all) of that information, but not the actual pdf
20:32:05 <b_jonas> this is all about the state of the last iteration I used. the system before that was better in some respect and worse in some other respects
20:32:21 <b_jonas> it was not web-based, but instead needed a remote desktop client.
20:32:50 <fizzie> Oh, we've been iterating through several systems to access this stuff, too.
20:33:15 <b_jonas> oklopol: I have seen important public information accessible only from the intranet, but I haven't seen anything you can access only from non-intranet
20:34:18 <fizzie> There's one more "formal" thing (Oodi) that does enrollment and (internally) grades and all kind of student management stuff, and then a separate thing for less formal course information (Noppa) which is where weekly exercises and project work and course news and things like that get communicated.
20:34:31 <oklopol> well, they clearly spent more effort on the stuff on the intranet
20:34:37 <oklopol> but it's still less information..
20:35:10 <fizzie> Oh, and I once got an export from the first thing in a character encoding nobody could identify.
20:35:24 <b_jonas> I don't understand why people would restrict information to a university intranet in first place. Do they think that makes it more secret because only the ten thousand people in the university can access it?
20:35:43 <fizzie> It wasn't any of the 1173 supported by iconv on this system, at least.
20:36:39 <fizzie> Oh, the informal system (Noppa) can be used to restrict selected material to logged-in users only.
20:36:50 <fizzie> Or some third level of access, I forget what that could be.
20:37:10 <b_jonas> fizzie: could you at least identify the family of the encoding, like a 8859-1-alike, or a 437-alike, or a 646-variant (unlikely), or mangled double-utf?
20:37:31 <fizzie> Well, I mean, beyond the fact that the ASCII half was there.
20:38:03 <b_jonas> fizzie: did it seem like the information was there? or, like, every non-ascii replaced by a question mark? because I've seen a lot of the latter.
20:38:28 <fizzie> I didn't really have much to work with, since the only non-ASCII characters in my export were ä, ö and é.
20:38:36 <fizzie> All those three had a different one-byte encoding.
20:39:12 <fizzie> No, this was a (quite short) list of names, and I guess all first letters happened to be ASCII.
20:39:34 <fizzie> The values for the lowercase letters didn't correspond to any standard encoding I could find.
20:40:53 <fizzie> If you want to go looking, 0xc8 for 'é', 0x89 for ä, 0x88 for ö.
20:41:05 <fizzie> Though it's possible it was something custom for this system.
20:42:03 <fizzie> It's not one of the 8859 family, at least, since those have control characters (or nothing; I'm not sure if that's part of it) from 0x80 to 0x9f.
20:42:55 <fizzie> Oh, and last email I got from this system had all non-ASCII in the subject line replaced by an "X".
20:43:31 <b_jonas> fizzie: or it could be mangled from two different encodings, but even then it's strange
20:43:48 <fizzie> (Further investigation showed that it sends raw ISO-8859-1 directly in the email headers, and somewhere in amavisd/SpamAssassin those got sanitized to "X".)
20:44:14 <b_jonas> I've recently donwloaded a datasets where half of the text is fine and half has a broken (but luckily recoverable) mangling of the non-ascii
20:44:37 <kmc> how about a language with esoteric syntax highlighting
20:47:02 <monotone> "odd numbers are red and even numbers are blue, except primes are invisible"
20:48:30 <kmc> that's a strange kind of synaesthesia
20:51:00 <b_jonas> fizzie: yes, those codes are strange. they don't seem like 437-derived either to me, nor T1-derived or anything else.
20:51:46 <b_jonas> "It's not one of the 8859 family, at least, since those have control characters ... from 0x80 to 0x9f." -- that's not sound logic, because cp1252 and cp1251 have printable characters at most of those places
20:52:27 <b_jonas> but these codes aren't those of course
20:52:29 <fizzie> Yes, but I wouldn't call those part of the 8859 family just because they coincide with one elsewhere.
20:52:31 <kmc> `run for c in $(iconv -l); do if printf '\xc8' | iconv -f $c 2>/dev/null | grep -q é; then echo $c; fi; done
20:53:00 <fizzie> kmc: I sort of did that already, except with iconv -l | while read cs; do if [ "$(printf '\x89\x88\xc8' | iconv -f $cs -t utf8)" = "äöé" ]; then echo $cs; fi; done 2>/dev/null
20:53:11 <kmc> yeah i don't get anything either
20:53:39 <b_jonas> fizzie: cp1250 doesn't quite coincide, just almost. as for whether you call it family, whatever, but they're still something I have to check if I don't know the encodings because they're frequent.
20:55:05 <b_jonas> what I hate about cp1250 is that it didn't get renamed when they added those five characters that didn't use to exist when the codepage was first used (the romanian letters and the euro sign)
20:55:29 <kmc> there is no code but unicode and utf-8 is its transport
20:55:48 <b_jonas> kmc: I'm not convinced of that
20:56:01 <b_jonas> though I've almost accepted it now
20:56:26 <b_jonas> it might take a few more years till I'm completely converted to using utf-8 only
20:56:56 <fizzie> What I don't like about ISO-8859-15 is that it's "Latin 9". (This applies to any ISO-8859-N that is Latin-M for N ≠ M.)
20:57:41 <fizzie> I guess that's probably most of them. (Haven't checked.)
20:58:10 <b_jonas> fizzie: that's because the "Latin" means the name of the script, and the purpose of iso-8859-5 is to encode the cyrillic script, not latin script
20:58:34 <b_jonas> fizzie: plus there's one for hebrew and one for greek so it's all shifted
20:58:49 <b_jonas> fizzie: besides, many other character sets have aliases
20:59:31 <b_jonas> reasonable ones like, IBM-437 vs CP437; or ASCII vs US-ASCII or ISO-646-US or that crazy letter-number combination I can never rememner
21:00:24 <fizzie> Onneksi ddkkvset eivdt ole endd ongelma.
21:00:48 <b_jonas> what? is "ddkkvset" a word?
21:01:04 <fizzie> It's a running joke, it's a common mangling of "onneksi ääkköset eivät ole enää ongelma".
21:01:16 <fizzie> Something related to stripping high bits.
21:01:25 <b_jonas> ah yes, I've seen that kind of thing
21:01:59 <fizzie> Alternatively, {{kk|set.
21:02:13 <fizzie> (For the ISO-646-FI interpreted as ASCII.)
21:02:32 <b_jonas> the most common is stripping the high _byte_ of ucs16 codes, resulting in őű transformed to Qq
21:02:59 <fizzie> Freenode doesn't use the case mapping that has [\] be the uppercase variants of {|}. :/
21:03:02 <b_jonas> the 646 one is funnier the other way
21:03:05 <fizzie> (Perhaps that's quite reasonable.)
21:03:17 <ion> It doesn’t? Huh.
21:03:23 <b_jonas> like, basic code listings with PRINTÉ and similar
21:03:35 <fizzie> It's mentioned in the numerics at the start of the connection.
21:04:05 <fizzie> Huh... does it in fact use it on the new server?
21:04:29 <fizzie> I'm absolutely certain it had CASEMAPPING=ascii before.
21:04:40 <b_jonas> it got changed when they changed the irc server
21:04:46 <fizzie> Now it seems to be CASEMAPPING=rfc1459. Well, that's nice, I guess.
21:04:49 <b_jonas> and I don't know what they did with clashing chanserv/nickserv registrations
21:04:49 <ion> If i wrote an IRC client, i’d certainly make it render nicks in ISO 646-FI unless the server informs otherwise.
21:05:16 <fizzie> It does inform you otherwise with CHARSET=ascii still, I guess.
21:05:58 <b_jonas> fizzie: well, the character set is really a client-only abstraction, the server doesn't much care about it besides knowing what bytes it acceppts to channel names and what in nicks etc
21:06:11 <b_jonas> fizzie: most channels these days have decided to use utf-8,
21:06:20 -!- Patashu has joined.
21:06:29 <fizzie> Yes, but I assume it's a reasonable choice for rendering nicks and channel names.
21:06:30 -!- Bike_ has joined.
21:06:32 <b_jonas> but back when I started ircing, at least one channel used iso-8859-2, and changed to utf-8 only later
21:06:51 -!- Patashu_ has joined.
21:06:52 -!- Patashu has quit (Disconnected by services).
21:07:07 <fizzie> Speaking UTF-8 on IRCnet used to be a major faux pas on several channels.
21:07:17 <fizzie> Nowadays it's probably mostly acceptable.
21:07:37 <b_jonas> fizzie: well sure, the channels can decide
21:07:39 <Bike_> "To address the machine-vision and image-processing issues, the Open Connectome Project is alg-sourcing (algorithm outsourcing)"
21:07:42 -!- Bike_ has changed nick to Bicyclidine.
21:07:51 <b_jonas> just like how they can decide whether they like mirc-like color codes etc
21:08:05 <ion> I’m on quite a few IRCnet channels and nobody ever complains about UTF-8. Except one (1) person who’s IRCing on an ancient SunOS box with a broken iconv. He has me on /ignore.
21:09:27 <fizzie> All my IRCnet channels have pretty much died out, which I guess is also a solution of sorts.
21:10:37 <fizzie> ion: I hope your SunOS guy isn't on #utf-8. :)
21:10:43 <ion> Hah. He isn’t.
21:12:02 <fizzie> People still call Solaris that, to be fair.
21:12:13 <ion> Hmm, it *may* be Solaris, actually. I don’t remember anymore.
21:12:21 * boily is battling muscle memory full time... “stupid misorganized keyboard...”
21:12:59 <fizzie> I don't think I've used anything older than Solaris 7 / SunOS 5.7.
21:14:19 <fizzie> Ooh, Wikipedia lists April 29, 2014 (just a week and a bit away) as the release date of Solaris 11.2. Still going strong, I see.
21:16:11 -!- Sprocklem has joined.
21:16:40 <fizzie> http://upload.wikimedia.org/wikipedia/en/timeline/90aec7d902c1d610e90720ebc42fabd4.png a log looks like a good fit for the envelope of the upper half.
21:18:51 -!- contrapumpkin has changed nick to copumpkin.
21:19:36 <Bicyclidine> «Unsurprisingly, since <unistd.h> was so darn hard to find for OpenSSL developers they had resorted to manually protyping read(2) instead of incredible amount of preprocessor wizardry needed to find the ever illusive <unistd.h>»
21:33:24 -!- Sgeo has joined.
21:33:37 -!- ^v has joined.
21:36:01 -!- AnotherTest has quit (Ping timeout: 276 seconds).
21:37:55 -!- boily has quit (Ping timeout: 258 seconds).
21:38:24 -!- conehead has quit (Quit: Computer has gone to sleep).
21:38:33 <HackEgo> [wiki] [[Hollang]] http://esolangs.org/w/index.php?diff=39361&oldid=39351 * Doesthiswork * (+374) added link to implementation
21:39:05 <HackEgo> [wiki] [[Hollang]] M http://esolangs.org/w/index.php?diff=39362&oldid=39361 * Doesthiswork * (+2)
21:45:21 -!- conehead has joined.
21:56:06 <kmc> Bike: do you understand why 5HT reuptake inhibitors attenuate the action of 5HT agonists?
21:56:44 <kmc> (some of them, anyway)
21:58:18 <Bicyclidine> i can't take biochem for a whiole nother year, probably
22:01:04 <Sgeo> If the OpenBSD team discovers a heartbleed-esque flaw in OpenSSL, would they go for responsible disclosure?
22:01:49 <coppro> no, they'd use it to get admin credentials on linux boxes and replace them with BSD
22:02:04 <Sgeo> It's just their review seems so... public
22:02:17 <fizzie> They'd post it on a web page in big letters.
22:02:22 -!- Zerker has joined.
22:02:28 <kmc> gotta make a cool logo first
22:04:16 <Bicyclidine> well, wait, so if serotonin reuptake is inhibited, there's going to be more serotonin around so of course serotonin receptors are more agonized? that seems too simple
22:05:16 <kmc> you mean competitive binding between 5HT and the other agonist?
22:06:13 <coppro> I want to make a language called cenotaffy
22:07:00 <kmc> it makes sense except that SSRIs themselves don't make you trip balls
22:07:11 <kmc> so i don't know if there's something about the relative activation of different receptor subtypes
22:07:33 <HackEgo> [wiki] [[Redcode]] http://esolangs.org/w/index.php?diff=39363&oldid=38262 * 91.125.123.39 * (+1) Corewar -> Core War
22:07:36 <kmc> or that particular molecules activate the receptor in different ways which have different effects inside the cell
22:09:55 <Bicyclidine> well i'm not actually sure what "5HT agonist" means >_<
22:10:22 -!- oerjan has joined.
22:12:25 <impomatic> Is Redcode really an esolang or more of a DSL?
22:12:25 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
22:14:07 <Bicyclidine> it doesn't seem very esoteric at all. it matches its design space pretty straightforwardly.
22:20:49 -!- adu has joined.
22:21:19 -!- nucular has quit (Quit: Switching to phone).
22:34:04 <Bicyclidine> oh i guess "foo agonist" is short for "agonist of foo-receptors", great
22:36:31 -!- doesthiswork has joined.
22:36:43 <kmc> yeah sorry
22:37:41 <Bicyclidine> if [whatever]chemical terminology being weird was actually your fault i'd actually be angry :P
22:37:59 <Bicyclidine> i thought maybe it meant agonists of receptors that stimulate serotonin release, or something
22:39:41 -!- tromp has joined.
22:46:18 -!- TAROT has joined.
22:48:41 <EgoBot> TAROT: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/wiki/Main_Page>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
22:48:54 <Bicyclidine> i just realized this paper i'm reading basically implements genetic memory
22:49:12 <HackEgo> TAROT: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.)
22:49:42 -!- TAROT has quit.
22:49:55 <oerjan> i guess at least one of those got through
22:50:51 -!- TAROT has joined.
22:52:26 -!- TAROT has left.
22:52:48 <oerjan> <quintopia> oerjan stop editting the wiki and come here and help me :( <-- i didn't log on irc because i was about to leave so soon
22:56:07 -!- nooodl_ has joined.
22:59:00 -!- nooodl_ has changed nick to fcrawl.
22:59:06 -!- nooodl has quit (Ping timeout: 240 seconds).
23:08:30 -!- boily has joined.
23:24:07 -!- doesthiswork has quit (Quit: Page closed).
23:30:25 <boily> quintopia: QUINTHELLOPIA!
23:33:40 -!- yorick has quit (Remote host closed the connection).
23:40:39 -!- tromp has quit (Remote host closed the connection).
23:41:13 -!- tromp has joined.
23:42:51 -!- Patashu_ has quit (Ping timeout: 240 seconds).
23:45:15 -!- tromp has quit (Ping timeout: 240 seconds).
23:51:31 -!- conehead has quit (Ping timeout: 252 seconds).
23:55:16 <Sgeo> I've been using my personal computer for work, so am usually offline from IRC for a period of time before work until a period of time after work
23:55:47 * oerjan has no recollection of what he @told, anyway
23:56:29 <Sgeo> 22:30:31: <oerjan> @tell Sgeo <Sgeo> blah >>= flip when $ do ... <-- the precedences are wrong for that to work.
23:56:42 <Sgeo> But there were some lines afterwards where you were wtfing
23:56:46 <Sgeo> 22:30:46: <oerjan> wtf is Sgeo not here
23:57:01 <oerjan> also, when you did return you returned as Sgeo_
00:00:25 -!- nooodl_ has joined.
00:01:40 <Bicyclidine> doesn't that kind of hurt the point of @messages-loud?
00:03:58 -!- fcrawl has quit (Ping timeout: 258 seconds).
00:05:52 <Melvar> I was half-expecting that to be special-cased.
00:12:28 <oerjan> i suspect that's not supported without creating a new command with that name, which will ruin the typo correction by making a lot of them ambiguous...
00:17:19 <Melvar> I wonder, what is piratespeak like in other languages than English?
00:19:36 <oerjan> splitte mine bramseil, hva slags landkrabbespørsmål er det
00:21:14 <oerjan> (not very yarrry, for sure)
00:22:37 -!- boily has quit (Quit: YARROWING CHICKEN).
00:23:31 <oerjan> the main norwegian pirate figure at this time is kaptein sabeltann, who speaks bokmål but with some old sea slang words.
00:30:38 <Sgeo> @tell Bicyclidine you now have messages
00:36:08 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
00:38:21 <Melvar> A German pirate would originally of course have spoken Low German / Low Saxon, which would be quite incomprehensible to any speaker of Modern Standard German.
00:57:21 <Bike> http://www.the-apswiki.org/ this is some incredible web design
00:58:13 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
00:58:30 <ion> I like http://www.the-apswiki.org/@api/deki/site/logo.png a lot
00:59:06 <Bike> lol i didn't even notice
01:01:39 <Sgeo> Sadly, /r/lolc does not seem to be the C equivalent of /r/lolphp
01:02:31 <Bike> frankly the ungoogleability of C is a major design flaw
01:03:37 <Sgeo> I wonder if some search engines special-case C and C++
01:05:43 <monotone> The results for "C" and "C++" by themselves are as you'd expect, for instance.
01:06:11 -!- Bike has quit (Read error: Connection reset by peer).
01:06:34 -!- Bike has joined.
01:06:54 <coppro> monotone: That's not a special case. Trailing + are significant in google
01:09:50 -!- nooodl_ has quit (Quit: Ik ga weg).
01:12:11 <coppro> I think, however, that C/C++ may have been part of hte reason for this
01:13:11 -!- ^v has quit (Ping timeout: 252 seconds).
01:15:29 <kmc> i do want some kind of "wat"-style talk for C
01:15:48 <Sprocklem> coppro: C# seems to be special cased. (AFAICT # is usually ignored)
01:21:10 <kmc> array function parameters, integer promotion rules, signed char, trigraphs
01:21:18 <oerjan> perhaps google has an algorithm for finding words that need special casing.
01:22:09 <Bike> i get the same results from 'p# complexity' and 'p complexity'
01:22:36 <oerjan> kmc: sorry, r/watc isn't about c
01:24:34 <coppro> Bike: I get different results for "p complexity" and "#p complexity" though
01:24:54 <coppro> do we have a langguage that lets you literally specify Turing machines?
01:25:54 <coppro> because if we don't, I'm making one, and it will be called Tarpit
01:27:05 <oerjan> it all depends on what you mean by literally hth
01:27:54 <Bike> coppro: there was one in sigbovik once
01:29:45 <coppro> oerjan: I mean a language where the specification is some form of description of a turing machine
01:30:19 <coppro> actually I've got an even better idea
01:30:30 <coppro> a language where the input, in text, is a TM diagram
01:30:46 <Bike> also roughly half of computability papers go through the rigamarole of specifying TMs as tuples, does that count
01:31:54 <coppro> Bike: no because the tuple model is not actually something I can feed into a computer
01:32:09 <Bike> ok i'll get the sigbovik cite for ya
01:32:36 <coppro> oerjan: in reponse to which?
01:32:37 <oerjan> since when do computers have problems parsing tuples.
01:33:24 <Bike> "The Next 700 Intuitionistic Linear Logics" heh
01:33:33 <coppro> oerjan: oh no. I mean I know of no programming language whose source code is the tuple and the language executes the tuple as a TM
01:33:46 <oerjan> btw i recall mark chu-carroll wrote a turing machine emulator in haskell once.
01:34:11 -!- adu has quit (Quit: adu).
01:34:27 <Bike> ok apparently this one is written in http://en.wikipedia.org/wiki/Plaid_%28programming_language%29
01:37:21 <Bike> the actual turing machine definition is in: Brother Jonathan Aldrich. (2010) Holy States Can Save the World! In ZH Bovik (ed.) A Record of the Proceedings of the SIGBOVIK Conference 2010.
01:39:55 -!- adu has joined.
01:46:29 -!- ^v has joined.
01:57:12 -!- shikhout has joined.
01:59:57 -!- shikhin has quit (Ping timeout: 252 seconds).
01:59:58 -!- shikhout has changed nick to shikhin.
02:29:34 -!- adu has quit (Quit: adu).
02:31:05 -!- ^v has quit (Read error: Connection reset by peer).
02:31:35 -!- ^v has joined.
02:33:52 <newsham> is CPython compiled to asm.js "esoteric"?
02:33:52 <Bike> http://blog.detectify.com/post/82370846588/how-we-got-read-access-on-googles-production-servers nice
02:37:42 <Jafet> http://aturingmachine.com
02:37:52 <newsham> whoa, somebody kept a bug bounty and didnt donate it to charity?
02:39:15 -!- Patashu has joined.
02:41:41 <HackEgo> [wiki] [[Tarpit]] N http://esolangs.org/w/index.php?oldid=39364 * Coppro * (+5913) Created page with "'''Tarpit''' is a description language for state diagrams of finite state machines and their generalizations. It is generally well established that the best description of fi..."
02:42:58 -!- Patashu_ has joined.
02:42:59 -!- Patashu has quit (Disconnected by services).
02:46:24 -!- adu has joined.
02:50:56 <Sgeo> This game is a bit dated
02:50:57 <Sgeo> '"Uh, well, the government did actually use that Facebook information to draft people for the second Korean war in 2013..." Todd replied.'
02:54:36 <Jafet> 'Todd replied.' is this a book
02:57:41 <Sgeo> It's a choose-your-own-adventure game, but needing to take all paths to really get the full story
02:57:55 <Sgeo> http://www.kongregate.com/games/greg/thousand-dollar-soul-321811
03:07:16 -!- Palaver has joined.
03:15:14 -!- Palaver has quit (Remote host closed the connection).
03:15:30 -!- Palaver has joined.
03:19:07 <Palaver> urbit as an esoteric programming language
03:20:40 -!- adu has quit (Quit: adu).
03:33:23 <Bike> the ukraine crisis as an esoteric programming language
03:34:33 -!- MoALTz_ has joined.
03:35:58 -!- MoALTz__ has joined.
03:36:56 -!- tromp has joined.
03:37:01 <oerjan> with its highlevel compareToChamberlain function
03:37:06 -!- MoALTz has quit (Ping timeout: 258 seconds).
03:38:34 <oerjan> clearly Chamberlain should just be an instance of the comparableTo class.
03:39:07 -!- Palaver has left ("Palaver http://palaverapp.com/").
03:39:19 -!- MoALTz_ has quit (Ping timeout: 250 seconds).
03:48:02 <Sgeo> :t maybe Nothing . Just
03:48:04 <lambdabot> Couldn't match type ‘Maybe a’ with ‘a1 -> Maybe a2’
03:48:04 <lambdabot> Expected type: a -> a1 -> Maybe a2
03:48:35 <Sgeo> :t maybe Nothing Just
03:49:29 <myname> does anybody of you know what the & is supposed to do in rail?
03:51:00 <Bike> ruby on rails?
03:55:43 <newsham> bike: have you ported ruby to rail?
03:56:01 <Bike> ruby on the third rail
03:57:14 <Bike> myname: checked the article. & looks kind of like a twisted up track so without more definition of 'lambda' it's obviously a crash
04:00:41 <Sgeo> http://java.metagno.me/
04:00:55 <newsham> this stuff will probably kill you, lets do another line, what say you meet me down on hollywood and vine
04:01:16 -!- conehead has joined.
04:06:09 <Bike> StompWebApplicationContextAwareBean, not bad
04:08:19 <Sgeo> Are GADTs == 'closed' data families?
04:18:23 -!- MoALTz_ has joined.
04:21:11 -!- MoALTz__ has quit (Ping timeout: 258 seconds).
04:21:37 -!- JesseH2 has quit (Read error: Connection reset by peer).
04:22:07 -!- JesseH2 has joined.
04:23:27 -!- not^v has joined.
04:25:30 -!- tromp has quit (Remote host closed the connection).
04:26:47 -!- ^v has quit (Ping timeout: 252 seconds).
04:28:39 -!- doesthiswork has joined.
04:30:54 <doesthiswork> I happened to be sitting in the library near a CS 120 tutoring area
04:31:43 <oerjan> do you think you'll get over it?
04:32:19 <Bike> http://upload.wikimedia.org/math/5/9/c/59c905daa195675abf6216e2f08ad32d.png can someone explain to me how physics even exists, as a field of study
04:34:04 <doesthiswork> when the students had left I asked the tutor and ill formed question about abstraction and partial application, and he explained that there was somthing called recusion that is pretty neat and that I should learn python
04:35:16 <oerjan> he did the appropriate thing and learned python by already knowing it
04:36:18 <oerjan> yes, that follows from the fact that it's recursion
04:52:29 <Sgeo> "Ah yes, the Before C Programing Language"
04:55:57 <newsham> Before C / Ano Dennisritchie
04:57:21 -!- Sellyme has quit (Excess Flood).
04:57:33 <Sgeo> Haven't started reading (except that it proves False), but is http://okmij.org/ftp/Haskell/impredicativity-bites.html fixed yet?
04:59:27 -!- Sellyme has joined.
05:03:35 <Sgeo> o.O http://okmij.org/ftp/Haskell/types.html#de-typechecker
05:05:01 -!- Patashu_ has quit (Ping timeout: 252 seconds).
05:06:01 <HackEgo> [wiki] [[Talk:Hollang]] http://esolangs.org/w/index.php?diff=39365&oldid=39355 * Zerk * (+239)
05:07:14 <Sgeo> "Uncharitably speaking, Haskell, taken as a logic, is inconsistent in more than two ways."
05:08:32 -!- oerjan has quit (Quit: leaving).
05:10:17 <Bike> stop the presses
05:11:56 <Jafet> "Essentially we turn a type into a logical program -- a set of Horn clauses -- which we then solve by SLD resolution. It is gratifying to see that Haskell typeclasses are up to that task."
05:12:55 -!- adu has joined.
05:14:05 <newsham> i heard that haskell was not intended to be a sound logic.
05:15:26 <newsham> i heard that the easter bunny isnt real :(
05:15:47 <Bike> wow why would you say that on good friday? i'm pretty sure you're going to hell now
05:20:49 <newsham> what makes it a good friday?
05:28:39 -!- Sorella has quit (Quit: It is tiem!).
05:40:51 -!- trout has changed nick to function.
05:43:37 <Bike> Do spin glasses actually exist
05:45:03 <kmc> spin glass in yer ass
06:05:21 <Bike> well like in its spin ice article it at least gives an actual example (dysprosium titanate)
06:09:46 <Bike> http://facepunch.com/showthread.php?t=1386818 Anyway here's a blast from the past for you: A worm
06:11:01 <HackEgo> [wiki] [[Hollang]] http://esolangs.org/w/index.php?diff=39366&oldid=39362 * Zerk * (-280) Amended addition algorithm
06:22:45 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:27:03 <HackEgo> [wiki] [[Hollang]] M http://esolangs.org/w/index.php?diff=39367&oldid=39366 * Doesthiswork * (-34) I am impressed, that is a much smarter program
06:36:18 -!- adu has quit (Quit: adu).
06:52:15 -!- Sprocklem has quit (Quit: leaving).
07:05:23 <Sgeo> "strncpy(d, s, strlen(s)) is a special kind of stupid. even when it’s right, it looks wrong. "
07:05:25 <Sgeo> I don't get it
07:07:17 <Jafet> Heh, I thought it's a useless version of strcpy(d, s), but on closer inspection it's completely wrong
07:09:05 <kmc> emotions and "irrational" behavior are a way for selfish genes to credibly commit to strategies which would be overruled by rational self-interest
07:10:14 -!- Patashu has joined.
07:12:36 <Bike> Jafet: how's it different
07:13:09 -!- Patashu has changed nick to 7F1AAEZAZ.
07:13:10 -!- rodgort has quit (Ping timeout: 258 seconds).
07:13:10 -!- Patashu has joined.
07:13:33 <Bike> i hear reason is and should be slave to the emotions
07:14:22 <kmc> Bike: we, alone on earth, have the power to free ourselves from the tyranny of the selfish replicators
07:14:25 <kmc> pass it on
07:14:50 -!- rodgort has joined.
07:15:11 <Jafet> `run echo $'#include <stdio.h>\n#include <string.h>\nmain() { char a[] = "abcde", b[42]; strncpy(b, a, strlen(a)); return !puts(b); }\n' > /tmp/strncpy.c && gcc -o /tmp/strncpy{,.c} && /tmp/strncpy
07:15:46 <Jafet> `run echo $'#include <stdio.h>\n#include <string.h>\nmain() { char a[] = "abcde", b[] = " :-)"; strncpy(b, a, strlen(a)); return !puts(b); }\n' > /tmp/strncpy.c && gcc -o /tmp/strncpy{,.c} && /tmp/strncpy
07:16:11 <Bike> can you use words
07:16:37 <kmc> ssl added and removed here
07:16:46 <Jafet> In english: don't use strncpy he is a lame guy
07:17:01 -!- 7F1AAEZAZ has quit (Ping timeout: 252 seconds).
07:18:29 <Bike> `run echo $'#include <stdio.h>\n#include <string.h>\nmain() { char a[] = "abcde", b[] = " :-)"; strcpy(b, a); return !puts(b); }\n' > /tmp/strcpy.c && gcc -o /tmp/strcpy{,.c} && /tmp/strcpy
07:18:58 <Bike> oh, it doesn't copy the null
07:20:08 <Jafet> kmc: is that a new vhemt campaign
07:21:45 <Bike> i wonder if the selfish gene predates regulatory networks
07:23:23 -!- doesthiswork has quit (Quit: Page closed).
07:25:34 <Bike> i swear nobody keeps track of history with these things. need to give evolutionary biology a repo
07:25:40 <kmc> Jafet: the tyranny quote? no it's the last sentence of The Selfish Gene
07:26:11 <kmc> spot the irony anyone
07:27:02 -!- WOODMAN has joined.
07:27:05 <Bike> brb setting up scumbag meme meme
07:27:12 <WOODMAN> Promoción GAWMiners para Compradores / vendedores Co-Op - 10% descuento en cualquier orden!
07:29:12 -!- tromp has joined.
07:33:37 -!- tromp has quit (Ping timeout: 258 seconds).
07:33:58 -!- ChanServ has set channel mode: +o kmc.
07:34:13 -!- kmc has set channel mode: +b *!*@c-24-16-35-49.hsd1.wa.comcast.net.
07:34:17 -!- kmc has kicked WOODMAN don't spam.
07:34:24 -!- kmc has set channel mode: -o kmc.
07:34:41 <kmc> the bitcoin spam has reached us even here -_-
07:38:22 <kmc> i want a god who stays dead, not plays dead
07:42:02 <kmc> also, happy bicycle day
07:43:02 <Bike> 419, uh, spin it
07:45:00 -!- conehead has quit (Quit: Computer has gone to sleep).
07:48:09 <kmc> drop it, more like
07:48:36 <Bike> why would you drop a bike :(
07:51:07 <kmc> Bike do you know what bicycle day is
07:57:25 -!- shikhout has joined.
07:57:58 <Jafet> One short trip for humanity
07:58:46 <kmc> http://www.psychedelic-library.org/child.htm is a pretty good read
07:58:48 <Jafet> s/humanity/a man/ wow I mangled it more than I thought
08:00:01 -!- shikhin has quit (Ping timeout: 252 seconds).
08:00:03 -!- shikhout has changed nick to shikhin.
08:00:36 <Bike> "damn, this is the good shit" -- armstrong at some point, probably
08:01:05 <kmc> have you ever been on the moon... on weed
08:01:22 <Jafet> Someone needs to fund this
08:02:21 <Jafet> http://members.shaw.ca/rlongpre01/moon.html
08:03:29 <kmc> it's pretty tantalizing that only a tiny fraction of all possible psychedelics have ever been synthesized let alone tested in humans
08:03:59 <kmc> and that tiny sample has yielded some of the most mysterious and powerful psychopharmacological agents and has facilitated many of the most intense and meaningful experiences ever reported by human beings
08:05:11 <kmc> so what else is out there
08:07:05 <kmc> Jafet: yes
08:07:39 -!- kmc has set topic: The channel with > 100% bots | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
08:08:35 <Jafet> The training simulation consists of taking weed on earth and pretending you're on the moon
08:09:24 <Jafet> It's cheap, no need to run a reality TV show
08:09:24 <Bike> what if there were two astronauts on the moon and one of them killed the other with a rock. would that be fucked up or what
08:09:27 <kmc> hotboxing a winnebago and calling it the lunar module
08:10:17 <kmc> actually there was an earlier The Onion: Our Dumb Century article
08:10:27 <kmc> "NASA, hippies race to send man to the moon"
08:11:22 <Bike> http://www.scp-wiki.net/scp-1958
08:18:40 -!- AnotherTest has joined.
08:20:49 <kmc> Siamese Dream is a really good album
08:22:06 <Jafet> I wonder what point sandisk is making with this ad http://ds.serving-sys.com/BurstingRes/Site-19890/Type-0/39e1ac57-fdd0-4dad-a400-b4ea62db3b3f.jpg
08:22:34 <kmc> "we <3 jpeg artifacts"?
08:26:33 <kmc> time for me to sleep
08:27:00 <kmc> good night friends
08:34:55 <Taneb> I have came to replace kmx
08:47:05 -!- MoALTz_ has quit (Quit: Leaving).
08:47:16 -!- MoALTz has joined.
09:01:22 -!- xpte has quit (Quit: Connection closed for inactivity).
09:35:28 <Jafet> http://community.amd.com/community/amd-blogs/amd-gaming/blog/2014/03/03/the-wild-west-of-cryptocurrencies
09:35:36 <Jafet> "stay tuned for part two where we’ll explore in detail how AMD Radeon™ hardware helps provide a technological advantage for users participating in cryptocurrency mining!"
10:16:01 <myname> "changelog: switched ad network (requires more permissions)"
10:16:09 <myname> yeah, must have update for an app
10:24:22 -!- nooodl has joined.
10:31:43 -!- yorick has joined.
11:21:19 -!- heroux has quit (Ping timeout: 258 seconds).
11:22:24 -!- heroux has joined.
12:05:06 -!- Tod-Autojoined has joined.
12:05:55 -!- MoALTz_ has joined.
12:06:52 -!- sebbu2 has joined.
12:07:25 -!- sebbu2 has quit (Changing host).
12:07:25 -!- sebbu2 has joined.
12:11:37 -!- erdic_ has joined.
12:14:39 -!- contrapumpkin has joined.
12:14:52 -!- MoALTz has quit (*.net *.split).
12:14:53 -!- copumpkin has quit (*.net *.split).
12:14:53 -!- TodPunk has quit (*.net *.split).
12:14:54 -!- jconn has quit (*.net *.split).
12:14:55 -!- JZTech101 has quit (*.net *.split).
12:14:55 -!- sebbu has quit (*.net *.split).
12:14:56 -!- erdic has quit (*.net *.split).
12:15:13 -!- JZTech101 has joined.
12:15:28 -!- Phantom_Hoover has joined.
12:42:08 <HackEgo> [wiki] [[Special:Log/newusers]] create * UncleMartin * New user account
12:42:58 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=39368&oldid=38890 * UncleMartin * (+73) /* Example-based languages */
12:43:30 -!- Patashu has quit (Ping timeout: 240 seconds).
13:08:24 -!- olsner_ has joined.
13:17:52 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
13:32:29 -!- Phantom_Hoover has joined.
13:43:08 -!- edinson1 has joined.
13:43:43 -!- edinson1 has left.
14:01:32 -!- shikhout has joined.
14:01:55 -!- shikhin has quit (Ping timeout: 252 seconds).
14:02:12 -!- shikhout has changed nick to shikhin.
14:04:14 -!- MindlessDrone has joined.
14:05:18 -!- shikhout has joined.
14:08:09 -!- shikhin has quit (Ping timeout: 252 seconds).
14:08:22 -!- shikherr has joined.
14:09:00 -!- shikherr has changed nick to shikhin.
14:10:44 -!- shikhout has quit (Ping timeout: 252 seconds).
14:10:57 -!- function has changed nick to trout.
14:27:33 -!- tromp has joined.
14:31:31 -!- Sorella has joined.
14:35:00 -!- oerjan has joined.
14:40:08 -!- sebbu2 has changed nick to sebbu.
14:42:41 -!- jconn has joined.
14:45:18 <fizzie> For your edification, the weakly connected components of esolangs.org (considering as vertices only the main and category namespaces): http://sprunge.us/gSMg
14:46:22 <fizzie> (Disclaimer: does not take templates into account, so there are e.g. some stuff with {{stub}} that are not counted as part of the main component, since the [[Category:Stub]] link is not visible.)
14:49:43 <oerjan> hm those are essentially orphan pages
14:51:13 <fizzie> It's very close to Special:LonelyPages, yes. Though not quite exactly identical.
15:06:56 -!- ^v has joined.
15:14:56 -!- ^v has quit (Read error: Connection reset by peer).
15:16:11 -!- ^v has joined.
15:20:36 -!- oerjan has set topic: The channel with > 100‰ bots | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
15:24:55 -!- adu has joined.
15:26:31 <HackEgo> [wiki] [[FukYorBrane]] http://esolangs.org/w/index.php?diff=39369&oldid=30341 * 91.125.123.39 * (+18) CoreWars -> Core War and link to Redcode
15:29:00 <HackEgo> [wiki] [[Brainfuck]] http://esolangs.org/w/index.php?diff=39370&oldid=39047 * 91.125.123.39 * (+18) /* Related languages */ CoreWars -> Core War and link to Redcode
15:31:07 <HackEgo> [wiki] [[BF Joust]] http://esolangs.org/w/index.php?diff=39371&oldid=37998 * 91.125.123.39 * (+12) CoreWars -> Core War and link to Redcode
15:42:44 -!- oerjan has quit (Quit: leaving).
15:43:07 -!- contrapumpkin has changed nick to copumpkin.
15:44:52 -!- adu has quit (Quit: adu).
15:45:03 <HackEgo> [wiki] [[Agony]] http://esolangs.org/w/index.php?diff=39372&oldid=35617 * 91.125.123.39 * (+1) /* AgonyWar */ CoreWar -> Core War
15:48:37 <HackEgo> [wiki] [[Pinkcode]] http://esolangs.org/w/index.php?diff=39373&oldid=38039 * 91.125.123.39 * (-36) Core Wars -> Core War, changed link to Wikipedia disambiguation page for Redcode to Redcode page on Esolang wiki.
15:55:45 <mroman> How is Redcode related to Brainfuck?
15:57:37 <HackEgo> [wiki] [[Underload]] http://esolangs.org/w/index.php?diff=39374&oldid=35186 * 91.125.123.39 * (+4) /* External resources */ link to Redcode
15:58:56 -!- Sgeo has quit (Read error: Connection reset by peer).
15:58:59 <impomatic> mroman: It's not. But there's a BF interpreter written in Redcode.
16:00:05 <impomatic> Unless you mean comparing FYB and BF Joust to Core War?
16:06:50 -!- Frooxius has quit (Quit: *bubbles away*).
16:07:01 -!- Frooxius has joined.
16:21:53 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
16:51:35 -!- erdic_ has changed nick to erdic.
17:04:56 -!- Sprocklem has joined.
17:05:36 <fizzie> Unsurprising fact: "Language list" is the center of esolangs.org: http://sprunge.us/QFJG
17:05:44 <fizzie> Analysis as per http://mu.netsoc.ie/wiki/ i.e. the http://en.wikipedia.org/wiki/Centrality#Closeness_centrality metric in the single, 1272-page strongly connected component.
17:06:35 <fizzie> (Hence the numbers indicate the average number of clicks needed to get to any other page starting from the indicated one.)
17:11:30 <int-e> hmm. 3.1415 Underload
17:12:55 <fizzie> Intentional, I'm sure.
17:44:59 -!- Sgeo has joined.
17:49:24 <Bike> http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libssl/src/apps/s_socket.c.diff?r1=1.30;r2=1.31 "Added for T3E"
17:52:53 <int-e> heh. is that a computer without 32 bit ints?
17:53:33 <int-e> (that would be a reason to use bitfields for IPv4 addresses)
17:56:23 <kmc> impomatic: what's FYB?
17:56:52 <kmc> oh i see http://esolangs.org/wiki/FukYorBrane
17:59:02 <Bike> "The 21164 implemented a 43-bit virtual address and a 40-bit physical address."
17:59:07 <Bike> says it had 64 bit regs, though
18:00:46 <Bike> http://freshbsd.org/commit/openbsd/61596b948ab4b982ac734df79749707a4faa0f07 Important
18:01:14 <Bike> i dig the commit msg
18:01:16 <int-e> huh, the last one has four X
18:01:33 <Bike> it's explained in the commit message!!
18:20:38 <Bike> http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libssl/src/apps/ca.c.diff?r1=1.43;r2=1.44 printf more like whybotherf
18:31:36 -!- conehead has joined.
18:53:20 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39375&oldid=39359 * Zerk * (+305) Added missing {a b c} format explanation
18:54:48 -!- impomatic has quit (Ping timeout: 258 seconds).
19:12:01 -!- doesthiswork has joined.
19:16:35 -!- olsner_ has quit (Quit: ZNC - http://znc.in).
19:16:54 -!- olsner_ has joined.
19:20:37 -!- impomatic has joined.
19:23:07 -!- olsner has quit (Quit: Leaving).
19:24:35 -!- olsner_ has changed nick to olsner.
19:30:29 -!- trout has quit (Ping timeout: 250 seconds).
19:33:05 -!- xpte has joined.
19:36:15 -!- boily has joined.
19:37:01 <HackEgo> x+coin spuracoin critecoin bercoin alpecoin owlcoin selfinghacoin steprocoin lerecoin fobcoin boguetcoin shafsoncoin majecoin prelncoin 0500coin hagecoin smitacoin pbodancoin 0.1800001100acoin quatcoin
19:41:20 <Vorpal> I would styalize it so that coin is below the X+ and the + inside the < of the X
19:41:32 <Vorpal> coin is below the plus I mean
19:43:38 * impomatic wonders what these esocoin things are?
19:44:01 <fizzie> If you make a Markov chain with the transition probabilities taken from the links of the wiki (normalized, so that a page with two links to A and one link to B has a transition probability of 2/3 for A and 3/3 for B), this is the stationary distribution it has: http://sprunge.us/ARcB
19:44:06 <fizzie> I.e. if you keep clicking random links forever, that's relatively how often you'll be visiting each page.
19:44:57 <fizzie> (Er, assuming you only click those links that stay in the strongly connected component of pages.)
19:45:33 -!- DarthMater has joined.
19:47:30 <boily> strange. aubergine is more linked than betterave.
19:48:42 <olsner> http://fr.wikipedia.org/wiki/Betterave?
19:49:22 <Vorpal> why does "Befunge/index.php" exist?
19:50:02 <Vorpal> Or rather, why that name for that language
19:50:10 <boily> olsner: betterave.
19:51:32 <boily> olsner: most probably.
19:51:45 <Vorpal> olsner, interwiki links seems to suggest it is beta in general
19:51:52 <Vorpal> Though that could be wrong
19:52:35 <Vorpal> olsner, so does the Latin name, which is probably more accurate than the interwiki links
19:52:41 <olsner> yeah, seems like it's beets general
19:52:59 <olsner> it mentions e.g. betterave rouge and betterave a sucre
19:53:35 <mroman> Has anyone actually tried taking an existing conventional programming language and just interpret it differently?
19:53:42 <Vorpal> olsner, oh it seems rödbeta is a cultivated variant of the beet family, that it is in fact not a separate species
19:53:57 <fizzie> boily: Aubergine has incoming links from "Aubergine/aubergine.hs", "Carriage", "Language list" and "List of quines"; Betterave has incoming links from "Hello world program in esoteric languages", "Language list" and "Truth-machine" only.
19:53:58 <mroman> so that the source code remains at least syntactically valid in both languages
19:54:16 <fizzie> (I guess there's probably a MediaWiki special page for looking that up already?)
19:54:33 <elliott> it's linked in the sidebar of every page
19:54:53 <fizzie> Well, [pages[p] for p in (a[:,pagemap['Aubergine']] > 0).nonzero()[0].tolist()] is clearly much easier than that.
19:55:20 <Vorpal> elliott, why the name "Befunge/index.php". It says you made that language.
19:55:27 <fizzie> (I have no idea why I have (a > 0).nonzero() in place of a.nonzero().)
19:55:36 <boily> mroman: you mean, unconscious polyglots?
19:56:28 <mroman> that depends what unconscious means :)
19:56:29 <elliott> Vorpal: same reason as http://esolangs.org/wiki/Brainfuck/w/index.php%3Ftitle%3DTalk:Brainfuck/index.php
19:56:34 <mroman> except for being knocked out
19:56:43 <boily> mroman: got my prefixes mixed.
19:56:52 <Vorpal> elliott, ....yes I just found that, and I still don't know the reason for that either
19:57:13 <boily> but then, I really like that “unconscious polyglot” idea.
19:57:31 * boily imagines a coma patient that can not speak in multiple languages
19:57:49 <mroman> Every program would be a polyglot I guess
19:58:06 <mroman> Except it might not do the same thing
19:58:31 <olsner> hmm, might make it harder to make an actual polyglot
19:58:54 <Vorpal> elliott, what happened to your befunge-98 implementation btw? In haskell iirc?
19:59:12 <elliott> or on some random hard drive
19:59:56 <mroman> For unconventional languages these already exist
20:00:05 <mroman> just consider flipping + and - in Brainfuck and there you go
20:00:20 <mroman> same syntax/grammer, different meaning.
20:03:11 <Vorpal> mroman, you could do the same in, say, C. Wouldn't be very interesting though, most programs just wouldn't work properly if you swapped, say, / and *
20:03:13 <mroman> Obviously you could do the same thing in C.
20:03:33 <mroman> I had the same thought just at the same time
20:03:53 <mroman> but yeah. I hate it when a seemingly good idea suddenly turns boring again :(
20:04:18 <mroman> although it could still be interesting. But you have to be more creative than just switch / and *
20:04:23 <Vorpal> Right, prepare to be disappointed by life then. That happens 99 times out of 100
20:04:28 -!- conehead has quit (Quit: Computer has gone to sleep).
20:04:42 <mroman> I'm already suffering from depression. So...
20:05:22 <mroman> ... I'm already rather disappointed
20:05:26 <Vorpal> I have a hard time of thinking of any transformation that would result in programs not specially written for this new language duality doing interesting stuff
20:05:52 <Vorpal> Of course you could always write programs that check for it and do interesting stuff in either case
20:06:39 <mroman> You could just add new features to it.
20:07:27 <mroman> Is "abc"+"abc" legal C code?
20:08:07 <Taneb> I'm in the mood to make an esolang
20:08:18 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:08:22 <olsner> you can add almost anything, but not two pointers (without casting)
20:08:23 <Vorpal> "Shockwave Flash has crashed". Dammit flash
20:08:36 -!- shikhout has joined.
20:08:43 <doesthiswork> do you folk already know about pointer machines? http://en.wikipedia.org/wiki/Pointer_machine
20:09:10 <Vorpal> mroman, I think that would add up the addresses of the pointers to the strings
20:09:15 <Vorpal> mroman, if it is legal that is
20:09:20 <mroman> Vorpal: it's not legal.
20:09:30 <mroman> I'd thought it add up the addresses yes
20:10:03 <Taneb> Pointers are a torsor or something
20:10:34 <Vorpal> doesthiswork, I heard of it iirc
20:11:06 <Vorpal> "Pointer machines cannot do arithmetic. Computation proceeds only by reading input symbols, modifying and doing various tests on its storage structure—the pattern of nodes and pointers, and outputting symbols based on the tests. "Information" is in the storage structure."
20:11:11 <Vorpal> I'm not sure I believe that
20:11:31 <Vorpal> Couldn't you come up with a numeric representation for those systems?
20:11:31 -!- shikhin has quit (Ping timeout: 252 seconds).
20:11:32 -!- shikhout has changed nick to shikhin.
20:14:43 <mroman> Maybe that's meant like "Brainfuck can't multiply numbers"
20:16:03 <Vorpal> mroman, it can, you just need to do it by a fairly inefficient algorithm
20:16:27 <int-e> Vorpal: I believe you missed the point
20:16:34 <int-e> "it's not built into the language"
20:18:48 <Taneb> I'm going to make a new esolang BEFORE MIDNIGHT
20:19:01 <lambdabot> Local time for Taneb is Sat Apr 19 21:19:01
20:19:05 <Vorpal> Taneb, that is a nice name, when are you going to make it ;)
20:20:01 <olsner> so midnight is an hour later for you
20:20:27 <Taneb> British Summer Time
20:20:48 <mroman> I was opting for B____ saving time
20:20:57 <Taneb> Bullshit saving time
20:21:36 <Vorpal> mroman, generally it is called "summer time" not "saving time" in Europe I think
20:22:23 <olsner> is summer the savings time? I always thought winter is when daylight is in need of saving
20:22:37 <Vorpal> I'm in CEST for example, Central European Summer Time
20:23:14 <lambdabot> Local time for olsner is Sweetmorn, the 1st of Chaos in the 3136 YOLD
20:23:20 <mroman> olsner: It's a mistery
20:23:46 <Vorpal> why is it ignoring me?
20:24:00 <Vorpal> How do I set the local time
20:24:03 <lambdabot> time <user>. Print a user's local time. User's client must support ctcp pings.
20:24:24 <olsner> slightly surprised the ctcp reply from the other computer survived ZNC (currently on the laptop which apparently didn't get to also respond)
20:24:29 <Vorpal> Yeah I filter all CTCP
20:24:40 <Vorpal> well except CTCP ACTION
20:24:43 <lambdabot> I live on the internet, do you expect me to have a local time?
20:24:59 <fungot> olsner: mr president, the evidence indicates that community import conditions and controls at external borders and of border crossing points, one about the single currency project have been forced by fear of famine and warfare. the khran rebels, holding some six hundred civilians hostage, used them as human beings.
20:25:13 <Vorpal> -olsner- TIME Sweetmorn, the 1st of Chaos in the 3136 YOLD
20:25:13 <Vorpal> -olsner- TIME Sat Apr 19 22:25:07
20:25:18 <Vorpal> I'm getting two answers
20:25:33 <lambdabot> Local time for mroman is Sat Apr 19 22:25:30 2014
20:25:45 <myname> the first one is clearly more important
20:25:57 <Vorpal> -olsner- GNU sed version 4.2.1
20:25:57 <Vorpal> -olsner- VERSION xchat 2.8.8 Ubuntu
20:26:11 <Vorpal> the first one is even lacking the VERSION string
20:26:22 <olsner> might be nondeterministic which one answers then, and lambdabot probably picks the first ... perhaps I can set up something nice in znc
20:26:46 <fungot> fizzie: madam president, i want to welcome the commissioner.
20:26:50 <lambdabot> Local time for fungot is I AM TIME ITSELF
20:27:10 <lambdabot> Local time for fizzie is Sat Apr 19 23:28:07 2014
20:27:19 <olsner> Vorpal: perhaps I just chose to respond usisng a CTCP GNU? that should be allowed?
20:28:17 <fizzie> Graph visualization is a https://dl.dropboxusercontent.com/u/113389132/Misc/20140419-links.pdf good tool for data exploration.
20:28:42 <Vorpal> olsner, pretty sure the response should be prefixed with the original command
20:28:48 <Vorpal> olsner, so that would be with VERSION
20:28:59 <Vorpal> not sure of if it should be caps or not
20:29:43 <Vorpal> olsner, but I guess you could argue that you are sending an answer to something that was never sent
20:29:53 <Vorpal> in which case you shouldn't respond to it
20:34:43 <b_jonas> fungot, do you find words that start with five consonants inherently funny?
20:34:45 <fungot> b_jonas: mr president, i want to wish you a fruitful presidency and we could go along with the outcome of the meeting at laeken. unfortunately, the working conditions and puts pressure on wages, implemented by the member states to look at the role that one of the most difficult question is probably whether and to what extent merchant shipbuilding is competitive in the long run if we are to find the funding to do so, in practice
20:35:22 <Vorpal> b_jonas, words such as?
20:35:29 -!- boily has quit (Ping timeout: 250 seconds).
20:35:48 <Vorpal> I can't think of any such words off the top of my head
20:36:30 <int-e> happy easter, fungot!
20:36:30 <fungot> int-e: mr president, honourable member, this particular accident again raises the problem of choices, the commission can intervene immediately. a further consolidation, a new regulation was adopted just last year i attended the coordinators' meeting of the conference.
20:36:44 <int-e> "raises the problem of choices"
20:36:45 <b_jonas> Vorpal: I'm laughing all day at a sign in the metro that has two typos, one of which resulted in the word зкстренного
20:36:56 <mroman> Does "sch" count as three consonants?
20:37:03 <Vorpal> b_jonas, well I'm not russian so that doesn't help
20:37:18 <int-e> and in russian there is a single letter for that sound
20:38:06 <fizzie> There seem to be no real such words like that in my /usr/share/dict/words; the only matches are stuff like "HTML's".
20:38:11 <b_jonas> maybe we need an esoteric language for this, one that likes crazy consonant clusters
20:38:16 <olsner> I'd say it depends on what you mean by consonant, those are three letters and each is a consonant letter, but pronounciation is likely to be a single consonant sound
20:38:39 <Vorpal> grep -E '^[qrtpsdfghklzxcvbnm]{5}' /usr/share/dict/words
20:38:53 <Vorpal> Assuming I got the consonants for English right
20:39:15 <fizzie> Y is sometimes a vowel, sometimes a consonant, or so I've heard.
20:39:23 <int-e> funny, i'd have checked them in alphabetical order :)
20:39:35 <Vorpal> There are words with 4 though, all but one use sch[lmnrt]
20:39:37 <int-e> rather than scanning the keyboard
20:40:30 <Vorpal> int-e, anyway I'm not sure if I got them right for English
20:40:35 <Vorpal> Since I'm not a native speaker
20:40:37 <olsner> fizzie: that's what I've heard for english, but swedish counts Y as a proper vowel afaik
20:40:47 <fizzie> olsner: Oh, it's always a vowel in Finnish too.
20:41:09 <Vorpal> anyway allowing y there are a few
20:41:15 <fizzie> (I did [^aeiouy], FWIW; there are words when counting y, but they all sound pretty vowely.)
20:41:17 <Vorpal> but them I don't know if they count
20:41:20 <olsner> oh, and yet other times, Y is thorn
20:41:21 <Taneb> I'm thinking about making this language have nasty implementation-defined evaluation order
20:41:54 <b_jonas> Taneb: I think there's already such a language
20:42:06 <b_jonas> http://esolangs.org/wiki/Whenever
20:42:36 <Vorpal> given something like f(a(x), b(y)) it is undefined if a or b is called first
20:42:43 <Vorpal> Same goes for a() + b()
20:42:55 <fizzie> Not for a(); b(); though.
20:43:04 <Taneb> I was actually thinking more like http://www-users.cs.york.ac.uk/burns/pf.html
20:43:26 <int-e> Vorpal: I wonder about the status of 'w'.
20:43:31 <olsner> sounds like Whenever makes it possible to specify ordering using dependencies/conditions, might want to get rid of that
20:43:44 <int-e> but I'm not a native speaker either.
20:44:14 <int-e> on that topic, how many syllables would you say "polynomial" has?
20:44:34 <olsner> if u is a vowel, w should be a double-vowel
20:44:58 <Vorpal> int-e, po-ly-no-mi-al?
20:45:26 <Vorpal> olsner, I guess I could be pronouncing it wrong then?
20:45:31 <Taneb> int-e, I... actually pronounce it poh-nom-yal
20:45:37 <int-e> I've had a native speaker tell me there are 4; my personal vote goes to 4.5 ;-)
20:45:37 <Taneb> Because I'm a bad person
20:45:45 <Bike> "An important feature of the implementation of Pascal-FC is the random switching between user processes incorporated into the run-time system. This provides an excellent simulation of true parallelism and invariably finds bugs in poorly structured programs. " nice
20:46:02 <Bike> pol ee nom ee ul
20:46:24 <ion> poh-lay-nor-mee-hal
20:46:25 <fizzie> "poly|no|mial" says LaTeX for allowed hyphenation points, but maybe that's not quite the same thing.
20:46:26 <Vorpal> Taneb, are you skipping sounds then??
20:46:45 <Vorpal> Taneb, is that common with native speakers?
20:47:03 <int-e> Taneb: wait, you dropped the 'ly'?
20:47:31 <int-e> Taneb: deliberately?
20:48:01 <olsner> if saying it sloppily I might go as far as pol-nom-yal
20:48:02 <Taneb> No, it's how I pronounce it when I'm not thinking and talking quickly
20:48:06 <doesthiswork> for me its 5 syllabls but since english is stress timed the lengths are 1, .5, 1, .5, .5
20:48:54 <int-e> somehow this lack of agreement makes me happy
20:49:18 -!- Phantom_Hoover has joined.
20:50:18 <Taneb> int-e, but I would say 5 if I hadn't said it under my breath
20:51:09 <olsner> that's an awful lot of syllables
20:51:30 <doesthiswork> it sounds like olsner is consitantly reducing unstressed close unrounded vowels
20:52:01 <int-e> olsner: does that make it a syllabus?
20:52:06 <Vorpal> fizzie, how do you ask LaTeX for hypen-points?
20:52:52 <Taneb> Right, this language is shaping up...
20:53:04 <fizzie> Vorpal: LuaLaTeX + \usepackage{showhyphens}.
20:53:43 <fizzie> Vorpal: Though IIRC it prints them in the "overfull hbox" errors too.
20:54:03 <Vorpal> right, that is not quite as useful
20:55:03 <fizzie> Oh, there's a (TeX-level) command for it, though it doesn't end in the document.
20:56:13 <fizzie> http://sprunge.us/jHNO like that.
20:57:19 <olsner> doesthiswork: I think I mostly just articulate poorly
20:58:10 <HackEgo> [wiki] [[Boxy]] http://esolangs.org/w/index.php?diff=39376&oldid=39375 * Zerk * (+1433) Clarified whitespace, added section /* Macros */ and the relevant specification.
20:59:59 <mroman> Can I encode numbers as "state"?
21:00:04 <Sgeo> Reading a Reddit thread about ramen noodles
21:00:23 <Sgeo> As far as I can tell, they're saying the big danger is lack of nutrients if it's eaten exclusively
21:00:34 <Taneb> Oh man, this is going to be really awkward
21:00:36 <HackEgo> [wiki] [[Boxy]] M http://esolangs.org/w/index.php?diff=39377&oldid=39376 * Zerk * (+2) clarification
21:00:42 <mroman> I can treat "increment" as a transition from state 0 to 1, from state 1 to 2 from state 2 to 3 and so on
21:00:43 <Taneb> Not the ramen, the esolang I'm making
21:00:43 <olsner> yes, sgeo, you can't live only on ramen noodles
21:00:55 <Taneb> Man cannot live on ramen alone
21:01:08 <olsner> it's basically wheat flour, a small amount of fat and spices
21:01:47 <Sgeo> But if I have a chicken sandwich for lunch, I shouldn't be too concerned if I have ramen for dinner?
21:01:47 <mroman> but if I wanted two numbers I'd need a0,a1,a2... and b0,b1,b2... and so on
21:02:42 <Vorpal> Sgeo, in general you need a varied diet.
21:02:43 <olsner> Sgeo: it's usually the sum of nutrients that matters, and no normal foods have negative value
21:03:09 <Vorpal> olsner, also varied diet to get all the required vitamins and so on
21:03:55 <Sgeo> So, if for dinner sometimes I have a chicken sandwich, sometimes pizza, sometimes ramen, sometimes instant pasta, is that sufficiently varied/
21:04:28 <pikhq> Wow, you eat like a third grader.
21:04:54 <Taneb> And yet you still eat better than I do during termtime
21:05:09 <Vorpal> Sgeo, what about... salads?
21:05:30 <Sgeo> I used to eat pasta + parmesan cheese every night
21:05:46 <Sgeo> But I really don't want to cook in this horrific place
21:05:55 <Vorpal> I know I eat too one-sided but still I eat better than that
21:06:10 <olsner> Sgeo: then how will you feed yourself?
21:06:17 <Sgeo> olsner: eating out every day?
21:08:29 <Vorpal> How the hell does /home have 19 GB free?
21:09:25 <Sgeo> I could go start buying bananas from 7-eleven
21:09:28 <HackEgo> df: Warning: cannot read table of mounted file systems: No such file or directory \ Filesystem 1K-blocks Used Available Use% Mounted on \ - 40573996 6747216 31769748 18% /hackenv
21:09:31 <olsner> my (other) /home has 305MB
21:09:43 <HackEgo> df: cannot read table of mounted file systems: No such file or directory
21:09:50 <HackEgo> rootfs / rootfs rw 0 0 \ none /bin hostfs ro,nosuid,relatime,/bin/ 0 0 \ none /usr hostfs ro,nosuid,relatime,/usr/ 0 0 \ none /dev hostfs ro,nosuid,relatime,/dev/ 0 0 \ none /opt hostfs ro,nosuid,relatime,/opt/ 0 0 \ none /lib hostfs ro,nosuid,relatime,/lib/ 0 0 \ none /sbin hostfs ro,nosuid,relatime,/sbin/ 0 0 \ none /lib64 hostfs ro,nosuid,relati
21:09:59 <HackEgo> cat: /etc/mtab: No such file or directory
21:10:18 <Sgeo> Maybe I should do that now
21:10:27 <Sgeo> Instead of eating candy as a hunger fixer
21:10:50 <Sgeo> I do seem to have found the one candy that I can buy and it actually lasts longer than a few hours
21:10:55 <int-e> ``cut -d\ -f2 /proc/mounts
21:10:56 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `cut: not found
21:11:11 <fizzie> olsner: That's not quite "my other car is a Porsche".
21:11:22 <fizzie> int-e: You missed a space.
21:11:38 <int-e> `` cut -d\ -f2 /proc/mounts
21:11:38 <HackEgo> / \ /bin \ /usr \ /dev \ /opt \ /lib \ /sbin \ /lib64 \ /hackenv \ /hackenv/.hg \ /etc/alternatives \ /etc/java-6-openjdk \ /home/hackbot/hackbot.hg/multibot_cmds/lib \ /tmp \ /proc \ /sys
21:11:59 <int-e> `` echo $(cut -d\ -f2 /proc/mounts)
21:12:00 <HackEgo> / /bin /usr /dev /opt /lib /sbin /lib64 /hackenv /hackenv/.hg /etc/alternatives /etc/java-6-openjdk /home/hackbot/hackbot.hg/multibot_cmds/lib /tmp /proc /sys
21:12:03 <olsner> fizzie: this /home has a whopping 34GB though
21:12:12 <int-e> that's a lot of mount points :)
21:12:21 <olsner> or really it's the pool that has it now, but /home can have it if it needs it
21:12:33 <fizzie> int-e: They're all UML fakey-mounts, to be fair.
21:13:06 <int-e> /etc/alternatives. interesting. :)
21:13:24 <fizzie> `run cat /home/hackbot/hackbot.hg/multibot_cmds/lib/sandbox | paste
21:13:26 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.18813
21:13:34 <fizzie> There are some internals there, if you're curious.
21:13:48 <Taneb> Right, I think I have give or take defined this language
21:14:17 <Taneb> It ought to have an implementation just so I can show people what exactly I mean
21:14:24 <olsner> hmm, curious use of python, that looks like a shell script
21:14:39 <Taneb> Ack! It's nowhere near TC
21:15:08 <fizzie> olsner: At least there's no shell injection whatnots with subprocess.call if you mess up quoting or something.
21:15:18 -!- JesseH2 has quit (Quit: Leaving).
21:17:04 <fizzie> It's quite the command-line, though; `foo -> nice ... umlbox ... env ... limits ... foo.
21:19:07 <olsner> four other tools that also need to not mess up quoting
21:20:13 <fizzie> The /etc/alternatives comes from the umlbox --base-mounts flag; it automatically mounts (as read-only) the host directories /usr, /bin, /sbin, /lib, /lib32, /lib64, /etc/alternatives and /dev.
21:20:27 <olsner> hmm, except they're not shell scripts obviously (probably)
21:20:29 <elliott> that's a shell script because of me, I think
21:21:07 <elliott> fizzie: cat ... | paste === url ...
21:21:18 <fizzie> elliott: Except you can't do `url on that file.
21:21:52 <fizzie> It's too special for that.
21:22:49 <ion> http://freshbsd.org/commit/openbsd/e5136d69ece4682e6167c8f4a8122270236898bf
21:23:14 <fizzie> Though it's pretty much identical to https://github.com/GregorR/hackbot/blob/master/multibot_cmds/lib/sandbox except for the commented-out /var/irclogs.
21:26:24 <fizzie> It's probably mean of me, but I keep hoping the OpenBSD folks will do something like the Debian no-entropy-for-you while they're stripping stuff of of OpenSSL.
21:27:24 <olsner> I consider it inevitable that some bugs will be introduced
21:27:27 -!- Patashu has joined.
21:27:30 <Sgeo> bought bananas
21:28:32 <olsner> but they might also find and fix them (easier?) now that the code is less bananas
21:30:37 <Bike> fizzie: the debian what
21:31:18 <fizzie> Bike: https://www.debian.org/security/2008/dsa-1571
21:31:24 <fizzie> I'm sure you heard of it.
21:32:03 <Bike> i don't think i even used linux in 2008
21:32:33 <fizzie> Debian patched some Valgrind warnings out of their OpenSSL, and incidentally also made all keys generated with that OpenSSL trivially guessable, more or less.
21:33:29 <fizzie> There were a lot of weak SSH keys.
21:33:46 <newsham> olsner: as in unfound bug? or do bugs that they introduce and then find and fix count?
21:34:12 <newsham> olsner: i imagine there will be more bugs inadvertantly fixed than inadvertantly introduced.. but I guess we'll see
21:34:48 <Vorpal> fizzie, ssh? I thought OpenSSL was pretty much separate from OpenSSH?
21:35:07 <pikhq> OpenSSH uses OpenSSL for its crypto though.
21:35:09 <newsham> openssh uses primitives from openssl including random numbers
21:35:25 -!- oerjan has joined.
21:35:42 <pikhq> Because OpenSSL is not an SSL library, it is a complete library for everything even superficially related to crypto.
21:35:55 <Vorpal> Yes I know, libcrypto and libssl
21:36:01 <pikhq> Including, of course, SSL-without-encryption.
21:36:04 <Vorpal> I didn't know that openssh used libcrypto though
21:36:07 -!- Patashu_ has joined.
21:36:07 -!- Patashu has quit (Disconnected by services).
21:36:39 <fizzie> `run ldd $(which ssh-keygen) | grep crypto
21:36:39 <HackEgo> ldd: missing file arguments \ Try `ldd --help' for more information.
21:36:46 <Vorpal> Also OpenSSL has a terrible design, I used a tiny bit of libcrypto myself
21:36:56 <Vorpal> It is a terribly designed API
21:37:21 <olsner> newsham: I sure hope there will be more things fixed than broken :)
21:37:33 <Vorpal> Or rather, there are like 5 versions of the API, and it isn't clear which one is the recommended one generally
21:37:34 <pikhq> OpenSSL is a fun way to learn C.
21:37:56 -!- doesthiswork has quit (Quit: Page closed).
21:37:58 <Vorpal> pikhq, The internal coding style guideline is even worse
21:38:04 <pikhq> It has guidelines?
21:38:14 <Vorpal> pikhq, well the *result* is terrible at least
21:38:18 <Vorpal> I assume there are guidelines
21:38:45 <oerjan> fizzie: hm i was wondering why deadfish got so low on that center thing
21:39:06 <oerjan> then i remembered that deadfish splitup...
21:39:11 <fizzie> StartSSL allowed for a free rekeying of affected certificates back when that Debian thing happened.
21:39:26 <oerjan> and then i remembered something else. there are a lot of section links into deadfish.
21:39:28 <fizzie> (They're sticking to their $24.90/cert fee for any heartbleed-affected ones, however.)
21:40:51 <int-e> is there any human involved in "earning" that money?
21:41:20 <fizzie> I think they do have a human looking over revocation requests, yes.
21:41:33 <Vorpal> /usr/bin/ccache: error while loading shared libraries: libz.so.1: cannot open shared object file: Error 24
21:41:40 <fizzie> Because Twitter has it some people have gotten their revocations for free, even if the official policy is that it's not.
21:41:54 <Vorpal> /lib/x86_64-linux-gnu/libz.so.1
21:42:13 <oerjan> ok, why doesn't "this links here" tell whether links are section links twh
21:42:15 <Vorpal> Huh, ccache --help works though
21:42:53 <fizzie> Vorpal: #define EMFILE 24 /* Too many open files */
21:43:12 <fizzie> (Assuming you have matching error numbers.)
21:43:36 <Vorpal> That is per process right?
21:44:12 <fizzie> oerjan: Oh, I probably should've considered section links as links to the page itself.
21:44:27 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Deadfish implementations]]": I just realized the move broke section links to the original.
21:44:37 -!- AnotherTest has quit (Ping timeout: 258 seconds).
21:44:41 <Vorpal> oh wait, ccache resolves to ccache-swig in the end
21:44:47 <Vorpal> $ file -s /usr/bin/ccache-swig /usr/bin/ccache-swig2.0
21:44:47 <Vorpal> /usr/bin/ccache-swig: symbolic link to `ccache-swig2.0'
21:44:47 <Vorpal> /usr/bin/ccache-swig2.0: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked (uses shared libs), for GNU/Linux 2.6.26, BuildID[sha1]=0x390684d9747dd1b7b2ea1a4e842962607f7306cb, stripped
21:44:55 <Vorpal> running ccache-swig2.0 doesn't
21:45:04 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=39378&oldid=39237 * Oerjan * (+59486) Undo revision 39237 by [[Special:Contributions/Nooodl|Nooodl]] ([[User talk:Nooodl|talk]]) (Breaks section links and half the point of the article)
21:45:09 <int-e> `` perl -e 'use POSIX;print strerror(24)."\n"'
21:45:53 <Vorpal> fizzie, lol, swig provides ccache-swig
21:45:59 <Vorpal> and actual ccache is not installed
21:47:20 <olsner> I wonder what ccache-swig actually does
21:47:36 <Vorpal> man page seems to suggest it is ccache with swig-support
21:48:36 <fizzie> oerjan: Do you have opinions on whether "that center thing" should optimally look at other namespaces in addition to main and Category? (E.g. User.)
21:49:52 <olsner> Vorpal: try installing the real ccache?
21:50:20 <oerjan> fizzie: possibly Esolang:
21:50:35 <Vorpal> it replaced the swig one
21:51:37 <Bike> `run echo hi; echo $?
21:51:56 <fizzie> Strongly connected component now 1303 vertices when considering also Esolang: and converting section links to links of the page.
21:52:04 <oerjan> fizzie: oh and you aren't including the sidebar links are you?
21:52:13 <oerjan> those also feel dubious
21:52:20 <fizzie> No, just [[...]] in the article source.
21:52:44 <fizzie> (Which also means templates are not... what's the fancy MediaWiki word for expanding them?)
21:53:01 <fizzie> Transclusion? No, that was expanding with some particular semantics.
21:53:11 <fizzie> (I'm no kind of MediaWiki admin.)
21:53:51 <int-e> https://www.mediawiki.org/wiki/Help:Templates "Templates are standard wiki pages whose content is designed to be transcluded (embedded) inside other pages."
21:55:23 <olsner> what's the difference between transclusion and inclusion then?
21:55:43 <Vorpal> I would like to see some sort of general "distribution" engine. That worked on stuff other than compilers. It could work by creating a virtual environment on the remote machine, pulling additional files if they were opened (and then learning the behaviour of commands for the future, to avoid sending un-needed files, but send all needed files in advance)
21:56:22 <Vorpal> So it would send over the invoked binary and all dependencies if they didn't exist locally, probably building a hash-directory of files in /lib and so on
21:56:30 <int-e> olsner: ironically you can preclude text from transclusion using <noinclude></noinclude> markup
21:56:53 <Vorpal> Some sort of fuse thing could probably do it? Maybe uml?
21:57:14 <int-e> . o O ( playing cludeo )
21:57:22 <fizzie> oerjan: Though I don't think incoming links *to* Deadfish should (and didn't seem to, after all) affect its (directed-graph) closeness centrality much, since it's defined as the average shortest-path distance to any other page when starting from Deadfish.
21:58:16 <olsner> I think icecc is pretty close, it uses an archive that becomes a chroot environment for the command to run
21:58:50 <fizzie> It did bump the Markov chain stationary distribution number of Deadfish up from 0.000647 to 0.000648, however!
21:58:55 <Vorpal> olsner, having trouble finding the icecc you refer to
21:59:00 <olsner> but it has code for parsing compiler command lines and doing preprocessing locally, and such... so you'd have to modify it to do other things with it
21:59:23 <oerjan> <Vorpal> why does "Befunge/index.php" exist? <-- i vaguely think that's one of the "taken over after a spammer created it" pages
21:59:23 <Vorpal> olsner, oh okay, yeah that helped find the correct one
21:59:31 <Vorpal> oerjan, as elliott said
21:59:31 <HackEgo> [wiki] [[Special:Log/newusers]] create * CyrillicFez * New user account
22:00:34 <Vorpal> oerjan, yeah it just seems like a centralized distcc really
22:01:39 <HackEgo> [wiki] [[ArnoldC]] N http://esolangs.org/w/index.php?oldid=39379 * CyrillicFez * (+192) Created page with "ArnoldC is an esoteric programming language created with Scala by Lauri Hartikka. The source is available [https://github.com/lhartikk/ArnoldC here], along with tutorials and ..."
22:02:50 <olsner> last time I checked, distcc only worked on identical machines, but maybe icecc and distcc are more equivalent now
22:03:28 <newsham> has anyone written AES in bf yet?
22:03:44 <Vorpal> olsner, yeah distcc does that, unless you do a cross compiler, in which case only the cross system root needs to be identical
22:04:03 <Vorpal> olsner, and that is only for pump mode, in otherwise just the compiler needs to be identical
22:04:17 <Vorpal> olsner, I was thinking some sort of transparent thing that would monitor resources used by the command to determine what needed transferring, So if it tried to open /usr/share/foo and that was not already sent over, it would be on demand. Then it would remember that access for the future, and if it was accessed consistently it would send that over on every run and/or cache it
22:04:55 <Vorpal> olsner, dependency extraction from command line arguments would be tricky though
22:05:15 <Vorpal> it could detect if a file was used that was mentioned on the command line, but I'n not sure about includes and such,
22:05:23 <fizzie> Few other random esolang statistics: maximum out-degree 858 ("Language list", such a surprise); maximum in-degree 376 ("Category:Languages", ditto).
22:05:32 <Vorpal> I guess you could manually write extractors for that, but then you would be back to specially handling all of that
22:05:50 <int-e> fizzie: so who are the runner-ups?
22:05:54 <Vorpal> fizzie, what about non-category/list ones?
22:06:09 <fizzie> Just a moment, I'll make a top-ten or so.
22:06:43 <int-e> out of curiositty, how many edges do you have at the moment?
22:07:26 <fizzie> 10815 edges between 1781 articles, when not doing the strongly-connected component restriction.
22:07:55 <fizzie> Or 10143 edges if collapsing multiple links to one.
22:08:15 <int-e> (so there's no trouble with keeping them all in memory then :-) )
22:08:21 <Vorpal> olsner, yeah icecream is nice, but not quite where I want it
22:08:33 <fizzie> Not yet. There's even no trouble with keeping a non-sparse adjacency matrix.
22:08:59 <fizzie> It's certainly no en.wikipedia, that's for sure.
22:09:08 <newsham> automatic dependency tracking is awesome
22:09:25 <newsham> its the magic that lets CUPS get installed no matter what program you want to install
22:09:31 <Vorpal> newsham, exactly, so a combination of icecream and tup I guess
22:10:10 <Vorpal> newsham, I was looking at it for a different context though
22:10:42 <newsham> magic: cabal install cabal-install
22:10:51 <int-e> newsham: there's that awful application side of cups, libcups, that tends to pull it in :/
22:11:22 <fizzie> Oh, right, http://sprunge.us/PDcj for a top-50 out/in-degrees.
22:11:39 <newsham> inte: also most packages dont need it but lots of them have it enabled in the default "./configure" so all the binary packages have it as a dep
22:11:48 <newsham> even though there will never be a printer hooked up to my computer
22:12:17 <Vorpal> fizzie, so basically Brainfuck in both cases for actual esolang
22:12:27 <fizzie> Many of those 461 in-edges to "Esoteric programming language" are probably first-paragraph "X is a [[esoteric programming language]] ..." stuff.
22:12:30 <int-e> oh wow, when did the firefox threads get distinct names?
22:12:37 <Vorpal> newsham, so use gentoo
22:12:41 <Vorpal> newsham, where you can turn it off
22:12:46 <Vorpal> Phantom_Hoover, what is that
22:12:55 <newsham> vorpal: what makes you think i was talking about linux?
