2012-10-01: 00:04:08 it has been known to associate with certain ... identities. sometimes while commuting. 00:05:05 and it is also suspected of distribution, although we have no firm evidence 00:06:23 so we simply had to bust this ring. 00:06:33 oerjan: I'm sure you'll be abel to come up with something. 00:06:57 /kick oerjan 00:08:03 oerjan: If you manage to join their secret meet, you'll have a field day. 00:08:33 don't lattice get _all_ out of hand, now 00:24:04 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:35:37 darn wikipedia front page is knocking monads 00:37:03 kick oerjan 00:37:27 Monads are impossible for humans to understand 00:38:04 Lumpio-: is the joke that that's bullshit 00:38:49 itt: Lumpio- reveals himself to be soundnfury in disguise 00:39:08 well it is ok because we have kmc here to argue with tedious morons who say bullshit about haskell 00:39:10 that is his job 00:39:11 good old kmc 00:40:42 The joke is that it's the truth 00:40:58 Developers should stick to well-established and easily understandable industry-standard design patterns 00:41:26 Lumpio-: are you really this stupid hahahahahahahahaha 00:41:50 no way that last sentence wasn't a joke 00:41:55 I take it you have never experienced working in the enterprise. 00:42:08 ok yeah you are obviously just bullshitting at this point 00:42:52 We do not take kindly to propeller-cap wearing kids trying to replace our proven practice COBOL systems with their new fancy schmancy C or Haskell or whateveritis these days 00:43:06 there is no way you're not joking 00:43:06 monqy: You have 2 new messages. '/msg lambdabot @messages' to read them. 00:43:16 well obviously by now 00:43:20 so please stop!!! 00:43:30 we clearly is missing a language called whateveritis 00:43:34 *are 00:43:34 Would *you* have your stock transactions go through a "monad"? 00:43:41 I for one wouldn't. 00:43:56 nobody likes your joke stop it you're hurting our joke feelings 00:44:09 i know this because i conducted a joke meeting 00:44:15 we all agreed your joke is bad 00:44:15 Punched tape has worked perfectly fine for the last eleven decades and it's not going anywhere. 00:44:18 joke consortium 00:44:19 ¬u¬ 00:44:22 damn 00:44:28 joke council handing down joke fines 00:44:35 joke sentencing of joke jailtime 00:44:45 people get joke arrested and go to joke prison 00:44:48 but prison is no joke 00:44:50 I'll be sure to file an advance application the next time I feel like making a joke 00:45:02 ...in punched tape form 00:45:35 joke council accepts only .rtf 00:46:19 Not .docx!? 00:49:03 docx uses monads 00:50:20 it's been years since I've last seen an rtf 00:50:26 maybe not even a year since I've seen docx 00:51:19 I guess this means rtf is better??? 00:52:04 monqy: it's because geocities died and took all the rtfs with it : ( 01:03:30 pumpkin jokes.pdf 01:03:39 :O 01:13:56 -!- TeruFSX has joined. 01:32:12 -!- jiella has quit (Quit: Leaving.). 01:57:21 the nice thing about punched tape is it's human readable 01:57:45 -!- augur has quit (Read error: Connection reset by peer). 01:57:46 -!- augur_ has joined. 01:57:56 ^without electricity 01:58:34 because, you just know that any year now the property of technology that doesn't need electricity will become important for some reason 02:00:31 whoa 02:00:57 bec isn't supposed to lose his sword like that I think 02:03:08 itidus21: http://en.wikipedia.org/wiki/Dies_the_Fire hth 02:27:02 -!- oerjan has quit (Quit: Good night). 02:33:34 -!- hogeyui_ has quit (Ping timeout: 244 seconds). 02:34:25 "a mysterious worldwide event that suddenly alters physical laws so that electricity, gunpowder, and most other forms of high-energy-density technology no longer work." just because 02:37:12 Is that possible? I doubt it. Anyways, even if such things is possible, it may be a "universewide" event, not just the worldwide event. 02:42:19 -!- augur_ has quit (Read error: Connection reset by peer). 02:43:13 -!- augur has joined. 02:43:58 it doesn't have to be possible to be a good sci-fi premise 02:45:28 OK, but even in sci-fi, maybe it should be apply for universe, possibly other thing in universe also goes wrong later they realized later on 02:52:51 -!- augur has quit (Remote host closed the connection). 02:57:08 -!- augur has joined. 03:03:47 a special goo was invented such that an animal's form interpolates with the last animal it was in contact with 03:04:40 when you think about it, thats quite an impressive backstory to spin to account for anthropomorphic turtles 03:11:17 google translation shuffle from "once upon a time he said riddle me this." to "Time, he said to me once when this mystery." 03:21:06 -!- TeruFSX_ has joined. 03:32:10 -!- augur has quit (Remote host closed the connection). 03:51:38 -!- Jafet has joined. 04:37:24 How do I convert double to HWND type in C? 04:39:16 -!- ais523 has quit. 04:39:26 @hoogle Double -> HWND 04:39:26 Warning: Unknown type HWND 04:39:27 Unsafe.Coerce unsafeCoerce :: a -> b 04:39:27 Control.OldException throwDyn :: Typeable exception => exception -> b 04:39:45 "Warning: unknown type, but why not try unsafeCoerce anyway?" 04:40:20 I mean in C, not in Haskell. 04:41:19 this is one of those cases where I say something which is not 100% a serious suggestion 04:42:08 -!- augur has joined. 04:42:21 How to make a DLL in MinGW? 04:43:02 -!- TeruFSX has quit (Ping timeout: 256 seconds). 04:43:49 Something like g_hWnd=(HWND)(int)hwnd; seems to compile at least, but I don't know if it is correct, and it won't link, maybe I need some switch to tell it to make DLL? 04:46:20 I tried -Wl,--export-all-symbols -Wl,--dll but it doesn't work. 04:47:13 -!- hogeyui has joined. 04:49:40 Maybe it works now.... 04:50:50 zzo38: do you know a program that converts formatted text to .txt by wrapping italics in // and underlines in __ etc 04:52:10 quintopia: I don't know, but what file format is the input in? 04:52:49 what is formatted text 04:52:57 who cares? pdf, html, rtf? 04:53:08 well presumably you care since you wanted a program for it :P 04:53:17 there are html to markdown converters 04:53:25 well i'd like to know if it exists for any format 04:53:26 cf. http://milianw.de/projects/markdownify/ 04:54:03 quintopia: pandoc can convert stuff to markdown 04:54:25 html and latex in particular 04:54:34 though it's not, like, a full implementation of the TeX macro engine 04:55:58 cool 05:02:12 -!- FreeFull has quit (Quit: 6am). 05:32:24 -!- ais523 has joined. 06:38:52 -!- ais523 has quit (Read error: Connection reset by peer). 06:39:07 -!- ais523 has joined. 06:42:07 How good is ARCFOUR as just a random number generator? 07:15:38 -!- zzo38 has quit (Remote host closed the connection). 07:28:54 -!- ais523 has quit (Read error: Connection reset by peer). 07:41:13 -!- mtve has joined. 07:41:25 -!- AnotherTest has joined. 07:41:31 Hello 07:42:16 It's better than RANDU. 07:46:27 anyone go to the magic prerelease 07:46:59 -!- sivoais has quit (Ping timeout: 260 seconds). 07:47:44 I picked the Azorius guild 07:49:39 -!- dajfsa has quit (Quit: leaving). 07:59:54 -!- sivoais has joined. 09:01:56 -!- Sgeo has quit (Read error: Connection reset by peer). 09:09:56 -!- Sgeo has joined. 09:27:28 -!- ais523 has joined. 10:07:33 -!- Arc_Koen has joined. 10:08:13 -!- Arc_Koen has quit (Read error: Connection reset by peer). 10:08:28 -!- Arc_Koen has joined. 10:21:48 -!- copumpkin has quit (Ping timeout: 245 seconds). 10:22:25 -!- copumpkin has joined. 10:26:59 -!- carado has joined. 10:40:41 -!- carado has quit (Quit: Leaving). 11:08:16 -!- barts has joined. 11:11:16 -!- barts_ has quit (Ping timeout: 248 seconds). 11:22:57 -!- jiella has joined. 11:30:56 -!- monqy has quit (Quit: hello). 11:39:44 -!- kinoSi has quit (Read error: Connection reset by peer). 11:40:11 -!- kinoSi has joined. 12:06:05 -!- heroux_ has quit (Read error: Operation timed out). 12:10:28 -!- heroux has joined. 12:20:01 -!- Phantom_Hoover has joined. 12:30:58 hey sgeo 12:31:29 -!- boily has joined. 12:32:24 Hi 12:34:01 i agree 12:34:17 my tutor did his phd with ian stewart WHAT SAY YOU 12:35:11 I say I know why you're mentioning Ian Stewart to me, you are curious what my reaction is. 12:35:49 such insight 12:36:41 I want to see if I can find the quote 12:36:42 I would've said something irrelevant that fact is to me, but actually I'M VERY JEALOUS 12:37:22 that's nothing 12:37:38 There's a guy at UW who did his PhD under Hawking 12:38:23 "Page 435 is not part of this book preview" 12:38:36 Now I'm annoyed, since it now seems very likely that that's the exact page I want 12:39:13 why, what's on it 12:40:13 The part where there's an advertisement screaming something like "Supersymmetric Sisters!" or something like that, very uncomfortably reminiscent of quantum mechanics quackery 12:41:02 that sounds more like porn than physics to me :/ 12:41:02 Not at all convinced that the best approach to equality is "Hey! In some invisible dimensions, we actually have more sides than the men" 12:41:39 Actually, that wasn't the exact concept, but something similar to it 12:41:46 Number of symmatries I think 12:42:05 so in other words symmetry is entirely relevant 12:42:54 also he had coffee with terry pratchett once 12:42:59 he was 'surprisingly normal' 12:43:16 I think maybe trying to push for equality based on the idea that number of symmetries is irrelevent is better than "technically, we're better" 12:44:58 I was in the same room as hawking once is what say I 12:45:23 you dont have the same galactic scale as i coppro 12:45:24 Well, *I* see prof. (em.) Kohonen here every now and then! Uh... I guess that's not terribly impressive, he's maybe not exactly a household name. 12:45:51 for i can claim to have been on the same planet as hawking, and there are billions more planets than there are rooms! 12:46:20 http://i.imgur.com/OkbGc.jpg 12:46:43 not only that, but i managed to be alive at the same time as hawking! out of the ~14b yrs the universe has existed and at least that much more it will go on 12:46:51 I'm gonna puke 12:47:03 (Not for reasons relevant to this conversation) 12:48:09 "at least that much more it will go on" not if I have something to say about that! ...er, nothing. 12:50:11 -!- ogrom has joined. 12:55:58 -!- ais523 has quit (Ping timeout: 245 seconds). 12:56:29 fizzie: PROFESSOR KOHONEN?!??!?!?! 12:56:32 fizzie: Tell him he's my hero. 12:56:40 -!- aloril_ has quit (Ping timeout: 244 seconds). 12:57:06 tell him he's a mangy frua 13:04:53 fizzie: so I wanted to add a possibility for subroutines in Kipple, but I did not want to add new syntaxes 13:05:08 I made it so that stacks are executable, but that doesn't sound like Kipple at all 13:06:40 I saw something about that. It's not all *that* far off, really. 13:07:46 well I didn't write down what it meant to execute a stack exactly - for instance, should it be parsed already? or can it still contain whitespace and numbers expressed as multiple digits? 13:08:46 maybe I should just include a way to define and call functions... but as I said I don't really like the idea of new syntax - I'd like everything to use stacks 13:09:13 or maybe I should make functions, and include a special "call stack" 13:11:04 (isn't there already a language that allows to access its call stack?) 13:13:47 -!- aloril_ has joined. 13:15:49 Forth, at least. If a bit unportably. 13:19:05 http://sprunge.us/XMOh -- nasty, eh? 13:34:00 fizzie: http://sprunge.us/SDDP 13:34:10 I'm thinking the call stack doesn't add anything useful, actually 13:39:45 i think the entire purpose of humans existing is to have a species which does things that do not make any sense whatsoever from a biological standpoint 13:40:08 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 13:40:35 thats the whole point.. thats why the earth is not free of humans 13:40:42 good observation itidus21 13:42:23 we are a species which spends most of it's time seeking states of intoxication and laughter 13:43:06 and when not doing that we try to travel along roads at 300miles an hour just because we can 13:43:53 oh yes and porn.. 13:44:10 so you think other species don't do that? 13:44:12 by "we" do you mean "me" 13:44:33 Arc_Koen: i am actually fairly confident other species do not drive on roads at 300 mph just because they can 13:44:52 i pulled 300mph mostly out of hte air 13:47:24 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:47:44 by analyzing bits and pieces of the universe it can seem to make sense, but taking everything as one thing, it can only be some kind of joke 13:48:20 so you've read that egg thing? 13:49:45 if you ask an infinite number of "why?" questions, in the limit you find "for a joke" 13:50:34 i dont know what in the limit means... 13:50:36 why? 13:50:44 im heavily borrowing idioms 13:50:52 -!- boily has quit (Quit: Poulet!). 13:50:54 -!- boily1 has joined. 13:52:19 why? 13:53:59 should make a bot that does that... "I love chocolate" "Why do you love chocolat?" "because it tastes good" "Why does it taste good?" "because there is cocoa in it "Why is there cocoa in it?" and so on 13:55:24 "why did the chicken cross the road?" "to get to the other side" 13:55:51 "Why get to the other side?" 13:56:14 BECAUSE GRASS IS GREENER 13:56:40 quintopia: its true 13:56:52 or at least i would like to think it's a joke 13:57:03 hi coppro 13:57:13 -!- Nisstyre-laptop has quit (Ping timeout: 245 seconds). 13:57:50 why, has the universe been bullying you? 13:58:51 facebook is somewhat of a joke 14:01:18 haha! facebook! good oone! 14:07:35 -!- Phantom_Hoover has joined. 14:09:31 -!- copumpkin has joined. 14:10:25 by "we" i do basically mean "me" 14:10:48 how humble you 14:12:49 "i am a species which spends most of its time seeking states of intoxication and laughter" 14:12:56 you're my kind of species itidus 14:20:40 "For some time, Gell-Mann was undecided on an actual spelling for the term he intended to coin, until he found the word quark in James Joyce's book Finnegans Wake" 14:20:46 wow 14:21:13 i see you've been reading the wiki article on quarks 14:21:28 only that part 14:21:29 i did so also fairly recently 14:21:55 somehow i found that part 14:22:46 it would be a better story if it went 14:23:23 my plan was to say: i am tempted to say i wonder what would happen if there were no electrons. but then it would mean there were no quarks, but then i pondered saying no particles, but quarks were particles 14:23:30 "Gell-Mann was undecided on an actual spelling for the term he intended to coin, until he saw an episode of Star Trek: Deep Space Nine featuring everyone's favorite Ferengi" 14:23:33 so i wonder what would happen with no particles 14:24:12 Also what if everything was made of asparagus 14:24:17 way to ask meaningful questions 14:24:45 lemme try 14:25:01 i wonder what would happen if time went backwards and reverse entropy was the norm 14:25:08 damn that one actually has an answer 14:25:13 i'm no good at this 14:25:21 um 14:25:58 sometimes i act like there are no particles 14:26:06 i wonder what would happen with the fourth fundamental force being antigravity 14:26:11 i'm gonna ask randall 14:26:41 Also I'm not sure reversing time would reverse entropy 14:26:46 ah that reminds me to check whatif 14:28:05 on a monday? 14:29:43 i have not looked for a while 14:36:23 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 14:37:00 i find most whatifs end in tragedy 14:50:13 -!- FreeFull has joined. 15:00:49 -!- augur has quit (Remote host closed the connection). 15:00:58 -!- sivoais has quit (Ping timeout: 245 seconds). 15:09:40 -!- sivoais has joined. 15:09:47 -!- jiella1 has joined. 15:11:00 -!- jiella has quit (Ping timeout: 244 seconds). 15:14:12 -!- aloril_ has quit (Read error: Operation timed out). 15:28:22 -!- aloril_ has joined. 15:36:41 -!- Sgeo has quit (Ping timeout: 245 seconds). 15:38:58 -!- Sgeo has joined. 15:44:55 -!- ogrom has quit (Quit: Left). 15:45:57 -!- Sgeo has quit (Read error: Connection reset by peer). 15:46:23 -!- Sgeo has joined. 15:48:20 -!- Phantom_Hoover has joined. 16:00:03 -!- augur has joined. 16:03:13 itidus21: WE BLEW THE MOON UP!! that's not a tragedy that's AN ACCOMPLISHMENT 16:03:37 The introduction of emulators created to play illegally copied Nintendo software represents the greatest threat to date to the intellectual property rights of video game developers. […] the assumption that the games involved are vintage or nostalgia games is incorrect. Nintendo is famous for bringing back to life its popular characters for its newer systems http://www.nintendo.com/corp/legal.jsp 16:04:27 Oh no. :-( 16:05:26 well, emulators themselves are legal, aren't they? 16:06:07 -!- augur has quit (Read error: Connection reset by peer). 16:06:29 Arc_Koen: Possibly, but since they are the GREATEST THREAT maybe they shouldn't be! 16:06:35 -!- augur has joined. 16:07:48 "Such emulators have the potential to significantly damage a worldwide entertainment software industry which generates over $15 billion annually, and tens of thousands of jobs." 16:07:57 See, you are RUINING it. 16:08:43 In case you feel like saying something to the contrary, remember that it's not open to debate. 16:08:47 ("Emulators developed to play illegally copied Nintendo software promote piracy. That's like asking why doesn't Nintendo legitimize piracy. It doesn't make any business sense. It's that simple and not open to debate.") 16:09:58 They also have the "linking is infringing" argument, I note. That's always a fun one. 16:13:01 * FreeFull links to google.com 16:13:03 Oh no 16:22:10 How many ROMs exist that aren't copies of Nintendo games? 16:22:14 As in, homebrew ROMs? 16:25:07 I don't know how you could count that kind of thing, since there's presumably quite a few that only exist on their creator's computer. 16:27:46 Are there a significant enough number that there's at least some usage of emulators that are legitimate? 16:30:44 yes 16:30:55 (that's a wild guess) 16:31:05 (but I think it's a good approximation) 16:31:29 pouet's search finds 33 releases for NES; presumably watching those on an emulator should be legal. Depending, of course, whether those involve any burned-in-ROM code for which Nintendo claims copyright. 16:32:34 -!- Arc_Koen has quit (Read error: No route to host). 16:33:02 -!- Arc_Koen has joined. 16:33:31 -!- Arc_Koen has quit (Client Quit). 16:33:34 (As well as 98 SNES releases, and somewhere around 250 GBA things.) 16:34:01 Can't you legally make a copy of a ROM you have for your own use? 16:36:34 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 16:36:42 shachaf: Not according to Nintendo, because the copying devices are illegal. 16:36:46 Due to their "functions". 16:37:10 "Are Game Copying Devices Illegal? Yes. Game copiers enable users to illegally copy video game software onto floppy disks, writeable compact disks or the hard drive of a personal computer. They enable the user to make, play and distribute illegal copies of video game software which violates Nintendo's copyrights and trademarks. These devices also allow for the uploading and downloading of ... 16:37:16 ... ROMs to and from the Internet. Based upon the functions of these devices, they are illegal." 16:37:17 -!- elliott has quit (Read error: Connection reset by peer). 16:37:29 I'd argue, but I'm sure this too is "not open to debate". 16:38:46 Anyway, I don't think there's (at least currently) a DMCA exemption for archival copying, so they might be (US-)right for all I know. 16:47:07 So... CD-Burners are illegal too? 16:47:31 also: By that definition, any regular computer is illegal? 16:47:38 -!- Phantom_Hoover has joined. 16:47:56 I need to talk out my emotions somewhere, and my gf isn't online 16:48:23 oh lord 16:48:38 I'm probably not actually going to talk them out 16:48:41 At least, not here 16:49:25 mroman: Well, IANAL. It might have to do with a value judgement on whether the device is "intended" to circumvent technical rights-protection measures or not, and whether it has any other uses. At least the Finnish anti-circumvention law criminalizes "circumvention devices" that have "only limited commercial uses" in addition to the circumvention bit. For regular computers and CD burners, I ... 