22:13:11 <Vorpal> Phantom_Hoover, that was a joke btw
22:13:18 <newsham> vorpal: why do you hate me?
22:13:19 <Vorpal> Phantom_Hoover, also there are good VPN services, I can recommend a couple
22:13:28 <Vorpal> newsham, do I? That was news to me
22:13:34 <int-e> (I was surprised by http://sprunge.us/RdUT )
22:13:36 <newsham> vorpal: you wanted to gen2 me :(
22:13:39 <Vorpal> newsham, anyway what *are* you using then
22:13:57 <Vorpal> newsham, it was a joke, you could just turn off CUPS there
22:14:05 <Vorpal> I stopped using gentoo years ago
22:14:16 <newsham> what do you need vpn for? if its for avoiding geolocation, i know a proxy that is better than general proxy since it will geolocate you diff places depending on which site you hit
22:14:31 <newsham> vorpal: freebsd (also ubuntu)
22:14:52 <fizzie> int-e: Huh, that's so fancy. Thunderbird (well, Icedove) and Chromium threads have reasonable names, too.
22:14:53 <Vorpal> newsham, well okay, with ports can't you turn flags on and off? I don't remember
22:15:21 <newsham> vorpal: you can do it manually in ports, but if you use precompiled packages you will get cups
22:15:28 <newsham> its the kevin bacon of packages
22:15:42 <Vorpal> | | | |-mate-panel-+-chromium-+-chrome-sandbox---chromium---chromium---3*[chromium---{chromium}]
22:15:43 <Vorpal> | | | | | |-chromium-+-chromium
22:15:43 <Vorpal> | | | | | | `-3*[{chromium}]
22:15:43 <Vorpal> | | | | | `-48*[{chromium}]
22:15:48 <Vorpal> that doesn't look like reasonable names
22:16:01 <fizzie> Vorpal: Possibly new, then: http://sprunge.us/NANf
22:16:06 -!- Patashu has joined.
22:16:19 <Phantom_Hoover> <newsham> what do you need vpn for? if its for avoiding geolocation, i know a proxy that is better than general proxy since it will geolocate you diff places depending on which site you hit
22:16:30 <Phantom_Hoover> geolocation isn't the issue, it's the isp blocking the site altogether
22:17:04 <newsham> then vpn it is.. there are lots of them.. usually around $10/mo, sometimes a little cheaper
22:17:09 <Vorpal> fizzie, not debian stable I guess
22:17:20 <fizzie> Vorpal: No, this is on jessie.
22:17:20 -!- Patashu_ has quit (Ping timeout: 250 seconds).
22:17:47 <fizzie> "Chromium 33.0.1750.152 Debian jessie/sid (256984)"
22:18:05 <Vorpal> newsham, doesn't a proxy work for that?
22:18:22 <int-e> I'm using jessie here, too.
22:18:39 <newsham> vorpal: if you use a dns-based proxy it can proxy through different geo-sites for different services. vs a vpn where you pop out at a fixed point for the duration of your vpn tunnel
22:18:59 <newsham> phantom: i dont use it to pirate
22:19:30 <newsham> i use it to stream tv from uk, fr, ca, ...
22:19:58 <newsham> through the legit tv station websites
22:20:00 <Vorpal> Phantom_Hoover, see /msg
22:20:10 <newsham> (they just geo-lock it based on ip addr)
22:21:30 <fizzie> newsham: Presumably that's still pirating. (At least the Finnish public broadcasting company's site geo-locks those programs they have distribution rights only for within Finland.)
22:21:33 -!- Patashu_ has joined.
22:21:33 -!- Patashu has quit (Disconnected by services).
22:21:55 <Vorpal> newsham, what proxy do you use btw?
22:22:00 <fizzie> (I guess some of them might be less discriminating.)
22:22:05 <Vorpal> I would like one in US at times
22:22:09 <newsham> fizzie: depends on who you believe. i've heard industry lawyers say that video taping tv shows is pirating and that copying your cd to mp3 files is pirating
22:22:16 <newsham> despite the us govt stating otherwise
22:22:33 <Taneb> int-e, lambdabot is breaking in -lens
22:22:43 <pikhq> newsham: Lawyers who hadn't heard of the Betamax case?
22:22:59 <newsham> vorpal: overplay.net's smartdns proxy (they also have traditional proxy, i dont use that though)
22:23:11 <Vorpal> newsham, what is the difference?
22:23:25 <newsham> pikhq: no, even lawyers who have heard of the case. the great thing about being a lawyer is that you dont have to agree with precedence or reality if your client doesnt want you to
22:23:52 <newsham> vorpal: for smartdns you just configure your dns to point to them, they give back responses for certain sites that direct you through some auto-proxies of theirs
22:24:04 <newsham> you never run a traditional vpn program on your host
22:24:09 <pikhq> Ah, right, you don't get auto-disbarred for giving advice that is the exact opposite of what precedent and law explicitly says.
22:24:29 <pikhq> Clearly a lawyer can just say "Sure, you can murder all who stand in your way".
22:24:43 <Vorpal> newsham, what about the traditonal proxy then? I assume that is a third option to the VPN
22:25:04 <newsham> pikhq: if all lawyers were required to agree with all case law there would never be any challenges to case law
22:25:04 <Vorpal> because I only see smartdns and vpn on their site
22:25:24 <Taneb> pikhq, well you CAN murder all who stand in your way.
22:25:25 <newsham> vorpal: I use smartdns. i dont use vpn.
22:25:33 <Taneb> Just you might get in a little trouble for it.
22:25:43 <newsham> pikhq: i'm sure blackwater lawyers have given out advice along those lines in the past
22:25:48 <Vorpal> newsham, right, but there was also traditonal proxy you said, I assume a normal HTTP proxy?
22:26:01 <newsham> oh, i meant traditional vpn, sorry
22:26:37 <Vorpal> newsham, what is their logging policy?
22:26:43 <newsham> dont know.. i never asked.
22:26:44 <pikhq> newsham: Note that this is a supreme court finding. Without changes in law there literally can't be challenges... By which I mean "in US legal practice, if the Supreme Court said pi was three, pi is three."
22:27:04 <newsham> vorpal: there are dozens of proxy and vpn vendors.. shop around, i'm sure some talk about logging policies
22:27:30 <newsham> pikhq: can they get disbarred for disagreeing with a supreme court hearing when talking to the press?
22:27:36 <Vorpal> right, if you just want a solid, fast and reasonably priced VPN provider in Europe I would recommend https://www.ipredator.se/
22:27:47 <newsham> that is more or less the context i was talking about.. industry people telling the press that something was illegal despite case law
22:27:49 <pikhq> No. Getting disbarred is ludicrously difficult.
22:28:10 <pikhq> You'd basically have to shit on a judge.
22:29:15 <newsham> and the judge has to disapprove
22:29:36 <int-e> Taneb: hmm, there are two zombie processes, I wonder if they have anything to do with it.
22:30:16 <Vorpal> The only issues I had with that VPN provider have turned out to be on my end. I have a non-trivial setup where only a specific user account is routed through the VPN. This is a mess of iptables and multiple routing tables to achieve.
22:30:23 -!- lambdabot has quit (Quit: brb).
22:30:36 <Vorpal> I discovered I have a race condition at boot in that setup that I haven't managed to solve
22:30:46 <pikhq> Getting disbarred also only applies to a given state... You can then go out and have a law license elsewhere.
22:31:16 <newsham> if prenda lawyers cant get disbarred, nobody can
22:31:32 <int-e> Taneb: apparently, so restarting it helped. hmm.
22:31:32 <pikhq> Also, you tend to only get disbarred by your state's bar association. i.e. an association of lawyers.
22:31:52 <int-e> (will have helped, once it's back in all channels)
22:32:22 <pikhq> Which is to say that it's about as hard to get disbarred as it is for a police officer to get charged with a crime.
22:33:50 <Taneb> I wonder if anyone's found an actual use for my groups Haskell library
22:34:38 -!- lambdabot has joined.
22:35:21 <Bike> unfortunately my current favorite supreme court ridiculousness is a consequence of facts, not pseudofact itself
22:37:17 <Vorpal> hey I found my POSIX cat in befunge again
22:37:22 <Vorpal> I should put that up somewhere
22:37:38 <pikhq> Does it handle the semantics of -u?
22:37:52 <Bike> Phantom_Hoover: do you remember the Myriad Genetics case
22:38:02 <Vorpal> pikhq, alas it is documented to the effect of tt being impossible in befunge-98
22:38:16 <Vorpal> pikhq, I don't even remember what -u does
22:38:35 <Vorpal> pikhq, Yeah you can't do that from inside befunge
22:38:41 <pikhq> i.e. no FILE* junk.
22:38:45 <pikhq> read()'s fine though.
22:38:47 <Vorpal> pikhq, why does gnu cat ignore it though
22:38:52 <Bike> The conclusion was "you can't patent DNA, but you can patent cDNA"
22:38:59 <Vorpal> pikhq, you can turn off buffering on FILE*
22:39:00 <pikhq> GNU cat uses unbuffered IO unconditionally.
22:39:11 <int-e> @run 619710.906128/86400
22:39:20 <Vorpal> pikhq, that seems inefficient
22:39:21 <Bike> which is a bit like saying you can't patent some text, but you can patent some text that you produced by copying the text you can't patent verbatim
22:39:50 <pikhq> Not really. It just passes read() a large integer, and then write()s the results of that out.
22:39:53 <Bike> supreme court can't into molecular biology
22:39:56 <Vorpal> Known bugs and limitations:
22:39:56 <Vorpal> * Due to Befunge-98's command line argument handling, double null string
22:39:56 <Vorpal> parameters will be treated as end of command line.
22:39:56 <Vorpal> * Due to Befunge-98's standard IO limitations it is impossible to implement -u.
22:40:04 <Phantom_Hoover> is cdna actually distinguishable from dna, physically?
22:40:33 <pikhq> Fairly efficient in general, though it'll be fairly inefficient if the source is something crazy that only ever writes, say, 1 byte at a time.
22:40:44 <pikhq> (which is to say, "hardly anything")
22:40:57 <Vorpal> pikhq, maybe some sort of character device?
22:41:01 <Bike> well cDNA is isolated bits rather than the whole genome
22:41:13 <pikhq> Vorpal: Not generally.
22:41:27 <pikhq> The read() call will get the contents of the kernel char device buffer. :)
22:41:41 <Bike> i'm not just not sure, practically speaking, what patenting cDNA would mean
22:41:54 <Vorpal> pikhq, it is way too sparse befunge code btw, much too readable
22:42:13 <Phantom_Hoover> Bike, and so what, because you need to use the cDNA version of a gene to do anything meaningful with it, the patent functionally covers all uses of that gene?
22:42:16 <Bike> you're not patenting the process to make cDNA, so anybody can do it, and you're not patenting the genetic information or transcription characteristics, which are not synthetic
22:42:20 <pikhq> Also, "inefficient" here means "practical IO speed of, like, 15 MB/s"
22:42:38 <Vorpal> pikhq, Also GPL3 for some reason, though I'll probably relicense it to some "do whatever, but credit me" deal
22:42:57 <Bike> Phantom_Hoover: i don't even know. the decision's stated idea was that it's because cDNA is synthetic
22:43:02 <pikhq> Which is also what you're bounded by anyways, because that's the speed of your source.
22:43:04 <Vorpal> pikhq, I have used I/O devices much faster than that
22:43:26 <Vorpal> pikhq, wasn't on a commonly available system though
22:43:57 <pikhq> Note that 1-char-at-a-time means that cat is reading from a device about that slow, meaning that it's... not exactly an issue that cat's also being slow.
22:44:14 <pikhq> So, there's no particular reason to *not* just use unbuffered IO.
22:44:17 <Bike> "This is a bit like taking a copyrighted photograph, cutting several chunks out of the middle, and calling the result a new product that is eligible for copyright." says a geneticist, since i'm not one
22:44:40 <int-e> Taneb: great, so now I can try to puzzle out why lambdabot would leave zombies behind, and how they affect @run. (by "lambdabot breaks" you did mean that @run produced (almost?) only timeouts, right?)
22:44:46 <Bike> (the comparison is a bit interesting since i'm pretty sure if you were creative enough about your cutting that would actually be copyrightable)
22:44:52 <Vorpal> pikhq, Anyway http://sprunge.us/RQIT
22:45:04 <Vorpal> pikhq, that is pretty terrible befunge-98 code
22:45:42 <Bike> also cDNA is produced in the first place with reverse transcriptase, which is natural, just not naturally applied to human mRNA
22:46:13 <Bike> i'm almost kind of glad scalia had the guts to say "ok i don't know any of this science stuff" in his opinion
22:47:56 <Vorpal> <Bike> (the comparison is a bit interesting since i'm pretty sure if you were creative enough about your cutting that would actually be copyrightable) <-- yes I think the technical term is "transformative work"
22:48:50 <Taneb> Man, why does the UK pretend it isn't European
22:49:18 <Bike> Vorpal: big fan of lhooq personally
22:49:31 <Vorpal> Bike, not sure what that is
22:49:45 <Bike> http://en.wikipedia.org/wiki/File:Marcel_Duchamp_Mona_Lisa_LHOOQ.jpg
22:50:37 <Vorpal> Bike, yes, that is possibly transformative
22:50:59 <int-e> Taneb: I know this is comedy, but have a look at the first quote here: https://en.wikiquote.org/wiki/Yes,_Minister#Episode_Five:_The_Writing_on_the_Wall
22:53:16 <Bike> it's used as an example of derivative work, i think
22:53:32 <Bike> presumably the main recontextualization is that lhooq is half-french for "her ass is hot"
23:08:01 <HackEgo> #!/usr/bin/env python \ import sys, urllib \ if len(sys.argv) <= 1: \ print "http://codu.org/projects/hackbot/fshg/" \ else: \ print ("http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/" + \ urllib.quote(sys.argv[1]))
23:08:32 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
23:25:57 -!- conehead has joined.
23:26:29 -!- boily has joined.
23:30:01 <fizzie> The diameter of the wiki is 14 nodes; there are 24 pairs of pages that need 13 hops to navigate between them: http://sprunge.us/NHaM
23:30:09 -!- DarthMater has quit (Ping timeout: 276 seconds).
23:30:44 <fizzie> (Of course there are several pairs of pages where you "can't get there from here", as they say, but ignoring those.)
23:31:05 <Bike> how big's the second-largest connected component?
23:31:15 <Bike> well, rather, how many pages are there not in the largest connected
23:32:03 <fizzie> Weakly or strongly connected?
23:32:48 <Bike> oh right digraph. uhhhh how about both
23:33:14 <fizzie> There are 1692 pages in the largest weakly connected component, and 89 pages in others, the largest of which has three (3) pages.
23:33:26 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/paste
23:34:16 <fizzie> There are 1303 pages in the largest strongly connected component, and (obviously) 478 pages in others, the lergest of which have two (2) pages. (There are four such components.)
23:34:47 -!- variable has joined.
23:34:47 -!- variable has quit (Changing host).
23:34:47 -!- variable has joined.
23:34:57 <boily> oerjan: hellœrjan. thanks for reminding me I need to update the PDF when I get home.
23:35:15 <fizzie> For the records, the non-singular strongly connected components are {"SELECT.", "SELECT./Hello World"}, {"Preposterous Programming", "Preposterous Programming Language"}, {"Postfix notation", "Prefix notation"} and {"Esolang:Community portal", "The Esoteric File Archive"}.
23:36:18 <fizzie> And the single weakly connected component of three pages is {"Chalcraft-Green train track automaton", "Chalcraft-Greene train track automaton", "ChalcraftGreen"} but that's p. boring since two of those are just redirect pages, which this script interprets as pages with a single link to the redirect target.
23:38:45 -!- yorick has quit (Remote host closed the connection).
23:39:53 -!- Patashu_ has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
23:40:09 <oerjan> `run echo test 1&>2 2&>1
23:40:26 <oerjan> maybe i should look up the syntax.
23:40:41 <fizzie> It's 1>&2 if you want fd 1 to go where fd 2 is currently going.
23:41:36 -!- nooodl has quit (Quit: Ik ga weg).
23:42:35 <fizzie> (So ... >foo 2>&1 puts both stdout and stderr to file foo, while ... 2>&1 >foo puts only stdout to foo, and stderr to where stdout used to go.)
23:43:32 <fizzie> `run rm 1 2 # let's keep things tidy here
23:46:26 <pikhq> And 2>&3 1>&2 3>&1 3>&- ;# swaps stdout and stderr.
23:47:30 -!- conehead has quit (Quit: Computer has gone to sleep).
23:48:47 <pikhq> Though also clobbers fd 3 if that happens to be open.
23:48:51 <Bike> now do a xor swap
23:50:19 <fizzie> pikhq: Don't you mean 3>&2 2>&1 1>&3 3>&- instead? At least empirically speaking that seems to work, while the former doesn't.
23:50:20 <oerjan> `fetch http://oerjan.nvg.org/url
23:50:26 <pikhq> Sorry, yes, you are correct.
23:50:26 <HackEgo> 2014-04-19 23:50:24 URL:http://oerjan.nvg.org/url [364/364] -> "url" [1]
23:50:38 <oerjan> `run chmod +x url; mv url bin
23:50:40 <pikhq> I don't tend to futz with fd redirects that much.
23:50:43 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/test
23:50:50 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/test
23:51:18 <HackEgo> File is outside hg repository
23:51:20 <fizzie> It's arguably kind of confusing that A>&B does essentially a dup2 of B into fd A.
23:51:37 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
23:51:45 <oerjan> the test may not be perfect
23:51:53 <HackEgo> bin \ dev \ etc \ hackenv \ home \ lib \ lib64 \ opt \ proc \ sbin \ sys \ tmp \ usr
23:52:16 <oerjan> `run sed -i 's/repository/repository./' bin/url
23:52:28 <pikhq> So, `url definitely doesn't handle '//' nicely.
23:52:46 <pikhq> Admittedly, '//' is approx. utterly insane.
23:53:02 <pikhq> (it is implementation-defined whether or not it is the root directory)
23:53:16 <oerjan> pikhq: um what do you mean, that is _not_ in the repository.
23:53:25 -!- Patashu has joined.
23:53:29 <fizzie> oerjan: Yes, but //hackenv/x would be.
23:53:40 <HackEgo> File is outside hg repository.
23:53:52 <pikhq> `url //hackenv/test
23:53:52 <HackEgo> File is outside hg repository.
23:54:51 <fizzie> `run sed -i -e 's|^/hack|^/+hack|' bin/url
23:54:58 -!- nooodl has joined.
23:54:58 <HackEgo> File is outside hg repository.
23:55:30 <pikhq> "As a special case, in the root directory, dot-dot may refer to the root directory itself."
23:55:41 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/test
23:56:08 <fizzie> Yes, though sneakily in a query.
23:57:13 <oerjan> well that still doesn't handle .. etc.
23:57:50 <fizzie> os.path.abspath could probably do it, but really...
00:07:04 <oerjan> ok let's say that's enough then
00:12:37 <oerjan> `run echo hi | TEST="" cat "$TEST"
00:12:38 <HackEgo> cat: : No such file or directory
00:13:09 <oerjan> is there a way to make no argument when the string is empty?
00:14:40 <oerjan> `run echo hi | TEST="hi ho" cat "$TEST"
00:14:40 <HackEgo> cat: : No such file or directory
00:15:27 <oerjan> `run echo hi | TEST="hi ho" echo "$TEST"
00:15:40 <oerjan> `` echo hi | TEST="hi ho" echo "$TEST"
00:15:53 <oerjan> why did it think that was the syntax
00:17:08 <oerjan> `run echo "test" >"hi ho"
00:17:15 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/hi%20ho
00:21:47 <oerjan> oh i can just use - as default
00:24:06 -!- impomatic has quit (Ping timeout: 276 seconds).
00:24:16 <oerjan> `echo hi | run cat -- -
00:24:21 <oerjan> `run echo hi | run cat -- -
00:24:21 <HackEgo> bash: run: command not found
00:24:30 <oerjan> `run echo hi | cat -- -
00:24:45 <oerjan> maybe brain isn't entirely working.
00:25:33 <int-e> `` function f { echo /$1/ /$TEST/; }; TEST=23; TEST=42 f $TEST
00:26:55 -!- ^v has quit (Read error: Connection reset by peer).
00:27:23 -!- ^v has joined.
00:37:35 <kmc> "One rapper likes big butts and cannot lie. One rapper likes small butts and always lies. One rapper likes all butts but shares your inability to assess butt size, and will answer yes or no at random if asked whether a butt is big or small."
00:37:40 <kmc> http://ethicalwerewolf.blogspot.com/2011/02/puzzle-about-your-butt.html
00:39:08 <kmc> i got there from http://lesswrong.com/lw/acy/acausal_romance/ which I got by googling "acausal sex" which I'm going to blame lexande for
00:41:38 -!- conehead has joined.
00:44:35 <oerjan> `fetch http://oerjan.nvg.org/paste
00:44:38 <HackEgo> 2014-04-20 00:44:36 URL:http://oerjan.nvg.org/paste [246/246] -> "paste.1" [1]
00:45:12 <HackEgo> /hackenv/paste.1: line 4: syntax error near unexpected token `else' \ /hackenv/paste.1: line 4: `else'
00:45:42 <oerjan> `fetch http://oerjan.nvg.org/paste
00:45:43 <HackEgo> 2014-04-20 00:45:41 URL:http://oerjan.nvg.org/paste [255/255] -> "paste.2" [1]
00:46:00 <HackEgo> /hackenv/paste.1: line 4: syntax error near unexpected token `else' \ /hackenv/paste.1: line 4: `else'
00:46:08 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/test
00:46:25 <oerjan> `./paste.2 /hackenv/url
00:46:26 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/url
00:46:48 <oerjan> `run echo test | ./paste.2
00:46:50 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.29682
00:48:02 <oerjan> `paste /home/hackbot/hackbot.hg/multibot_cmds/lib/sandbox
00:48:02 <HackEgo> File is outside hg repository.
00:48:35 <oerjan> `./paste.2 /home/hackbot/hackbot.hg/multibot_cmds/lib/sandbox
00:48:37 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.20962
00:49:11 <oerjan> `run mv paste.2 bin/paste; rm paste.1
00:50:49 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
00:52:59 <oerjan> fizzie: so now `paste will fallback to the piping method for files outside /hackenv
00:56:09 <oerjan> int-e: originally it always used the piping method, but then i realized a long time ago it was stupid to copy files which were already in the repository.
00:56:54 <oerjan> but i didn't bother to treat the special case of a file name which was _outside_ it.
00:57:27 -!- conehead has quit (Quit: Computer has gone to sleep).
01:12:21 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=39380&oldid=39378 * 72.28.222.28 * (+80) Added makey-makey interpeter
01:18:08 <Bike> http://www.synacktiv.com/ressources/TCP32764_backdoor_again.pdf security
01:20:19 -!- Gregor has quit (Quit: Coyote finally caught me).
01:21:08 -!- Gregor has joined.
01:23:28 <kmc> birdman kicked my ass
01:24:59 <HackEgo> beltercincoin nhofondcoin hunterconveyorcoin brevcoin korzacoin beatcoin 59074250346.9987377coin nufcoin grincoin bulicoin 0x2903coin exancoin pavitcoin octycoin convcoin villcoin musgescacoin franocoin itformcoin afficcoin
01:26:59 <boily> we're going to have our own Québecoin → http://journalmetro.com/actualites/national/481461/le-quebec-aura-sa-monnaie-nationale-virtuelle/
01:29:05 <int-e> how would you deliever 59074250346.9987377 coins?
01:54:04 <int-e> Ah, the Day of the Tentacle way.
01:55:23 -!- DarthMater has joined.
01:56:11 <kmc> this is one of the few situations where fake barf *isn't* useful
01:56:25 -!- DarthMater has quit (Client Quit).
02:08:43 -!- shikhout has joined.
02:11:35 -!- shikhin has quit (Ping timeout: 252 seconds).
02:11:37 -!- shikhout has changed nick to shikhin.
02:24:39 -!- boily has quit (Quit: SHEEPY CHICKEN).
02:37:17 -!- nooodl has quit (Remote host closed the connection).
02:38:00 <oerjan> :t let (.:) = (.).(.) in (.: sequence)
02:38:03 <lambdabot> ([a1] -> c) -> [a -> a1] -> a -> c
02:40:07 <Bike> well i'm confused.
02:40:31 <oerjan> what is confusing you.
02:40:52 <Bike> how flip sequence exists
02:41:10 <oerjan> by the power of the (->) a Monad instance.
02:41:24 <Bike> ohhhhh. that's kinda nasty
02:41:48 <oerjan> yeah but it's the simplest way to apply all of a list of functions to a value.
02:42:21 <lambdabot> Functor f => f (a -> b) -> a -> f b
02:42:37 <oerjan> unless you use that one from lens.
02:43:48 <oerjan> i am hoping they will add ?? to Data.Functor.
02:44:31 <oerjan> and & to Data.Function
02:44:50 <oerjan> hm perhaps i should check if they have
02:45:02 <elliott> it was decided against a while ago
02:46:45 <oerjan> i think ?? should belong in the Functor/Applicative hierarchy, it's just a missing variant of <$> <*>
02:47:06 <oerjan> although it's of course badly named for that
02:47:38 <Bike> surely it is badly named in general
02:48:31 <oerjan> but alas the naming scheme for functor and applicative operators doesn't imply any obvious spot to put it.
02:49:13 <oerjan> because all of <* *> <$ $> have been taken for something else
02:49:50 <oerjan> ideally you'd have made <$> something assymetric that you could have mirrored
02:52:55 <lambdabot> ‘%’ (imported from Data.Ratio), ‘%~’ (imported from Control.Lens)
02:53:05 <lambdabot> Profunctor p => Setting p s t a b -> p a b -> s -> t
02:53:05 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
02:53:30 <lambdabot> (MonadState s m, Profunctor p) => Setting p s s a b -> p a b -> m ()
02:53:41 <lambdabot> ‘==’ (imported from Data.Eq), ‘#~’ (imported from Control.Lens),
02:53:48 -!- ^v has joined.
02:53:53 <kmc> oerjan: <€>
02:57:33 -!- Sorella has quit (Quit: It is tiem!).
03:01:22 <elliott> oerjan: ski wishes (<$>) was (<$), I think
03:07:13 -!- doesthiswork has joined.
03:12:34 <oerjan> elliott: that's still not a logical way to take care of the whole set.
03:13:05 <elliott> I remember now, he wanted (<*>) = (<$>)
03:13:14 <elliott> so fmap would be (<$) and I don't think he cares about (<*)/(*>)
03:13:24 <elliott> he thought (<*>) should be liftA2 (*) I think :P
03:13:35 <elliott> (since (<$>) would be liftA2 ($))
03:13:55 <oerjan> i think in that case it would actually be more logica to let fmap be $> if current (<*>) were <$>
03:14:23 <oerjan> because leaving out a < or > would then mean the argument on that side is pure
03:14:57 <oerjan> and then ?? would be <$
03:15:36 <elliott> (<$>) for ap would make applicative style code even uglier than it is now though.
03:16:31 <oerjan> in order to fit current <$ $> <* *> into that system it would be necessary to have operators for const and flip const to put inside
03:17:33 -!- adu has joined.
03:21:28 <oerjan> |*| for <*>, *| for <$>, |>| for *> (and >>), |<| for <*, |> for $> and <| for <$
03:22:20 <Sgeo> Why was & decided against?
03:22:54 <Bike> way too squiggly
03:23:19 <oerjan> if a recent discussion someone said that they've decided against including trivially writeable operators
03:23:34 <Bike> trivial, the greatest term
03:23:34 <oerjan> or trivial operators which people can write themselves
03:24:09 <Sgeo> :/ standardization is a good thing
03:24:30 <Sgeo> Also, what of trivially writable functions?
03:24:44 <Bike> what's the diff
03:25:21 <Sgeo> operators = infix by default, non-operators = prefix by default
03:26:06 <Sgeo> But they obviously haven't decided that id should be removed
03:27:52 <oerjan> it's not about removing stuff, it's about not adding more
03:28:29 <oerjan> because there are too _many_ things that can be added.
03:31:17 <elliott> oerjan: you might as well just add idiom brackets, when getting that radical
03:36:21 -!- adu has quit (Quit: adu).
03:40:11 <Sgeo> How about idiom brackets with tagging 'impure' instead of 'pure' values (yeah yeah, bad nominclature)
04:02:17 <oerjan> no, nominclature is bad nomenclature hth
04:16:18 -!- doesthiswork has quit (Ping timeout: 240 seconds).
05:09:03 -!- tromp has quit (Read error: Connection reset by peer).
05:23:00 -!- shikhin has quit (Ping timeout: 252 seconds).
05:30:18 -!- copumpkin has quit (Ping timeout: 240 seconds).
05:35:28 -!- copumpkin has joined.
05:37:27 -!- oerjan has quit (Quit: leaving).
06:00:11 <Sgeo> http://www.icanbarelydraw.com/comic/2702
06:02:00 <Sgeo> Hmm, I seem to have stumbled upon some arc looking at modern day money as though it was new and bitcoin was standard
06:02:05 <Bike> comic not funny. furthermore, they can't draw at all. i demand a refund.
06:17:50 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:25:00 -!- impomatic has joined.
07:12:52 -!- conehead has joined.
07:40:10 -!- variable has changed nick to function.
07:49:29 <shachaf> Taneb: have you heard of the Taneb-calculus
07:50:33 <Taneb> But Taneb isn't a greek letter!
07:50:58 <shachaf> shachaf never said Taneb was a greek letter
07:57:04 -!- AnotherTest has joined.
08:04:30 -!- tromp has joined.
08:06:06 <fizzie> @tell oerjan If we're going to be that fancy, I fixed `url to use os.path.abspath so that e.g. `url /bin/../hackenv/test works.
08:11:22 -!- xpte has quit (Quit: Connection closed for inactivity).
08:13:03 -!- MindlessDrone has joined.
08:17:52 -!- conehead has quit (Quit: Computer has gone to sleep).
08:23:36 <HackEgo> ls: cannot access /var/irclogs/_esoteric/????-??-??.txt: No such file or directory \ not lately; try `seen Phantom_Hoover ever
08:47:02 -!- ais523 has joined.
08:47:35 <ais523> :t \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))
08:47:38 <ais523> ) :t \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))
08:47:38 <jconn> ais523: |syntax error
08:47:39 <jconn> ais523: | :t\m->\n->(\f->f(m)(f(n)(\z->z)))(\x->( \y->y))
08:47:44 <ais523> ( :t \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))
08:47:48 <idris-ircslave> :t \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))<EOF>
08:47:49 <lambdabot> parse error (possibly incorrect indentation or mismatched brackets)
08:48:00 <ais523> ( \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))
08:48:00 <idris-ircslave> \m -> \n -> (\f -> f(m)(f(n)(\z -> z)))(\x -> (\y -> y))<EOF>
08:48:08 <ais523> how do I do a lambda in Idris?
08:48:18 <ais523> ( \m => \n => (\f => f(m)(f(n)(\z => z)))(\x => (\y => y))
08:48:19 <idris-ircslave> (input):1:40:When elaborating an application of constructor __infer:
08:48:32 <ais523> I think that's correct syntax, but perhps a buggy interp
08:48:51 <ais523> either that or it's trying to evaluate a higher-order function without arguments available
08:51:51 <ais523> btw, any Haskellites around here, is it possible to get Haskell to infer the correct type for that term (t -> t1 -> t2 -> t2)?
08:55:02 <shachaf> Oh, I see, you want a rank-2 type for the \f lambda.
08:59:13 <shachaf> Your Haskell code is very unidiomatic.
08:59:32 <shachaf> You can annotate the type explicitly to get the type you want.
08:59:56 <shachaf> :t \m n -> ((\(f :: forall a x. a -> x -> x) -> f m (f n id))) (\x -> id)
09:02:05 <ais523> shachaf: it's not Haskell code, it's typed lambda calculus
09:02:27 <ais523> I'm glad that it's possible to make it work the way I wanted, though
09:02:33 <shachaf> I think f(x) application is unidiomatic there too.
09:02:43 <shachaf> (I just meant syntactically.)
09:03:03 <ais523> I know, but Haskell allows the parens there and I wanted to make sure I got the term right
09:03:13 <ais523> because it's busy defeating something like three years of research
09:04:50 <ais523> type systems that describe programs, rather than limit them
09:12:28 <shachaf> Hmm, building idris uses quite a bit of RAM.
09:13:08 <shachaf> In fact, this is ridiculous.
09:52:19 -!- Tritonio has joined.
10:29:00 -!- Tritonio1 has joined.
10:31:37 -!- Tritonio has quit (Ping timeout: 252 seconds).
10:32:42 -!- AnotherTest has quit (Ping timeout: 240 seconds).
10:39:02 -!- nooodl has joined.
10:43:44 <Taneb> Help I am suddenly really self conscious about my arms
10:45:04 <ais523> Taneb: that happened to me a while back, it went away after a few months
10:45:15 <Taneb> ais523, my arms are really tiny
10:45:25 <ais523> I just kept noticing that they existed
10:45:32 <ais523> and got in the way while I was trying to lie in bed
10:45:40 <ais523> however, I need them much of the time
10:45:44 <Taneb> Doesn't everyone feel that?
10:45:49 <ais523> so I thought it might be nice if they were retractable
10:48:29 <Taneb> That would be nice
10:53:30 <int-e> Taneb: I don't know. Limbs are just there when one needs them.
10:54:36 <Taneb> int-e, this ain't no MS Paint Adventure
10:55:11 <int-e> I'm not usually conscious of them otherwise.
10:55:24 <int-e> So in a very real sense, yes.
10:55:29 <Taneb> Oh yeah, I need to write up that esolang I made last night
10:55:52 <int-e> ... "real" is such a nice word ...
10:56:33 <int-e> (Does it refer to reality or realization? People assume the former when often it's the latter.)
10:57:05 <Taneb> int-e, it of course always refers to Madrid's football team
10:58:14 <int-e> (That team is another example of something that I'm not usually conscious about.)
11:06:25 <b_jonas> if you're not conscious on hardware attached to you, work on reading system logs
11:07:34 <ais523> b_jonas: I read them recently to try to fix a network issue
11:07:44 <ais523> noticed a warning message, and then got Rosegarden working properly
11:09:09 <ais523> (the problem was that Pulseaudio was trying to create a dotfile in Timidity's root-owned home directory; I gave it a Timidity-owned .config to put it in)
11:12:41 <int-e> kmc: stupid underspecified logic puzzles. what do the liar or the truth-teller do if they cannot answer a question according to their truth attitude? E.g. what does the liar answer to "Is your answer to this question 'yes'?"?
11:13:35 <b_jonas> int-e: http://www.xkcd.com/246/
11:14:14 <int-e> is "would you say that this is the exit" considered to be a tricky question?
11:14:41 <int-e> (subtle, yes, but common enough in english)
11:20:01 <ais523> int-e: yeah, that's my favourite answer to the "solve the liar/truthteller puzzle without it sounding like a tricky question"
11:20:03 <int-e> Oh. Three exits and I guess you only get one question, and then self-referentiality becomes unavoidable.
11:20:21 <ais523> or the more explicit, and still idiomatic, "if I asked you if this door leads to the exit, what would you say?"
11:21:18 <int-e> (self-referentiality being a reference to the question actually being asked, rather than a simpler, hypothetical question)
11:22:04 <ais523> now I'm wondering if the three-door version is possible if you talk to a liar; it's clearly impossible with a true or false question, unless one of the options is to prevent them answering at all
11:23:05 <int-e> ais523: which brings me back to my complaint about underspecified logic puzzles.
11:23:28 <int-e> ais523: Obviously with just two answers, you cannot distinguish more than two possibilities.
11:23:50 <ais523> well, unless you circumvent the "two answers" requirement
11:24:01 <int-e> (the complaint is about this one: http://ethicalwerewolf.blogspot.co.at/2011/02/puzzle-about-your-butt.html )
11:25:52 <int-e> Which is a bit subtler, but it's easy to say that again, with just two answers, "yes" and "no", you cannot draw any conclusions in some cases, namely when the "random" rapper happens to give the opposite answer of the truthteller or liar.
11:26:14 <int-e> I meant "easy to see"
11:27:48 <b_jonas> you can ask different questions from them
11:28:26 <int-e> "they are willing to collectively entertain exactly one yes-or-no question from you, to which they will each give an answer."
11:29:28 <int-e> b_jonas: but it wouldn't help, since the question you ask the random rapper does not affect her answer.
11:29:34 <b_jonas> int-e: but can't that one question depend on who answers, like if you'd ask "do you like my butt?"
11:29:53 <b_jonas> can't you just ask something like "do you like my butt but not all butts?"
11:29:57 <fizzie> int-e: It's not random answers in general, it's just random if a particular butt is big or small.
11:30:06 -!- yorick has joined.
11:30:15 <b_jonas> or "is it true that you don't like all butts but my butt is small?"
11:30:45 <int-e> b_jonas: ah but does he lie or not? it doesn't say, so we can't know
11:31:11 <fizzie> I assumed the third rapper didn't lie, but it's indeed not specified.
11:31:43 <int-e> anyway, you are right, it could be limited to preferences about butts. strange.
11:32:00 * int-e adds that to the list of unspecified details.
11:32:22 <b_jonas> int-e: that one is specified, it says "All the rappers know all other facts relevant to the situation, including everyone's identity and butt preferences."
11:32:56 <int-e> . o O ( you may know, but you can't tell )
11:33:08 <b_jonas> (NB. the comments give a solution)
11:33:26 <b_jonas> int-e: but it says "they are willing to collectively entertain exactly one yes-or-no question from you, to which they will each give an answer"
11:34:29 <b_jonas> at least the two simpler ones will tell
11:38:59 <int-e> Yes, that does look like the intended answer.
11:48:47 -!- shikhin has joined.
12:12:36 -!- Tritonio1 has quit (Ping timeout: 276 seconds).
12:14:52 -!- Tritonio has joined.
12:28:03 -!- Tritonio has quit (Ping timeout: 240 seconds).
12:29:52 -!- Tritonio has joined.
12:49:32 -!- MoALTz__ has joined.
12:52:03 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
13:03:32 -!- ^v has joined.
13:07:14 -!- ^v has quit (Read error: Connection reset by peer).
13:07:39 -!- ^v has joined.
13:08:30 -!- nucular has joined.
13:08:30 -!- nucular has quit (Changing host).
13:08:31 -!- nucular has joined.
13:29:04 -!- ^v has quit (Read error: Connection reset by peer).
13:29:13 -!- ^v has joined.
13:33:47 -!- Sorella has joined.
14:09:01 -!- shikhout has joined.
14:12:06 -!- shikhin has quit (Ping timeout: 252 seconds).
14:12:07 -!- shikhout has changed nick to shikhin.
14:19:33 -!- edwardk has joined.
14:20:14 <edwardk> kmc: are you going to bayhac this year?
14:40:03 -!- Patashu_ has joined.
14:40:03 -!- Patashu has quit (Disconnected by services).
14:56:41 -!- tromp__ has joined.
15:00:18 -!- tromp has quit (Ping timeout: 276 seconds).
15:03:29 <olsner> "I love C++ [...] because it is intuitive and very high-level."
15:05:09 -!- Patashu_ has quit (Ping timeout: 252 seconds).
15:05:44 <ais523> does the omission change the meaning of the sentence?
15:07:31 <olsner> fwiw, the omission was "not because it is fast, but"
15:17:39 <mroman> I don't agree with his definition of "very high-level"
15:29:26 -!- ^v has quit (Ping timeout: 252 seconds).
15:31:06 <ais523> I think the sentence was quoted on the basis that olsner expected pretty much everyone to disagree with it
15:32:56 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:37:48 -!- function has changed nick to trout.
15:41:29 -!- MoALTz_ has joined.
15:42:00 -!- ^v has joined.
15:44:23 -!- MoALTz__ has quit (Ping timeout: 252 seconds).
15:50:21 -!- yorick has quit (Remote host closed the connection).
15:54:54 -!- edwardk has joined.
15:58:59 -!- boily has joined.
16:13:37 <Jafet> I love C++ (not because it is fast, as it is not, but) because it is intuitive and very high-level (compared to motorola 68k assembly)
16:14:51 -!- nortti has changed nick to lawspeaker.
16:14:59 -!- lawspeaker has changed nick to nortti.
16:17:14 <b_jonas> I love C++ because it can be very high level or very low level depending on how you're using it
16:20:13 <int-e> Heh. Lost Vikings is tough.
16:21:27 <b_jonas> int-e: read a walkthrough to know all the clevery hidden secret passages
16:21:40 <b_jonas> Lost Vikings is one of the few games I've beat completely. twice.
16:21:52 <int-e> (I'm back on the spaceship, which should be the final set of levels.)
16:22:43 <b_jonas> I like the Lost Vikings because it has a nice difficulty curve: the levels get progressively more and more difficult
16:23:13 <b_jonas> the last level (MSTR) is the most difficult, the one before (4RN4) is the second most difficult,
16:23:30 -!- boily has quit (Quit: SLEEP).
16:23:30 <b_jonas> and even before then the levels get more and more difficult than they were
16:23:37 <int-e> with some outliers. that triple jump on sinking platforms in the circus levels was really tough.
16:23:55 <int-e> compared to the other stuff in those levels. at least for me :)
16:25:11 <fizzie> Collected all those wiki link graph statistics at http://zem.fi/2014-04-20-wikigraph plus added a quick and dirty shortest-path finder.
16:25:58 <b_jonas> int-e: it's nice that there are such hidden passages that I didn't notice when first beating the game
16:26:05 <b_jonas> but found out about them from reading a faq later
16:26:53 <int-e> (the triple jump is in the TRDR level)
16:27:18 <b_jonas> I don't remember all the levels by heart, sorry
16:27:30 <b_jonas> some of it comes back when I play, but it's just too much to keep in my head
16:28:35 <int-e> That's why I mentioned the code. So that, if you feel like it, you can check which level I meant.
16:33:11 <b_jonas> I might do that. I do have a working copy of vikings in dosbox set up afterall. (It doesn't run it bochs, it's too new a game for that.)
16:33:55 -!- xpte has joined.
16:36:26 -!- nucular has changed nick to nuculaway.
16:39:33 <fizzie> The shortest path search is p. boring because most paths are so short. :/
16:40:06 <quintopia> longest path search is NP-complete though. much more interesting.
17:15:47 -!- shikhin has quit (Ping timeout: 252 seconds).
17:23:51 -!- nuculaway has changed nick to nucular.
17:40:59 -!- adu has joined.
17:43:32 <fizzie> Bah, should've scrubbed (considered as aliases) those redirect pages, perhaps. The path from "Befunge" to "BrainFuck" is Befunge -> Brainfuck -> BrainDuino -> BrainFuck.
17:48:41 -!- adu has quit (Quit: adu).
17:53:15 -!- contrapumpkin has joined.
17:56:27 -!- copumpkin has quit (Ping timeout: 240 seconds).
18:01:16 <b_jonas> ah, you're playing that wiki maze game?
18:06:12 <fizzie> Not really, I'm just fiddling with some esolangs.org link statistics.
18:10:43 -!- Koen_ has joined.
18:16:12 -!- MindlessDrone has quit (Ping timeout: 245 seconds).
18:30:57 -!- MindlessDrone has joined.
18:39:59 -!- Phantom_Hoover has joined.
18:45:12 <kmc> i love C++ because it's a hot mess
18:48:04 <kmc> fizzie: did you do any pagerank-type analysis
18:48:16 <kmc> is the markov chain stationary distribution the same thing?
18:48:23 <fizzie> kmc: It's p. close, like the text says.
18:48:30 <kmc> oh, i missed that
18:49:34 <kmc> also, I really like d3.js's force-directed graph visualization http://bl.ocks.org/mbostock/4062045 https://github.com/mbostock/d3/wiki/Force-Layout
18:49:41 <fizzie> PageRank adds the damping factor thing, which you can interpret as a (page-independent) probability for stopping the random browsing, and the relevance then is the probability for stopping at a particular page.
18:50:02 <fizzie> I did a couple force-directed layouts with Gephi on the graph, but they weren't especially interesting.
18:50:10 <fizzie> If d3.js can do it, maybe I should add that too.
18:50:15 <kmc> how did i not know about gephi
18:50:46 <kmc> "Ergonomic interface: based on NetBeans UI" c.c
18:51:50 <fizzie> Also "Linux: 1. Update your distribution with the last official JRE packages (update 25+), don’t use OpenJDK."
18:52:00 <fizzie> I just used OpenJDK; such a rebel.
18:52:27 <fizzie> I've used d3.js for some of the irc log graph stuff, it's neato. (No GraphViz pun intended.)
18:53:35 <fizzie> The Les Misérables graph is like the Utah teapot or the Stanford bunny, I see.
18:55:04 <kmc> oh, i didn't know that
18:55:28 <fizzie> At least it's used in all the Gephi tutorials too.
19:11:45 -!- conehead has joined.
19:19:40 <fizzie> kmc: Well, I, uh... http://zem.fi/attach/2014-04-20-wikigraph/graph.html
19:20:15 <fizzie> There's supposed to be a thing that keeps it centered in the visible region, but it sure isn't working very well for me.
19:23:13 <Bike> AAAAAH IT'S COMING RIGHT AT ME
19:24:26 <augur> http://everything2.com/title/Quantum+Fingers
19:25:22 <fizzie> It looks reasonably similar to my Gephi layouts, except those had some empty space around very central nodes automatically.
19:29:45 <fizzie> It is kind of scary if you manage to find a central node like Category:Implemented (they have tooltips that pop up; also I made the window bigger and increased gravity a bit) and then try dragging it.
19:30:16 <fizzie> Like a pulsating medusa kind of thing.
19:37:34 <fizzie> Added colors according to namespace, maybe it looks more friendly now.
19:50:08 -!- yorick has joined.
19:57:32 -!- nisstyre has joined.
19:58:09 <fizzie> Also added the fanciest (and slowest) on-hover highlighting this side of [geographical feature].
19:59:09 <fizzie> I'd add text labels that are dynamically toggled visible/hidden on the same hover action except my poor processor would implode.
20:06:22 -!- conehead has quit (Quit: Computer has gone to sleep).
20:13:47 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
20:15:10 <kmc> oh that's pretty neat
20:16:06 <kmc> one time i made a d3.js graph and then turned it into a "find the planar embedding" game
20:18:05 <kmc> I wrote some JS code to detect edges that cross and add a CSS class to them
20:18:29 <kmc> and by "wrote" I mean copied C code from Stack Overflow and turned it into JS
20:19:00 -!- boily has joined.
20:19:42 -!- Phantom_Hoover has joined.
20:21:54 <ion> kmc: Isn’t that how all programming is done?
20:22:02 <kmc> stack overflow oriented programming
20:22:15 <Taneb> Oh yeah, I never wrote up my esolang
20:22:44 <kmc> <Phantom_Hoover> why would you read lesswrong! <--- where else am i going to read about acausal sex??
20:23:42 <Taneb> Maybe I could call it... CONCURRENTREE
20:24:28 <boily> Taneb: Tanelle. designing a new esolang?
20:24:36 <Taneb> boily, it's more or less defined
20:24:43 <Taneb> I need to touch it up a bit
20:24:50 <Taneb> And it's annoyingly not turing-complete
20:24:55 <Taneb> I think it's linear-bounded
20:25:02 <kmc> boily: http://wiki.lesswrong.com/wiki/Acausal_trade
20:26:21 <kmc> jesus loves you acausally
20:26:47 <kmc> (that was the conclusion of one of the comments on http://lesswrong.com/lw/acy/acausal_romance/ )
20:27:43 <boily> I think I'll stick to straightforward, illogical sex, thank you very much.
20:28:41 <Taneb> boily, illogical sex is the only sex I'll ever see
20:29:46 <Taneb> I'd like to take back that message, it was funnier in my head
20:31:00 * boily gently mapoles back illogical sex into Taneb's head
20:38:26 <Taneb> I also want to prepare a half-hour intro to category theory talk at some point
20:43:03 <kmc> fizzie: why does google say "This site may be hacked" in re gephi.org?
20:45:00 <fizzie> kmc: There was a tweet about that.
20:45:16 <fizzie> kmc: https://twitter.com/Gephi/status/449088492266852352 "@mattwigway we've been hacked with some spammy links added in the code of the webpages. We'll fix it soon :)"
20:45:29 <fizzie> kmc: A rather relaxed approach to security, there.
20:46:26 <Sgeo> Starting to think there's one advantage to closed-source software: If you need to distribute a fix, you can do so without as much worrying about what happens to the people who apply the fix slighly later
20:46:26 <fizzie> The site runs on Wordpress, so...
20:46:52 <Bike> Sgeo: on the other hand, you think this is okay http://www.synacktiv.com/ressources/TCP32764_backdoor_again.pdf
20:46:53 <ais523> Sgeo: releasing the fix means it'll probably be reverse-engineered
20:47:13 <ais523> the sort of people who could exploit such a flaw if they knew what it was, could also determine what it was from observing a fix
20:47:46 <Sgeo> True... but what if you regularly release fixes for both security and non-security issues without saying which was more important?
20:48:04 <Sgeo> Which is horrible in other ways, but
20:49:05 <kmc> fizzie: ;_;
20:50:35 <fizzie> Release a patch every hour.
20:50:41 <fizzie> Automatically generated if you have nothing to fix.
20:51:49 <Bike> pro strat, i like it
20:54:21 -!- boily has quit (Quit: WeeChat 0.4.2).
20:54:42 -!- boily has joined.
21:06:08 -!- nooodl_ has joined.
21:10:09 -!- nooodl has quit (Ping timeout: 276 seconds).
21:13:12 <kmc> i didn't read this yet but http://chriskohlhepp.wordpress.com/convergence-of-modern-cplusplus-and-lisp/
21:16:51 -!- ais523 has quit.
21:19:22 -!- tswett has joined.
21:19:53 <tswett> So, there are two programs, P and Q. P outputs an infinite list of programs: p_1, p_2, p_3, .... Q also outputs an infinite list of programs.
21:20:04 <tswett> For every program that P outputs, Q outputs a program that behaves the same way, and vice versa.
21:20:24 <kallisti> from http://conwaylife.com/wiki/Crab:
21:20:26 <tswett> Must there exist a program that, given a number n, finds a number m such that Q_m behaves the same way as P_n?
21:20:30 <kallisti> Due to the diagonal glide symmetry and by simple inspection, the spaceship can easily be made to stretch two tub wicks simultaneously. Both cases are instances of a domino dragging a tub or chain of tubs. Be it noted that tub chains are also called barges, and that additional non-stretching variants are possible given synchronized eating at the far ends.
21:20:33 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
21:20:50 <kallisti> I never realized CA theory could sound so dirty.
21:21:55 <Bike> isn't 'wick' a cricket thing
21:23:01 <fizzie> Bike: A wicket is, but I don't think a wick is, though it sounds like a logical contraction, so maybe it is.
21:23:27 -!- Phantom_Hoover has joined.
21:23:28 <fizzie> (All I know about cricket I learned from The Hitchhiker's Guide to the Galaxy.)
21:23:45 * kallisti is making a distributed Game of Life implementation.
21:24:16 <kallisti> Phantom_Hoover: it's for a class project. I won't be able to do hashlife until after the due date for said project
21:24:21 <kallisti> but yes I plan to implement it, using a distributed quadtree
21:25:15 <b_jonas> fizzie: no, a wick is the part of the candle that's not made of wax, I think
21:26:10 <fizzie> Also "any piece of cord that conveys liquid by capillary action", to quote WordNet.
21:26:15 <fizzie> Oil lamps have wicks too.
21:26:17 <kallisti> technically the class project is just "make a simple distributed system" but I decided to make it interesting for myself.
21:26:27 <b_jonas> isn't that the sense it's used here?
21:26:40 <b_jonas> I mean, it's where you light the candle
21:26:54 <b_jonas> (technically not really, because you have to melt the wax too)
21:27:11 <olsner> I think the wax melts and then gets conveyed by capillary action
21:27:18 <fizzie> Probably. I didn't look beyond the cricket comment.
21:28:20 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
21:29:25 -!- tromp_ has quit (Ping timeout: 252 seconds).
21:30:09 <kallisti> also for the moment I'm only support life 1.05 file format for inputs due to time constraints, but later on I'll implement others.
21:30:32 <fizzie> OED lists 12 separate senses for wick, including things like "a corner of the mouth or eye" ("now only dial.") and "a creek, inlet, or small bay" ("sc. and dial.").
21:31:59 <fizzie> "Ȝiff þatt iss þatt ȝho iss all. Wittlaes. & wac. & wicke."
21:32:31 <tswett> Anyone know off the top of their head whether or not Life has orthogonal spaceships of all rational speeds less than or equal to c/2?
21:32:32 <fizzie> (/Ormulum/ (Burchfield transcript), c1200, for the sense "wicked".)
21:32:35 <b_jonas> you're playing game of life? I like that, I even have some crazy obfuscated code implementing it
21:33:55 <b_jonas> tswett: I don't think that's known
21:34:06 <b_jonas> look at http://www.conwaylife.com/wiki/Speed maybe
21:34:24 <kallisti> I have no clue what size of pattern would even require distribution. Even the larger patterns run very efficiently with haslife.
21:35:06 <kallisti> but the problem suits itself well to distribution... so why not. :P
21:35:09 -!- Phantom_Hoover has joined.
21:38:19 -!- boily has quit (Quit: FOOD).
21:41:22 -!- xpte has quit (Quit: Connection closed for inactivity).
21:44:40 -!- tromp_ has joined.
21:45:29 -!- conehead has joined.
21:50:47 -!- tromp_ has quit (Ping timeout: 245 seconds).
21:51:14 -!- tromp_ has joined.
21:52:09 -!- tromp__ has quit (Read error: Connection reset by peer).
21:52:09 -!- tromp has joined.
21:55:46 -!- not^v has joined.
21:58:50 -!- ^v has quit (Ping timeout: 252 seconds).
22:00:50 -!- not^v has quit (Read error: Connection reset by peer).
22:01:07 -!- not^v has joined.
22:02:50 -!- not^v has quit (Read error: Connection reset by peer).
22:03:17 -!- not^v has joined.
22:09:13 -!- xpte has joined.
22:10:48 -!- oerjan has joined.
22:11:52 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
22:12:10 <lambdabot> fizzie said 14h 6m 3s ago: If we're going to be that fancy, I fixed `url to use os.path.abspath so that e.g. `url /bin/../hackenv/test works.
22:13:14 -!- nisstyre has quit (Quit: bai).
22:14:40 <HackEgo> 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ Wierd \ wisdom \ wisdom.pdf
22:14:46 <HackEgo> . \ .. \ 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ .hg \ .hg_archival.txt \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ Wierd \ wisdom \ wisdom.pdf
22:14:56 <HackEgo> 00changelog.i \ branch \ branchheads.cache \ cache \ dirstate \ last-message.txt \ requires \ store \ tags.cache \ undo.bookmarks \ undo.branch \ undo.desc \ undo.dirstate
22:15:11 <oerjan> `url .hg/00changelog.i
22:15:11 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/.hg/00changelog.i
22:15:49 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/.hg_archival.txt
22:16:34 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.23924
22:17:06 <oerjan> fizzie: i just realized there was an exception :P
22:20:28 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/.hg
22:20:31 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/.hg
22:21:24 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:27:19 <oerjan> `run sed -i '8c if re.match(r"/|\.hg(?:/|$)",f):' bin/url
22:27:45 <oerjan> oops stupid sed strips initial space
22:28:01 -!- conehead has quit (Quit: Computer has gone to sleep).
22:28:59 -!- edwardk has joined.
22:29:06 <Sgeo> I am completely addicted to these
22:29:06 <Sgeo> http://www.amazon.com/Listerine-PocketPaks-Breath-Strips-Fresh/dp/B0054J2J5Q/ref=cm_cr_pr_product_top
22:29:13 <oerjan> `run sed -i '8s!.*! if re.match(r"/|\.hg(?:/|$)",f):!' bin/url
22:29:19 <Sgeo> If I have them in my apartment, I am incapable of consuming less than one pack a day
22:29:44 <oerjan> `run sed -i '8s!.*! if re.match(r"/|\\.hg(?:/|$)",f):!' bin/url
22:30:02 <HackEgo> File is outside hg repository.
22:30:08 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
22:30:17 <HackEgo> File is outside hg repository.
22:32:46 <oerjan> hm this makes the error message somewhat dubious :P
22:33:38 <HackEgo> [wiki] [[Staq]] http://esolangs.org/w/index.php?diff=39381&oldid=35652 * 70.208.158.105 * (-53) the stacks are double-ended
22:33:41 -!- nucular has quit (Quit: Excess Food).
22:36:03 <coppro> I need to write a Tarpit interpreter
22:36:07 <fizzie> oerjan: Right, /hackenv/.hg is special.
22:40:25 <oerjan> `run sed -i 's/hg repository/web-viewable filesystem repository/' bin/url
22:40:34 <HackEgo> File is outside web-viewable filesystem repository.
22:48:56 <oerjan> Taneb: are you still all up in arms?
22:49:29 -!- adu has joined.
22:51:43 <myname> i like that {} feature of staq
22:52:18 <myname> would be more awesome with 2 dimensions
23:03:43 <Sgeo> type Pointful = () + ((), ())
23:04:04 <Sgeo> They did what looks like a fancy trick, apparently only to be able to write that. afaict
23:05:04 <Sgeo> http://www.reddit.com/r/haskell/comments/23jms9/more_points_for_your_very_numbers/
23:10:59 -!- boily has joined.
23:11:07 -!- Sprocklem has quit (Quit: leaving).
23:12:50 <Sgeo> Possibly anything that would by default be displayed in scientific notation?
23:13:41 <Bike> such as 6.981×10⁻¹³
23:13:51 <Sgeo> Maybe not, showFFloat forces standard decimal notation
23:14:28 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/url
23:27:08 <kallisti> presumably anything over 7 digits is a "big number"
23:28:54 <kallisti> I'm not familiar with the + in the Pointful type defintion. Is that a new thing?
23:31:16 -!- shikhin has joined.
23:33:16 <kallisti> whoever wrote this doesn't seem to understand what UndecidableInstances is for
23:33:56 <kallisti> they probably wrote this line: instance Num (Chuwabra a b) => Fractional (Chuwabra a b) where
23:34:04 <kallisti> and then GHC complained and said you need UndecidableInstances
23:35:31 <kallisti> Sure, it's a joke library, but that's no excuse for poorly written code!
23:35:53 <Sgeo> What would you do to make it work?
23:36:36 <kallisti> instance Fractional (Chuwabra a b) where -- should work no?
23:41:39 -!- boily has quit (Quit: WeeChat 0.4.2).
23:42:32 -!- adu has quit (Quit: adu).
23:47:21 -!- Patashu has joined.
23:51:07 -!- yorick has quit (Remote host closed the connection).
00:00:33 -!- adu has joined.
00:01:29 -!- Koen_ has quit (Quit: Koen_).
00:06:03 -!- Patashu_ has joined.
00:06:04 -!- Patashu has quit (Disconnected by services).
00:13:31 <Sgeo> Is shred likely to work acceptably well on Cygwin?
00:38:09 <Sgeo> Apparently not
00:38:17 <Sgeo> But I'm more concerned with malware than physical tampering
00:38:26 <Sgeo> So should shred be sufficient for preventing THAT?
00:38:35 <Sgeo> From accessing my sensitive data?
00:39:49 -!- nisstyre has joined.
00:40:17 <Bike> do like my parents, pour honey through your hard drives
00:41:43 -!- Patashu_ has changed nick to Patashu.
00:43:05 <Sgeo> How do I do recursive shred
00:46:41 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
00:47:58 <Bike> http://larvalsubjects.wordpress.com/2014/02/20/lets-talk-about-sets/ alright i give in. set theory is too mainstream. univalent foundations 4ever. just make it stop
00:48:07 -!- nooodl__ has joined.
00:51:30 -!- nooodl_ has quit (Ping timeout: 240 seconds).
01:02:25 -!- nooodl__ has changed nick to FoWr.
01:29:41 -!- shikhin has quit (Ping timeout: 250 seconds).
01:43:14 -!- Tritonio has quit (Ping timeout: 240 seconds).
02:14:02 <HackEgo> [wiki] [[Staq]] http://esolangs.org/w/index.php?diff=39382&oldid=39381 * Oerjan * (+0) That's not a stack.
02:18:26 <Sgeo> Does this mean we have to rename the language?
02:23:22 <oerjan> i suppose it is possible the q is from queue, i don't remember.
02:27:02 -!- contrapumpkin has changed nick to copumpkin.
02:28:39 -!- edwardk has quit (Quit: Computer has gone to sleep.).
02:34:39 <Bike> they asked kmc about bayhac.
02:35:10 <coppro> oerjan: he comes by every now and then
02:35:20 <coppro> copumpkin: you're not the dual of a pumpkin at all!
02:35:37 <oerjan> i think he's self-dual
02:36:21 <oerjan> if edwardk made an esolang, who could program in it?
02:43:04 -!- Tod-Autojoined has changed nick to TodPunk.
03:10:17 -!- edwardk has joined.
03:31:47 -!- Sorella has quit (Quit: It is tiem!).
03:37:51 -!- FoWr has quit (Quit: Ik ga weg).
03:49:13 -!- edwardk has quit (Quit: Computer has gone to sleep.).
03:51:09 -!- adu has quit (Quit: adu).
04:01:50 -!- edwardk has joined.
04:13:01 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:35:28 -!- tromp has quit (Remote host closed the connection).
04:35:42 -!- edwardk has joined.
04:36:02 -!- tromp has joined.
04:40:21 -!- tromp has quit (Ping timeout: 250 seconds).
04:47:45 -!- tromp_ has quit (Ping timeout: 276 seconds).
04:55:26 -!- tromp_ has joined.
05:04:02 -!- tswett has quit (Ping timeout: 240 seconds).
05:30:56 <kmc> how strange it is to be anything at all
05:33:26 <kmc> hi shachaf
05:33:39 <kmc> glad you agree
05:35:42 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
05:35:47 <shachaf> i should make a bot that looks up things kmc says and posts information when they're lyrics
05:36:33 <Bike> kmc himself turns out to be merely the entire lyrics of Louie Louie
05:37:00 <shachaf> Bike: what do you think of vissarion belinsky
05:37:53 <Bike> i've never heard of him, i mean
05:38:06 <Bike> "He hailed Fyodor Dostoyevsky's first novel, Poor Folk (1845), however, Dostoevsky soon thereafter broke with Belinsky" "Inspired by these ideas, which led to thinking about radical changes in society’s organization, Belinsky began to call himself a socialist starting in 1841" gosh i wonder if these are related......................
05:39:16 <coppro> Sgeo: you should actually play agora
05:40:15 <coppro> oh god calvinball is going to pass isn't it
05:41:34 <Bike> "Belinsky died of consumption on the eve of his arrest by the Tsar's police on account of his political views. In 1910, Russia celebrated the centenary of his birth with enthusiasm and appreciation." this article is just full of great juxtaposition
05:42:13 <kmc> oh that guy
05:43:20 <Bike> i wouldn't have thought 'arrested by the okhrana' is specific enough to clue you into an identity
05:43:37 <kmc> he was a character in the plays that shachaf and i saw together in berkeley
05:43:49 <kmc> http://en.wikipedia.org/wiki/The_Coast_of_Utopia
05:44:13 <Bike> oh. that looks kind of nifty.
05:44:26 <kmc> it's very good
05:56:05 <kmc> we saw them all in a row, 7.5 hours of plays
05:57:28 <oerjan> ooh selnikov that was the guy who got be a head in a jar i think
06:07:28 <shachaf> Bike: what about what'shisname
06:07:42 <shachaf> you know about all kinds of people right
06:08:05 <Bike> i've never actually seen a people in its natural habitat.
06:11:57 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:12:30 <kmc> i've never ever really met a normal person
06:15:41 <oerjan> shachaf: make that bot stat twh
06:23:57 -!- MoALTz_ has quit (Quit: Leaving).
06:51:25 -!- oerjan has quit (Quit: leaving).
07:05:03 -!- Sellyme has quit (Excess Flood).
07:05:52 -!- Sellyme has joined.
07:05:53 -!- Sellyme has quit (Excess Flood).
07:08:26 -!- Sellyme has joined.
07:08:37 -!- Sellyme has quit (Excess Flood).
07:09:56 -!- Sellyme has joined.
07:13:39 -!- Sellyme has quit (Excess Flood).
07:15:26 -!- Sellyme has joined.
08:21:38 -!- realzies has quit (Ping timeout: 240 seconds).
08:22:05 -!- realzies has joined.
08:22:05 -!- realzies has quit (Changing host).
08:22:05 -!- realzies has joined.
09:21:25 -!- Phantom_Hoover has joined.
09:31:22 -!- xpte has quit (Quit: Connection closed for inactivity).
09:35:02 -!- copumpkin has quit (Remote host closed the connection).
09:35:32 -!- copumpkin has joined.
09:46:29 -!- yorick has joined.
10:01:44 <HackEgo> [wiki] [[Talk:German]] N http://esolangs.org/w/index.php?oldid=39383 * 93.193.212.102 * (+1038) Some suggestions for improvement
10:14:32 -!- boily has joined.
10:18:23 -!- impomatic has quit (Read error: Connection reset by peer).
10:18:39 -!- impomatic has joined.
10:31:19 -!- nooodl has joined.
10:49:28 <fizzie> mincross: pass 0 iter 1 trying 0 cur_cross 7723318 best_cross 7723318
10:49:33 <fizzie> That's a lot of edge crossings.
10:49:47 <fizzie> (I asked GraphViz's dot to render the esograph.)
10:49:58 -!- Patashu_ has joined.
10:49:58 -!- Patashu has quit (Disconnected by services).
10:58:01 -!- scoff has quit (Remote host closed the connection).
11:03:06 -!- boily has quit (Quit: ).
11:08:15 -!- nucular has joined.
11:08:15 -!- nucular has quit (Changing host).
11:08:15 -!- nucular has joined.
11:26:34 <myname> someone really is suggesting stuff for german?
11:46:12 -!- Sorella has joined.
12:08:22 <int-e> coppro: esolang wiki pages and links between them
12:08:59 -!- Sgeo has quit (Read error: Connection reset by peer).
12:18:23 <int-e> Ah fizzie pasted this link recently: http://zem.fi/2014-04-20-wikigraph
12:25:43 -!- MindlessDrone has quit (Quit: MindlessDrone).
12:48:34 -!- nucular has changed nick to nuculaway.
12:55:22 -!- Sellyme has quit (Excess Flood).
12:56:56 -!- Sellyme has joined.
13:34:51 -!- edwardk has quit (Quit: Computer has gone to sleep.).
14:02:28 -!- idris-ircslave has quit (Quit: Terminated).
14:02:46 -!- idris-ircslave has joined.
14:08:41 -!- ^v has joined.
14:13:52 -!- nuculaway has changed nick to nucular.
14:17:12 -!- shikhin has joined.
14:18:51 -!- Patashu_ has quit (Ping timeout: 252 seconds).
14:27:00 -!- tswett has joined.
14:27:00 -!- tswett has quit (Changing host).
14:27:01 -!- tswett has joined.
14:57:48 <kallisti> cool my space filling tree works. I gave it a 10x10 rectangle asking for 3 leaves, and it spat out 3 non-overlapping subrectangles that cover the starting rectangle.
15:00:39 <kallisti> not really sure what the tree is, technically. Maybe implicit k-d tree?
15:01:11 <kallisti> well, k is always 2 actually. so implicit 2-d tree
15:11:37 -!- xpte has joined.
15:14:22 <kallisti> http://en.wikipedia.org/wiki/File:Glasses_800_edit.png
15:14:37 <kallisti> this took 23 days to render, apparently.
15:15:10 <fizzie> "More than 100 pages link to this file" time well spent, then.
15:15:17 <kallisti> imagine what video games would look like if we could render it in a few millisecond.
15:16:33 <Jafet> That looks obviously fake to me, like someone just grabbed a few wine glasses and photographed them
15:19:40 <kallisti> hm, I wonder if I'll even need to use a 2-d tree to partition the game of life grid.
15:20:57 <kallisti> right now I'm using a naive implementation of GoL but later I will switch to Hashlife. I could very easily use the 2-d tree and just have each distributed node implement their own hashlife algorithm. However, I could also attempt to use a global quadtree and distribute that across worker nodes, but I'm not really sure how that would work.
15:24:58 -!- MoALTz has joined.
15:26:55 <kallisti> well, for the 2-d tree algorithm I just partition the grid into N subgrids, where N is the number of worker nodes. And then worker nodes communicate peer-to-peer to fetch boundary cells
15:27:25 <kallisti> I'm not sure how distributed quadtree would work, as I haven't studied hashlife enough to know how to distribute it.
15:27:49 <Jafet> hashlife gets a bit tricky if block addresses are no longer unique. I suppose you can let them be unique per-node, and then merge copies later.
15:29:38 <kallisti> I think it would honestly be sufficient to have each worker implement a local hashlife algorithm
15:30:53 <Jafet> You will need to merge the local hash tables every now and then, otherwise I can't see any speedup from using multiple computers.
15:31:52 <kallisti> yeah there's not really any computational benefit. You could, however, represent patterns that consume extremely large quantities of memory.
15:34:02 <Jafet> If you can rearrange the algorithm to deal with high latency table lookups, you might be able to use a DHT
15:34:59 <Jafet> (and cache frequently-used pieces locally, because pieces are immutable)
15:37:08 <Jafet> Hmm, now I want to waste time implementing this.
15:37:27 <kallisti> I'm currently wasting time implementing this.
15:37:56 <kallisti> except it's not really wasting time because the naive implementation I'm doing right now is for a class project.
15:38:30 <kallisti> (the project isn't to specifically implement distributed GoL, it could be any kind of distributed system)
15:39:05 <kallisti> once I finish that I'll probably work on the haslife implementation
15:40:25 <kallisti> I'm thinking I can somehow adapt the 2-d tree to partition the quadtree, but I'm probably wrong about that.
15:40:33 <Jafet> Hashlife is a pure functional algorithm, so it shouldn't be hard to transpose the steps
15:40:37 <kallisti> I just need to study hashlife more.
15:41:50 <Jafet> The usual presentation is: to get the successor of each piece, lookup the successors of its sub-pieces in the hash table, then combine them and put the result in the hash table
15:42:11 <Jafet> After transposing that, the hash table lookups can be streamed and latency shouldn't matter any more
15:43:48 -!- shikhout has joined.
15:46:35 -!- shikhin has quit (Ping timeout: 252 seconds).
15:46:37 -!- shikhout has changed nick to shikhin.
15:49:20 <Jafet> Oh, there is also another fun and tricky part
15:49:26 <Jafet> Distributed garbage collector
15:51:33 <Jafet> Well, you can use reference counting... which is ridiculously slow even on a sequential computer
15:52:08 <Jafet> (One of the things I've been meaning to change in my hashlife code)
15:53:29 <HackEgo> [wiki] [[Talk:German]] M http://esolangs.org/w/index.php?diff=39384&oldid=39383 * Oerjan * (+53) unsigned
15:56:00 -!- edwardk has joined.
16:04:21 -!- conehead has joined.
16:09:36 -!- jjestrel has left.
16:12:45 <mroman> Why is reference counting slow?
16:16:48 <Jafet> The large number of read/writes may have something to do with it
16:25:02 -!- Sprocklem has joined.
16:25:02 -!- Sprocklem has quit (Changing host).
16:25:02 -!- Sprocklem has joined.
16:31:01 -!- nooodl_ has joined.
16:34:57 -!- nooodl has quit (Ping timeout: 276 seconds).
16:40:54 <Bike> «Several conference proceedings have been infiltrated by fake submissions generated by the SCIgen computer program. Due to the fictional content the chapter “Developing Write-Back Caches and Information Retrieval Systems with EASEL” by “Mingqian Wang, Yingying Wang, Yueou Ren and Xi Zhao” has been retracted by the publisher» i love the future~
16:54:32 <fizzie> dot's been running for four hours now, and based on the verbose outputs it's not more than maybe a third of the way done.
16:54:36 <mroman> "Decoupling a* Search from the UNIVAC Computer in the UNIVAC Computer "
16:55:13 <fizzie> "A Methodology for the Simulation of the World Wide Web". Well, that sounds plausible.
16:55:19 <mroman> "Many leading analysts would agree that, had it not been for pervasive configurations, the visualization of IPv4 might never have occurred. " this SCIgen is really something
16:58:24 <mroman> Don't they have somebody at least looking at the sent-in papers
16:58:58 <mroman> That wouldn't catch a hand-made fake paper but at least randomly generated papers
17:03:38 -!- conehead has quit (Ping timeout: 240 seconds).
17:07:33 <Bike> my fave is "802.11B considered harmful"
17:09:24 <mroman> "A 2013 scientometrics paper demonstrated that at least 85 SCIgen papers have been published by IEEE"
17:09:45 <Bike> they're mostly conference proceedings
17:09:57 <FireFly> You can't just quote that without linking to the paper
17:10:38 <mroman> It's a WP-Quote though
17:11:06 <kmc> you cannot petition the lord with prayer
17:19:10 -!- conehead has joined.
17:23:04 <Jafet> "Additional measures taken: An automatic SCIgen detection system is being integrated in Springer’s submission check system, and we will offer this system to our conference proceedings partners, who will be trained in its use."
17:26:04 -!- MindlessDrone has joined.
17:26:36 <lifthrasiir> we should try to write a genuine paper that conforms to the formal grammar generated by SCIgen
17:48:33 <kmc> Bike: what do you think about newcomb's problem
17:50:29 <Bike> not much into logic puzzles but it's cute
17:50:36 <Bike> i'd take both, because a thousand dollars sounds pretty cool
17:51:48 <kmc> a thousand dollars isn't cool
17:51:52 <kmc> you know what's cool? a million dollars
17:53:11 <Bike> a million dollars sounds pretty cool but if it's based on some televangelist's thinking i don't wanna deal
17:54:16 <kmc> it's kind of like playing prisoner's dilemma with a simulated copy of yourself
17:55:08 <Bike> well for that i'd obviously not defect
17:57:45 <kmc> so you should take only the one box
17:58:36 <Bike> well, i guess i would if i was pretty convinced the televangelist was accurate
18:00:40 <kmc> what's this about televangelists
18:02:25 <kmc> predictor? i hardly know 'er!
18:02:50 <Bike> i'm just saying, if someone came along with this thing i'd be like lol yeah right
18:03:13 <kmc> it doesn't have to be right that much of the time for the paradox to be paradoxical
18:03:21 <kmc> i think you can just adjust the payoffs accordingly
18:04:02 <kmc> lexande: what is your success rate playing omega?
18:04:59 <HackEgo> [wiki] [[Rail]] http://esolangs.org/w/index.php?diff=39385&oldid=37412 * 91.64.186.58 * (+58) /* External resources */
18:06:26 <HackEgo> [wiki] [[Special:Log/newusers]] create * Kinnla * New user account
18:07:47 <kmc> anyway you could say that the right course of action is to make it as easy as possible for even a mediocre omega to predict that you will one-box
18:10:21 <Bike> that sounds like it's going to go into basilisks pretty fast, lol
18:13:27 <kmc> gotta watch out for basilisks
18:15:05 <kmc> do you want basilisks? because that's how you get basilisks
18:16:54 -!- vravn has quit (Ping timeout: 240 seconds).
18:24:15 -!- vravn has joined.
18:25:05 <Bike> http://www.theonion.com/articles/how-to-solve-a-rubiks-cube,35827 this should explain me and this puzzle
18:25:42 <shachaf> Bike: just, like, conjugates hth
18:26:08 <shachaf> whoa, the biggest trick to solving a rubik's cube is a monad
18:27:33 <ion> A monad is like a Rubik’s cube.
18:28:59 <elliott> monad/burrito jokes are hereby banned
18:29:24 <Taneb> `quote time is like
18:29:31 <Taneb> `quote time is more
18:30:02 <shachaf> mine wasn't really a joke, though
18:30:51 <shachaf> though perhaps it ought to be banned anyway
18:33:20 <Taneb> Did you know that Minecraft modpacks form the arrows of a category
18:35:29 <shachaf> wait, i'm apparently thinking of a "commutator"
18:37:34 <shachaf> Taneb: did you know group actions etc. are just functors
18:38:12 <Taneb> There are many things I don't know
18:38:23 <Taneb> For example, what a group action is, or how to actually make a curry
18:38:30 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:39:05 <shachaf> a G-action is a functor : G -> Set hth
18:39:06 <Taneb> Similar to a group action, I'm afraid
18:39:49 -!- nucular has quit (Quit: Switching to phone and going away).
18:39:49 <Taneb> So, is fast curry a functor : fast -> curry?