16:49:32 ... would think it's reasonably clear they have substantial noninfringing uses. 16:54:31 (At least the Finnish law has a general-purpose exemption that you are allowed to circumvent a protection if you need to in order to use the product; so it'd be legal to go through AACS to watch a legally bought Blu-ray disc. Er, assuming you were clever enough to figure out how to do that; importing, distributing, selling, etc. of devices, products, parts or services to do it is of course a ... 16:54:37 ... criminal act. 16:55:31 fizzie, does your client do some sort of wrapping thing automatically 16:55:53 There exists a person with the nick of fi 16:56:06 Discovered while trying to VERSION fizzie 16:56:26 It does, and I've configured it with a somewhat pessimal auto-wrapping line length limit. 16:56:59 Because the one it calculates (from uhost prefix, channel/target name etc.) sometimes fails miserably and leaves a few characters clipped. 16:57:14 (It's the quasi-standard irssi splitlong.pl.) 16:59:11 The autoguessed length is 497 - length($server->{nick} . $server->{userhost} . $target) where 497 is 510 - length(":! PRIVMSG :") and I think I did puzzle out why it's not always right but forgot already. 17:00:14 I've just fixed it to 400 bytes of actual content. 17:02:37 Perhaps it was simply the mismatch between "fis@iris.zem.fi" and "fis@unaffiliated/fizzie". 17:03:03 The former presumably being what $server->{userhost} expects. 17:05:58 I need sleep 17:06:06 And to not feel so nauseous 17:08:01 both sterling idea 17:08:04 *s 17:16:37 -!- augur has quit (Remote host closed the connection). 17:19:15 -!- carado has joined. 17:27:04 -!- ogrom has joined. 17:39:25 -!- kinoSi has quit (Read error: Connection reset by peer). 17:39:53 -!- kinoSi has joined. 17:46:58 -!- Arc_Koen has joined. 17:50:07 -!- carado has quit (Quit: Leaving). 17:52:26 One of my typical channels for emotion stuff is also mostly inactive right now 17:54:58 we can be used to emote! 17:55:07 just ask that guy who was contemplating suicide a while back! 17:57:35 I feel nauseous. Not sure if I'm physically sick, or if it's just emotions+lack of sleep 17:57:39 I'm not running a fever. 17:58:26 those aren't emotions Sgeo 17:58:30 those are just feeling sick 17:58:34 perhaps ask a doctor 17:58:52 i guess this is a bad time for snark, i'll stop 17:58:54 But I'm having some emotions, and unsure if they may be causing the symptoms 17:59:15 a doctor would probably be able to tell you! 18:00:02 What, there was an #esoteric suicide and I missed it? 18:01:55 i think he means unknown character 18:02:22 <-- aware of the useless trivias 18:03:28 * Sgeo mentally replaces "useless" with "wicked". The wicked trivias 18:03:29 -!- sivoais has quit (Ping timeout: 255 seconds). 18:03:37 honk HONK 18:03:59 18:04:35 fizzie, he didn't commit suicide, at least not in-channel. 18:04:40 I hope not at all, I don't need that kind of angst. 18:04:59 for some reason i associate angst with fried chicken 18:07:28 -!- sivoais has joined. 18:07:38 i don't think it's synesthesia 18:10:46 Synæsthesia. (I just wanted a ligature.) 18:22:38 s/bringing back to life its popular characters/shamelessly porting very old games/ 18:23:40 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 18:26:54 Who was it that said that making a game made you immortal? 18:27:03 Because people will find ways to keep the game working 18:27:23 Sounds like something Sam Hugh would say, except he said it about math 18:29:09 Hmm, I might be changing my mind about Ian 18:30:31 It does make sense to say "Your arbitrary reason for discrimination doesn't even work", even if I would prefer "Arbitrary reasons for discrimination just suck, don't do that" 18:31:28 problem is, if someone disagrees with your second statement, you're in a dead-end 18:31:42 whereas it might be possible to reason him using the first 18:32:55 Indeed 18:35:48 Oh, PH isn't here 18:35:57 @ask Phantom_Hoover Have you read Flatterland? 18:35:57 Consider it noted. 18:36:19 @tell Phantom_Hoover Do read logs around when I @ask'd that. 18:36:20 Consider it noted. 18:50:39 -!- AnotherTest has left. 18:51:15 Sgeo: would you like me to object to the intent to deregister you, on your behalf? 18:51:36 o.O 18:51:38 Hmm, sure 18:55:29 o.O https://twitter.com/shit_hn_says 18:58:29 -!- oerjan has joined. 18:59:50 -!- zzo38 has joined. 19:01:14 Sgeo: _why? 19:01:36 shachaf, why what? 19:03:20 "if you program and want any longevity to your work, make a game. all else recycles, but people rewrite architectures to keep games alive." 19:04:27 -!- atriq has joined. 19:06:10 I completed Bastion this afternoon 19:06:10 atriq: You have 1 new message. '/msg lambdabot @messages' to read it. 19:06:12 The ending was sad 19:06:39 shachaf, oh, I feel like a derp now. 19:06:41 And thank you. 19:08:38 fizzie, in mcmap's colour scheme (in colors.txt and block.c) 19:10:46 How does the alpha work? 19:10:53 As in, which end's which? 19:12:29 apparently, the alpha is bi-endian so that depends on which mode it's in 19:12:40 Hmm 19:19:30 i find most whatifs end in tragedy <-- he does seem to make a point of that 19:20:14 *munroe 19:23:21 Maybe he's sad because his wife has cancer 19:25:03 i think it's because bad things happening to other people is the basis of humor 19:25:13 (not actually true) 19:25:21 I thought bad puns were the basis of humour 19:33:55 Puns *are* bad things happening to people. 19:34:09 Wow 19:34:33 This is like when I first got told that Monads *are* monoids in the category of endofunctors 19:35:37 I have the feeling that reading a page full of quotes from _Stranger in a Strange Land_ is a better experience than reading the actual book. 19:37:51 -!- ogrom has quit (Quit: Left). 19:45:59 atriq: It's actually opacity, so 255 is fully opaque, 0 is completely transparent. 19:48:19 atriq: (As far as I know, anyhow. And water is special.) 19:51:02 @tell Arc_Koen did you mean to remove an a from the kipple truth-machine program? i don't know kipple so... 19:51:02 Consider it noted. 19:58:49 -!- jiella1 has changed nick to jiella. 20:03:51 Is the random number generator I used in Famicom Hangman OK? 20:07:43 http://www.daniellesucher.com/2011/11/jailbreak-the-patriarchy-my-first-chrome-extension/ 20:11:14 from another internet place: 20:11:35 "Damn it Jim, I'm a roleplayer not a whore." 20:14:25 fizzie, thanks 20:16:50 fizzie, what's the point of block traits? The only one with LAVA_TRAIT is lava and lave, similar for WATER_TRAIT 20:17:23 "There is a known bug with the English language itself that Im dealing with imperfectly at the moment. See, sometimes her should translate to him, and sometimes it should translate to his. There are a lot of tricky edge cases here." 20:18:58 well translate may be the wrong word, but i understand what it's trying to say. 20:19:35 "her" is both oblique form and possessive, but "him" and "his" divide this. 20:20:57 I'm just amused by calling English "buggy" 20:24:07 atriq: Future-proofing, I suppose. It used to be so that IS_WATER checked against block IDs directly, I think. It was felt cleaner if such block properties were more centrally collected. 20:24:21 Okay 20:24:30 atriq: There are, after all, apparently two waters. (0x08 and 0x09.) 20:24:49 -!- augur has joined. 20:26:56 Okay 20:27:20 Yeah, water source and running water 20:30:21 Which generation's "Generation Y"? 20:30:24 (not mcmap) 20:31:19 The one after X, I think? Maybe? 20:31:42 Is it my generation? The one before me? The sort of half generation between my and my parents? 20:31:43 ??? 20:37:14 if it wasn't obvious, these "generations" are arbitrary groupings that are very vaguely related to the time people are born, and anyone can invent a Generation Fnarf if they want to 20:37:55 you could be in as many as a thousand generations simultaneously 20:38:03 Generation Fnarf is Gregor's, naturally. 20:38:28 and his children will be Generation Fnarf' 20:38:58 Apparently, Generation Y is the children of Generation X 20:39:02 Who were the baby boomers 20:39:11 So, I'm right at the end of Generation Y 20:43:29 I thought somehow that baby boomers were an older thing. 20:44:20 Generation after WWII? 20:44:43 "There are no precise dates for when Generation Y starts and ends. Commentators use beginning birth dates ranging somewhere from the later 1970s[2] or the early 1980s to the early 2000s (decade).[3]" 20:44:52 Sounds kinda longish-timey. 20:45:05 lul 20:45:11 Generation Y is like six generations. 20:45:42 i thought a generation was about 30 years. 20:47:30 oerjan: It's supposed to be a "demographic cohort (a group of subjects with a common defining characteristic)", not exactly a generation in the "mean time between current children becoming parents" sense. 20:47:55 Mmm hmmm. 20:48:50 oerjan: with all the kids running around getting kids nowadays, it's probably more like 15 years now 20:49:17 -!- augur has quit (Remote host closed the connection). 20:50:29 15 years!? 20:50:40 What have I been missing for the past 3!? 20:51:06 -!- atriq has quit (Quit: Leaving). 20:51:22 About LAVA_TRAIT for lava only, it is actually something similar I did in MegaZeux, I changed it to do like that due to the features I have added to make new kind of objects, so that they can be treated as lava by movement functions. 20:51:24 I suppose he left to start a family now 20:55:39 -!- boily1 has quit (Quit: Poulet!). 20:57:06 olsner: Finnish statistics for children born in 2011: mean age of mother, 30.3 years; 28.4 considering only firstborn. 20:57:46 (Firstborn children, that is. There are no statistics on the firstbornedness status of the mothers.) 21:01:33 hmm, that'd mean finland is about 1 generation behind per 15 years 21:01:39 25.0 for the latter figure over all of US in 2006. 21:02:38 -!- Phantom_Hoover has joined. 21:04:42 25.2 in 2009. 21:09:06 So I “should” be having children. 21:09:09 Ha ha. 21:09:10 Ha ha. 21:09:12 *sob* 21:09:55 I did not know you aspire to being a mother. 21:11:26 Gregor: Generation Fnarf' is dying for you to get going 21:11:59 fizzie: I assume the age is about the same for mothers and fathers >_< 21:12:22 I would guesstimate that it's higher for fathers. 