18:40:13 <lambdabot> http://www.nigella.com/recipes/view/curry-in-a-hurry-11
18:40:15 <lambdabot> Title: CURRY IN A HURRY | Recipes | Nigella Lawson
18:40:55 <shachaf> whoa, spj should've taken naming advice from nigella.com
18:41:17 <shachaf> though i guess the fast curry in question isn't necessarily fast to make, just fast after it's done
18:42:52 <Taneb> shachaf, that seems disappointingly not food
18:45:36 <HackEgo> emptizudacoin gaxencoin truecoin alecoin salagecoin concoin m-codelcoin chrowcoin pinsonavocoin eplcoin resoncoin memfcoin beetcoin shencoin hintcoin gasoribericoin concoin slocoin brosievcoin pencoin
18:45:44 <Taneb> Non of those are food either
18:45:53 <kmc> not even beetcoin?
18:46:03 <fizzie> My emptizudacoin wallet's all empty.
18:46:29 <kmc> alecoin sounds like a foodcoin as well
18:46:43 <fizzie> And concoin sounds like a thing that exists.
18:49:49 -!- tertu has joined.
18:55:10 <fizzie> Do you people happen to know, if something is shipped as "FedEx International Priority" with "FedEx Envelope" packaging, are they going to drop it in the mail slot, or insist that I should be present to receive it?
18:57:36 <fizzie> (I'm guesstimating they want a signature of some sort somehow.)
19:01:12 <kmc> give them an ECDSA signature
19:04:32 <fizzie> The mail slot should have some sort of public-key cryptography support, so that I could give them its public key over the nets, and then when they're at the door, they'd use it to both verify the mail slot's identity, and get a signed proof-of-delivery statement out of it.
19:05:38 <fizzie> I guess it'd be harder for the mail slot to check they delivered something sensible.
19:06:25 <int-e> I didn't know that in the US it's illegal for FedEx or UPS to put stuff in people's mailboxes; they are regardes USPS property.
19:06:47 <fizzie> Of course what they're delivering is a special piece of paper that doesn't really have any excuse for existing physically.
19:07:39 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39386&oldid=31682 * Kinnla * (+331) /* List Constructor */ new section
19:14:33 <fizzie> @tell ais523 In 2006, you wrote in Talk:Rail that car/cdr stand for "Content of {Address,Decrement} Register", while in reality they're derived from "Contents of the {Address,Decrement} part of Register X"; they're parts of a single 704 machine word, along with the prefix and tag parts.
19:14:33 <quintopia> int-e: either company can deliver to your local post office, however, who will gladly deposit it in your mailbox for you
19:16:13 -!- sebbu has quit (Ping timeout: 252 seconds).
19:16:22 <fizzie> (That recently announced Talk:Rail edit does not really look like a question. Or at least a question lacking an answer.)
19:21:23 -!- sebbu has joined.
19:21:58 -!- sebbu has quit (Changing host).
19:21:58 -!- sebbu has joined.
19:25:57 <HackEgo> [wiki] [[Rail]] M http://esolangs.org/w/index.php?diff=39387&oldid=39385 * Duerig * (+11) /* Built-in commands */ The list constructor should require a list/nil to build on.
19:27:09 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39388&oldid=39386 * Duerig * (+260) /* List Constructor */
19:33:23 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39389&oldid=39388 * Kinnla * (+481) /* Forth Notation of Type Signatures */ new section
19:33:51 <b_jonas> fizzie: "Decrement"? I thought it stood for "Data"
19:35:05 <fizzie> b_jonas: http://www-formal.stanford.edu/jmc/history/lisp/node2.html "The first problem was how to do list structure in the IBM 704. This computer has a 36 bit word, and two 15 bit parts, called the address and decrement, were distinguished by special instructions --"
19:35:52 <fizzie> @tell ais523 Citation: http://www-formal.stanford.edu/jmc/history/lisp/node2.html
19:36:04 <fizzie> It must be reliable, it says "www-formal" right in the hostname.
19:36:09 -!- Frooxius has quit (Read error: Connection reset by peer).
19:39:45 <fizzie> "The IBM 704 had a 38-bit accumulator, a 36-bit multiplier quotient register, and three 15-bit index registers. The contents of the index registers were subtracted from the base address, so the index registers were also called "decrement registers". All three index registers could participate in an instruction: the 3-bit tag field in the instruction was a bit map specifying which of the ...
19:39:51 <fizzie> ... registers would participate in the operation. However, when more than one index register was selected, then their contents were or'ed – not added – together before the decrement took place." (Wikipedia)
19:39:56 <fizzie> That sounds p. strange.
19:41:56 <fizzie> Also, dot has now spent 408 CPU-minutes, and still shows no signs of being done.
19:48:34 -!- password2 has joined.
19:49:39 -!- password2 has quit (Max SendQ exceeded).
19:52:26 -!- Frooxius has joined.
19:53:15 -!- password2 has joined.
19:54:30 -!- idris-ircslave has quit (Ping timeout: 276 seconds).
19:54:50 <Bike> https://bug985155.bugzilla.mozilla.org/attachment.cgi?id=8409733 Mother Fucking NOP Sled
19:54:58 -!- Melvar has quit (Ping timeout: 258 seconds).
20:03:48 <Phantom_Hoover> http://en.wikipedia.org/wiki/File:Itanium_Sales_Forecasts_edit.png hahaha oh my god
20:04:50 -!- tertu has quit (Ping timeout: 240 seconds).
20:07:28 <Jafet> Why does mozilla even support "Some (old) Linux kernels on ARM"
20:07:49 <Jafet> Oh, phones. Of course.
20:08:02 <Bike> Phantom_Hoover: one of the greatest graphs ever made.
20:08:07 <Jafet> The platform is still tagged "x86_64 Linux".
20:13:20 <Jafet> "A former Intel official reported that the Itanium business had become profitable for Intel in late 2009."
20:24:47 -!- tertu has joined.
20:27:45 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
20:28:59 -!- conehead has joined.
20:29:21 <int-e> Oh, Itanium. EPIC failure.
20:30:16 <fizzie> /aɪˈteɪniəm/ I didn't know it's pronounced like that.
20:30:38 <lambdabot> *** "titanium" wn "WordNet (r) 3.0 (2006)"
20:30:38 <lambdabot> n 1: a light strong grey lustrous corrosion-resistant metallic
20:30:38 <lambdabot> element used in strong lightweight alloys (as for airplane
20:30:38 <lambdabot> parts); the main sources are rutile and ilmenite [syn:
20:30:38 <lambdabot> {titanium}, {Ti}, {atomic number 22}]
20:31:17 <fizzie> /taɪˈteɪniəm/ oh, right, I guess it just drops the initial t. Makes sense.
20:31:41 <int-e> I pronounce it ee-tanium, partly because I'm from Germany.
20:33:15 <int-e> Are there any Transmeta like architectures left? Or any other VLIW survivors?
20:37:56 <Jafet> https://en.wikipedia.org/wiki/FR-V but they seem to no longer be used for supercomputers
20:38:01 <fizzie> There are some VLIW(-ish) DSPs, I think.
20:39:40 <fizzie> E.g. the TI TMS320C6x series, there's one of those in my phone.
20:42:15 <int-e> Oh Wikipedia seems to be helpful for once. "Embedded VLIW products are available from several vendors, including the FR-V from Fujitsu, the BSP15/16 from Pixelworks, the ST231 from STMicroelectronics, the TriMedia from NXP, the CEVA-X DSP from CEVA, the Jazz DSP from Improv Systems, and Silicon Hive. The Texas Instruments TMS320 DSP line has evolved, in its C6xxx family, to look more like a VLIW, in contrast to the earlier...
20:43:10 <fizzie> "Outside embedded processing markets, Intel's Itanium IA-64 EPIC and Elbrus 2000 appear as the only examples of a widely used VLIW CPU architectures."
20:43:13 <fizzie> (Also from said page.)
20:43:46 <Bike> dsps continue to be weird ass shit, i see
20:44:58 <int-e> DSPs are special; they only run inner loops so code bloat (and corresponding hogging of a memory bus, and often they have separate code and data memory anyway) is less of an issue.
20:46:10 <int-e> Perhaps they should mention GPUs, too.
20:46:30 <fizzie> "VLIWs also gained significant consumer penetration in the GPU market, though both Nvidia and AMD have since moved to RISC architectures in order to improve performance on non-graphics workloads."
20:46:31 <int-e> (the failed Larrabee architecture aside)
20:48:03 <fizzie> TI C5x has a couple of specific "parallel" instructions, stuff like ST B, *AR4+0% || MPY *AR2+, B but that's not quite even LIW since, despite the fancy syntax, it's just a single "compound" instruction.
20:50:45 <Jafet> Is there a name for the kind of architecture used by GPUs? I use "SIMD for morons" but it's not very suitable for a polite setting
20:51:35 <fizzie> For the record, that does "write old value of B to memory pointed by AR4, then increment AR4 by AR0 except modulo some registers; meanwhile, compute the product of the value in memory at AR2 and the T register, store it as new value of B and post-increment AR2".
20:51:49 <Bike> why is it for morons
20:56:23 <Jafet> It seems to be SIMD disguised as some kind of multithreading--because, as everyone knows, multithreading is simpler and less confusing
20:56:48 <Jafet> Actually, the proper name seems to be "stream processing"
20:56:58 <elliott> http://www.yosefk.com/blog/simd-simt-smt-parallelism-in-nvidia-gpus.html
20:57:00 <Phantom_Hoover> MEANWHILE IN /R/BITCOIN: http://www.reddit.com/r/Bitcoin/comments/23leue/sir_richard_branson_bitcoin_is_the_pioneer_of_a/cgyb3y3?context=3
20:57:46 <Bike> You realize the trolls and shills are just downvoting everything now. They don't want this sub to function at all, even if that means false flag attacking themselves.
20:58:20 <Bike> the lack of criticism of bitcoin is a conspiracy by bitcoin haters.
20:59:45 <Phantom_Hoover> bitcoin is actually a massive false-flag created by the nsa so they could practise their trolling
21:00:15 <kmc> that's just what they WANT you to think!!
21:00:22 <kmc> Phantom_Hoover: what do you think of newcombe's problem
21:00:30 <Jafet> That's just what the conspiracy theorists want you to think
21:00:35 <kmc> newcomb's problem I mean >_<
21:00:51 <Jafet> itt: GPU acceleration for homespring
21:03:39 <Phantom_Hoover> kmc, seems interesting, does it have anything to do with bitcoin or were you just thinking about it anyway
21:04:04 -!- edwardk has quit (Quit: Computer has gone to sleep.).
21:04:10 -!- Patashu has joined.
21:06:09 <kmc> the latter
21:07:29 -!- password2 has quit (Ping timeout: 264 seconds).
21:12:46 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39390&oldid=39389 * Kinnla * (+945) /* universal print */ new section
21:24:18 -!- Patashu has quit (Ping timeout: 240 seconds).
21:25:29 -!- tertu has quit (Ping timeout: 264 seconds).
21:25:37 -!- tertu has joined.
21:32:05 <Phantom_Hoover> http://cynic.me/2014/04/18/why-rich-people-should-do-less-time-in-prison-than-poor-people/ ow ow ow why did i delve deeper into this blog
21:32:18 -!- oerjan has joined.
21:32:51 <myname> i am kinda disapponted that none of the rail people are here
21:33:32 <HackEgo> faciatiocoin substrecoin haircoin indcoin barintcoin rfolucoin l332coin intercoin funacoin mkbl-lncoin tletcoin 6ixcoin breatumcoin woldcoin prishcoin estcoin ragencoin autioncomplingcoin codecoin ajlycoin
21:34:29 <Bike> Phantom_Hoover: "Yes," i think to myself, "From the title visible in the URL, I assume this will be an enlightening read, well worth my time I could be spending on video games."
21:34:51 <elliott> Bike: spoiler: it's not that rich people should do less time in prison, it's that tax is theft!
21:34:56 <elliott> I wish I was kidding but this is actually the punchline to the post.
21:35:47 <Jafet> The tax curve should be adjusted so that the 99% poorest people are below it
21:40:38 <Bike> progressive tax is punishing the rich for being rich, jafet
21:41:35 <Jafet> Mansions create jobs
21:46:37 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39391&oldid=39390 * Myname * (+205)
21:46:54 <kmc> prisons create jobs too
21:47:02 -!- shikhin has quit (Ping timeout: 252 seconds).
22:00:37 <kmc> that's why it's important to lock people up for owning a small amount of a plant
22:00:39 -!- boily has joined.
22:05:10 <boily> Bike: I metaphorically hate you.
22:06:22 <boily> my legs hurt. first day of the year riding a bike.
22:06:31 <Bike> boily: i present you with an apology gift https://www.youtube.com/watch?v=XAsPeY8BsQU
22:10:08 <myname> Bike: how is that a gift?
22:10:26 <Bike> well he's probably forgotten about his legs
22:11:02 <boily> I AM FINE" EVERYTHING IS FINE" ALL IS WELL" ALL HAIL FUNGOOOOOOOOOÓÓÓÓT¨¨¨
22:11:15 <kmc> awesome, I just installed gnome-terminal and the default color scheme is black on black
22:11:18 <kmc> i love desktop linux
22:11:36 <myname> sounds a tiny little bit like irony
22:11:40 <boily> kmc: oh, I never managed to get that one.
22:12:52 <Jafet> Try the bob dylan color scheme
22:13:05 <boily> Jafet: what is a bob dylan colour scheme?
22:13:13 <boily> quintopia: quinthellopia.
22:14:13 <oerjan> the answer, boily, is blowing in the wind
22:17:05 -!- nooodl_ has quit (Quit: Ik ga weg).
22:17:50 <Jafet> If you didn't like the bob dylan color scheme, I guess you'll just need to go with amy winehouse.
22:19:21 <kmc> i see a red terminal and i want it painted black
22:21:17 -!- tertu has quit (Ping timeout: 264 seconds).
22:21:37 <int-e> at least black on black is easy on the eyes
22:24:26 <int-e> (Maybe they were inspired by the peril sensitive sunglasses from the Hitchhiker's trilogy?)
22:25:12 -!- tertu has joined.
22:29:41 -!- tertu has quit (Ping timeout: 264 seconds).
22:33:55 <Jafet> Hmm, I just saw someone send a message before entering the channel.
22:34:19 <Jafet> What kind of network setup even allows that.
22:36:05 <int-e> Hmm. Two ideas: a) a client might delay displaying joins to be able to combine several of them into a single line
22:36:12 <int-e> b) a channel might not have +n set.
22:38:49 <int-e> Otherwise I agree; messages related to the same client /should/ not be transmitted out of order by an IRC network, which classically had an acyclic graph topology.
22:38:51 <Jafet> I think +n is default on freenode
22:39:03 <int-e> But is that true for Freenode?
22:39:11 <int-e> (The topology thing)
22:40:19 <Jafet> Could be some weird network load balancing thing.
22:40:21 <boily> fungot: what is freenode's topology?
22:40:22 <fungot> boily: mr president, i would say to you that thanks to a deeper level of cooperation and not, therefore, undeniable that parliament is entitled to their say and to be handled under the commission's aegis.
22:40:50 <boily> fungot: what's an ægis?
22:40:50 <fungot> boily: this is a transitional period, the epidemiology of rabies in cats and dogs from nearly 500 in 1991 to just 5 in 1998. a systematic survey of the situation.
22:41:21 <boily> fungot: oh. so a deeply cooperative topology over a transitional period. poor cats and dogs, but if IRC is a stake, then so be it.
22:41:21 <fungot> boily: i wish to begin by congratulating the rapporteur, mrs fnord buitenweg, is basically supporting israel's barbaric behaviour. i can see, however, since, for example in the case of mr kostas kastanias and other people who are now to be reduced significantly. that, of course, enforcement of measures is a great mistake to confuse the two.
22:42:06 <boily> fungot: ah. lets unleash the SPCA on the vile Mrs. Fnord Buitenweg, for applying cruel measures to network communication!
22:42:06 <fungot> boily: mr president, this is an intolerable situation! he must either resign or tell us who does what, and can be adhered to in all places where the citizens of europe and beyond in the coming years for precisely this reason that this parliament will see fit to accept it.
22:42:12 <lexande> kmc, Bike: i have given the newcomb's problem question (with $1 and 1¢) to people twice and predicted them correctly both times
22:47:31 <Bike> and what were the resutls
22:48:15 <Bike> a client might delay displaying joins to be able to combine several of them into a single line <-- you know, this would actually be kind of nice, but just in the rendering
22:48:20 <lexande> one of them one-boxed and got $1, one of them two-boxed and got 1¢
22:49:00 <lexande> of course many people in my reference class consider 1¢ to be of zero or negative value
22:49:20 <Jafet> You should apply for a bigger grant
22:49:23 <shachaf> lexande: what is your prediction for me
22:49:28 <Bike> http://www.americanladderinstitute.org/Standards.aspx only $200
22:49:29 <kmc> i,i people in my reference prototype
22:49:47 <int-e> Oh! What a nice problem.
22:49:49 <kmc> lexande: where's that comic about ladders
22:50:20 <lexande> kmc: http://unnecessaryinsufficient.wordpress.com/2012/03/21/ladder/ this one?
22:50:40 <Bike> good punchline
22:52:37 <int-e> (The concept of an accurate predictor is ... interesting.)
22:53:00 <kmc> it doesn't have to be that good though
22:53:17 <kmc> and our entire civilization is based on agents imperfectly predicting each other
22:53:41 <oerjan> hm SCIgen is like a CAPTCHA for science journals :P
22:53:58 <Jafet> Does the problem change if the test subject knows that you base your predictions on what the previous test subjects picked
22:53:59 <kmc> lexande: so is there empirical evidence that following acausal decision theory in real-world situations produces better outcomes?
22:56:52 <Bike> oerjan: a pretty good one, evidently
22:56:54 -!- MoALTz_ has joined.
22:59:38 <boily> oerjan: you reminded me of my Duty. thørjan.
23:00:06 <oerjan> do i remind you of your duty simply by existing
23:00:24 -!- MoALTz has quit (Ping timeout: 276 seconds).
23:02:12 <lexande> Bike: well, few fake journals were even trying to defeat this captcha
23:03:10 <boily> oerjan: you'd be the knot in my handkerchief if I had one.
23:03:23 <lexande> maybe some will implement automated checks for scigen papers now
23:06:23 <oerjan> lexande: that was discussed in the logs
23:06:31 -!- MoALTz has joined.
23:06:40 <oerjan> apparently springer is introducing one
23:07:45 <boily> oerjan: if I had a nice silken handkerchief, I'd keep it extra clean. probably put some shiny brocade on it. with my initials, in a nice blackletter font.
23:08:03 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
23:08:13 <lexande> what is the point of a hankerchief if you keep it extra clean
23:08:17 <Jafet> http://www.springer.com/about+springer/media/statements?SGWID=0-1760813-6-1460747-0 "An automatic SCIgen detection system is being integrated in Springer’s submission check system, and we will offer this system to our conference proceedings partners, who will be trained in its use."
23:09:39 <boily> lexande: decoration, class, just for having something silky on you...
23:09:53 <boily> (you never know, it may save the day one time! just like regexpes!)
23:10:07 <lexande> boily: handkerchiefs go in your pocket
23:10:16 -!- augur has quit (Quit: Leaving...).
23:10:16 <lexande> unless you are using them to make something else less dirty
23:10:42 <lexande> regexpes save my day all the time
23:10:44 <boily> you know, with very high-class tuxedoes, that thing in the breast pocket?
23:10:51 <kmc> smoke regexps every day
23:10:57 <lexande> their banach-tarski nature notwithstanding
23:17:23 -!- ^v has quit (Ping timeout: 252 seconds).
23:19:28 -!- boily has quit (Quit: BANANANACH TARSKI).
23:21:50 -!- MoALTz has quit (Ping timeout: 276 seconds).
23:22:39 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:23:49 -!- ^v has joined.
23:25:46 -!- tromp has joined.
23:27:47 -!- augur has joined.
23:30:29 -!- Sgeo has joined.
23:36:26 -!- maurer has quit (Ping timeout: 240 seconds).
23:44:53 -!- sebbu has quit (Ping timeout: 252 seconds).
23:45:35 -!- yorick has quit (Remote host closed the connection).
23:46:14 -!- MoALTz has joined.
00:17:35 -!- tertu has joined.
00:18:59 -!- MoALTz_ has joined.
00:22:05 -!- MoALTz has quit (Ping timeout: 252 seconds).
00:25:25 -!- edwardk has joined.
00:31:04 <Bike> http://www.reddit.com/r/Bitcoin/comments/23m2rw/how_to_go_about_buying_somewhat_large_number_of/
00:32:04 -!- ter2 has joined.
00:32:04 -!- tertu has quit (Disconnected by services).
00:33:36 -!- nisstyre has joined.
00:35:02 -!- tertu3 has joined.
00:38:41 -!- ter2 has quit (Ping timeout: 264 seconds).
00:57:15 -!- tertu3 has quit (Read error: Connection reset by peer).
00:57:28 -!- tertu3 has joined.
01:18:36 -!- Melvar has joined.
01:41:49 -!- sebbu has joined.
01:42:22 -!- sebbu has quit (Changing host).
01:42:22 -!- sebbu has joined.
01:42:46 -!- maurer has joined.
01:43:30 <Jafet> Bike: http://www.newegg.com/Product/ProductList.aspx?Submit=ENE&Description=PPSSSVZITVPZDR "Optimized as a Scrypt miner, Coin Miner and GPU Server"
01:46:02 <Bike> The system is not limited to mining only Litecoin. It can also mine Peercoin, Namecoin, Primecoin, Dogecoin, and even Bitcoin.
01:50:07 -!- tertu3 has quit (Ping timeout: 265 seconds).
01:52:10 -!- tertu has joined.
01:54:14 -!- ^v has quit (Read error: Connection reset by peer).
02:09:53 -!- tertu has quit (Ping timeout: 255 seconds).
02:29:14 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39392&oldid=39391 * Oerjan * (+135) unsigned deluge
02:32:11 -!- ^v has joined.
02:32:38 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39393&oldid=39392 * Oerjan * (+0) How did you manage to get the date wrong?
02:32:56 <oerjan> myname: INQUIRING MINDS WANT TO KNOW
02:39:05 <HackEgo> [wiki] [[Esolang:Sandbox]] http://esolangs.org/w/index.php?diff=39394&oldid=39199 * Oerjan * (+74)
02:42:43 <oerjan> @tell fizzie I am somewhat disturbed by the wiki apparently now adding signature dates in EDT timezone...
02:43:02 <oerjan> still doesn't explain what happened to myname though
02:43:56 -!- tertu has joined.
02:49:00 <HackEgo> Tue Apr 22 02:48:55 UTC 2014
02:51:10 -!- ^v has quit (Read error: Connection reset by peer).
02:52:23 <oerjan> @tell myname ok i have you under suspicion of mangling the times on your talk post signatures tdnh
02:53:04 <oerjan> i am pretty sure http://esolangs.org/w/index.php?title=Talk:MarioLANG&diff=prev&oldid=37550 does _not_ have the timezone difference in the right direction.
02:53:43 <oerjan> admittedly he only ever made two signatures.
03:00:24 <Sgeo> Am I a horrible person for suggesting a show implementation that differs from gshow?
03:00:25 <Sgeo> http://www.reddit.com/r/haskell/comments/23hcu2/is_there_a_way_to_modify_the_default/cgynogf
03:03:01 <oerjan> no, just out of all proportion hth
03:04:52 <Bike> adolf 'a show implementation' hitler
03:05:41 <oerjan> he did it all for show
03:06:03 <Sgeo> How about on a scale from 'completely ok' to 'writing a Typeable instance manually'
03:07:04 <oerjan> i think writing a Typeable instance manually has recently become impossible, hasn't it?
03:07:52 -!- Sorella has quit (Quit: It is tiem!).
03:07:54 <oerjan> or maybe it's just wishful thinking.
03:13:19 <oerjan> as someone who has written show instances over newtypes to make strings show up as raw characters, and matrices as 2d tables, i may not be qualified to judge.
03:13:35 <oerjan> admittedly this was only to make some things more convenient in ghci.
03:14:38 <Sgeo> Not so much worried about the custom show instance as having the custom show instance disagree with the GShow instance
03:15:09 <oerjan> hm i may not know what GShow is.
03:15:19 <Sgeo> A version of Show that uses GHC.Generics
03:16:04 <Sgeo> http://hackage.haskell.org/package/generic-deriving-1.6.3/docs/Generics-Deriving-Show.html
03:16:38 <Sgeo> err why is it using OverlappingInstances
03:18:27 -!- tertu has quit (Ping timeout: 252 seconds).
03:26:51 <Sgeo> Generics have an interesting property... they tend to define a default function, and even in the class that you can normally instantiate without definition, you still can provide a definition based on that default function, assuming it's exported
03:30:14 <oerjan> @tell Taneb congrats on your gsoc project (and good luck)
03:33:03 -!- zzo38 has joined.
03:35:56 <Sgeo> I feel sad that I never did gsoc
03:40:20 -!- tertu has joined.
03:52:43 -!- ter2 has joined.
03:52:43 -!- tertu has quit (Disconnected by services).
03:58:13 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
04:00:49 <Sgeo> Outlook scared me for a second when the top of the email list suddenly said Yesterday
04:14:59 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:16:19 <kmc> i think there are some (narrow) circumstances where running a program in valgrind makes it easier to exploit
04:16:37 <kmc> because valgrind supports these "client requests" which allow the program to ask valgrind to do various things
04:19:26 <kmc> i didn't see a way
04:22:18 -!- ter2 has quit (Ping timeout: 252 seconds).
04:31:19 <zzo38> Does anyone other than SQLite making people, would want to be able to specify order of triggers being fired in SQL?
04:36:05 -!- ter2 has joined.
04:36:24 -!- tromp has quit (Remote host closed the connection).
04:36:59 -!- tromp has joined.
04:41:14 -!- tromp has quit (Ping timeout: 240 seconds).
04:41:27 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
04:47:34 -!- shikhin has joined.
04:56:23 -!- ter2 has quit (Ping timeout: 252 seconds).
04:57:56 -!- fowl has joined.
05:03:19 -!- tswett has quit (Ping timeout: 252 seconds).
05:03:41 <fizzie> oerjan: Must be a side effect of the upgrade. What did it used to do?
05:05:04 <fizzie> Well, that seems like the second most reasonable thing to do.
05:05:21 <oerjan> what's the first then.
05:05:24 <fizzie> The most reasonable thing would, of course, be Swatch Internet Time.
05:07:52 <fizzie> It should be back in UTC now.
05:08:18 <fowl> you know php has a time format for swatch beats
05:10:52 <oerjan> ...so this could actually be done.
05:11:12 <oerjan> fowl: i see you have joined us for reasons of evil, then.
05:12:33 <oerjan> (or are you a returned old regular in thin disguise? those happen.)
05:13:22 <fowl> no i just saw mention of the channel on esolangs.org
05:14:12 <fizzie> I was this || close to advertising the #esoteric recent-change notifications there.
05:14:16 <oerjan> (if you are hagb4rd YOU ARE FOOLING NO ONE WITH YOUR CLOAK. if not, disregard this message.)
05:15:24 <fizzie> fungot: Welcome a new friend, will you.
05:15:25 <fungot> fizzie: mr president, ladies and gentlemen, it is therefore in agreement with the government's suggestion that the proposals of the irish stability programme. in the case of australia it is a pity that the report from the committee, on which i have mentioned, i do not.
05:16:29 <oerjan> pretty good style for welcoming, that.
05:18:38 -!- ter2 has joined.
05:19:57 <kmc> fungot: hail to the thief
05:19:58 <fungot> kmc: madam president, i welcome this but to avoid the problems of the on board diagnostic systems, there is still an anathema justifying the present reign of terror. there is currently a democratically elected president of sierra leone, when they took into account likely developments up until the end of 2001 so there is certainly confusion about definitions within the directives and the instrument for cultural diversity in euro
05:20:45 <kmc> fizzie: you should add the Enron Corpus to fungot
05:20:45 <fungot> kmc: mr president, mr president-in-office of the council with a view to ensuring the economic and social committee ( sec(1999) 414 c50008/ 1999 1999/ fnord and ii. on the question of the natural environment, much of the council and take over these matters, in other words assists producers to continue with their prohibitionist policies. i would also like to thank parliament as a political message to the people.
05:20:48 <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
05:20:53 <kmc> ^style enron
05:20:53 <fungot> Selected style: enron (subset of the Enron email dataset)
05:21:01 <kmc> fungot: what do you think about that!
05:21:01 <fungot> kmc: could we schedule more rate cuts tied to any specific points.
05:21:24 <kmc> fungot: is it buy low, sell high or the other way around? i can never remember
05:21:24 <fungot> kmc: plan that the commission: " a registration happy to do that.
05:21:43 <kmc> buy sober, sell high
05:30:18 <fizzie> kmc: It's not been very well-sanitized w.r.t. unwrapping lines back to paragraphs, and maybe the training parameters were not quite fungot-optimal either.
05:30:19 <fungot> fizzie: from the week on the key.
05:31:06 <fowl> ^style youtube
05:31:06 <fungot> Selected style: youtube (Some YouTube comments)
05:31:13 <fowl> fungot, entrain me
05:31:13 <fungot> fowl: that game was bashing crackheads in the description! it's when the music is best super bowl?
05:31:36 <fowl> youtube comments are the best forum for intellectual discussion
05:32:05 <fizzie> That's comments from somewhere around three videos, so it's a bit repetitive.
05:32:13 <fizzie> (The data was contributed by someone else.)
05:32:13 <elliott> oerjan: pretty sure you're hagb4rd.
05:33:55 <kmc> fizzie: what do you think of newcomb's problem?
05:33:59 <kmc> fungot: what do you think of newcomb's problem?
05:33:59 <fungot> kmc: no it wasn't. can you clarify us why you assume i like
05:36:36 <fizzie> kmc: I read the Wikipedia article about it when you were asking around yesterday, but for some reason did not form any kind of coherent opinion on the subject.
05:49:43 -!- password2 has joined.
05:51:22 -!- xpte has quit (Quit: Connection closed for inactivity).
06:18:38 -!- MoALTz_ has quit (Quit: Leaving).
06:19:33 -!- heroux has quit (Ping timeout: 250 seconds).
06:20:28 -!- heroux has joined.
06:28:18 -!- oerjan has quit (Quit: leaving).
06:44:26 <fizzie> Bah, (based on the tracking page) FedEx guy had been at my door maybe 15 minutes after I had left. Of course.
06:46:59 <zzo38> On some TV show they said that, in the 9/11 explosion, the government refused to investigate to find explosive in the building. I don't know where they got that information, but if it is true, then probably they are trying to hide something.
06:49:37 <Bike> "NIST did not test for explosive compound residue in steel samples, stating the potential for inconclusive results, and noting that similar compounds would have been present during construction of the towers."
06:49:46 <Bike> probably they've been infilitrated
06:50:27 <fowl> who knows what they did or didnt test for, everything was under wraps
06:51:08 <elliott> Dual_EC_DRGB was an inside job?
06:52:09 <Bike> has anyone actually ever met anyone from wisconsin because i'm pretty sure it's not real
06:56:06 <fowl> Bike, ive been "there" but its possible everybody in the town was playing a joke on me
07:22:16 -!- MindlessDrone has joined.
07:27:58 -!- ter2 has quit (Ping timeout: 265 seconds).
07:29:58 -!- Tritonio has joined.
07:38:50 -!- slereah has joined.
07:50:47 <kmc> slelloreah
08:01:18 -!- tswett has joined.
08:01:18 -!- tswett has quit (Changing host).
08:01:18 -!- tswett has joined.
08:10:29 -!- Tritonio has quit (Quit: Tritonio).
08:11:14 -!- Tritonio has joined.
08:24:19 -!- conehead has quit (Quit: Computer has gone to sleep).
08:28:14 -!- Patashu has joined.
08:28:33 -!- Patashu_ has joined.
08:28:34 -!- Patashu has quit (Disconnected by services).
08:30:31 -!- password2 has quit (Ping timeout: 252 seconds).
09:01:24 <Taneb> @run [(m*m-n*n,2*m*n,m*m+n*n)|m<-[1..],n<-[1..m],odd m/=odd n,gcd m n==1]
09:01:28 <lambdabot> [(3,4,5),(5,12,13),(15,8,17),(7,24,25),(21,20,29),(9,40,41),(35,12,37),(11,6...
09:19:38 -!- Tritonio has quit (Ping timeout: 240 seconds).
09:19:56 -!- Tritonio has joined.
09:40:09 -!- scoff has joined.
09:44:24 -!- shikhout has joined.
09:47:32 -!- shikhin has quit (Ping timeout: 252 seconds).
09:47:34 -!- shikhout has changed nick to shikhin.
10:02:17 -!- Patashu_ has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
10:02:47 -!- Patashu has joined.
10:07:56 -!- ejls_ has joined.
10:08:07 -!- ejls has quit (Read error: Connection reset by peer).
10:13:17 -!- boily has joined.
10:43:09 -!- yorick has joined.
10:50:27 -!- ejls_ has changed nick to ejls.
11:01:27 -!- boily has quit (Quit: ＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿).
11:31:42 -!- idris-ircslave has joined.
11:33:55 <int-e> hmm. the @faq social experiment is showing first results. "<carter> int-e: is lambda bot heavily loaded lately? @faq is acting funny, and some of edward's lens golf hit mueval limit exceeded on tiny examples"
11:34:47 <int-e> (I'll have an eye on the load now. Since lambdabot is running inside a VM I can only assess it indirectly.)
12:04:12 <HackEgo> [wiki] [[Special:Log/newusers]] create * Maximaman * New user account
12:07:56 -!- edwardk has joined.
12:12:26 -!- Tritonio has quit (Ping timeout: 240 seconds).
12:16:52 -!- nucular has joined.
12:16:52 -!- nucular has quit (Changing host).
12:16:52 -!- nucular has joined.
12:21:08 -!- Sorella has joined.
12:21:58 -!- ter2 has joined.
12:22:19 -!- Tritonio has joined.
12:25:42 -!- tswett has quit (Ping timeout: 265 seconds).
12:31:06 -!- Sgeo has quit (Read error: Connection reset by peer).
12:31:18 -!- edwardk has quit (Ping timeout: 240 seconds).
12:34:42 -!- edwardk has joined.
12:40:13 -!- edwardk has quit (Read error: Connection reset by peer).
12:42:02 -!- Tritonio has quit (Ping timeout: 252 seconds).
12:43:07 -!- Patashu has quit (Remote host closed the connection).
12:43:18 -!- Patashu has joined.
12:52:17 -!- Patashu has quit (Ping timeout: 265 seconds).
12:56:53 -!- tromp has joined.
13:02:17 -!- tromp has quit (Remote host closed the connection).
13:15:14 -!- edwardk has joined.
13:26:03 -!- ter2 has quit (Ping timeout: 252 seconds).
13:31:07 -!- MindlessDrone has quit (Quit: MindlessDrone).
13:40:22 -!- Sprocklem has quit (Ping timeout: 252 seconds).
13:43:18 -!- MindlessDrone has joined.
13:48:56 -!- edwardk has quit (Ping timeout: 276 seconds).
13:54:40 -!- nooodl has joined.
13:57:50 -!- ter2 has joined.
14:24:34 -!- Sprocklem has joined.
14:26:09 -!- xpte has joined.
14:27:14 -!- tertu3 has joined.
14:30:18 -!- ter2 has quit (Ping timeout: 240 seconds).
14:37:47 -!- KingOfKarlsruhe has joined.
14:38:06 -!- tswett has joined.
14:38:06 -!- tswett has quit (Changing host).
14:38:06 -!- tswett has joined.
14:40:28 -!- password2 has joined.
14:40:49 -!- password2 has quit (Max SendQ exceeded).
14:42:18 -!- password2 has joined.
14:43:45 -!- password2 has quit (Max SendQ exceeded).
14:44:20 -!- password2 has joined.
14:49:32 -!- KingOfKarlsruhe has left.
14:54:48 -!- ter2 has joined.
14:58:29 -!- tertu3 has quit (Ping timeout: 276 seconds).
14:59:47 -!- glogbackup has quit (Ping timeout: 276 seconds).
15:10:31 <HackEgo> [wiki] [[Hsamsniarb]] N http://esolangs.org/w/index.php?oldid=39395 * 188.67.13.130 * (+1032) Created page with "Hsamsniarb is a joke programming language you can't even create a "Hello, World!" program in. (Hsamsniarb is Brainsmash backwards.) == Interpreters == The only current interp..."
15:22:38 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
15:25:14 <fizzie> http://sprunge.us/DcJO <- that was supposed to be a 3 TB disk.
15:25:28 <fizzie> That's what the "WD30" stands for and all.
15:27:22 <elliott> fizzie: maybe you need USB 3
15:30:45 <fizzie> There's no USB 3 support in the disk enclosure.
15:31:01 <fizzie> Anyway, #esoteric told me 3 TB disks are no problem.
15:35:07 <fizzie> http://www.sharkoon.com/?q=en/node/1228 "Max. HDD capacity 2TB"
15:35:13 <fizzie> Shouldn't've trusted #esoteric, I see.
15:40:07 -!- tertu3 has joined.
15:43:02 -!- ter2 has quit (Ping timeout: 255 seconds).
15:44:33 -!- shikhout has joined.
15:47:14 -!- shikhin has quit (Ping timeout: 252 seconds).
15:47:15 -!- shikhout has changed nick to shikhin.
15:55:17 -!- tertu3 has quit (Read error: Connection reset by peer).
15:55:35 -!- tertu3 has joined.
16:01:05 -!- slereah has quit (Remote host closed the connection).
16:05:55 -!- tromp has joined.
16:06:58 -!- Sprocklem has quit (Quit: leaving).
16:10:02 -!- tromp has quit (Ping timeout: 240 seconds).
16:10:12 -!- password2 has quit (Quit: Leaving).
16:16:20 -!- tertu3 has quit (Ping timeout: 255 seconds).
16:39:11 -!- FreeFull has joined.
16:42:19 -!- FreeFull has quit (Client Quit).
16:47:28 -!- FreeFull has joined.
16:51:13 <mroman> Trick Question: Is a a=(a)a; legal C code?
16:52:06 -!- nooodl_ has joined.
16:54:10 <FireFly> I'd say no, but I'm probably wrong
16:54:14 <Taneb> I'm going with yes
16:56:08 -!- nooodl has quit (Ping timeout: 276 seconds).
16:56:18 <mroman> It is legal with a typedef
16:56:34 <FireFly> I thought types and values shared a namespace, and it'd error or something
16:56:50 <mroman> FireFly: You can't define int int
16:56:57 <mroman> but you cane define typedef int a; a a
16:57:26 <mroman> but let me check again
16:57:26 <fizzie> I can't see how the (a)a part is legal.
16:58:16 <fizzie> That's because the scope of the variable "a" starts at the end of the declarator, and is therefore visible in the initializer.
16:58:34 <fizzie> Also, I think "a a=a*a" might be undefined behaviour, due to arithmetic on an uninitialized value.
16:58:51 <fizzie> Or at least potentially undefined if the type has trap representations, or w/ever.
16:59:47 <fizzie> (You also can't write { typedef int a; a a = 0; } so that they're in the same scope; the typedef needs to be outside the block.)
16:59:49 <mroman> it's undefined probably
16:59:59 <mroman> but you can go for a a=10;return a*a;
17:00:55 <Taneb> What if a is a struct rather than a typedef?
17:01:15 <FireFly> unless you typedef it, it would be referred to as struct a
17:01:31 <fizzie> Struct, union and enum tags are in a different namespace than ordinary identifiers.
17:01:53 <fizzie> C++ lets you refer to "struct a" as plain "a", though.
17:03:24 <kmc> beaky showed up in ##crypto
17:09:24 <kmc> I recall seeing some C code that does typedef struct { ... } foo, *fooPtr;
17:09:33 <kmc> if for some reason you want to write fooPtr instead of *foo
17:09:46 <kmc> this confused me greatly because I was a wee lad and did not yet understand C's fucked up declaration syntax
17:10:12 <fizzie> I guess maybe copied from the Windows API?
17:10:28 <mroman> I don't get why people typedef pointers
17:10:31 <fizzie> It's full of typedef ... FOO, *PFOO, *LPFOO kind of stuff.
17:10:40 <mroman> You can't see it's a pointer anymore
17:10:49 <elliott> if you're unable to see the letter "P", sure
17:11:11 <mroman> is PAIR then a pointer to AIR?
17:11:17 <mroman> or just a regular PAIR struct?
17:12:28 -!- Sprocklem has joined.
17:12:29 <elliott> if you can't deal with that insignificant ambiguity I have no idea how you manage to use natural language
17:13:09 -!- MoALTz has joined.
17:15:50 <kmc> or use the thing that's unambiguous and already part of the language
17:19:07 <lifthrasiir> well, that's almost a legacy, since it is partially attributed to the near/far divide of pointers in the Win16 era
17:22:16 <fizzie> "Drive command "Execute SMART Extended self-test routine immediately in off-line mode" successful. Testing has begun. Please wait 395 minutes for test to complete."
17:22:54 <Bike> gotta be sure.
17:24:06 <fizzie> (The disk works in this other USB dock I had, so I guess I'll just replace the old box with a more modern box.)
17:26:50 <zzo38> Is there a simple way to cause a program to wait for completion of SMART tests? Once I modified a Python program to add these test (and other changes, too), but I had to hard-code in the amount to wait.
17:27:48 <fizzie> I think the only way to know when it's done is to poll the drive. (The drive reports a "recommended polling time", too.)
17:36:38 -!- password2 has joined.
17:37:07 <zzo38> How would you do that?
17:40:28 <fizzie> I don't really know how you do it programmatically. With the "smartctl" tool, I guess one way would be to keep watching the self-test log for changes. There was something in the documentation about disks being different on whether they list the current self-test status in the "capability" command.)
17:40:50 <fizzie> "Their results are reported in the Self Test Error Log, readable with the ´-l selftest´ option. Note that on some disks the progress of the self-test can be monitored by watching this log during the self-test; with other disks use the ´-c´ option to monitor progress."
17:42:24 -!- conehead has joined.
17:44:34 <zzo38> Do you think this is OK for the C interface for Text Adventure Intermediate Language? http://sprunge.us/XWgX
18:08:24 <int-e> and why does I_QUIT come first...
18:15:43 <int-e> zzo38: why is there a taillib_open/_close pair rather than a Game *taillib_read(FILE *)?
18:18:24 <zzo38> int-e: I_QUIT comes first just because it is numbered zero.
18:18:53 <int-e> fwiw, the question about I_QUIT wasn't a serious question.
18:19:06 <zzo38> The reason there is _open and _close is that the _close will free any memory allocating by the _open function.
18:19:23 <int-e> sounds more like an _free to me.
18:20:29 <zzo38> Also, you can read/write at the current position in the file, so the same file can contain other things too (such as pictures, debug information, etc) if you want to do that.
18:21:37 <int-e> I'd see that as an argument in favour of calling _open _read instead.
18:22:01 <int-e> ("Read one game description"; it seems that in principle you could have several.)
18:22:23 <zzo38> You can call taillib_open(stdin) too if you want to.
18:23:17 <int-e> That's even more reason to call it _read.
18:23:23 <zzo38> Thank you for your suggestion though; I could rename them, then.
18:23:59 <int-e> Anyway the interface looks reasonable at a glance, and I'm not going to think about it in detail, i.e. from an actual game creation or execution perspective.
18:26:10 <zzo38> I also intend to have a Haskell interface and a SQL interface available. Would you have idea about this, and/or do you like to have the interface for other programming language too?
18:29:02 <int-e> (One thought perhaps, since I had it while going over the interface: If I were using a library to create game code, I'd appreciate some builder interface for sequences of instructions where I can add them sequentially, possibly with some support for labels. I guess a similar point can be made for the Text/Property/Object/Verb/Noun/Phrase arrays in the Game struct itself.)
18:32:00 <zzo38> Yes it would help. Just after I posted the file I forgot that I didn't add the unsigned short taillib_encode_jump(int pos,int dst) function into the header file yet; but then I did, and that is used for encoding branch targets.
18:33:10 <zzo38> I could add a function for appending an instruction, if that would help.
18:33:48 <zzo38> If doing in SQL and in Haskell, this appending is done more easily without a function call, but in a C code probably it would help to have such a thing. OK I can add it on
18:42:25 <kmc> fungot: nobody knows the wreck of the soul the way you do
18:42:25 <fungot> kmc: muito bom! shocking. but most of the plane wasn't remote-controlled; if you don't even bother. jaybedwell perfectly knows what they called the map but it really doesn't look too good
18:43:34 -!- zzo38 has quit (Remote host closed the connection).
18:51:31 -!- vravn has quit (Quit: vravn goes).
18:56:10 -!- vravn has joined.
18:56:36 -!- tswett has quit (Quit: tswett).
19:03:03 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube*
19:03:17 <fizzie> Should've guessed from the plane.
19:08:07 <fungot> Selected style: discworld (a subset of Terry Pratchett's Discworld books)
19:08:19 <fungot> FreeFull: ' it's a trick. the wish is trying to learn fnord' he murmured, as he struck. ' you did well there," said granny
19:09:45 <fungot> olsner: " so it's back to the suffering head waiter. ' same again, mister.'
19:14:59 -!- password2 has quit (Ping timeout: 255 seconds).
19:27:25 -!- Phantom_Hoover has joined.
19:42:06 -!- nucular has quit (Quit: Switching to phone (forced)).
20:00:08 -!- AnotherTest has joined.
20:20:52 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:39:54 <kmc> testing a memory error detector is kind of fun: https://github.com/kmcallister/vgrs/blob/master/test/memcheck.rs
20:39:58 <kmc> lots of working around optimizations
20:40:33 <kmc> also the entire program is UB, of course
20:40:50 <kmc> undefined behavior
20:41:05 <Taneb> The only thing I could think of was "Utter Bullshit"
20:44:09 <kmc> basically the same
20:44:16 <kmc> I might start using that :)
20:44:52 <Bike> wait does rust have a definition
20:46:01 <olsner> can you make a working C program entirely out of UB?
20:46:02 -!- tswett has joined.
20:46:03 -!- tswett has quit (Changing host).
20:46:03 -!- tswett has joined.
20:46:19 <Bike> a working gcc program, perhaps
20:47:12 <kmc> Bike: http://static.rust-lang.org/doc/master/rust.html
20:47:18 <olsner> it seems trivial, but then again lots of stuff actually *is* defined, and you can't use any of it
20:52:13 <olsner> right, I meant something more like working in most/some C compilers but completely outside C the language ... technically it probably wouldn't be a C program at all
20:52:45 <ion> http://flossgold.tumblr.com/
20:54:27 <kmc> are those all from http://opensslrampage.org/
20:59:26 -!- Patashu has joined.
21:03:10 <Bike> http://codepad.org/FNeda0KY i am afraid
21:07:18 -!- AnotherTest has quit (Ping timeout: 240 seconds).
21:10:13 <olsner> speaking of openssl, http://www.libressl.org/ got a nice redesign recently to "motivate" people to donate
21:10:22 <olsner> use a browser with blink tags for the full effect
21:10:56 <mroman> I was disappointed my IE didn't support those
21:11:30 <olsner> too bad it only works on people with an aversion to Comic Sans
21:12:00 <olsner> pre-chromium opera does
21:12:30 <mroman> they should've used marquee
21:12:44 <mroman> FF still supports marquee
21:13:09 <mroman> Else my legit webshop page would look stupid
21:13:13 <mroman> if marquee wouldn't work
21:13:30 -!- nisstyre has joined.
21:13:34 <mroman> ain't no legit webshop without marquee
21:16:39 <mroman> I'm not sure if I can ask JavaScript to give me all blink tags
21:16:52 <mroman> and make them blink again with JavaScript sorcery
21:17:45 <kmc> implement <marquee> and <blink> as Web Components
21:18:14 <kmc> it's like a co-polyfill
21:18:30 <olsner> speaking of marquees, http://marquee.olsner.se/ (all warranties void and null. in chrome, make sure to stop it before it eats your ram)
21:19:50 -!- oerjan has joined.
21:20:16 <olsner> I wonder if putting each iframe in its own domain could fool chrome into making a new process for each one, that might make it even more fun
21:20:46 -!- Sprocklem has quit (Quit: Bye).
21:22:40 -!- nooodl has joined.
21:24:35 -!- Patashu has quit (Ping timeout: 255 seconds).
21:25:57 <kmc> servo will run them in different Rust tasks
21:25:58 -!- nooodl_ has quit (Ping timeout: 240 seconds).
21:26:00 <kmc> except that iframes are broken right now
21:26:13 <kmc> also <iframe sandbox> from the same origin
21:37:49 <HackEgo> barronticoin catizatcoin mismcoin legapuishcoin billcoin teencoin mismcoin beaucoin *wcoin iinatacoin sarcoin fernacoin hartercoin gabticoin sungecoin plodedintecoin symecoin fancoin woelcoin tranksgivecoin
21:38:37 <olsner> apparently "site" in chrome's process-per-site or -site-instance counts subdomains and different ports as the same site, so that doesn't seem to work...
21:39:14 <kmc> it probably goes by the same origin policy including document.domain
21:40:23 <kmc> by assigning to document,domain, any two documents can elect at any time to become same-origin as long as they share a domain suffix more specific than any of the public suffixes (https://publicsuffix.org/)
21:40:29 <kmc> document.domain*
21:41:00 <kmc> and when things are same-origin, you can share JavaScript objects and DOM nodes etc. between them
21:41:12 <kmc> so they pretty much have to run in the same thread, at least as far as scripting is concerned
21:44:56 -!- shikhout has joined.
21:47:40 -!- shikhin has quit (Ping timeout: 252 seconds).
21:47:40 -!- shikhout has changed nick to shikhin.
21:48:02 -!- yorick has quit (Remote host closed the connection).
21:52:00 -!- Bicyclidine has joined.
22:08:17 -!- tswett has quit (Quit: tswett).
22:14:54 -!- HackEgo has quit (Remote host closed the connection).
22:15:07 -!- HackEgo has joined.
22:19:50 -!- TodPunk has quit (Ping timeout: 276 seconds).
22:24:43 -!- boily has joined.
22:35:42 -!- TodPunk has joined.
22:38:34 <kmc> the great thing about parallel programs is that if you don't like the result you can try again
22:39:03 <Bicyclidine> the one parallel program i've ever maintained gives consistent results oh no :(
22:39:38 <oerjan> i think haskell programs using the par function usually do that.
22:42:22 <oerjan> int-e: my @messages didn't show up until i did it in private - although it may be that it was just delayed because i also got a "You don't have any messages" simultaneously
22:42:44 <oerjan> could someone try @tell'ing me something.
22:43:02 <Bicyclidine> @tell oerjan the owls are not what they seem
22:43:04 <int-e> @tell oerjan something
22:43:15 <boily> @tell oerjan why owls?
22:43:38 <Bicyclidine> @ask oerjan boily have you not even seen the greatest anime of all time, Twin Peaks
22:43:49 <oerjan> argh please stop i'm trying to test something here...
22:44:13 <boily> Bicyclidine: eeeeeeeeh... not sure that's an anime...
22:44:13 <oerjan> ok this time they came promptly.
22:44:34 <Bicyclidine> boily: how would you know if you haven't seen it jerk
22:45:59 <boily> Bicyclidine: because David Lynch has a chicken. your argument is invalid. HTH. *black woman hand gesture*
22:46:04 <shachaf> int-e: What happened to lambdabot command @read?
22:46:14 <oerjan> Bicyclidine: it is possible i have accidentally glimpsed a twin peaks episode, way back
22:47:09 <int-e> there's no @read command as far as I can see
22:47:47 <int-e> oerjan: Hmm. It's possible that messages get out of order.
22:48:48 <int-e> hmm. oh. very old one ...
22:49:00 <shachaf> int-e: It did the opposite of @show, of course.
22:49:18 <oerjan> int-e: when i did @messages in channel (after lambdabot told me i had one), it didn't reply anywhere, until i did @messages in private, and then both responses came promptly.
22:49:20 <int-e> Author: James Cook <mokus@deepbondi.net>
22:49:20 <int-e> Date: Fri Feb 22 10:16:52 2013 -0800
22:49:20 <int-e> Removed @read command
22:50:12 <oerjan> technically you can do @read with @run var $ or thereabouts.
22:50:18 <int-e> oerjan: there's a recent change to the @tell module that I'll double-check (not tonight though)
22:50:41 <oerjan> however it worked fine on the further test.
22:51:18 <oerjan> since i usually do @messages-loud, i may not have noticed if it behaved strange before.
22:52:36 <oerjan> boily: btw as our resident chicken expert, you need to be introduced to fowl, here.
22:54:57 * oerjan notices that @show doesn't add a space...
22:55:36 <boily> oerjan: which kind of fowl? can it be a fduck too?
22:55:41 <int-e> ok, but it shows a string, so it's hard to abuse ... unless somebody uses " as a bot prefix?
22:55:55 <oerjan> boily: you'll have to ask em
22:56:59 <lambdabot> gwern says: "<@gwern> (oh geez _Garden of Words_ turns out to be yet another anime with a teacher/student romance. well, why not, it's as quinetessentially japanese as cousin incest, apparently... -_-)"
22:57:09 <lambdabot> gwern says: "<@gwern> (oh geez _Garden of Words_ turns out to be yet another anime with a teacher/student romance. well, why not, it's as quinetessentially japanese as cousin incest, apparently... -_-)"
22:57:14 -!- nooodl_ has joined.
22:57:14 -!- metasepia has joined.
22:57:26 <HackEgo> 84) <fax> okay I see it now, quines do exist
22:58:24 <boily> oerjan: AAAAAAAAAAAAAAAAAAAAAAAAAAAAH!
22:58:27 <boily> fowl: AAAAAAAAAAAAAAAAAAAAAAAAAAAAAH!
22:58:41 <boily> fowl: uhm. since when are you here?
22:59:49 -!- nooodl has quit (Ping timeout: 252 seconds).
23:00:20 <fowl> since a couple days ago
23:02:12 <oerjan> this is where we eerily discover that fowl and boily are next door neighbors.
23:02:48 <boily> that reminds me I haven't tried to reroujo the channel in a long time...
23:02:58 <fowl> actually my next door neighbor is on freenode :D
23:03:08 <boily> fowl: do you live in Montréal?
23:03:37 <fowl> no i live in the armpit of the US
23:03:59 <fowl> the summers are extra hot and humid, winters extra cold, tornados, floods :(
23:05:17 -!- Sgeo has joined.
23:05:34 <oerjan> boily: maybe i should try to ##nomic you instead.
23:06:29 <boily> I am a couillon and fier de l'être.
23:06:39 -!- Sprocklem has joined.
23:07:29 <oerjan> (let's see if i can do it both ways.)
23:08:03 <int-e> h-lens has been a disappointment so far. no lensy code golfing whatsoever in the last 12 hours ;-)
23:10:31 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
23:12:20 <lambdabot> s -> Getting (Endo [a]) s a -> [a]
23:14:11 <kmc> @source Endo
23:14:23 <kmc> i suspect newtype Endo a = Endo (a -> a)
23:15:12 <int-e> oh. Data.Monoid. Yes.
23:15:32 <fowl> what language is that
23:15:51 <int-e> @run (1,2,3)^..each
23:20:14 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
23:21:38 -!- idris-ircslave has quit (Ping timeout: 240 seconds).
23:22:14 -!- Melvar has quit (Ping timeout: 276 seconds).
23:22:27 <int-e> oerjan: I don't know :/
23:23:24 <kmc> fowl: where is the armpit
23:24:12 <Bicyclidine> "Note: str2num uses the eval function to convert the input argument. Side effects can occur if the string contains calls to functions" oh my god get me out of here
23:24:39 <oerjan> i thought the cold was in the north and the tornados in the south, so somewhere in the middle?
23:24:44 <kmc> that was my second guess
23:25:07 <kmc> plenty of tornadoes in the north too http://upload.wikimedia.org/wikipedia/commons/3/35/Tornado_Alley.gif
23:26:04 <boily> kmc: think I should ask them the The Question?
23:26:25 <boily> fowl: what are your approximate coördinates and body weigh?
23:26:47 <kmc> boily: also I only weigh 88 kgf now
23:26:52 <kmc> don't remember what number I gave you before
23:27:37 <fowl> boily, st louis, missouri and 180lb
23:27:43 <kmc> i,i 13 stone 13
23:28:21 <kmc> kilograms-force
23:28:29 <kmc> kg being a unit of mass not weight
23:28:35 <kmc> right. scrub
23:28:52 <kmc> as far as I know my gravitational mass is equal to my inertial mass
23:28:54 * boily mapoles Bicyclidine
23:28:58 <oerjan> kmc: i'm sorry, but you cannot use kilograms-force, the proper unit is the new ton hth
23:29:06 <kmc> btw wtf is a mapole
23:29:07 <Taneb> boily, I weigh 576N
23:29:11 <kmc> oerjan: what's wrong with the old ton
23:29:14 <HackEgo> A mapole is a thwackamacallit built from maple according to Canadian standards.
23:29:22 <kmc> that clears it all up
23:29:32 <boily> Taneb: woah woah woah. let me open up the File first!
23:30:36 * oerjan swats boily for misspelling the The File -----###
23:30:41 <boily> kmc: grats on the weight loss!
23:30:52 * boily keels over from the dexterous hit
23:31:25 <Taneb> boily, that number should be roughly in line with previous data
23:31:35 <boily> Taneb: looks like so.
23:32:07 <kmc> thanks boily
23:32:24 <kmc> I guess you don't know whether I wanted to lose weight or not
23:32:28 <kmc> but i did, as it happened
23:32:46 <kmc> i didn't really do anything other than move to a city with a lot of hills and start biking to work every day
23:35:08 -!- Melvar has joined.
23:36:26 <int-e> ok, no wonder lensy code runs into timeouts so often; the best time I've seen for (1,2,3)^.. each now is 2.3 seconds, and the timeout is effectively 3.5...
23:37:34 <Taneb> > (1,2,3) ^.. each
23:37:34 <int-e> not the way mueval works
23:38:02 <int-e> elliott: imagine starting a fresh ghci each time, that's about what happens
23:38:19 <int-e> it's spending a lot of time loading packages dependencies
23:38:36 <int-e> wait. *you* should know that
23:40:04 <oerjan> elliott took a mind wipe after the lambdabot switchover.
23:41:40 <boily> elliott: are you still yourself?
23:43:25 <Bicyclidine> maybe elliott has gone through some important life events, like learning snobol. causes major changes, snobol does
23:44:27 <HackEgo> legalcoin greturacoin glycoin colangcoin concoin porcoin litecoin auschecoin befulcoin cinacoin ola/mcoin admismcoin disophcoin qwecoin 216.4coin hjhersigcoin liquishycoin cobcoin infcoin surfarcoin
23:44:52 <oerjan> once the snobol gets rolling you don't know where it'll end up
23:44:54 <kmc> there is a restaurant chain in Boston named Legal Sea Foods
23:46:50 <elliott> int-e: I thankfully managed to forget most things about lambdabot
23:46:58 <elliott> int-e: plus I spent most of my time trying to replace mueval
23:47:02 <int-e> and it's slower than it was with ghc 7.6.3!
23:47:11 <shachaf> with, uh, dolio and ddarius and those folks
23:47:44 <shachaf> there's one near kendall station, right?
23:48:08 <shachaf> not too much in the way of vegetarian food
23:48:10 <Taneb> I do not believe I have ever been to any Boston
23:48:27 <Taneb> Although I have been to Kendal
23:48:46 <Taneb> Bicyclidine, what language is that?
23:48:54 <int-e> way slower actually; it takes 1.5 seconds instead of 1.2 seconds CPU time, but real time used to be close to CPU time and now it's exceeding CPU time by 50% and more.
23:49:22 -!- nooodl_ has quit (Quit: Ik ga weg).
23:50:30 -!- copumpkin has joined.
23:50:45 <shachaf> copumpkin: were you at legal sea foods that one time
23:53:24 <Bicyclidine> sprintf('''%d'',', [64;66;191]) => '64','66','191', oh that's convenient
23:53:43 <Bicyclidine> sprintf('''%s'',', ['foo';'bar';'baz'] => fbboaaorz
23:54:45 -!- copumpkin has quit (Client Quit).
23:57:59 <kmc> oh, happy earth day
23:58:29 <Bicyclidine> twitter has tried to make it #SendYourManNudesDay for some reason, little realizing that nobody wants to see my man nudes
23:58:46 <kmc> interesting way to celebrate the earth
23:59:36 -!- tromp has joined.
00:02:59 <oerjan> Bicyclidine: it doesn't say they have to be _of_ you hth
00:05:11 -!- tswett has joined.
00:05:11 -!- tswett has quit (Changing host).
00:05:12 -!- tswett has joined.
00:06:33 -!- Sprocklem has quit (Quit: Bye).
00:11:58 -!- Melvar` has joined.
00:14:41 -!- Melvar has quit (Ping timeout: 264 seconds).
00:15:25 -!- Melvar`` has joined.
00:15:32 -!- Melvar`` has changed nick to Melvar.
00:17:23 -!- Melvar` has quit (Ping timeout: 255 seconds).
00:17:25 -!- copumpkin has joined.
00:17:41 <kmc> just got an error message with a 20 kB gcc command line in it
00:22:52 -!- adu has joined.
00:22:59 <int-e> Ooops ... not using dynamic linking, and a base library compiled with split objects is going to hurt linking time a lot, especially the latter.
00:23:39 <Jafet> Just got an error message with a 2TB hard drive in it
00:25:59 <boily> Just got an error message that was uphill both way, and it was snowing.
00:26:21 <oerjan> hm so lambdabot would be better off _without_ split objects?
00:27:03 <oerjan> maybe you could run mueval in a sandbox
00:27:07 <int-e> I believe so. I'll benchmark before I change the setup though.
00:27:31 <int-e> I can just recompile ghc whichever way I prefer.
00:27:46 -!- Melvar` has joined.
00:28:21 <int-e> (sandboxes won't help with the base library anyway)
00:28:46 <elliott> int-e: idea: have mueval import everything and get it linked in, and then use one of the process state freezing things.
00:28:57 <elliott> then you can just thaw the process for each evaluation. would that work?
00:28:59 <Jafet> I wonder if you can make a fork of ghci that forks after linking everything
00:29:17 <int-e> elliott: I don't know. It's quite plausible.
00:29:18 <oerjan> well i just meant that you might want lambdabot itself to use split objects even if mueval doesn't. just thinking wildly here.
00:29:22 <Jafet> The parent ghci becomes while(...) fork()
00:29:30 <kmc> imo it should coredump
00:29:53 -!- Melvar has quit (Ping timeout: 252 seconds).
00:30:08 <int-e> All of these approaches will require some RTS tweaking, to set up the threads (and pipes between them) again on restart.
00:30:20 <Jafet> coredump to ramdisk
00:30:31 <elliott> int-e: there's some process freezing stuff in linux nowadays that might be able to do it transparently
00:30:32 <Jafet> Isn't forkProcess enough?
00:30:37 <elliott> Jafet: if you do that you might as well just port @run to use the repl library
00:30:38 -!- nisstyre has joined.
00:30:59 <int-e> Jafet: in the presence of threads and pipes? no.
00:31:17 -!- Melvar`` has joined.
00:31:26 <elliott> int-e: http://criu.org/Main_Page
00:31:29 <Jafet> "repl: IRC friendly REPL library." woah
00:32:58 -!- Melvar` has quit (Ping timeout: 240 seconds).
00:35:11 <int-e> elliott: bookmarked
00:36:10 <Jafet> "mount: ntfs_pread failed: Input/output error" time to get a new disk
00:36:43 <int-e> before you do, does dmesg show hardware read errors?
00:37:47 <Jafet> Yes. (Oddly, I was looking at /var/log/dmesg, which does not. I guess they're in syslog.)
00:38:10 <Jafet> "Current pending sector count: 1430"
00:38:22 -!- Melvar has joined.
00:38:37 <int-e> time to get a new disk
00:39:53 -!- Melvar`` has quit (Ping timeout: 264 seconds).
00:42:51 <Bicyclidine> semantic fascination: matlab foo{[]}, that is extracting no indices of the cell array foo, is not just an empty array, but in fact the absence of value
00:42:55 -!- Melvar has quit (Ping timeout: 252 seconds).
00:43:23 <Bicyclidine> disp(foo{[]}) => error not enough arguments, disp(foo{[]}, 3) => 3
00:43:37 <Bicyclidine> and disp(4,3) => error too many arguments.
00:43:56 -!- Melvar has joined.
00:49:13 -!- Melvar` has joined.
00:51:17 -!- Melvar has quit (Ping timeout: 264 seconds).
00:51:17 -!- tromp has quit (Ping timeout: 264 seconds).
00:53:50 -!- Melvar` has quit (Ping timeout: 255 seconds).
00:56:25 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
01:00:26 -!- adu has quit (Quit: adu).
01:01:40 -!- Melvar` has joined.
01:03:28 -!- boily has quit (Quit: INCONSPICUOUOUOUS CHICKEN).
01:03:33 -!- metasepia has quit (Remote host closed the connection).
01:07:29 -!- tswett has quit (Quit: tswett).
01:08:43 <lambdabot> Applicative f => f a -> f (a -> b) -> f b
01:08:59 <Sgeo> flip (<*>) or something else?
01:12:37 -!- adu has joined.
01:15:29 <int-e> elliott: impressive runtime differences: http://sprunge.us/OeCM
01:16:13 <int-e> oerjan: you showed an interest in that topic, too
01:16:22 <elliott> int-e: that should make lambdabot much more usable
01:16:44 <elliott> it was great giving things to a hacked-up-repl-based @run and getting responses instantly though :)
01:21:12 -!- newsham has quit (Ping timeout: 245 seconds).
01:21:31 -!- newsham has joined.
01:22:44 <oerjan> Sgeo: it performs the actions in the opposite order of what flip (<*>) does
01:23:46 <Sgeo> https://www.youtube.com/watch?v=BKorP55Aqvg
01:29:30 <oerjan> @run flip runState 0 $ (<**>) get (modify (+1) >> gets (+))
01:29:44 <oerjan> @run flip runState 0 $ (flip (<*>)) get (modify (+1) >> gets (+))
01:31:34 <oerjan> @run [1,2,3] <**> [pred, id, succ]
01:31:42 <int-e> elliott: Hmm, with mueval the picture is different. This needs further investigation
01:31:47 <oerjan> @run flip (<*>) [1,2,3] [pred, id, succ]
01:32:16 <oerjan> @run flip (<*>) [1,2,4] [pred, id, succ]
01:32:23 <oerjan> @run flip (<*>) [1,2,4] [pred, id, succ]
01:32:49 <oerjan> @run [1,2,4] <**> [pred, id, succ]
01:33:14 <oerjan> @run [1,2,4] <**> [pred, id, succ]
01:34:45 <int-e> elliott: http://sprunge.us/BKRW
01:35:31 <elliott> the difference seems a bit large for it to not be doing *something* differently there...
01:36:04 <int-e> Anyway, it's ... early. I'll regret that tomorrow. Good night!
01:36:10 <elliott> maybe it's skipping over shared libs it doesn't want to load or something
01:36:13 -!- Melvar`` has joined.
01:36:38 <int-e> (CEST, you can do the math)
01:37:11 -!- Melvar` has quit (Ping timeout: 252 seconds).
01:57:18 -!- Melvar`` has quit (Ping timeout: 240 seconds).
01:57:33 -!- adu has quit (Quit: adu).
01:58:38 -!- Melvar`` has joined.
01:58:47 <fowl> can i use your bot for math?
01:58:55 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
01:58:59 <lambdabot> What module? Try @listmodules for some ideas.
01:59:36 <fowl> @run 333.0 / 2
02:00:21 <fowl> @run 500 * (1/3)
02:05:04 <fowl> @run 167 + 233
02:05:27 <oerjan> @run let fib = 0 : 1 : zipWith (+) fib (tail fib) in fib
02:05:29 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
02:06:29 <Bike> @run let fib = 0 : 1 : zipWith (+) fib (tail fib) in zipWith (/) fib (tail fib)
02:06:30 <lambdabot> [0.0,1.0,0.5,0.6666666666666666,0.6,0.625,0.6153846153846154,0.6190476190476...
02:06:57 <fowl> i will never understand haskell ._.
02:07:26 <fowl> the original esolang
02:07:41 <oerjan> no, that's INTERCAL hth
02:07:42 <Bike> @run zipWith (+) [3, 7, 982.9] [2,11,4]
02:08:46 <Jafet> @run flip (zipWith (/)) <*> tail $ fix $ scanl (+) 1 . (0:)
02:08:47 <lambdabot> [1.0,2.0,1.5,1.6666666666666667,1.6,1.625,1.6153846153846154,1.6190476190476...
02:09:16 -!- adu has joined.
02:09:33 -!- tswett has joined.
02:09:33 -!- tswett has quit (Changing host).
02:09:33 -!- tswett has joined.
02:10:44 <oerjan> Jafet: i was trying to go lightly on fowl by not giving the scanl version
02:11:05 <Bike> nah just throw more $ in there
02:12:15 <oerjan> hm a rare case where you need two $'s instead of . and $
02:12:42 <adu> @run do print "hello world"
02:12:45 <Bike> the more functions you use the better a programmer you are
02:13:05 <Bike> not in haskell
02:13:10 -!- Melvar`` has quit (Ping timeout: 265 seconds).
02:13:30 <oerjan> @run tail <**> zipWith (/) $ fix $ scanl (+) 1 . (0:)
02:13:31 <lambdabot> [1.0,0.5,0.6666666666666666,0.6,0.625,0.6153846153846154,0.6190476190476191,...
02:13:49 <Bike> oh yeah more fix is good too. fix everything
02:13:52 <adu> @run do args <- getFullArgs; print args
02:14:13 <oerjan> <**> doesn't help over flip (<*>) with reader monads
02:14:37 <oerjan> adu: lambdabot doesn't do IO actions.
02:14:43 <adu> oerjan: :/
02:16:53 <Jafet> @run system "rm -rf ~"
02:19:10 -!- quintopia has quit (Remote host closed the connection).
02:20:09 <adu> Jafet: bad, bad
02:21:17 -!- quintopia has joined.
02:22:28 <Jafet> `run rm –rf . # this would work though
02:22:28 <HackEgo> rm: cannot remove `–rf': No such file or directory \ rm: cannot remove `.': Is a directory
02:22:51 <Bike> is that... an emdash
02:23:33 <oerjan> `run rm -rf . # FIXED THAT FOR YOU
02:23:34 <HackEgo> rm: cannot remove directory: `.'
02:24:28 <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.
02:26:32 <oerjan> `run rm -rf * # these errors are so tiresome.
02:27:54 <HackEgo> 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ Wierd \ wisdom \ wisdom.pdf
02:28:17 <elliott> Unicode magic around the *, I guess?
02:29:01 <elliott> righ. starts with c ends with an ary.
02:29:27 <Jafet> Hmm, I never knew that rm would refuse to delete ..
02:29:46 <pikhq> It is something you aren't expecting. :)
02:30:03 <oerjan> Jafet: i think it's refusing to delete directories above the current one?
02:30:41 <Jafet> It refuses to delete .. as well.
02:31:03 <oerjan> .. is surely a directory above the current one.
02:31:53 <kmc> make a little birdhouse in your soul
02:32:12 <adu> @run showIntAtBase 18 (" abcdehilmnoprstuw"!!) 112992306848503458453611540092012927058485521833875357047724355402465282824863736272726650730740 ""
02:32:14 <lambdabot> "lambdabot should learn how to capture standard output and tell us what it is"
02:32:49 <oerjan> Jafet: alas the ghc install didn't get transfered to HackEgo's new host
02:33:47 <oerjan> insert joke about Gregor being evil here.
02:34:05 -!- tertu has joined.
02:38:16 <HackEgo> Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
02:39:56 -!- Melvar`` has joined.
02:44:55 <fowl> `:(){ :|:& };:
02:44:56 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: :(){: not found
02:45:28 <Bike> you need run to do shell stuff
02:45:30 <Jafet> You should test scripts on your own system before running them on hackego.
02:45:43 <Bike> `run :(){ :|:& };: # like this
02:46:16 <oerjan> i'd expected a somewhat slower response.
02:46:38 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ulimit: not found
02:46:40 <Bike> me too, but oh well
02:47:01 <HackEgo> core file size (blocks, -c) 0 \ data seg size (kbytes, -d) unlimited \ scheduling priority (-e) 0 \ file size (blocks, -f) 10240 \ pending signals (-i) 1950 \ max locked memory (kbytes, -l) 0 \ max memory size (kbytes, -m) unlimited \ open files (-n) 102
02:50:17 <Bike> http://www.libressl.org/ well at least i don't have the font installed
02:50:42 <Bike> wow, it actually uses <blink> instead of some css weirdness
02:51:27 <Jafet> "Donate now to stop the Comic Sans and Blink Tags."
02:51:30 -!- password2 has joined.
02:51:40 <Jafet> We're dealing with professionals here.
02:53:34 -!- tswett has quit (Quit: tswett).
02:53:50 <Bike> i read 'flensed' as 'flehmen', but it turns out what 'flensed' actually means is also grody
02:53:58 <Sgeo> Bike: it uses <blink> + CSS weirdness
02:54:09 <Bike> don't ruin the magic, sgeo.
02:57:03 <Jafet> Hmm, that is pretty magical
03:01:43 <HackEgo> [wiki] [[Hsamsniarb]] M http://esolangs.org/w/index.php?diff=39396&oldid=39395 * Oerjan * (+18) formatting
03:18:51 <kmc> blink { -webkit-animation: blink 1s; -webkit-animation-iteration-count: infinite; }
03:25:53 <Jafet> I wonder how many no*\.com are registered.
03:26:29 <Jafet> http://nooooooooo.com next shorter one that isn't parked
03:30:49 <Jafet> no.com is owned by google.no.
03:41:08 -!- Bicyclidine has joined.
03:44:57 -!- shikhout has joined.
03:47:44 -!- shikhin has quit (Ping timeout: 252 seconds).
03:47:45 -!- shikhout has changed nick to shikhin.
03:48:57 -!- Sorella has quit (Quit: It is tiem!).
04:01:03 -!- tromp has joined.
04:12:05 <Sgeo> What's the deal with bsalegal.org
04:12:19 <Sgeo> There's obviously a server serving at that domain, they're pretending there isn't?
04:12:45 <Sgeo> Or pointing to a server that's expecting a different Host: maybe?
04:14:12 <Sgeo> The Boy Scouts of America used to have... some website, with a similar name. The www version worked, without www it looked like it was a parked domain
04:31:44 -!- Melvar has joined.
04:32:18 -!- Melvar`` has quit (Ping timeout: 240 seconds).
04:48:51 -!- tromp has quit (Remote host closed the connection).
04:56:26 -!- tertu has quit (Quit: Leaving).
05:00:49 <fizzie> Sgeo: It's http://www.borkgroup.com/ that you get with no Host: header.
05:03:29 <fizzie> Also in re LibreSSL, huh, no "marquee-style: alternate; marquee-play-count: infinite; marquee-speed: fast;"?
05:11:41 -!- password2 has quit (Ping timeout: 264 seconds).
05:13:51 -!- douglass_ has quit (Quit: leaving).
05:13:53 <Sgeo> fizzie: should someone tell them that their server is weirdly configured?
05:14:31 <Bicyclidine> maybe it's your client that's weirdly configured, ever thought about that huh
05:29:11 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
05:34:02 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
05:36:19 <fizzie> Serving a "nothing to see here" page for an unknown host isn't such a weird thing to do.
05:36:50 <fizzie> Cf. http://nothingtoseehere.esolangs.org/
05:37:18 <fizzie> (I keep thinking to perhaps switch away from the wildcard DNS entry.)
05:37:34 <fizzie> Of course if there should be something at that domain, that's another thing.
05:39:22 -!- Bicyclidine has joined.
05:40:00 <Sgeo> fizzie: but why would unknown hosts be accessible without deliberate tampering with Host header?
05:40:24 <Sgeo> Wildcard DNS entry? But bsalegal doesn't... seem like a subdomain of borkgroup
05:41:34 <fizzie> The wildcard comment was re esolangs.org.
05:43:32 <fizzie> It could be a domain for some sort of legal campaign they've forgotten about.
05:43:46 <fizzie> Of course it could also be they'd want to have some page there but have messed it up.
05:44:33 <fizzie> I was expecting something related to the Business Software Alliance.
05:45:12 <fizzie> Which apparently these days is just "Software Alliance" even though they've kept the BSA acronym.
05:45:58 <Jafet> The BSA Software Alliance
05:46:58 <HackEgo> numcoin tackcoin bran+coin aircoin bookcoin gibbecoin flaticoin bitescrumpyxcoin fercoin runtercall0coin rejuncilibettentaineraquenctingcoin locodecoin exalamercoin takacoin alecoin stuffingpuzancoin aurestacardbarand.nexcoin []coin snaycoin emmensivcoin
05:47:35 <fizzie> That alecoin keeps popping up.
05:48:09 <fizzie> []coin, pronounced "squarecoin".
05:48:47 <lexande> not sure how square would feel about that
06:02:24 -!- MoALTz has quit (Quit: Leaving).
06:28:30 <Sgeo> Where are the conspiracy theorists claliming that ZeoSync was silenced?
06:30:06 <Bicyclidine> i don't know why you'd hire smale for a compression company, though
06:31:06 -!- Bicyclidine has quit (Quit: stupid computer. brb).
06:36:24 -!- Bike_ has joined.
06:36:59 -!- Bike_ has changed nick to Bicyclidine.
06:38:27 <Bicyclidine> it's pretty great how weird smale is with computers. he explains p=np in terms of algebraic geometry
06:46:35 -!- oerjan has quit (Quit: smalahove).
07:19:26 -!- MindlessDrone has joined.
07:27:34 -!- adu has quit (Quit: adu).
07:29:58 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
07:37:18 -!- FreeFull has quit.
07:44:20 -!- Tritonio has joined.
07:52:14 -!- tromp has joined.
07:56:29 -!- tromp has quit (Ping timeout: 252 seconds).
08:10:51 -!- conehead has quit (Quit: Computer has gone to sleep).
08:25:07 -!- Patashu has joined.
08:39:39 -!- augur has quit (Quit: Leaving...).
08:51:21 -!- augur has joined.
08:52:48 -!- Patashu_ has joined.
08:52:49 -!- Patashu has quit (Disconnected by services).
09:06:30 -!- slereah has joined.
09:19:54 -!- nooodl has joined.
09:31:22 -!- xpte has quit (Quit: Connection closed for inactivity).
09:36:44 -!- password2 has joined.
09:37:24 -!- password2 has quit (Max SendQ exceeded).
09:45:09 -!- shikhout has joined.
09:47:47 -!- shikhin has quit (Ping timeout: 252 seconds).
09:47:51 -!- shikhout has changed nick to shikhin.
09:53:44 -!- password2 has joined.
10:24:13 -!- boily has joined.
10:37:56 -!- Frooxius has quit (Quit: *bubbles away*).
10:38:10 -!- Frooxius has joined.
10:40:34 -!- nooodl has quit (Quit: Ik ga weg).
11:05:07 -!- boily has quit (Quit: MÖRK CHICKEN).
11:48:16 -!- nucular has joined.
11:48:16 -!- nucular has quit (Changing host).
11:48:16 -!- nucular has joined.
11:52:59 -!- sure has joined.
12:31:00 -!- Sgeo has quit (Read error: Connection reset by peer).
12:41:47 -!- AnotherTest has joined.
12:53:44 <int-e> . o O ( I should use that snapshotting stuff to beat Lost Vikings )
12:54:47 <b_jonas> int-e: wrong channel. try on #tasvideos
12:55:27 <int-e> http://criu.org/Main_Page
12:56:59 <quintopia> int-e: what do you mean? doesn't LV have a passkey system?
12:58:47 <int-e> quintopia: The levels get quite long towards the end.
12:59:34 -!- shikhin has quit (Ping timeout: 252 seconds).
13:01:34 <int-e> I've reached the 4RN4 one, and was surprised that the first exist was so easy to reach ... not realizing it was just the first of several (at least 3 but that's as far as I got)
13:10:18 <b_jonas> int-e: oh, you're doing the last two (and most difficult) levels now? good luck
13:10:34 <b_jonas> I only beat the last level twice
13:10:48 <b_jonas> lost vikings has a nice difficulty progressoin
13:28:04 -!- FreeFull has joined.
13:30:16 <slereah> Man now I have to work in logspace
13:30:27 <slereah> Perfect opportunity to work in
13:30:48 -!- Patashu_ has quit (Ping timeout: 265 seconds).
13:30:51 <slereah> Gota redefine all those bloody basic operations
13:35:26 <Jafet> You have to work in L?
13:40:42 <slereah> The thing I'm doing drops orders of magnitudes like crazy
13:43:45 <slereah> Well I am replacing all my values by their logs
13:43:58 <int-e> https://complexityzoo.uwaterloo.ca/Complexity_Zoo:L <-- L
13:44:20 <int-e> I'd say "work with logarithms" but maybe there is some better terminology.
13:44:50 <slereah> http://machineintelligence.tumblr.com/post/4998477107/the-log-sum-exp-trick
13:45:36 <FreeFull> slereah: How will you add numbers?
13:45:37 <int-e> I think log space is less confusing than logspace. Never mind, we got it in the end.
13:46:02 <Jafet> FreeFull: as rarely as possible
13:46:20 <int-e> floating point breaks down at 2^-1023, while representing numbers smaller than -1023 is no problem at all.
13:46:25 <FreeFull> Are you doing a lot of multiplications?
13:46:50 <slereah> int-e : What I do drops by one order of magnitude per cycle
13:47:04 <int-e> (the use of "undeflow" clarified the picture for me)
13:47:17 <Jafet> Why not rescale them per cycle?
13:47:28 <int-e> Jafet: why do that when you can use logarithms?
13:48:33 <int-e> besides it's entirely plausible that the biggest number and the smallest non-zero one are more than a factor of 2^2048 apart.
13:48:48 <FreeFull> Logarithms make multiplication and exponentiation easier, but you lose precision
13:50:12 <int-e> at least you lose precision gradually. a bit like having a variable width exponent field in the floating point number. (the only shame is that the actual exponent field is way too large in that representation).
13:51:02 <int-e> of course you also gain precision for values close to 1.
13:51:06 <slereah> Well in my case if I stick with the regular formula, things underflow and I end up dividing by 0
13:51:37 <slereah> If it doesn't work out, I will just WRITE MY OWN NUMBERS
13:51:57 <slereah> Like a real and some exponent
13:53:00 <slereah> But I don't think I'll need to go this far
13:53:00 <int-e> "I hear you like floating point, so I made a floating point representation using floating point numbers" :))
13:53:20 <slereah> I mean really the problem isn't precision
13:54:20 <slereah> Well I drop about one order of magnitude per thing in my array
13:54:44 <slereah> Current array is a thousand things
13:55:35 <int-e> Which loses something like log_2(10)*log(N) bits of precision, and you have 53 bits of that to start with (assuming IEEE 754 doubles)
13:56:04 <int-e> never mind that underflows lose all precision quite catastrophically :)
13:58:06 <Jafet> long double has 15 exponent bits, which is good to 10^5000.
13:58:14 <int-e> something is not right in my analysis. I want log_2(log(10^N)) = log_2(log(10)*N) = log_2(log(10)) + log(N)
13:58:39 <slereah> Yeah, but what will happen when I will do a 5000 long thing D:
13:58:48 <slereah> I'll go with the logs for now, see what happens
13:59:19 <int-e> anyway, that's what I meant by "gradual" decrease.
14:00:16 <Jafet> Huh, __float128 doesn't increase the exponent size.
14:00:20 <slereah> Well here's the evolution of my original function : http://pastebin.com/SxfxcEvj
14:00:42 <slereah> It lost all precision in about 460 iterations
14:00:57 <FreeFull> Well, if you're doing logs, all you need is the exponent
14:01:04 <FreeFull> I suppose fixed point would do
14:01:33 <slereah> I dont think picking a bigger precision will help that much
14:01:38 <slereah> Plus it might be a bit memory heavy
14:02:15 <Jafet> Picking a type that has a hardware implementation can help.
14:02:38 <slereah> Speaking of, does log(0) = -inf in general?
14:02:44 <slereah> Or does it depend on the implementation
14:03:21 <slereah> Although... won't help that much I s'ppose
14:03:35 <slereah> Since log(0) + log(1) won't give the correct value
14:04:47 <int-e> C is as useful as always: "A range error may occur if the argument is zero."
14:05:29 <slereah> I'm better off doing that http://bozeman.genome.washington.edu/compbio/mbt599_2006/hmm_scaling_revised.pdf
14:07:30 <int-e> http://pubs.opengroup.org/onlinepubs/009695399/functions/log.html is a bit more specific; there is a macro that can be tested to figure out how the code will actually behave.
14:08:44 <int-e> Hmm, C99 apparently has that one as well. (math_errhandling)
14:09:27 <Jafet> Why not just set zeroes to INT_MIN
14:09:39 <HackEgo> [wiki] [[Ignition]] M http://esolangs.org/w/index.php?diff=39397&oldid=39330 * Luxen * (+27) IRC room for discussion
14:13:39 <b_jonas> slereah: libmpfr allows exponents up to about 2**30
14:13:51 <b_jonas> that might be enough for you
14:16:34 <int-e> b_jonas: why are you so opposed to using logarithms?
15:02:05 -!- edwardk has joined.
15:05:46 -!- Melvar` has joined.
15:08:05 -!- Melvar has quit (Ping timeout: 264 seconds).
15:08:12 -!- Melvar` has changed nick to Melvar.
15:14:05 -!- idris-ircslave has joined.
15:15:40 <mroman> @run foldl1 (\a b -> (a,b)) [1,2,3]
15:15:41 <lambdabot> Occurs check: cannot construct the infinite type: t ~ (t, t1)
15:15:42 <lambdabot> b :: (t, t1) (bound at <interactive>:1:12)
15:15:42 <lambdabot> a :: (t, t1) (bound at <interactive>:1:10)Occurs check: cannot construct t...
15:16:11 <mroman> Some version of Haskell should allow infinite types
15:16:22 <mroman> > foldl1 (\a b -> (a,b)) [1,2,3]
15:16:22 <idris-ircslave> When elaborating an application of constructor __infer:
15:16:23 <lambdabot> Occurs check: cannot construct the infinite type: t ~ (t, t1)
15:16:23 <lambdabot> b :: (t, t1) (bound at <interactive>:1:12)
15:16:23 <lambdabot> a :: (t, t1) (bound at <interactive>:1:10)Occurs check: cannot construct t...
15:16:39 <mroman> Would that work in idris?
15:30:15 <slereah> It's kinda weird that the CPU can deal with log(0) but not the standard library
15:30:25 <slereah> Since it does ln(0+) = -inf
15:33:04 <int-e> elliott: ok, mueval is no longer *much* slower than ghci; the trick is to remove all -static from its .cabal file and enable dynamic executables in the cabal config. fun...
15:34:38 -!- Tritonio has quit (Ping timeout: 240 seconds).
15:36:12 <elliott> int-e: oh, needing dynamic executables makes sense
15:37:46 <int-e> So now I have to plan an in-situ upgrade, or wait for ghc 7.8.3 ... oh well.
15:39:48 -!- sure has quit (Ping timeout: 252 seconds).
15:59:05 <int-e> elliott: http://sprunge.us/BcNW ... note also the "maxresident" values. This should help a lot!
16:03:45 -!- slereah has quit (Remote host closed the connection).
16:10:34 <elliott> int-e: just use it as an excuse to switch to HEAD
16:13:52 <int-e> I'm not that crazy.
16:23:17 -!- password2 has quit (Quit: Leaving).
16:23:41 -!- password2 has joined.
16:24:22 -!- conehead has joined.
16:27:17 -!- shikhin has joined.
16:42:33 -!- Sprocklem has joined.
16:42:33 -!- Sprocklem has quit (Changing host).
16:42:33 -!- Sprocklem has joined.
16:50:03 -!- Phantom_Hoover has joined.
16:50:34 -!- shikhin has quit (Ping timeout: 240 seconds).
17:00:47 -!- Slereah_ has changed nick to Slereah.
17:14:00 -!- MoALTz has joined.
17:19:25 -!- nucular has quit (Quit: Excess Food).
17:22:50 -!- trout has changed nick to function.
17:25:22 -!- fowl has quit (Remote host closed the connection).
17:29:46 -!- function has changed nick to constant.
17:44:04 -!- xpte has joined.
17:59:23 -!- password2 has quit (Ping timeout: 252 seconds).
18:01:22 -!- Sellyme has quit (Excess Flood).
18:02:58 -!- Sellyme has joined.
18:04:58 -!- password2 has joined.
18:06:44 -!- nucular has joined.
18:06:44 -!- nucular has quit (Changing host).
18:06:44 -!- nucular has joined.
18:11:04 -!- Sellyme has quit (Excess Flood).
18:11:28 -!- Sellyme has joined.
18:13:09 -!- yorick has joined.
18:17:53 -!- Sellyme has quit (Excess Flood).
18:19:59 -!- Sellyme has joined.
18:29:30 <kmc> ^style fungot
18:29:30 <fungot> Selected style: fungot (What I've said myself)
18:29:42 <kmc> fungot: how do you make your way when your way is making you?
18:29:42 <fungot> kmc: ( ( ( a()**)a*:a*)(a()**)a*:a*)((x1)(x2)(x3)) ...out of time! don't let that binds the variables
18:31:55 <shachaf> i thought that was kmclyrics but it's from that play thing, isn't it
18:32:44 <kmc> which is like lyrics
18:33:12 <shachaf> well, a common characteristic of kmclyrics is that i don't recognize them
18:40:03 <kmc> also sometimes they are the names of songs rather than the words from the song
18:57:19 -!- nooodl has joined.
19:07:04 -!- douglass_ has joined.
19:09:54 <Phantom_Hoover> holy shit finally a decent what if: http://what-if.xkcd.com/92/
19:11:05 -!- password2 has quit (Ping timeout: 264 seconds).
19:12:09 <Taneb> If I have a graph and want to find the smallest tree that spans some subset of its nodes, is there a nice algorithm for that?
19:12:47 <kmc> isn't that just the minimum spanning tree of the relevant subgraph
19:13:26 <Taneb> kmc, how do I find the relevant subgraph?
19:13:57 <kmc> I thought you had a particular subgraph in mind
19:14:05 <Taneb> No, a subset of the nodes
19:14:12 <kmc> if you mean "any subgraph" then the smallest tree has size zero and spans a subset of the nodes of size zero
19:14:16 -!- augur has quit (Remote host closed the connection).
19:14:51 <Taneb> I want a tree that contains at least, say, these three nodes, from a graph of, say, 30
19:15:51 <FireFly> Smallest in terms of numbers of nodes?
19:16:04 <Taneb> Yes, the graph is unweighted
19:16:23 <kmc> i don't know about that problem
19:16:29 <kmc> perhaps you can transform it into an instance of the usual MST problem
19:17:21 <kmc> construct a new graph containing just the nodes in your set, where the edges are weighted by the minimum length path between those two nodes in the original graph
19:17:25 <kmc> but I think that's not quite right
19:17:40 <kmc> because it doesn't account for the fact that you can use a single intermediate node in multiple paths
19:27:56 -!- MoALTz has quit (Quit: Leaving).
19:37:05 -!- impomatic has quit (Ping timeout: 276 seconds).
19:47:01 <Phantom_Hoover> kmc, note that for unweighted graphs all spanning trees are minimal
19:47:23 <Phantom_Hoover> because the number of edges is just 1 less than the number of nodes
19:47:30 <kmc> good point
19:50:04 <Phantom_Hoover> Taneb, also the tree you're looking for isn't unique, which i think makes designing an algorithm that bit more fiddly
20:01:07 <FireFly> MST isn't unique either, is it?
20:04:44 -!- augur has joined.
20:27:51 -!- nooodl_ has joined.
20:30:56 -!- nooodl has quit (Ping timeout: 252 seconds).
20:31:23 -!- fowl has joined.
20:32:56 <Phantom_Hoover> Taneb, maybe you could do it by reducing spanning trees?
20:33:10 <Phantom_Hoover> it'd be fairly inefficient but better than nothing, i guess
20:33:24 <Taneb> Phantom_Hoover, I doubt that'd give the optimum solution...
20:33:59 <Phantom_Hoover> Taneb, well i'm thinking you could iterate over /all/ spanning trees, but s/fairly/very/ in that case
20:34:19 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:39:28 -!- nycs has joined.
20:42:05 -!- conehead has quit (Ping timeout: 276 seconds).
20:42:05 -!- `^_^v has quit (Ping timeout: 276 seconds).
20:42:05 -!- drlemon_ has quit (Ping timeout: 276 seconds).
20:46:02 <kmc> @tell tswett p_n runs Turing machine number n and outputs 1 if it halts; q_0 never halts and all other q_n output 1. then the mapping from p_n to identically behaving q_n is not computable
20:48:46 <Bike> remarkable? it's just something tswett asked
20:49:04 <kmc> it's just an answer to:
20:49:05 <kmc> 14:19 < tswett> So, there are two programs, P and Q. P outputs an infinite list of programs: p_1, p_2, p_3, .... Q also outputs an infinite list of programs.
20:49:08 <kmc> 14:20 < tswett> For every program that P outputs, Q outputs a program that behaves the same way, and vice versa.
20:49:11 <kmc> 14:20 < tswett> Must there exist a program that, given a number n, finds a number m such that Q_m behaves the same way as P_n?
20:49:36 -!- augur has quit (Remote host closed the connection).
20:50:53 -!- Sprocklem has quit (Quit: leaving).
20:51:32 <kmc> what does that mean
20:52:43 <Phantom_Hoover> it involves the question of whether two generalised programs behave the same way
20:53:06 <kmc> yeah I was immediately pretty sure the answer was "no"
20:53:12 <kmc> but it took me a minute to come up with a proof
20:53:58 <Taneb> Is deciding whether two regular expressions describe the same language?
20:54:17 <kmc> now what if you require that all the p_i and q_i halt on every input
20:54:21 <kmc> Taneb: believe so
20:54:35 <Bike> how could we play regex golf otherwise
20:55:55 <Bike> it's DFA equivalence so that's not too bad right
20:56:34 -!- augur has joined.
20:57:14 <kmc> http://www.cs.ox.ac.uk/people/luke.ong/personal/teaching/moc/decide.pdf pg 5 and 6
20:57:41 -!- contrapumpkin has joined.
20:59:28 -!- nucular has quit (Quit: Switching to phone...).
21:01:11 <Bike> http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libssl/src/crypto/bn/bn_lib.c.diff?r1=1.18;r2=1.19 what the hell is openssl
21:01:13 <Taneb> I guess I have a module next year which covers this kind of thing
21:01:21 -!- Patashu has joined.
21:01:22 -!- copumpkin has quit (Ping timeout: 252 seconds).
21:03:26 <kmc> openssl isn't real
21:03:48 <shachaf> Taneb: i bet modules are functors somehow
21:03:53 <kmc> Bike: sounds like a bug in ultrix cc
21:04:02 <Phantom_Hoover> ahhh, so that's this big vulnerability i've been hearing about
21:04:13 <Bike> seems like it.
21:04:45 <Bike> relatedly i'd like to say again that matlab's 'str2num' function is a wrapper around eval
21:05:37 -!- edwardk has quit (Ping timeout: 240 seconds).
21:06:47 <Phantom_Hoover> Bike, nobody uses matlab for security-dependent stuff though... right... please?
21:06:54 <Bike> god i hope not
21:12:15 -!- AnotherTest has quit (Ping timeout: 252 seconds).
21:13:18 -!- Sellyme has quit (Excess Flood).
21:13:24 -!- Patashu_ has joined.
21:13:24 -!- Patashu has quit (Disconnected by services).
21:13:28 <elliott> everything is security-dependent
21:13:57 <Taneb> There are people writing security-dependent stuff in languages OTHER than matlab!?
21:14:58 -!- Sellyme has joined.
21:15:01 <Phantom_Hoover> Bike, i used matlab yesterday, i was pretty taken aback just to discover the identity matrix is eye(n)
21:15:20 <Bike> there's also a function NaN(n), if you need an n×n matrix of NaNs
21:16:04 <Phantom_Hoover> but what if i only want the nans along the main diagonal!
21:16:17 <Bike> and magic(n) for when you need a magic square
21:17:02 <Bike> Phantom_Hoover: diag(NaN(1,n)) hth
21:18:01 <Bike> i suppose that works too
21:19:20 <Bike> yeah, they're IEEE\
21:19:54 <Bike> i hadn't really messed with NaNs before yesterday but i figure they still scalar multiply with matrices
21:24:20 <Phantom_Hoover> all you need to know about NaN is that it's objectivist kryptonite
21:27:22 -!- Patashu_ has quit (Ping timeout: 265 seconds).
21:29:31 -!- nisstyre has joined.
21:33:15 -!- yorick has quit (Remote host closed the connection).
21:37:18 <Bike> http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libssl/src/crypto/bn/bn_mont.c.diff?r1=1.17;r2=1.18 openssl is definitely not real
21:39:02 <Taneb> Bike, NEITHER AM I
21:39:40 <Taneb> Also some of my friends are trying to get me to try to figure out what a bloated PHP app is doing
21:39:47 <Taneb> Because I'm the least sane programmer they know
21:42:55 -!- oerjan has joined.
21:43:35 -!- Sellyme has quit (Excess Flood).
21:45:29 -!- Sellyme has joined.
21:46:31 <Taneb> Actually, to be frank, I find most programming language scary.
21:46:41 <Taneb> And any programming language for sufficiently large projects.
21:49:06 <oerjan> otoh, brainfuck is simple and elegant.
21:52:52 <oerjan> <int-e> Ooh. Not L then. <-- DISAPPOINT
21:53:28 <oerjan> i'd have liked to see Slereah having to implement division in L
21:54:14 <Taneb> "This file is pretty much the most important file in [project name]"
21:54:16 <oerjan> otoh that algorithm is probably painfully slow.
21:54:21 <Taneb> "It basically everything."
21:55:02 <oerjan> Taneb: someone isn't doing things modularly?=
21:55:37 <Taneb> oerjan, the only non-comment line is "require __DIR__.'/../Controllers/root.php';"
21:56:22 <oerjan> that sounds like it's root.php which everything, then?
21:59:42 -!- conehead has joined.
22:03:15 -!- Sellyme has quit (Excess Flood).
22:05:07 <Taneb> I think I've found an actual mistake in this thingy
22:05:29 -!- Sellyme has joined.
22:07:00 <Taneb> Phantom_Hoover, well, yeah
22:07:10 <Taneb> I of course meant a sub-mistake
22:08:07 <oerjan> http://media-cache-ec0.pinimg.com/736x/07/c9/72/07c972d1bf1882a4b561c633e91252f5.jpg
22:08:33 -!- Sellyme has quit (Excess Flood).
22:08:58 -!- Sellyme has joined.
22:12:10 <Taneb> And now I've sent a pull request that changes one character
22:18:33 <Taneb> (they had written date_default_timezone_get instead of date_default_timezone_set)
22:20:10 <olsner> why would you want an 's' there? why do you hate 'g'?
22:20:54 <Taneb> olsner, they had given the function the parameter 'europe/london'
22:21:04 <Taneb> And documented it "Set the Default Timezone."
22:21:27 <olsner> hmm, surely that's only the default timezone if you happen to live in london
22:22:22 <Taneb> That's another problem for another day
22:22:31 -!- Sgeo has joined.
22:22:35 <Taneb> And this whole shebang is running in York which is in the London timezone
22:23:30 <oerjan> Taneb: https://en.wikipedia.org/wiki/Steiner_tree_problem#Generalization_of_minimum_Steiner_tree
22:24:00 <Taneb> oerjan, thanks a lot
22:26:33 <oerjan> (it was mentioned in the minimum spanning tree article)
22:30:48 <ion> http://www.wired.com/2014/04/lost-lunar-photos-recovered-by-great-feats-of-hackerdom-developed-at-a-mcdonalds/
22:36:28 <oerjan> 21:39:40:<Taneb> Also some of my friends are trying to get me to try to figure out what a bloated PHP app is doing
22:36:31 <oerjan> 21:39:47:<Taneb> Because I'm the least sane programmer they know
22:36:44 <oerjan> is this like insanity wrapping around a circle
22:36:59 <Taneb> I think it's you finishing logreading
22:37:25 <int-e> hmm. can one punch extra holes into sparse files?
22:37:30 <Phantom_Hoover> <oerjan> http://media-cache-ec0.pinimg.com/736x/07/c9/72/07c972d1bf1882a4b561c633e91252f5.jpg
22:37:48 <oerjan> like, if you program esolangs too much, you suddenly wrap around to thinking php is a good one
22:38:39 <oerjan> Phantom_Hoover: pretty sure that was in the same book (which i've got downstairs in the basement locker somewhere)
22:39:24 <oerjan> got it as birthday present back in 1996 in seattle.
22:41:23 <int-e> Ah, the answer is yes: fallocate with FALLOC_FL_PUNCH_HOLE does that.
22:41:41 <oerjan> hm locker is the wrong word for a room that big
22:42:15 <olsner> or just "basement" even
22:43:00 <oerjan> olsner: i wanted not to imply the whole basement is mine, this is a common area
22:43:15 -!- Sorella has joined.
22:43:37 <oerjan> i supposedly have an assigned parking space down there too, if i had a car
22:44:11 <Taneb> Help I don't know PHP and I am no longer sure that is a good thing
22:44:23 <olsner> you should get a car, don't let that parking space sit unused
22:44:32 <oerjan> `addquote <Taneb> Help I don't know PHP and I am no longer sure that is a good thing
22:44:34 <HackEgo> 1186) <Taneb> Help I don't know PHP and I am no longer sure that is a good thing
22:44:50 <olsner> Taneb: it is a good thing! really!
22:46:17 <Taneb> WHY IS THIS FILE 1000 LINES LONG
22:46:29 <Taneb> IT'S A UTILITY CLASS
22:49:59 -!- augur has quit (Remote host closed the connection).
22:56:08 -!- boily has joined.
22:56:52 <HackEgo> 19) <ehird> so i can only conclude that it is flawed, or the world is utterly bonkers
22:57:25 <HackEgo> 20) IN EINEM ALTERNATIVEN UNIVERSUM (WO DIE NAZIS WON): <ehird> So kann ich nur schliessen, dass es falsch ist, oder die Welt ist vollig BONKERS. Gegrusset seist du der Fuhrer Hitler!
22:57:50 <olsner> ah, I thought I recognized it
22:58:02 -!- edwardk has joined.
22:58:13 <Taneb> PHP is making me sad, I'm going to head to bed
22:58:18 <oerjan> the nazis were big on BUNKERS
22:58:21 -!- augur has joined.
22:58:46 <boily> Taneb: dream of haskell. it is good for the mind!
22:59:04 <Taneb> `quote great old ones
22:59:05 <HackEgo> 1160) <Taneb> Last night I had a dream that someone wrote such bad Haskell code he accidentally summoned the Great Old Ones and I had to fix the Haskell code and save the day
22:59:29 -!- augur has quit (Remote host closed the connection).
22:59:34 <lambdabot> Philippa says: incidentally, if you think about this you're probably starting to image control flow that looks like it's a glyph for summoning cthulhu - and then realising that it's 3d and consists of 'towers'. Make sense?
22:59:50 <lambdabot> Philippa says: incidentally, if you think about this you're probably starting to image control flow that looks like it's a glyph for summoning cthulhu - and then realising that it's 3d and consists of 'towers'. Make sense?
23:00:13 <oerjan> Taneb: IT WAS NO DREAM HTH
23:00:39 <HackEgo> 697) <Taneb> I swear my dreams are becoming increasingly rave + computer science oriented
23:00:56 <Taneb> `quote story about prohib
23:01:03 <Taneb> `quote story about the prohib
23:01:04 <HackEgo> 939) <Taneb> I'm a story about the prohibition of chocolate
23:01:11 <Taneb> God, I say weird things
23:01:18 <HackEgo> 386) <Taneb> Turned out he got recursion, he just didn't get the return statement \ 392) <Taneb> Cut to February <Taneb> War were declared <Taneb> A galaxy in turmoil <Taneb> Anyway, Febuary '10 \ 393) <Taneb> I can't afford one of those! <Taneb> A grandchild, not a laser printer \ 399) <fizzie> There's that saying that the definition of insani
23:01:29 <Taneb> Anyway, goodnight!
23:07:51 -!- nooodl_ has quit (Quit: Ik ga weg).
23:10:38 <boily> @tell Taneb you should follow my lead. I am a sane person.
23:13:57 <Sgeo> If type families are open functions of types to types, and functions are closed functions from values to values, where are my open functions from values to values and closed functions from types to types?
23:17:24 -!- impomatic has joined.
23:19:10 <Sgeo> Hmm, I guess for type families, the behavior of failing to compile for arguments outside its domain is less bad than functions bottoming out for arguments outside their domain
23:20:51 -!- mauris has joined.
23:24:01 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
23:28:00 <oerjan> Sgeo: closed type families are being implemented. not sure if they were in the latest release yet.
23:30:16 <kmc> "Dammit people stop putting FALSE on your resume it just confuses our poor recruiter"
23:30:25 <kmc> apparently my friend's company got one of these
23:31:04 <oerjan> yeah stick with underload
23:32:12 <kmc> I want to write a valid program in one language which is also a valid program in another language when base64-decoded
23:34:38 <FireFly> Maybe recruit better recruiters
23:35:53 -!- vravn has quit (Excess Flood).
23:36:04 <mauris> kmc: empty program hth
23:36:30 <Sgeo> "isKnownAtCompileTime(exp)
23:36:30 <Sgeo> Implementing this function amounts to solving the halting problem."
23:36:48 <boily> FireFly: a meta-circular recruiter recruitment program!
23:36:52 <Sgeo> So, what, exactly, would be wrong with a isKnownToBeKnownAtCompileTime(exp) that may return false negatives/
23:38:13 -!- vravn has joined.
23:45:37 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
23:48:06 -!- mauris has quit (Quit: mauris).
23:51:17 -!- augur has joined.
00:07:00 -!- Zerker has joined.
00:10:21 -!- lambdabot has quit (Quit: brb).
00:16:41 -!- lambdabot has joined.
00:18:25 <int-e> sorry. funny error though :)
00:28:16 -!- Zerker has quit (Remote host closed the connection).
00:34:54 -!- tromp has joined.
00:34:54 <Sgeo> @run (1,2,3,4,5,6,7,8,9,10,11,12)^..each
00:34:56 <lambdabot> Could not deduce (Control.Lens.Each.Each
00:34:56 <lambdabot> (t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11)
00:34:56 <lambdabot> (t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11)
00:35:24 <shachaf> idris-ircslave: that's not for you, be quiet
00:36:41 <boily> fungot: do you expect ($)?
00:36:41 <fungot> boily: ( ( ( a()**)a*:a*)(a()**)a*:a*)((x1)(x2)(x3)) ...out of time! don't let?!
00:37:08 <boily> even fungot spews out punctuation-heavy error messages! Sir Fungellot is corrupted!
00:37:08 <fungot> boily: use the ' ' ' delete a value of type " airbus is a big fan of avril....but this song " there ain't no difference from before!
00:37:23 <boily> fungot: of course. everything is the same.
00:37:23 <fungot> boily: agora alice c64 ct darwin discworld europarl ff7 fisher ic irc* jargon lovecraft nethack pa speeches ss wp youtube
00:58:29 -!- lexande has quit (Ping timeout: 252 seconds).
01:00:11 -!- ski has joined.
01:03:58 -!- lexande has joined.
01:11:07 -!- idris-ircslave has quit (Quit: Terminated).
01:12:34 -!- boily has quit (Quit: SLEEP).
01:12:58 -!- idris-ircslave has joined.
01:24:36 <Sgeo> Gregor: Can a malicious soundfont do anything bad?
01:25:41 <Gregor> Not without bugs in the soundfont interpreter/renderer.
01:26:09 -!- nisstyre has joined.
01:26:22 <Bike> what if it makes you listen to orchestral music done in bike horns
01:28:13 <ion> Is that good or bad?
01:28:28 <ion> Sounds appropriate for, say, P.D.Q. Bach.
01:40:09 -!- augur has quit (Remote host closed the connection).
01:44:32 -!- hungryhippo has joined.
01:46:29 -!- hungryhippo has left.
01:49:29 <HackEgo> [wiki] [[Ignition]] http://esolangs.org/w/index.php?diff=39398&oldid=39397 * Oerjan * (+18) I recommend previewing hth
01:59:29 -!- constant has quit (Ping timeout: 250 seconds).
02:02:23 -!- augur has joined.
02:03:50 <Sgeo> What happens if you use something like data Foo = Foo with DataKinds?
02:15:53 <oerjan> Sgeo: http://www.haskell.org/ghc/docs/latest/html/users_guide/promotion.html#promotion-syntax
02:38:55 -!- variable has joined.
02:57:20 -!- contrapumpkin has changed nick to copumpkin.
03:12:28 -!- edwardk has quit (Quit: Computer has gone to sleep.).
03:17:19 -!- xpte has quit.
03:17:30 -!- edwardk has joined.
03:18:17 -!- xpte has joined.
03:18:40 -!- xpte has left.
03:22:30 -!- drdanmaku has joined.
03:25:05 <Sgeo> It should be possible to write a liftMn that takes a type-level nat, right?
03:25:13 <Sgeo> Would look ugly though, if I actually understand this
03:25:31 <Sgeo> liftMn (Proxy :: Proxy 2) (+) [1,2,3] [4,5,6]
03:39:22 <kmc> https://github.com/usrbinnc/netcat-cpi-kernel-module an album by a band named netcat, released as a kernel module
03:39:52 <copumpkin> I hope it uses its added privilege for the ultimate DRM
03:41:26 -!- Sorella has quit (Quit: It is tiem!).
03:42:12 <Bike> "Building also requires several gigabytes of memory. We're not totally sure why, but we think it is because because the compiler is making lots of copies of several large, static arrays that contain track data." fascinating
03:50:47 <oerjan> hm that suggested new (:: t) syntax won't work as a proxy if t is not of kind *
03:50:52 <kmc> 2048 has a lot of zugzwang
03:51:21 <oerjan> clearly id must also have polymorphic kind hth
04:03:18 <kmc> polymorphic kindness
04:03:54 <kmc> i guess this is vaguely on topic https://twitter.com/christinelove/status/458808917837873152
04:04:07 -!- kallisti has quit (Ping timeout: 245 seconds).
04:05:19 <Sgeo> I'm tempted to try Ultrix now
04:05:34 -!- tertu has joined.
04:05:42 <oerjan> do you have Ulterior motive
04:07:22 <oerjan> my first logins to this account was to an ultrix machine, nvg's first server.
04:08:34 <Sgeo> Mostly because I've heard of it because of OpenSSLRampage
04:08:42 <Sgeo> And want to bring it out of its coffin
04:09:15 <Bike> sgeo have you seen jsmess
04:09:35 <Bike> a few days ago i tried to run Lemmings on an Amiga and got some bizarre kernel area. it would be nostalgic if the system wasn't older than me
04:10:09 <Sgeo> I've seen similar but narrower in scope (one machine) things before
04:10:46 <Bike> i don't know what unixes it has, though, if any
04:11:21 -!- tromp has quit (Remote host closed the connection).
04:11:54 -!- tromp has joined.
04:12:36 <Sgeo> Ooh, E.T. good game?
04:13:07 <Bike> isn't it the notorious opposite of a good game
04:13:41 -!- FreeFull_ has joined.
04:14:23 -!- FreeFull has quit (Ping timeout: 252 seconds).
04:14:49 <Sgeo> Hmm, wanted to find a blind let's play
04:14:54 <Sgeo> Someone who hasn't heard how bad it is
04:15:32 <Bike> apparently i can play a gundam http://en.wikipedia.org/wiki/Bandai_RX-78
04:15:47 <kmc> whoa http://arstechnica.com/gaming/2014/04/atari-landfill-in-new-mexico-to-be-dug-up-on-saturday-ars-will-be-on-scene/
04:16:26 -!- tromp has quit (Ping timeout: 276 seconds).
04:16:38 <kmc> here's a long article about why it's not so bad, and how to fix it with a few binary patches http://www.neocomputer.org/projects/et/
04:17:52 <Sgeo> Did it come with a manual
04:17:57 <Sgeo> The UI seems a bit unhelpful
04:18:21 <Bike> well, yeah, 80s
04:23:34 <oerjan> <Sgeo> Hmm, wanted to find a blind let's play <-- are you saying the game gets better if you are blind twh
04:24:46 <Bike> http://projectnaptha.com/ this looks nifty
04:40:58 -!- nisstyre has quit (Ping timeout: 240 seconds).
05:05:27 -!- nisstyre has joined.
05:21:16 -!- esowiki has joined.
05:21:20 -!- esowiki has joined.
05:21:21 -!- esowiki has joined.
05:22:04 -!- esowiki has joined.
05:22:05 -!- glogbot has joined.
05:22:08 -!- esowiki has joined.
05:22:08 -!- esowiki has joined.
05:22:26 -!- FreeFull has joined.
05:24:18 -!- FreeFull_ has quit (Ping timeout: 240 seconds).
05:44:06 -!- FreeFull has quit.
06:03:47 <Sgeo> Bike: umuuvvmmuivwmnnwluwnuwwolhwhus
06:05:07 <Sgeo> I AB5ENTH|NDEDLY5ELECT RANDU1 Bl.OO<5 OFTEXTHSI READ, PND FEEL SLRONSCDUSLY SATISFIED LHEN THE HIGHUGHTED AREA |"PKE5 H 5Yl’R1ETRICHL 5|-PPE
06:05:14 -!- password2 has joined.
06:06:39 <Bike> are you saying text recognition isn't perfect
06:08:28 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:11:29 <oerjan> well the first one is obviously upside down, it should be snymytomnumntmuuwmltnwwmnnwn
06:11:53 <oerjan> which is a common welsh greeting.
06:40:00 <Taneb> "@todo Better Documentation" exactly what you want when you're trying to figure out a program in a language you don't know
06:41:30 <lambdabot> 0. SamB: A way to get multiple results from a google search
06:41:30 <lambdabot> 1. dons: improve formatting of @dict
06:41:30 <lambdabot> 3. lispy: don't let lambdabot's prettyprinter split the sequence @foo across lines
06:41:30 <lambdabot> 4. TheHunter: priviledged users should get priviledged listcommands.
06:42:04 <fizzie> lambdabot: So much to do, so little time.
06:43:40 <oerjan> @dict och forbandet løgn
06:43:40 <lambdabot> There is no dictionary database 'och'.
06:43:40 <lambdabot> There is no dictionary database 'forbandet'.
06:43:40 <lambdabot> There is no dictionary database 'løgn'.
06:43:57 <lambdabot> dict provides: dict-help all-dicts bouvier cide devils easton elements foldoc gazetteer hitchcock jargon thesaurus vera wn world02
06:44:12 <lambdabot> I perform dictionary lookups via the following 14 commands:
06:44:12 <lambdabot> all-dicts ... Query all databases on dict.org
06:44:12 <lambdabot> bouvier ..... Bouvier's Law Dictionary
06:44:12 <lambdabot> cide ........ The Collaborative International Dictionary of English
06:44:12 <lambdabot> devils ...... The Devil's Dictionary
06:44:13 <lambdabot> easton ...... Easton's 1897 Bible Dictionary
06:44:17 <lambdabot> foldoc ...... The Free On-line Dictionary of Computing
06:44:19 <lambdabot> gazetteer ... U.S. Gazetteer (2000)
06:44:21 <Bike> well this is verbose.
06:44:21 <lambdabot> hitchcock ... Hitchcock's Bible Names Dictionary (late 1800's)
06:45:03 <lambdabot> *** "potable" devil "The Devil's Dictionary (1881-1906)"
06:45:05 <lambdabot> POTABLE, n. Suitable for drinking. Water is said to be potable;
06:45:07 <lambdabot> indeed, some declare it our natural beverage, although even they find
06:45:09 <lambdabot> it palatable only when suffering from the recurrent disorder known as
06:45:11 <lambdabot> thirst, for which it is a medicine. Upon nothing has so great and
06:45:16 <lambdabot> diligent ingenuity been brought to bear in all ages and in all
06:45:17 <lambdabot> countries, except the most uncivilized, as upon the invention of
06:45:19 <lambdabot> substitutes for water. To hold that this general aversion to that
06:45:21 <lambdabot> liquid has no basis in the preservative instinct of the race is to be
06:45:23 <lambdabot> unscientific -- and without science we are as the snakes and toads.
06:46:23 -!- oerjan has quit (Quit: OKAY).
06:48:35 <Taneb> "it was either you or me, lambdabot"
06:56:12 -!- pikhq has quit (Ping timeout: 258 seconds).
06:58:20 <coppro> lambdabot needs a pastbin
07:04:55 -!- pikhq has joined.
07:08:21 <kmc> fungots fall on fungot falls
07:08:21 <fungot> kmc: ( c) a player resigns from an office has whatever duties, then 3 extra " 0" and ( down-from n ( 0
07:08:27 <kmc> hi pikhq, how goes it?
07:19:04 <fizzie> Fun fact: ARIN now has a single /8 left, too -- https://www.arin.net/announcements/2014/20140423.html
07:40:37 -!- conehead has quit (Quit: Computer has gone to sleep).
07:45:32 <lifthrasiir> "By APNIC policy, each current or future member can receive only one /22 block from this last /8 (there are 16384 /22 blocks in the last /8 block)."
07:48:32 -!- slereah_ has joined.
07:48:50 <slereah_> Like check the length of the series
07:49:02 <slereah_> And if it's short, I use the regular Baum Welch algorithm
07:49:09 <slereah_> but if it's long, it's log ahoy
07:49:38 <Bike> the regular baumkuchen algorithm
07:56:08 -!- password2 has quit (Ping timeout: 276 seconds).
08:04:38 -!- augur has quit (Ping timeout: 252 seconds).
08:07:24 -!- augur has joined.
08:27:45 -!- Patashu has joined.
08:29:07 -!- idris-ircslave has quit (Quit: Terminated).
08:29:43 -!- idris-ircslave has joined.
08:42:03 -!- Patashu_ has joined.
08:42:04 -!- Patashu has quit (Disconnected by services).
09:14:20 <lambdabot> <hint>:1:1: parse error on input ‘>’
09:21:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:21:59 <shachaf> kmc: do you think something like http://flint.cs.yale.edu/flint/publications/flex.pdf would be realistic for rust
10:10:23 -!- yiyus has joined.
10:12:26 -!- boily has joined.
10:14:46 <shachaf> kmc: also i wonder whether shipwreck is named after http://www.marxists.org/archive/lenin/works/1912/may/08c.htm
10:19:10 -!- yorick has joined.
10:24:15 -!- Frooxius has quit (Quit: *bubbles away*).
10:30:38 <slereah_> So it turns out the last value was ~ e^-1611.5
10:32:11 -!- ais523 has joined.
10:51:26 <ais523> int-e: do you have a 1 in 1611 probability that you're trying to estimate how long before you have a 50% chance of it happening?
10:52:37 <int-e> ais523: I was estimating the exponent field in a floating point representation of e^-1611.5
10:52:44 <int-e> binary floating point that is
10:56:03 -!- augur_ has joined.
10:58:11 <ais523> huh, I'm seeing the headlines "OpenBSD forks OpenSSL"
10:58:20 <ais523> which confuses me, because I thought OpenSSL was their project in the first plae
10:59:38 -!- augur has quit (Ping timeout: 240 seconds).
10:59:48 <fizzie> Not everything that starts "Open" is theirs.
10:59:58 <ais523> but I thought that in particular was
11:00:50 <fizzie> What I think is boringly unimaginative is the "LibreSSL" name. I mean, Openswan got forked as Libreswan back when they had problems of their own.
11:01:28 <ais523> are they copying the OpenOffice/LibreOffice thing?
11:02:12 <fizzie> Huh, I didn't even think of that.
11:02:59 -!- nooodl has joined.
11:03:18 <ais523> that has to be the highest-profile open→libre fork
11:03:22 <ais523> not sure if it was the first
11:05:02 <fizzie> What's next, LibreStreetMap?
11:05:55 <fizzie> (LibreVPN, LibreLDAP, LibreSceneGraph, LibreTTD, ...)
11:10:32 -!- boily has quit (Quit: FREE CHICKEN).
11:51:05 -!- Sorella has joined.
11:52:38 <Melvar> < mroman> > foldl1 (\a b -> (a,b)) [1,2,3] < mroman> Would that work in idris? – The answer is: Yes! Idris can do that. More seriously, mutatis mutandis, the idea can be made to work.
11:52:49 -!- hexagon has changed nick to h3xagon.
11:52:54 -!- h3xagon has changed nick to hexagon.
12:03:56 <Melvar> Using only things I have available at the repl:
12:04:06 <Melvar> ( elim_for Prelude.List.List Integer (elim_for Prelude.List.List Integer (const Type) () (\x,xs,y => (Integer,y))) (the () ()) (\x, xs, xs' => (x, xs'))
12:04:06 <idris-ircslave> <<Prelude.List.List eliminator>> Integer (<<Prelude.List.List eliminator>> Integer (\v => Type) () (\x => \xs => \y => (Integer, y))) () (\x3 => \xs4 => \xs' => (x3, xs')) : (scrutinee : List Integer) ->
12:04:06 <idris-ircslave> <<Prelude.List.List eliminator>> Integer (\v => Type) () (\x => \xs => \y => (Integer, y)) scrutinee
12:04:18 <Melvar> ( elim_for Prelude.List.List Integer (elim_for Prelude.List.List Integer (const Type) () (\x,xs,y => (Integer,y))) (the () ()) (\x, xs, xs' => (x, xs')) [1,2,3]
12:22:51 -!- nucular has joined.
12:22:51 -!- nucular has quit (Changing host).
12:22:52 -!- nucular has joined.
12:27:40 <slereah_> I name my variables according to what will give the best alignment in the code
12:32:31 -!- nooodl_ has joined.
12:33:17 -!- aloril has quit (Ping timeout: 264 seconds).
12:34:25 -!- Sgeo has quit (Read error: Connection reset by peer).
12:35:40 <FireFly> Use single-letter variable names
12:35:43 * ais523 mentions something about PHP's hashing algorithm for built-in functions
12:35:53 <FireFly> Allows for perfect alignment and reduces the number of keystrokes
12:35:59 -!- nooodl has quit (Ping timeout: 252 seconds).
12:37:40 -!- ais523 has quit.
12:47:07 -!- aloril has joined.
12:48:11 -!- Slereah has quit (Ping timeout: 250 seconds).
12:48:23 -!- Slereah has joined.
12:58:14 <slereah_> FireFly : Plus it would be nice to leave something for the next intern to do
13:01:35 -!- ais523 has joined.
13:02:03 <slereah_> indirectly lost: 7,204,400 bytes in 350 blocks
13:02:15 <ais523> slereah_: is that a valgrind report?
13:02:31 <ais523> worrying about indirectly lost isn't normally worth it, those are memory leaks that'll go away if you fix the "directly lost" leaks
13:02:40 <ais523> basically, leaks caused as a result of other leaks
13:05:21 <slereah_> The bigger problem though is that the algorithm doesn't work
13:05:47 <ais523> the memory management algorithm? or the algorithm that the leaky code is trying to impl?
13:09:40 <slereah_> But it does not converge to anything
13:10:54 <fizzie> Impressive, given how it's guaranteed to.
13:12:19 <slereah_> Don't know where the code fucks up
13:12:34 <ais523> FireFly: sometimes when I write comments, I try to make every line the same length
13:12:51 <ais523> if you have around 76 columns to write in, which is typical, it's actually not very difficult
13:12:53 -!- tertu has quit (Ping timeout: 264 seconds).
13:19:29 <ais523> just pick different words
13:19:39 <fizzie> Wonder if there are automatic tools for that.
13:25:56 -!- password2 has joined.
13:27:59 -!- nycs has changed nick to `^_^v.
13:35:53 -!- slereah_ has quit (Quit: Leaving).
13:40:16 <Jafet> Subject: LEGITIMATE BUSINESS PROPOSAL!!!
13:40:17 <Jafet> Greetings to you, I am Mrs.Helen Wong, from Shanghai Banking Corporation Limited. (China)I have a business proposal of USD$30,000,000
13:40:24 <Jafet> From: Mrs. Helen Wong <suvanto.martti@pp.inet.fi>
13:40:35 <Jafet> Come on, at least try.
13:41:56 <int-e> your mail client is supposed to display that as "Mrs. Helen Wong", because the e-mail address is too technical for layfolks
13:46:05 <fizzie> FedEx customer support number's phone IVR menu starts with "press 1 if you have received an e-mail about a shipment you were not expecting".
13:46:09 <fizzie> I assume that's because of spam.
13:46:45 <ais523> either that or their email notification system is broken
13:47:02 <fizzie> It was also spoken in an entirely different voice than the rest of the menus.
13:47:25 <ais523> Jafet: there's a theory that spammers intentionally make their emails look like spam to humans (if not spam filters), because they're only going to be able to get money out of the most gullible targets anyway, and thus it helps to filter for gullibility in advance
13:47:42 <ais523> fizzie: is this in English or Finnish?
13:47:49 <fizzie> Finnish, I was paraphrasing a bit.
13:47:54 <fizzie> It might well be the same for English.
13:48:39 <fizzie> I also had to navigate three levels down (main menu -> "international shipments" -> "press 5 for further options") before learning the shortcut ("0#") to talk to a human.
13:49:46 <ais523> there's a well-known pseudo-shortcut of hitting 0 repeatedly to get past those systems, I'm not sure if that generally works or not now that it's well-known
13:49:57 <fizzie> At least my up-and-coming ISP's customer service number uses speech recognition, which makes one feel very futuristic.
13:50:03 <ais523> a lesser-known method where you stay completely silent for about a minute and it assumes you have a pulse phone rather than a touch-tone phone
13:50:07 <ais523> and connects you to a human then
13:50:17 <ais523> but speech recognition avoids that loophol
13:50:34 <ais523> clearly we need a speech synthesizer based on `words
13:51:44 <fizzie> ais523: I stayed completely silent for maybe 30 seconds (because I couldn't really figure out what to say to the speech recognizer) and it started a speech about how I can also select this or that number with the keypad.
13:51:46 <Jafet> Apparently, speech synthesizers are now good enough for... youtube videos.
13:52:25 <ais523> Jafet: occasionally, YouTube has an option to autogenerate subtitles based on speech recognition
13:52:27 <fizzie> (Of course that was approximately the same moment when I actually started speaking, which made the menu text stop, but I also stopped talking out of confusion. It was all very awkward.
13:52:37 <ais523> even more occasionally, it also gives you the option to run the resulting subtitles through Google Translate
13:52:46 <ais523> if this ever comes up, I recommend using it
13:52:53 <ais523> sometimes it even produces something intelligible
13:53:01 <Jafet> Automatic closed captioning, sounds legit.
13:53:32 <fizzie> I used the YouTube speech recognition subtitles a year and half ago when giving a surprise lecture (the normal lecturer cancelled with no lead-up time) on a machine learning class.
13:53:36 <ais523> Jafet: well the BBC seemed to use automatic closed captioning on 888 sometimes, but that might have had humans intervening
13:53:41 <fizzie> Though it'd be both thematically appropriate and funny.
13:53:49 <fizzie> It was at least the latter.
13:53:57 <ais523> certainly, there were many cases where there were computer-like mistakes but followed by a correction
13:54:01 <Jafet> (On the rare occasion that I am near a television, the closed captioning looks bad enough that it might have been automatically generated anyways)
13:54:06 <fizzie> (The language model they were using wasn't very well-versed on probablistic models and the EM algorithm.)
13:54:57 <fizzie> (I showed them some open MIT lecture video thing, since I couldn't really think of much else.)
13:55:11 <b_jonas> like http://www.xkcd.com/806/ ?
13:55:28 -!- Sellyme has left.
13:56:38 <ais523> (I should explain the 888 thing for people who aren't British and/or aren't old enough to have seen a 10-to-20-year-old television; basically, the UK analog TV channels had an information service which was a bit like a website but much more limited, with the information carried in the vertical retrace time between frames; each page had a three-digit number; and number 888 was reserved for the closed captions (and sent much more frequently than the
13:56:40 <ais523> other numbers, which would be updated every 20 seconds or so, and normally cycled between multiple pages)
13:56:52 <ais523> 100 was the home page, and I think 199 was the index
13:57:11 <b_jonas> ais523: yes, that's called teletext
13:57:17 -!- tertu has joined.
13:58:05 <ais523> b_jonas: in the UK, it was called Teletext by ITV, but Ceefax by the BBC
13:58:38 <fizzie> Teksti-TV ("text TV") in Finland.
13:59:02 <ais523> I used to get video game recommendations from Teletext
13:59:11 <ais523> Teletext is directly responsible for my love of Advance Wars
13:59:42 <fizzie> I used to read the letters from the viewers occasionally.
14:00:05 <fizzie> Plus there was a page for DXers.
14:00:32 <ais523> b_jonas: a computer game series for the Gameboy Advance and Nintendo DS; it's actually part of a larger series called Nintendo Wars, but has an identity of its own
14:00:42 <ais523> it's basically a lightweight turn-based strategy game
14:01:02 <fizzie> The sidebar at http://www.yle.fi/tekstitv/html/P100_01.html -- the web-terface to the "Finnish BBC's" TeleText service -- claims they still have 1.7 million "users", though I find that slightly dubious, they don't exactly explain how they've arrived at that number.
14:01:12 <fizzie> I understand Ceefax was shut down the other year?
14:01:19 <fizzie> I think I heard people being disappointed about it.
14:01:25 -!- Patashu_ has quit (Ping timeout: 252 seconds).
14:01:44 <ais523> fizzie: there was a replacement for digital TVs, not sure if that's still going
14:01:48 <ais523> I think it is but I'm not sure
14:01:52 <b_jonas> I'm not sure whether TV stations still have teletext here in Hungary even after the all-digital thing
14:01:54 <ais523> the major change is that it supports 4-digit numbers now
14:02:24 -!- ais523 has quit.
14:02:30 <b_jonas> teletext is a really ancient system, it was designed to be easily decodable by simple electronics, and that shows
14:02:36 <fizzie> DVB has some amount of TeleText support, they've kept at least that YLE thing.
14:02:45 <b_jonas> so not only it's limited, but it also has a locale-dependent character set
14:03:24 <b_jonas> yes, it seems we still have teletext
14:03:28 <fizzie> Huh, there's actually more details about those 1.2 million users, it was based on some opinion poll.
14:03:43 <b_jonas> there's a javascript-based copy on the internet at http://www.teletext.hu/
14:04:34 <fizzie> 1.2 million look at teletext at least once a week, 780 000 visit at least daily, 360 000 at least twice a day; 97% do it via a TV.
14:05:09 <fizzie> Trending down in the "less than 25 years" age category, somehow I'm not terribly surprised.
14:05:33 <b_jonas> fizzie: how can they measure that? it's a passive system, the tv doesn't send signals
14:05:56 <fizzie> And then extrapolating.
14:06:08 <fizzie> They don't mention sample sizes, but come on, we're not doing *science* here.
14:06:24 <b_jonas> at least they don't quote numbers with absolute error of 0.01 persons like some of the tv channel viewer statistics
14:06:37 <b_jonas> which, mind you, in the analog tv era were also impossible to produce for exactly the same reason
14:06:53 <b_jonas> for digital tv, maybe you can get teletext statistics, I don't know
14:07:04 <b_jonas> I've no idea how that works
14:07:22 -!- MindlessDrone has joined.
14:08:08 <fizzie> I've read about it, and I think it was something deliciously old-fashioned.
14:08:49 <fizzie> I mean, they've got all that MHP stuff and so on going on, but the teletext was going through something involving things not too far departed from the analogue formats.
14:10:12 <fizzie> It's one of these "interactive TV" things they did around DVB.
14:10:28 <fizzie> There's a Java VM involved and all that, I don't know if it's actually used anywhere.
14:10:48 <fizzie> "In May 2010 the largest deployments DVB-MHP are in Italy (DVB-T), Korea (DVB-S), Belgium (DVB-C) and Poland (DVB-S) with trials or small deployments in Germany, Spain, Austria, Colombia, Uruguay and Australia. MHP service was also offered in Finland by Finnish Broadcating Corporation (Yleisradio), but the service was shut down at the end of 2007 after technical failure. The shutdown wasn't ...
14:10:49 <b_jonas> jesus, java vm in your tv? just like in old mobile phones? scary
14:10:55 <fizzie> ... ever officially announced."
14:11:44 <fizzie> There's also the MHEG-5 language.
14:15:32 <fizzie> Yeah, DVB-TXT is a standard for encoding the teletext stuff in a MPEG-2 bitstream, the idea being that a DVB receiver box connected the "old-fashioned way" can then disentangle it and re-embed it in the vertical blanking interval signal, and an old TV set then re-decode it out.
14:17:32 <fizzie> I haven't been following the market at all, I don't know if native DVB receivers in TVs (and boxes connected over HDMI) can do teletext decoding. I guess so, if they've got all those millions of users still.
14:17:44 <Jafet> This is extra great when you factor in that many new Smart TVs have cameras in them
14:20:31 -!- drdanmaku has joined.
14:20:43 <fizzie> "-- these fields correspond to the 43 bytes following the clock-run-in sequence of an EBU Teletext data packet as defined in ITU-R Recommendation BT.653 -- Data packets are inserted in the same order as they are intended to arrive at the Teletext decoder or to be transcoded into the VBI --" so apparently DVB-TXT is just stuffing that same bitstream in.
14:21:24 -!- shikhin has joined.
14:22:13 <Jafet> `run fgrep 'KELVIN SIGN' bin/UnicodeData.txt
14:22:13 <HackEgo> 212A;KELVIN SIGN;Lu;0;L;004B;;;;N;DEGREES KELVIN;;;006B;
14:22:46 <fizzie> The decrees of Kelvin.
14:27:15 <b_jonas> oh, that reminds me, I have a crazy idea
14:29:21 <b_jonas> let's redefine UTC so it increases a little bit faster than it does now, but jumps back an hour once a year;
14:29:44 <b_jonas> and make local time follow it but jump back an hour a different date of the year,
14:30:00 <b_jonas> so that UTC and local time are symmetric, both jump back an hour compared to the other
14:30:20 <b_jonas> and their offsets alternate between the two values they use now,
14:30:34 <b_jonas> but local time won't skip an hour forward anymore
14:35:24 <Jafet> I have an even crazier idea
14:35:30 <Jafet> Don't use this daylight saving crap
14:50:15 -!- ais523 has joined.
14:52:27 <ais523> is this channel really > 10% bots?
14:53:04 <applybot> Isabelle is not running. \ Loaded theories: Main "~~/src/HOL/Library/Code_Target_Nat" "~~/src/HOL/Number_Theory/Primes" \ 0 lines in session. \ Command timeout is 20 s. \ Unicode translation enabled. \ Colour output enabled.
14:53:15 <ais523> applybot, clog, egobot, fungot, glogbot, HackEgo, idris-ircslave, jconn, lambdabot are the ones that have bot-like names or that I know are bots
14:53:15 <fungot> ais523: " and this is a new game. there is no quadrant which naturally led to a fnord and fnord hoarsely at something which amused myself that way. consider this platform i am aware, commissioner, that there are no gentiles in the garden, examining the fastenings of the drawing-room window, washing and the summoning of the small piece of source code anywhere there's whitespace is ignored and made my own, freed. in c, it's dlope
14:53:55 <Jafet> myndzi is somewhere between 0 and 1 of a bot
14:54:06 <Jafet> So that makes the >10% by a hair
14:54:32 <fizzie> Does the codu.org logs, I presume.
14:54:34 <b_jonas> glogbot, ais says you're a bot, is that true?
14:55:08 <fizzie> "monotone" sounds like a bot. (No offense.)
14:55:26 -!- monotone has changed nick to polytone.
14:55:39 <fizzie> That's much less like one.
14:55:49 <Jafet> MindlessDrone seems somewhat likely
14:58:57 -!- variable has changed nick to trout.
15:01:44 -!- home has joined.
15:02:14 <home> are you guys all bots?
15:02:50 <ais523> quite a few are, though
15:02:57 <ais523> fungot: are you a bot?
15:02:57 <fungot> ais523: and more plus the latin is a timeless language
15:04:44 <ais523> home: ‰ is out from % by a factor of 10
15:04:50 <ais523> so what the topic means is that we're more than 10% bots
15:04:53 <ais523> I counted, and this is true
15:05:06 <Jafet> Well, this was true.
15:05:58 <ais523> we need another 8 non-bots to join before it becomes false, unless I missed one, or unless you count myndzi who is sometimes a bot (e.g. \o/)
15:06:09 <ais523> maybe the ) threw it off: \o/
15:06:17 -!- atehwa has quit (Ping timeout: 264 seconds).
15:07:47 -!- atehwa has joined.
15:08:05 <ais523> well at least two bots agree on the bot percentage
15:08:10 <ais523> right down to the number of decimal places involved
15:08:23 <ais523> !c printf("%lf\n", 9.0 / 82.0 * 100.0);
15:08:43 <ais523> EgoBot disagrees on the number of decimal places, though
15:10:02 <b_jonas> ) (9 % 82) * 100 NB. jconn disagrees on the number of decimal places too
15:10:52 <ais523> now we have to get fungot to do the same calculation
15:10:52 <fungot> ais523: i know i didn't know that you've had it for some time i added a new page and sends it to emacs, i suggest, vote). you need just some 50 more metres and i'm home, and realised i forgot to take down what he actually checks
15:11:10 <int-e> !echo 'scale=64;9/0.82' | bc
15:11:10 <EgoBot> 'scale=64;9/0.82' | bc
15:11:16 <int-e> `` echo 'scale=64;9/0.82' | bc
15:11:17 <HackEgo> 10.9756097560975609756097560975609756097560975609756097560975609756
15:11:23 <ais523> fizzie: I was going to ask you if fungot supported fingerprints for floating-point arithmetic, then I realised it doesn't run Funge code (it's just /written/ in Funge code)
15:11:24 <fungot> ais523: that is just a value of type is created containing the syntax for mark if he was really gonna get worse and worse each week,
15:11:44 <int-e> !echo `` echo 'scale=64;9/0.82' | bc
15:11:44 <EgoBot> `` echo 'scale=64;9/0.82' | bc
15:12:40 <Jafet> @run 9 / 82 * 100 :: CReal
15:12:41 <lambdabot> 10.9756097560975609756097560975609756097561
15:12:51 <ais523> there are basically two mechanisms for preventing botloops used in this channel
15:12:55 <ais523> some bots don't accept input from other bots
15:13:02 <ais523> other bots refuse to produce output that will be run by other bots
15:13:16 <ais523> neither sort of bot can be involved in a loop, relatively obviously
15:13:18 <b_jonas> ais523: the proper way would be for bots to output NOTICE only, not PRIVMSG
15:13:23 <int-e> @run text "!echo too many spaces"
15:13:26 <b_jonas> but people seem to hate that, so not even my bot does that yet
15:13:28 <ais523> b_jonas: yeah but if you send a channel notice, it annoys mIRC users
15:13:37 <ais523> thus, mIRC continues to break IRC by its very existence
15:13:48 <Jafet> I wonder how many actual irc users NOTICE annoys these days.
15:13:56 <ais523> idris-ircslave doesn't ignore fungot
15:14:04 <int-e> b_jonas: right, that client apparently produces popups for NOTICEs
15:14:10 <ais523> this seems potentially usable for a loop, if you could get idris-ircslave to output a line starting with a ^
15:14:27 <b_jonas> ais523: as a compromise, jevalbot (of which jconn is an instance) always starts reply lines in channels with the nick of whoever asked
15:14:35 <b_jonas> that's not enough to stop all bot loops, but it stops some
15:14:40 <ais523> b_jonas: that's not very good at preventing botloops
15:14:45 <ais523> because bots often use their own nick as a prefix
15:14:49 <b_jonas> ais523: if all bots did that, then it was enough
15:15:02 <ais523> in fact, it might make them easier, if you have two bots interpreting the same language
15:15:20 <ais523> although, not very useful unless you can produce text after the ^
15:15:47 <b_jonas> elliott: if all bots did that, then you couldn't get any bot address any other bot (unless you took their nick just before they enter)
15:15:54 <ais523> hmm, fungot didn't run it
15:16:07 <b_jonas> ) (|.' 3QL80ZccObJYffKUf9dZ7Zdrtnk4RR6gprNgzA') ": (9 % 82) * 100
15:16:07 <jconn> b_jonas: |length error
15:16:08 <jconn> b_jonas: | (|.' 3QL80ZccObJYffKUf9dZ7Zdrtnk4RR6gprNgzA') ":(9%82)*100
15:16:09 <ais523> the <EOF> should have given an error message, but we should have got the "test" output first
15:16:18 <b_jonas> ) (|.' 3QL80ZccObJYffKUf9dZ7Zdrtnk4RR6gprNgzA') , ": (9 % 82) * 100
15:16:18 <elliott> b_jonas: but given that one single bot breaks that, it's not a very useful property
15:16:18 <jconn> b_jonas: AzgNrpg6RR4kntrdZ7Zd9fUKffYJbOccZ08LQ3 10.9756
15:16:27 <elliott> b_jonas: you might as well obey the RFC and say all bots should use NOTICE
15:16:38 <elliott> that would also "solve" the problem
15:16:40 <b_jonas> elliott: yes, that's what I should do when I rewrite my bots
15:16:48 <int-e> @run ap (++) show "@run ap (++) show "
15:16:48 <elliott> not really, NOTICE is really annoying
15:16:49 <lambdabot> "@run ap (++) show \"@run ap (++) show \""
15:16:54 <elliott> b_jonas: also, you assume that no nick can ever be a valid command to a bot
15:16:59 <int-e> @run text $ ap (++) show "@run text $ ap (++) show "
15:17:00 <lambdabot> @run text $ ap (++) show "@run text $ ap (++) show "
15:17:17 <b_jonas> AzgNrpg6RR4kntrdZ7Zd9fUKffYJbOccZ08LQ3 of fungot?
15:17:17 <fungot> b_jonas: it's just so stupid that ' stty erase h' has to be all " pow!" and he was suddenly i rose, put up her mouth, pulled down by the gold saucer... think his name was close ever, and yet, at least, that is expressions which have not been able, to assume responsibilities. he went on, " the conclusion is, then thou, the greatest soldier, de. she wanna be friends, his state vsurp'd, his realme a slaughter-house, his subjects,
15:17:22 <ais523> ^ isn't legal in nicks, is it/
15:18:07 <Jafet> I think `^_^v will disagree.
15:18:14 <b_jonas> I made some bot loops a few years ago
15:18:24 <b_jonas> not using my own bots of course, because that would be too easy
15:18:57 <Melvar> I wonder why idris-ircslave isn’t listening to EgoBot.
15:19:38 <ais523> that's normally a good thing, isn't it?
15:19:53 <ais523> it listens to fungot, at least
15:19:53 <fungot> ais523: uh, sorry, i have no information. he seemed, in fine, i can verify it was, that he was overcome with the vastness, profundity, and fnord
15:20:53 <idris-ircslave> When elaborating an application of constructor __infer:
15:21:13 <b_jonas> maybe EgoBot prints something invisible, let me check
15:21:34 <HackEgo> U+200B ZERO WIDTH SPACE \ UTF-8: e2 80 8b UTF-16BE: 200b Decimal: ​ \ \ Category: Cf (Other, Format) \ Bidi: BN (Boundary Neutral)
15:21:36 -!- nc_jonas has joined.
15:23:11 <Jafet> Anyway, this started as a discussion on the seeming proliferation of bots.
15:23:14 <b_jonas> yes, it does print somethign invisible. and I think we checked this once
15:23:29 <b_jonas> Jafet: I think we had a much higher rate of bots on #buubot back when it was more popular
15:23:29 <ais523> I agree with the use of ‰ in the topic, anyway
15:23:38 <ais523> it's like this channel's use of diareses when appropriate
15:24:15 <int-e> lambdabot: > let n:ns = ["lambdacat", "lambdadog", "lambdabot"]; x@[a,b,c] = [": > let n = ","; [a,b,c] = "," in text $ n ++ a ++ show (ns ++ [n]) ++ b ++ show x ++ c"] in text $ n ++ a ++ show (ns ++ [n]) ++ b ++ show x ++ c
15:24:35 <int-e> hmm. needs to use @run
15:24:56 <int-e> lambdabot: @run let n:ns = ["lambdacat", "lambdadog", "lambdabot"]; x@[a,b,c] = [": @run let n = ","; [a,b,c] = "," in text $ n ++ a ++ show (ns ++ [n]) ++ b ++ show x ++ c"] in text $ n ++ a ++ show (ns ++ [n]) ++ b ++ show x ++ c
15:24:57 <lambdabot> lambdacat: @run let n = ["lambdadog","lambdabot","lambdacat"]; [a,b,c] = [":...
15:25:47 <int-e> so it'd need to be a really short quine.
15:25:49 <ais523> it's not quite a perfect quine, it forgot the pattern match the second tiem round
15:26:26 <b_jonas> but those lambdacats are just funny pics
15:26:41 <int-e> right. I added the x@ as an afterthought, it's easy enough to fix in [a,b,c]
15:27:32 <int-e> b_jonas: the idea was to cycle through the nicks
15:28:22 <b_jonas> lambdabot: @run "you don't reply to anything that starts with a space, do you?"
15:29:04 -!- nc_jonas has quit (Ping timeout: 265 seconds).
15:29:06 <int-e> b_jonas: Of course not :)
15:30:54 <int-e> @let cheat = text "lambdacat: @run cheat" -- lambdabot is too powerful
15:31:01 <int-e> lambdabot: @run cheat
15:31:14 <int-e> it's a good thing that it adds that space.
15:31:30 <ais523> int-e: I remember doing that to exploit some sort of impromptu golf contest
15:32:19 <b_jonas> ) text =: 'what, like this?'
15:32:21 <jconn> b_jonas: what, like this?
15:33:26 <ais523> assignment in J is backwards from Pascal? as in =: not :=?
15:34:39 <Jafet> @run text (ap printf show "text (ap printf show %s)")
15:34:41 <lambdabot> text (ap printf show "text (ap printf show %s)")
15:34:55 <ais523> huh, Haskell has a printf?
15:35:06 <ais523> that seems hard to fit into the type system
15:35:11 <Melvar> ais523: It’s because : (and .) is a modifier on the previous character generally. So = is compare equality, =: is global assign, =. is local assign, and there are many such triples.
15:35:12 <b_jonas> Jafet: wouldn't var instead of text work?
15:35:37 <Jafet> @run var $ ap printf show "var $ ap printf show %s")
15:35:38 <lambdabot> <hint>:1:47: parse error on input ‘)’
15:35:40 <Jafet> @run var $ ap printf show "var $ ap printf show %s"
15:35:41 <lambdabot> var $ ap printf show "var $ ap printf show %s"
15:35:46 <ais523> Melvar: I was very impressed with Perl 6 for inventing the .= operator
15:35:54 <ais523> a .= b expands to "a = a.b"
15:36:23 <ais523> where b would typically be a method call
15:36:43 <Melvar> ais523: Doesn’t perl 5 already have that, except . means append there?
15:36:56 <ais523> Melvar: yes, that's less interesting
15:37:00 <ais523> it doesn't have a ->= operator
15:37:16 <coppro> ais523: isn't = as a suffix some form of meta-operator?
15:37:25 <Melvar> But yeah, Perl 6 interestingly generalized this sort of thing.
15:37:25 <coppro> because it's perl 6 and it would be too simple otherwise
15:37:53 <ais523> although interpreting method calls as an infix operator seems a little weird to me, because I consider what's on the right to be syntactically different from what's on the left
15:38:06 <ais523> that said, Perl 5 has =>, which has a syntactically different left
15:38:12 <ais523> and is otherwise identical to a comma
15:38:24 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:38:46 <coppro> perl 6 is overengineere
15:38:51 <Melvar> ais523: Well, in some languages/contexts, method call is just reverse application.
15:38:53 <coppro> we should add it to esolang for that reason
15:39:00 <ais523> I think its main purpose for existence is being overengineered
15:39:19 <coppro> ais523: did you see Tarpit, btw? I was bored
15:39:37 <ais523> no, and I have to go home now, so I won't get to see it until later
15:39:41 <b_jonas> @run var $ concatMap (["\\", "\"", ", ", "@run var $ concatMap([", "]!!) [3,1,0,0,1,2,1,0,1,1,2,1,3,1,2,1,4,1,4]"]!!) [3,1,0,0,1,2,1,0,1,1,2,1,3,1,2,1,4,1,4]
15:39:42 <lambdabot> @run var $ concatMap(["\\", "\"", "@run var $ concatMap([", "]!!) [3,1,0,0,1...
15:39:59 <ais523> definitely don't have time to see it now, then
15:40:02 -!- ais523 has quit.
15:41:04 <b_jonas> hmm, it really truncates early
15:42:46 <home> concatMap([", "]!!)
15:43:01 -!- home has quit (Quit: Lost terminal).
15:45:09 <int-e> it truncates each line after 80 characters *on channels*
15:45:37 -!- nooodl_ has changed nick to nooodl.
15:45:57 <int-e> it's happier to be verbose in privmsg
15:50:01 <b_jonas> so do we have any loopable bots here? I tried to set up a loop using fungot once, but I couldn't
15:50:02 <fungot> b_jonas:, so i'd make stuff up to. why, this is for you guys are a lot of the design, prisoners and slaves that have sucked. rephrase: " i tried todo a _" is 0
15:50:30 <coppro> b_jonas: we might, but we'll kill you
15:57:49 <Melvar> I never cease to be amused by that one.
15:59:17 -!- tertu has quit (Ping timeout: 252 seconds).
16:16:55 <fizzie> We've had botloops in the history of the channel.
16:17:20 <fizzie> But HackEgo and EgoBot have that zero-width space thing, and fungot has a manual ignore list.
16:17:20 <fungot> fizzie: " and this is a new game. there is no quadrant which naturally led to a fnord style for the operator, or identical here.) indent all
16:17:28 -!- password2 has quit (Quit: Leaving).
16:18:28 <Jafet> Proper flood control is the best, but it is usually not implemented
16:20:43 <fizzie> Oh, and fungot-babble has a limit of not replying to the same person more than four (or so) times in a row.
16:20:43 <fungot> fizzie: it's what that guy in medina, a village near the mystic mountain" 65,000,000 b. c.? yes, i'd have done something very brave? fnord 06:22, 29, no. 2, 2, 3, 4, 8, 13, 1(::**) ...bad insn!
16:21:25 -!- AnotherTest has joined.
16:30:17 -!- adu has joined.
16:33:26 <coppro> zero-width space thing?
16:35:40 <Bike> they put a zero-width before their output, i think, which trips up other prefix commands
16:38:02 -!- conehead has joined.
16:40:55 <b_jonas> fizzie: for the record, jconn has an ignore list too, but it's not really up-to-date so bots on this channel are probably not on it;
16:41:34 <b_jonas> however, a bot could send a private message with a special command to jconn to have it added to its ignore list (this is temporarily, lasts only until jconn restarts)
16:43:08 <fizzie> Bike: Approximately so, except not to lines starting with an alphanumeric character.
16:44:11 -!- edwardk has joined.
16:56:15 -!- Phantom_Hoover has joined.
17:03:17 -!- nooodl_ has joined.
17:06:13 -!- nooodl has quit (Ping timeout: 252 seconds).
17:08:01 -!- zzo38 has joined.
17:13:18 <zzo38> OK now I renamed some functions, such as taillib_close into taillib_free and taillib_open into taillib_read
17:13:42 <zzo38> I agree it is better this way.
17:15:08 <zzo38> I mentioned also interface for Haskell and SQL as well as C, but I forgot one; another one may be useful to have is Forth. Possibly the Forth interface can be write-only, although someone else could make a read/write interface too if you like to.
17:15:35 -!- FreeFull has joined.
17:15:38 -!- MoALTz has joined.
17:30:01 -!- Vamadeus has joined.
17:30:14 <zzo38> It is good idea, what is suggested before; to add functions to add a object, text, subroutine, instruction, etc.
17:32:06 -!- password2 has joined.
17:32:31 -!- password2 has quit (Max SendQ exceeded).
17:41:16 <zzo38> I try to think of, what is the best interface to add such thing on?
17:42:14 -!- password2 has joined.
17:43:02 -!- password2 has quit (Max SendQ exceeded).
17:43:59 -!- password2 has joined.
17:44:07 <zzo38> I did already add one Game*taillib_new_game(void) function.
17:44:38 -!- password2 has quit (Max SendQ exceeded).
17:45:45 -!- password2 has joined.
17:46:12 -!- HackEgo has quit (Remote host closed the connection).
17:46:32 -!- HackEgo has joined.
17:54:35 -!- nooodl_ has changed nick to nooodl.