21:12:37 The statistics reports don't bother saying. 21:13:00 These particular ones, anyway; I'm sure such a statistic exists. 21:14:23 29.65 for a first-time father in 2010. 21:15:14 So about four-and-half years oldr, assuming the mother ages didn't drastically change in one year. 21:16:16 Hm. 21:16:19 oerjan: yes, one specificity of Kipple is that operators can share operands, I thought it would be a good thing to show it in the truth-machine 21:16:19 Arc_Koen: You have 1 new message. '/msg lambdabot @messages' to read it. 21:16:21 OK, got a little bit of time! 21:16:43 @ask Gregor hi 21:16:43 Consider it noted. 21:16:46 ok 21:17:04 @messages 21:17:04 shachaf asked 21s ago: hi 21:17:06 Coincidentally, I seem to be approximately 29.46, and there's a kind of a 0.75 year obligatory delay in the process, or so I believe. 21:17:09 for instance, 0>a? first pushes a zero on a (with >), then if a's top element is 0, clear the stack 21:17:22 So I suppose I'll just forget about it. 21:18:15 or the cat program (i>o) uses i both as an operand for the test condition of the '(' loop, and as a value to push on the output stack 21:18:28 it's equivalent to (i i>o) 21:19:38 I guess I should have made a comment about the modification but I thought it was minor 21:26:56 hmm, question: is it possible to use non-printable characters in thue? 21:27:21 I saw in the external resources a link to a brainfuck interpreter in thue, and thought it would be a cool thing to do 21:27:53 and I'm thinking the easiest way to implement brainfuck cells is by stocking chars directly 21:28:51 (well I guess writing them as 8-bit sequences would work as well, but because of . I'd need to have all the translations anyway) 21:28:53 afair the main problem with thue i/o is that input is line oriented in a way that makes it impossible to do input without possible "code injection" 21:29:16 oh it's a whole line 21:29:18 right 21:30:13 * itidus21 thinks. 21:30:15 iirc the brainfuck interpreter doesn't even try to use thue i/o for brainfuck i/o 21:30:38 no I was using thue's input for brainfuck code 21:31:03 that should be possible as long as you have no comments 21:31:05 this way I can place the brainfuck instruction next to the current cell 21:31:31 yes, I decided to assume the input would be +-.,><[] only 21:31:41 (though I may drop ,.) 21:31:43 -!- augur has joined. 21:35:49 (thinks) haiku 5 bytes 7 bytes 5 bytes (look at wiki found haifu) (thinks more) pi 3 1 4 1 5 9.. a program whence the number of tokens per line is the line number'th digit of pi 21:36:48 not a big deal, just a thing 21:38:42 trivial in something like C that has free whitespace 21:39:36 yeah 21:40:43 could be an interesting text format though. 21:41:29 pi is so boring though 21:41:29 Phantom_Hoover: You have 2 new messages. '/msg lambdabot @messages' to read them. 21:41:36 agh no no it wouldn't.......... 21:41:37 ooh, messages 21:43:41 oerjan: perhaps if each pi digit was a token length, including whitespace 21:44:05 I think something that might help improve thue is an event-driven feature 21:44:29 uh i guess you wouldn't need whitespace actually 21:44:31 like "if you just applied rule x, apply rule y" 21:44:56 Sgeo, would you like me to find ian stewart and present your objections to him 21:45:03 i think he has a lecture soon 21:45:18 a public one obv. not a teaching one 21:45:22 ok +->< were easy to implement... now to loops 21:45:41 Phantom_Hoover, um 21:45:53 * Sgeo panics 21:46:05 don't worry i'm not nearly motivated enough to do that 21:46:37 Oh, ok 21:46:51 Heyaduck.Lookswonderfuleh 21:48:07 oerjan: what do you think of http://sprunge.us/EPIe 21:48:21 itidus21: ooh, now that's a bit more interesting 21:48:30 Can we make up a programming language that requires use of bus conflicts and race conditions? 21:48:31 yes, i finally struck something 21:48:49 * itidus21 drops wool. picks up pitext 21:49:36 zzo38: it will have to be named after Rosa Parks 21:49:47 (well BEGIN!::=BEGIN00000000!; should be BEGIN!::=BEGIN;00000000!; instead but appart from that) 21:50:13 oerjan: ha! 21:50:15 oerjan: OK, but why, and why is Rosa Parks? 21:50:28 Arc_Koen, this is Thue right 21:50:30 why and how is she? 21:50:33 yes 21:50:40 ok i just got that 21:50:42 an interpreter for brainfuck 21:50:46 I mean, who is Rosa Parks? 21:50:51 hats off for that pun 21:51:18 but I really don't know how to implement loops 21:51:48 the whole program is one big loop, really 21:52:04 what program? 21:52:08 the thue program 21:52:11 oh, yes 21:52:21 but I mean I don't know how to implement brainfuck's [ and ] 21:52:27 bus conflicts! 21:52:43 they'd need to keep the brainfuck code somewhere, instead of taking it char after char from input 21:52:52 zzo38: "Rosa Louise McCauley Parks (February 4, 1913 – October 24, 2005) was an African-American civil rights activist, whom the U.S. Congress called "the first lady of civil rights", and "the mother of the freedom movement"." 21:52:53 if i didn't know better i'd say zzo38 did that on purpose 21:53:14 but if I do so, then how can I have statements like "if the current instruction is so, do so to the tape"? 21:53:19 Did what on purpose? 21:53:32 you made a joke 21:53:46 What joke? 21:53:51 Arc_Koen: I think the usual way is to encode some kind of marker that points out the next thing for the interpreter to do 21:54:01 zzo38: no you made the setup to my rosa parks joke 21:54:04 Can we make up a programming language that requires use of bus conflicts and race conditions? zzo38: it will have to be named after Rosa Parks 21:54:26 OK 21:54:26 olsner: I'm not sure I understand 21:55:07 problem is if I have brainfuck code someplace, and the tape in another place, I cannot apply the code to the tape 21:55:21 you see zzo38, rosa parks caused a conflict on a bus when she refused to let a white person take her seat because her race was black 21:55:35 the !::=::: statement allowed me to inject the brainfuck instruction directly into the tape 21:55:53 itidus21: OK. Now I know who is Rosa Parks. 21:55:58 -!- heroux has quit (Ping timeout: 245 seconds). 21:56:08 it couldn't be more fitting 21:56:09 But I didn't make a joke; oerjan did. 21:56:22 Arc_Koen: that _would_ seem to be a problem. i think you'll just have to move things about, that's usual with thue 21:56:34 But I am OK if you want to call it that. 21:57:20 i think they keep the bus in question in a museum or something 21:57:43 can't recall if i remember that or if i read something wrong 21:57:45 -!- heroux has joined. 21:57:53 -!- FreeFull has quit (Quit: Sleeeeeeep?). 21:57:58 oerjan: move things about? like, moving a whole portion of brainfuck code inside the tape? problem is, thue doesn't allow for "variables" (as some kind of regexp or pattern-matching), so i'd need to write transformation laws for every possible code 21:58:38 hhmmm, or I guess I could move the tape through the code instead of moving the code through the tape 21:58:46 iirc, moving everything around is what the other bf in thue interpreter is doing ... I'm not too sure where the tape is, but there is stuff moving around in the state space that roughly corresponds to the instruction pointer 21:58:47 that would feel weird though 21:58:59 the irony is on the intra bus conflicts and inter bus conflicts 22:01:44 well I'll think about it, at least it looks possible now 22:01:51 thank you for your help and good night 22:02:26 it is definitely possible 22:04:37 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 22:05:03 hehe :) 22:06:15 Arc_Koen: yeah i have also been thinking about events.. 22:06:59 ok you did say good night 22:07:02 someone dropped a comment on list of ideas saying "hey I have ideas for an object-oriented derivative for thue, but I don't know how to create a page" 22:07:26 btw, I really like today's xkcd 22:08:54 (I'm puzzled as to how thue could be object-oriented... this is probably the last paradigm I would've thought of for a derivative) 22:09:05 anyway, gnight 22:09:25 hmm, object rewriting 22:11:04 oerjan: shall I answer to the thue derivative idea on the list of ideas page? since it's not a user I don't know of another way to talk to him 22:13:53 that page has always been a bit talky anyway 22:23:20 -!- copumpkin has joined. 22:28:40 well, done, good night for good 22:28:52 -!- Arc_Koen has quit (Quit: Arc_Koen). 22:48:59 hmm, how does ^/([^q].*)$ not match '/+++++.'? 22:50:38 olsner: Maybe / is being treated as a special character? 22:54:44 Maybe there's a newline at the end. (Don't laugh. Sometimes there is!) 22:57:34 !perl '/+++++.' =~ m{^/([^q].*)$} ? print "match" : print "no"; 22:57:35 match 22:57:51 itidus21: The Rosa Parks bus is in the Henry Ford museum. 22:58:19 I think the problem was that RewriteCond applies to the next RewriteRule, didn't remember that part 23:00:08 thanks 23:00:30 olsner: Do you have brainfuck in your URIs? 23:00:36 fizzie: yes 23:00:48 Sounds like a situation. 23:01:24 that's not the problem though, the problem is that it's not working 23:01:55 -!- TeruFSX has joined. 23:02:28 it seems to be going "oh, qq000000000000000101^ioiooooooooooooooo looks like a valid uri, let's go to that file!" and then serves a 400 Bad Request error 23:03:23 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:07:37 !perl 'qqr000000000000000101^ioiooooooooooooooo' =~ m{^(q.*q[^r].*)$} ? print "match" : print "no"; 23:07:38 no 23:07:52 oh, reading it backwards again 23:16:34 that's a fancy esolang 23:18:15 argh, the problem was so damn silly :( 23:18:41 you're supposed to add a colon followed by the input to the program followed by an underscore 23:18:50 if you don't, then nothing happens 23:28:27 -!- monqy has joined. 23:36:23 -!- Nisstyre has quit (Ping timeout: 245 seconds). 23:38:05 -!- TeruFSX has quit (Ping timeout: 256 seconds). 23:40:22 in other words, it was never broken in the first place, I was just using it wrong 23:49:49 wtf, now I got the 10% bug but in the *other direction* 23:50:50 -!- Nisstyre has joined. 23:57:38 -!- Sgeo has quit (Ping timeout: 245 seconds). 23:58:23 > (zipWith (/) `on` map (fromIntegral . ord)) "Oovvy#^y|vn$" "Hello World!" 