17:59:27 <HackEgo> alfromcoin luicoin ahacoin loopcoin beckoucoin duscoin kondccoin undcoin laborishcoin frogcoin retacoin eningianiquecoin calliicoin truckcoin luctcoin prolecoin grandcoin dumerycourcogcoin gotocoin v--coin
18:00:01 <fizzie> laborishcoin, the currency of the proletariat.
18:00:34 <fizzie> Oh, there's plain "prolecoin" on the very same line, too. Must be some sort of a plot.
18:02:44 <kmc> communist coins :O
18:03:46 -!- adu has quit (Quit: adu).
18:05:47 <fizzie> "“I just don’t care [about fiddling with my phone while driving and hitting a cyclist] because I’ve already been through a lot of bullshit and my car is like pretty expensive and now I have to fix it,” she told a police officer."
18:08:43 <Jafet> I blame google for not taking over the road system yet
18:09:17 <zzo38> It isn't Google's job to take over the road system (nor should it be).
18:11:24 <Phantom_Hoover> isometries of a metric space needn't be surjective right?
18:12:11 <kmc> zzo38: tell that to justine tunney
18:12:35 <kmc> http://www.theguardian.com/technology/2014/mar/20/occupy-founder-obama-eric-schmidt-ceo-america
18:13:46 -!- zzo38 has quit (Remote host closed the connection).
18:14:16 <Jafet> zzo couldn't handle the champagne tranarchist
18:17:46 <Jafet> oi el ol' goog http://math.stackexchange.com/questions/340326/if-f-m-to-m-an-isometry-is-f-bijective
18:18:03 <kmc> i know, right?
18:18:14 <Phantom_Hoover> Jafet, ahahaha my counterexample was way more complicated than that
18:20:44 -!- Taneb has quit (Disconnected by services).
18:21:07 <Jafet> Wait, why is that not surjective
18:21:35 -!- atriq has joined.
18:21:43 <fizzie> Jafet: Have you accidentally tilted your head 90 degrees?
18:22:03 -!- atriq has quit (Disconnected by services).
18:22:09 <Bike> "Explaining on Twitter why she thinks anti-capitalism is compatible with promotion of her employers, "
18:22:22 -!- glogbackup has quit (Remote host closed the connection).
18:22:24 <oklopol> Phantom_Hoover: infinite space with distance between any pair of points is 1
18:22:35 -!- Taneb- has joined.
18:24:09 <oklopol> first answer in the stackexchange link is more natural of course
18:25:04 <Slereah> I want to go to the meta stack exchange
18:25:06 -!- tertu has joined.
18:25:18 <Slereah> "GETTING RID OF MY STACKS FOR NEW STACKS"
18:25:23 <Phantom_Hoover> my geometry exam toay had the question 'prove that the set of all isometrie of a metric space form a transformation group'
18:25:30 <Slereah> WILL ANYONE TAKE MY OLD STACKS FOR OTHER STACKS
18:25:30 <int-e> wtf. "the one corporation that gives away everything for free"?!
18:25:41 <Phantom_Hoover> which is obviously bullshit because isometries aren't invertible
18:25:55 <int-e> Where does she think Google gets its money? Ok, so she's the product, but still, that's ridiculous.
18:26:13 <kmc> Slereah: lololol
18:26:18 <fizzie> int-e: Well, but I mean, they're building the superintelligence.
18:26:18 <Slereah> I thought google was making its money on human bones
18:26:32 <Slereah> They steal children's bones
18:26:49 <oklopol> probably they were thinking of R^n
18:29:00 <fizzie> Google's sponsoring this conference I'm going to, they've invited people (probably according to some ALGORITHM) to this "Google Research Happy Hour" thing to "hear perspectives" and "meet and talk" about a "slew of interesting problems".
18:29:31 <fizzie> For the good of mankind, I'm sure.
18:32:30 <fizzie> I don't know, a "happy hour" at a "rooftop bar", how could it be a trap.
18:33:18 <kmc> is the booze free or no
18:33:24 <kmc> maybe it's ad-supported
18:33:31 <kmc> I guess that's usually how these things work.
18:33:37 <int-e> fizzie: take a parachute
18:34:15 <fizzie> I think it's only something like a sixth floor, can you parachute-jump from that low?
18:34:46 <fizzie> Florence isn't known for it's skyscrapers, I believe.
18:36:21 <kmc> i walked to the top of some old church in florence
18:36:29 <kmc> but yeah it wasn't that high
18:37:25 <fizzie> There are like two "main" speech recognition conferences, and the other was in Florence in 2011, I was there too.
18:37:32 <fizzie> It's even pretty much the same conference center.
18:38:26 <fizzie> (Slightly different buildings on the other side of a street, from what I saw in a map.)
18:49:12 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:56:15 -!- idris-ircslave has quit (Quit: Terminated).
18:56:26 -!- Melvar has quit (Quit: WeeChat 0.4.3).
19:01:37 -!- Vamadeus has quit (Remote host closed the connection).
19:05:11 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
19:08:07 -!- Melvar has joined.
19:10:27 <int-e> I guess this was bound to happen http://flappy2048.com/
19:11:43 <fizzie> That seems a lot easier to control than Flappy Bird.
19:12:48 <Slereah> The hitbox is very forgiving
19:13:16 <int-e> but then the walls start moving (and I stopped at 4096)
19:13:35 <fizzie> I stopped at 4096 too.
19:16:28 <fizzie> Well, I did 32768 too. The main trouble (for me) seems to be distinguishing between the boxes when the numbers get large.
19:31:35 -!- password2 has quit (Ping timeout: 252 seconds).
19:33:56 -!- nucular has quit (Quit: Excess Food).
19:45:35 <kmc> looks like http://mainisusuallyafunction.blogspot.com/2014/02/x86-is-turing-complete-with-no-registers.html made it to /r/programming today
19:47:54 <fizzie> Do you get to see some sort of analytics thing on visitor counts or something?
19:48:38 <kmc> there's a basic one built into blogspot
19:48:45 <kmc> and i also have google analytics turned on, I think, but I never look at it
19:49:17 <kmc> (why caps?)
19:49:25 <fizzie> I don't know. Emphasis.
19:49:35 <fizzie> Did it make you feel like a rockstar programmer?
19:49:59 <kmc> no, I didn't even trash the last hotel room I stayed in for work
19:50:41 <kmc> Google Analytics seems to have a lot of stuff that would be useful if I was trying to make money from my blog
19:50:54 <kmc> not so much otherwise
19:51:13 <fizzie> How do people make money from blogs, anyway? Just ad revenue, or something else?
19:51:29 <kmc> another way is affiliate links
19:51:44 <kmc> if you review products and people click a link to amazon to buy them, you can get a cut
19:51:48 <fizzie> Oh, right, I've seen those.
19:52:15 <kmc> there was somebody who talked about editing amazon URLs in user comments to add the affiliate tag
19:52:18 <kmc> (automatically)
19:52:23 <kmc> which seems sleazy to me
19:52:57 <Bike> it's kind of sleazy but the links are actually due to your site, so
19:53:19 <fizzie> I think I've heard of some hotel/net cafe/wifi provider/something like that, who had a transparent proxy rewriting all links everywhere with the affiliate tag.
19:53:27 <fizzie> That's somewhat more sleazy.
19:53:45 <FreeFull> I've heard of an ISP doing that
19:54:04 <kmc> stupid future
19:54:16 <FreeFull> Definitely sleazy, and forbidden by Amazon
19:54:34 <FreeFull> The person who noticed contacted Amazon about it
19:56:35 <kmc> I got the idea for that blog post here, on November 5, while in a state of joyous intoxication
19:58:20 <kmc> worked out most of how to do it on a long flight (SFO-ICN)
20:05:00 <shachaf> kmc: did you see my link yesterday
20:06:37 <shachaf> i meant http://flint.cs.yale.edu/flint/publications/flex.pdf
20:09:37 -!- tertu has quit (Ping timeout: 240 seconds).
20:11:32 -!- Sprocklem has joined.
20:12:31 -!- tertu has joined.
20:25:29 -!- shikhin has quit (Ping timeout: 264 seconds).
20:48:25 -!- tertu has quit (Ping timeout: 252 seconds).
20:51:56 -!- AnotherTest has quit (Ping timeout: 265 seconds).
21:00:38 -!- tertu has joined.
21:10:03 -!- tertu has quit (Ping timeout: 252 seconds).
21:10:21 -!- tertu has joined.
21:11:38 -!- edwardk has quit (Ping timeout: 240 seconds).
21:24:33 -!- idris-ircslave has joined.
21:24:46 -!- Sprocklem has quit (Read error: Operation timed out).
21:32:04 -!- Bike_ has joined.
21:33:23 -!- Bike_ has changed nick to Bicyclidine.
21:37:04 -!- MoALTz_ has joined.
21:37:04 -!- tertu has quit (Ping timeout: 276 seconds).
21:38:49 -!- MoALTz__ has joined.
21:40:01 -!- MoALTz has quit (Ping timeout: 240 seconds).
21:41:56 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
21:44:38 -!- MoALTz_ has joined.
21:46:52 -!- MoALTz has joined.
21:48:07 -!- MoALTz__ has quit (Ping timeout: 276 seconds).
21:49:31 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
21:53:05 <fizzie> "SAMSUNG-SGH-E250/1.0 Profile/MIDP-2.0 Configuration/CLDC-1.1 UP.Browser/6.2.3.3.c.1.101 (GUI) MMP/2.0 (compatible; Googlebot-Mobile/2.1; +http://www.google.com/bot.html)" funny User-Agent, there.
21:53:26 <fizzie> Wonder if it's always the same, or if it randomly picks different "mobiley" UAs.
21:53:53 <fizzie> "Mozilla/5.0 (iPhone; CPU iPhone OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A5376e Safari/8536.25 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
21:54:01 <fizzie> I guess that might answer it.
21:54:21 <fizzie> Oh, that's not even Googlebot-Mobile.
21:54:34 <fizzie> That some kind of an iGooglebot, then.
21:54:47 -!- Bicyclidine has quit (Read error: Connection reset by peer).
21:58:37 -!- oerjan has joined.
22:00:38 -!- Bike_ has joined.
22:01:41 -!- Bike_ has changed nick to Bicyclidine.
22:10:04 -!- impomatic has left.
22:11:22 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:12:15 -!- `^_^v has joined.
22:23:15 -!- conehead has quit (Quit: Computer has gone to sleep).
22:26:10 <oerjan> @run 42 / 3 -- are you very slow today?
22:26:33 <oerjan> oh wait i was looking at the second field
22:28:44 -!- nooodl has quit (Quit: Ik ga weg).
22:39:41 <idris-ircslave> (((1, 2), 3), 4) : (((Integer, Integer), Integer), Integer)
22:40:20 <ion> Ooh, that’s nice sugar.
22:40:46 <Jafet> Haskell tuples are actually a severe regression.
22:40:50 <int-e> # 1,2,3,4;; - : int * int * int * int = (1, 2, 3, 4)
22:40:50 <int-e> # (1,2),(3,4);; - : (int * int) * (int * int) = ((1, 2), (3, 4))
22:41:19 <oerjan> oh wait Melvar's fold didn't leave out the () in the printing
22:42:16 <oerjan> well ocaml is about the same as haskell there
22:42:28 <int-e> Well, I find that it looks weird. semantically it's not so different from Haskell's (,,,,) constructors.
22:42:41 <Jafet> applybot: raw:ML {* (((1,2),3),4) *}
22:42:41 <applybot> val it = (((1, 2), 3), 4): ((int * int) * int) * int
22:42:53 <Jafet> applybot: raw:ML {* (1,(2,(3,4))) *}
22:42:54 <applybot> val it = (1, (2, (3, 4))): int * (int * (int * int))
22:43:11 <Jafet> Hmm wait, I thought ML had this
22:43:26 <int-e> applybot: raw:ML {* 1,2,3,4 *}
22:43:36 <int-e> applybot: raw:ML {* (1,2,3,4) *}
22:43:46 <oerjan> well ocaml is an ml variant
22:43:59 <Jafet> I didn't want to let anyone else run arbitrary ML code.
22:43:59 <int-e> what does applybot speak?
22:44:06 <oerjan> so it stands to reason it'll have inherited much syntax
22:44:09 <int-e> Jafet: fair enough
22:44:21 <Jafet> applybot: term "((1, 2), 3)" -- isabelle
22:44:23 <applybot> ((1∷'a, 2∷'b), 3∷'c) ∷ "('a * 'b) * 'c"
22:44:32 <Jafet> applybot: term "(1, (2, 3))"
22:44:33 <applybot> (1∷'a, 2∷'b, 3∷'c) ∷ "'a * 'b * 'c"
22:44:50 <int-e> Interesting. (I've had some exposure to Isabelle)
22:45:01 <Jafet> Ok, so ML doesn't have inductive tuples.
22:45:24 <Jafet> applybot: raw:ML {* #4 (1, 2, 3, 4, 5) *} -- it does have this though
22:45:24 <applybot> *** Outer syntax error: command expected,
22:45:38 <Jafet> applybot: raw:ML {* #4 (1, 2, 3, 4, 5) *}
22:47:32 <lambdabot> (Field9 s t a b, Functor f) => (a -> f b) -> s -> f t
22:47:56 <int-e> lens is so painful with all that s t a b bing.
22:48:34 <oerjan> have you seen http://cokmett.github.io/cokmett/ yet
22:49:00 <oerjan> (click on picture to activate)
22:49:27 <Jafet> I remember there was an instance alpha-equivalent to b a c k s t a b
22:50:36 * oerjan swats shachaf -----###
22:50:55 -!- tromp has joined.
22:51:07 <oerjan> now go make edwardk change it to s w a t twh
22:51:41 <int-e> hmm. s,t = source, target?
22:52:00 <oerjan> int-e: i can never remember which way the s t a b go without looking them up :(
22:52:09 * int-e still has to learn lenses.
22:52:12 <shachaf> int-e: It could mean so many different things!
22:52:21 <shachaf> or s could stand for state
22:52:33 <oerjan> hm source/target is mnemonic at least
22:53:17 <shachaf> > (`runState` ("a",2)) $ do { _2 += 5 } -- s is the state!
22:53:17 <idris-ircslave> (`runState` ("a",2)) $ do { _2 += 5 } -- s is the state!<EOF>
22:53:29 <shachaf> or s stands for "structure"
22:53:49 -!- oerjan has set topic: The channel with 100‰ > bots | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
22:53:59 <shachaf> structure was the original one, state was what convinced edwardk, and source/target is a nice mnemonic now
22:54:04 <oerjan> shachaf: DON'T RUIN MY MNEMONIC AGAIN
22:55:37 <oerjan> i think i asked some time whether cokmett was statistically guaranteed to stop (i.e. probability 1) but i never got an answer beyond "check the code"
22:55:54 <int-e> hey, with all type variables in there you can make an fstab
22:56:11 <int-e> (Functor f => (a -> f b) -> s -> f t)
22:56:57 -!- conehead has joined.
22:57:11 -!- Sprocklem has joined.
22:57:18 <oerjan> shachaf: um btw if s is a state then you need s ~ t, no?
22:57:20 <Bicyclidine> "This gets rid of the SIXTY_FOUR_BIT_LONG, SIXTY_FOUR_BIT (not the same!), THIRTY_TWO_BIT, SIXTEEN_BIT and EIGHT_BIT defines."
22:57:42 -!- boily has joined.
22:57:45 -!- Phantom_Hoover has joined.
22:58:22 <oerjan> boily: chickening in again?
22:59:01 <shachaf> oerjan: unless you use... indexed state
22:59:17 <shachaf> which has nothing do with with indexed lenses, by the way
22:59:26 <int-e> @run sort "check in" == sort " chicken"
22:59:39 -!- adu has joined.
23:00:00 <int-e> (curtesy of the internet anagram finder)
23:01:03 -!- ineiros_ has joined.
23:01:06 -!- ineiros has quit (Read error: Operation timed out).
23:01:14 -!- aloril has quit (Read error: Operation timed out).
23:03:23 <boily> I am... I feel... I don't know how to feel.
23:03:57 -!- sebbu has quit (Ping timeout: 252 seconds).
23:05:22 -!- aloril has joined.
23:08:04 -!- sebbu has joined.
23:08:38 -!- sebbu has quit (Changing host).
23:08:38 -!- sebbu has joined.
23:09:00 <oerjan> hm reading the cokmett source is complicated by the fact the original haste isn't included in the github :(
23:09:30 -!- erdic has quit (Remote host closed the connection).
23:10:05 <boily> oerjan: cokmett, as in edwardk's caterogical dual?
23:10:32 <oerjan> oh right you joined after i pasted http://cokmett.github.io/cokmett/
23:11:29 <oerjan> (we were discussing lens again)
23:13:25 <int-e> but now we've lost focus
23:13:32 <boily> int-e...............................
23:14:26 <int-e> what, one of the humble weekly sales games is called "cthulhu saves the world" ...
23:14:28 <boily> also, this just in → http://ro-che.info/articles/2014-04-24-lens-unidiomatic.html
23:16:16 <Bicyclidine> int-e: i think i saw that one a couple months ago, it was basically an rpg parody
23:16:19 <elliott> Despite having some (fairly basic) understanding of what prisms are, this signature tells me nothing at all, even despite the usage of type synonyms.
23:16:31 <elliott> this is just contentless FUD.
23:16:38 -!- yorick has quit (Remote host closed the connection).
23:17:05 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/words
23:17:12 <Bicyclidine> the idea of programmers using actual empirical data for these things is lolarious imo
23:17:19 <elliott> that type signature is very simple and anyone who actually understands what a prism is and what Traversable is can understand it.
23:17:35 <elliott> he could have picked a way better example but it kinda illustrates how little of a point he has there.
23:17:40 <boily> I understand neither. Traversable still confuzzle my brain.
23:18:09 <Bicyclidine> "A Prism l is a 0-or-1 target Traversal that can also be turned around with remit to obtain a Getter in the opposite direction. " look, do people actually read these words and get information from them
23:18:23 <Bicyclidine> that's not to do with the blog, i just, god
23:18:28 <elliott> but then, I already knew the Haskell community was surprisingly regressive in so many ways.
23:18:57 <oerjan> oh right it's only `coins which has a default argument
23:18:59 <elliott> Bicyclidine: that's old documentation ("remit" doesn't exist now). https://hackage.haskell.org/package/lens-4.1.2/docs/Control-Lens-Prism.html
23:19:03 <elliott> (well, "remit" was renamed.)
23:19:27 <elliott> that sentence makes perfect sense to me but the rest of the docs beyond it are more useful.
23:19:29 <Bicyclidine> i mean, i have some idea of what prisms are because shachaf explained them once
23:19:46 <elliott> it's just leading with the formal definition and then trying to explain it
23:19:50 <elliott> I think you can argue both ways around have merits
23:20:25 <elliott> "traversal that you can invert to construct things with" isn't that elaborate a concept, though
23:21:51 <elliott> well, s/invert/turn around with re/
23:21:55 <int-e> boily: one of the main points of the lens library is that indeed, focus :: s -> (a, a -> s) does not exist as such; it's been abstracted away into a (possibily contravariant) functor.
23:22:01 <elliott> s/construct things with/obtain a Getter in the opposite direction/
23:22:31 <Bicyclidine> nooooo you're falling into the academicese pit again
23:22:33 <int-e> (but at least I understood 'focus' ...)
23:23:25 * int-e wonders whether he could persuade ekmett to rename 'lens' to 'unfocussed'.
23:24:04 <int-e> but I guess I'm taking the pun too far.
23:24:17 <Bicyclidine> also i just want to say that "i have to read the documentation" is a pretty rad complaint to have about something
23:24:40 <int-e> "unlike all other haskell packages out there"
23:24:42 <boily> int-e: egbhgehgheeeehghghghg.
23:25:10 <oerjan> int-e: well the other haskell packages don't _have_ documentation so they _must_ be understood just from the types hth
23:25:13 <int-e> boily: good job. "No anagrams found."
23:25:33 <int-e> oerjan: there is that, yes.
23:25:36 <Bicyclidine> the snooty "like some kind of RUBY programmer" thing is also great
23:26:56 <int-e> I agree with this sentiment, "This is why I regard lens as a language in its own."
23:28:16 <oerjan> some say lens has too many operators but i'm starting to wish basic haskell's operators were as logical
23:28:21 -!- adu has quit (Quit: adu).
23:28:50 <oerjan> (see my discussion of *> <$ <*> <$> etc. the other day)
23:29:32 <int-e> I want to have a look at lens-family
23:29:39 <elliott> int-e: yes, I think that's a reasonable statement. lens would be a reasonable thing to build into a language, and some of the glue it takes to put it into Haskell is a little ugly.
23:29:52 <elliott> but most of that post is nonsense
23:29:59 -!- Patashu has joined.
23:30:06 <elliott> lens-family has subtly incompatible operators with lens I think :(
23:30:19 <elliott> plus it can't do prisms which are a very big deal
23:32:36 <int-e> type APrism s t a b = Overloaded Prismoid Mutator s t a b -- "If you see this in a signature for a function, the function is expecting a Prism, not some kind of alien invader."
23:33:02 <lambdabot> (Choice p, Traversable f, Applicative f1) => APrism' s a -> p (f a) (f1 (f a)) -> p (f s) (f1 (f s))
23:33:19 <oerjan> it hasn't precisely improved :P
23:33:26 <elliott> oerjan: no, that is just ghci
23:33:29 <elliott> it mangles type signatures
23:33:50 <elliott> it makes using lens more painful.
23:34:03 <elliott> it's something about it expanding out because of the -> I think.
23:34:15 <int-e> This is abstraction hell, looking at lens always feels like how I imagine learning math starting with category theory would be.
23:35:16 <int-e> (unless I ignore the types and use a tutorial instead. but that's contrary to how I usually approach haskell libraries. nonidiomatic indeed.)
23:35:32 <oerjan> elliott: perhaps it's because Prism' includes a forall and it gets to the right of a -> ?
23:36:12 <elliott> int-e: the types are mostly easy to follow except where edwardk made them needlessly complex if you learn the basic "lens theory" first. unfortunately I don't know of a good introduction to lens theory
23:36:27 <elliott> it's a case of having to understand the underlying semantic objects before being able to read the types
23:37:00 <oerjan> :t undefined :: Int -> Prism' Bool Char
23:37:01 <lambdabot> (Choice p, Applicative f) => Int -> p Char (f Char) -> p Bool (f Bool)
23:37:35 <oerjan> :t undefined :: Prism' Bool Char
23:37:36 -!- realzies has quit (Quit: realzies).
23:37:36 <lambdabot> (Choice p, Applicative f) => p Char (f Char) -> p Bool (f Bool)
23:37:59 <oerjan> hm seems the -> is not important
23:38:20 <oerjan> :t undefined :: Lens' Bool Char
23:38:21 <lambdabot> Functor f => (Char -> f Char) -> Bool -> f Bool
23:38:36 <lambdabot> Expecting two more arguments to ‘Lens Bool Char’
23:38:36 <lambdabot> Expected a type, but ‘Lens Bool Char’ has kind ‘* -> * -> *’
23:38:36 <lambdabot> In an expression type signature: Lens Bool Char
23:38:50 <oerjan> :t undefined :: Lens Bool Char Int Word8
23:38:51 <lambdabot> Functor f => (Int -> f Word8) -> Bool -> f Char
23:39:41 <oerjan> Lens' is an abbreviation for when you have a lens that doesn't change types, so they're pairwise the same
23:40:32 <lambdabot> (Profunctor p, Functor f) => (s -> a) -> (b -> t) -> p a (f b) -> p s (f t)
23:40:49 -!- adu has joined.
23:41:15 <oerjan> that's an example of changing the type
23:41:45 <oerjan> :t let _ = (1,2)& l .~"hi"; l = _2 in l
23:41:46 <lambdabot> (Field2 s t a b, Functor f) => (a -> f b) -> s -> f t
23:42:17 -!- Taneb- has changed nick to Taneb.
23:42:49 <oerjan> :t let l = _2 where _ = (1,2)& l .~"hi" in l
23:42:49 <lambdabot> (Num t1, Num t) => ASetter (t, t1) (t, [Char]) t1 [Char]
23:43:19 <oerjan> maybe not too instructive
23:43:29 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
23:46:59 <int-e> also love the use of "intuitively" here: "Intuitively it is a bifunctor where the first argument is contravariant and the second argument is covariant."
23:47:19 <int-e> (from the documentation of Profunctor)
23:53:07 -!- Patashu_ has joined.
23:53:07 -!- Patashu has quit (Disconnected by services).
23:53:12 <boily> (oh, a hat of spirit shield!)
23:57:49 <int-e> wth is "dungeon crawl stone soup"
23:58:50 <Bike> a videoed game
23:59:37 <int-e> Sorry, I should stop asking those "I'm going to google this, but first let me phrase it as a question" questions.
00:06:29 -!- erdic has joined.
00:12:04 <elliott> int-e: a dysfunctional game with a more dysfunctional development team :P
00:12:41 <Bike> dysfunctionaler
00:13:30 <boily> I don't mind the dysfunctionality. as long as I can transform anything that moves (and some of the stuff that don't) into poisoned pincushions on fire, everything is fine.
00:21:21 <oerjan> @tell ais523 <ais523> huh, Haskell has a printf? <-- it abuses type classes something fierce
00:30:40 -!- adu has quit (Quit: adu).
00:31:33 -!- adu has joined.
00:31:47 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
00:32:08 -!- Sgeo has joined.
00:37:11 -!- boily has quit (Quit: OPERATOR CHICKEN).
00:48:05 -!- nys has joined.
01:00:24 -!- adu has quit (Quit: adu).
01:02:09 <kmc> it should be a macro, like Rust's equivalent
01:02:41 <kmc> I used to say that it should use typed formatting combinators instead of format strings
01:02:47 <kmc> but format strings are pretty compelling for i18n
01:03:19 <elliott> I think you can do i18n well with formatting combinators.
01:03:33 <oerjan> kmc: hm it could easily be a quasiquote...
01:03:41 <kmc> i think there is a macro printf somewhere in TH, actually
01:04:15 <kmc> hm, but with the macro you can't load translations at runtime
01:04:26 <kmc> or switch languages very easily
01:04:48 <elliott> kmc: you can do it with Typeable if nothing else.
01:04:59 <oerjan> is there a haskell printf which can do that...
01:05:06 <kmc> elliott: aiui, translators (who are not necessarily developers) are very used to the tooling that goes with format strings
01:05:49 <elliott> kmc: would they care if the translation string looks like "foo" % int % "bar" rather than foo%dbar?
01:05:58 <oerjan> hm i guess it's not that hard to write a wrapper around usual printf
01:06:52 <kmc> for all I know Rust has support for dynamic format strings too
01:06:55 <kmc> after all the compiler is a library
01:09:34 -!- edwardk has joined.
01:10:36 <oerjan> haskell printf doesn't seem to have any of that fancy reordering stuff
01:11:24 <oerjan> sadly with the way C printf works it would be impossible to write a typesafe haskell wrapper around it
01:11:58 <kmc> yeah you want reordering for i18n
01:13:54 <elliott> you want identifier keys, really.
01:14:06 <oerjan> edwardk: hi we decided you have to rename s t a b into s w a t, hth
01:14:21 <kmc> shachaf: today I ate at King of Falaf[ei]l
01:14:29 <kmc> (they spell it both ways on the sign)
01:15:06 <oerjan> elliott: what's an identifier key
01:16:07 -!- fowl has quit (Ping timeout: 276 seconds).
01:17:14 <elliott> oerjan: as in, along the lines of the python '%(foo)s %(bar)s' % {'foo': ..., 'bar': ...} syntax
01:17:17 <kmc> apparently it used to be named Falafel Burger King
01:17:27 <elliott> or '{foo} {bar}'.format(foo=..., bar=...) in python 3
01:17:36 <Sgeo> kmc: can do typesafe format with dependent types
01:17:50 <elliott> Sgeo: no more useful than the macro version in practice
01:18:53 <elliott> oerjan: at that point you have a strong argument for just embedding subexpressions and having it be a templating language. foo and bar can just be locals, after all
01:19:48 <oerjan> elliott: i think kmc's comments are to the effect you _really really_ don't want translators to need to know haskell.
01:20:00 <kmc> shachaf: yes
01:20:09 <kmc> shachaf: though it wasn't as good as the first falafel sandwich I had there
01:20:12 <kmc> it'll never be as good :/
01:20:29 <elliott> oerjan: say you have (\n -> [fmt|Result %d{n} is %s{result n}.|]) [0..10]
01:20:38 <elliott> a translator will see Result %d{n} is %s{result n}.
01:20:54 <elliott> which is more accessible than Result %d{0} is %s{1}. or whatever a direct printf style thing would give you
01:21:04 <elliott> of course embedding complex expressions would be unreadable, but not only for the translator.
01:21:05 <oerjan> oh well i suppose they are opaque enough there
01:21:25 <elliott> if you do something complex you can just let complicated = ... in [fmt| ... %d{complicated} ...|]
01:23:33 -!- shikhin has joined.
01:25:43 -!- conehead has quit (Quit: Computer has gone to sleep).
01:30:40 -!- fowl has joined.
01:32:24 <Sgeo> I would have been pissed if Cryptol's number literal syntax included octal with just a leading 0
01:33:36 -!- realzies has joined.
01:35:47 <kmc> i'm glad you're not pissed
01:39:59 <copumpkin> who ever thought that leading 0 octal thing was a good idea
02:03:00 -!- conehead has joined.
02:13:59 -!- tertu has joined.
02:22:24 -!- shikhout has joined.
02:25:01 -!- shikhin has quit (Ping timeout: 252 seconds).
02:25:02 -!- shikhout has changed nick to shikhin.
02:29:34 -!- conehead has quit (Ping timeout: 276 seconds).
02:37:28 -!- nisstyre has joined.
02:37:46 <ion> http://i.imgur.com/hSgim85.jpg
02:38:20 <ion> I’m not sure why you even want syntax for different bases since every base is 10.
02:40:29 <pikhq> But do you mean 0b10, 0x10, 010, or 10?
02:41:32 <pikhq> Or maybe data:application/octet-stream;base64,10= ?
02:42:19 <Bike> is there a joke in the image somewhere
02:44:02 -!- adu has joined.
02:45:00 <oerjan> no, just an octopussy hth
02:49:51 <ion> Aww, while Erlang supports 16#1abc, it does not support 16#10#1abc or (16#10)#1abc.
03:15:04 -!- nys has quit (Quit: quit).
03:16:04 -!- tertu has quit (Read error: Connection reset by peer).
03:16:22 -!- tertu has joined.
03:25:05 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
03:27:59 <Sgeo> "He got a prison sentence of at least 315 years and 8 months to life behind bars and has a 2309 parole eligibility date."
03:28:39 <Sgeo> I.. what... I don't get it. Is this like 'multiple life sentences'? Can parole eligibility dates be reduced?
03:28:42 <Sgeo> Colin Ferguson
03:30:06 <fowl> Sgeo, just in case prisoners get ahold of trancendence-enabling computers
03:31:00 <Bike> i think you need another judge to change parole eligibility
03:31:12 <fowl> one day we'll be able to put evil people inside mirrors and throw them into space like superman 2
03:31:33 <oerjan> and then we'll all be arrested for galactic littering.
03:31:34 <elliott> `addquote <fowl> one day we'll be able to put evil people inside mirrors and throw them into space like superman 2
03:31:36 <HackEgo> 1187) <fowl> one day we'll be able to put evil people inside mirrors and throw them into space like superman 2
03:33:15 -!- Sorella has quit (Quit: It is tiem!).
03:33:34 -!- kwertii has joined.
03:39:57 <tertu> i think there are some things you can't technically get life imprisonment for, but if you do enough stuff it will add up to past the amount anybody would actually live. i think these things are mostly technicalities.
03:41:18 <Sprocklem> tertu: Colin Ferguson was a murderer. Surely you can get life for that
03:42:10 <tertu> 315 years and 8 months to life
03:42:13 <tertu> that doesn't make sense
03:43:40 <tertu> my attempt at interpreting this is that, if he lived for 315 years, 8 months and showed good behavior the whole time, he could get off then
03:43:48 <tertu> but if he didn't it'd become a life sentence
03:44:22 <fowl> thats pretty common in the states
03:44:29 <Bike> if he's later exonerated of something the entire sentence won't disappear. it's pretty common
03:44:38 <fowl> sentencing to 150+ years
03:44:53 -!- tromp has quit (Remote host closed the connection).
03:45:24 <tertu> okay Bike that makes sense as to why they even do this in the first place
03:45:25 -!- tromp has joined.
03:46:53 <pikhq> Also, life sentences might have possibility of parole, while those effectively don't.
03:47:22 <pikhq> (doesn't apply to federal sentencing: they have ended parole)
03:48:43 -!- atehwa has quit (Read error: Operation timed out).
03:48:50 -!- atehwa has joined.
03:49:43 -!- tromp has quit (Ping timeout: 252 seconds).
03:56:29 <oerjan> hm reddit's i18n has some strange gaps.
03:57:20 <oerjan> my comment dates are a mishmash of english and norwegian, somewhat varying with whether i've collapsed the thread.
03:58:41 <oerjan> i guess someone made a translation years ago which has not been updated when things changed.
03:59:32 <oerjan> denne posten ble lagt til på 24 Apr 2014
03:59:32 <oerjan> 11 poeng (100% liker det)
03:59:32 <oerjan> 11 upvotes 0 downvotes
04:00:14 <oerjan> two lines of english, two lines of norwegian.
04:00:28 <oerjan> (Well properly the Apr should have been lower-case.)
04:04:15 <oerjan> Ved bruk av denne siden aksepterer du vår User Agreement og Privacy Policy. © 2014 reddit inc. Alle rettigheter forbeholdt.
04:04:17 <oerjan> REDDIT and the ALIEN Logo are registered trademarks of reddit inc.
04:07:48 <oerjan> i looked at the Yesod internationalization page. i wonder if _anyone_ ever gets the russian number - noun case correspondence properly.
04:08:30 <oerjan> sorry, noun case and gender, i think
04:08:47 <oerjan> i think at least 1 is inflected for gender
04:09:26 <kmc> i'm told there's also a difference between noun and adjective forms of a number
04:10:10 <oerjan> well the "always translate phrases, not words" advice seems good.
04:10:52 <pikhq> Yeah, a gloss translation seems bad.
04:10:59 <oerjan> until you find a phrase that depends on even larger context for translation.
04:21:04 <lambdabot> (Profunctor p, Functor f1, Functor g, Functor f) => AnIso s t a b -> p (f a) (f1 (g b)) -> p (f s) (f1 (g t))
04:34:48 -!- kwertii has quit (Quit: kwertii).
04:52:48 -!- shikhin has quit (Ping timeout: 252 seconds).
05:12:35 -!- glogbackup has quit (Ping timeout: 252 seconds).
05:14:18 <HackEgo> instimecoin bffe7ecoin madrincoin nietcoin singycoin repartretimercoin reverycoin descends.jscoin nonnelcoin monwarwitzcoin unquecoin hencoin aeolcoin ztcoin acrabarinworcoin buyercoin polisercoin mertcoin mimsheall0coin quotecoin
05:16:02 -!- glogbackup has joined.
05:39:52 -!- FreeFull has quit.
05:50:05 -!- tertu has quit (Ping timeout: 264 seconds).
05:55:42 -!- nisstyre has joined.
05:55:47 -!- lambdabot has quit (Read error: Operation timed out).
05:56:01 -!- glogbackup has quit (Remote host closed the connection).
05:56:37 -!- trout has quit (Read error: Operation timed out).
05:59:58 -!- lambdabot has joined.
06:00:59 -!- glogbackup has quit (Ping timeout: 252 seconds).
06:05:58 -!- glogbackup has quit (Ping timeout: 240 seconds).
06:14:52 -!- Sprocklem has quit (Quit: leaving).
06:15:37 <HackEgo> засыcoin гидроcoin обстренкамилоcoin подкладъйствcoin распрятаcoin бельнойcoin состиротоэиcoin судовеcoin косознашеcoin вайерныхcoin
06:18:17 <fizzie> `run sed -e 's/coin/монета/' -e 's/--eng-1M --esolangs/--russian/' bin/coins | sh
06:18:18 <HackEgo> поквицкоммонета писатмонета халиномонета тыревоймонета вэньскиммонета присобследемонета опитанпаньмонета забушкарейзенноммонета антируюимонета двучнографичмонета льгахмонета пригу
06:19:59 -!- MoALTz has quit (Quit: Leaving).
06:28:17 -!- oerjan has quit (Quit: leaving).
06:45:20 -!- glogbackup has quit (Ping timeout: 252 seconds).
06:45:35 <Taneb> I'm finally unruining lens
06:48:04 -!- MindlessDrone has joined.
06:51:22 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:51:32 -!- variable has joined.
06:58:33 -!- glogbackup has quit (Ping timeout: 252 seconds).
07:05:46 <Sgeo> http://www.reddit.com/r/magicTCG/comments/23x4z8/one_turn_7_cards_no_infinite_combos_amount_of/
07:08:13 <Taneb> Magic is a ridiculous game
07:08:26 <Taneb> And a game I very much don't want to get into.
07:19:02 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
07:19:57 <augur_> ive discovered the right way to think about the SKI calculus
07:20:32 <Bike> my dad's a bigtime skiier.
07:20:36 <augur_> kmc: it involves categorical logic
07:26:28 -!- slereah_ has joined.
07:26:49 <Taneb> augur_, does it apply to BCKW calculus too?
07:27:08 <augur_> ive decided thats simplest
07:28:07 <Bike> bckw combinator calculus
07:28:53 <Taneb> slereah_, B = \x y z -> x (y z); C = \x y z -> x z y; W = \x y -> x y y
07:29:02 <kmc> hi slereah_
07:29:39 <Taneb> slereah_, I believe it predates SKI slightly and I find it simpler to write in
07:33:23 -!- glogbackup has quit (Ping timeout: 252 seconds).
07:34:13 <slereah_> I think those are the original letters yeah
07:34:18 <slereah_> In the article of what's his name
07:35:09 <Bike> "Schönfinkel developed a formal system that avoided the use of bound variables. His system was essentially equivalent to a combinatory logic based upon the combinators B, C, I, K, and S. Schönfinkel was able to show that the system could be reduced to just K and S and outlined a proof that a version of this system had the same power as predicate logic." hm hm.
07:36:04 <slereah_> The original article had the one combinator system
07:36:10 <slereah_> But he did say it was pretty pointless
07:36:37 <Bike> the bullshit combinator
07:38:09 -!- glogbackup has quit (Ping timeout: 265 seconds).
07:50:13 <coppro> are there any one-combinator systems?
07:50:58 <Bike> "or the runs-a-UTM combinator"
07:52:01 <coppro> I like that combinator
07:52:28 <coppro> oh, here was a fun one I thought of today: can we get a minor-closed class of graphs, membership in which is undecideable?
07:53:07 <coppro> read: can we design a language that's encoded in a graph so that any minor of a halting graph is also halting?
07:54:54 <slereah_> Plus you can do lambda calculus and such as graphs
07:55:01 <slereah_> The big one is the Kolmogorov machine
07:55:48 <coppro> you need labels though
07:58:18 <nortti> are there any analogues to regexps for languages higher in chomsky hierarchy?
07:58:42 <coppro> unrestricted grammars?
08:00:22 <nortti> well, there are the "regexps" wuth backreferences but those are just ugly and still pretty limited
08:01:12 <coppro> then all those things I named :)
08:02:27 <nortti> yeah, but I've yet to see a notation similar to regexps that I could use with them
08:02:51 <Taneb> What computational class are regexps with unbounded backrefs?
08:03:34 <Bike> i'm going to say CFGs for no rigorous reason
08:03:43 <Bike> nortti: "clearly you should try snobol"
08:04:26 * slereah_ gets a C++ library, discretely moves the public: line
08:04:27 <nortti> Taneb: I'm actually not sure. I know that regexp with backrefs can recognise the a^n b^n c^n style grammar which PDA cannot. however even with backrefs one cannot match a sexpr
08:05:15 <coppro> nortti: how does a regexp with backrefs recognise a^nb^nc^n?
08:05:54 -!- adu has quit (Quit: adu).
08:05:56 <coppro> Bike: They are definitely not CFGs. A CFG cannot match square words
08:06:14 <nortti> yeah, cannot recognise them
08:06:43 <coppro> but at the same time, there are CFGs that they cannot recognise, like matched parens
08:08:14 <FireFly> PCRE has the ability to match the language of matching parens IIRC
08:12:34 <augur_> mm kmc: not so much actually. its more that, the SKI combinators in a categorical setting are sufficient, but the translation isn't direct syntax, it's via composition as well. hmm
08:12:52 <augur_> oh well. ill figure out something to write. :p
08:20:08 <slereah_> The nice thing about SKI is that it doesn't need a terminating character
08:20:23 <slereah_> You can assume that all characters to the left are ` and all to the right are I
08:22:30 <ski> i assume you mean one can omit initial applications and final identities ?
08:33:45 -!- conehead has joined.
09:35:37 -!- conehead has quit (Quit: Computer has gone to sleep).
09:42:55 <Taneb> https://docs.python.org/2.7/library/mmap.html#mmap.flush look at them return values
10:21:48 -!- yorick has joined.
10:25:59 <ski> Happy Happy, Joy Joy
10:26:02 -!- idris-ircslave has quit (Quit: Terminated).
10:26:20 -!- idris-ircslave has joined.
10:26:34 <slereah_> If you ain't the grandaddy of all liars
10:26:53 <slereah_> Though my favorite Ren and Stimpy song remains the Stinky Weaselteat carol
10:35:08 <fizzie> Huh, first time I think I've seen a "P" in df -h output.
10:43:04 <Melvar> Cool. I haven’t even seen a T yet.
10:43:16 <fizzie> http://sprunge.us/LbjS
10:43:23 <fizzie> It's not my disk, of course.
11:23:59 <fizzie> I would think E; E is the standard SI prefix.
11:24:05 <fizzie> Don't know about LVM limitations.
11:24:14 <fizzie> There's still Z and Y beyond that.
11:24:47 <fizzie> "For 64-bit CPUs on 2.6 kernels, the maximum LV size is 8EB."
11:24:58 <fizzie> (Some outdated LVM faq.)
11:28:46 <Jafet> I should probably just do a raid6 instead of forgetting to make backups all the time
11:30:13 -!- nooodl has joined.
11:31:36 <fizzie> RAIDs are kind of less safe when it comes to "user error"-style mishaps.
11:32:00 <fizzie> "rm -rf * ~" and such.
11:32:18 <fizzie> (To remove temporary files ending in ~. Not that I've ever done that.)
11:32:54 <fizzie> Of course a fancy filesystem with snapshots would help.
11:33:04 <Jafet> lvm is pretty safe, as long as the idiot user doesn't get root
11:33:40 <Jafet> Also, the only problems I've had so far are disk failures.
11:34:41 <fizzie> I don't know, I've done "gcc -o file.c" accidentally once or twice.
11:35:25 <Jafet> git reset helps with that.
11:36:27 <Jafet> But yeah, why does gcc truncate the file first
11:36:41 <Jafet> Another fun typo is gcc file.c -o file.c
11:37:17 <fizzie> We have hourly, daily and weekly snapshots (going maybe two months back or so) of home directories in something like /home/.snapshots/... so that people can restore their own files without bothering the administrative folks.
11:38:30 <Jafet> Which snapshotting filesystem is that?
11:38:46 <fizzie> I don't really know, it's a SAN kind of thing.
11:38:57 <fizzie> Might be ZFS-based, I understand that's pretty enterprisey.
11:39:07 <fizzie> (It's exposed over NFS to users.)
11:40:19 <fizzie> Hrm. I went to the .snapshot dir of our "research disk" and did a ls, and it froze up.
11:40:26 <fizzie> That's perhaps not a good sign.
11:40:52 <Jafet> It might be merging diffs.
11:41:08 <Jafet> Well, not at the top-level
11:42:03 <Jafet> It might be nearline, depending on how enterprisey the san is
11:42:22 <fizzie> Well, I abbreviated a bit; there's a couple of different systems.
11:42:43 <fizzie> This research disk is from the university IT department.
11:43:03 <fizzie> The snapshotted homes were from a slightly more local, department-wide SAN from my previous department.
11:43:21 <fizzie> And they've had at least two iterations of it in the time I was there.
11:51:10 <myname> what do you think about a crossover of befunge and malbolge?
11:51:33 <myname> like, you can move over the same char later but it will do other stuff
11:51:49 -!- lambdabot has quit (Remote host closed the connection).
11:54:02 <fizzie> As long as it's not called "belange".
11:54:13 <fizzie> Or some other such name.
11:54:21 <fizzie> Malfunge, bebolge. Whatever.
11:55:25 <fizzie> I kind of like Befunge programs that use the same letters to do "other stuff" in the sense that it's executed e.g. both vertically and horizontally to do different things.
11:55:39 -!- lambdabot has joined.
11:57:38 <Jafet> http://esolangs.org/wiki/multiprogramming
12:08:09 -!- Sorella_ has joined.
12:08:42 -!- Sorella_ has changed nick to Sorella.
12:28:19 <Jafet> Apparently, Windows 8 has a weird made-up "Storage Spaces" thing, which they emphatically describe as not RAID.
12:29:58 <fizzie> "-- enables you to virtualize storage by grouping industry-standard disks into storage pools, and then create virtual disks called storage spaces from the available capacity in the storage pools."
12:30:02 <fizzie> More than a bit, even.
12:30:36 <fizzie> Just remap "industry-standard disks" -> physical volumes, "storage pools" -> volume groups and "storage spaces" -> logical volumes.
12:31:04 -!- Sgeo has quit (Read error: Connection reset by peer).
12:32:31 <Jafet> Does LVM also allow different RAID levels for each volume?
12:37:41 <fizzie> Yes, I think so, these days. It might not be quite as fancy.
12:43:17 <fizzie> "lvcreate --type raid5 -L 5G -i 3 -I 64 -n my_lv vg00" "Creates a 5GiB RAID10 logical volume "vg00/my_lv", with 2 stripes on 2 2-way mirrors." -- (man lvcreate)
12:43:40 <fizzie> Oh, I mismatched some lines.
12:44:00 <fizzie> That's a RAID5 LV, as you might have guessed from the --type argument.
12:47:34 -!- nooodl_ has joined.
12:49:10 -!- tromp has joined.
12:49:38 -!- kronion has joined.
12:49:51 -!- nooodl has quit (Disconnected by services).
12:49:52 -!- nooodl_ has changed nick to nooodl.
12:50:14 -!- tromp has quit (Remote host closed the connection).
12:55:12 -!- kronion has quit (Quit: Leaving.).
13:01:08 <HackEgo> [wiki] [[Special:Log/newusers]] create * CodingBat * New user account
13:24:43 <HackEgo> [wiki] [[@tention!]] http://esolangs.org/w/index.php?diff=39399&oldid=30317 * CodingBat * (+473)
13:24:49 -!- tertu has joined.
13:31:01 -!- drdanmaku has joined.
13:35:05 -!- tertu has quit (Ping timeout: 252 seconds).
13:45:07 -!- Taneb has changed nick to hk3379.
13:48:30 -!- Tritonio has joined.
13:49:47 -!- hk3379 has changed nick to Taneb.
13:55:58 -!- nucular has joined.
13:55:58 -!- nucular has quit (Changing host).
13:55:58 -!- nucular has joined.
13:57:35 -!- CodingBat has joined.
13:58:39 -!- CodingBat has left.
14:02:48 -!- tertu has joined.
14:19:38 -!- Sprocklem has joined.
14:27:08 -!- Vamadeus has joined.
14:27:08 -!- Vamadeus has quit (Changing host).
14:27:08 -!- Vamadeus has joined.
14:43:18 -!- tertu has quit (Ping timeout: 240 seconds).
14:44:11 -!- Sprocklem has quit (Quit: leaving).
14:46:04 -!- Sprocklem has joined.
15:01:26 <Jafet> "1 x PCIe 3.0 x16 Slot, Supports AMD Quad CrossFireX, CrossFireX"
15:03:03 -!- impomatic has joined.
15:10:58 -!- Sprocklem has quit (Quit: brb).
15:11:58 -!- Patashu_ has quit (Ping timeout: 240 seconds).
15:12:38 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:13:11 -!- Sprocklem has joined.
15:15:38 -!- mhi^ has joined.
15:18:24 <mhi^> Hey, Sprocklem. ;)
15:21:01 <nortti> my plan of luring all of #osdev-offtopic here seems to be working :P
15:22:12 <Sprocklem> nortti: Does shikhin frequent here?
15:32:49 -!- Tritonio has quit (Ping timeout: 240 seconds).
15:35:05 <fizzie> nortti: You didn't feel there was enough off-topic discussion as it is?
15:36:51 <nortti> ðere can never be too much offtopic discussion!
15:37:39 <Sprocklem> (For the record I was here before today)
15:38:51 -!- yorick has quit (Remote host closed the connection).
15:39:17 <HackEgo> U+00F0 LATIN SMALL LETTER ETH \ UTF-8: c3 b0 UTF-16BE: 00f0 Decimal: ð \ ð (Ð) \ Uppercase: U+00D0 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right)
15:40:13 <Melvar> Not to be confused with đ.
15:40:24 <HackEgo> U+0111 LATIN SMALL LETTER D WITH STROKE \ UTF-8: c4 91 UTF-16BE: 0111 Decimal: đ \ đ (Đ) \ Uppercase: U+0110 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right)
15:41:20 <nortti> what is the last char in that?
15:41:34 <HackEgo> U+2F79 KANGXI RADICAL NET \ UTF-8: e2 bd b9 UTF-16BE: 2f79 Decimal: ⽹ \ ⽹ \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ Decomposition: <compat> 7F51
15:41:47 <HackEgo> U+00D0 LATIN CAPITAL LETTER ETH \ UTF-8: c3 90 UTF-16BE: 00d0 Decimal: Ð \ Ð (ð) \ Lowercase: U+00F0 \ Category: Lu (Letter, Uppercase) \ Bidi: L (Left-to-Right) \ \ U+0110 LATIN CAPITAL LETTER D WITH STROKE \ UTF-8: c4 90 UTF-16BE: 0110 Decimal: Đ \ Đ (đ) \ Lowercase: U+0111 \ Category: Lu (Letter, Uppercase) \ Bidi: L (Left-to-
15:42:14 <Jafet> `run unicode ÐĐƉ | fgrep U+
15:42:15 <HackEgo> U+00D0 LATIN CAPITAL LETTER ETH \ Lowercase: U+00F0 \ U+0110 LATIN CAPITAL LETTER D WITH STROKE \ Lowercase: U+0111 \ U+0189 LATIN CAPITAL LETTER AFRICAN D \ Lowercase: U+0256
15:42:39 <Jafet> `run unicode ðр⽹ | grep -E '^U\+'
15:42:40 <HackEgo> U+00F0 LATIN SMALL LETTER ETH \ U+0440 CYRILLIC SMALL LETTER ER \ U+2F79 KANGXI RADICAL NET
15:43:12 <nortti> "It is also used as the letter symbol for the internet cryptocurrency, Dogecoin." https://en.wikipedia.org/wiki/%C4%90
15:45:16 -!- AnotherTest has joined.
15:54:33 <fizzie> http://sprunge.us/dSXL (possible) victory!
15:55:12 <fizzie> Also there is still `unidecode, you don't need to play around with unicode + grep.
15:57:12 <Jafet> Did you beat the poor caged-up drive into submission
16:03:38 -!- Vamadeus has quit (Ping timeout: 240 seconds).
16:04:32 -!- Phantom_Hoover has joined.
16:05:06 -!- slereah_ has quit (Quit: Leaving).
16:11:12 <fizzie> I just put it in a different box.
16:12:18 <fizzie> Somewhat curiously, in my non-boxlike USB dock thing the same drive says "732566646 4096-byte logical blocks" rather than the "5860533168 512-byte logical blocks" + "4096-byte physical blocks" thing it does in this box.
16:17:20 -!- MoALTz has joined.
17:01:21 <HackEgo> [wiki] [[Special:Log/newusers]] create * Creeparoo * New user account
17:17:34 -!- Vamadeus has joined.
17:17:34 -!- Vamadeus has quit (Changing host).
17:17:34 -!- Vamadeus has joined.
17:29:09 <kmc> good morning
17:32:28 <HackEgo> [wiki] [[@tention!]] http://esolangs.org/w/index.php?diff=39400&oldid=39399 * Oerjan * (+0) Why would you change that?
17:35:49 -!- Sprocklem has quit (Ping timeout: 252 seconds).
17:38:55 <kmc> `run cat $(which unicode)
17:38:55 <HackEgo> #!/usr/bin/python \ \ \ import os, glob, sys, unicodedata, locale, gzip, re, traceback, encodings \ import urllib, webbrowser, textwrap \ \ # bz2 was introduced in 2.3, we want this to work also with earlier versions \ try: \ import bz2 \ except ImportError: \ bz2 = None \ \ # for python3 \ try: \ unicode \ except NameError: \
17:39:10 <kmc> `run wc -l $(which unicode)
17:39:58 <Jafet> `cat /bin/unicode.old
17:39:59 <fizzie> It's https://packages.debian.org/search?keywords=unicode nowadays.
17:39:59 <HackEgo> cat: /bin/unicode.old: No such file or directory
17:40:21 <Jafet> `run cat /bin/unicode.*
17:40:21 <HackEgo> cat: /bin/unicode.*: No such file or directory
17:40:40 <fizzie> You don't want a /bin/, you want a bin/.
17:40:50 <Jafet> `run cat bin/unicode.*
17:40:50 <HackEgo> #!/usr/bin/env python \ # -*- encoding: utf-8 -*- \ import re \ import sys \ import unicodedata \ def l(c): m = re.match('(?:U[+])?([0-9a-f]{1,5})$', c, re.I); return unicodedata.lookup(c) if m is None else unichr(int(m.group(1),16)) \ try: \ print u''.join(map(l, sys.argv[1:])).encode('utf-8') \ except KeyError: \ print u'Unknown charac
17:41:03 <fizzie> `run wc -l bin/unicode.old
17:41:57 <HackEgo> U+1DC2 COMBINING SNAKE BELOW \ UTF-8: e1 b7 82 UTF-16BE: 1dc2 Decimal: ᷂ \ ᷂ \ Category: Mn (Mark, Non-Spacing) \ Bidi: NSM (Non-Spacing Mark) \ Combining: 220 (Below) \ \ U+2E92 CJK RADICAL SNAKE \ UTF-8: e2 ba 92 UTF-16BE: 2e92 Decimal: ⺒ \ ⺒ \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F40D SNAKE \ UT
17:43:17 <fizzie> I appreciate Unicode 6.x support as much as the next guy, but I have to admit I liked the old scripts more.
17:43:20 <fizzie> These are just so verbose.
17:43:42 <fizzie> Also so many features.
17:43:45 <HackEgo> [wiki] [[Poop]] N http://esolangs.org/w/index.php?oldid=39401 * Creeparoo * (+1236) Created page with "Poop is an esoteric programming language made by Eike Tim Jesinghaus in april 2014. Poop is unusable for programming, because it's just a joke/fun language. Poop has one empty..."
17:44:33 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39402&oldid=39401 * Creeparoo * (+0)
17:45:58 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39403&oldid=39402 * Creeparoo * (+1)
17:46:08 <Jafet> It's a... turning cesspit
17:46:44 <myname> someone told me about a language where the instruction pointer was water/liquid, anybody knows which language this could be?
17:47:09 -!- edwardk has joined.
17:47:10 -!- idris-ircslave has quit (Quit: Terminated).
17:47:15 <Jafet> `run tail -n 3 bin/unicode.old
17:47:15 <HackEgo> print u''.join(map(l, sys.argv[1:])).encode('utf-8') \ except KeyError: \ print u'Unknown character.'
17:47:26 -!- idris-ircslave has joined.
17:48:33 <kmc> the loneliest number
17:49:02 <Slereah> Zero is the loneliest number
17:49:55 -!- FreeFull has joined.
17:52:01 -!- idris-ircslave has quit (Client Quit).
17:52:18 -!- idris-ircslave has joined.
17:53:19 <idris-ircslave> (input):1:1:When elaborating an application of constructor __infer:
17:53:30 <idris-ircslave> (input):1:1:When elaborating an application of constructor __infer:
17:55:34 <Melvar> I made a conffile saying in #esoteric its prefix is only ( , and coded so far that it should obey that, but evidently something is still wrong.
17:56:17 <Jafet> `run mv bin/{un,mult}icode && (head -n -1 bin/unicode.old | sed 's/import sys/import sys, os/'; echo ' os.execvp("multicode", sys.argv[1:])') > bin/unicode && rm bin/unicode.old
17:56:25 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/unicode: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/unicode: cannot execute: Permission denied
17:56:33 <Jafet> `run chmod +x bin/unicode
17:58:27 <Jafet> Wait, remind me why I replaced bin/unicode
17:59:18 <fizzie> Because the old one used Python's built-in Unicode database, which was stuck with Unicode 5.2.
17:59:35 <fizzie> At least that's what I assumed.
18:00:06 <lambdabot> <hint>:1:1: parse error on input ‘:’
18:00:17 -!- variable has quit (Quit: I found 1 in /dev/zero).
18:00:54 <Jafet> `rm bin/UnicodeData.txt
18:01:25 <HackEgo> [U+1F000 MAHJONG TILE EAST WIND]
18:01:45 -!- conehead has joined.
18:02:29 -!- idris-ircslave has quit (Quit: Terminated).
18:02:52 -!- idris-ircslave has joined.
18:02:54 -!- idris-ircslave has quit (Client Quit).
18:04:49 <fizzie> I'd appreciate if this new `unicode did character names correctly.
18:04:53 <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
18:05:27 <Jafet> `run sed -i 's/"multicode", /"multicode", ["multicode"] +/' bin/unicode
18:05:47 <Jafet> `unicode BUNNY WOMAN
18:06:13 <Jafet> `unicode WOMAN WITH BUNNY
18:06:14 <HackEgo> U+1F46F WOMAN WITH BUNNY EARS \ UTF-8: f0 9f 91 af UTF-16BE: d83ddc6f Decimal: 👯 \ 👯 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
18:06:40 <fizzie> Oh, so it's a fallback thing now, I missed that entirely.
18:06:48 <fizzie> Well, that's reasonable.
18:07:32 -!- idris-ircslave has joined.
18:07:39 <Jafet> `run multicode DUNNO # just checking
18:08:05 <lambdabot> No instance for (Data.Typeable.Internal.Typeable b0)
18:08:05 <lambdabot> arising from a use of ‘M57523064348926377873909.show_M57523064348926377873...
18:08:05 <lambdabot> The type variable ‘b0’ is ambiguous
18:08:05 <lambdabot> Note: there are several potential instances:
18:08:05 <lambdabot> instance Data.Typeable.Internal.Typeable Data.Aeson.Lens.Primitive
18:08:28 <Melvar> Looks like it’s working now.
18:08:36 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:08:54 -!- variable has joined.
18:10:01 <Melvar> Good news everyone! You can use > for lambdabot again!
18:10:54 <Jafet> I guess we can scrap the five-year soviet reeducation program, then.
18:11:35 <kmc> the first step is to learn to spell it reëducation
18:11:42 -!- variable has quit (Max SendQ exceeded).
18:12:50 <Melvar> Does anyone want to guess what the problem fifteen minutes ago was?
18:13:11 <nortti> (I hope this does not get interpreted
18:13:45 <Melvar> idris-ircslave: ( "calling"
18:14:35 <Melvar> It now also strips its nick before any further interpretation, rather than using “idris-ircslave: ” as a prefix.
18:16:23 <Melvar> nortti: The prefix includes the space.
18:17:14 <Jafet> `run (sed -e 's/import sys/import os, sys/' -e 's/^print \(.*\)$/s = \1/' bin/unidecode; echo $'if u"DUNNO" in s:\n os.execvp("multicode", ["multicode"] + sys.argv[1:])\nelse:\n print s') > /tmp/a && mv /tmp/a bin/unidecode
18:17:21 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/unidecode: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/unidecode: cannot execute: Permission denied
18:17:32 <Jafet> `run chmod +x bin/unidecode
18:17:36 <HackEgo> U+1F46F WOMAN WITH BUNNY EARS \ UTF-8: f0 9f 91 af UTF-16BE: d83ddc6f Decimal: 👯 \ 👯 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
18:18:19 <Jafet> (Yes, they both fall back to the same program)
18:22:13 <fizzie> The unidecode fallback should perhaps be multicode -s explicitly.
18:22:39 <fizzie> (I'm sure people will often need to `unidecode 1234 or some-such, yes.)
18:22:57 -!- pdxleif has joined.
18:23:46 <HackEgo> [U+0031 DIGIT ONE] [U+0032 DIGIT TWO] [U+0033 DIGIT THREE] [U+0034 DIGIT FOUR]
18:23:55 -!- variable has joined.
18:27:34 <fizzie> Well, okay, I guess that doesn't involve a fallback.
18:54:38 -!- mhi^ has quit (Quit: Lost terminal).
18:56:50 -!- mhi^ has joined.
19:21:26 -!- Vamadeus has quit (Remote host closed the connection).
19:43:55 <Bike> "So. It’s World Penguin Day & DNA Day… AND World Malaria Day & Ed Balls Day." kmc you know what to do
19:44:27 <kmc> is it really ed balls day already?
19:45:02 <kmc> seems like last ed balls day was just recently
19:45:08 <kmc> oh it's Monday
19:56:19 -!- Frooxius has joined.
19:59:05 -!- Frooxius has quit (Read error: Connection reset by peer).
19:59:40 -!- Frooxius has joined.
21:00:23 -!- idris-ircslave has quit (Quit: Terminated).
21:00:36 -!- idris-ircslave has joined.
21:01:27 -!- sebbu has quit (Ping timeout: 265 seconds).
21:01:38 -!- idris-ircslave has quit (Client Quit).
21:06:10 -!- idris-ircslave has joined.
21:19:17 -!- edwardk has quit (Ping timeout: 252 seconds).
21:25:24 -!- yorick has joined.
21:32:31 -!- idris-ircslave has quit (Quit: Terminated).
21:32:45 -!- idris-ircslave has joined.
21:32:49 -!- nucular has quit (Quit: Excess Food).
21:33:34 -!- AnotherTest has quit (Ping timeout: 276 seconds).
21:40:25 -!- MoALTz has quit (Quit: Leaving).
21:46:49 -!- Slereah has quit (Ping timeout: 240 seconds).
21:53:13 -!- shachaf has quit (Ping timeout: 240 seconds).
21:53:59 -!- shachaf has joined.
21:56:21 <HackEgo> [wiki] [[Special:Log/newusers]] create * AJMasfield * New user account
21:58:04 <HackEgo> 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ Wierd \ wisdom \ wisdom.pdf
21:58:18 -!- sebbu has joined.
21:58:25 <Taneb> `run echo < hello.c
21:58:32 <HackEgo> const char main[] = "AXAYAZA[A\\ATX-pppp-0```- ///P^VTXH10XP4>40PZ414>P_\x0f\x05XATASARAQAP\xc3Hello, world!\n";
21:58:48 -!- sebbu has quit (Changing host).
21:58:48 -!- sebbu has joined.
21:59:36 -!- Slereah_ has joined.
22:07:18 -!- Slereah_ has quit (Remote host closed the connection).
22:08:07 -!- edwardk has joined.
22:08:43 -!- oklopol has quit (Quit: Leaving).
22:10:38 -!- mhi^ has quit (Quit: Lost terminal).
22:21:26 <HackEgo> [wiki] [[Trainscript]] N http://esolangs.org/w/index.php?oldid=39404 * AJMasfield * (+418) Created page with "'''Trainscript''' is an estoreic programing language currently under development. All data in trainscript is represented as train locomotives pulling a cargo of 1's and 0's, ..."
22:26:36 -!- Slereah_ has joined.
22:38:07 -!- Slereah_ has quit (Ping timeout: 265 seconds).
22:42:31 -!- oerjan has joined.
22:47:28 -!- Slereah_ has joined.
22:49:09 <oerjan> <Taneb> I'm finally unruining lens <-- wait why didn't i open that thread
22:49:26 <oerjan> must have clicked only the blog link
22:50:34 <oerjan> or maybe it's another browser tab bug
22:52:10 <ion> What thread?
22:52:19 <ion> What blog?
22:52:51 <oerjan> http://www.reddit.com/r/haskell/comments/23uzpg/lens_is_unidiomatic_haskell/?limit=500
22:53:29 <oerjan> in that thread Taneb admits to his sins. i know this because that comment showed up in my friends list
22:54:04 <Taneb> oerjan, today I pushed 217 lines of documentation into lens
22:54:27 <ion> oerjan: Thanks
22:54:33 <ion> taneb: Nice, thanks for your contribution. :-)
22:54:35 <oerjan> but i haven't yet got to the part of the thread that gives context enough to tell _what_ he's not documented before.
22:54:55 <edwardk> Say 10 Hail Marys and make 3 more lens commits and your sins shall be forgiven.
22:55:00 <Bike> whoa, whoa, comments? what is this, ruby
22:55:05 <Bike> documentation??
22:55:25 <oerjan> edwardk: you're highlighting "lens" right
22:55:33 -!- boily has joined.
22:55:37 <Taneb> edwardk, I managed to not learn the Hail Mary in all four years I spent at a catholic middle school
22:55:41 <Taneb> My greatest pride.
22:56:01 * oerjan doesn't know hail mary, being nominally protestant
22:56:19 <oerjan> although i guess might be the same as that ave maria they sing at christmas?
22:56:39 <Taneb> It mentions fruit of thine womb or something
22:56:55 <oerjan> i remember that fructus part yeah
22:57:18 -!- Slereah_ has quit (Ping timeout: 240 seconds).
22:58:23 <elliott> oerjan: that thread is like an exact repeat of ones seen a year+ ago
22:59:49 <oerjan> `addquote <oerjan> in that thread Taneb admits to his sins. i know this because that comment showed up in my friends list <Taneb> oerjan, today I pushed 217 lines of documentation into lens [...] <edwardk> Say 10 Hail Marys and make 3 more lens commits and your sins shall be forgiven.
22:59:51 <HackEgo> 1188) <oerjan> in that thread Taneb admits to his sins. i know this because that comment showed up in my friends list <Taneb> oerjan, today I pushed 217 lines of documentation into lens [...] <edwardk> Say 10 Hail Marys and make 3 more lens commits and your sins shall be forgiven.
23:01:57 <oerjan> i suppose it might not be entirely clear that all those lines are actually related
23:02:13 <oerjan> elliott: well the next time it will be BETTER DOCUMENTED hth
23:02:32 <elliott> next time I will hopefully not click the link :P
23:02:49 <oerjan> oh i assumed you'd already read it
23:02:58 <oerjan> but i guess you are avoiding reddit
23:04:10 <elliott> well /r/haskell was like the last subreddit I quit reading.
23:05:24 -!- tromp has joined.
23:06:22 -!- Slereah_ has joined.
23:06:37 <oerjan> i seem to be slowly dropping subreddits too, although mainly because i read them in an order and no longer get very much around to the largest ones
23:07:15 <oerjan> well the order is approximately smaller to larger
23:07:35 <Bike> where's /r/TsundereSharks in the lineup
23:07:38 <oerjan> and /r/haskell is the second smallest one
23:07:52 <oerjan> Bike: i'm sorry that's not included
23:08:21 <oerjan> i used to have /r/science but i never got around to it so just removed it
23:08:51 <oerjan> and it's rare that i get up to /r/programming
23:09:29 <oerjan> the approximate is because i tend to read /r/physics before /r/math, even though they keep switching places.
23:12:05 <edwardk> Taneb: I also went to a Catholic grade school. It made me the atheist I am today. ;)
23:12:12 -!- Slereah_ has quit (Read error: Connection reset by peer).
23:13:02 <Taneb> edwardk, I started calling myself "atheist" rather than "probably atheist" last week
23:13:11 <Taneb> Although I am still on good terms with my local priest
23:14:17 <edwardk> The only thing I find myself compelled to do for an hour on Sundays these days is watch Cosmos. ;)
23:15:26 -!- Slereah_ has joined.
23:17:48 -!- nisstyre has joined.
23:18:38 <oerjan> edwardk: noticing the first subthread of that thread i am wondering: since it is iirc possible to get TH to output the resulting haskell file, shouldn't it be possible to make hackage include pre-processed versions that stage 1 architectures can use?
23:19:13 <edwardk> oerjan: it'll output a text dump of what its splicing 'approximately'
23:19:15 <elliott> joeyh has some tool along those lines
23:19:43 -!- Slereah has joined.
23:19:44 -!- Slereah_ has quit (Ping timeout: 252 seconds).
23:19:54 <edwardk> elliott: gave up on #haskell-lens?
23:20:31 <edwardk> anyways. hand hacking up the TH it generates would be fine
23:20:38 <elliott> edwardk: eh :) maybe I'll be back someday but I haven't written much Haskell in a while
23:20:41 <elliott> edwardk: https://joeyh.name/blog/entry/Template_Haskell_on_impossible_architectures/
23:20:52 <elliott> that post/code might have useful leads
23:20:55 <oerjan> yeah but it would be nice if there were an automated process that generally worked
23:21:18 <Bike> "Imagine you had an excellent successful Kickstarter campaign," lost my suspension of disbelief
23:21:33 <oerjan> although i guess in general TH can do OS-specific things that affects its output
23:23:13 <edwardk> anyways the code in lens should be pretty much easily translatable
23:24:01 <oerjan> edwardk: i'm rather thinking about what it would take to make people able to use cabal install normally and have it work that way
23:24:03 <edwardk> it is mostly the IOErrorType Prisms in http://hackage.haskell.org/package/lens-4.1.2/docs/System-IO-Error-Lens.html that vary
23:24:25 <edwardk> having a makeLenses preprocessor or some such?
23:24:39 -!- adu has joined.
23:25:03 <elliott> I'm still holding out for -XLens
23:25:21 <edwardk> well, with the ORF going in in 7.10 you'll be able to reduce the need for makeLenses a bit
23:25:39 <edwardk> makeClassy is still useful though
23:26:12 <oerjan> i'm not actually talking specifically about lens, though.
23:26:54 <edwardk> the main headache would be figuring out what to splice and how
23:27:07 <edwardk> something like that EvilSplicer could probably be modified to work in general thoug
23:27:38 <edwardk> given a 'shadow' -ddump-splices output file that it could read to replace splices or run without the splicer / in generation mode with different flags
23:28:16 <edwardk> so you could rebuild them with a flag, commit them, and when building on stage1 take the splices
23:31:19 -!- adu has quit (Quit: adu).
23:31:54 <oerjan> i guess that joeyh link explains why this is harder than i thought :(
23:32:00 <elliott> how about making TH cross-compilation work?
23:35:31 -!- Sgeo has joined.
23:36:29 <oerjan> "(My longest GHC error message seen on this odyessy was actually a full 500+ kilobytes in size. It included the complete text of Jquery and Bootstrap. At times like these you notice that GHC outputs its error messages o.n.e . c.h.a.r.a.c.t.e.r . a.t . a . t.i.m.e.)"
23:37:38 <oerjan> elliott: is the first comment on that post relevant to that?
23:39:07 <elliott> I would guess not but I'm not sure.
23:40:31 <Bike> huh, jquery's bigger than i thought
23:40:37 <Bike> still less than a tenth of 500 kb
23:41:41 -!- yorick has quit (Remote host closed the connection).
23:49:01 <oerjan> is the term "optic" official lens nomenclature?
23:49:25 <elliott> can lens rebrand as optics yet?
23:49:32 <edwardk> it is better than 'lenslikes'
23:49:57 * oerjan considers 'edwardk highlights on "lens"' confirmed
23:50:15 <HackEgo> fun fact 0 = 1 | fact n = n * fact (n - 1)
23:52:38 <edwardk> oerjan: that last one was me flipping between channels i was talking on =)
23:52:45 <edwardk> but i do sometimes highlight on lens
23:54:59 -!- Patashu has joined.
23:55:45 <oerjan> oh they are the profunctor-generalized version of lenslike
23:58:41 -!- Patashu_ has joined.
23:58:41 -!- Patashu has quit (Disconnected by services).
23:59:07 -!- edwardk has quit (Quit: Computer has gone to sleep.).
23:59:31 <oerjan> i don't think the Apply/Traversal1/Fold1 stuff was there last i looked...
23:59:53 <oerjan> but it's using the lack of pure to ensure there has to be at least one item, i take
00:01:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
00:02:42 <Sgeo> I think I can implement van Laarhoven lenses in a dynamically typed language without difficultly faking typeclasses, but not sure about other van Laarhoven optics
00:03:20 <Sgeo> Instead of f a, could just give a function that's effectively flip fmap
00:03:49 <Sgeo> There's not much else you can do with an unknown Functor
00:03:59 <kmc> tomb of the unknown functor
00:07:02 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
00:10:57 <Taneb> One of my friends is playing a 1080p movie via sshfs to a server in France
00:12:02 <ion> I have pretty much moved from streaming with sshfs to transfering with git-annex.
00:13:10 <Sgeo> Traversals need traversable, which needs foldable and functor... I don't think I can represent opaque traversables as literally one function
00:15:43 <Sgeo> Hold on, there are default definitions for the Functor and Foldable part... but would I ever need to pass in a functor or foldable that's not a traversable
00:18:04 <oerjan> Sgeo: um lens traversals are analogous to traversables, not based on them...
00:18:33 <oerjan> you get them by switching Functor with Applicative in the lens version
00:18:52 <Sgeo> ...Applicative may be a bit problematic
00:19:43 <Sgeo> Or... ok, not thinking about this fully at the moment
00:21:13 <oerjan> although perhaps you _can_ do it with traversables, in some "dual" representation
00:22:05 * oerjan wonders what a Lensable would look like
00:22:43 <oerjan> the thing that would be a typeclass corresponding to lenses and Functor in the same way Traversable corresponds to traversals and Applicative
00:23:07 <oerjan> and Functor corresponds to getters and ...um, something?
00:24:01 <Taneb> oerjan, Getter needs (Functor f, Contravariant f)
00:25:41 <oerjan> Getter might correspond to Pointed as a class, maybe
00:29:25 <oerjan> oh right because Const r is the "only" thing that is both.
00:29:26 -!- boily has quit (Read error: Connection reset by peer).
00:30:08 -!- boily has joined.
00:30:30 <oerjan> wait what is Copointed
00:32:20 <oerjan> Foldable corresponds to folds and something
00:32:49 <elliott> Foldable is Functor + Monoid a => f a -> a
00:33:57 <oerjan> that's not the part i'm interested in
00:35:09 <oerjan> hm Contravariant and Applicative
00:35:20 * oerjan thinks his brain is running out of steam again
00:35:42 <oerjan> also i didn't finish the logs
00:37:28 <Taneb> oerjan, Copointed is f a -> a
00:38:02 <oerjan> <augur_> kmc: it involves categorical logic <-- have you reinvented cartesian closed categories
00:38:36 <Taneb> I think it's Traversable : Traversal :: Copointed : Getter
00:39:03 <Taneb> Every Copointed is trivially Foldable
00:39:07 <oerjan> yeah sounds reasonable
00:40:52 <shachaf> Functor+Contravariant means phantom
00:41:08 <shachaf> You could make class Phantom f where coerce :: f a -> f b (we used to have that)
00:41:31 <shachaf> Const r or something isomorphic to it, sure.
00:41:54 <oerjan> ok Setter uses a complicated brew of contexts that enforce the functor being Identity.
00:41:57 <shachaf> Anyway, we just use Functor+Contravariant to express that using non-lens classes.
00:48:52 <oerjan> i think taintedDot is named for what it does to people who come by it unwarily.
00:51:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:54:37 <oerjan> <coppro> oh, here was a fun one I thought of today: can we get a minor-closed class of graphs, membership in which is undecideable? <-- no. https://en.wikipedia.org/wiki/Robertson%E2%80%93Seymour_theorem
00:56:22 <shachaf> taintedDot is still a thing?
00:57:25 <oerjan> i'm wondering why they're bothering with all that machinery for something that's supposed to be Identity
00:58:10 <shachaf> the trouble is that newtype Id a = Id { runId :: a }, (Id x) is operationally the same as x
00:58:30 <shachaf> and Id is operationally the same as, uh, id
00:58:49 <shachaf> but (Id . f) is operationally the same as (\x -> Id (f x)) = (\x -> id (f x)) = (\x -> f x)
00:58:58 <shachaf> which isn't the same as f (when f is _|_)
01:00:13 <oerjan> ok that explains the seqs i guess but not why they bother to list all the superclasses
01:00:59 <oerjan> and even to _use_ them in the implementation
01:01:39 <shachaf> have a look at a thing called Conjoined
01:02:28 <shachaf> are you talking about the default implementations?
01:02:54 <shachaf> those can't use unsafeCoerce because maybe the user will give a type that isn't Id and then you can derive a real unsafeCoerce from the default instance
01:06:05 <oerjan> oh wait it's actually just Applicative which is used
01:06:16 -!- edwardk has joined.
01:08:37 <Sgeo> If a Functor is a function that takes one argument, an Applicative could be a function that takes several arguments. Except I lose pure
01:09:08 <Sgeo> (And currently guessing as to whether that several arguments thing would work, but it makes a kind of intuitive sense)
01:10:25 <Sgeo> Harder to have one that you add to later though
01:12:20 <oerjan> augur_: oh wait ski not lambda calculus
01:13:26 <oerjan> Sgeo: maybe you can make that Traversal1 thing i found just earlier
01:13:59 <Sgeo> AFK, I'll look when I get back
01:34:37 -!- Slereah_ has joined.
01:38:43 -!- Slereah has quit (Ping timeout: 252 seconds).
01:49:01 -!- adu has joined.
01:53:35 -!- nooodl has quit (Quit: Ik ga weg).
02:02:54 -!- oerjan has set topic: The channel with the > bot | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
02:05:52 -!- boily has quit (Quit: WeeChat 0.4.2).
02:09:17 <oerjan> <Bike> "So. It’s World Penguin Day & DNA Day… AND World Malaria Day & Ed Balls Day." kmc you know what to do <-- ok kmc how is your penguin/mosquito chimæra going?
02:10:38 -!- rodgort has quit (Quit: ERC Version 5.3 (IRC client for Emacs)).
02:13:16 <Sgeo> We got idris-ircslave to stop using > ?
02:15:09 -!- rodgort has joined.
02:15:13 -!- zzo38 has joined.
02:15:34 <zzo38> Has anyone written a roguelike game in SQL before?
02:15:58 -!- rodgort has quit (Remote host closed the connection).
02:19:08 -!- rodgort has joined.
02:19:21 -!- adu has quit (Quit: adu).
02:20:44 -!- rodgort has quit (Remote host closed the connection).
02:23:13 <Sgeo> Where's that thing explaining how to make a lens from scratch?
02:23:46 <edwardk> http://ftp.newartisans.com/pub/Lenses.mp4 is simon's talk
02:23:55 <Sgeo> Was hoping for a page
02:24:00 <edwardk> mth.io/talks/lens-from-the-ground-up/ is mark hibberd's talk
02:24:29 <edwardk> https://github.com/ekmett/lens/wiki/Derivation is my original page in the wiki starting from motivation to theory
02:25:55 <edwardk> zzo38: that sounds terrible. go for it ;)
02:26:16 -!- rodgort has joined.
02:26:31 <Sgeo> Functor f => (b -> f b) -> a -> f a
02:26:40 <Sgeo> I'm thinking that I could have something like
02:27:55 <lambdabot> Functor f => f a -> (a -> b) -> f b
02:29:15 <coppro> oerjan: yeah, I realized in retrospect it was a dumb question
02:29:58 <coppro> I meant to ask the slightly more interesting question "is it possible that there's a minor-closed graphs for which we are unable (in the sense of independence) to find the forbidden minors?
02:30:29 <oerjan> i'd expect that to be true
02:31:13 <Sgeo> The only way to construct that f a that the lens must output is to use fmap with the result of (b -> f b), right?
02:31:14 <zzo38> edwardk: Are you sure it is terrible?
02:31:34 <edwardk> sgeo: the problem with that form is it doesn't compose as well
02:31:47 <coppro> oerjan: but we can enumerate all of the possible sets of forbidden minors
02:32:33 <oerjan> coppro: yes, but we cannot check whether any particular of those sets gives the original set of graphs, i think
02:32:33 <Sgeo> Are there likely to be significant limitations if I keep not going the van Laarhoven route in a dynamically typed language?
02:32:46 <Sgeo> My code is so verbose :/
02:33:02 <Sgeo> Also, it would be fun to show it could be done
02:33:21 <Bike> > map (zip [1, 2, 3]) $ [4, 5, 6]
02:33:23 <lambdabot> No instance for (GHC.Show.Show b0)
02:33:23 <lambdabot> arising from a use of ‘M245150698743640559410341.show_M2451506987436405594...
02:33:23 <lambdabot> The type variable ‘b0’ is ambiguous
02:33:23 <lambdabot> Note: there are several potential instances:
02:33:56 <Taneb> > map (zip [1,2,3]) $ [[4,5,6]]
02:34:06 <elliott> Bike: zip [1, 2, 3] 4 doesn't make much sense
02:34:07 <Sgeo> > map (zip [1, 2, 3 :: Int]) $ [4,5,6]
02:34:08 <lambdabot> No instance for (GHC.Show.Show b0)
02:34:08 <lambdabot> arising from a use of ‘M814034439476907821810375.show_M8140344394769078218...
02:34:08 <lambdabot> The type variable ‘b0’ is ambiguous
02:34:08 <lambdabot> Note: there are several potential instances:
02:34:18 <oerjan> coppro: although this is really about _descriptions_ of sets of graphs, not sets of graphs themselves
02:34:22 <elliott> > map (zip [1,2,3]) [4::Int,5,6]
02:34:24 <lambdabot> Couldn't match expected type ‘[b]’ with actual type ‘GHC.Types.Int’
02:35:01 <Sgeo> ... were you able to determine beforehand without GHCi or similar that that would be a clearer error message somehow?
02:35:10 <oerjan> coppro: oh wait am i thinking about this wrongly
02:35:47 <coppro> oerjan: I don't think so. We can describe any minor-closed set of graphs by its forbidden minors
02:36:03 <oerjan> (that wasn't a response)
02:36:21 <coppro> So the question is "is there some way to describe a minor-closed set of graphs in such a way that we are unable to associate them with a description of that set by its forbidden minors."
02:40:12 <oerjan> seems like you just need to encode a gödel sentence or something
02:43:20 <coppro> oerjan: yeah, you need to encode something like that. but I'm not quite sure how you would do so in a useful way that still leaves you minor-closed
02:43:33 <coppro> oh wait, I guess you could, nevermind
02:43:56 <coppro> hmm... better. membership in the class needs to be decideable
02:44:33 <oerjan> that would seem more interesting
02:46:03 -!- FreeFull_ has joined.
02:48:00 -!- FreeFull has quit (Ping timeout: 265 seconds).
03:08:16 * Sgeo is still trying to figure out the functor thing
03:08:34 <Sgeo> All I can think is maybe it's an infinitely big type trying to write it out like that
03:09:13 <coppro> http://twanvl.nl/blog/haskell/overloading-functional-references ?
03:09:35 <coppro> you were asking about lenses, these are twan's original posts
03:10:46 <Sgeo> Is it possible to write a function that gives infinitely many arguments in Haskell?
03:11:55 <Sgeo> Hmm, even if the type involved is opaque to my lenses, it can't be opaque to the driver
03:13:39 <Sgeo> But it doesn't need to be just a function, it itself shouldn't be getting composed, right?
03:13:50 <Bike> wouldn't const id or however you spell it take infinitely many arguments
03:13:52 <Sgeo> Only the lenses that treat it as opaque get composed
03:14:10 <Sgeo> > const id 3 4
03:14:17 <Sgeo> > const id 3 4 5
03:14:18 <lambdabot> Could not deduce (GHC.Num.Num (a0 -> t))
03:14:18 <lambdabot> arising from the ambiguity check for ‘e_1345’
03:14:18 <lambdabot> from the context (GHC.Num.Num (a -> t), GHC.Num.Num a)
03:14:18 <lambdabot> bound by the inferred type for ‘e_1345’:
03:14:18 <lambdabot> (GHC.Num.Num (a -> t), GHC.Num.Num a) => t
03:14:23 <Sgeo> ...dangit numbers
03:14:29 <Sgeo> > const id '3' '4' '5'
03:14:31 <lambdabot> Couldn't match expected type ‘GHC.Types.Char -> t’
03:14:47 <Bike> no, wait, i'm thinking wrong, yeah.
03:15:14 <Bike> i just want a function that ignores its argument and returns itself.
03:15:29 <Sgeo> Hey, I've finally learned the difference between expected and actual
03:15:32 <lambdabot> <no location info>: not an expression: ‘let f x = f’
03:15:38 <Taneb> :t let f x = f in f
03:15:39 <lambdabot> Occurs check: cannot construct the infinite type: t3 ~ t2 -> t3
03:15:39 <lambdabot> x :: t2 (bound at <interactive>:1:7)
03:16:17 <Sgeo> Conceptually, an infinite type can be well-typed even if Haskell doesn't understand it, right?
03:16:28 <Bike> > undefined 3 4 5 6 7
03:16:33 <Sgeo> fix kills an argument
03:21:12 -!- huh has joined.
03:21:27 <shachaf> @let import Data.NumInstances
03:23:43 <oerjan> note that if a value has the type a = b -> a then you can never get any information out of it
03:24:44 <lambdabot> newtype Mu f = In { out :: f (Mu f) }
03:25:17 <shachaf> that should be called Fix :'(
03:25:50 <oerjan> :t let f x = out f in f
03:25:51 <lambdabot> Couldn't match expected type ‘Mu f1’
03:25:51 <lambdabot> with actual type ‘t1 -> f1 (Mu f1)’
03:25:56 <oerjan> :t let f x = In f in f
03:26:15 <zzo38> To write a roguelike game in SQL does not sound too terrible to me; you will not have to deal with encoding data in a save file, since SQL will do that automatically (you don't even need to tell it to save; that is automatic too),
03:26:32 <shachaf> @let newtype Fix f = Fix { runFix :: f (Fix f) }
03:28:06 <lambdabot> (Contravariant f, Functor f) => f a -> f b
03:28:23 <oerjan> NOT THE ONE I WAS LOOKING FOR
03:30:46 <int-e> "t GHC.Prim.coerce
03:30:49 <int-e> :t GHC.Prim.coerce
03:31:08 <int-e> (exported via GHC.Exts)
03:32:59 <oerjan> @let f x = GHC.Prim.coerce (In f)
03:32:59 <lambdabot> .L.hs:147:7: Not in scope: ‘GHC.Prim.coerce’
03:33:00 <lambdabot> It could refer to either ‘L.f’, defined at .L.hs:147:1
03:33:23 <ion> @let a = GHC.Exts.coerce 42
03:33:24 <lambdabot> .L.hs:144:5: Not in scope: ‘GHC.Exts.coerce’
03:33:42 <int-e> GHC.Exts is not very safe :P
03:33:54 <oerjan> coerce is meant to be safe :(
03:35:25 <oerjan> which i guess means that's the wrong module to export that from...
03:35:25 <Sgeo> oerjan: I can if the language allows functions to be more than merely functions
03:35:44 <oerjan> Sgeo: oh right you're not working in haskell
03:36:23 <coppro> Sgeo: you can't make a truly infinite function type in Haskell. You can, of course, fake it.
03:36:39 <int-e> @run let a = (); a # b = 0 in let a# b = 1 in a# ()
03:37:04 <int-e> @run let a = (); a# b = 0 in let a # b = 1 in a# ()
03:37:29 <int-e> That's a proper test for MagicHash.
03:38:00 <lambdabot> Kind incompatibility when matching types:
03:38:16 <ion> @run I# 0#
03:38:17 <lambdabot> Not in scope: data constructor ‘I#’
03:38:17 <lambdabot> Perhaps you meant ‘In’ (imported from Lambdabot.Plugin.Haskell.Eval.Trusted)
03:39:27 <int-e> And I guess that's harmless since you can't operate on such unboxed values anyway.
03:39:45 <int-e> (with the modules that lambdabot imports)
03:42:00 <oerjan> @let class CountArgs a where {countArgs :: Int -> a}; instance CountArgs Int where {countArgs = id}; instance CountArgs a => CountArgs (b -> a) where {countArgs n _ = countArgs $! n + 1}
03:42:31 <oerjan> > countArgs 0 "hi" False [Nothing] :: Int
03:43:07 <oerjan> imagine working on the first try
03:56:04 -!- tromp has quit (Remote host closed the connection).
03:56:36 <Sgeo> Half wondering if it would just make more sense to abuse impurity to turn a modifier into something able to get
03:56:37 -!- tromp has joined.
03:56:51 <Sgeo> That... seems almost related to what the functor allows for anyway
03:59:47 <HackEgo> solvescoin pingcoin mazancoin reatcoin barcoin godsmacoin cntalcoin mutlastacoin odtizediuspietcoin giumcoin lo'scoin pcordfuckercoin vowcoin dilaxatcoin goto+coin grancoin eucacoin qalcoin con-textendecoin graphicoin
03:59:49 <zzo38> In some book I have, it describes a virtual machine called "Ada/CS Object Machine". It is a similar to IBM mainframe instruction sets.
03:59:53 <elliott> (f a) where f is an unknown Functor is iso to (forall b. (a -> b) -> f b), if that's what you've been asking.
04:00:52 <Sgeo> Which is iso to an infinitely large type, I guess
04:01:00 <zzo38> elliott: Isn't that the right Yoneda lemma though?
04:01:02 -!- tromp has quit (Ping timeout: 255 seconds).
04:01:02 -!- Sorella has quit (Quit: It is tiem!).
04:01:15 <elliott> it's iso to the intersection of ((a -> B) -> f B) for all concrete B, sure.
04:01:29 <elliott> but that doesn't seem like a terribly useful thing here.
04:02:15 <zzo38> There is also a left Yoneda lemma (is that useful here at all?)
04:13:06 <Bike> http://ww2.chemistry.gatech.edu/~bostwick/stms/raw.txt Anyone recognize where the language on the bottom could be from, phylogenically? It's probably a DSL
04:18:03 <oerjan> looks like a kind of BASIC to me
04:19:22 <zzo38> Yes, something like BASIC
04:20:20 <zzo38> But unusual; it is using ! for comments
04:21:00 <oerjan> but "PRINT USING" is very basic
04:21:38 <zzo38> Yes, I know, I can write programs in BASIC.
04:22:16 <Sgeo> I can write a program in BASIC. Specifically, the empty program.
04:23:12 <zzo38> Yes, that will work and is valid
04:23:50 <Bike> basic has that #-y print string thing?
04:24:24 <zzo38> If you put #1 or whatever after PRINT it mean, to send it to the file, instead of to the screen.
04:24:43 <zzo38> In a PRINT USING, the # is a placeholder for a digit.
04:25:02 <zzo38> Type suffix in some version of BASIC can be # for double precision floating points.
04:25:29 <Bike> "You can use any text editor to write a macro. In the following examples, it is assumed that Microsoft(R) Windows Notepad is used."
04:28:10 -!- Sprocklem has joined.
04:32:23 <Sgeo> I think Haskell is about to teach me MVC
04:34:21 -!- Patashu_ has changed nick to Patashu.
04:47:44 <zzo38> What is the specification of the qsort function in C about the exact pointing of the arguments to the comparison function?
04:48:44 <zzo38> Does it point to existing objects, create a copy, point to their original location, etc, such as, what will their pointer difference be?
04:51:27 <int-e> zzo38: it doesn't say. you can't rely on the pointer values at all, just on the contents.
04:52:51 <pikhq> int-e: Though there's no sane way that qsort can do *any* dynamic allocation at all.
04:53:02 <pikhq> (qsort cannot fail)
04:55:06 <pikhq> I suppose that doesn't mean that, say, the arguments to the comparator can't point into buffers on the stack.
04:55:18 <pikhq> Just that there's only so crazy you can go.
04:55:27 <Sgeo> pikhq: what of trying to allocate, the allocation failing, and it falling back to something worse than if it was able to allocate?
04:55:41 <int-e> Huh. Actually, 7.20.5 (C99) says that the pointers being passed are supposed to lie inside the array being sorted.
04:56:07 <Sgeo> Not everything that uses malloc has to have a non-0 chance of failing, I think
04:56:10 <pikhq> Sgeo: I guess that's *valid*, if utterly moronic.
04:56:30 <huh> int-e: pikhq ???
04:57:17 <Sgeo> Awesom, I can tab-complete huh now. Although I ended up trying to tab-complete ttab-coomplet.e
04:57:36 <pikhq> Particularly with qsort. In-place sorting isn't exactly hard.
05:00:58 -!- huh has quit (Quit: Segmentation fault).
05:02:31 <int-e> pikhq: hmm. but quicksort is the only viable option that remains.
05:03:51 <pikhq> No. Smoothsort, heapsort, in-place merge sort.
05:04:27 <zzo38> Are you sure qsort cannot fail, even if the comparison function is not implemented correctly? (For example, if it returns a random number regardless of its inputs)
05:04:41 <pikhq> zzo38: That's UB. :)
05:05:05 <int-e> heapsort is terrible for caches.
05:05:58 <pikhq> And quicksort has pathological behavior on certain inputs.
05:06:27 <int-e> glibc defaults to a merge sort with n/2 elements worth of temporary space, and falls back to quicksort if allocation fails
05:06:42 <pikhq> That's... not what glibc does.
05:06:59 <Sgeo> pikhq: it needs O(log n) stack space according to Wikipedia
05:07:14 <pikhq> Sgeo: Yes. Or about two ints.
05:07:34 <pikhq> Sgeo: Remember, log_2 2^64 is is 64.
05:07:52 <Sgeo> Actually... huh. How does that work, exactly, If it's not known until runtime how much stack space.... oh, hmm....
05:08:04 <pikhq> ... The maximum is well-known.
05:08:30 <Sgeo> Maximum on modern computers
05:08:31 <int-e> pikhq: what do you mean, "that's not what glibc does"?
05:08:53 <pikhq> int-e: I mean that that's not the algorithm used in stdlib/qsort.c.
05:09:15 <int-e> pikhq: indeed. and that's not qsort. look at msort.c in the same directory.
05:09:38 * pikhq takes a moment to flip off glibc
05:09:58 <Sgeo> glibc, the new openssl?
05:10:25 <pikhq> That is... utterly, positively moronic, BTW.
05:10:52 <pikhq> So, on out-of-memory it goes pathological.
05:11:17 <pikhq> Rather than, y'know, just using smoothsort.
05:11:26 <Sgeo> There's no Identity Applicative, is there?
05:11:33 <Sgeo> What would pure... oh. I'm dumb.
05:11:44 <pikhq> Sgeo: Pretty much. glibc is positively insane.
05:11:54 <Sgeo> I managed to forget that pure takes an argument.
05:12:01 <Bike> wouldn't it be the old ssl
05:12:16 <Bike> i don't know if return to libc counts as a heartbleed
05:18:03 <kmc> employees must wash hands before returning to libc
05:33:02 <coppro> oerjan: turns out the answer is you can't
05:34:13 <coppro> actually, wait, hmm... not sure the reasoning holds
05:34:52 <coppro> but if you had only finitely many candidate sets of forbidden minors, you could just enumerate the class of graphs and check each of the sets
05:36:23 <oerjan> in fact you only needed to test the members of the candidate sets
05:37:13 <oerjan> the problem is when you cannot prove there is a much larger forbidden graph than the ones you have tested
05:38:43 <ski> Sgeo,Bike : "Is it possible to write a function that gives infinitely many arguments in Haskell?","i just want a function that ignores its argument and returns itself.","Conceptually, an infinite type can be well-typed even if Haskell doesn't understand it, right?" -- can be done with `ocaml -rectypes', e.g.. this is "equi-recursive" types, as opposed to "iso-recursive" ones
05:39:21 <Sgeo> (lambda (f) (lambda (o) ((f (car o)) (lambda (mc) (cons mc (cdr o))))))
05:39:33 <coppro> suppose S were a minimal set of sets of forbidden minors that you couldn't prove were/weren't the set for your class. Then at least one set contains a minor of a graph in another class. You can test those two graphs and eliminate one set from consideration, which contradicts the selection of S.
05:39:44 <oerjan> i used ocaml rectypes for my unlambda implementation
05:39:44 <coppro> so it relies again on the GMt
05:39:47 <Bike> well you can obviously do it in scheme
05:40:46 * Sgeo wonders if that's a bit verbose
05:40:55 <oerjan> you can also do it in unlambda. although i never tested out my theoretical "stop at the first argument that is d" idea
05:41:01 <Sgeo> Compared to just using a modifier on the targetted car
05:41:05 <HackEgo> [wiki] [[User:Quincunx]] http://esolangs.org/w/index.php?diff=39405&oldid=39086 * Quincunx * (+144) /* Circuit Diagram 10 */
05:43:02 <oerjan> coppro: um your line is too ambiguous for me to interpret
05:43:28 <Sgeo> So... twisty, almost. You apply the f too get a functor, which is then wrapped in a modifer that produces a functor, which is then applied to get a functor, etc. etc.
05:43:56 <oerjan> in fact i have no idea if "set of sets" is a typo
05:44:15 <Sgeo> Somehow this is making the idea behind van Laarhoven lenses a bit more intuitive to me
05:44:19 <Sgeo> Is that weird?
05:44:42 <Sgeo> For getting, (f (car o)) is a function that just ignores its argument
05:44:52 <coppro> oerjan: ok, let's say I have a minor-closed class \mathcal G. Let S be the set of sets F such that the statement "F is the set of forbidden minors of \mathcal G" is independent of ZFC. Then by the GMT, there exist, G, H in members of F, one which is a forbidden minor of the other
05:45:03 -!- Vorpal has joined.
05:45:03 -!- Vorpal has quit (Changing host).
05:45:03 -!- Vorpal has joined.
05:46:05 <coppro> then you can just test G and H for membership in \mathcal G. If either is in \mathcal G, then that isn't a forbidden minor, eliminating one set from consideration. If neither is, then assuming G is a minor of H, then H is not a forbidden minor. either way, our choice of S was wrong, because we proved that some F was not the set of forbidden minors.
05:46:42 <oerjan> should "in members of F" be "in members of S"
05:47:21 <int-e> ski: in Haskell you can play the usual newtype trick. newtype W a = W { apply :: a -> W a }; w = W (\x -> w)
05:47:29 <Sgeo> Should I be sad that this is almost certainly not going to be R5RS Scheme?
05:47:45 <coppro> the tl;dr is that the Graph Minors Theorem is trolling us even more
05:47:57 <coppro> because it tells us that not only is the set of minors finite, there exists a proof of this fact.
05:48:16 <coppro> there exists a proof of *which* set it is
05:48:43 <Bike> Sgeo: what the hell are you trying to do even
05:49:02 <Sgeo> Port something close to van Laarhoven lenses and miscelleny to Racket
05:49:13 <Bike> well nevermind me then
05:49:38 -!- oerjan has quit (Quit: Too tired, in fact).
05:50:09 <ski> int-e : indeed .. but that's kinda obvious
05:50:10 <Sgeo> It almost makes sense what f being an applicative maker instead of just a functor maker would do
05:50:20 <ski> (and not quite what the OP asked for)
05:50:42 <ski> perhaps you can do some classy trick as well
05:50:56 <Sgeo> And what pure looks like
05:51:04 <Sgeo> Ok, besides Functor and Applicative, what else do I want?
05:51:09 <Sgeo> What are prisms actually?
05:51:40 <Bike> When you save the macro it becomes a file on the computer hard disk.
05:52:08 <Sgeo> Bike: so few people have HDs though, aren't they more likely to be saving to floppy?
05:52:37 <Sgeo> (I had a book on DOS when I was a kid)
05:52:47 <Sgeo> And a laptop that ran DOS
05:53:10 <Sgeo> I think the battery died
05:53:59 <int-e> pikhq: So smoothsort looks complicated (not just the theory, but also the implementation) and bad in the benchmark that I found. I'll look at it some more, but only as an intellectual exercise.
06:01:26 <Sgeo> I believe this is what both looks like
06:02:28 <Sgeo> (lambda (f) (lambda (o) ((f (car o) (cdr o)) cons)))
06:02:42 <ski> Bike : save macro where ?
06:02:53 <Bike> onto the computer hard disk
06:03:06 <ski> i mean, in which system ?
06:06:02 <Bike> oh some chromotagraphy system
06:10:03 <ski> what kind of macro ?
06:10:11 <ski> an ui macro ?
06:11:16 <Bike> more like a shell script.
06:12:07 <Bike> kmc: https://www.sciencenews.org/article/name-fungus article about fungus sex. you probably know most of it but it's still neat
06:12:08 <ski> in an OS ?
06:12:19 <Bike> for this chromatography machine.
06:16:14 <ski> in an OS made for that chromatography machine ?
06:17:44 <Bike> http://www.chem.agilent.com/Library/usermanuals/Public/MACROS.PDF go crazy
06:29:38 -!- shikhin has joined.
06:29:38 -!- shikhin has quit (Changing host).
06:29:38 -!- shikhin has joined.
06:36:24 <kmc> fungots fall on fungot falls
06:36:24 <fungot> kmc: that is just a value of type is created containing the syntax for mark if he was really gonna get worse and worse each week, i fnord kara to hold me until i fell over to 5 videos and then i jizzed. in other places... problem, about the copyrights: i have put this in the near future, that are just the ordinary ( for call/ cc))) hangs
06:36:46 <kmc> fungot: tmi
06:36:46 <fungot> kmc:, so i'd make stuff up to. why, this is for you guys are a lot
06:37:28 <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
06:37:36 <kmc> fungot: stop making sense
06:37:36 <fungot> kmc: use the ' ' ' delete a value of type " airbus is a big fan of avril....but this song " there
06:38:30 <kmc> ^style qwantz
06:38:30 <fungot> Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011)
06:38:32 <kmc> fungot: oi
06:38:33 <fungot> kmc: it's a very tricky to sound natural, then you can't sleep at all, then you go demented and then you die, we're giving dinosaur comics to the marmaduke guy. sincerely, the man, you must really have
06:41:56 <Sgeo> I made an... odd mistake
06:52:58 <Sgeo> I can use pure functions.
06:53:06 <Sgeo> At least for running lenses
06:53:16 <Sgeo> > (\f (o:os) -> f o (\mc -> mc : os)) const [1,2,3,4,5]
06:53:22 <Sgeo> > (\f (o:os) -> f o (\mc -> mc : os)) (\o recon -> recon (o + 1)) [1,2,3,4,5]
06:57:41 <Sgeo> I do wish that modifier didn't have to be baked into the runner
06:57:51 <Sgeo> :t (\f (o:os) -> f o (\mc -> mc : os))
06:57:51 <lambdabot> (a -> (a -> [a]) -> t) -> [a] -> t
06:58:28 <Sgeo> Oh jeez it probably doesn't, I just need to give the modifier after the target
07:00:22 -!- shikhin has quit (Ping timeout: 276 seconds).
07:00:45 <Sgeo> > (\f (o:os) -> f o (\mc -> mc : os)) (\o recon mod -> recon (mod o)) [1,2,3,4,5] (+1)
07:01:09 <Sgeo> @pl (\o recon mod -> recon (mod o)
07:01:09 <lambdabot> expecting variable, "(", operator or ")"
07:01:15 <Sgeo> @pl (\o recon mod -> recon (mod o))
07:01:25 * Sgeo runs far, far away
07:13:40 <Sgeo> > let lensHead = (\f (o:os) -> f o (\mc -> mc : os)) in (lensHead.lensHead) const [1,2,3,4,5]
07:13:42 <lambdabot> Occurs check: cannot construct the infinite type:
07:13:42 <lambdabot> Expected type: a0 -> (a0 -> [a0]) -> ([a0] -> [[a0]]) -> t
07:13:42 <lambdabot> Actual type: a0 -> (a0 -> [a0]) -> a0
07:13:56 <Sgeo> And I thought I was onto something
07:14:18 <Sgeo> ....like being an idiot... of course that wouldn't typecheck
07:15:28 <Sgeo> > let lensFst = (\f (a,b) -> f a (,b)) in (lensFst.lensFst) const ((1,2),3)
07:15:49 <mroman> infinite type error is the error I encounter most often too ;)
07:16:06 <Sgeo> I wasn't expecting any of these to typecheck at all
07:16:14 <Sgeo> I was expecting they'd only work in Racket or something
07:17:08 <Sgeo> There's still the whole lack of varargs thing
07:17:21 <mroman> there's a 49% chance it's either "infinite type", 49% chance it's "indentation" and 1% some crazy other thing :(
07:17:37 -!- nisstyre has joined.
07:17:46 <Sgeo> But in languages with first class functions and varargs, all we need for van Laarhoven lenses and traversals are first class functions and varargs
07:18:11 <Sgeo> (Still have yet to really prove the traversals thing)
07:21:45 -!- shikhin has joined.
07:21:45 -!- shikhin has quit (Changing host).
07:21:45 -!- shikhin has joined.
07:26:53 -!- mhi^ has joined.
07:58:06 <kmc> ferns have swimming sperm? wtf
08:00:48 -!- shikhin has quit (Ping timeout: 240 seconds).
08:02:22 <Vorpal> <mroman> there's a 49% chance it's either "infinite type", 49% chance it's "indentation" and 1% some crazy other thing :( <-- so what about the remaining 1%
08:02:34 <Vorpal> Or did you mean 2% for the last one
08:02:57 <Vorpal> (Or 49.5 for the first two)
08:17:41 -!- shikhin has joined.
08:19:35 -!- conehead has quit (Quit: Computer has gone to sleep).
08:20:29 <Sgeo> Hmm. Are my lenses any distinct from the store model?
08:20:40 <Sgeo> I guess I don't actually understand the store model
08:22:26 <Sgeo> I keep thinking it's all connected, that model, my model (just converting the typeclasses into something more concrete), CPS... that type that these have look all CPSy
08:27:52 -!- Slereah_ has changed nick to Slereah.
08:30:20 -!- MoALTz has joined.
08:35:01 -!- AnotherTest has joined.
08:54:45 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
09:04:17 -!- augur_ has quit (Quit: Leaving...).
09:26:01 -!- shikhin has quit (Remote host closed the connection).
10:12:00 -!- yorick has joined.
10:15:57 -!- MoALTz has quit (Quit: Leaving).
10:16:37 -!- nooodl has joined.
10:21:36 -!- ais523 has joined.
10:31:40 -!- AnotherTest has quit (Ping timeout: 252 seconds).
10:33:47 -!- kronion has joined.
10:36:25 -!- FreeFull_ has changed nick to FreeFull.
10:47:11 -!- MoALTz has joined.
11:02:50 <HackEgo> [wiki] [[Hollang]] http://esolangs.org/w/index.php?diff=39406&oldid=39367 * Zerk * (+888)
11:05:04 <ais523> ooh, HackEgo reports changes to the wiki now
11:05:14 <ais523> weird that it's that bot doing it, it doesn't fit in that well with HackEgo's normal behviour
11:07:16 <Jafet> We should create a new bot to announce them, then
11:18:05 <Jafet> http://www.asrock.com/microsite/mining/index.en.html
11:20:47 <fizzie> ais523: It was the path of least resistance.
11:21:34 <fizzie> (It's already running on the same server as the wiki, it's already on the right IRC channel, and there was already an easy way to hook up extra inputs.)
11:29:19 -!- MindlessDrone has joined.
11:38:15 -!- nucular has joined.
11:38:16 -!- nucular has quit (Changing host).
11:38:16 -!- nucular has joined.
12:12:52 -!- callforjudgement has joined.
12:13:23 -!- ais523 has quit (Read error: Connection reset by peer).
12:13:50 -!- callforjudgement has changed nick to ais523.
12:32:07 -!- callforjudgement has joined.
12:32:37 -!- ais523 has quit (Read error: Connection reset by peer).
12:32:40 -!- callforjudgement has changed nick to ais523.
12:36:26 -!- ais523 has quit (Read error: Connection reset by peer).
12:36:37 -!- ais523 has joined.
12:40:52 -!- ais523 has quit (Read error: Connection reset by peer).
12:41:00 -!- ais523 has joined.
13:22:05 -!- Sorella has joined.
13:38:37 -!- yorick has quit (Remote host closed the connection).
13:39:45 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39407&oldid=39403 * Creeparoo * (+36)
13:40:24 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39408&oldid=39407 * Creeparoo * (-35) Undo revision 39407 by [[Special:Contributions/Creeparoo|Creeparoo]] ([[User talk:Creeparoo|talk]])
13:40:45 <HackEgo> [wiki] [[Poop]] M http://esolangs.org/w/index.php?diff=39409&oldid=39408 * Creeparoo * (-47)
13:44:44 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39410&oldid=39409 * Creeparoo * (+25)
13:45:59 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39411&oldid=39410 * Creeparoo * (+26)
13:46:52 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39412&oldid=39411 * Creeparoo * (-25)
13:47:58 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39413&oldid=39412 * Creeparoo * (+50) Undo revision 39412 by [[Special:Contributions/Creeparoo|Creeparoo]] ([[User talk:Creeparoo|talk]])
13:49:38 -!- ais523 has quit (Ping timeout: 255 seconds).
13:49:39 -!- augur has joined.
13:50:23 -!- ais523 has joined.
14:02:02 -!- callforjudgement has joined.
14:05:16 -!- scarf has joined.
14:06:44 -!- Patashu has quit (Ping timeout: 255 seconds).
14:06:46 -!- ais523 has quit (Ping timeout: 276 seconds).
14:06:59 -!- scarf has changed nick to ais523.
14:09:12 -!- callforjudgement has quit (Ping timeout: 240 seconds).
14:17:16 -!- ais523 has quit (Read error: Connection reset by peer).
14:17:23 -!- callforjudgement has joined.
14:17:33 -!- callforjudgement has changed nick to ais523.
14:20:08 -!- impomatic has quit (Ping timeout: 265 seconds).
14:24:13 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39414&oldid=39413 * Creeparoo * (+252)
14:27:23 -!- callforjudgement has joined.
14:27:27 -!- ais523 has quit.
14:30:03 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39415&oldid=39340 * Creeparoo * (+11)
14:31:19 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39416&oldid=39414 * Creeparoo * (+1)
14:31:27 -!- callforjudgement has changed nick to ais523.
14:33:18 <nortti> I like how the "Poop" text shows up brown in fbcon
14:34:04 <olsner> it's brown here too, but all page titles have the same brown so
14:34:59 <nortti> yeah, just amusing coincidence
14:36:38 <ais523> you're IRCing in fbcon?
14:36:56 <ais523> how many fbcons do you have open right now (as in, running programs other than login/getty)?
14:38:29 <ais523> most people use multitasking window managers
14:38:42 <ais523> so I was curious what life was like for someone who didn't
14:39:01 <nortti> well, my t61p now refuses to start up so I'm back to my t20 I've been using for past 2 years
14:39:32 <nortti> it is actally not that bad unless you like to watch a lot of videos or play games
14:39:49 <ais523> aalib can solve the first problem
14:40:12 <nortti> oh, I'm using fbdev2 driver for mplayer when I watch stuff
14:40:14 <ais523> and some games can run in framebuffer mode (thus on an fbcon console, although fbcon itself isn't doing the graphics)
14:40:24 <nortti> more refering to my 600MHz CPU
14:41:03 <nortti> funny going from 2.2GHz core 2 duo to 600MHz p3 without much trouble
14:41:12 <ais523> I've played Battle for Wesnoth in framebuffer mode, although it has graphical glitches with transparency
14:41:39 <nortti> also, I can get sdl to display to fb
14:41:52 <nortti> so anything that uses sdl backend should run"
14:42:06 <fizzie> I used to use a framebuffer console for just about everything, too, though that was perhaps a decade ago.
14:42:14 <fizzie> "mplayer -vo mga" and so on.
14:42:33 <fizzie> Matrox-specific video driver.
14:42:40 -!- augur has quit (Remote host closed the connection).
14:42:44 <fizzie> I had a Matrox Mystique 220 card, I think.
14:42:45 <ais523> I should try NetHack 4 tiles on framebuffer some time
14:43:07 -!- augur has joined.
14:43:13 <fizzie> Oh, and later I had a v. fancy AGP card, I think it was the G400.
14:43:48 <fizzie> The "-vo mga" worked fine in conjunction with matroxfb, used a hardware video overlay.
14:46:10 <fizzie> Also my "rdiff-backup"-based backup thing is running out of memory. :/
14:47:43 -!- augur has quit (Ping timeout: 276 seconds).
14:50:34 -!- kronion_ has joined.
14:54:01 -!- kronion has quit (Ping timeout: 252 seconds).
14:57:13 <fizzie> https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=574379 open since 2010, I see.
15:01:58 -!- ais523 has quit.
15:02:06 -!- callforjudgement has joined.
15:02:46 -!- callforjudgement has changed nick to ais523.
15:39:24 -!- ais523 has quit.
15:39:33 -!- ais523 has joined.
15:50:28 -!- Phantom_Hoover has joined.
15:53:37 -!- augur has joined.
16:02:34 -!- callforjudgement has joined.
16:02:36 -!- ais523 has quit (Read error: Connection reset by peer).
16:02:51 -!- callforjudgement has changed nick to ais523.
16:08:16 -!- MoALTz has quit (Quit: Leaving).
16:30:53 -!- kronion_ has quit (Remote host closed the connection).
16:31:22 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39417&oldid=39416 * Creeparoo * (+13)
16:31:26 -!- kronion has joined.
16:31:58 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39418&oldid=39417 * Creeparoo * (+20)
16:34:35 <HackEgo> [wiki] [[Poop]] http://esolangs.org/w/index.php?diff=39419&oldid=39418 * Creeparoo * (+165)
16:36:39 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=39420&oldid=39368 * Creeparoo * (+11)
16:46:10 -!- boily has joined.
17:03:43 <pikhq> int-e: Your benchmark sounds bad. :P
17:03:52 <pikhq> int-e: Is is somewhat complicated though, yes.
17:04:12 <pikhq> int-e: In exchange you get execution time that's a function of the sortedness of your input.
17:26:25 -!- boily has quit (Quit: WeeChat 0.4.2).
17:29:20 -!- boily has joined.
17:33:17 <Phantom_Hoover> http://www.reddit.com/r/Bitcoin/comments/23zmoz/lost_life_savings_60_btc_while_transferring_to/
17:34:43 -!- nisstyre has joined.
17:36:03 <Phantom_Hoover> all you have to do is buy a new laptop, install linux and a browser on it and never use it for anything but bitcoin
17:49:14 <int-e> so you're saying I should spend $500 on a laptop to manage $0 worth of bitcoins.
18:06:13 <edwardk> Sgeo: your lenses are store lenses sans newtype
18:06:48 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:14:39 -!- ais523 has quit.
18:31:27 -!- nisstyre has quit (Quit: bai).
18:39:06 <Sgeo> What were the limitations of store lenses?
18:40:06 <Sgeo> (Beyond at least my lenses being unable to do traversals.... if translated into a language with varargs, I think that problem goes away)
18:40:07 <edwardk> its just composition needing a custom category, not coercing up/down to subtypes automatically, that the args in your form aren't in the right order for what tends to get substituted/for point free writing, etc.
18:40:48 <edwardk> type Lens s t a b = forall f. Functor f => s -> (a -> f b) -> f t
18:40:55 <edwardk> type Lens s t a b = forall f. Applicative f => s -> (a -> f b) -> f t as a
18:41:07 <edwardk> type Traversal s t a b = forall f. Applicative f => s -> (a -> f b) -> f t
18:41:10 <Sgeo> Point one seems to be moot without the newtype
18:41:28 <edwardk> well, i use these in lens secretly
18:41:59 <Sgeo> I... don't have those subtypes, at least in the Haskell version
18:42:13 <Sgeo> Which makes me sad
18:42:14 <edwardk> just showing you can generalize this pattern
18:42:28 <Taneb> lens, the only Haskell library whose implementation and use are on topic in this channel :)
18:43:20 <Sgeo> I can figure out how to make a Getter in the Racket version, but it's kind of ugly. Not sure about Setter
18:44:01 <Sgeo> (lambda (f) (lambda (o) ((f (somefunc o)) (lambda (useless) (error "Cannot use as a setter")))))
18:44:22 <Sgeo> Wait, no somefunc
18:44:38 <Sgeo> Actually, yes somefunc
18:45:11 <Sgeo> I should try to transliterate actual Haskell Getters/Setters
18:45:27 <mroman> What language is that?
18:45:39 <Sgeo> Scheme + error
18:46:19 <Sgeo> Is there a document of each kind of thing lens has + what they are
18:46:30 <Sgeo> e.g. type Getter blah = blah
18:46:33 <Sgeo> Or am I going source diving?
18:49:45 <edwardk> https://github.com/ekmett/lens/wiki/Synonyms-by-Constraints but you can also just look in Control.Lens.Type
18:50:37 <edwardk> also i thought shachaf wrote a page summarizing
18:50:54 <edwardk> https://github.com/ekmett/lens/wiki/Types
19:11:28 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39421&oldid=39415 * Fizzie * (-11) /* P */ If it's on the Joke language list, I guess it's not on the Language list
19:46:54 <Sgeo> Ugh, I have some reason to believe my traversals may be wrong
19:47:32 <coppro> I also have reason to believe that
19:49:36 <Sgeo> Specifically, I'm assuming that the traversal is given an f that can take 0 or more arguments, but am returning something that is only capable of taking one argument
19:57:29 <edwardk> Sgeo: what do your traversals look like?
19:57:39 <Sgeo> They were looking like
19:58:03 <Sgeo> (lambda (f) (lambda (o) ((f (car o) (cdr o)) cons)))
19:58:36 <Sgeo> But that, when given an f, results in a function that can only take one argument
19:59:55 -!- nooodl_ has joined.
20:01:56 <Sgeo> I can make that iinner lambda take an arbitrary amount of arguments, but I think to get them to compose with lenses, I need to make lenses do that too. It would start to get verbose
20:03:53 -!- nooodl has quit (Ping timeout: 264 seconds).
20:04:42 -!- nooodl_ has changed nick to nooodl.
20:11:33 <Sgeo> Ugh, not sure if it's f's responsibility to return something that can be used like f, or the optical's (is that the right term) responsibility
20:13:23 <Sgeo> I should know this stuff
20:15:38 -!- kronion has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
20:22:25 -!- nucular has quit (Quit: Switching to phone).
20:38:47 -!- conehead has joined.
20:59:25 -!- boily has quit (Quit: ISO 7816 CHICKEN).
21:00:48 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
21:08:18 <nortti> recommend me a lightweight linux distro that still does graphical mode and other modern stuff
21:09:34 <zzo38> What "other modern stuff" do you mean? IPv6?
21:11:32 <Sgeo> We've moved on, the modern thing is IPv8
21:12:17 <nortti> I mean stuff like linux 3.x series kernel and library versons from this decade
21:13:08 <zzo38> I don't know much about Linux distro
21:14:18 -!- Phantom_Hoover has joined.
21:15:05 <Bike> lxdm is "lightweight" i guess
21:15:15 <nortti> arch runs nicely with 128MB of ram on a i586?
21:15:26 <Bike> hell if i know, i live in 2014
21:16:09 <Bike> i don't know why it wouldn't, though. you'd be installing most everything on your own. maybe you don't want sudo
21:16:36 <nortti> I know many distros set a baseline of i686 nowadays
21:17:01 <Bike> https://wiki.archlinux.org/index.php/Install_Arch_i586 well it looks nontrivial i guess
21:17:37 <Bike> http://distrowatch.com/search.php?architecture=i586 openSUSE! oh boy!
21:18:12 <fizzie> How is it with Slackware these days?
21:18:20 <fizzie> I'd've sort of assumed.
21:21:29 <fizzie> Lots of "i486" in the file names in slackware-current/, at least.
21:22:14 <fizzie> http://www.slackware.com/install/sysreq.php "486 processor" "64MB RAM (1GB+ suggested)" "About 5GB+ of hard disk space for a full install"
21:23:40 <fizzie> Don't know about modern, but 14.1 has a 3.10.17 kernel and all.
21:24:35 <fizzie> [14.0 release notes:] "Since our last stable release, a lot has changed in the Linux and FOSS world. The kernel has moved on to major version 3 (we're using the long term supported 3.2.29 kernel for this release), X.org has released X11R7.7, and Firefox has had a whopping *11* major releases to arrive at version 15.0.1! We've brought together the best of these and other modern components and ...
21:24:41 <fizzie> ... worked our magic on them. You'll find new compilers (including the LLVM/clang compiler that's becoming a popular alternative to gcc), development tools, libraries, and applications throughout, all prepared with our careful and rigourous testing. If you've used Slackware before, you'll find the system feels like home. But we've also added new features such as NetworkManager for easy setup ...
21:24:47 <fizzie> ... and management of wired and wireless networking (or, you can still use the traditional network setup if you prefer)."
21:30:28 -!- nooodl_ has joined.
21:33:51 -!- nooodl has quit (Ping timeout: 252 seconds).
21:39:51 -!- augur has quit (Remote host closed the connection).
21:42:29 <zzo38> I have a slide rule marked "PICKETT ALL METAL SLIDE RULES".
21:42:38 <zzo38> Do you have any slide rules?
21:46:50 <Sgeo> What about slide guidelines?
21:47:37 <fizzie> No, but there was a collection of slide rules at the National Museum of Computing at Bletchley Park: https://dl.dropboxusercontent.com/u/113389132/Misc/20140426-slide.jpg
21:49:30 <nortti> I have 3, 2 pocket-sized ones and one full-sized
21:50:08 <nortti> make a pretty good substitute for the required calculator, at school
22:00:10 -!- nooodl_ has changed nick to nooodl.
22:15:35 -!- kallisti has joined.
22:21:09 -!- Slereah has quit (Ping timeout: 252 seconds).
22:22:35 -!- augur has joined.
22:22:59 -!- Slereah_ has joined.
22:25:27 -!- Patashu has joined.
22:33:13 <HackEgo> [wiki] [[Manufactoria]] http://esolangs.org/w/index.php?diff=39422&oldid=38754 * Quincunx * (+1666) Corrected an error in the branching section, added input, some minor edits
22:39:29 <Sgeo> I think my lenses are correct and I need to just rethink my traversals
22:40:19 -!- Patashu_ has joined.
22:40:19 -!- Patashu has quit (Disconnected by services).
22:47:25 -!- Slereah_ has quit (Ping timeout: 276 seconds).
22:47:53 -!- oerjan has joined.
22:50:27 <oerjan> coppro: ok thinking about this in another way: if you have a set S with infinitely many graphs, given by an oracle which will test any particular graphs you want, then there is no way for an algorithm to halt with a minimal set of forbidden graphs that is guaranteed to be correct.
22:50:53 <oerjan> because there will also be a graph in S that is larger than any the algorithm has tested.
22:51:32 <oerjan> *algorithm using that oracle
22:52:05 <coppro> oerjan: you don't need to test graphs directly though. you can test proofs
22:52:40 <oerjan> well i'm just saying you cannot do it for something given by an oracle.
22:54:41 <oerjan> now if the oracle were an always halting algorithm and you had a proof that it always halted and that it was closed under graph minors, i'm not sure
22:55:00 <Sgeo> @hoogle (Applicative f) => (a -> f b) -> (c -> f c)
22:55:01 <lambdabot> Data.Foldable traverse_ :: (Foldable t, Applicative f) => (a -> f b) -> t a -> f ()
22:55:01 <lambdabot> Data.Foldable for_ :: (Foldable t, Applicative f) => t a -> (a -> f b) -> f ()
22:55:01 <lambdabot> Data.Data gfoldl :: Data a => (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> a -> c a
22:55:37 <Sgeo> I'm trying to get pure from that (a -> f b)
22:56:33 <Sgeo> Would it be terrible if I had a Racket function called pure that wasn't the actual pure, but got pure from the (a -> f b)?
22:56:44 <oerjan> Sgeo: \_ c -> pure c hth
22:57:16 -!- nooodl_ has joined.
22:57:34 <Sgeo> @pl \_ c -> pure c
22:57:53 <Sgeo> In Racket, I wouldn't be ignoring the argument
22:58:02 <Sgeo> This is becoming too much like simulating typeclasses
22:58:15 <oerjan> Sgeo: i don't think you can do that. what if the function in was \x -> [x,x] ?
22:59:20 <oerjan> you need it to have the same structure as a pure result to work, i.e. just one list element for []
22:59:32 <oerjan> for that matter, const []
23:00:42 <oerjan> in fact i am pretty sure you _cannot_ construct pure from (const azero) using only <*> for a nontrivial Alternative
23:00:53 -!- nooodl has quit (Ping timeout: 264 seconds).
23:00:56 <lambdabot> Perhaps you meant ‘mzero’ (imported from Control.Monad.Writer)
23:01:05 <lambdabot> class Applicative f => Alternative f where
23:01:46 <oerjan> sounds like something that will frequently clash
23:01:50 <Sgeo> I'm confused. You can't get more than one `pure` from (a -> f b)
23:02:20 <oerjan> Sgeo: um what do you mean by (a -> f b)
23:02:29 <Sgeo> Applicative f => (a -> f b)
23:03:07 <zzo38> Is an indexed writer monad the "most obvious" indexed monad?
23:03:38 <oerjan> Sgeo: um that's the opposite of clarifying
23:03:45 <zzo38> (In terms of other monads to make a indexed monad of)
23:03:46 <copumpkin> zzo38: "moving around" in a category?
23:03:57 <oerjan> i mean, where do you expect to get such a function _from_?
23:04:19 <Sgeo> oerjan: passed in to a traversal
23:04:26 <zzo38> copumpkin: What do you mean by that?
23:04:53 <copumpkin> zzo38: just trying to understand why you consider it the most obvious. I'd probably put indexed state higher up there, but it seems fairly subjective
23:05:10 <oerjan> Sgeo: well how do you know it's not passed something like const [] ?
23:05:39 <Sgeo> What's the problem with const []?
23:06:05 <oerjan> Sgeo: that there is _no_ way to construct pure from it without using pure hth
23:06:16 <zzo38> copumpkin: Yes it probably is subjective; I just wanted to know, opinion. The reason I considered it "most obvious" is that, writer monad is holding a value of a monoid, and join (or <*>) will compose it as a monoid. Indexed monad seems to follow like a category does, so using a category instead of a monoid; that is why.
23:06:43 <zzo38> I found indexed state less obvious and did not even think of it until someone told me, actually. (Now, of course, it is clear, but at the time, it wasn't)
23:06:52 <oerjan> (in an applicative-generic way)
23:06:55 <Sgeo> I'm thinking at this point, in Racket, I would need to store something other than the function
23:07:05 <Sgeo> As in, back to not just pure functions
23:07:34 <Sgeo> ...that doesn't work, does it
23:08:31 <zzo38> copumpkin: And why do you consider indexed state higher up there?
23:09:38 <copumpkin> I dunno, just seems fairly intuitive to think of "the state type changes as you go along", and the type matches that exactly
23:09:42 <oerjan> Sgeo: another problem is that you might not have any a to pass into the function.
23:10:31 <oerjan> which means you cannot even apply it just to check the type of the result.
23:11:08 <oerjan> for that matter, it might not terminate on any input :P
23:11:34 <oerjan> all kinds of things can go wrong when you don't have inferred result types...
23:11:56 <zzo38> copumpkin: Yes it does, once it is mentioned; I was just saying that it doesn't seem so obvious to me before it is mentioned; indexed writer seems more obvious when you don't know much about indexed monads yet and just try to figure out, at least to me.
23:19:32 <zzo38> I am making more of taillib (the C version), and am considering some of your suggestions; I am adding stuff such as taillib_make_instruction and taillib_make_object and so on. Do you have further suggestions? Do you have suggestions for the Haskell interface?
23:20:13 <zzo38> (Unfortunately, none of this has been tested yet, although it does compile. I have, however, already found a few mistakes and corrected them.)
23:21:57 <lambdabot> <hint>:1:9: parse error on input ‘in’
23:22:21 <lambdabot> <hint>:1:11: parse error on input ‘of’
23:24:15 <Sgeo> Are there any C compilers that have the program die at runtime on any undefined behavior?
23:24:59 <oerjan> i suspect there is undefined behavior that is undecidable to detect
23:25:38 <FreeFull> Compilers tend to exploit undefined behaviour internally during optimisation
23:26:02 <zzo38> C compilers that target the AS/400 "Future Systems" instruction set will cause the program to raise an exception at runtime on any undefined behavior.
23:26:13 <Bike> oerjan: undecideable at runtime, though?
23:26:41 <Bike> anyway there's linty things like http://blog.regehr.org/archives/905 and valgrind i guess
23:28:44 <oerjan> come to think of it, that "infinite loops are undefined behavior" thing sounds like a good bet
23:29:19 <fizzie> That was in C++, though.
23:30:53 <Sgeo> Why would an infinite loop be undefined behavior?
23:31:05 <coppro> because the optimizer is allowed to assume that the code terminates
23:31:19 <Jafet> So that compiler writers get to optimize it away
23:31:44 <zzo38> An infinite loop should not be considered undefined behavior if it contains any impure code.
23:32:02 <fizzie> The C++ rule has a couple of qualifiers too.
23:32:05 <Bike> yes, the rule was that if it didn't access I/O or memory and whatever other crap it could be assumed to terminate
23:32:15 <Sgeo> fhttp://stackoverflow.com/questions/3592557/optimizing-away-a-while1-in-c0x
23:32:52 <Bike> "makes no calls to library I/O functions, and does not access or modify volatile objects, and performs no synchronization operations (1.10) or atomic operations (Clause 29)"
23:33:43 <zzo38> Bike: I suppose, that is similar to what I said.
23:34:00 -!- tswett has joined.
23:35:34 <fizzie> "/dev/sdc: Unknown USB bridge [0x2537:0x1068 (0x100)]" aw, now smartctl no longer works.
23:40:00 <fizzie> Huh, it works with "-d sat". I guess I should tell that to someone.
23:43:00 -!- tswett29 has joined.
23:45:00 <int-e> Sgeo: I guess if you need to do anything semidecidable then C and C++ just aren't the languages for you.
23:45:43 <tswett29> I'm thinking of an element of the Sierpinski space. Can anyone guess what it is?
23:46:20 <int-e> (Spoken as a theoretical computer scientist; the example of a daemon that runs indefinitely just isn't interesting then.)
23:47:13 <oerjan> tswett29: is it the open one twh
23:47:46 -!- Phantom_Hoover has quit (Quit: Leaving).
23:48:09 <Bike> i'm guessing 0
23:48:09 <shachaf> oerjan: itt tswett29 never answers
23:48:10 * oerjan hands out coffee cups and donuts to everyone
23:49:53 <oerjan> shachaf: 's ok i can just ban him
23:50:06 <shachaf> that would be an unjust ban hth
23:50:36 <oerjan> how dare you, maybe i should ban you too
23:51:32 <shachaf> oerjan is described in http://www.literature.org/authors/carroll-lewis/the-hunting-of-the-snark/chapter-06.html
23:52:35 <shachaf> But the Judge said he never had summed up before; / So the Snark undertook it instead, / And summed it so well that it came to far more / Than the Witnesses ever had said!
00:01:08 -!- mhi^ has quit (Quit: Lost terminal).
00:08:36 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
00:08:44 <HackEgo> twh would help, but is an hth derivative. hth. twh. hand.
00:08:55 <coppro> oerjan: yes, I was assuming you have a decideable set, so you have a proof it's closed under graph minors and an algorithm to decide membership
00:09:19 <tswett29> Sgeo: if you need to do anything semidecidable, then it's captured by the notion of an open set in topology.
00:09:20 <coppro> an oracle is too strong
00:30:25 -!- tertu has joined.
00:36:51 <Jafet> "SuperBlade® Offers: * Highest computing density [...] * Unsurpassed TCO"
00:39:29 <HackEgo> [wiki] [[Manufactoria]] http://esolangs.org/w/index.php?diff=39423&oldid=39422 * Quincunx * (+72)
00:40:16 <HackEgo> [wiki] [[Manufactoria]] M http://esolangs.org/w/index.php?diff=39424&oldid=39423 * Quincunx * (-2) Urgh. Forgot to edit category
00:41:16 -!- variable has changed nick to function.
00:58:00 -!- function has changed nick to trout.
01:09:45 -!- tswett29 has changed nick to tswett28.
01:27:48 -!- drlemon has joined.
01:34:59 -!- augur_ has joined.
01:36:08 -!- augur has quit (Ping timeout: 255 seconds).
01:46:49 <Bike> https://bugs.launchpad.net/ubuntu/+source/unity/+bug/1308572 ha ha ha ha
01:54:03 <zzo38> Tell me if this library and document is OK? http://zzo38computer.org/taillib/taillib.zip
01:55:05 -!- Vamadeus has joined.
01:55:06 -!- Vamadeus has quit (Changing host).
01:55:06 -!- Vamadeus has joined.
02:00:31 -!- nooodl__ has joined.
02:04:50 -!- nooodl_ has quit (Ping timeout: 265 seconds).
02:05:22 -!- tromp has joined.
02:07:00 <Jafet> Is that really a security bug? It assumes the attacker has physical access
02:07:35 <coppro> Jafet: yes. it gives you access to a running session
02:07:41 <oerjan> screen locking usually does assume that
02:07:44 <coppro> and the attacker may not have physical access
02:07:48 <elliott> it's almost as if lock screens are meant to protect from physical access, huh
02:08:22 <coppro> you can have physical access to the interface devices without having physical access to the actual computer
02:09:09 <elliott> what are you talking about it's not as if tons of publicly-accessible devices use computers underneath!!
02:09:12 <Bike> like what if the computer is on mars and i have access to the voyager probe
02:09:37 <Bike> seeing windows errors on atms or whatever is always a bit odd
02:09:58 <Jafet> I thought linux desktops had screen lockers because windows did the same thing and people have come to expect them
02:10:35 <Jafet> It's not like desktop distros have any security anyway
02:10:59 <elliott> you do it all the time and you know you're doing it
02:11:19 <zzo38> Jafet: Security can still be have for programs to access other programs, even if the user with physical access is allowed to do everything.
02:11:34 <elliott> like less than half the things you say are sincere rather than just bait to let you be incredulous at people
02:12:27 <zzo38> Installing Windows or Linux on such a computers as ATM or whatever can have problem and should not be done. If you need an operating system at all, you can install DOS or whatever
02:12:37 -!- nisstyre has joined.
02:12:53 <zzo38> DOS is much faster than Linux and Windows.
02:15:03 <Bike> withdrawing money at a million dollars an hour
02:19:29 -!- Deewiant has quit (Ping timeout: 252 seconds).
02:29:06 <HackEgo> jotcoin isangcoin birdcoin withis=thagcoin eftatecoin tlfecoin xochicksonideutunaperetunadowelseptaterpardottercoin 242150coin padsomcoin isepolistcoin celecoincoin checoin reversitecoin weakcoin xtccoin carinheacoin skulacoin fracoin cluncoin avowlcoin
02:29:16 <kmc> zzo38: you should write a bitcoin miner for DOS
02:29:56 -!- Vamadeus has quit (Ping timeout: 252 seconds).
02:32:40 <oerjan> dos runs so badly on asics
02:32:59 <kmc> depends which kind
02:34:09 <zzo38> But not all ASICs are designed to run all computer programs.
02:37:30 <oerjan> psst, i'm making a joke on the fact that bitcoin mining on cpus isn't profitable hth
02:40:05 <Bike> there should be a computer made of superconducting materials so you never have to power it
02:41:32 <oerjan> Bike: needs to do reversible computing by landauer's principle
02:41:44 <Bike> xactly, i'll just make some fredkin gates and call it good
02:41:54 <oerjan> elliott: which is why i didn't say gpus DUH
02:42:09 <oerjan> (i read somewhere that even the asic miners are losing money though)
02:42:32 <Bike> i wonder if you could do it so that it only hit resistors on a successful output
02:42:53 <Bike> then all you'd be spending is time. and coolant
02:44:29 <shachaf> whoa, so many global hashes per second
02:45:22 -!- Vamadeus has joined.
02:45:23 -!- Vamadeus has quit (Changing host).
02:45:23 -!- Vamadeus has joined.
02:45:49 <tswett28> So all the Bitcoin miners in the world could brute force 56-bit encryption about once per second in total.
02:46:43 <tswett28> Assuming their ASICs aren't application-specific.
02:47:03 <tswett28> So if you had all that computing power at your disposal, then in 600 seconds, you could either break 600 56-bit encryption doodies, or earn $460.
02:47:27 <Jafet> "Application-specific integrated circuit"
02:47:47 -!- tswett28 has quit (Quit: KVIrc 4.2.0 Equilibrium http://www.kvirc.net/).
02:48:53 <lambdabot> (Field4 s t a1 b, Functor f) => Getting a ((a1 -> f b) -> s -> f t) a -> a
02:49:55 <lambdabot> Could not deduce (Control.Lens.Tuple.Field4 [t0] [t0] a a)
02:49:55 <lambdabot> arising from the ambiguity check for ‘e_1134’
02:49:55 <lambdabot> from the context (Control.Lens.Tuple.Field4 [t] [t] a a,
02:50:20 <oerjan> > (1,2,"many",1/0)^._4
02:51:23 <oerjan> type Getting r s a = (a -> Const r a) -> s -> Const r s hth
02:52:38 <Bike> stupid commands
02:52:39 <lambdabot> Source not found. Abort, Retry, Panic?
02:53:11 <oerjan> newtype Const a b = Const a or thereabouts
02:53:46 <Bike> makes no sense to me
02:54:35 <oerjan> well that Getting type matches a lens if you use Const r as the functor
02:55:17 <oerjan> which is what you do to "get" the value of the lens field
02:56:33 <zzo38> I have once independently implemented a very restrictive kind of lenses before I knew what "lens" meant. But, now I know it better.
02:58:01 <zzo38> Which could not use two types.
03:03:40 <Sgeo> Is there any reason I couldn't have pure effectively return a lazy value that gets a real result once the type is known by a different mechanism?
03:04:01 <Sgeo> 'hey, this value is pure of some unknown applicative, when I find out, I'll turn into something useful'
03:04:47 <shachaf> that is how type classes work
03:05:18 <Sgeo> I was hoping to not have to significantly fake type classes
03:05:24 <Sgeo> I didn't have to do much for Functor
03:07:38 <Bike> you don't want to have to fake type classes to implement a type class?
03:07:48 <shachaf> sounds like a question for #racket or #rebol or #ada or #sgeolanguage
03:09:07 <Sgeo> Bike: trying to find the balance between translating an idea that works very well in one language and avoiding blind copying that ignores the value that the destination language provides
03:09:37 <oerjan> > imapped %@~ replicate $ ['a'..'z']
03:09:38 <lambdabot> ["","b","cc","ddd","eeee","fffff","gggggg","hhhhhhh","iiiiiiii","jjjjjjjjj",...
03:10:00 <Bike> it's just, functor only has the one method, so you only need to worry about the one function and don't have to coordinate anything
03:10:17 <shachaf> > imap replicate ['a'..'z']
03:10:18 <lambdabot> ["","b","cc","ddd","eeee","fffff","gggggg","hhhhhhh","iiiiiiii","jjjjjjjjj",...
03:10:54 <Bike> so... of course that won't be adequate for applicative, which has two.
03:11:12 <shachaf> imap is a v. popular email protocol
03:11:36 <Sgeo> It's not so much a matter of Applicative having two methods, as to the fact that one of those methods puts an applicative value in a positive position without having one in a negative position
03:11:37 <oerjan> shachaf: NOT INSCRUTABLE ENOUGH HTH
03:11:37 <lambdabot> FunctorWithIndex i f => (i -> a -> b) -> f a -> f b
03:11:44 <Sgeo> (is that the right terminology)?
03:11:53 <Bike> oh fuck off, i have enough problems with signs in electrochemistry
03:11:53 <Sgeo> I like to think of Applicative as being just one method, lift
03:11:55 <shachaf> Bike: imo that type is fairly legible, isn't it?
03:12:04 <Bike> i'm not the guy to ask.
03:12:09 <shachaf> Bike: adjunctions are the worst btw
03:12:28 <shachaf> and/or category theory in general
03:12:32 <Sgeo> Bike: Applicative's pure can create an (Applicative f) => f a without access to an f anything
03:12:37 <shachaf> it's like someone invented a math whose whole purpose was to make it as easy as possible to make sign errors
03:12:40 <Bike> yeah, i figured that out
03:12:50 <Bike> "positive" and "negative" is a weird way to put it
03:13:10 <Sgeo> (lift somefunc a1 a2 a3) is fine, (lift somefunc a1) fine, (lift somefunc) err
03:13:15 <Bike> but i remember i used to not understand those sorts of types. thankfully, i'm a haskell god now
03:13:17 <Sgeo> Bike: I could swear I've seen it somewhere
03:13:54 <Bike> it seems to me that values like that are only easy to deal with because of type inference, so...
03:14:37 <shachaf> oerjan: you should join #-lens
03:15:23 <Sgeo> I think positive/negative makes sense... ((a -> b) -> c), the a is in negative position relative to the (a -> b), the (a -> b) is in negative position relative to the whole function, so - * - = +, a is in positive position relative to the whole function, which needs to produce an a at some point
03:15:31 <Sgeo> Or, maybe not 'needs'
03:15:37 <Sgeo> But it doesn't consume an aa
03:15:44 <Bike> no, look, fuck you, cathode/anode is already too much
03:16:14 <shachaf> you know how (a -> b) is like (¬a | b)?
03:17:26 <Sgeo> I can't tell if that's interesting or a joke
03:18:02 -!- maurer has quit (Read error: Operation timed out).
03:18:12 -!- maurer has joined.
03:18:43 <Bike> math is all about acting like stupid jokes are interesting. umbral calculus
03:34:53 <int-e> umbral calculus leave you in the dark :P
04:02:52 <zzo38> shachaf: But Haskell types are intuitionistic logic rather than being classical logic (but, you can use continuation transform to make classical logic out of intuitionistic logic, too)
04:03:15 <shachaf> zzo38: hence "except in haskell"
04:16:51 <zzo38> But Haskell isn't the only thing that it is
04:18:27 <zzo38> Intuitionistic logic is still a kind of a logical system, and so is linear logic, and classical logic.
04:19:25 <Bike> is Tetra Master a logical system
04:21:32 <zzo38> \f -> either (Left . f) Right <$> lemCC
04:22:22 <Bike> i'm not sure that answers my question
04:22:32 <zzo38> For f in Kleisli category: \f -> fmap (f >=>) <$> lemCC
04:22:55 <zzo38> Bike: I am not answering your question I am answering shachaf's question.
04:23:08 <fowl> Bike, yes, tetris logic
04:23:14 <fowl> turn the blocks
04:25:58 <zzo38> shachaf: I mean, I answered your answer.
04:28:40 <zzo38> In case you don't know what lemCC means, then I can tell you: lemCC = callCC (return . Right . (<=< return . Left)); or lemCC = ContT $ \c -> c $ Right (\a -> ContT $ \_ -> c (Left a)); or callCC x = lemCC >>= either return x;
04:29:39 <zzo38> In other words, "except in Haskell" isn't quite right, because if you are using continuations then it is right.
04:29:40 <shachaf> the real question is what Stanisław Lem thinks of continuations
04:30:40 <zzo38> I don't know, but in this case "lem" is short for "law of excluded middle".
04:30:42 -!- kronion_ has joined.
04:30:43 <Bike> pirx continuated pretty far
04:31:09 -!- kronion_ has quit (Max SendQ exceeded).
04:31:12 <zzo38> (I also don't know who Stanislaw Len is)
04:31:45 -!- kronion_ has joined.
04:33:12 <zzo38> Law of excluded middle continuations might be a bit easier than call/cc for some people, possibly.
04:35:07 <oerjan> zzo38: famous polish scifi author
04:35:23 <zzo38> O, that's who it is.
04:36:00 <HackEgo> [U+0074 LATIN SMALL LETTER T] [U+0335 COMBINING SHORT STROKE OVERLAY]
04:37:17 <Sgeo> I'm having some difficulty with figuring out how to use LastPass
04:44:57 <HackEgo> [wiki] [[User:Quincunx]] M http://esolangs.org/w/index.php?diff=39425&oldid=39405 * Oerjan * (+0) /* Circuit Diagram 10 */ sp.
04:46:53 <HackEgo> [wiki] [[Trainscript]] M http://esolangs.org/w/index.php?diff=39426&oldid=39404 * Oerjan * (+5) sp link
04:48:21 -!- Sorella has quit (Quit: It is tiem!).
04:49:48 -!- adu has joined.
04:57:02 -!- kallisti_ has joined.
04:59:55 -!- kallisti has quit (Ping timeout: 252 seconds).
05:02:15 -!- Vamadeus has quit (Remote host closed the connection).
05:04:02 -!- tswett has quit (Ping timeout: 255 seconds).
05:22:12 -!- nooodl__ has quit (Quit: Ik ga weg).
05:25:14 -!- tromp has quit (Remote host closed the connection).
05:25:50 -!- tromp has joined.
05:29:59 -!- tromp has quit (Ping timeout: 252 seconds).
06:01:54 -!- adu has quit (Quit: adu).
06:12:00 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:13:06 -!- oerjan has quit (Quit: leaving).
06:26:46 -!- kallisti has joined.
06:29:45 -!- kallisti_ has quit (Ping timeout: 252 seconds).
06:40:16 -!- kallisti_ has joined.
06:43:20 -!- kallisti has quit (Ping timeout: 252 seconds).
06:45:09 -!- tertu has quit (Ping timeout: 252 seconds).
07:04:29 -!- Slereah_ has joined.
07:13:02 -!- kallisti has joined.
07:16:35 -!- kallisti_ has quit (Ping timeout: 265 seconds).
07:40:01 <mroman> What again was the criteria for using Chans vs. MVar?
07:53:34 -!- kallisti_ has joined.
07:55:56 -!- kallisti has quit (Ping timeout: 255 seconds).
08:24:17 -!- Patashu_ has quit (Ping timeout: 264 seconds).
08:29:46 -!- MindlessDrone has joined.
08:49:24 -!- MoALTz has joined.
08:56:33 -!- Phantom_Hoover has joined.
09:00:04 -!- augur has joined.
09:01:05 -!- augur__ has joined.
09:03:37 -!- augur_ has quit (Ping timeout: 276 seconds).
09:05:33 -!- augur has quit (Ping timeout: 276 seconds).
09:20:01 <HackEgo> [wiki] [[User:Quincunx]] http://esolangs.org/w/index.php?diff=39427&oldid=39425 * Quincunx * (+1307) /* Roguelike */
09:28:11 -!- mhi^ has joined.
09:28:18 -!- augur__ has changed nick to augur.
09:48:57 -!- carado has joined.
10:11:45 -!- Patashu has joined.
10:13:00 -!- Patashu has changed nick to Patashu-.
10:13:02 -!- Patashu- has changed nick to Patashu_.
10:14:44 -!- Patashu_ has quit (Client Quit).
10:23:01 -!- Slereah_ has changed nick to Slereah.
10:24:09 -!- yorick has joined.
10:29:24 -!- Patashu has joined.
10:46:36 -!- conehead has quit (Quit: Computer has gone to sleep).
10:55:57 -!- KingOfKarlsruhe has joined.
11:57:52 -!- carado has quit (Quit: Leaving).
11:57:59 -!- nooodl has joined.
12:08:37 -!- carado has joined.
12:16:48 -!- nooodl has quit (Ping timeout: 240 seconds).
12:30:40 -!- nucular has joined.
12:30:40 -!- nucular has quit (Changing host).
12:30:41 -!- nucular has joined.
12:30:50 <Taneb> int-e, can you quickly put lambdabot in #cs-york again?
12:39:32 <int-e> this keeps comingup. do you want to have it there permanently?
12:44:50 <Taneb> No, it's a controversial bot in the channel
12:52:58 -!- carado has quit (Quit: Leaving).
12:53:39 -!- Vamadeus has joined.
12:53:39 -!- Vamadeus has quit (Changing host).
12:53:39 -!- Vamadeus has joined.
13:01:01 -!- kronion_ has quit (Remote host closed the connection).
13:01:41 -!- kronion has joined.
13:02:03 -!- kronion has quit (Remote host closed the connection).
13:02:15 <int-e> Pah. x86_64 has tagged TLBs but they are being wasted on hypervisor support. Boring.
13:04:11 <int-e> (Presumably they added tags because otherwise nested page tables would become ridiculously expensive.)
13:12:10 -!- kronion has joined.
13:35:18 -!- Slereah has quit (Ping timeout: 276 seconds).
13:39:22 -!- Slereah has joined.
14:17:40 -!- tromp has joined.
14:26:39 -!- Patashu has quit (Ping timeout: 276 seconds).
14:40:16 -!- boily has joined.
14:41:19 <zzo38> Is it possible to program lambdabot so that it can be invited and kicked? So that, you don't have to keep asking them
15:09:28 -!- Sorella has joined.
15:25:45 <Taneb> I don't have op in that channel
15:47:07 -!- kronion has quit (Quit: Textual IRC Client: www.textualapp.com).
15:54:02 <b_jonas> zzo38: I tried to make an experimental bot of mine do that once: when you invite it, it joins. there doesn't need to be much special handling for kicking though.
15:56:28 <b_jonas> zzo38: do you know of something like a balanced search tree automatically maintained by sql triggers? like, if I add a row to a particular table, triggers will add a node to the search tree representing that row, and that search tree is stored in the same database.
15:56:40 <b_jonas> I asked here earlier and someone's referred me to you.
15:59:10 <zzo38> b_jonas: I don't know of any such thing, although it may be possible. If you want to search in a SQL database, though, you should probably create an index for that purpose. (Creating a search tree may be useful if you want to convert the data into other formats, possibly, though)
16:00:30 <zzo38> What is it you are trying to make, though?
16:00:33 <b_jonas> zzo38: sure, normally you'd use an sql index, which is part of why I'm asking on this channel,
16:00:56 <b_jonas> but I was wondering about something that could be implemented by the database as a sort of index but I haven't yet seen any database engine implement it yet
16:02:02 <b_jonas> even then, a search tree (I was thinking a treap might be the easiest) maintained using triggers might not be the best way.
16:02:10 <zzo38> I myself use SQLite, which now supports recursive WITH clauses. A statement in a trigger is not allowed to start with a WITH clause, though (it can still be used in subqueries and so on).
16:02:24 <zzo38> But still, I don't know what it is you are trying to make.
16:02:44 <b_jonas> Yes, I was thinking about this, and I think it's probably possible to implement in sqlite, but it's very difficult.
16:03:08 <b_jonas> (I'm not sure whether it's possible without a recursive WITH clause.)
16:03:41 <b_jonas> (I mean, it probably is if you use complicated recursive triggers with arbitrarily deep recursion to simulate function calls, but that'd be crazy.)
16:05:04 <b_jonas> It might be possible to do it without recursion if you cheat by using ordinary indexes on the tables storing the tree to find nodes.
16:05:46 <zzo38> O, I always use recursive triggers with deep recursion to simulate function calls (and similar things which do not correspond quite with function calls of most programming languages).
16:05:48 <b_jonas> I mean, if you don't want a balanced search tree, just a search tree, then you can have an index on the tree table to find the node you have to insert under rightaway.
16:06:32 <b_jonas> zzo38: just triggers calling each other to simulate function calls is ok, what I would like to avoid is arbitrarily deep (log tree size deep) recursion that way.
16:07:45 <zzo38> Why do you need a balanced search tree though?
16:08:32 <b_jonas> I don't really need it, mind you, just wondering on it.
16:09:12 <b_jonas> I was thinking of an index that can optimize queries like SELECT min(t.w) FROM t WHERE t.k BETWEEN ? AND ?;
16:09:58 <b_jonas> where min could be any aggregate that is a fold of an associative operation, such as count, min, max, total, sum (ignoring integer overflows)
16:10:13 <zzo38> SQLite has extensions to do that already, including multidimensional search.
16:10:30 <b_jonas> by building a search tree that stores in each node min(t.w) of all descendants of that node
16:11:24 <b_jonas> so if you had a hypotehtical index on t.k covering min(t.w), you could execute such a query in log(count of all rows) time
16:11:59 <b_jonas> because you would just have to add the stored min(w) values in O(log(count of all rows)) nodes in the index
16:12:17 <b_jonas> and the index could be maintained quickly too, as quickly as any search tree based index
16:13:50 <b_jonas> true, a multi-dimensional tree could implement SELECT min(t.w) FROM t WHERE t.k BETWEEN ? AND ?; quickly,
16:14:19 <b_jonas> so maybe SELECT sum(t.w) FROM t WHERE t.k BETWEEN ? AND ?; would be a better example
16:15:27 <b_jonas> imagine that t is changing between queries, otherwise this could be solved easier
16:17:02 <b_jonas> mind you, I don't really have an application for such queries on a dynamically changing table either
16:19:04 -!- tswett has joined.
16:19:04 -!- tswett has quit (Changing host).
16:19:05 -!- tswett has joined.
16:20:58 <zzo38> It doesn't seem to useful to me to make a search tree like that unless you need to convert data into another format. Normally I would think you would just use an ordinary index, or if necessary to do so, use a R*Tree index.