23:58:25 [1.0972222222222223,1.099009900990099,1.0925925925925926,1.0925925925925926... 2012-10-02: 00:02:21 -!- Sgeo has joined. 00:07:41 -!- TeruFSX has joined. 00:14:52 -!- jiella has quit (Quit: Leaving.). 00:18:07 -!- kwertii has joined. 00:18:21 > (zipWith (/) `on` map (fromIntegral . ord)) "A[bbe\GSPehbZ\RS" "Hello World!" -- previous 10% bug, fwiw 00:18:23 [0.9027777777777778,0.900990099009901,0.9074074074074074,0.9074074074074074... 00:45:07 olsner: what was this esolang again, i vaguely recall this 10% bug thing... 01:10:22 -!- monqy has quit (Quit: hello). 01:44:07 -!- trout has changed nick to const. 01:50:52 -!- madbr has joined. 01:52:50 -!- oerjan has quit (Quit: Ribbit). 01:55:52 -!- Jafet has quit (Quit: Leaving.). 02:19:40 -!- TeruFSX has quit (Ping timeout: 246 seconds). 02:33:20 -!- olsner has quit (Ping timeout: 246 seconds). 02:33:48 -!- olsner has joined. 02:37:52 http://goatkcd.com/1115/sfw [nsfw] 03:06:35 -!- Jafet has joined. 03:14:55 -!- ogrom has joined. 03:16:14 -!- ogrom has quit (Client Quit). 03:38:22 What does 6502 do on each cycle of an instruction? 03:39:09 usually a memory operation 03:39:50 in some cases just an "internal operation" (all 2 cycle instructions that don't access memory are like this) 03:40:08 such as nop (2 cycles) 03:40:33 or lsr a (2 cycles) 03:40:55 But in instructions taking longer to execute, what memory access read/write done with each cycle? When does it read the next instruction and its operands? 03:41:09 (a large majority of cycles do a memory op) 03:41:24 hm 03:41:36 I don't think it is pipelined 03:42:14 so a cycle is something like 03:42:46 [cycle 1] read instruction 03:43:17 [cycle 2] no memory op but ALU is active 03:44:01 If there is no memory operations, what is on the address bus at that time? 03:44:09 who knows 03:44:44 -!- sivoais has quit (Ping timeout: 246 seconds). 03:44:46 F L O A T I N G B U S 03:44:46 probably the same address as last cycle, or 0 03:44:57 or z :D 03:46:10 fun fact: the original nmos 6502 was so slow that it actually only accessed memory half the cycles on the Apple II 03:46:24 the other half was used by the video display :D 03:46:50 i heard the original nmos 6502 would also do crazy shit if you gave it invalid instructions 03:46:52 Now I know. 03:47:23 kmc: yeah that's what the docs say :D 03:47:24 I think there are unofficial instructions? 03:47:38 i thought some of them were byproducts of the instruction decode logic 03:47:47 zzo: the docs say that a lot are unstable 03:47:58 plus they won't work on a 65816 03:48:06 Yes I know, I read that some are unstable, but they said some are stable. 03:48:38 But some are the same as other instructions and so are not so useful unless you are also using the instruction opcodes as data in the same program 03:48:44 -!- sivoais has joined. 03:49:18 Demo sceners have been using the “invalid” 6502 instructions a lot. 03:49:54 supposedly they do weird shit like adding and anding stuff at the same time 03:50:13 Such things can occasionally be useful. 03:50:46 If you’re counting cycles, certainly. 03:51:31 I have added the stable unofficial instructions into Unofficial MagicKit (only available for targets which do not override those instructions with new ones) 03:53:04 reading about the 6502 it does come off as totally underpowered 03:53:28 or even the 65816 04:01:25 6502 has decimal mode, but some 6502 based computers lack decimal mode 04:03:03 who uses decimal mode? 04:03:13 Is the decimal mode useful for something other than decimal calculation? 04:03:39 trolling 04:03:42 I don't know who uses decimal mode. 04:03:52 my guess is: banks 04:05:59 Some programs I wrote are for Famicom which lacks decimal mode, so I have never used it. If I program a computer which does have decimal mode I may sometimes used it. 04:06:25 x86 has some instructions for BCD arithmetic. 04:06:41 But I think they cannot be used in 64-bit mode. 04:07:04 correct :/ 04:07:34 they are useful for things besides BCD 04:07:47 AAM does AH <- AL / 10; AL <- AL % 10 04:07:56 but you can actually change that 10 by changing the second byte of the instruction 04:07:58 Yes, AAM and AAD, you can change the base 04:08:01 I know that 04:09:47 So I suppose setting the base to 1 would be a way to move AL to AH and then set AL to zero, it might be slower but it might also be a smaller code 04:09:58 What happen if you set the base to zero? 04:11:00 Will GCC or LLVM make these instructions if it is not 64-bit mode? 04:12:12 probably not imho 04:12:24 they probably don't run fast on modern processors 04:12:52 I know it may be slow, but might it sometimes result in a smaller code, if you select that option for some subroutines? 04:13:11 smaller code? 04:13:41 like, you can't even express BCD operations in C/C++ afaik 04:13:54 In case you want to optimize some functions for size and some for speed 04:15:29 how would you shrink a function by using BCD? 04:15:34 I know C has no commands for BCD operation, and LLVM also has no commands for BCD operation, but some things may sometime result in equivalent to such operation, or even other operation which the target computer may have 04:17:01 madbr: I don't know, but it might if the function is used for making BCD calculation. And anyways, the AAM and AAD instruction can be used for operations other than BCD arithmetic too. 04:17:23 like what 04:18:05 They described above AAM does AH <- AL / 10; AL <- AL % 10 but it does not have to be 10 you can use a different number instead 04:18:33 -!- kwertii has quit (Quit: kwertii). 04:20:39 Such as if you just want to move AL to AH and then set AL to zero, or to move some of the bits of the numbers in certain way, it would probably be very slow to use division but may result in a smaller code, such as if used only for initialization, or if you want the code to fit in MBR 04:22:57 perhaps 04:23:13 still hare brained and no new instruction set should have those monstruosities :D 04:24:35 like, wtf, 6 BCD instructions on x86 04:24:45 which could have been something useful instead 04:25:55 Yeah, but in CISC design it almost makes sense 04:26:54 Well, I think AAM and AAD are useful instructions. 04:27:06 -!- Jafet has quit (Ping timeout: 245 seconds). 04:27:10 they all have 1 byte opcodes too 04:27:52 zzo: no way 04:28:09 they take 10/18 cycles on the pentium 04:28:23 bear in mind that x86 is evolved from a wee little calculator processor 04:28:51 Yeah. Its lineage goes back to a CPU with 4-bit address space for a desktop calculator. 04:28:53 -!- Jafet has joined. 04:29:06 Erm. Was it 4 bit address space? 04:29:12 depressing but true 04:29:13 Might've just been 4 bit registers. 04:29:19 Anyways. Silly. 04:29:42 12-bit address space. 04:29:46 4 bit registers. 04:29:48 amazingly it's still better than the 6502 04:30:09 which never got a 32bit version 04:30:21 It did. 04:30:36 Sorry, thinko. 04:30:39 It got a 16 bit version. 04:30:41 Yes they are too slow, but if they are not too slow it may sometimes be useful, and it can also be useful if you do not need it to be fast 04:30:50 yeah, 65816, used on the snes 04:31:06 *Not* a 32 bit version. 04:31:33 zzo: you could simply store a LUT somewhere 04:32:07 and do the same operation in 1 cycle, pairable on the pentium 04:34:45 it's all about the pentiums 04:36:18 well, essentially on the pentium they decided which instructions would be fast, and which ones would be slow 04:36:29 and the same selection applies to the later processors 04:37:58 and essentially that's where they turned x86 into a bogo-risc 04:45:17 kmc: mosh works with the scroll wheel now? 04:45:48 it does? 04:45:59 for what values of "works"? 04:46:15 I'm moshing to my irssi and scrolling the scroll wheel goes up and down in history. 04:46:43 huh 04:47:04 i am surprised 04:47:22 Hmm, this might be a fluke. 04:47:31 -!- Jafet has quit (Quit: Leaving.). 04:47:39 i don't think we're setting alternate screen on the client 04:47:42 https://github.com/keithw/mosh/issues/2 is still open 04:47:48 you can ask in #mosh though 04:47:50 Yep, even if I detach from screen, scroll-wheel goes up and down in bash history. 04:48:08 Somehow I got into scroll-wheel-sends-up-and-down-arrows mode, or something. 04:49:10 huh 04:49:12 well that's useful 04:50:18 in the neon sign, scrolling up and down, i am born again 04:50:20 kmc: Hah, irssi put me in this mode. 04:50:25 irssi ate my balls 04:50:31 brb 04:50:39 I previous sshed to irssi and exited with ~. 04:57:57 the ARM has like 10 different multiply instructions 05:00:57 wait no 05:00:58 20 05:00:58 What kind of multiply instrucions? 05:01:10 multiply, multiply accumulate, multiply subtract 05:01:20 multiply to 64 bit 05:01:24 multiply 16 bit 05:02:38 weird "wide" multiply (32*16) 05:03:29 multiply 16 bit into 64 bit accumulator (weird :o ) 05:04:25 double 16 bit multiply adding/subtracting the productions 05:05:06 32 bit mul keeping only the most significant 32 bits of the result 05:06:31 dual 16bit multiply adding/subtracting the products then accumulating 05:07:29 multiply with combining grass radical above 05:07:35 same but accumulating 64bit 05:08:36 multiply 32 bit into 64bit accumulator 05:08:39 and that's it 05:09:00 ...for the non SIMD multiplications :D 05:09:18 the SIMD ones are even crazier :D 05:13:38 good thing ARMs don't have bcd 05:17:15 Do you know any computers with a triple indirect jump with post increment instruction? 05:18:38 well the RCA 1802 has weird indirect registers 05:18:40 "Using the SEP instruction, you can select any of the 16 registers to be the program counter; using the SEX instruction, you can select any of the 16-bit registers to be the index register." 05:19:08 but i don't know what the addressing modes are 05:19:16 zzo38: do you want this address mode for any particular purpose? 05:20:05 I am just wondering if anything has something like that. 05:20:48 It allows you to change which register is the program counter? I have never seen anything like that before. 05:21:05 yes 05:21:23 as wikipedia describes, this was sometimes used for fast subroutine calls, even alternating coroutines 05:30:07 so CISC 05:30:13 sooooooooo CISC 05:32:23 can be translated as "this architecture will never be able to be pipelined" 05:34:59 heh 05:35:27 ARM lets you swap the contents of the instruction pointer and another register, right? 