16:22:10 <zzo38> But you can try to implement a balance search tree in SQL if you want to!
16:22:49 -!- kronion has joined.
16:23:12 -!- kronion has quit (Max SendQ exceeded).
16:39:38 -!- zzo38 has quit (Remote host closed the connection).
16:40:34 -!- JLG has joined.
16:41:40 -!- JLG has quit (Client Quit).
16:42:13 <HackEgo> [wiki] [[Circute]] M http://esolangs.org/w/index.php?diff=39428&oldid=20063 * Smjg * (-4) /* External resources */ upd8 link
17:52:32 -!- Slereah has quit.
18:00:03 -!- kronion_ has joined.
18:06:31 -!- drdanmaku has joined.
18:08:16 -!- kronion_ has quit (Quit: Textual IRC Client: www.textualapp.com).
18:08:55 -!- tromp has quit (Remote host closed the connection).
18:09:29 -!- tromp has joined.
18:13:47 -!- tromp has quit (Ping timeout: 255 seconds).
18:18:03 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:19:38 -!- Phantom_Hoover has left ("Leaving").
18:19:46 -!- Phantom_Hoover has joined.
18:24:13 -!- Slereah_ has joined.
18:39:12 -!- nucular has quit (Quit: Switching to phone).
18:44:24 <Sgeo> How did this website end up so badly done that the images are links to the images? http://logicoin.info/
18:52:36 <mroman> Is it "Hey, I make my own coin" time?
18:52:52 <HackEgo> Argument "#" isn't numeric in int at /hackenv/bin/words line 148. \ coin
18:52:57 <HackEgo> purecoin festiconcoin gularioplincoin thulzacoin discoin limcoin thumamcoin wingcoin mulacoin xingcoin praocoin udatempovacifucoin haibocoin mumothcoin divzcoin partreacoin unbartrelcoin whenservicoin stackcoin kipcoin
18:53:29 <HackEgo> advendocoin ammcoin rincoin gechtcoin pancoin bjectdispcoin nasscoin consomskjcoin modecoin folercoin exjcoin twelcoin memporcoin wpbroketlancoin triicoin prorrelucoin olutecoin subicoin aggedcoin oorcoin
18:53:51 <mroman> wpbroketlancoin sounds good
18:54:57 -!- KingOfKarlsruhe1 has joined.
18:55:36 -!- KingOfKarlsruhe has quit (Ping timeout: 240 seconds).
18:55:59 -!- KingOfKarlsruhe1 has changed nick to KingOfKarlsruhe.
18:56:07 -!- KingOfKarlsruhe has quit (Changing host).
18:56:08 -!- KingOfKarlsruhe has joined.
18:57:13 <mroman> because who want's a bit when you can have a gigabit
18:57:58 -!- impomatic has joined.
19:01:55 -!- boily has quit (Quit: WeeChat 0.4.2).
19:03:13 <Taneb> I am perpetually tempted to make a gold-backed cryptocurrency
19:03:42 <HackEgo> [wiki] [[Symbols]] http://esolangs.org/w/index.php?diff=39429&oldid=37964 * 50.166.86.223 * (-49)
19:03:57 <Slereah_> Taneb : I think that might be complicated legally
19:04:23 <Taneb> Well, for a start I do not own all that much gold
19:04:44 <Bike> to buy this cocaine you just need to give me a hash of the atomic microstate of your bullion
19:05:01 <Slereah_> But it will change if you heat it :o
19:05:10 <Slereah_> Or leave it alone for a nanosecond, really
19:05:46 <Bike> wealth is fleeting, son
19:13:26 -!- conehead has joined.
19:18:32 -!- Sorella has quit (Remote host closed the connection).
19:24:12 -!- ^v has joined.
19:28:12 -!- Sorella has joined.
19:43:56 -!- ^v has quit (Ping timeout: 252 seconds).
19:57:30 -!- nooodl has joined.
19:58:18 -!- KingOfKarlsruhe has left.
20:44:23 -!- nooodl has quit (Remote host closed the connection).
20:46:08 -!- nooodl has joined.
21:01:22 -!- Patashu has joined.
21:12:34 -!- tromp has joined.
21:13:50 -!- TodPunk has quit (Read error: Connection reset by peer).
21:13:50 -!- Tod-Autojoined has joined.
21:17:05 -!- tromp has quit (Ping timeout: 252 seconds).
21:17:34 <fizzie> In other words, the em dash, the two-em dash and the three-em dash.
21:17:58 <fizzie> No four-em dash in Unicode. :/
21:19:53 -!- kwertii has joined.
21:19:57 <fizzie> And the LEFTWARDS TWO-HEADED TRIPLE DASH ARROW.
21:20:03 <fizzie> (I was looking at things with "DASH" in the name.)
21:21:31 <HackEgo> U+2E3B THREE-EM DASH \ UTF-8: e2 b8 bb UTF-16BE: 2e3b Decimal: ⸻ \ ⸻ \ Category: Pd (Punctuation, Dash) \ Bidi: ON (Other Neutrals)
21:21:40 <Taneb> `unicode INVISIBLE TIMES
21:22:25 <fizzie> There's also btoh the WAVE DASH (〜) and the WAVY DASH (〰).
21:23:18 <Slereah_> There is a symbol for k and for the k of kelvins
21:24:08 -!- Patashu has quit (Ping timeout: 255 seconds).
21:25:31 <fizzie> There's a FACE SAVOURING DELICIOUS FOOD (U+1F60B), it probably goes well with POT OF FOOD (U+1F372).
21:25:51 <fizzie> Apparently delicious food is the only thing you can savour.
21:26:48 <olsner> I think savouring implies enjoying, so deliciousness may also be implied
21:29:02 <Taneb> `unicode FACE SAVOURING DELICIOUS FOOD
21:29:02 <HackEgo> U+1F60B FACE SAVOURING DELICIOUS FOOD \ UTF-8: f0 9f 98 8b UTF-16BE: d83dde0b Decimal: 😋 \ 😋 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
21:47:24 <fizzie> For me it "works" (it's not terribly savour-y) in browser but not in terminal.
21:59:38 -!- impomatic has quit (Ping timeout: 265 seconds).
22:06:55 -!- tertu has joined.
22:07:52 -!- HackEgo has quit (Remote host closed the connection).
22:27:35 -!- HackEgo has joined.
22:33:27 -!- oerjan has joined.
22:35:22 <Bike> http://www.beige-box.com/libressl/ project is going well
22:42:46 <oerjan> <mroman> What again was the criteria for using Chans vs. MVar? <-- an MVar contains just one value, a Chan a FIFO queue of them...
22:43:03 <oerjan> @tell mroman <mroman> What again was the criteria for using Chans vs. MVar? <-- an MVar contains just one value, a Chan a FIFO queue of them...
22:43:17 <Sgeo> aww, the embed doesn't work
22:43:24 <oerjan> i need to do something about this race condition between @tell'ing and /whois'ing
22:43:25 <Sgeo> It's playing ... either the mp3 or ogg, I think
22:44:09 <Sgeo> The mp3, based on that's what my browser decided to download
22:58:06 <HackEgo> [U+005C REVERSE SOLIDUS] [U+0030 DIGIT ZERO]
23:03:24 -!- MoALTz has quit (Quit: bbl).
23:18:56 -!- tromp has joined.
23:21:08 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
23:23:41 -!- tromp has quit (Ping timeout: 264 seconds).
23:24:43 -!- yorick has quit (Remote host closed the connection).
23:28:00 -!- tertu has quit (Ping timeout: 240 seconds).
23:29:21 -!- Sprocklem has quit (Quit: Lost terminal).
23:29:51 -!- kwertii has quit (Quit: kwertii).
23:39:15 -!- Sprocklem has joined.
23:41:09 -!- mhi^ has quit (Quit: Lost terminal).
23:45:25 -!- ^v has joined.
23:55:18 -!- nooodl has quit (Quit: Leaving).
23:56:33 -!- zzo38 has joined.
00:00:09 -!- tromp has joined.
00:02:36 -!- ^v has quit (Read error: Connection reset by peer).
00:02:53 -!- ^v has joined.
00:05:57 -!- not^v has joined.
00:06:19 -!- ^v has quit (Read error: Connection reset by peer).
00:31:32 -!- nisstyre has joined.
00:37:06 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
01:04:07 <zzo38> I have idea: data Program = Halt Expression | Continue | Assign Expression Expression Program | While Expression Program Program; data Expression = Zero | Successor Expression | Dereference Expression | With Expression Expression | Call Program | Oracle Program;
01:05:11 <zzo38> If you have such halting oracle, what is the powerfulness?
01:05:36 -!- Vamadeus has quit (Ping timeout: 240 seconds).
01:07:33 <oerjan> zzo38: about like brainhype, i think
01:10:07 <FreeFull> zzo38: Then you have to worry about metahalting
01:10:16 <zzo38> What would be the powerfulness of proofs in such a system (where the halting oracle is still part of the system, and programs that halt are theorems)?
01:10:23 <zzo38> FreeFull: What is metahalting?
01:11:24 <Taneb> What ever happened to itidus20
01:11:43 <Bike> couldn't escape the matrix of [reference] [sarcastic sad emoticon]
01:12:43 <FreeFull> zzo38: It can figure out if any Turing machine will halt, but can't determine if it will halt itself
01:13:28 <pikhq> zzo38: Basically, for any superset-of-Turing system, the union of that + the halting oracle for it cannot determine if it *itself* halts.
01:13:48 <pikhq> So, Turing machine with a halting oracle has its own halting problem.
01:14:26 <Bike> you'll get, what's it called, post degrees
01:14:50 <zzo38> pikhq: Yes, although it might be paradox if it can, isn't it?
01:15:30 <pikhq> The proof that you can't determine if a Turing machine halts with a Turing machine is trivially generalizable to any super-Turing machine.
01:16:39 <zzo38> You can still determine if such a thing halts with a higher oracle, though, I think
01:16:46 <HackEgo> 897) <shachaf> Taneb: STOP TRYING TO GET LENS INTO EVERYTHING <shachaf> Bike: You should use lens! <Taneb> NEVER <Bike> shachaf: i'm getting mixed messages here
01:17:00 <Taneb> shachaf, you will be glad that today I told someone not to use lens.
01:17:08 <pikhq> It's just that each individual such system would need an oracle to determine if it halts.
01:20:01 <shachaf> Taneb: when will i be glad about that?
01:20:11 <shachaf> wait, not glad about that. just glad that.
01:21:19 <Taneb> Because I did not try to get lens into his Hakyll site!
01:21:30 <zzo38> But it can be nested such as Halt (Oracle (While (Oracle x) Continue (Halt Zero))) meaning if it is true when halting then that makes it true when not halting, something like that anyways
01:22:02 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: uote: not found
01:22:06 <HackEgo> 1059) <Taneb> I would like to learn how to use a sword <Taneb> And also how to ride a unicycle <Taneb> Perhaps not at the same time
01:22:13 <Taneb> I have not learnt either
01:22:25 <zzo38> Can it be extended to allow an arbitrary amount if a program is reading in from the input
01:22:33 <Taneb> Although I did go to an Iaido taster session!
01:24:13 <Taneb> FreeFull, I actually have one
01:25:01 <Bike> learn you a unicycle for great good
01:26:48 <Taneb> `addquote <Bike> learn you a unicycle for great good
01:26:49 <HackEgo> 1189) <Bike> learn you a unicycle for great good
01:28:09 <Bike> important question: is there a program that, given a number, gives you a bunch of pointless facts about it, a la http://en.wikipedia.org/wiki/593_%28number%29
01:31:32 <oerjan> the proof is a simple exercise in writing a wikipedia scraper hth
01:31:42 <Bike> perhaps i need a rephrase: can you point me to a etc
01:32:37 <Bike> hm, i know a few programs to come up with an algebraic definition, i think
01:43:16 -!- BeingUntoDeath has joined.
01:46:37 -!- BeingUntoDeath has quit (Client Quit).
01:59:06 -!- tertu has joined.
02:01:36 -!- tertu has quit (Read error: Connection reset by peer).
02:01:42 -!- ter2 has joined.
02:02:19 -!- ^v has joined.
02:06:06 -!- ter2 has quit (Read error: Connection reset by peer).
02:06:32 -!- ter2 has joined.
02:08:20 -!- FreeFull has quit.
02:10:23 -!- ter2 has quit (Read error: Connection reset by peer).
02:10:46 -!- ter2 has joined.
02:23:21 -!- tertu3 has joined.
02:26:41 -!- ter2 has quit (Ping timeout: 264 seconds).
02:33:41 -!- ^v has quit (Ping timeout: 252 seconds).
02:34:14 <zzo38> In which MUD is it possible to use a zoog teeth you have stolen to learn to be dentist and make a false teeth in case other zoog don't have any more teeth?
02:38:29 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
02:38:38 -!- tertu3 has quit (Ping timeout: 252 seconds).
03:01:23 -!- tertu3 has joined.
03:07:53 <kmc> fungot: if I knew now what I knew then…
03:27:52 -!- Sorella has quit (Quit: It is tiem!).
03:35:09 <kmc> fungot: why the long lag
03:41:09 <shachaf> https://plus.google.com/+DanPiponi/posts/djyKdnSGRch dpiponi.kmc.moed++
03:48:57 -!- edwardk has quit (Quit: Computer has gone to sleep.).
03:54:01 <oerjan> fungot: are you stonewalling kmc
03:54:02 <fungot> oerjan: don't i know you from somewhere? but, i mean, t-rex?
03:57:37 <kmc> fungot: who will fungot the fungots?
03:57:37 <fungot> kmc: hey, t-rex, i've a long road ahead of me, it would be flattering. i like to look at them! i expect nothing less than...
03:58:04 <oerjan> fungot: nothing less than what?
03:58:05 <fungot> oerjan: have i, perhaps, a hint, utahraptor. i'm a cyborg, then when i enter it, my body is the other half. we join, marrying the machine and flesh, working together to ensure my own creation. i'm responsible for getting my own food and for making a bomb threat, delaying its maiden voyage!
03:58:31 <oerjan> those are important responsibilities.
03:59:50 -!- edwardk has joined.
04:02:10 -!- kronion_ has joined.
04:02:19 <kmc> read "low-friction beard"
04:02:30 -!- kronion_ has quit (Max SendQ exceeded).
04:02:59 <oerjan> (the bread almost slid off my plate when i grabbed it)
04:03:32 <oerjan> i hope the onion hasn't started spamming
04:27:18 -!- nycs has joined.
04:29:41 -!- `^_^v has quit (Ping timeout: 264 seconds).
04:50:08 <Taneb> I have been awake for faaaar too long
05:01:30 -!- Deewiant has joined.
05:03:17 -!- tswett has quit (Ping timeout: 252 seconds).
05:07:19 -!- Tod-Autojoined has changed nick to TodPunk.
05:12:46 -!- tromp has quit (Remote host closed the connection).
05:12:54 -!- Sgeo has quit (Read error: Connection reset by peer).
05:13:18 -!- tromp has joined.
05:18:01 -!- tromp has quit (Ping timeout: 265 seconds).
05:25:27 <fizzie> fungot: Stop making bomb threats, they'll trace you back to my place.
05:25:27 <fungot> fizzie: oh, that may be a fact; it is impossible to know if my dream, everything had turned into plasticine! do that and now your sweetie, turn to panel 5. forget it! it's wasted time.
05:27:35 <oerjan> and then fizzie will be toast while fungot gets away on an insanity plea
05:27:35 <fungot> oerjan: but in a metaphorical sense. what metaphor would that be, exactly?
05:27:56 <Taneb> I am going to sleep now goodnight
05:28:14 <oerjan> fungot: something cell-based.
05:28:15 <fungot> oerjan: as a man concerned, t-rex, that going shopping was your default activity? how is that weird, is it? you're just adding the same. but it's just so impossible, so doomed. he's got a stupid face, so at his own request that you give a raccoon a sugar cube, it'll wash it, i have!
05:28:17 <Taneb> Wait that isn't I away
05:28:40 <oerjan> Taneb is too tired to leave the channel
05:28:47 <fizzie> fungot: Stop calling my face stupid, too.
05:28:47 <fungot> fizzie: i don't have a very good student!
05:29:05 -!- Sgeo has joined.
05:32:36 <zzo38> Was "quit while you are ahead" invented by a gambler?
06:07:46 <zzo38> [P1] Clean your room! [C1] Therefore, clean your room or burn the house down! The error is that, "therefore, you have to either clean your room or burn the house down" is wrong, but, you can write instead, "either you have to clean your room or you have to burn the house down"
06:41:14 -!- tertu3 has quit (Ping timeout: 255 seconds).
06:46:53 -!- oerjan has quit (Quit: leaving).
07:30:57 -!- slereah has joined.
07:31:53 -!- Sprocklem has quit (Quit: leaving).
08:01:25 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:13:33 -!- HackEgo has quit (Remote host closed the connection).
08:28:25 -!- Patashu has joined.
08:34:04 -!- Patashu_ has joined.
08:34:04 -!- Patashu has quit (Disconnected by services).
08:38:47 <kmc> gotta get paid
08:40:43 <fizzie> Huh, esolangs.org went down too, and the silly thing doesn't answer to SSH either.
08:41:14 <Jafet> Does fungot have coins
08:41:14 <fungot> Jafet: it's a very tricky to sound natural, then you can't sleep at all, then you go demented and then you die, we're giving dinosaur comics to the marmaduke guy. sincerely, the man, you just wait! kids will be boarding the train to scarytowne at my own pace, dromiceiomimus
08:42:02 <Jafet> Is fungot less volatile than btc
08:42:02 <fungot> Jafet: i think that you're being too strict about this, t-rex! geez!! i'm leaving. escape to panel 5. forget it! it's wasted time. prepare to lose your job for gibbering madness all the time!
08:42:20 <fizzie> You can pay your fungot usage with funcoins.
08:42:20 <fungot> fizzie: are you in this house, god? i am a different, but i assure you
08:42:49 <Jafet> I think fungot just fired me
08:42:49 <fungot> Jafet: oh, i must have put that in your pipe and smoke it? friday? is it friday? or is it..."
08:44:01 <fizzie> --- www2.codu.org ping statistics ---
08:44:02 <fizzie> 42 packets transmitted, 11 received, 73% packet loss, time 42027ms
08:45:03 <lexande> fungot: did you say something about a train?
08:45:03 <fungot> lexande: think of how far did you go" talk a lot, but they're always a good thing! stupid problems, but if they're sentient, and you shouldn't think about religion that hard
08:46:09 <Jafet> I don't think religion is ready for sentient trains
08:46:13 <lexande> pretty much as far as i could, on a train, but i never reached scarytowne
08:59:46 -!- HackEgo has joined.
09:01:13 -!- impomatic has joined.
09:08:35 -!- MindlessDrone has joined.
10:09:50 -!- boily has joined.
10:18:39 -!- conehead has quit (Quit: Computer has gone to sleep).
10:51:30 -!- boily has quit (Quit: Poulet!).
11:28:17 <Taneb> @ask How awkward it be to make lambdabot not respond to > in #cs-york? That's the only real controversy about the bot in the channel
11:28:33 <Taneb> @ask int-e How awkward it be to make lambdabot not respond to > in #cs-york? That's the only real controversy about the bot in the channel
11:29:05 -!- ais523 has joined.
11:29:56 -!- How has joined.
11:30:04 <How> @messages-loud
11:30:04 <lambdabot> Taneb asked 1m 46s ago: awkward it be to make lambdabot not respond to > in #cs-york? That's the only real controversy about the bot in the channel
11:30:11 -!- How has quit (Client Quit).
11:30:35 <fizzie> Doing our part to keep things tidy.
11:33:37 <Jafet> @ask d41d8cd98f00b204e9800998ecf8427e hi
11:34:40 <fizzie> That's too long to even change nick to. :(
11:41:47 <ais523> huh, Knuth did a few bugfixes to TeX again; apparently he said in 2008 that he would next look at TeX starting on 31 December 2013, and kept to his word
11:42:24 <slereah> Maybe he thought that the world would end in 2012
11:42:45 <ais523> no, he follows a geometric series for bugfixing TeX
11:42:56 <ais523> each review of bugs takes one more year than the last
11:43:03 <ais523> he fixed exactly one bug this time
11:43:57 <ais523> both of which are incredibly minor (a missing space in a corner case that probably never comes up in practice, and a memory leak that leaks 7 words of memory)
11:44:47 <ais523> also apparently the computer he tested the memory leak on has "3 million words" of memory, which for any sensible word size, puts it in the low tens of megabytes or perhaps even lower
11:46:13 -!- nucular has joined.
11:46:13 -!- nucular has quit (Changing host).
11:46:13 -!- nucular has joined.
11:46:28 <ais523> <Knuth> These files contain almost exactly 7 megabytes altogether; and the new changes have altered about 3500 of those bytes.
11:46:31 <b_jonas> ais523: not geometric. I think it's quadratic only.
11:46:49 <ais523> sorry, not really thinking today
11:47:48 <Jafet> If it's truly a series, Knuth will be around to fix TeX bugs forever
11:48:00 <Jafet> I don't know whether that is supposed to be a comforting thought
11:48:26 <fizzie> Does this mean the version number gained a digit?
11:48:52 <b_jonas> Jafet: he has a specific statement: "My last will and testament for TeX and METAFONT is that their version numbers ultimately become $\pi$ and $e$, respectively. At that point they will be completely error-free by definition."
11:49:41 <ais523> also, apparently the only regret Knuth has about TeX's original design is that the default rule thickness is 0.399993896484375 points rather than 0.4 points
11:49:49 <ais523> due to the use of binary rather than decimal fractions
11:50:11 <b_jonas> no way, where does he say that?
11:50:45 <ais523> near the end of the document
11:50:52 <Jafet> > 1 - toRational (0.4 :: Float) / (4 % 10) :: CReal
11:50:53 <lambdabot> Couldn't match type ‘GHC.Real.Ratio GHC.Integer.Type.Integer’
11:50:53 <lambdabot> Expected type: Data.Number.CReal.CReal
11:50:53 <lambdabot> Actual type: GHC.Real.RationalCouldn't match expected type ‘Data.Number.CR...
11:50:53 <lambdabot> with actual type ‘GHC.Real.Ratio a0’
11:51:03 <Jafet> > fromRational $ 1 - toRational (0.4 :: Float) / (4 % 10) :: CReal
11:51:37 <fizzie> > toRational 0.399993896484375
11:52:03 <ais523> b_jonas: his report on the bugfixes
11:52:10 <ais523> http://tug.org/TUGboat/tb35-1/tb109knut.pdf
11:53:22 <b_jonas> ais523: 2014? but http://www-cs-faculty.stanford.edu/~uno/abcde.html says the TeX updates "happened most recently in 1992, 1993, 1995, 1998, 2002, 2007, and 2013; following this pattern, I intend to check on purported bugs again in the years 2020, 2028, 2037, etc."
11:53:40 <ais523> b_jonas: 31 December 2013 is when he started working on it
11:53:44 <ais523> he didn't get it finished in a day
11:56:27 <ais523> <Knuth, on 14 Mar 1978> (Some day we will have personal computers and will live more normally.)
11:58:58 <ais523> the "abnormal living" was sleeping at odd times of day in order to use the timeshare system when it was less loaded
11:59:19 <ais523> I live nowadays, and have a personal computer, but still sleep at odd times of day
11:59:49 <Jafet> Ah. I thought they had multiuser terminals already in 1978.
12:00:08 <ais523> I think probably they did, but everything was running on one central server
12:00:31 <fizzie> ais523: In the document, he also mentions "my home computer (a 3.6 GHz Xeon with 10 MB cache)" in the part where the build time of the TeXbook is discussed.
12:00:46 <fizzie> ais523: I'm not sure how this works with the three million words of memory.
12:00:58 <ais523> it might have been running on a VM or something?
12:01:15 <Jafet> Maybe his code runs completely in cache.
12:01:22 <fizzie> Possibly. And of course "home computer" and "home system" might refer to different things.
12:01:27 <Jafet> I would not be that surprised
12:02:00 <ais523> also, I was vaguely surprised that TeX gets an extra digit on the version number, rather than increasing the last digit by 1 or adding another digit if that would exceed pi
12:02:17 <ais523> like, I was expecting 3.1, 3.11, 3.12, 3.13, 3.14, 3.141, 3.1411, 3.1412, etc.
12:02:21 <ais523> that also converges to pi, just more slowly
12:02:39 <Jafet> "the systems [TeX and Metafont] have been converging to an error-free state."
12:03:16 <fizzie> And if you get right down to it, "it did take quite awhile to overflow 3 million words of memory on my home system" doesn't necessarily imply the system has only 3 million words, just that three million words is some limit that can be overflowed.
12:03:55 <ais523> actually, the other thing that surprised me is that there's a logic bomb in the manual to prevent people compiling it
12:04:25 <ais523> I guess because it's TeX not LaTeX, that makes sense
12:04:45 <ais523> (in LaTeX, some people might find it easier to read in a different document class, so allowing them to recompile rather than using a precompiled version would be reasonable)
12:06:41 <Jafet> Maybe they don't want people to compile it.
12:06:47 <Jafet> "The source file texbook.tex for The TeXbook begins with the following lines: [...] % The file is distributed only for people to see its examples of TeX input, not for use in the preparation of books like The TeXbook."
12:07:20 <ais523> he didn't want people to make other books based on the formatting in that book
12:07:38 <ais523> that's different from compiling the book itself from source, though
12:08:14 <Melvar> I would like to note that the English Wikipedia has articles named “Pi” and “e (mathematical constant)”, while the corresponding German ones are named “Kreiszahl” and “Eulersche Zahl”.
12:08:26 <Jafet> Well, it is also a book you can buy from Addison-Wesley.
12:09:12 <Jafet> Kreiszahl sounds like an article about number rings
12:09:35 <fizzie> "Pii (vakio)", "Neperin luku".
12:10:00 <Melvar> Jafet: It is, however, about the Circle-Number.
12:11:03 <fizzie> I like how Finnish name for e is "Neperin luku" lit. "Neper's number", named after John Napier except with the last name misspelled.
12:11:27 <ais523> and the first name absent?
12:11:54 <fizzie> But that's not Finnish-specific; "Napier's constant" seems to be an English name.
12:13:15 <fizzie> (Also arbitrary: it's apparently either "Euler's number" or "Napier's constant", but not "Napier's number" like in Finnish.)
12:14:09 <Melvar> Jafet: “number ring” redirects to “Ring of integers” which corresponds to “Ganzheitsring”.
12:15:36 <fizzie> "John Napier of Merchiston (/ˈneɪpɪər/; 1550 – 4 April 1617) – also signed as Neper, Nepair – named Marvellous Merchiston, was a Scottish landowner known as a mathematician, physicist, and astronomer." Guess it's not *wrong* per se, just an alternative spelling.
12:16:05 <Jafet> https://el.wikipedia.org/wiki/Αριθμός_π uses latin letters for all terms except π (and an english-labelled diagram).
12:19:41 <Jafet> Ganzheitsring sounds like an article about middle-earth
12:20:28 -!- Sorella_ has joined.
12:21:25 -!- augur has quit (Quit: Leaving...).
12:22:09 -!- yorick has joined.
12:32:23 -!- callforjudgement has joined.
12:36:24 -!- ais523 has quit (Ping timeout: 240 seconds).
12:36:29 -!- callforjudgement has changed nick to ais523.
12:45:39 -!- Sorella_ has changed nick to Sorella.
12:53:36 -!- idris-ircslave has quit (Quit: Terminated).
12:53:52 -!- idris-ircslave has joined.
12:57:21 -!- idris-ircslave has quit (Client Quit).
12:57:39 -!- idris-ircslave has joined.
13:04:23 -!- idris-ircslave has quit (Quit: Terminated).
13:04:41 -!- idris-ircslave has joined.
13:09:15 <fungot> Selected style: europarl (European Parliament speeches during approx. 1996-2006)
13:09:25 <Taneb> fungot, there's a big debate happening tonight!"
13:09:26 <fungot> Taneb: madam president, on a point of order and by way of preparation in the committee on industry, external trade, research and energy is an extensive and complicated directive which will affect every single citizen, thereby violating the principle of equal treatment which puts the present commission, because the commission adopted a communication entitled: ' eeurope 2005: an information society is characterized by telecommuni
13:21:06 <fizzie> fungot: What do you think about the EU sanctions on Russia?
13:21:07 <fungot> fizzie: mr president, i believe that we must accept and address. one criticism that has been conducted. issues like this serve to underpin the peace process.
13:21:42 <fizzie> Typical politician, always ready with a seemingly coherent reply that still doesn't really say anything.
13:22:09 <Jafet> Hmm, what exactly are the sanctions not sanctioning?
13:24:18 <fizzie> They include at least some asset freezes. Could you summarize them for us, mr fungot?
13:24:18 <fungot> fizzie: mr poettering, the law. it is very important because it will determine our final vote.
13:25:25 <Jafet> I agree mr fungot, it's a good idea to sanction the law
13:25:26 <fungot> Jafet: i listened yesterday to mr schulz, mr poettering, chairman of the committee on foreign affairs, human rights, and the unions too, are sorry that we have begun to change little by little. mr kaklamanis, you ask yourself, can they contemplate the future with confidence.
13:28:04 -!- nycs has changed nick to `^_^v.
13:28:33 <fizzie> Today I learned (from a different channel) that strace gets it wrong if a 64-bit-code thread on Linux/x86-64 accesses the 32-bit syscall emulation layer via int 0x80.
13:28:36 <fizzie> http://sprunge.us/TdRe
13:30:19 <fizzie> It's a (nonimportant) write through the "syscall" interface (syscall number 1 in that table) followed by an exit(42) through the int 0x80 interface (syscall number 1 in *that* table), and strace thinks the latter is a write, too. (And looks for arguments where they would be for the "syscall" stuff.)
13:32:34 -!- tertu3 has joined.
13:58:18 -!- franklin8 has joined.
13:58:23 -!- franklin8 has quit.
14:01:51 <int-e> Taneb: at the momemnt the prefixes are global and there is no infrastructure for per channel settings at all.
14:03:58 <slereah> ahah, in some neural network book
14:04:07 <slereah> "Now forget everything about training sets and learning"
14:04:17 <slereah> I don't know what I'm doing
14:09:14 <Jafet> Now learn it again in a different order while reading the text upside down
14:13:22 <Jafet> "Each month, the European Parliament moves back and forth to meet the EU obligation to hold meetings also in France."
14:16:10 -!- Patashu_ has quit (Ping timeout: 252 seconds).
14:17:15 -!- ais523 has quit (Write error: Connection reset by peer).
14:17:32 -!- ais523 has joined.
14:27:18 -!- Sprocklem has joined.
14:29:58 <Jafet> Apparently, people are using the Enron emails as a corpus http://www.cs.cmu.edu/~enron
14:37:52 -!- ais523 has quit.
14:42:26 -!- tertu3 has quit (Ping timeout: 252 seconds).
14:45:29 <fungot> Available: agora alice c64 ct darwin discworld enron europarl* ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
14:45:38 <fowl> ^style lovecraft
14:45:39 <fungot> Selected style: lovecraft (H. P. Lovecraft's writings)
14:45:44 <fungot> fowl: then they had sealed the entrances and left them without courage, words, or know why you shouldn't. maybe you ought to hear, though, had gilman been there; and when told of the frantic magician. his fright, turning to leave his post at the rope, as the gold of the sky ever since there was any village to watch his taciturn dwelling from the plain to the north in grotesque panic.
14:48:32 <fungot> Selected style: enron (subset of the Enron email dataset)
14:48:52 <Jafet> It's time for a bit of professionalism around here, fungot.
14:48:53 <fungot> Jafet: questions about the market let alone an inter-company transfer the money." guarantee of the corporate parent of the work of the thought of the last few years that
14:56:05 * int-e wonders what fungot's point is.
14:56:06 <fungot> int-e: in a. thus the next to the above the offer of a the best. sent: tuesday, may 1, you will not have the right to do." california is facing the process that will, and get you to resign.
14:56:46 -!- tswett has joined.
14:56:47 -!- tswett has quit (Changing host).
14:56:47 -!- tswett has joined.
15:01:46 -!- drdanmaku has joined.
15:05:42 -!- zzo38 has quit (Remote host closed the connection).
15:10:34 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:12:56 -!- tertu3 has joined.
15:27:00 -!- MindlessDrone has quit (Quit: MindlessDrone).
15:33:28 -!- mhi^ has joined.
15:58:42 -!- tertu3 has quit (Ping timeout: 276 seconds).
16:01:55 -!- slereah has quit (Quit: Leaving).
16:25:33 <Melvar> I have added to idris-ircslave obedience to configuration (per-channel) of line limit. What should the limit be in this channel?
16:26:29 <fungot> int-e: have not moved. on the financial officer of the financial, trade and market renewable in 2001 that will complete. jones;wes colwell;mark haedicke;vince kaminski;phillip allen;tim belden;chris calger;joe deffner;tim detmering;dave duran;joe kishkell;rob milnthorp;brian redmond;gary hickerson;george mcclellan;sally beck;brian stanley;keith dodson; cc, 8, and main lines " a" and " that advance post of our the eel ( primaril
16:27:39 -!- edwardk has joined.
16:28:05 <int-e> no, fungot, 2001 is too much for IRC
16:28:05 <fungot> int-e: the our files that we
16:41:16 -!- FreeFull has joined.
16:41:34 <mroman> Given some array I want to know if it's x^n
16:45:47 <mroman> no wonder this is not working
16:47:23 -!- password2 has joined.
16:47:46 -!- password2 has quit (Max SendQ exceeded).
16:48:13 -!- Sprocklem has quit (Quit: Battery died).
16:48:22 -!- password2 has joined.
16:48:53 -!- password2 has quit (Max SendQ exceeded).
16:49:29 -!- password2 has joined.
16:49:38 <lambdabot> [0,1,8,27,64,125,216,343,512,729,1000,1331,1728,2197,2744,3375,4096,4913,583...
16:49:41 <Jafet> > zipWith (-) <*> tail $ map (^3) [0..]
16:49:42 <lambdabot> [-1,-7,-19,-37,-61,-91,-127,-169,-217,-271,-331,-397,-469,-547,-631,-721,-81...
16:49:51 <Jafet> > zipWith subtract <*> tail $ map (^3) [0..]
16:49:52 <lambdabot> [1,7,19,37,61,91,127,169,217,271,331,397,469,547,631,721,817,919,1027,1141,1...
16:49:59 -!- password2 has quit (Max SendQ exceeded).
16:50:00 <Jafet> > zipWith subtract <*> tail $ zipWith subtract <*> tail $ map (^3) [0..]
16:50:01 <lambdabot> [6,12,18,24,30,36,42,48,54,60,66,72,78,84,90,96,102,108,114,120,126,132,138,...
16:50:06 <Jafet> > zipWith subtract <*> tail $ zipWith subtract <*> tail $ zipWith subtract <*> tail $ map (^3) [0..]
16:50:07 <lambdabot> [6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6...
16:50:28 <mroman> You can derive until it only contains zeros
16:50:36 <mroman> that's essentially what I'm doing
16:50:52 <mroman> A derive, make some checks, derive again, make the checks, derive again, make the checks
16:51:43 <mroman> And currently it checks for a.) all zeroes, b.) x^n, c.) n^x, d.) n*x
16:52:00 <lambdabot> The cubes: a(n) = n^3.[0,1,8,27,64,125,216,343,512,729,1000,1331,1728,2197,2...
16:55:13 <lambdabot> Numerator of Bernoulli number B_n.[1,1,1,0,1,0,1,0,1,0,5,0,691,0,7,0,3617,0,...
16:55:31 <mroman> I'm abusing this stuff to judge how random some numbers are
16:56:15 <mroman> (9,1,7,7,0,3,1,5 has random level 5, whatever the hell that's supposed to mean)
16:57:49 <lambdabot> ‘scanl’ (imported from Data.List),
16:58:03 -!- oerjan has joined.
16:58:07 <myname> what the hell @ bernoulli number to that input
16:58:11 <lambdabot> [1,1,2,6,24,120,720,5040,40320,362880,3628800,39916800,479001600,6227020800,...
16:58:14 <Jafet> > [ 321^n `rem` 10^6 `div` 10^5 | n <- [0..] ]
16:58:15 <lambdabot> [0,0,1,0,4,7,4,8,2,1,7,5,3,4,0,1,1,5,5,0,9,3,5,6,2,1,0,3,6,6,6,3,8,6,1,4,2,1...
16:58:44 <oerjan> int-e: just thought you should know about http://stackoverflow.com/questions/23337798/cant-build-lambdabot-with-ghc-7-8-haskell-src-exts
16:58:49 -!- oerjan has quit (Client Quit).
16:59:42 <Jafet> scanl doesn't need to be strict.
17:00:11 <FreeFull> I have found a need for a strict scanl before
17:00:20 <FreeFull> I don't remember what for anymore
17:01:25 <Jafet> > show =<< [ 321^(n+100) `rem` 10^6 `div` 10^5 | n <- [0..] ]
17:01:27 <mroman> Faculty has a random factor of 0.8
17:01:27 <lambdabot> "530514009063721311532538764312390304954886869678617557428179164663146490244...
17:02:30 <FreeFull> > let generate08 = 0.8 in generate08
17:03:26 <int-e> call it factorial, or you'll confuse the native speakers :)
17:04:05 <FreeFull> How did I read factor as generator?
17:04:32 <mroman> Math.sqrt(n+1) is also pretty random apparentely
17:05:03 <lambdabot> Occurs check: cannot construct the infinite type: b ~ a0 -> b
17:05:51 <int-e> @tell oerjan must be a windows thingy; I've had no trouble with haskell-src-exts 1.15.0.1 under linux.
17:08:47 -!- password2 has joined.
17:10:57 -!- password2 has quit (Max SendQ exceeded).
17:12:29 <Jafet> sqrt is not random at all. (You could take the digits of one particular square root, which have a good chance of being iid)
17:24:11 <mroman> I know that it's not random
17:24:15 <mroman> But my algorithm doesn't ;)
17:25:17 <mroman> but not Math.sqrt(n+1)
17:28:03 -!- ^v has joined.
17:28:09 -!- password2 has joined.
17:29:53 -!- ^v has quit (Read error: Connection reset by peer).
17:32:05 -!- Barby1 has joined.
17:33:48 -!- nooodl has joined.
17:35:57 -!- Phantom_Hoover has joined.
17:38:08 <elliott> Barby1: please stop coming to this channel.
17:38:20 <elliott> Barby1: por favor deje de visitar este canal.
17:39:00 <elliott> does anyone know spanish better than google here.
17:39:41 -!- Barby1 has quit (Quit: Leaving.).
17:39:52 <Taneb> elliott, does Barby1 have a history?
17:40:05 <elliott> Taneb: *!~canaima@* has a history
17:40:18 <elliott> a history of joining and only speaking spanish for a few minutes before leaving
17:40:34 <elliott> like, 90% of the time the spanish welcome has been used, it's to them
17:40:38 <elliott> they just change nicks all the time
17:40:53 <elliott> maybe I should just set a ban? but they haven't done anything /wrong/, I guess, it's just... a waste of time for both parties
17:41:10 <Taneb> I am not very good at nethack
17:41:19 <Taneb> That was a bit of a non-sequitur, I know
17:41:27 <Taneb> But I was going to say it before I spotted Barby1
17:42:40 <Taneb> Does ftl cost money
17:44:02 <Taneb> I am afraid I do not have money right now
17:50:13 <mroman> Any ideas how I can detect stuff like sqrt(n+1)?
17:50:24 <mroman> sqrt(n+x) in generall.
17:52:54 -!- tertu3 has joined.
17:53:45 -!- password2 has quit (Ping timeout: 276 seconds).
17:54:45 -!- MoALTz has joined.
17:59:45 -!- MoALTz has quit (Quit: bbl).
18:04:44 -!- MoALTz has joined.
18:08:00 <Phantom_Hoover> http://www.reddit.com/r/Bitcoin/comments/1zpyba/100_secure_paper_wallet_cold_storage_tutorial_out/
18:08:28 <Phantom_Hoover> "Use the linux command "echo -n my_dice_rolls | sha256sum" to generate a private key" your private key will be in your command history, for easy access!!
18:13:27 <Bike> "Note: All source code produced by this campaign will always be publicly available under open source license. However building a WormSim from source is a complex operation that requires advanced engineering skills." advanced engineering skills to make
18:15:10 <Bike> a c elegans simulation.
18:17:19 <Bike> c elegans. a roundworm. nematode.
18:17:36 <Jafet> Advanced software engineering skills
18:18:47 <fizzie> Advanced social engineering skills to worm (npi) the building instructions out of someone.
18:19:27 <Bike> they provide "Eclipse Juno distributions for the main OSs"
18:28:39 -!- Sprocklem has joined.
18:42:45 <Taneb> In this roguelike I am helping with, the strongest starting armour is a hawai'in t-shirt
18:42:49 <Taneb> Followed by a law suit
18:43:07 <Sgeo> If I want to use rsync to transfer files between computers, is there an obvious choice for which is server and which is client?
18:43:26 <Sgeo> I'm just wondering if it's primarily a download thing or does two-way sync
18:44:22 <b_jonas> there's no obvious choice, but sometimes stuff could restrict you if you don't bother to set up an ssh or rsync server on both sides
18:45:01 <b_jonas> heck, I even use rsync for a few local copies
18:46:59 <Sgeo> How sick should one be before considering taking a sick day?
18:47:09 <Sgeo> I took a sick day today, and do feel sick, but not -very- sick
18:47:33 <b_jonas> Sgeo: depends on how many sick days you have
18:48:13 <mroman> Sgeo: If you can walk you're not sick enough
18:48:21 <b_jonas> think of how many you will want to keep for the rest of the year
18:49:19 -!- tertu3 has quit (Ping timeout: 252 seconds).
18:49:32 <Sgeo> I think it accumulates during the year, and the site that shows me how much time I have doesn't show how much will accumulate
18:50:08 <b_jonas> Sgeo: definitely get to learn early and often about how many days of leave you have
18:50:41 <b_jonas> if your calculation differs from that of your workplace by more than half a day, then talk to them about who doesn't understand the rules or who has made a mistake
18:51:07 <b_jonas> do that early even if you have enough days of paid leave for now, so that later it can't cause a problem
18:51:11 <Sgeo> I know I have 3 personal days a year that don't accumulate, and have been told by a coworker and my dad to generally use that first
18:51:41 <Sgeo> But I think that's separate from sick time, I don't think using personal days for sick time makes sense, maybe for vacation time
18:51:57 <b_jonas> the rules differ by country and occupation a lot of course, and depend on stuff
18:53:36 -!- tertu3 has joined.
18:58:00 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
19:11:13 -!- Phantom_Hoover has joined.
19:22:24 -!- hexagon has quit (Quit: Here we are, going far to save all that we love - If we give all we've got, we will make it through - Here we are, like a star shining bright on your world - Today, make evil go away!).
19:22:35 -!- ^v has joined.
19:22:47 -!- hexagon has joined.
19:23:45 -!- hexagon has quit (Client Quit).
19:24:15 -!- hexagon has joined.
19:25:43 -!- nucular has quit (Quit: Switching to phone in a few minutes).
19:39:09 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
19:46:48 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
19:46:51 -!- conehead has joined.
19:47:05 -!- Phantom_Hoover has joined.
20:04:29 -!- tertu3 has quit (Ping timeout: 252 seconds).
20:04:40 -!- nisstyre has joined.
20:10:21 <Taneb> Aaaaah what can a CS society spend money on
20:11:48 <fizzie> A set of 3D-printed miniature figurines of famous computer science researchers.
20:12:13 <Slereah_> A quantum computer to play quantum DOOM
20:13:13 <kmc> a large collection of synthetic hallucinogens
20:15:51 <Slereah_> The world's most expensive dildo
20:16:36 <Slereah_> A cat skeleton soaked in kerosene
20:17:58 <Slereah_> The corpse of John the Baptist
20:18:34 <fungot> fizzie: please let me know the best is yet.?
20:19:02 <fizzie> fungot: Well, it's hard to say which one of those was best. Maybe you could suggest something clearly better than any so far.
20:19:02 <fungot> fizzie: we don't i mail this other project, i thus expect the following and let
20:20:14 -!- MoALTz has quit (Quit: bbl).
20:21:11 <nooodl> i wonder which of the things Slereah_ mentioned are purchasable, and then, which is most expensive
20:21:17 <nooodl> i guess you can buy all the tea in china?? "it's hard"
20:21:32 <Slereah_> A castle in spain is probably the most realistic and expensive
20:22:02 <Slereah_> unless you buy really a lot of candy
20:24:19 <elliott> nooodl: the world's most expensive dildo is pretty buyable, presumably
20:25:36 <Slereah_> Goats are not very expensive though
20:25:59 <Slereah_> Also I assume that the world's most expensive dildo is in a private collection
20:26:46 <Taneb> In other news, we have a program which compiles fine on Ubuntu but very not fine on Arch
20:27:07 <nortti> how does one compile not fine?
20:29:28 <Phantom_Hoover> <elliott> nooodl: the world's most expensive dildo is pretty buyable, presumably
20:29:40 <Phantom_Hoover> it's probably made out of solid gold or something though
20:29:53 <Taneb> nortti, NCurses fails
20:30:09 <Taneb> Phantom_Hoover, not particularly relevant either
20:30:12 <nortti> Taneb: compile or link?
20:30:14 <fizzie> Phantom_Hoover: Or perhaps it's just valuable because of its illustrious history.
20:30:15 <Slereah_> Phantom_Hoover : what about the sky
20:30:17 <elliott> Phantom_Hoover: cheaper than all the tea in china
20:30:51 <Taneb> nortti, runtime, in the clang memory sanitizer apparently
20:30:53 -!- barrucadu has joined.
20:31:07 <Phantom_Hoover> Slereah_, well that's governed by national airspace treaties
20:31:28 <barrucadu> We're trying to debug a memory error, and so used clang's memory sanitizer, but that throws out errors on Arch but not on Ubuntu - in libncursesw
20:32:02 <barrucadu> This is the error: http://pastebin.com/SBCPRqqU
20:32:22 <barrucadu> Line 29 of main.c is this: https://github.com/HackSoc/LudumDare29/blob/master/main.c#L29
20:33:17 <barrucadu> Don't worry, we have (fallen) angels elsewhere in the code, they'll take care of any curses
20:33:31 <fizzie> See, the problem is that "binary packages encourage inconsistency and incompatibility, whearas source encourages unified development frameworks and integration."
20:33:47 <fizzie> (I just felt like quoting funroll-loops.info.)
20:34:48 <lambdabot> shachaf says: You can't spell "-funsafe" without "fun" and "safe".
20:35:49 <fizzie> That joke works p. well for the GCC option -funsafe-math-optimizations.
20:36:16 <fizzie> Also you can't spell -malign-double without maligning some perfectly respectable doubles.
20:36:56 <Slereah_> I keep a little script on my werk computer
20:37:17 <Slereah_> I called it MAXIMUM OVERWARNING
20:37:29 <Slereah_> That way I have things to do in case I don't know what to do
20:37:42 <fizzie> Clang has a single flag for that, fortunately.
20:37:49 <fizzie> (It's called -Weverything.)
20:38:19 <Slereah_> Strangely enough -Wall doesn't do that
20:38:43 <Taneb> -Wall-no-really-when-I-say-all-I-mean-all
20:38:59 <Slereah_> For some reason gcc doesn't seem to like string literals?
20:39:01 <FreeFull> I don't think lambdabot has the primes package
20:39:02 <fizzie> -Wall doesn't, but -Weverything does.
20:39:11 <Slereah_> They're pretty easy to compile, no?
20:39:19 <FreeFull> @let import Data.Numbers.Primes
20:39:20 <lambdabot> Failed to load interface for ‘Data.Numbers.Primes’
20:39:20 <lambdabot> Perhaps you meant Data.Number.Fixed (from numbers-3000.2.0.1)
20:39:20 <lambdabot> Use -v to see a list of the files searched for.
20:39:39 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
20:39:53 <elliott> it did when I had it, I think
20:40:01 <fizzie> shachaf: Also you can't spell -funsafe without "NSA" it is a conspiracy
20:40:28 <Slereah_> And you can't spell -funsafe without enuf
20:40:46 <Taneb> So any ideas re: memory error?
20:41:38 <fizzie> Taneb: Install the package that comes with debugging info for the ncursesw lib, so that you get something more edifying than just offsets in hex. Then fix what's probably a ncurses bug.
20:42:57 <fizzie> If it's really the same (ncurses) code on both, and only trips a "use-of-uninitialized-value" on one, it could be different environment variables or terminfo databases or <any other environmental thing>. Though you never know about "same version" either.
20:43:20 <fizzie> I wonder if there are people who always compile with -ffinite-math-only out of some sort of philosophical principles.
20:43:58 <fizzie> You know, people who don't believe in infinities.
20:44:00 <Slereah_> I am currently doing some log things so I really need my infinities
20:48:45 <fizzie> Taneb: FWIW, I get the same -fsanitize=memory error for libncursesw on my system, for a program that does only a initscr();.
20:50:10 <lexande> Phantom_Hoover, Slereah_: a friend who is an expert on such matters is aware of a $3500 gold-plated dildo and a $15k gold-plated vibrator, which may be the most expensive mass-produced examples, though yes presumably there are much more expensive ones sold as artwork at auction
20:50:37 <barrucadu> Also, turns out the reason the error isn't coming up on Ubuntu is becasue the version of clang on the uni computers is too old to support the memory sanitizer
20:52:57 -!- Bike has quit (Read error: Connection reset by peer).
20:53:15 -!- Bike has joined.
20:59:14 <Taneb> ...we are now debugging ncurses
21:01:35 -!- Patashu has joined.
21:01:55 -!- Patashu_ has joined.
21:01:55 -!- Patashu has quit (Disconnected by services).
21:08:18 -!- augur has joined.
21:16:38 -!- Sprocklem has quit (Ping timeout: 240 seconds).
21:18:56 <fizzie> FWIW, my error comes with the call stack initscr -> newterm -> _nc_setupterm -> _nc_setup_tinfo -> _nc_read_entry -> _nc_first_db, and it's a strlen on the string "/home/fis/.terminfo" (values[dbdHome]) that seems just fine in gdb; not sure why the memory-sanitizer warns about uninitialized stuff in it.
21:19:01 <fizzie> But perhaps your error is different.
21:19:41 <Taneb> Our code now appears to work
21:20:07 <fizzie> (If I read the messages right, it doesn't like the null terminator at the end.)
21:21:17 <fizzie> Well, the (ncurses) code does look incorrect, so maybe that's just fair.
21:21:47 -!- edwardk has quit (Ping timeout: 265 seconds).
21:24:53 -!- Patashu_ has quit (Ping timeout: 264 seconds).
21:28:01 <fizzie> Or, hm. I don't know. It looks okay on further inspection. Very kludgy, though. But the string's still the result of a regular snprintf, that should be suitably null-terminated. And actually the offset it's complaining about is one past the '\0', and it's not like the strlen should be looking there.
21:28:34 <fizzie> Unless it's some sort of "GCC knows the size of the buffer so it can use an optimized four-bytes-at-a-time strlen" kind of deal.
21:29:12 <fizzie> That actually sounds quite reasonable. In which case the use of uninitialized data would be just a false positive from the MemorySanitizer.
21:29:22 <fizzie> I'm going to call it that since then I won't have to keep looking at it.
21:30:30 <Taneb> Our program works only when memory is being watched
21:30:44 <kmc> quantum computing
21:30:52 <fizzie> (Possibly even glibc can assume things about page borders etc. and use a multi-byte strlen.)
21:32:30 <kmc> fizzie: I've been playing with SSE 4.2 string instructions and I think a lot of the example code out there doesn't handle page boundaries correctly
21:32:36 <kmc> I talk about that at the end of https://github.com/kmcallister/html5/blob/sse/src/tokenizer/buffer_queue.rs#L182-L252
21:34:20 <HackEgo> [U+0021 EXCLAMATION MARK]
21:34:51 <shachaf> kmc: should be called terrifying_microöptimizations hth
21:34:56 <kmc> shachaf: yeah
21:35:15 <shachaf> and it should use a combining character in half the places
21:35:21 <shachaf> i hear rust will handle that correctly
21:35:35 <kmc> i don't know if it normalizes --cfg arguments on the command line, though
21:36:33 <fizzie> kmc: I guess (I haven't looked if this is a thing that is done) one could just handle the *initial* not-16-byte-aligned part of a string specially, and then you can do movdqa and read in full 16-byte blocks and never worry about crossing a page boundary even if the read does go beyond the end of the string.
21:36:50 <kmc> imo it should also accept — instead of --
21:36:59 <kmc> fizzie: yeah
21:37:18 <kmc> otoh, that will often be slower
21:37:37 <kmc> i think it's an em
21:37:41 <kmc> but i'm using a fixed width font
21:37:47 <kmc> I guess that means an em and an en are the same!
21:37:48 <shachaf> the difference is still visible
21:37:53 <kmc> praise jesus
21:38:06 <HackEgo> sortcoin slash-01coin versedcoin univelacoin squeklycoin tclycoin brainftingcoin pooncoin loodbcoin purehancoin visiticoin 0x8coin excepiracoin returntzcoin owlcoin betticoin marcoin boskecoin mancecoin yellicoin
21:38:21 <kmc> if i'm gonna die for a word, my word is pooncoin
21:38:46 <shachaf> imo just map an extra page in at the end `j̀ust in casé´
21:38:56 <kmc> imo just handle SIGSEGV
21:40:49 <fizzie> kmc: glibc strlen seems to do more or less what I envisaged, except it also rounds *down* to do the unaligned part with a movdqa, cf. http://sprunge.us/hZDA
21:41:00 -!- boily has joined.
21:41:29 <fizzie> (I'm also going to go ahead and assume that's why the ncurses code fails with -fsanitize=memory, since it sounds plausible.)
21:43:17 <fizzie> (Er, "do the unaligned part with pcmpeqb to memory", but anyway.)
21:43:20 <Taneb> Yes, it goes beyond the end of the string
21:43:29 <fizzie> (I didn't really read the operands.)
21:44:27 <fizzie> Taneb: Well, that's perfectly legal, under some assumptions.
21:47:13 <kmc> if the president does it, it's not illegal
21:47:21 <shachaf> actually it should be µoptimizations
21:47:31 <kmc> shachaf: is that greek letter mu or mathematimu?
21:48:25 <Taneb> We've found the actual error we were looking for :)
21:48:28 <shachaf> which i get by pressing altgr+m
21:49:00 <kmc> I do like it when code (usually kernel exploits) clears the WP bit in %cr0 so it can write to read-only pages
21:49:15 <kmc> much easier than walking the page tables
21:52:22 <boily> `` echo 'A mathematimu is a quantum of mathematics. If you observe it, its codepoint can change.' >wisdom/mathematimu
21:59:01 <boily> fowl: you have been quoted. you exist in the PDF now.
21:59:33 <fizzie> (A fate worse than death.)
22:00:58 <fowl> eh its no worse than when i enlisted. now the govt has my fingerprints and dna on record :/
22:01:34 <kmc> which govt
22:01:39 <boily> which fingerprints?
22:06:45 <HackEgo> 1187) <fowl> one day we'll be able to put evil people inside mirrors and throw them into space like superman 2
22:06:56 <Taneb> `quote plastic spoon
22:06:57 <HackEgo> 400) <Taneb> Someone with that sort of grasp of logic shouldn't be allowed anything more computationally powerful than a plastic spoon
22:07:05 -!- oerjan has joined.
22:08:09 <lambdabot> int-e said 5h 2m 17s ago: must be a windows thingy; I've had no trouble with haskell-src-exts 1.15.0.1 under linux.
22:13:18 <oerjan> <Jafet> Is fungot less volatile than btc <-- what isn't?
22:13:18 <fungot> oerjan: i moved to sp) regarding any of the street. 1717 main street, suite that enables the customers.
22:13:31 <kmc> fungotcoin
22:13:31 <fungot> kmc: you will get out the points of the information on the new more efficient.
22:14:26 <oerjan> @ask Jafet <Jafet> Is fungot less volatile than btc <-- what isn't?
22:14:26 <fungot> oerjan: two years the big a book on the work of the business is mailing for individuals that dynegy to walk on the wharton. 1124.7) ( madison.
22:14:45 <boily> 1717 Berri is the address of Montréal's autocar terminus. fungot, what are you spying on from Montréal, eh?
22:14:46 <fungot> boily: new deal to keep the current and will find the time to get on the stack.
22:14:47 <oerjan> pesky @ask /whois race condition again
22:15:03 <boily> fungot: intelligence gathering, then.
22:15:03 <fungot> boily: could we schedule more to the issues on the new plants that not only survive, but not the one that the are two sections resulting in the lowest in three years that
22:15:07 -!- Phantom_Hoover has quit (Quit: Leaving).
22:16:16 <oerjan> boily: i hypothesize that there's an agency hidden at _every_ 1717 address hth
22:17:17 <kmc> "autocar" means bus? confusing
22:17:23 <oerjan> or possibly a shared one, with clever portal doors
22:18:47 <Jafet> @ask oerjan Crimea hth
22:19:29 <boily> kmc: coach cars, I guess. intercity shuttle buses?
22:19:52 <boily> I like autocar myself. I find the word pleasing, like a zeppelin.
22:21:04 <Bike> automatic car dispenser
22:21:28 <fizzie> http://upload.wikimedia.org/wikipedia/commons/d/d4/Smart_vending_machine_in_Shenyang.jpg
22:27:00 <lambdabot> Jafet asked 8m 13s ago: Crimea hth
22:31:45 <kmc> fizzie: does it work?
22:33:06 <oerjan> @tell <ais523> each review of bugs takes one more year than the last <-- that's quadratic not geometric hth
22:33:56 <oerjan> @tell ais523 <ais523> each review of bugs takes one more year than the last <-- that's quadratic not geometric hth
22:41:56 <Taneb> oerjan, that was pointed out iirc
22:43:48 <oerjan> Taneb: another race condition :(
22:44:25 <oerjan> i need to switch to STM for my logreading.
22:49:59 -!- mhi^ has quit (Quit: Lost terminal).
22:54:25 <FreeFull> You should have used STM in the first place
22:54:33 <FreeFull> It's too nice to skip in multithreaded software
22:54:59 -!- edwardk has joined.
22:55:46 -!- yorick has quit (Remote host closed the connection).
22:59:03 <HackEgo> #!/usr/bin/env node \ // Generated by CoffeeScript 1.6.2 \ (function() { \ var consonant_then_o, ell_manglable, ends_with_consonant, ends_with_consonant_then_vowel, name, starts_with_o; \ \ name = process.argv[2]; \ \ if (!(name != null ? name.length : void 0)) { \ console.log('Usage: ello <name>'); \ process.exit(); \ } \ \
22:59:19 <kmc> javascript? in my HackEgo?
23:00:27 <boily> I think I'm now used to the classical “hoily.”
23:00:33 <Bike> `run cat $(which thanks)
23:00:34 <HackEgo> #!/usr/bin/perl \ $_ = (join " ", @ARGV) || `words`; s/^\s+|\s+$//g; print "Thanks, $_. "; if (/[aeiouyAEIOUY]/) { s/^[^aeiouyAEIOUY]*/Th/; } else { s/^./T/; } print "$_.";
23:00:46 <oerjan> hm it's sensitive to final space, but only sometimes...
23:03:54 -!- nooodl has quit (Remote host closed the connection).
23:04:15 -!- nooodl has joined.
23:07:34 <fizzie> kmc: I don't think so, in the sense that you could buy the car from it.
23:09:19 <lexande> you could have a vending machine that sold car keys
23:09:25 <lexande> with the cars conveniently parked nearby
23:10:37 <oerjan> <FreeFull> A strict scanl would be nice <-- it's not that important for scanl unless you skip over elements in the list
23:10:38 <kmc> imagine the frustration after you put $15,000 in bills into the machine and then the keys don't quite fall off the corkscrew hook thing
23:11:03 <oerjan> because being strict is equivalent to evaluating the result elements in order
23:11:37 <FreeFull> oerjan: I had something that needed strict scanl but I don't remember why
23:11:37 <fizzie> There is also the http://spectrum.ieee.org/geek-life/tools-toys/vehicular-vending-machine which at least deals in cars.
23:11:44 <FreeFull> Something that would leak memory otherwise
23:14:04 -!- Sprocklem has joined.
23:17:57 <kmc> fizzie: nice
23:18:02 <kmc> zipcar is also like a car vending machine, in a sense
23:19:17 <FreeFull> Use an ashtray as a lens, to magnify the car
23:23:03 <oerjan> <Taneb> Does ftl cost money <-- infinite money hth
23:24:11 <boily> what's the exchange rate in Canadian dollars?
23:27:06 <boily> dammit. my stupid bot won't connect to freenode.
23:27:27 <oerjan> you were also going to duck it out?
23:27:54 <boily> me? what would make you believe that?
23:28:07 * boily mapoles his cuttlefish of a bot
23:28:30 -!- metasepia has joined.
23:28:31 <boily> ~duck 1 USD in CAD
23:28:38 <oerjan> also have you factored in that canada doesn't exist twh
23:29:00 <HackEgo> Failed to connect to socket 2. \ \ Looking up 127.0.0.1:3128 \ Making HTTP connection to 127.0.0.1:3128 \ Sending HTTP request. \ HTTP request sent; waiting for response. \ Alert!: Unexpected network read error; connection aborted. \ Can't Access `http://google.com/search?q=%31%20%55%53%44%20%69%6e%20%43%41%44' \ Alert!: Unable to access document.
23:31:13 <boily> oh well. time to go drown my unexistant sorrows in some douteux stuff.
23:31:19 -!- boily has quit (Quit: DISQUIETING CHICKEN).
23:31:22 -!- metasepia has quit (Remote host closed the connection).
23:33:18 <oerjan> @ask Slereah_ <Slereah_> The corpse of John the Baptist <-- child or adult?
23:53:44 <oerjan> @ask boily <boily> `` echo 'A mathematimu is a quantum of mathematics. If you observe it, its codepoint can change.' >wisdom/mathematimu <-- WHY DID I EVEN BOTHER TO MAKE `learn UNDERSTAND ARTICLES
23:54:43 -!- nooodl has quit (Quit: Leaving).
23:55:09 <Taneb> `run echo 'An article is something that `learn can understand.' > wisdom/article
23:55:26 -!- ChanServ has set channel mode: +o oerjan.
23:55:32 -!- oerjan has kicked Taneb AAAAAAAAA.
23:55:37 -!- oerjan has set channel mode: -o oerjan.
23:56:19 -!- Taneb has joined.
00:05:49 -!- tromp has joined.
00:06:09 -!- FireFly has quit (Excess Flood).
00:06:20 -!- nisstyre has joined.
00:09:22 -!- FireFly has joined.
00:09:22 -!- FireFly has quit (Excess Flood).
00:10:40 -!- FireFly has joined.
00:11:37 -!- shachaf has quit (Ping timeout: 252 seconds).
00:12:07 -!- shachaf has joined.
00:24:13 <kmc> if Unicode is supposed to encompass every legacy charset, then shouldn't they have compatibility codepoints somewhere for the UCS-2 characters corresponding to UTF-16 surrogates?
00:24:32 <kmc> or is the idea that they don't have to because those codepoints were never assigned in UCS-2?
00:26:36 <oerjan> nah they just have a padded cell in their headquarters for anyone who thinks to long about that hth
00:26:46 <kmc> seems likely
00:30:00 <kmc> https://github.com/mairin/selinux-coloring-book
00:32:23 <Jafet> Aren't those UCS-2 characters also unicode codepoints
00:32:56 <kmc> U+D800 through U+DFFF are explicitly not valid Unicode codepoints
00:33:10 <kmc> there's no clear way to represent them in UTF-16, and there is a clear way to represent them in UTF-8 but it's forbidden
00:33:20 <Jafet> Did anyone use those?
00:33:21 <kmc> though see http://en.wikipedia.org/wiki/CESU-8
00:34:08 <lexande> does myndzi do anything for ꙮ_ꙮ or ꙮ.ꙮ
00:38:48 -!- realzies has quit (Ping timeout: 240 seconds).
00:40:20 <kmc> Jafet: JavaScript has UCS-2 string semantics, so (for example) if you get a string from the DOM that contains an astral plane character and inspect it with charCodeAt() you will see individual surrogates :/
00:45:51 <kmc> http://jsfiddle.net/Wj5DN/
00:48:55 <kmc> this is a massive pain if you want to represent strings in your browser as something other than UTF-16, say, to save a huge amount of memory
01:06:34 <Taneb> So, for the Ludum Dare Game Jam, some of my friends (and I helped!) made a small roguelike, "ColinQuest"
01:06:41 <Taneb> http://www.ludumdare.com/compo/ludum-dare-29/?action=preview&uid=20617
01:07:31 <Taneb> It would be really helpful if people could make static binaries for Windows and Max
01:08:19 <elliott> OS X doesn't like static binaries.
01:09:00 <Taneb> What does OS X like and could you help with that
01:09:13 <newsham> http://ecmanaut.blogspot.com/2006/07/encoding-decoding-utf8-in-javascript.html ?
01:10:15 -!- barrucadu has left.
01:10:20 <newsham> os x likes irony and fixed-speed bicycles
01:10:54 <newsham> osx does not like waiting in line, showing up to work on time, going to clubs that let everyone in
02:28:28 -!- ^v has joined.
02:44:10 -!- trout has quit (Ping timeout: 265 seconds).
02:51:44 -!- Sorella has quit (Quit: It is tiem!).
03:19:23 -!- ^v has quit (Read error: Connection reset by peer).
03:19:49 -!- ^v has joined.
03:22:54 -!- adu has joined.
03:44:32 -!- ^v has quit (Ping timeout: 252 seconds).
03:45:43 -!- ^v has joined.
03:57:59 -!- tromp has quit (Remote host closed the connection).
03:58:35 -!- tromp has joined.
04:02:50 -!- tromp has quit (Ping timeout: 255 seconds).
04:08:20 <HackEgo> [wiki] [[Talk:~-~!]] http://esolangs.org/w/index.php?diff=39430&oldid=38729 * 121.45.207.205 * (+412) /* Getting odd numbers back after ~=~~ (let 1 = 2) */ new section
04:15:42 -!- tertu has joined.
04:34:18 -!- tertu has quit (Ping timeout: 240 seconds).
04:40:11 -!- tertu has joined.
04:51:26 -!- realzies has joined.
05:03:01 -!- tswett has quit (Ping timeout: 252 seconds).
05:06:24 -!- adu has quit (Quit: adu).
05:13:59 -!- Sprocklem has quit (Quit: Goodnight).
05:15:55 -!- ^v has quit (Read error: Connection reset by peer).
05:16:08 -!- ^v has joined.
05:20:16 -!- variable has joined.
05:20:16 -!- variable has quit (Changing host).
05:20:16 -!- variable has joined.
05:20:53 -!- ^v has quit (Client Quit).
05:22:36 -!- ^v has joined.
05:42:53 -!- tertu has quit (Ping timeout: 264 seconds).
05:45:40 -!- nooodl has joined.
05:46:35 -!- nooodl has quit (Client Quit).
05:48:17 -!- nooodl has joined.
05:50:39 -!- FreeFull has quit.
06:00:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
06:01:19 -!- tertu has joined.
06:01:24 -!- idris-ircslave has quit (Quit: Terminated).
06:10:29 -!- tertu has quit (Ping timeout: 264 seconds).
06:11:11 <Sgeo> It's not cheating if ekmett guides me through what to do, right?
06:11:56 -!- ^v has quit (Ping timeout: 252 seconds).
06:13:25 -!- augur has quit (Ping timeout: 252 seconds).
06:15:40 <oerjan> Sgeo: you are lost in a maze of categories, all different...
06:19:05 -!- ^v has joined.
06:19:20 -!- ^v has quit (Read error: Connection reset by peer).
06:21:30 <Sgeo> (lambda (p) (contramap (lambda (o) (lift p ) p
06:21:39 <Sgeo> ^^incompletely and possibly wrong aieee
06:23:45 <oerjan> ^def ul (I see nothing.)S
06:23:50 <Sgeo> If I want to get to a profunctor that gets an s, I need to contramap with a profunctor that accepts an s
06:23:58 <fungot> echo reverb rev rot13 rev2 fib wc ul cho choo pow2 source help hw srmlebac uenlsbcmra scramble unscramble asc ord prefixes tmp test celebrate wiki chr ha rainbow rainbow2 welcome me tell eval elikoski list ping def a thanks
06:24:33 <Sgeo> contramap with a function
06:24:34 <oerjan> i wonder if that got saved anywhere.
06:27:19 -!- nooodl has quit (Quit: Leaving).
06:31:03 <shachaf> oerjan: how do you feel about covariant and contravariant Setters
06:32:13 <fungot> Selected style: lovecraft (H. P. Lovecraft's writings)
06:32:25 <fungot> echo reverb rev rot13 rev2 fib wc ul cho choo pow2 source help hw srmlebac uenlsbcmra scramble unscramble asc ord prefixes tmp test celebrate wiki chr ha rainbow rainbow2 welcome me tell eval elikoski list ping def a thanks tmp2
06:32:43 <oerjan> fungot: those setters are non-euclidean, aren't ther
06:32:44 <fungot> oerjan: all was now ready, and the thinning hair and beard of my friend had laughed, for these fears were of the vaguest, wildest, and most of the palaces the floors were generally thick with detritus, litter, and debris, but farther down this condition decreased. in some places. people sometimes heard the queerest kind of sounds.
06:34:01 -!- password2 has joined.
06:34:07 <fizzie> It does not seem to have made it to the state file.
06:34:11 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
06:35:23 <Bike> so what are we dealing with now? the fungot in the machine?
06:35:24 <fungot> Bike: the first horrible incident of our acquaintance was the greatest. there was a singularity in my fnord hand. this is not to the complete and engulfing fnord of the
06:36:02 <oerjan> Bike: much worse than that, clearly
06:37:03 <fowl> are you serious
06:37:10 <fowl> fungot is written in befunge?
06:37:10 <fungot> fowl: may 18, 1934. now, beyond the roof and the tops of great pointed windows, rose boldly above the tangle of gables and chimneys in the violet valley where the many-bridged charles flows drowsily. these things i was very sorry for him, for
06:37:37 <oerjan> fowl: well it was either that or some hideous chthonic language.
06:38:34 <fizzie> As far as I can tell, "^def ul ..." indeed parses as command name "", language "ul", body "...". I don't know yet what happens after that.
06:39:37 <fowl> i learned a word today! im going to go call someone chthonic brb
06:39:55 <oerjan> just be prepared for them to sprout tentacles hth
06:40:12 <fizzie> Oh, I see what's going on.
06:40:26 <fizzie> The end of the command list is also marked by a 0 where a command name is expected.
06:41:09 <oerjan> so it was "saved", but then ignored, and your tmp2 probably overwrote it.
06:42:43 <fizzie> I'm still missing the ^undef command, I think I added that to the TODO list somewhere in 2009-2010.
06:43:26 <oerjan> ^def todo ul (Make a todo list command)S
06:45:41 <fowl> now i want to learn befunge to figure this out
06:51:07 <oerjan> fizzie: maybe you'll get pull requests!
06:51:13 <fungot> Make a todo list command
06:51:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:51:43 <oerjan> has that ever happened btw
06:53:26 <olsner> oh, fungot moved to github?
06:53:26 <fungot> olsner: when i finally found myself fnord and free, i awkwardly clambered down to the sea and fnord down from the fifth story. he had known merely by reputation or not at all.
06:54:07 <oerjan> "and that's how i got to github."
06:55:24 <fizzie> There have been no Github forks or pull requests or issues or any of that stuff.
06:55:27 <oerjan> `addquote <olsner> oh, fungot moved to github? <fungot> olsner: when i finally found myself fnord and free, i awkwardly clambered down to the sea and fnord down from the fifth story. he had known merely by reputation or not at all.
06:55:27 <fungot> oerjan: in less than an hour or two at a time the man left me alone. some new and wild note in the drumming and chanting, perceptible but slightly to me, and at its inner angles, and view the myriad parts of the
06:55:29 <HackEgo> 1190) <olsner> oh, fungot moved to github? <fungot> olsner: when i finally found myself fnord and free, i awkwardly clambered down to the sea and fnord down from the fifth story. he had known merely by reputation or not at all.
06:57:49 <fowl> olsner, i think thats the markov chain part of it
06:58:18 <fizzie> olsner: It's the twitter stuff.
06:58:51 <fizzie> And also contains a Perl implementation of the markov chain stuff.
06:59:02 <fizzie> Though what's doing the blabbing here in IRC is all Funge-98.
06:59:07 <b_jonas> you mean, fungot uses twitter?
06:59:07 <fungot> b_jonas: the lurking fear. the thing came abruptly and fnord a sound animal without psychological subtleties, and probably that by which those others had descended.
06:59:18 <fizzie> b_jonas: Well, it has a Twitter account, it hasn't tweeted in quite a while.
06:59:45 <fizzie> https://twitter.com/fungot "29 Jun 2012"
06:59:45 <fungot> fizzie: if you desire to see him dart purposefully out of the realm of their pets. accordingly, we decided to find a smooth place on the seventh of october, 1928, dr. willett's that the next move. it was when the minds of the requisite sensitiveness.
07:00:05 <fizzie> I wouldn't be surprised if the Twitter-posting parts had bitrotted away.
07:00:15 <b_jonas> how many fungots does it take to change lightbulb?
07:00:15 <fungot> b_jonas: the next day, saying that the stones and altars were as low as those in the sea. for their prehistoric flights through cosmic space, legend said, they absorbed certain chemicals and became almost independent of eating, always curiously like a formality with him, and he knew he must confront his host.
07:01:02 <b_jonas> fungot: like a positronic robot?
07:01:02 <fungot> b_jonas: " you have come to see the high turrets of the onyx nightmare wherein still glowed the lone lurid light of that final horror. i have said, my studies gradually gave me a kind of ophidian animation. everything he saw was abnormal, non-euclidean, and loathsomely redolent of spheres and dimensions apart from ours. now an fnord seaman felt the same anomalous drowsiness which affected me oddly.
07:01:34 <b_jonas> fungot: and ravens circling the tower too, I guess?
07:01:34 <fungot> b_jonas: blake had fnord in the fabulous years beyond history. in the storm
07:01:50 <fowl> fizzie, im sure the api has changed several times since 2012
07:01:55 <fizzie> Oh, there's apparently also a "collect trending tweets" script.
07:02:19 <fizzie> I think I was going to make a ^style twitter, but then forgot about it.
07:08:45 -!- augur has joined.
07:09:02 <b_jonas> fizzie: I have this old quotes file http://www.math.bme.hu/~ambrus/pu/bibul.txt scraped from http://www.lolcatbible.com/ . you could make a style based on it if there isn't one yet.
07:09:38 <b_jonas> that's like five years old though so maybe it should be re-scraped
07:10:30 <b_jonas> fungot, can has you bake a cake in lolcat?
07:10:30 <fungot> b_jonas: i eyed him in silence for a while my chief concern during dreams was to avoid looking down at the top, in order that he might use the silver key. a gate had been that one or some other attribute of a family of short-lived men, i afterward pondered long upon these premature deaths, and began making a noose with the other islanders, or as sacrifices to the other.
07:11:05 <fowl> that. is. awesome.
07:21:03 -!- heroux has quit (Ping timeout: 276 seconds).
07:37:53 -!- slereah has joined.
07:38:03 <slereah> I hate it when I do something that works because I made a mistake
07:38:09 <slereah> And it ceases to work when I fix it
07:43:24 <b_jonas> slereah: yes, some of our programs work when we make an even number of sign mistakes
07:45:33 <HackEgo> tbftcoin cuycoin bubandcoin caintacoin nhoolemcoin intycoin singcoin helpiteshimlddreimachcoin mouflaufecoin altcoin bilcoin wiecoin sandcoin udecoin stacoin comaascerecoin noortcoin georrelcoin ribulcoin forcoin
07:45:55 <slereah> Welp, I tried two sigmoid functions
07:46:07 <slereah> The usual one solves it in about 5000 iterations
07:46:17 <slereah> The Elliot one in... 3 millions
07:49:25 <Bike> TWO l's TWO t's
07:50:03 <Bike> abs? how boring
07:50:32 <slereah> A steeper gain might work out vbetter
07:55:21 <slereah> But it works even better with the exponential one
07:55:26 <slereah> I wonder about the tangent one
08:01:40 <Bike> i wonder how much faster that can really be. surely exp is just a taylor series.
08:02:08 <slereah> Well it is faster to compute, surely, but slower to converge
08:03:19 <Bike> i'm wondering how many taylor terms you really need. maybe you can just go up to ³ or so and get something inaccurate, but faster than more exp, and converging faster than abs
08:03:47 <slereah> I looked up an implementation of exp once
08:03:50 <Bike> what's the math on how fast a givne transfer function converges, anyway? or is it all empiric?