05:35:31 that is similarly useful and less crazy 05:35:56 yeah ARM has the PC as one of the GPRs 05:36:05 which turned out to be a mistake 05:36:21 now if you look at the ARM manual most instructions say 05:36:44 "non of the operands of this instruction can be r15 (pc)" 05:37:02 that's too bad 05:37:27 it's ok when you're running at 10mhz and your pipeline is 2 cycles long 05:38:24 once your cpu is doing 2 instructions at the same time then your PC is not your PC anymore 05:38:58 not to mention crazy out of order CPUs (essentially all modern CPUs) 05:39:47 -!- sivoais has quit (Read error: Connection reset by peer). 05:40:04 CISC? 05:40:06 Pipelined? 05:40:25 sgeo: it's possible! 05:40:34 -!- sivoais has joined. 05:40:39 As in, I don't know what either of those mean. 05:41:00 I know RISC is reduced ... something about few instructions 05:41:08 Like a small number of opcodes or something 05:41:20 yeah 05:41:52 a CPU has several stages to process an instruction 05:42:13 fetch the instruction from memory, figure out what it means, fetch operand(s) from memory, do arithmetic or whatever, save result 05:42:18 risc = lots of registers, high instruction set orthogonality 05:42:28 each of these has a different piece of hardware 05:42:42 it would suck if we only used one of those units at a time 05:42:50 yeah but the number of stages varies a lot 05:42:59 in a pipelined processor we are fetching one instruction while we decode the previous one, while we fetch for another, etc. 05:43:04 yeah this is a simplistic explanation 05:43:06 but that's the idea 05:43:23 Ah 05:43:52 the ideal early RISC cpu runs 1 instruction per cycle 05:43:54 another way to look at it is, if you tried to do all that stuff in one clock cycle, your max clock speed would be really low, because of the delay to propogate through all those logic gates 05:43:56 What happens with jumps or conditionals? 05:44:10 sgeo: depends on the length of the pipeline 05:44:13 yeah, that's a trick 05:44:28 this is why on MIPS processors, the instruction after a branch gets executed even if the branch is taken 05:44:35 on longer pipelines and stuff like the x86 it tries to predict the result 05:44:46 RISC processors tend to expose these implementation details, on the grounds that the compiler can deal with them 05:45:10 Oh, hmm. I thought maybe the fetched thing that was after the jump just gets discarded 05:45:26 sgeo: not on the MIPS 05:45:35 yeah you can stall the pipeline like that 05:45:43 it makes CPUs easier to design 05:45:54 but then you're executing fewer than one instruction per clock 05:46:05 if the compiler has nothing useful to put there, it can insert a NOP 05:46:08 but there's not much point later on when your pipeline is 8 cycles and you have to do branch prediction anyways 05:46:09 otherwise maybe it can do some useful work 05:46:33 1 cycle isn't much, you can pretty much always put something there 05:47:20 Sgeo: another problem is data dependencies, what if a write and a read from the same register are in the ppipeline at the same time 05:47:31 oh yeah 05:47:48 you can stall, or you can insert "bypass" paths which let it read the value that will be written, rather than the stale value that's in the register file 05:47:54 which adds complexity 05:48:00 MIT's 6.004 is a really nice intro to this stuff 05:48:03 if your cpu is a well designed RISC you can do these all in 1 cycle 05:48:13 you design a RISC processor in a logic gate level simulator 05:48:19 and then you can optimize it for speed 05:48:32 the labs and software are available online 05:48:33 but once you're doing like 2 operations at the same time etc you have to introduce stalls 05:48:41 or out of order execution 05:49:09 i did the 2 stage pipeline with stalls on branches, which wasn't too bad 05:49:16 but more than 2 stages gets hairy 05:50:32 TMS320C64x has two-instruction delay slots. Except it's one instruction if it's one of the instructions that are followed by an immediate word. Keeping track of that kind of thing manually is kind of a pain. (Though I suppose you're meant to mostly just write C and use the provided algo libs.) 05:50:45 that's a DSP? 05:50:52 Yes. 05:51:00 VLIW is still popular for DSPs right? 05:51:02 * kmc does not know why 05:51:19 kmc: they're probably easier to design 05:51:49 of course that's a road to the intel itanium and we all know what happened to that one :D 05:51:54 I don't know how popular; the C64x used by the popular-in-phones OMAP platform (at least OMAP3 and I think 4 too) is a VLIW thing. 05:52:03 it's amazing how far the inner workings of a CPU are from the virtual machine suggested by the instruction set 05:52:16 when people talk about how C and assembly tell you "what the machine is really doing" i just laugh and laugh 05:52:39 They tell you what *a* machine is really doing. 05:52:44 (of course with C people also forget that there's an optimizing compiler which can make liberal use of undefined behavior) 05:52:47 There's always another turtle somewhere. 05:52:52 yeah 05:53:02 but they act like they've found the bottom turtle and it's special 05:53:33 anyway 05:53:37 We should make up the CPU where the instruction set corresponds closely to the inner working and work faster too. 05:53:38 The ISA is a pretty good turtle. 05:53:44 well, it's the bottom turtle you can actually write for 05:53:52 zzo38: that is the idea of RISC basically 05:53:54 zzo: that's called a VLIW 05:54:19 yeah i guess VLIW is that idea for superscalar 05:54:25 zzo: the big problem with VLIW is that they bust the instruction cache 05:54:42 you'd end up with an instruction word like 05:54:49 kmc: Doncha *love* it when people act like x86 asm is what the machine "really does"? 05:54:58 shachaf: do you know about implementing a touch / proximity sensor with two digital I/O pins, a resistor, and a piece of wire? 05:55:13 kmc: Nope! 05:55:18 Rather than just being the lowest abstraction Intel provides? *urgh* 05:55:22 -!- nortti has quit (Ping timeout: 268 seconds). 05:55:25 well you set one pin as input and one as output 05:55:41 connect the pins with a big resistor (≥ 1 MΩ) 05:55:48 add r0, r1, r4 sub r3, r7, r8 add r9, r2, r14 shfnop mulnop ldr r5, r13 05:55:50 I have had ideas of CPU instruction sets based on what is hardware what I was thinking of. 05:56:01 and also connect your wire or metal plate to the input pin 05:56:18 essentially a bunch of ALUs, each one gets an operation on every cycle 05:56:28 then you simply toggle the voltage at the output, and see how long it takes the input to match 05:56:43 this is a measure of the capacitance on that pin, which will change if someone touches or gets near the wire / plate 05:56:54 the other big problem with an architecture like that is that, what happens if you have a cache miss? 05:57:12 Makes sense. 05:57:16 you'd have to stall everything 05:58:05 also you'd probably have to cover the chip in multiplexers 05:58:55 the other other problem is that your compiler has to be crazy smart 05:59:05 true 05:59:08 Another idea I have, is first you need a open-specification FPGA (some people have partially reverse-engineered the AT40k FPGA, so we can use that), and have a compiler which takes LLVM codes with speed annotations (such as: this function runs in less than 1 million clock cycles if the third parameter is divisible by 5) and creates a hardware optimized for running this program. 05:59:13 dunno how smart it would have to be but yeah 05:59:48 would be workable if it could reorder operations over multiple loop iterations but afaik C pointers usually have some ways to defeat that 06:00:10 Does what I said would work at all? 06:00:35 tho I've heard that GCC is even able to autovectorize loops so it might be workable after all 06:01:20 If the FPGA is capable of reprogramming itself at runtime, then you can have not only self-modifying software codes, but you can have self-modifying hardware codes as well. 06:01:34 perhaps VLIW is popular for DSP because people are willing to hand-code these algorithms (and use them from libraries) rather than expecting to feed some 40 year old FORTRAN codes in and get good performance 06:01:54 imho the problem is C/C++ 06:02:10 kmc would surely agree that "C/C++" is a problem. 06:02:31 using "code" as a non-uncountable noun is a sign that one has worked in academic computing 06:02:36 What problem is C/C++? It has some problems but I don't know what problem you mean. 06:02:38 like "here is a code for fourier transform" 06:02:48 "here is a collection of codes for manipulating splines" 06:03:21 zzo: the general problem is that the user might throw weird pointers at your algo 06:03:26 I thought "code" as a non-uncountable noun is a sign that you don't understand programming at all and want people to give you stuff to copy and paste 06:03:29 -!- nortti has joined. 06:03:33 like multiple buffers that are really the same buffer 06:04:32 It is why you have to specify in your documentation, if it is allow to be the same buffer or not, and stuff like that 06:04:47 the compiler doesn't know that 06:04:59 well you can use the 'restrict' keyword in some cases 06:05:01 zzo: that's why older C/C++ compilers have a "no aliasing" switch 06:05:10 I think they added the "restrict" keyword so that the compiler will know that? 06:05:21 which means that you promise pretty promise that you're not going to do it 06:05:22 And I also think LLVM has corrected some things? 06:05:34 Does LLVM have all of these things better way? 06:05:42 though recent compilers don't seem to have the switch so they might have found out some better way yeah 06:07:04 if that is the case it reduces the VLIW's problems to "code size" and "how to prevent a stall when you have to fetch the data all the way from the RAM" 06:07:48 stopping irssi with ^z accidentaly seems to result in nothing else than disconnection from everywhere 06:08:27 My stomach hurts, don't know if it's hunger or nausea 06:08:32 Or what 06:09:24 My idea is to have multiple memory connected, one for program, one for data X, one for data Y, and any of them can be switched with each other, and then have the address bus for data X and Y to be their own registers, the data bus are also their own registers, use LFSR-based PC with one register affecting the LFSR taps, an instruction transfer register to register with condition.... 06:09:43 zzo: you don't need multiple memories when you have cache 06:10:52 Having the LFSR-based PC with a register affecting the LFSR taps is somewhat like having a multi-dimensional programming language, if done in the correct way needed to do this, I guess 06:11:18 O, and then also add multiplexer calculation like how the Muxcomp esolang does it 06:11:51 These are just some ideas I have to make a CPU; I don't know how it is really working. 06:12:31 I'd try going for one that has the maximum number of ALUs 06:12:35 madbr: But when you have cache, don't you then also need to have stuff such as cache invalidation and checking if it is cache and so on, unless your instruction set is dealing directly with the cache 06:12:48 and base everything else around keeping those ALUs full most of the time 06:13:41 zzo: yeah but afaik that's not so bad 06:14:57 It also seems difficult to predict how many clock cycles a certain sequence of instructions will take if it automatically reorders them and put into cache and all that other stuff. 06:16:45 true but still 06:16:58 considering how DRAM works it's a lot faster to have cache 06:17:30 also it prevents the need of having multiple ram areas for program, data x etc... 06:17:47 OK, but I still want it that the cache only works with instructions that directly tells the cache what to do 06:18:33 yeah but then the compiler has to guess what goes in cache 06:18:53 and all the manual cache management will probably slow it down a lot 06:20:24 the big benefit of cache is that essentially your inner CPU core doesn't have to deal with DRAM anymore 06:20:49 it becomes just "load from cache, stall if I get a cache miss" 06:21:31 right, for a long time the DRAM controller wasn't even on the processor 06:22:30 But you could require that instructions can only execute from cache, and these instructions modify other instructions in cache in order to affect the values you are dealing with, and have the external address/data bus to just be registers visible to the program stored in cache 06:23:46 good luck writing a program for that 06:25:24 You could then also have multi-cores executing separate programs simultaneously, with some registers shared, and others which are not shared, and some which are partially shared. 06:26:01 aka the Cell processor 06:30:56 Or have something like that checkboard design mentioned on esolang list of ideas, which has the checkerboard of processor and memory (so each processor accesses four memory cores and each memory is accessed by four processor cores) 06:31:17 I don't know how well it would work 06:31:22 hm 06:31:43 I'm not familiar with multicore operation 06:31:55 Neither am I, actually. 06:32:19 except from the user point of view ("you have to mutex everything because nothing happens in the real order") 06:33:06 I wrote in esolang list of ideas, make a programming language which requires bus conflicts and race conditions in order to work. 06:33:29 one nice idea I had is a dataflow processor 06:33:44 like, instead of having "write x to register y" 06:33:57 have each register take a new value each cycle 06:34:06 and have one ALU per register 06:34:17 Yes, do like that. 06:34:25 Somehow. 06:35:29 maybe with access to values produced 2 or 3 cycles ago 06:35:38 OK 06:35:39 or switching between two sets of registers 06:36:25 What would you think about my idea of making the program which includes the hardware description of the CPU optimized to execute this specific program? 06:36:42 afaik that already exists 06:37:06 Is it possible to compile LLVM programs into such things? 06:39:25 no, it's some crazy expensive design software 06:40:12 afaik most people just get a fast ARM system on a chip and run the C++ on that instead :D 06:41:58 it's probably not very different from writing a C++ program and optimising the few loops that run a lot in ASM 06:44:11 http://jollatides.com/2012/10/01/jolla-handset-poll-give-jolla-your-feedback/ 06:48:12 the other weird thing is that the amount of gates and latency of components like adders can vary 06:49:23 afaik modern processors use very low latency adders which means they're probably enormous 06:49:48 ARM has some complicated instructions, requires memory of differing data sizes, apparently you are not allowed to use some instructions unless you pay them, and OpenCores made a "Amber" processor based on ARM but they were sued and not allowed to make anything beyond ARMv2 06:50:43 heh 06:50:51 Oooh: a CPU where you have to plug in a credit card to enable some parts of the instruction set. And a per-instruction charge. Careful with those loops, now! 06:51:20 I think this is stupid so I do not want to use ARM in a computer design. 06:51:23 fizzie: that's ARM's revenue model 06:52:13 from what I can tell they license the SIMD unit and stuff like that 06:52:52 which is why some androids don't have them and you have to have a C++ version of like everything :D 06:53:40 Perhaps, but it doesn't quite go as far as getting money when the individual end users want to run something that takes advantage of tricky parts. 06:53:46 multiple data sizes is ok, the really complicated one afaik is when you allow unaligned accesses 06:54:34 supposedly there's a patent on that too 06:58:57 how about a design that has 2 modes: RISC, and VLIW 06:59:16 RISC is designed to run C++, have compact code (16bit opcodes) 06:59:40 VLIW is for the few inner loops that run a lot and have to be optimised 07:01:03 the vliw mode can probably even be specially simplified 07:01:47 since it probably doesn't have to deal with, say, real branching 07:02:05 it's going to mostly loop the same piece of code hundreads of time 07:02:16 ok sleep 07:02:18 -!- madbr has quit (Quit: Radiateur). 07:04:04 Blerp. They upgraded this workstation, and now XMonad keybindings for switching between monitors (mod-{w,e,r}) are in the wrong order, because screen 0 happens to be the right one, not the left one. 07:07:08 Man, these Intel model numbers, I've completely lost track of them. It used to be so simple. 07:07:20 Now this new workstation has an "E31230". 07:22:46 What hardware programming language would you program it by specifying what gates you use and what connection you use between them and what propagation delay? 07:31:09 -!- zzo38 has quit (Remote host closed the connection). 07:46:23 I wonder if he was trying to describe something like verilog 08:03:54 -!- atriq has joined. 08:04:04 @messages? 08:04:04 Sorry, no messages today. 08:10:22 I can't rotate this single screen when it's in a NVidia TwinView configuration? 08:15:40 fizzie, my lack of knowledge of C is letting me down 08:15:53 Does "typedef int8_t jbyte" name jbyte as a type synonym of int8_t? 08:16:08 Yes. 08:16:14 Okay 08:16:27 So, in Haskell, that'd be something like "type JByte = Int8" 08:17:33 If you take a regular declaration that makes 'foo', say, a pointer to a no-arg function returning int -- int (*foo)(void) -- then adding a typedef in front makes 'foo' a synonym for the type it would've normally made 'foo' an instance of. 08:18:17 Okay 08:18:28 "In a declaration whose storage-class specifier is typedef, each declarator defines an identifier to be a typedef name that denotes the type specified for the identifier in the way described in 6.7.6." 08:18:44 It's kind of a silly that 'typedef' is a "storage-class specifier". 08:19:37 ("The typedef specifier is called a ‘‘storage-class specifier’’ for syntactic convenience only.") 08:19:43 -!- Arc_Koen has joined. 08:23:02 Well, my C textbook is new enough to tell me about typedef, and despite elliott's recommendations I have not burnt it yet. 08:23:05 So, I'll read that 09:05:34 -!- pikhq_ has joined. 09:05:44 -!- pikhq has quit (Ping timeout: 255 seconds). 09:06:56 hello 09:07:02 Hey 09:07:32 so what's up? have you completed your fueue interpreter in haskell? 09:07:45 > (replicate 3 ) (replicate 2 [2, 2]) 09:07:47 [[[2,2],[2,2]],[[2,2],[2,2]],[[2,2],[2,2]]] 09:07:52 Haven't been working on it 09:08:04 I'm trying to port something fizzie and elliott made a while back to Haskell 09:13:48 I'm having difficulties in that C is not Haskell 09:17:56 atriq: go on 09:18:06 * kallisti has been working on a term rewriting grammar 09:18:10 Mutable variables, for a start 09:18:43 Actually, that's the only difference between C and Haskell I'm having trouble accounting ofr 09:18:45 *for 09:18:53 pattern -> [replcaement | condition] 09:19:01 each symbol has a weight 09:19:03 so it's really a tuple 09:19:31 Is there a way to search a github thing? 09:19:43 .. 09:19:50 uh, github? 09:19:55 No 09:20:02 A thing on github 09:20:06 * kallisti sips gumbo 09:23:02 atriq: GitHub's own "advanced search" form at least at some point. 09:23:09 Okay 09:23:39 You need some kind of a "repo:foo/bar" specifier and then tell it to search from source code too. 09:24:32 https://github.com/search and the bits about "Code Search". 09:28:53 atriq: I actually have a private git server 09:28:58 I could set up a web interface 09:29:05 No, it's okay 09:35:03 arrrrrrh 09:35:12 that was too easy 09:35:25 but I forgot about nested loops 09:35:56 how the hell can a brainfuck interpreter in thue account for nested loop? 09:36:21 -!- mig22 has joined. 09:36:28 in order to "jump to the matching ]" I usually have a variable that count how deep in nested loops the ip is 09:36:35 but thue has no variables 09:37:28 Arc_Koen: I was thinking of a string rewriting grammar that uses a term rewriting system 09:37:33 but on a tree of weighted values 09:37:47 with conditions on the weights, and a pattern from the tree 09:38:17 and the resulting term and also an update of the current state of the weight. 