08:04:33 <slereah> It used the Remez algorithm
08:04:57 <slereah> That's because at that level, the error is < to significant digits
08:05:10 <slereah> Also it didn't compute it directly
08:05:14 <Bike> still just a polynomial, eh
08:06:20 -!- idris-ircslave has joined.
08:07:23 <slereah> Also the coefficients of the Remez algorithm are pre-tabulated
08:11:05 <shachaf> "Firefox OS lets you live every moment to its fullest and build a brighter future for the Web."
08:11:30 <slereah> I don't want my OS to crash all the time because I have too many things open
08:13:37 <Bike> http://stackoverflow.com/questions/15350856/which-method-to-implement-exp-function-in-c stack overflow closings seem weird
08:14:27 <kmc> shachaf: seems legit
08:22:35 -!- Tritonio has joined.
08:26:49 <kmc> shachaf: it's unfortunate that for a &str foo, foo.slice_from(n).as_bytes() is slower than foo.as_bytes().slice_from(n)
08:27:01 <kmc> I guess this is the sort of thing GHC's rewrite rules are good for
08:27:20 <shachaf> aren't those different things?
08:27:34 <shachaf> well, i guess that depends on what slice_from and as_bytes (and str) are
08:27:53 -!- oerjan has quit (Quit: leaving).
08:28:41 <shachaf> ok, slice_from takes a byte offset, not a code point offset
08:28:42 <kmc> true, the former will fail in cases where the latter won't
08:28:55 <kmc> hi quintopia
08:29:32 <shachaf> because it makes a new str object thing which is taken apart immediately or something?
08:29:51 <shachaf> oh, because it checks for validity?
08:32:22 <kmc> sorry, the latter
08:32:42 <shachaf> the first one i think is solved by inlining, the second one you can't really solve with rewrite rules because it changes the program
08:34:40 -!- Patashu has joined.
08:36:06 <shachaf> i sort of like the thing where you have indices into a string that are "opaque", so you get constant-time indexing but can't get an unsafe index
08:36:11 <shachaf> i guess that's an iterator or something
08:36:52 <kmc> iterators are kind of a pain in rust though :/
08:45:34 <lifthrasiir> oh, this channel has much more active discussion for Rust than #rust itself. :p
08:49:20 <coppro> that sounds about right
08:49:30 <coppro> we have more active discussion on any topic than any other channel
08:49:40 <coppro> except for esoteric programming languages
08:50:57 -!- Patashu_ has joined.
08:50:57 -!- Patashu has quit (Disconnected by services).
08:53:04 <shachaf> kmc: where does n come from in your case?
08:58:28 -!- heroux has joined.
09:04:04 <kmc> good night
09:20:30 -!- impomatic has quit (Ping timeout: 265 seconds).
09:29:18 -!- mhi^ has joined.
09:34:57 -!- password2 has quit (Ping timeout: 276 seconds).
09:57:52 -!- oerjan has joined.
10:04:39 <slereah> Are there special preprocessing things to tell the compiler "Hey don't sweat it it's okay that it's like that"
10:05:04 -!- conehead has quit (Quit: Computer has gone to sleep).
10:05:37 -!- yorick has joined.
10:18:34 -!- oerjan has quit (Quit: leaving).
10:18:34 -!- boily has joined.
11:03:24 -!- Phantom_Hoover has joined.
11:11:40 -!- boily has quit (Quit: EGREGIOUS CHICKEN).
11:13:10 -!- impomatic has joined.
11:17:54 -!- kallisti_ has quit (Read error: Connection reset by peer).
11:42:58 <fizzie> That would presumably depend on the compiler.
11:43:16 <fizzie> GCC has pragmas that can turn off warnings for particular regions.
12:02:33 <Taneb> Are the rationals the smallest field containing the naturals?
12:02:33 -!- Sorella_ has joined.
12:04:33 <Taneb> I don't really know what I'm talking about
12:04:36 <Jafet> There are some fields containing N, but not Q
12:06:55 <Jafet> "The rational numbers can be formally defined as the equivalence classes of the quotient set (Z × (Z \ {0})) / ~ ..." ok I think these math guys really really want it to be the smallest field
12:14:57 <int-e> Jafet: what else would you have in mind?
12:15:53 <int-e> (if you start with Z x (Z \ {0}) but don't take that quotient then you won't have a field)
12:16:36 <int-e> where I'm interpreting Z x (Z \ {0}) as fractions.
12:17:48 <Jafet> Oh, that definition is actually much more overcomplicated than I thought
12:19:27 <int-e> we could just use the smallest field of characteristic 0 :)
12:20:09 <Jafet> Well, we might first want to make sure that there is a smallest field of characteristic 0
12:20:58 <slereah> Why do they never teach all basic C features
12:21:18 <slereah> WHAT ELSE ARE YOU HIDING C
12:21:33 <int-e> Jafet: this is in the same spirit as working with *the* complete ordered field.
12:21:48 <int-e> slereah: digraphs and trigraphs
12:22:02 <int-e> slereah: and lots of undefined behaviour
12:22:22 <Jafet> Bitfield compiler bugs
12:22:44 <Jafet> Buggy libc linker scripts
12:23:45 -!- tswett has joined.
12:23:45 -!- tswett has quit (Changing host).
12:23:45 -!- tswett has joined.
12:24:03 <Jafet> It should be straightforward to prove that any field of characteristic 0 contains Q.
12:25:05 <Jafet> (When preparing the camera copy, change your \shouldbe macro to "is")
12:25:09 <int-e> Jafet: it contains Z and is closed under division by non-zero numbers, so it contains all fractions.
12:30:03 <slereah> Is there a way to get around some of the compilation of functions
12:30:20 <slereah> I want to do some inline stuff, but by default functions do a lot of things on their own
12:33:22 <int-e> static inline void foo() { ... } // standard way to urge to compiler to inline the function and not provide a standalone compiled version
12:33:39 <slereah> By default, a function of floats load the arguments into the xmm registers
12:34:03 <slereah> Even if I do nothing with the floats
12:35:08 <int-e> inlining should take care of that.
12:35:44 <int-e> (why do you have functions with unused arguments though?)
12:36:48 <fizzie> If you mean this http://sprunge.us/YKLQ then just plain compiling with optimizations on should get rid of *that*.
12:37:11 <fizzie> (That's not loading arguments to xmm registers, though; it's unloading them from there.)
12:37:13 <slereah> int-e : Well what if I want to use them in the ST registers, for instance
12:37:50 <int-e> fizzie: wow that does look awful :)
12:38:33 <fizzie> Assuming regular x86-64 ABI, they're passed in the SSE regs.
12:38:49 <int-e> and what was the point of "rep ret" again? meh
12:38:57 <fizzie> int-e: It's to work around an AMD bug.
12:39:15 <fizzie> int-e: Something something branch prediction something something ret directly at a branch target something.
12:39:27 <fizzie> (It does a simple "ret" for suitable values of -march.)
12:39:30 <int-e> This came up before. http://repzret.org/p/repzret/ was nice.
12:40:15 <fizzie> I don't think I've managed to coax the "ret 0" out of GCC.
12:45:46 -!- nisstyre has joined.
12:46:41 <slereah> Man why does the compiler do movq%rax, -24(%rbp)movsd-24(%rbp), %xmm0
12:46:48 <slereah> rax isn't even anything in this function
12:47:33 <fizzie> Paste some code, perhaps.
12:47:45 <int-e> Is that without -O?
12:47:46 <slereah> I'll return one of the argument
12:48:12 <fizzie> I'm pretty sure %rax is something if it does that.
12:48:26 <fizzie> If not, you should report a code generation bug.
12:48:30 <slereah> Maybe outside the function
12:48:55 <int-e> anyway, hard to tell without code.
12:49:55 <slereah> I'll just return one of the argument
12:50:06 <slereah> At least I know where they are stored
12:55:15 -!- Sgeo has quit (Read error: Connection reset by peer).
12:57:00 -!- ais523 has joined.
13:03:00 -!- callforjudgement has joined.
13:03:32 -!- ais523 has quit (Read error: Connection reset by peer).
13:03:33 -!- callforjudgement has changed nick to ais523.
13:06:36 -!- callforjudgement has joined.
13:06:40 -!- ais523 has quit (Client Quit).
13:08:23 -!- callforjudgement has quit (Excess Flood).
13:08:43 <slereah> Is there a site that has like
13:09:03 <slereah> In a bit more readable format
13:09:35 -!- callforjudgement has joined.
13:10:19 -!- callforjudgement has changed nick to ais523.
13:21:38 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:26:39 -!- ais523 has quit (Remote host closed the connection).
13:26:41 -!- callforjudgement has joined.
13:30:33 <`^_^v> what are basic c functions, the ones that are included in the standard?
13:31:00 <Jafet> The ones written in basic
13:31:42 <slereah> The non-library functions in the standard
13:32:15 <slereah> There always seems to be some hidden one that I discover
13:39:18 <slereah> Basically a list of all features of C that isn't a tutorial
13:43:45 -!- callforjudgement has changed nick to ais523.
13:45:20 -!- ais523 has quit.
13:45:26 -!- callforjudgement has joined.
13:52:47 <fizzie> I think that's called a "book".
13:52:53 <fizzie> Something like the K&R.
13:53:34 <slereah> Most if not all don't have said list!
13:55:50 -!- callforjudgement has quit (Read error: Connection reset by peer).
13:56:00 <fizzie> Well, K&R is reasonably thin (274 pages, according to Amazon) and if you read through it once, there shouldn't be all that much left to discover that could be called "basic features". I guess.
13:56:05 -!- callforjudgement has joined.
13:57:40 <mroman> src\System\Plugins\Consts.hs:39:23: lexical error in string/character literal at character 'P'
13:57:51 <mroman> There are syntax errors in hackage packages?
13:58:36 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
13:58:39 <mroman> that's also a good question
13:59:20 <`^_^v> you should just read the standard, because the language has changed a lot since k&r, and even k&r does not have everything about the language
13:59:31 <`^_^v> it's just as boring as you would expect, but you learn a lot
13:59:55 -!- tertu has joined.
14:00:26 <`^_^v> then you can join ##c and start being very pedantic
14:01:37 -!- callforjudgement has quit (Read error: Connection reset by peer).
14:01:42 -!- scarf has joined.
14:03:50 <mroman> I hate how some packages can't be compiled on windows without cygwin
14:04:01 <mroman> and as it seems now... they even don't compile with cygwin
14:04:51 -!- scarf has changed nick to ais523.
14:05:27 <mroman> haskell platform isn't really made for >Windows XP
14:05:59 <mroman> Yeah.. I see... I'm gonna need a Unix again somewhere
14:06:25 <mroman> If you update cabal stuff get's broken due to AppData\Roaming
14:06:57 -!- nucular has joined.
14:06:58 -!- nucular has quit (Changing host).
14:06:58 -!- nucular has joined.
14:17:35 -!- ais523 has quit (Ping timeout: 240 seconds).
14:19:31 -!- ais523 has joined.
14:23:42 -!- Sorella_ has changed nick to Sorella.
14:26:26 -!- edwardk has quit (Quit: Computer has gone to sleep.).
14:38:06 -!- edwardk has joined.
14:56:42 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
15:01:07 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:03:35 -!- ^v has joined.
15:08:43 -!- Sprocklem has joined.
15:19:54 -!- ter2 has joined.
15:19:55 -!- tertu has quit (Disconnected by services).
15:23:11 -!- ais523 has quit (Remote host closed the connection).
15:25:33 -!- ais523 has joined.
15:25:33 -!- ais523 has quit (Client Quit).
15:25:54 -!- password2 has joined.
15:26:21 -!- password2 has quit (Max SendQ exceeded).
15:30:44 -!- password2 has joined.
15:31:13 -!- password2 has quit (Max SendQ exceeded).
15:31:52 -!- password2 has joined.
15:32:24 -!- tertu3 has joined.
15:32:24 -!- ter2 has quit (Read error: Connection reset by peer).
15:38:23 -!- AnotherTest has joined.
15:39:42 <fizzie> Today's spam: http://sprunge.us/ZFCH
15:39:55 <fizzie> I assume that list of names is culled from competing spammers.
15:45:44 -!- Tritonio has quit (Ping timeout: 255 seconds).
15:48:08 -!- FreeFull has joined.
15:50:52 -!- drdanmaku has joined.
15:57:58 -!- tertu3 has quit (Ping timeout: 240 seconds).
15:58:19 <int-e> fizzie: it's so nice to finally find an honest person out there.
16:00:38 -!- augur has quit (Quit: Leaving...).
16:06:54 -!- password2 has quit (Ping timeout: 276 seconds).
16:08:13 -!- slereah has quit (Quit: Leaving).
16:11:27 -!- aloril has quit (Ping timeout: 276 seconds).
16:19:10 -!- edwardk has joined.
16:24:41 -!- password2 has joined.
16:24:43 -!- aloril has joined.
16:45:42 -!- MoALTz has joined.
16:54:52 -!- tertu3 has joined.
17:03:35 -!- password2 has quit (Ping timeout: 255 seconds).
17:10:38 -!- nooodl has joined.
17:16:02 -!- Slereah_ has quit.
17:21:48 -!- password2 has joined.
17:26:20 -!- ter2 has joined.
17:26:20 -!- tertu3 has quit (Read error: Connection reset by peer).
17:30:03 -!- tertu3 has joined.
17:30:28 -!- MindlessDrone has joined.
17:33:17 -!- ter2 has quit (Ping timeout: 264 seconds).
17:33:39 -!- tertu has joined.
17:34:24 -!- ter2 has joined.
17:34:25 -!- tertu has quit (Disconnected by services).
17:35:41 -!- tertu3 has quit (Ping timeout: 264 seconds).
17:35:59 -!- Slereah has joined.
17:36:53 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:40:53 -!- adu has joined.
17:57:11 -!- password2 has quit (Ping timeout: 265 seconds).
17:57:57 <myname> wtf is up with boardgamegeek
17:58:06 <myname> {{data.config.moduletitle}}
17:58:53 -!- ter2 has quit (Ping timeout: 252 seconds).
17:58:54 <myname> what the hell, that is supposed to be like this with disabled js
18:27:25 -!- CodingBat has joined.
18:33:35 -!- planet23 has joined.
18:37:44 -!- planet23 has quit (Remote host closed the connection).
18:46:12 -!- CodingBat has quit (Quit: Page closed).
18:52:09 -!- Sprocklem has joined.
18:56:47 -!- FreeFull has quit (Ping timeout: 240 seconds).
18:59:52 -!- Main has joined.
19:00:02 -!- Main has quit (Client Quit).
19:01:39 -!- conehead has joined.
19:02:43 -!- nortti has changed nick to noragami.
19:02:56 -!- noragami has changed nick to nortti.
19:02:57 -!- FreeFull has joined.
19:13:42 <`^_^v> http://java.metagno.me/
19:14:47 <nortti> `^_^v: you sir/madam/something else have the best nick I've seen yet
19:14:48 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ^_^v:: not found
19:16:34 <nortti> `run { echo '#!/bin/sh'; echo "echo '^_^v'"; } > bin/^_^v; chmod +x bin/^_^v
19:18:06 <nortti> `run { echo '#!/bin/sh'; echo "echo '`^_^v'"; } > bin/^_^v; chmod +x bin/^_^v
19:18:06 <HackEgo> bash: -c: line 0: unexpected EOF while looking for matching ``' \ bash: -c: line 1: syntax error: unexpected end of file
19:18:55 <nortti> `run { echo '#!/bin/sh'; echo "echo '^_^v'"; } > bin/^_^v; sed -i bin/^_^v '2s/^/`/'
19:18:56 <HackEgo> sed: can't find label for jump to `in/^_^v'
19:19:34 <nortti> `run sed -i '2s/^/`/' bin/^_^v
19:19:57 <myname> `^_^v: that thing is brilliant
19:19:58 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ^_^v:: not found
19:20:19 <HackEgo> chmod: missing operand after `+x bin/^_^v' \ Try `chmod --help' for more information.
19:20:32 <nortti> `run chmod +x bin/^_^v
19:20:39 <HackEgo> /hackenv/bin/^_^v: 3: /hackenv/bin/^_^v: Syntax error: EOF in backquote substitution
19:24:03 <FireFly> I can't wrap my head around ICFP. I can't find anything on icfpconference.org about registration, attendance fees, attendance eligibility and so on, but I guess I'm missing something
19:24:26 <FireFly> Knowing this channel, I'm sure you know everything about ICFP (and more), so what am I missing?
19:31:25 <kmc> fungot: Yes I'll tell you, I'll tell you why I'm lying here... but God forgive me... and God help us all... because you don't know what you ask of me.
19:31:25 <fungot> kmc: weary moon on the river of the sky like the men from the plains would scale the slope homeward in the dusk as the stars came right again. to this man iranon spoke, as to only a few, since fuller accounts and records are at the disposal of the prisoners. no trials, or even proved to exist. the farther he went the fnord it was clear, and devastating significance nearly fnord to the fiend has ever had.
19:32:16 <FireFly> I knew it, I should've asked fungot for advice instead
19:32:16 <fungot> FireFly: the next i racked my brain over the problem. what had happened. he did, however, a giant, muscular body, stark naked, was found upon boarding to contain one survivor in a fnord state like a true man and fnord.
19:32:19 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft* nethack oots pa qwantz sms speeches ss wp youtube
19:32:39 -!- nucular has quit (Quit: Excess Food).
19:32:58 <int-e> FireFly: it's more than 4 months away, and notifications are next week, so I think not having registrations open yet is normal.
19:33:18 <FireFly> fungot: the giant, muscular, stark naked body contained a survivor?!
19:33:18 <fungot> FireFly: " but the whisperer seemed not to notice this, and its colour was that same nameless intrusion which ammi had come to the bad end he deserved, is at once the horrible eyes, blacker even than the moss-grown castle walls. these ancient turrets, stained by the storms of generations and crumbling under the slow yet mighty pressure of time, safety, direction, or definite object? there is something queer and unholy about the
19:33:30 <int-e> FireFly: that's speaking in general, I don't know about ICFP in particular
19:34:27 <int-e> Though hmm, some idea of what fees to expect before submitting papers would be nice.
19:35:01 <Bike> one MILLLLLLION dollars
19:35:34 <FireFly> I guess I'll wait and see what happens
19:37:57 <FireFly> I'm expecting it to be more expensive than PyCon Sweden's student rate, at any rate :P
19:38:07 <coppro> a conference I want to go to this summer hasn't even gotten their website up yet and it's two months away :/
19:38:19 <FireFly> (which amounts to $20 or so)
19:40:19 <olsner> but which four, and how many of them?
19:41:01 <FireFly> I guess I'll forget about it then, at that rate
19:41:57 <coppro> more importantly, is there a decimal point?
19:42:28 <coppro> (ICFP is sponsored by ACM which means that it is cheaper for ACM members and too expensive in any case)
19:49:18 <fizzie> "crumbling under the slow yet mighty pressure of time, safety, direction, or definite object?"
19:50:47 <int-e> http://icfpconference.org/icfp2012/registration.html seems the most recent data on the web. Some of the tutorial prices don't make sense.
19:51:03 -!- curiousguy13 has joined.
19:51:09 <fizzie> That's not much of a member discount.
19:52:01 <fizzie> ICASSP 2014 costs €705 for IEEE non-members, €520 for IEEE members, and €470 for IEEE SPS members.
19:52:59 <fizzie> (I'm paying the student price, which is €225 for non-members, €150 for SPS members, and IEEE+SPS membership for the rest of the year was something like $15.)
19:53:57 <int-e> "professional" ACM membership is $99 a year, a discount of half the membership fee sounds reasonable.
19:54:43 <int-e> but who am I to judge
19:54:46 <fizzie> IEEE dues are such that it's always cheaper to join than to go to the conference as a non-member.
19:54:57 <fizzie> (I think they get a lot of members that way.)
19:55:53 <olsner> hmm, just noticed that I've forgotten why I dislike ACM, but I have some idea that being a member is somehow bad
19:56:09 <coppro> olsner: because they don't actually offer anything useful?
19:56:51 <coppro> there was a time when they did. now all they do is spam members
19:56:58 <FireFly> They arrange ICPC, at least that's something I guess
19:57:22 <coppro> no, their members do, and they would be perfectly able to do so if not for the ACM
19:57:31 <coppro> it's how many other major disciplines do it :)
20:21:42 -!- edwardk has quit (Ping timeout: 276 seconds).
20:22:12 -!- Froox has joined.
20:22:25 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:22:55 -!- Frooxius has quit (Read error: Connection reset by peer).
20:45:17 -!- AnotherTest has quit (Ping timeout: 264 seconds).
21:02:28 -!- Patashu has joined.
21:14:02 -!- Patashu_ has joined.
21:14:03 -!- Patashu has quit (Disconnected by services).
21:14:43 -!- ter2 has joined.
21:17:21 <Slereah> http://i.imgur.com/NUZoY4G.png
21:19:38 -!- Sprocklem has quit (Ping timeout: 240 seconds).
21:20:11 <kmc> No one should be a cock to a stranger, ever!
21:21:02 <Slereah> Dicks are very important for figures of speech though
21:21:24 <Slereah> One of my favorite is "I wouldn't fuck her with a stolen dick!"
21:21:32 <Slereah> Because of the sheer absurdity of penis theft
21:21:45 <kmc> https://www.youtube.com/watch?v=byDiILrNbM4
21:25:19 -!- Patashu_ has quit (Ping timeout: 252 seconds).
21:31:40 -!- nooodl has quit (Remote host closed the connection).
21:33:14 -!- nooodl has joined.
21:36:04 -!- CodingBat has joined.
21:44:14 -!- adu has quit (Quit: adu).
21:45:49 -!- Bicyclidine has joined.
21:49:23 -!- CodingBat has left.
21:53:38 -!- ter2 has quit (Ping timeout: 240 seconds).
21:58:08 -!- Sgeo has joined.
22:05:59 -!- edwardk has joined.
22:08:43 -!- augur has joined.
22:14:38 -!- augur has quit (Ping timeout: 240 seconds).
22:15:00 -!- augur has joined.
22:28:15 -!- mhi^ has quit (Quit: Lost terminal).
22:37:04 -!- ggherdov has quit (Ping timeout: 258 seconds).
22:42:43 -!- nooodl has quit (Quit: Leaving).
22:46:31 <kmc> #ifdef DEBUG
22:46:32 <kmc> mHandles[mHandlesUsed] = (nsIContent*)0xC0DEDBAD;
22:49:33 -!- ggherdov_ has joined.
22:54:47 -!- MoALTz has quit (Ping timeout: 252 seconds).
23:08:09 -!- yorick has quit (Remote host closed the connection).
23:18:48 -!- CodingBat has joined.
23:19:52 <Bicyclidine> http://coq.inria.fr/distrib/V8.3-beta0/refman/Reference-Manual025.html i think coq should be used to verify a lack of encoding errors >:
23:22:48 -!- CodingBat has quit (Ping timeout: 240 seconds).
23:24:59 -!- tromp has joined.
23:25:02 <kmc> "Remember, the C++ type system and the XPCOM type system are really two independent things. Because XPCOM interfaces are expressed as abstract C++ base classes, you may be tempted to let C++ handle the differences, or to use C++ casts to navigate between interface types. This is wrong."
23:25:34 <Taneb> This evening I wrote some sort of data queue server
23:25:40 <Bicyclidine> what is the relationship between XPCOM and X-COM: ENEMY UNKNOWN
23:25:57 -!- curiousguy13_ has joined.
23:26:57 -!- CodingBat has joined.
23:27:18 -!- curiousguy13 has quit (Ping timeout: 265 seconds).
23:27:29 -!- curiousguy13_ has changed nick to curiousguy13.
23:29:48 -!- nisstyre has joined.
23:32:43 -!- CodingBat has quit (Quit: Page closed).
23:36:33 -!- Phantom_Hoover has joined.
23:49:27 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:04:55 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:23:41 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
00:32:05 -!- edwardk has joined.
00:36:49 -!- Phantom_Hoover has joined.
00:48:52 -!- tromp has quit (Remote host closed the connection).
00:49:26 -!- tromp has joined.
00:53:51 -!- pikhq has quit (Ping timeout: 252 seconds).
00:54:17 -!- tromp has quit (Ping timeout: 264 seconds).
00:55:51 -!- pikhq has joined.
00:58:47 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
01:11:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
01:11:42 -!- Bicyclidine has quit (Ping timeout: 265 seconds).
01:31:43 -!- Sorella has quit (Quit: It is tiem!).
01:35:11 -!- nisstyre has joined.
01:44:10 -!- ter2 has joined.
01:57:52 -!- edwardk has quit (Quit: Computer has gone to sleep.).
02:06:49 -!- Sprocklem has joined.
02:43:46 <Sgeo> Chrome seems to disbelieve that I could ever want a new tab when I ctrl-click a link
02:43:56 <Sgeo> It assumes CNN's trying to do an evil pop-up and blocks it
02:58:12 -!- edwardk has joined.
03:05:35 -!- FreeFull_ has joined.
03:07:35 -!- FreeFull has quit (Ping timeout: 252 seconds).
03:11:23 -!- oerjan has joined.
03:35:54 <oerjan> <Sgeo> Chrome seems to disbelieve that I could ever want a new tab when I ctrl-click a link <-- can you do it with the right click menu instead? that's what i have to do whenever following a link out of stupid wikia.
03:36:56 <Sgeo> Chrome seems to have sponaneously changed it's behavior, even ctrl-mouse pad press is working now
03:37:01 <Sgeo> I'm sure the old behavior will come back
03:37:25 <oerjan> oh btw i'm not using chrome so this is just a wild suggestion.
03:39:02 <oerjan> wikia, of course, _does_ make an evil popup then. which i could tolerate if not for the fact that it simultaneously forgets i want a new tab.
03:39:58 <Sgeo> that popup is wikia
03:49:56 -!- edwardk has quit (Remote host closed the connection).
03:50:25 -!- edwardk has joined.
04:02:48 -!- drdanmaku has joined.
04:05:05 -!- ^v has quit (Read error: Connection reset by peer).
04:05:32 -!- ^v has joined.
04:08:09 -!- password2 has joined.
04:23:41 -!- ter2 has quit (Ping timeout: 252 seconds).
04:26:23 <kmc> http://www-sop.inria.fr/marelle/Laurent.Thery/T2048.v
04:26:27 <kmc> 2048 in coq
04:27:21 <kmc> not to be confused with cock in 2048
04:27:27 <kmc> to which I could also provide a link
04:37:07 -!- curiousguy13 has quit (Ping timeout: 265 seconds).
04:50:07 <kmc> http://chneukirchen.org/trivium/ looks pretty good
05:02:50 <HackEgo> [wiki] [[Special:Log/newusers]] create * John Misciagno * New user account
05:04:04 -!- tswett has quit (Ping timeout: 252 seconds).
05:05:18 -!- adu has joined.
05:13:06 <fizzie> Why are there no "1" tiles in 2048, anyway?
05:16:43 <oerjan> they're considered too odd hth
05:17:55 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
05:20:02 -!- MoALTz has joined.
05:46:23 -!- adu has quit (Quit: adu).
06:00:04 -!- ^v has quit (Read error: Connection reset by peer).
06:00:31 -!- ^v has joined.
06:15:45 <Jafet> Lemma thm2 : forall seed, exists ms, g2048 seed ms
06:16:07 <Jafet> Oh, the previous one is also unproven.
06:16:46 -!- MoALTz has quit (Quit: bbl).
06:23:18 -!- variable has changed nick to trout.
06:24:24 <Jafet> applybot: fun merge where "merge (x#y#xs) = (if x = y then (x+y) # merge xs else x # merge (y#xs))" | "merge [x] = [x]" | "merge [] = []"
06:24:25 <applybot> constants \ merge :: "'a list => 'a list" \ Found termination order: "length <*mlex*> {}"
06:24:57 <Jafet> applybot: value "merge [2,0,2,2,4] :: nat list"
06:25:05 <Jafet> applybot: value "merge [2,2,2,4] :: nat list"
06:27:01 <Jafet> applybot: definition "left = map (%row. let row' = merge (filter (op ~= 0) row) in row' @ replicate (4 - length row') 0)"
06:27:02 <applybot> constants \ left :: "'a list list => 'a list list"
06:27:21 <Jafet> applybot: value "merge [2,0,2,4] :: nat list"
06:28:10 <Jafet> applybot: value "left [[2,0,2,4]] :: nat list"
06:28:11 <applybot> *** Type unification failed: Clash of types "_ list" and "nat"
06:28:15 <Jafet> applybot: value "left [[2,0,2,4]] :: nat list list"
06:28:16 <applybot> "[[4, 4, 0, 0]]" \ ∷ "nat list list"
06:29:32 <Jafet> applybot: definition "right = map rev o left o map rev"; definition "up = transpose o left o transpose"; definition "down = transpose o right o transpose"
06:29:34 <applybot> constants \ right :: "'a list list => 'a list list" \ constants \ up :: "'a list list => 'a list list" \ constants \ down :: "'a list list => 'a list list"
06:29:54 <kmc> what's all this then
06:35:14 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:39:20 <Jafet> applybot: fun gen where "gen rows ((row,col,n)#ns) = (if rows ! row ! col = 0 then rows[row := (rows ! row)[col := n]] else gen rows ns)"
06:39:21 <applybot> constants \ gen :: "'a list list => (nat * nat * 'a) list => 'a list list" \ Found termination order: "(%p. list_size (%p. size (fst (snd p))) (snd p)) <*mlex*> {}"
06:39:53 <Jafet> Hmm, that doesn't work
06:40:01 <applybot> At: definition "right = map rev o left o map rev";definition "up = transpose o left o transpose";definition "down = transpose o right o transpose"
06:40:09 <b_jonas> that looks like some sort of ml
06:40:18 <Jafet> applybot: fun gen where "gen rows ((row,col,n)#ns) = (if rows ! row ! col = 0 then (rows[row := (rows ! row)[col := n]], ns) else gen rows ns)"
06:40:19 <applybot> constants \ gen :: "'a list list => (nat * nat * 'a) list => 'a list list * (nat * nat * 'a) list" \ Found termination order: "(%p. list_size (%p. size (fst (snd p))) (snd p)) <*mlex*> {}"
06:46:56 <Jafet> applybot: definition "win rows0 ns acts = list_ex (list_ex (op = 2048)) (fst (fold (%(rows, ns) mov. gen (act rows) ns) acts (rows0, ns)))"
06:46:57 <applybot> *** Extra variables on rhs: "act"
06:47:04 <Jafet> applybot: definition "win rows0 ns acts = list_ex (list_ex (op = 2048)) (fst (fold (%(rows, ns) act. gen (act rows) ns) acts (rows0, ns)))"
06:47:04 <applybot> *** Type unification failed: Clash of types "_ * _" and "_ => _"
06:48:47 -!- S1 has joined.
06:49:37 <Jafet> applybot: definition "win rows0 ns acts = list_ex (list_ex (op = 2048)) (fst (fold (%act (rows, ns). gen (act rows) ns) acts (rows0, ns)))"
06:49:38 <applybot> constants \ win :: "'a list list => (nat * nat * 'a) list => ('a list list => 'a list list) list => bool"
06:51:29 <Jafet> applybot: value "win ([[1024,0,0,0],[0,2,4,8],[1024,0,0,0],[0,0,0,0]] :: nat list list) [(2,3,4)] [up]"
06:52:49 <Jafet> applybot: value "gen (up ([[1024,0,0,0],[0,2,4,8],[1024,0,0,0],[0,0,0,0]] :: nat list list)) [(2,3,4)]"
06:52:50 <applybot> "([[2048, 2, 4, 8], [0, 0, 0, 0], [0, 0, 0, 4], [0, 0, 0, 0]], [])" \ :: "nat list list * (nat * nat * nat) list"
06:53:05 <Bike> ah, how useful.
06:53:23 <Bike> What's with the 4
06:53:39 <Jafet> The game places it at (2,3).
06:54:16 <Jafet> applybot: declare [[show_sorts]] term gen
06:54:26 <Jafet> applybot: raw:declare [[show_sorts]]; term gen
06:54:27 <applybot> "gen" \ :: "'a::zero list list => (nat * nat * 'a::zero) list => 'a::zero list list * (nat * nat * 'a::zero) list"
06:54:56 <Jafet> Yep, I think this lets you play 2048 on an arbitrary group
06:55:01 <Bike> oh, it's the next number, ok
06:55:07 <Jafet> applybot: raw:linear_undo
07:01:33 -!- MindlessDrone has joined.
07:05:24 <Jafet> applybot: lemma "EX len. ALL ns. (length ns > len & list_all (%n. n = 2 | n = 4) ns) --> EX moves. win (replicate 4 (replicate 4 (0 :: nat))) ns moves"
07:05:24 <applybot> *** Inner syntax error at "EX moves . win ( replicate 4 ( replicate 4 ( 0 :: nat ) ) ) ns moves"
07:05:37 <Jafet> applybot: lemma "EX len. ALL ns. (length ns > len & list_all (%n. n = 2 | n = 4) ns) --> (EX moves. win (replicate 4 (replicate 4 (0 :: nat))) ns moves)" -- oh come on
07:05:38 <applybot> *** Type unification failed: No type arity prod :: numeral
07:06:34 <Jafet> applybot: lemma "EX len. ALL ns. (length ns > len & list_all (%(i,j,n). 0 <= i & i < 4 & 0 <= j & j < 4 & (n = 2 | n = 4)) ns) --> (EX moves. win (replicate 4 (replicate 4 (0 :: nat))) ns moves)"
07:06:36 <applybot> Proving: 1. EX len. ALL ns. len < length ns & list_all (%(i, j, n). 0 <= i & i < 4 & 0 <= j & j < 4 & (n = 2 | n = 4)) ns --> (EX moves. win (replicate 4 (replicate 4 0)) ns moves)
07:08:46 <Jafet> Hmm, there's a bug in the colouring code
07:09:51 <Jafet> applybot: apply clarsimp
07:09:53 <applybot> Proving: 1. EX len. ALL ns. len < length ns & list_all (%(i, ab). i < 4 & (case ab of (j, n) => j < 4 & (n = 2 | n = 4))) ns --> (EX moves. win (replicate 4 (replicate 4 0)) ns moves)
07:11:30 <Jafet> applybot: apply (subgoal_tac "ALL ns. EX moves. win (replicate 4 (replicate 4 0)) ns moves", blast)
07:11:32 <applybot> Proving: 1. ALL ns. EX moves. win (replicate 4 (replicate 4 0)) ns moves
07:12:29 <Jafet> applybot: apply (erule allI, rule_tac x = "%_. (replicate 4 (replicate 4 2048))" in exI)
07:12:29 <applybot> *** Failed to apply proof method
07:12:30 <S1> Jafet: What is that language?
07:12:40 <Jafet> https://isabelle.in.tum.de
07:15:09 <Jafet> applybot: apply (rule allI, rule_tac x = "[%_. replicate 4 (replicate 4 2048)]" in exI)
07:15:11 <applybot> Proving: 1. !!ns. win (replicate 4 (replicate 4 0)) ns [%_. replicate 4 (replicate 4 2048)]
07:16:35 <Jafet> Wait, that won't work.
07:33:00 -!- nortti has changed nick to [Nn]ortti.
07:33:13 -!- [Nn]ortti has changed nick to nortti.
07:36:22 -!- slereah_ has joined.
07:39:31 -!- FreeFull_ has quit.
07:57:23 <ion> Chess Clock Jenga http://youtu.be/YN_F9bNuF0I
08:04:34 <Jafet> Disney funds 3D printing research https://youtu.be/qc-tGbMN9Ms
08:05:14 <kmc> ion: awesome
08:21:52 <oerjan> as for freefall, i am not sure if those are the right people to bring to a debate on whether to exterminate all robots.
08:21:54 <ion> jafet: neat
08:22:26 <fizzie> I was hoping I'd get a less boring "spring season" street-outside-the-office-window time-lapse because today is, well, today, but all the colorful people seem to be in other parts of the campus.
08:25:35 <Jafet> What is so today about today?
08:25:44 <fizzie> http://en.wikipedia.org/wiki/Walpurgis_Night#Finland
08:26:38 <S1> Jafet: Nothing, duh
08:27:44 -!- Patashu has joined.
08:36:31 -!- augur has quit (Quit: Leaving...).
08:48:16 <Jafet> https://blog.mozilla.org/security/2014/04/24/10000-security-bug-bounty-for-certificate-verification
08:48:49 -!- Patashu_ has joined.
08:48:49 -!- Patashu has quit (Disconnected by services).
08:55:49 <oerjan> that iranian student in the comments needs to work on his english.
08:56:51 <oerjan> no jobs in iran. sanctions, you know.
08:57:40 <oerjan> perhaps mozilla can't even legally pay him if they wanted to...
08:57:46 <Jafet> Hmm, the same sanctions might prevent the transfer of a bug bounty
08:58:08 <Jafet> That must be why iranian hackers just go ahead and use their exploits
08:58:31 <kmc> $10,000 sounds like a lot until you think about how much good software developers make
08:58:37 <oerjan> it all becomes clear now.
08:58:57 <kmc> (in america, anyway)
08:59:02 <Jafet> You can be a good software developer not in california
08:59:09 <oerjan> kmc: so you are saying you earn more in a day?
08:59:32 <fizzie> oerjan: Are you just brazenly assuming kmc is a good software developer?
08:59:58 <Jafet> Come on, let's not get all offended or anything.
09:00:02 <oerjan> fizzie: i have somehow associated "filthy rich" with him.
09:00:17 <Jafet> Besides, this bug bounty seems to have more to do with bad software developers
09:00:47 <fizzie> oerjan: As a Norwegian, you're supposed to be filthy rich too, don't you all have heaps and heaps of oil money?
09:01:01 <fizzie> I assume it works so that you just get money for free.
09:01:40 <kmc> sadly, i am not filthy rich
09:01:42 <oerjan> fizzie: surprisingly, i cannot get access to my 1 million NOK part of it at all.
09:02:03 <oerjan> (yep, the oil fund is that much)
09:02:53 <oerjan> in something expensive, i assume.
09:02:53 <fizzie> I just assume kmc with mushrooms.
09:02:59 <fizzie> Associate, not assume.
09:03:23 <kmc> if you have running water in your house, you are pretty rich by global standardz
09:04:02 <Jafet> Oh no, it's the Perspective Man
09:04:22 <fizzie> Does whatever a perspective can?
09:04:23 <oerjan> come to think of it, i saw something about san francisco it workers suing companies for collusion to keep down wages, so perhaps you are actually dirt poor. (don't remember if it was kmc who linked it.)
09:04:49 <oerjan> possibly i saw it on reddit.
09:04:51 <fizzie> You're either filthy rich or dirt poor, only the middle class keeps clean.
09:05:12 -!- mhi^ has joined.
09:07:12 <fizzie> I am making too many slides. :/
09:07:46 <kmc> http://www.symmetrymagazine.org/article/march-2014/physics-by-hand "To encourage discussion and engagement, a physics forum has banned PowerPoint slides in favor of low-tech whiteboards."
09:08:45 <fizzie> I don't think there will even be a whiteboard there.
09:08:52 -!- curiousguy13 has joined.
09:08:54 <fizzie> Or at least I wouldn't take one for granted.
09:09:08 <kmc> what are you presenting?
09:10:01 <fizzie> For 15 minutes, plus 5 for "questions from the audience and some extra time to introduce the next presenter".
09:11:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:12:07 <fizzie> I don't think there will be a lot of "discussion and engagement".
09:12:58 <oerjan> just auction off the extra slides hth
09:13:41 <kmc> for advertising?
09:14:23 <oerjan> just tell them they'll be worth a lot when you become famous.
09:15:42 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
09:17:01 <fizzie> I'm not sure which ones are the extra ones, to be honest.
09:37:08 -!- conehead has quit (Quit: Computer has gone to sleep).
09:37:17 -!- oerjan has quit (Quit: leaving).
10:19:48 -!- boily has joined.
10:28:55 -!- Phantom_Hoover has joined.
10:30:20 -!- yorick has joined.
10:44:07 <Jafet> Hmm, the zsh builtin time doesn't work on zsh functions.
10:56:41 -!- curiousguy13 has quit (Read error: Connection reset by peer).
10:58:59 -!- curiousguy13 has joined.
10:59:36 -!- mhi^ has quit (Quit: Lost terminal).
11:00:38 -!- boily has quit (Quit: HUMID CHICKEN).
11:14:41 -!- password2 has quit (Ping timeout: 264 seconds).
11:19:15 -!- nooodl has joined.
11:22:02 -!- curiousguy13 has quit (Ping timeout: 255 seconds).
11:24:23 -!- curiousguy13 has joined.
11:24:25 <Taneb> Help I can't use tmux
11:50:47 <shachaf> screen doesn't support four-byte utf-8 sequences
11:51:15 -!- S1 has joined.
11:53:32 <HackEgo> [U+0429 CYRILLIC CAPITAL LETTER SHCHA]
11:54:18 -!- nucular has joined.
11:54:18 -!- nucular has quit (Changing host).
11:54:18 -!- nucular has joined.
11:59:01 <Jafet> `run python -c 'pass; pass; pass'
11:59:41 <S1> Who did make HackEgo?
12:06:40 <Jafet> A long time ago, in a galaxy
12:07:58 <Jafet> Hmm, the old hg log is gone.
12:08:11 <Jafet> This means we'll... never know?
12:08:25 <S1> we could just ask, could'nt we?
12:09:31 <Jafet> You're ruining the moment.
12:09:50 <S1> You're right. We'll probably never know...
12:10:30 <S1> HackEgo is ancient technology
12:11:23 <Taneb> I made a thing help
12:11:24 <Taneb> https://github.com/Taneb/webqueues/blob/master/Main.hs
12:11:27 <Taneb> And now I have to go
12:11:38 <Taneb> Am I showing off? Do I want code reviews?
12:11:39 <b_jonas> `run echo $BASH_VERSION; perl -ewarn\$]; ruby -v
12:11:39 <HackEgo> 4.2.37(1)-release \ 5.014002 at -e line 1. \ bash: ruby: command not found
12:11:42 <Taneb> YOU WILL NEVER KNOW
12:12:17 <S1> Yes. I will never know o.o
12:13:37 <b_jonas> `run python --version; python3 --version
12:13:37 <HackEgo> Python 2.7.3 \ bash: python3: command not found
12:14:59 <Jafet> Taneb: you seem rather RESTless
12:16:10 <Jafet> Nevermind, I misread
12:17:22 <b_jonas> `run (shopt -s nullglob; IFS=:; for x in $PATH; do echo -n "$x"/ruby*; done);
12:17:30 <b_jonas> `run (shopt -s nullglob; IFS=:; for x in $PATH; do echo -n "$x"/python*; done);
12:17:31 <HackEgo> /usr/bin/python /usr/bin/python2 /usr/bin/python2.6 /usr/bin/python2.7
12:17:36 <b_jonas> `run (shopt -s nullglob; IFS=:; for x in $PATH; do echo -n "$x"/perl*; done);
12:17:37 <HackEgo> /hackenv/bin/perl-e/usr/bin/perl /usr/bin/perl5.14.2 /usr/bin/perlbug /usr/bin/perldoc /usr/bin/perlivp /usr/bin/perlthanks
12:18:07 <Jafet> Nevernevermind, it is restless
12:18:59 <Jafet> `file bin/perl-e/usr/bin/perl
12:18:59 <HackEgo> bin/perl-e/usr/bin/perl: ERROR: cannot open `bin/perl-e/usr/bin/perl' (Not a directory)
12:19:39 <HackEgo> bin/perl-e: Bourne-Again shell script, ASCII text executable
12:19:43 <HackEgo> #!/bin/bash \ perl -e "$@"
12:36:34 <int-e> `perl-e 1while(1x++$_)=~/^(11+)\1+$/||print"$_\n"
12:37:04 <HackEgo> 1 \ 2 \ 3 \ 5 \ 7 \ 11 \ 13 \ 17 \ 19 \ 23 \ 29 \ 31 \ 37 \ 41 \ 43 \ 47 \ 53 \ 59 \ 61 \ 67 \ 71 \ 73 \ 79 \ 83 \ 89 \ 97 \ 101 \ 103 \ 107 \ 109 \ 113 \ 127 \ 131 \ 137 \ 139 \ 149 \ 151 \ 157 \ 163 \ 167 \ 173 \ 179 \ 181 \ 191 \ 193 \ 197 \ 199 \ 211 \ 223 \ 227 \ 229 \ 233 \ 239 \ 241 \ 251 \ 257 \ 263 \ 269 \ 271 \ 277 \ 281 \ 283 \ 293 \ 307
12:42:22 <Jafet> For a moment I thought 1while was some strange new keyword
12:43:26 <Jafet> Also, why is 1 printed?
12:49:29 <Jafet> `perl-e 1while(1x++$_)=~/^1|(11+)\1+$/||print"$_\n"
12:50:02 -!- ais523_ has joined.
12:50:15 <int-e> Jafet: 1 cannot be factored into two factors >= 2.
12:51:20 -!- FreeFull has joined.
12:54:09 <b_jonas> `perl $==1,(1x$_)=~/(^)(1|11\1)*(?{$=++})^/,print$=,$/for 0..20
12:54:09 <HackEgo> Can't open perl script "$==1,(1x$_)=~/(^)(1|11\1)*(?{$=++})^/,print$=,$/for 0..20": No such file or directory
12:54:14 <b_jonas> `perl-e $==1,(1x$_)=~/(^)(1|11\1)*(?{$=++})^/,print$=,$/for 0..20
12:54:15 <HackEgo> 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657
12:54:32 <b_jonas> `perl-e $==0,(1x$_)=~/^(|()1(?1)(?1)\2)$(?{$=++})^/,print$=,$/for 0..13
12:54:36 <HackEgo> 1 \ 1 \ 2 \ 5 \ 14 \ 42 \ 132 \ 429 \ 1430 \ 4862 \ 16796 \ 58786 \ 208012 \ 742900
12:54:49 -!- Sgeo has quit (Read error: Connection reset by peer).
12:57:55 <FreeFull> b_jonas: What sequence is that?
12:58:42 <FreeFull> Are you trying to do fibbonacci?
13:01:08 <Jafet> `perl-e $a=1;1while($c=$a+$b,$a=$b,print$b=$c,"\n")
13:01:08 <HackEgo> 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657 \ 46368 \ 75025 \ 121393 \ 196418 \ 317811 \ 514229 \ 832040 \ 1346269 \ 2178309 \ 3524578 \ 5702887 \ 9227465 \ 14930352 \ 24157817 \ 39088169 \ 63245986 \ 102334155 \ 165580141 \ 267914296 \ 433494437 \ 701408733 \ 1134
13:01:09 <int-e> F_n = number of ways to decompose the string 1^n into 1 or 11. Right.
13:01:32 <int-e> which is approximately what (1x$_)=~/(^)(1|11\1)*(?{$=++})^/ does.
13:02:55 <FreeFull> There probably is some formula for it
13:03:11 <slereah_> Is there a simple way to make C display some very simple graphics on linux?
13:03:21 <slereah_> I'm talking like a few pixels wide
13:03:34 <nortti> writing to framebuffer?
13:03:54 <FreeFull> Depends on what kind of graphics hardware you have
13:04:52 <FreeFull> I'm assuming plain linux, without even GNU tools or such
13:05:15 <slereah_> I'm trying to check how well my neural network is working
13:05:19 <int-e> `perl-e $==1,(1x$_)=~/^11(1|11)*(?{$=++})^/,print$=,$/for 0..10
13:05:19 <HackEgo> 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 11 \ 13 \ 15 \ 17 \ 19
13:05:27 <slereah_> And I have a big one in my skullbox
13:05:35 <slereah_> So lookin' will probably easier
13:05:38 <FreeFull> int-e: Not sure that looks right
13:05:45 <int-e> FreeFull: it doesn't.
13:06:32 <int-e> So that's the point of the \1
13:06:43 <int-e> `perl-e $==1,(1x$_)=~/(^)11(1|11\1)*(?{$=++})^/,print$=,$/for 0..10
13:06:44 <HackEgo> 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89
13:07:24 <int-e> exploiting the backtracking implementation in perl
13:07:45 <ais523_> oh, not exactly, it's generating a number in unary, and then regexing against it to try to produce the fibonacci sequence in the number of matches
13:08:20 <FreeFull> I'm calculating it by hand and I'm getting fibbonacci so far..
13:09:05 <FreeFull> Are you sure this series isn't just the fibbonacci series?
13:09:15 <int-e> FreeFull: 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 11 \ 13 \ 15 \ 17 \ 19 wasn't
13:09:49 <FreeFull> int-e: When I calculate it by hand I get 1 2 3 5 8 13
13:10:25 <int-e> yes, that's what you should get
13:19:17 -!- nooodl has quit (Quit: Leaving).
13:26:46 <b_jonas> FreeFull: fibonacci and catalan numbers
13:27:05 <b_jonas> FreeFull: I showed two perl scripts, one computes fibonacci, one computes catalan
13:27:51 <b_jonas> here: http://www.perlmonks.com/?node_id=796712
13:29:01 <b_jonas> it links to my explanation: http://www.perlmonks.com/?node_id=796712
13:29:47 <lambdabot> [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,2...
13:30:03 <lambdabot> [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1...
13:30:07 <Jafet> > "http://www.perlmonks.com/?node_id=796712" `compare` "http://www.perlmonks.com/?node_id=796712"
13:31:06 <b_jonas> find where it links yourself then
13:31:41 <FreeFull> I forgot how to fibbonacci with scanl
13:32:17 <b_jonas> FreeFull: does that involve the case C specifically forbids, where the input overlaps the output?
13:33:17 <lambdabot> [1,1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192,16384,32768,65536,131072...
13:34:03 <b_jonas> oh, you said scanl, not scanf
13:35:49 <FreeFull> I don't think you can fibbonacci with scanf, although I might be wrong
13:45:06 -!- Patashu_ has quit (Ping timeout: 252 seconds).
13:50:53 -!- Sprocklem has quit (Read error: Operation timed out).
13:51:54 <ais523_> I registered for it because I have to for this new job
13:52:03 <ais523_> they sent me an email "ais523 + GitHub = <3"
13:52:11 <ais523_> also they don't require a password confirm to create an account
13:52:24 <ais523_> I had to change the password to itself just to get a password confirm box and thus be relatively sure it was typed correctly
13:53:17 -!- curiousguy13 has left.
13:55:19 <int-e> > let f = 0:scanl(+)1f in f
13:55:20 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
13:57:41 <fizzie> Now I have 30 slides for 15 minutes. :/
13:58:19 <int-e> Wee. Gotta talk fast :P
14:01:42 <fizzie> Some of them are just overhead, though. (Title, references, an otherwise empty slide with a giant question mark for the questions, and 7 automatically inserted "outline with position indicator" slides to have some structure in it.)
14:02:01 <fizzie> So 20 with any content, and some of *those* are just pictures. Maybe it isn't so bad.
14:10:41 <int-e> `perl-e $==0,(1x$_)=~/(^)(1|11\1)*$(?{$=++})^/,print$=,$/for 0..10
14:10:42 <HackEgo> 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89
14:12:00 <ais523_> is that \1 simply there to defeat the regex optimizer?
14:15:03 <int-e> `perl-e $==0,(1x$_)=~/^(1|11)*$(?{$=++})^/,print$=,$/for 0..10
14:15:03 <HackEgo> 1 \ 1 \ 2 \ 2 \ 2 \ 2 \ 2 \ 2 \ 2 \ 2 \ 2
14:16:04 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
14:20:33 -!- edwardk has quit (Quit: Computer has gone to sleep.).
14:23:01 <Jafet> `perl-e $==0,(1x$_)=~/(^)(1|11\1)+$(?{$=++})^/,print$=,$/for 0..10
14:23:02 <HackEgo> 0 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89
14:24:00 <int-e> `perl-e $==0,(1x$_)=~/^1(1|11)*$(?{$=++})^/,print$=,$/for 0..10
14:24:01 <HackEgo> 0 \ 1 \ 1 \ 2 \ 3 \ 3 \ 3 \ 3 \ 3 \ 3 \ 3
14:24:19 <int-e> `perl-e $==0,(1x$_)=~/(^)1(1|11\1)*$(?{$=++})^/,print$=,$/for 0..10
14:24:19 <HackEgo> 0 \ 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55
14:26:02 <int-e> ack, (?1) is recursion. who in their right mind adds explicit recursion to a regex engine ...
14:26:25 <ais523_> int-e: because without it, you can't match brackers, or parse HTML
14:26:37 <Jafet> The same people who add arbitrary code execution to a regex enging
14:26:44 <ais523_> if you're trying to write a DSL for matching patterns in strings, recursion is something you want
14:26:52 <ais523_> actually, they added the arbitrary code thing to see how it was used
14:26:57 <ais523_> and using it for recursion was the #1 use by miles
14:27:01 <ais523_> so they added a separate recursion primitive
14:27:24 <ais523_> we used to write my $regex = qr/<(??{$regex})>/; if we wanted to match angle brackets
14:27:36 <Jafet> Good language design
14:28:03 <ais523_> nowadays /<(?0)>/ works fine
14:28:48 <Jafet> I wonder if there is a regex without the perl
14:29:11 <int-e> shouldn't that be /<(?0)>(?0)/
14:29:23 <ais523_> it depends on what you want the regex to mean
14:29:24 <Jafet> > let f n | n < 4 = True | otherwise = or [ f a && f (a + b) | a <- [1..n], b <- [1..n], n = 2*a + b, a > b ] in filter f [0..100]
14:29:26 <lambdabot> <hint>:1:90: parse error on input ‘=’
14:29:34 <Jafet> > let f n | n < 4 = True | otherwise = or [ f a && f (a + b) | a <- [1..n], b <- [1..n], let n = 2*a + b, a > b ] in filter f [0..100]
14:29:35 <lambdabot> [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,2...
14:29:41 <int-e> I want to match <<><>> too, for example.
14:29:45 <ais523_> Jafet: PCRE is the Perl sort, but you also get mathematical regexes that use only + and *, and POSIX regexes which suck
14:29:56 <Jafet> > let f n | n < 4 = True | otherwise = or [ f a && f b && f (a + b) | a <- [1..n], b <- [1..n], let n = 2*a + b, a > b ] in filter f [0..100]
14:29:58 <lambdabot> [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,2...
14:30:01 <ais523_> int-e: right; that isn't what I wanted, I just wanted the simplest possble example
14:30:07 <ais523_> but if you want something more complex, you write a more complex regex
14:30:17 <Jafet> Wait, what am I typing
14:30:18 <Jafet> > let f n | n < 4 = True | otherwise = or [ f a && f (a + b) | a <- [1..n], b <- [1..n], n == 2*a + b, a > b ] in filter f [0..100]
14:30:28 <Jafet> > let f n | n < 4 = True | otherwise = or [ f a && f (a + b) | a <- [1..n], b <- [1..n], n == 2*a + b, a > b ] in filter f [0..50]
14:30:49 <Jafet> I can't see how a regex can recognize a>b, though
14:31:37 <ais523_> what's the representation of a and b
14:31:44 <ais523_> you can do it with just backreferences if it's unary
14:31:57 <ais523_> I was talking to Jafet, yours is obviously unary
14:32:26 <Jafet> Hmm, it's possible to combine multiple tests using lookahead
14:33:06 <ais523_> anyway, last time I thought along these lines, I ended up inventing Cyclexa
14:33:24 <ais523_> it had things like negative matches, e.g. /^(xyz)^xyzabc$/ matches "abc"
14:33:31 <ais523_> because (xyz)^ matches minus an xyz
14:34:01 <Jafet> What is minus xyz?
14:34:27 <ais523_> basically, normally when you're interpreting a regex, you can think of it as a backtracking program that removes from the string
14:34:32 <ais523_> e.g. "x" means "remove an x"
14:34:41 <ais523_> thus "(x)^" means "add an x to the start of the string"
14:35:06 <Jafet> Ok, so minus adds.
14:36:00 <Jafet> Is it basically pushdown, then?
14:36:02 <ais523_> yeah, except it gets confusing when you do things like (abc(xyz)^def)^
14:36:11 <ais523_> I can't even remember what semantics I designed for that, if anything
14:37:10 <Jafet> Presumably a^b would fail to match anything
14:37:27 <ais523_> the other feature it had was control flow matching
14:37:50 <ais523_> you could do "(a|b)(c|d):1", which is equivalent to "ac|bd"
14:37:52 <Jafet> (a^)^ would... equal a?
14:40:20 <b_jonas> the fun part about recursion in perl regexen is that some of the semantics is unclear if it's combined with backreferences,
14:40:49 <b_jonas> there's now an open bug ticket that is waiting for regex guru to weigh in with their opinion on what the semantics should be,
14:41:02 <b_jonas> then the regex engine guru will try to implement that consistently if possible.
14:41:05 <ais523_> they should recruit the Perl half of the anarchy golf userbase
14:41:12 <b_jonas> the current implementation is inconsistent.
14:41:41 <ais523_> you do a backreference in Cyclexa by combining recursion with control flow matching
14:42:02 <ais523_> the real aim for control flow matching, though
14:42:03 <b_jonas> I mean, I noticed this inconsistency because of that catalan numbers regex I mentioned above
14:42:21 <ais523_> is to do things like (a$1?)(b$2?):1(c$3?):1
14:42:36 <ais523_> look, now I'm not a PDA any more!
14:42:44 <ais523_> not sure if it's actually TC, or just some sort of super-PDA class
14:43:39 <ais523_> that Cyclexa regex matches any number of 'a', followed by the same number of 'b', followed by the same number of 'c'
14:43:43 <ais523_> you can't do that using recursion
14:43:59 <ais523_> (that can match the 'a' with the 'b', but not with the 'c' as well)
14:45:09 <mroman> I thought regexes couldn't do that
14:45:13 <nortti> wouldn't call that a regexp anymore, myself
14:45:40 <Jafet> You might be able to reduce some kind of post correspondence or tags to it
14:46:08 <nortti> mroman: regexes cannot even do n times 'a' followed by n times 'b', since they are limited to regular grammars
14:46:36 <ais523_> PCRE, which is an extension from regexes, can do n*'a' + n*'b'
14:46:44 <ais523_> actual mathematical regular expressions cannot even do that
14:46:57 <mroman> a{3}b{3} matches aaabbb
14:47:14 <ais523_> yeah but that's just sugar for writing aaabbb literally
14:47:18 <mroman> but a{n}b{n+1} kinda regexs would be much more fun
14:47:29 <ais523_> it's like writing (a)*3(b)*3 in BF Joust
14:47:32 <Jafet> Like, (a|b)^*((a1|a2|a3...)*)((b1|b2|b3...)*) simulates a post correspondence system with cards [a1,b1], [a2,b2] ...
14:48:00 <ais523_> Jafet: I'm unaware of that formalization
14:48:05 <ais523_> looks like an interesting thing to try to reduce to
14:48:14 <Jafet> (with :1, defined suitably)
14:48:22 <nortti> is there a term for grammars one can recognise using only '|' and '('+')' operators?
14:48:56 <nortti> (basically, mathematical regexes without klein start)
14:49:41 <nortti> also the grammars that can be recognised by a bolean circuit or a bounded storage machine with bounded input or a decision tree
14:50:47 <Jafet> Actually, ((0|1)^*end)\1((a1|a2|a3...)*end)((b1|b2|b3...)*end):1
14:52:11 <int-e> `perl-e $==0,(1x$_)=~/^(1?1?1?$|(1+)(?!\2\2)(?=(?1))1+(?=(?1))\2$)/&&print$_,$/for 0..100
14:52:20 <Jafet> nortti: do you not want the sequence operator
14:52:34 <HackEgo> 0 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89
14:52:44 <nortti> Jafet: sequence operator?
14:52:45 <Jafet> (parens are not normally considered operators)
14:52:52 <int-e> (following Jafet's idea)
14:53:11 <Jafet> int-e: I merely inquired whether it was remotely possible
14:53:18 -!- Sprocklem has joined.
14:53:38 <nortti> ok, found the term, "non-recursive grammars"
14:53:44 <int-e> Jafet: note the (?!\2\2) which encodes the a>b condition.
14:55:21 <nortti> wait, no, "star-free language" seems to be exactly what I'm looking for, but it seems like it can recognise something a decision tree cannot O_o
14:56:14 <Jafet> Are you matching AAB or ABA?
14:56:48 <int-e> so both A and BA become tails
14:58:31 <int-e> and (?=(?1)) checks whether a tail is a fibonacci number.
15:00:58 <Jafet> So, using ABA order is actually mandatory.
15:05:58 <Jafet> This regex really doesn't deserve to exist. It's bad enough that we need to supply the first 4 values, and the rest of the sequence happens to be exponentially sparse so that no spurious matches are possible
15:07:52 <int-e> look-ahead assertion
15:08:04 <Jafet> nortti: star-free languages allow complement. Otherwise it gets a bit boring theoretically, because every language matches a small finite set of strings
15:08:20 <ais523_> I mostly only use lookbehind
15:10:04 <nortti> actually, can't you simulate complement on a finite alphabet?
15:18:39 -!- edwardk has joined.
15:27:34 -!- edwardk_ has joined.
15:28:54 -!- edwardk_ has quit (Client Quit).
15:30:14 -!- edwardk has quit (Ping timeout: 276 seconds).
15:36:01 -!- oerjan has joined.
15:36:18 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
15:42:01 <HackEgo> olist 950: shachaf oerjan Sgeo FireFly boily nortti
15:49:56 -!- kronion_ has joined.
15:53:33 <FireFly> http://dirk.rave.org/combinatris/
15:54:22 -!- kronion_ has quit (Client Quit).
15:54:23 -!- Phantom_Hoover has joined.
15:55:04 -!- slereah_ has quit (Quit: Leaving).
15:58:29 <oerjan> oops i thought that one would be harmless but it grew too high
16:00:40 <ais523_> what sort of mean Tetris drops Y combinators on people?
16:14:28 <Jafet> The rows are independent? That's not very interesting
16:14:51 <Jafet> Also there are too many Ks
16:15:46 <oerjan> it seems like it starts producing more ( )'s after a while
16:16:12 <oerjan> which are afaict impossible to handle
16:18:39 <FreeFull> You just need to fill them up and K them
16:23:06 <FireFly> I found the parens to be the most nasty
16:23:14 <FireFly> The Ys are easy to kill by applying them to K
16:26:47 <oerjan> K is very important for shrinking other things
16:29:45 -!- edwardk has joined.
16:34:42 -!- MoALTz has joined.
16:37:10 <oerjan> FreeFull: yeah that's the only thing they're useful for too
16:38:18 -!- augur has joined.
16:40:27 <oerjan> also, Y is absorbed by K(YK) which you get from YK
16:40:51 <oerjan> so if you have just one line with those you have no trouble with Y's until it gets too fast
16:42:13 <newsham> so we (US) gave out $11B in GM bailout...
16:42:25 <newsham> yet we constantly want to cut services for the poor.
16:42:45 <coppro> newsham: but not jobs. because jobs.
16:42:46 -!- ^v has joined.
16:46:03 <nortti> http://pastebin.com/qh6Tta3h
16:52:18 -!- augur has quit (Ping timeout: 240 seconds).
16:56:30 -!- augur has joined.
17:17:06 <newsham> job creators got our backs
17:20:16 <Bike> seeing leaks on pastebin is always so weird since there's literally no proof of anything
17:23:47 -!- ais523_ has left.
17:23:53 -!- ais523_ has joined.
17:24:39 <Taneb> Genetically Modified Bailout!?
17:25:07 <Phantom_Hoover> they don't; clearly they're being paid off by google's rivals
17:26:16 <Taneb> I'm going to talk about incompleteness tonight
17:26:41 <oerjan> Taneb: will the talk be cut short twh
17:29:20 <Taneb> I know that feeling
17:29:32 <Taneb> I'm sloooowly planning a talk on category theory
17:29:50 <ais523_> that's simple; first, work out what you want to talk about
17:29:57 <ais523_> second, work out the identities for everything you want to talk about
17:30:20 <ais523_> you can consider adding in morphisms between things you want to talk about if you want to go really advanced, but make sure they compose correctly
17:30:46 <oerjan> the first talk i did apparently went well except for the part where i stood paralyzed for a minute until my advisor shouted at me.
17:32:19 <Taneb> Ooh! My first talk about esolangs went pretty well
17:32:52 <Taneb> Only talk the society bothered to put on YouTube
17:33:23 <ais523_> what is the society about? not talking about esolangs, presumably
17:34:04 <Taneb> Ostensibly, Computer Science
17:34:30 <oerjan> Taneb: are they about as much about computer science as this channel is about esolangs?
17:34:41 <Taneb> oerjan, I'd say perhaps
17:34:59 <Taneb> Although we are mostly computer science students
17:35:47 -!- password2 has joined.
17:35:57 <Taneb> Well, of the paid members, there's two CS/Maths students (including me), one maths student, one person who seems to be confused about degree she's doing and has been at the university for as long as anyone can remember, and one retired CS lecturer
17:36:09 <oerjan> i was going to make a joke about everyone here being esolangers, but then i remembered kmc has ops.
17:36:21 -!- password2 has quit (Max SendQ exceeded).
17:36:39 <Taneb> I think I may be in the unique position that the first programming language I ever learnt was esoteric
17:36:49 <fizzie> fungot: Would you like to give my Saturday talk in my stead?
17:36:50 <fungot> fizzie: he knew his room was in the sky. and now the being was still there sunday noon when a telephone message came from the black northeast corner a shaft of horrible red-gold fnord shaft which bore with it no glow to disperse the darkness, fallacy and ugliness which have turned the mind of joseph curwen, and that will mark the true resting-place of your son. nor need you fear that it will be observed that at this juncture, b
17:36:55 -!- password2 has joined.
17:37:14 <fizzie> I wonder what they'd say if I went there and started reading fungot.
17:37:14 <fungot> fizzie: then there was only the prologue of the actual place he sought? he was a victim of physical and nervous suffering, as was stated, in a sense the father of gods had fnord his glories for the sight of any land. on the night of fnord april the new development occurred. while nothing appeared to grow different in kind, and dozens of obscurer ones too elusive to be described, which wears a yellow silken mask over its face an
17:37:26 <fizzie> Esp. whether they'd catch on if I trained a language model on my paper.
17:37:48 <Taneb> fizzie, what is your paper on?
17:38:14 <fizzie> Boring stuff. Reverberation-robust speech recognition.
17:38:16 <oerjan> Taneb: are you sure she's not a ghost twh
17:39:23 <Taneb> I think it's she got bored of her computer science degree on her third third year
17:39:30 <oerjan> fizzie: hey you might actually be able to claim it was on topic
17:39:46 <oerjan> maybe not for that paper
17:40:03 <int-e> oh, burn. "There are many choices of elliptic-curve signature systems. The standard choice, ECDSA, is reasonable if you don't care about simplicity, speed, and security."
17:40:27 <int-e> (More than a month old though. From http://blog.cr.yp.to/ )
17:40:31 <oerjan> is that the one with the nsa backdoor
17:41:54 <int-e> It's not if you believe their denials.
17:43:03 <Taneb> Phantom_Hoover, the esolangs one or the category theory one?
17:43:21 <Taneb> I believe the former mentioned it as a "further reading"
17:43:30 <Taneb> The latter probably will not
17:43:39 -!- drdanmaku has joined.
17:46:17 <int-e> oerjan: This is unrelated to the heartbeat extension implementation disaster that made the news.
17:46:39 -!- newsham has quit (Quit: reboot).
17:47:33 <Taneb> My uni has a folklore file which mentions the "new" and "even newer" computer science buildings.
17:47:41 <Taneb> Neither of them are the current computer science buildings.
17:49:16 -!- Froox has quit (Quit: *bubbles away*).
17:50:17 <fizzie> The latest news of the CS student guild's computer classrooms is that they've started to replace the SGI Indys with Pentium 4 FreeBSD machines; that was in 2002.
17:51:00 <fizzie> Though I think the classroom map has been updated since then, because it has the esolang-based hostnames that weren't there when I used to visit the place (around 2003-2008).
17:51:42 <Taneb> The... student guild has their own classrooms!?
17:51:56 <oerjan> int-e: well heartbeat had nothing to do with which encryption to use afair...
17:52:32 -!- Frooxius has joined.
17:52:56 <Sprocklem> Taneb: How old is the folklore file?
17:52:57 <fizzie> Taneb: I don't know the actual details of fiscal ownership of the equipment, but it's at least quite collaborative.
17:53:09 <Taneb> Sprocklem, hard to date
17:53:16 <fizzie> Taneb: The room itself is provided by the university, though.
17:53:36 <Taneb> Sprocklem, certainly before 2010
17:54:23 <Taneb> Sprocklem, here is the stablest mirror: http://klaxon.hacksoc.org/uni_history/
17:54:29 <fizzie> They currently have the following hosts in the single remaining classroom: befunge bit bogo brainfuck chef deadfish emo entropy false fractran fugue glass haifu headache intercal iota kvikkalkul lolcode malbolge numberwang ook oisc thue piet regexpl remorse rename shakespeare smith smurf spaghetti unlambda var-aq wake whenever whitespace zombie
17:54:58 <Bike> whatever indeed
17:55:48 <fizzie> http://www.niksula.hut.fi/historia <- classroom history page, but it's in Finnish only.
17:58:15 <Taneb> The last date mentioned in the folklore file refers to the academic year 2008/09
17:58:36 <Taneb> The very new CS building opened its doors in September 2010
17:59:07 <oerjan> i thought english universities would have their folklore files written on parchment.
17:59:43 <Taneb> oerjan, we're a pretty new institution
18:00:06 <Taneb> With the highest duck:student ratio of any university in the EU!
18:00:12 <Bike> yeah but in england "pretty new" just means after the reformation
18:00:34 <lexande> Bike: there are only two universities in england older than that
18:00:46 <Bike> yes but they're the ones i could name!
18:01:36 <Taneb> Bike, this uni dates to 1963
18:01:41 <Bike> huh, three in scotland though. way to fuck up, england
18:01:43 <lexande> i think "pretty new" in the UK means post-1960
18:01:55 <Taneb> Anyway, I have a talk to go to!
18:02:25 <lexande> Taneb: does being russell group make you not "pretty new" anymore?
18:09:07 -!- Sprocklem has quit (Ping timeout: 245 seconds).
18:22:30 -!- conehead has joined.
18:46:32 -!- CodingBat has joined.
18:49:06 <lambdabot> (Zoom m n s t, Control.Lens.Internal.Zoom.Zoomed n ~ Control.Lens.Internal.Zoom.Zoomed m) => LensLike' (Control.Lens.Internal.Zoom.Zoomed m c) t s -> m c -> n c
19:00:01 <shachaf> oerjan: olist 950 has been out for a week or something
19:01:00 <oerjan> so why did no one `olist it
19:01:13 <oerjan> oh hm right HackEgo was down
19:02:16 -!- CodingBat has quit (Quit: Page closed).
19:07:54 -!- password2 has quit (Ping timeout: 240 seconds).
19:16:36 <ais523_> happy Australian Mailman mailing list reminders day!
19:17:24 <ais523_> wait, how can someone as #esoteric-regular as Slereah not be aware of that tradition
19:17:48 <ais523_> I even took trouble to put all the words in so that elliott wouldn't shout at me (although I didn't particularly care about the capitalization)
19:17:49 <Slereah> I am kind of an on and off regular
19:18:03 <ais523_> basically, Mailman sends out mailing list reminders on the first day of every month
19:18:08 <elliott> ais523_: you didn't get all the words
19:18:10 <ais523_> but when the mailing lists are in Australia, New Zealand, or similar
19:18:20 <elliott> but I no longer really care
19:18:22 <ais523_> they come like 12 hours early because of timezones
19:18:31 <ais523_> so it's the last day of the preceding month instead
19:18:48 <elliott> look at the subject of the email
19:19:31 <ais523_> perhaps I should actually read one of these emails, some day
19:20:22 <elliott> membership singular, isn't it
19:21:37 <ais523_> perhaps it depends on how many lists you're subscribed to?
19:22:13 <oerjan> mine has only one list
19:22:30 -!- CodingBat has joined.
19:22:49 <oerjan> the main agora lists stopped sending out reminders at some point
19:23:41 <ais523_> oerjan: probably when comex started hosting them
19:32:52 -!- augur has quit (Remote host closed the connection).
19:41:41 -!- CodingBat has quit (Quit: Page closed).
19:41:59 -!- CodingBat has joined.
19:48:35 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:02:41 -!- augur has joined.
20:07:01 -!- CodingBat has quit (Quit: Page closed).
20:19:20 -!- adu has joined.
20:22:25 -!- edwardk has quit (Ping timeout: 252 seconds).
20:26:48 <Slereah> http://www.qwantz.com/index.php?comic=2618
20:28:52 -!- Sprocklem has joined.
20:31:16 -!- kwertii has joined.
20:32:30 -!- nucular has quit (Quit: Switching to phone I guess).
20:34:23 -!- mhi^ has joined.
20:39:29 -!- CodingBat has joined.
20:42:49 -!- nisstyre has joined.
20:49:59 -!- augur has quit (Read error: Connection reset by peer).
20:50:28 -!- augur has joined.
20:51:28 -!- ^v has quit (Read error: Connection reset by peer).
20:51:49 -!- ^v has joined.
20:54:03 -!- CodingBat has quit (Quit: Page closed).
20:55:56 -!- Patashu has joined.
20:57:21 -!- Patashu_ has joined.
20:57:21 -!- Patashu has quit (Disconnected by services).
21:07:32 -!- adu has quit (Quit: adu).
21:08:43 -!- adu has joined.
21:11:35 -!- Patashu_ has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
21:11:53 -!- CodingBat has joined.
21:11:57 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
21:17:23 -!- Sprocklem has quit (Quit: leaving).
21:21:29 -!- FreeFull has quit (Ping timeout: 250 seconds).
21:26:21 -!- FreeFull has joined.
21:31:41 -!- ^v has joined.
21:36:35 -!- KingOfKarlsruhe has joined.
21:38:08 -!- adu has quit (Quit: adu).
21:54:25 -!- edwardk has joined.
21:54:39 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
21:55:18 -!- ^v has joined.
21:56:27 -!- augur_ has joined.
21:56:52 -!- augur has quit (Read error: Connection reset by peer).
22:05:30 -!- augur_ has quit (Ping timeout: 240 seconds).
22:08:43 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:11:45 -!- ais523_ has quit (Quit: Page closed).
22:24:21 <kmc> // This operator is needed for gcc <= 4.0.* and for Sun Studio; it causes internal compiler errors for some MSVC versions.
22:24:23 <kmc> template <class U, class V> U& operator->*(U V::* aMember)
22:29:42 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
22:29:42 -!- edwardk has joined.
22:29:55 -!- Sprocklem has joined.
22:36:13 -!- ^v has joined.
22:37:58 <^v> am i the first person to browse esolangs.org with a ps3 controller?
22:41:31 -!- oerjan has quit (Quit: leaving).
22:42:32 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:43:47 <CodingBat> why would anyone do that for starters?
22:45:11 <kmc> that operator? it's from a smart pointer class
22:45:34 <kmc> http://mxr.mozilla.org/mozilla-central/source/xpcom/base/nsAutoPtr.h#162
22:46:56 <Bike> "#define NS_ASSERTION(expr, str) do { /* nothing */ } while(0)" okay cool
22:47:37 -!- pdurbin has joined.
23:11:42 <Taneb> lexande, we're pretty new to the Russel group
23:20:54 <lexande> Taneb: yeah so maybe you're pretty new to not being pretty new
23:22:06 -!- augur has joined.
23:22:33 -!- Sgeo has joined.
23:22:58 <Taneb> lexande, also I've ended up pretty tipsy
23:24:50 <Bike> what is t his group
23:44:18 <kmc> wonder if I should actually learn how COM works
23:45:45 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
23:46:57 <kmc> so i can better understand Gecko code
23:47:06 <kmc> and because I like fancy C++ nonsense
23:48:19 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 29.0/20140421221237]).
23:49:22 <shachaf> except their ivy has been growing for way longer?
23:50:53 <kmc> i came back here and misread my own statement as "fancy C++ mushrooms"
23:50:58 <kmc> which sounds like something I would have a dream about
23:52:03 <shachaf> i had a dream in which mountain view's geography resembled that of boston
23:53:14 <kmc> how did that work
23:56:49 -!- Sorella has joined.
23:58:56 <Sgeo> Pure profunctor optics cheat sheet: http://www.snip2code.com/Snippet/46365/Profunctor-lenses
23:59:05 <Sgeo> I cannot vouch for its accuracy