09:39:22 condition | pattern -> replacement[state] 09:39:36 state can be ++, --, or a numeric expression of the input weights 09:40:13 replacement is a result of tokens from the input patterns capture symbols 09:40:31 I'm not sure I know what you are talking about 09:40:37 condition is any numeric expression 09:41:21 a + b | "a -> b" -> ab [a + b] 09:41:48 transforms an -> into an addition of 2 weights 09:47:05 what about http://esolangs.org/wiki/Definer 09:49:51 not quite 09:49:55 hm 09:50:01 term rewriting though 09:56:22 -!- ais523 has joined. 10:00:34 -!- Phantom_Hoover has joined. 10:00:37 -!- Phantom__Hoover has joined. 10:00:38 -!- Phantom__Hoover has quit (Client Quit). 10:04:16 -!- carado has joined. 10:04:43 -!- carado has quit (Client Quit). 10:04:57 -!- carado has joined. 10:08:44 -!- atriq has quit (Remote host closed the connection). 10:37:11 -!- jiella has joined. 10:47:05 has anyone here tried programming the Z80 or one of its derivatives? 10:48:06 I've heard it mentioned. 10:48:12 Can't remember by whom. 10:58:54 I've done it a bit. 10:59:02 And I am under the impression that others have, too. 10:59:04 `pastelogs z80 10:59:27 http://zem.fi/rfk86/ <- mainly I just made that. 10:59:43 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.6799 11:00:02 `pastelogs z80 11:00:11 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.19994 11:00:39 Well, I do know mooz did quite a lot for the calculator, but he's no longer here. 11:01:36 which one have you programmed? 11:01:47 Just the original. 11:08:18 -!- barts_ has joined. 11:08:33 -!- ais523_ has joined. 11:09:34 -!- ais523 has quit (Ping timeout: 240 seconds). 11:10:41 -!- ais523_ has changed nick to ais253. 11:10:43 -!- ais253 has changed nick to ais523. 11:11:36 -!- barts has quit (Ping timeout: 252 seconds). 11:11:50 http://en.wikipedia.org/wiki/Gumbo 11:16:04 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 11:21:11 Now I'm hungry. 11:34:40 -!- ais523 has quit (Remote host closed the connection). 11:35:23 -!- carado has quit (Quit: Leaving). 11:39:33 -!- ais523 has joined. 11:41:19 -!- carado has joined. 11:50:16 -!- Jafet has joined. 11:59:03 -!- TeruFSX has joined. 12:12:49 -!- ogrom has joined. 12:15:09 -!- Phantom_Hoover has joined. 12:15:48 -!- ais523 has quit (Remote host closed the connection). 12:17:04 -!- ais523 has joined. 12:19:55 uh, the thue article doesn't say anything about comments 12:22:34 -!- ogrom has quit (Quit: begone). 12:26:01 I've seen #::=# as a kind of a line-comment indicator. 12:26:07 -!- TeruFSX has quit (Ping timeout: 240 seconds). 12:26:12 Presumably with the restriction that there won't be any #s ever. 12:26:18 yes 12:26:19 ais523: You have 1 new message. '/msg lambdabot @messages' to read it. 12:26:27 it's one of those comments-inside-the-language-semantics thing 12:26:38 like DO NOT put comment here in INTERCAL 12:27:07 hmm, yeah 12:27:15 there's definitely a problem with input though 12:28:36 basically if the input contains anything else than +-><[]., my interpreter will either not know of it (so it will halt because no rule can be applied) or will recognize it as injected code and then it can do about anything 12:29:42 It's a language for well-behaving users. 12:31:07 -!- ais523 has quit (Ping timeout: 246 seconds). 12:31:13 I guess I could have an ip go through the brainfuck program before execution starts, and remove anything that's not a brainfuck instruction - but still, willingly injected code can trigger any rule 12:34:14 also, my thue interpreter selects the rules to apply at random amongst the not-yet-tester-this-turn rules, but I guess the brainfuck interpreter in thue would be way faster if the thue interpreter tried rules in the order they are sorted, and brought the chosen rule on top of the rules list 12:35:17 (for instance if the brainfuck interpreter is currently interpreting a '+', only the '+'related rules will be applicable so trying all the other rules is a waste of time 12:45:05 -!- nortti- has quit (Ping timeout: 256 seconds). 12:56:28 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 13:03:51 -!- boily has joined. 13:03:54 -!- Phantom_Hoover has joined. 13:04:13 -!- nortti- has joined. 13:11:20 hello 13:12:38 -!- aloril_ has quit (Ping timeout: 244 seconds). 13:13:37 what is the most esoteric language? 13:13:48 eodermdrome 13:13:54 `welcome 13:13:56 why? 13:13:58 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.) 13:14:09 it's a personal opinion 13:14:11 i've already been welcomed, but thanks Arc_Koen 13:14:18 why do you hold such an opinion? 13:14:24 I don't think there is a "most" esoteric language, they are all esoteric in their own way 13:14:28 assuming you are the person of this personal opinion 13:14:42 eodermdrome uses graphs as a way to program 13:15:01 that is very interesting 13:15:05 does it process graphs? 13:15:18 hrm, I don't know enough about it, actually 13:15:31 i heard lisp could be implemented with a machine that does graph reduction. 13:15:33 's too esoteric for me :-) 13:15:46 It's a graph-rewriting language. 13:15:59 have a look at http://esolangs.org/wiki/Eodermdrome 13:16:11 (or hear what fizzie has to say, he knows much more than me) 13:16:22 There's a state graph, and rules for rewriting parts of it. 13:16:34 Well, the article is fine too. 13:17:43 It's really kind of like Thue except with (unlabeled) graphs. 13:18:28 talking about thue... http://sprunge.us/HhXO 13:19:31 it's 180 lines long already, I still have to do instructions > < . , and it's probably full of bugs because IT'S NOT HUMANLY READABLE 13:21:24 -!- epicmonkey has joined. 13:22:13 oh i just read up on it 13:22:14 it's nice 13:22:43 -!- carado has quit (Quit: Leaving). 13:24:03 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:24:04 I could possibly second the Eodermdrome opinion on esotericness, as ill-defined as that is. 13:24:31 (I do hope you're talking about eodermdrome when saying "it's nice") 13:26:50 yes 13:27:28 or i might be talking about sending digital signals in analog carriers via amplitude modulation 13:27:31 you'll never know 13:27:37 It possibly loses some appreciability points from the fact that it's still lacking an interpreter, and there aren't that many programs written in it. 13:28:00 Compare to something like Befunge which is being used daily in mission-critical applications all over the globe. 13:28:05 but does it have eclipse support 13:28:27 Perhaps someone should write a plugin. 13:28:31 haha 13:28:54 fungot: What's your opinion on the productivity and popularity and efficientness and such of Befunge? 13:28:55 fizzie: you just want to say " you can't make if a function is 13:29:04 (He's written in it.) 13:29:15 fungot: I don't think I want to say *that*. 13:29:16 fizzie: that's underload code in there, then 13:29:31 fizzie: what's your opinion on the productivity and popularity and efficientness and such of peptides? 13:29:50 :)) 13:29:59 I think we should get rid of them. 13:30:04 -!- aloril_ has joined. 13:30:07 too mainstream ???? 13:30:19 What have the peptides ever done for us? 13:30:22 ^source 13:30:23 http://git.zem.fi/fungot/blob/HEAD:/fungot.b98 13:30:25 -!- nortti- has quit (Ping timeout: 256 seconds). 13:36:14 has it just reproduced 13:36:16 that's naughty 13:39:24 -!- jiella has quit (Quit: Leaving.). 13:49:49 -!- copumpkin has joined. 13:52:37 -!- carado has joined. 13:56:41 -!- mig22 has quit (Quit: mig22). 14:14:10 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 14:16:28 -!- Phantom_Hoover has joined. 14:25:49 The Core http://edition.cnn.com/2012/10/01/tech/mantle-earth-drill-mission/index.html?hpt=butt 14:41:29 -!- nortti- has joined. 14:45:18 -!- Arc_Koen has quit (Quit: Arc_Koen). 14:51:07 -!- carado has quit (Remote host closed the connection). 15:10:50 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 15:15:38 -!- epicmonkey has quit (Ping timeout: 246 seconds). 15:31:42 -!- jiella has joined. 15:38:38 -!- atriq has joined. 15:39:00 @messages? 15:39:00 Sorry, no messages today. 15:41:24 -!- kinoSi has quit (Read error: Connection reset by peer). 15:41:51 -!- kinoSi has joined. 15:44:44 @messages 15:44:44 You don't have any new messages. 15:44:47 @messages? 15:44:47 Sorry, no messages today. 15:45:03 @tell Sgeo honk 15:45:03 You can tell yourself! 15:45:17 @tell lambdabot HONK 15:45:18 Nice try ;) 15:52:53 ... 15:53:03 Sgeo is Gamzee? 15:54:09 honk HONK honk HONK :o) 15:55:14 ion: i like the fact that they're doing a $1 billion mission to "answer questions about the origins and evolution of life" 16:09:16 itidus21, Homestuck fans have raised $2000000 for a video game that comes out in 2014. 16:09:18 @tell Sgeo honk 16:09:18 Consider it noted. 16:09:21 @massages 16:09:21 You don't have any new messages. 16:09:23 What do you make of that? 16:09:30 @messages? 16:09:30 Sgeo: You have 1 new message. '/msg lambdabot @messages' to read it. 16:09:53 -!- Phantom_Hoover has joined. 16:10:09 You don't have any new massages. 16:17:09 @messeges 16:17:09 You don't have any new messages. 16:17:35 * FireFly wonders if lambdabot checks if the edit distance is below some threshold or something 16:17:50 compared to the string 'messages', that is 16:18:09 I like 0 video games. 16:18:16 FireFly: It allows up to two edits, but only if the parse is unambiguous. 16:18:39 itidus21, I thought you liked Super Mario Bros? 16:19:01 @pime 16:19:05 Local time for fizzie is Tue Oct 2 19:19:02 2012 16:19:11 Uh, that's not what I meant; what I meant was. 16:19:14 @pixx 16:19:14 pong 16:19:17 But: 16:19:21 @pike 16:19:22 Maybe you meant: dice ping time wiki 16:19:52 I think the game I came closest to liking was legend of zelda: link's awakening on gameboy 16:20:31 (The @pime result shows it's enough for there to be a unique command with the shortest edit distance, as long as that's <= 2.) 16:20:46 also super mario bros 2 16:21:01 Lost Levels or USA? 16:21:08 USA 16:21:44 FireFly: Or I'm not entirely sure whether it's exactly edit distance or Hamming distance; and it's complicated by the fact that unique prefixes of commands are accepted too. 16:21:50 that was really something super mario usa 16:21:56 ^super mario 2 16:22:23 fizzie: ah, okay 16:22:25 it wasn't perfect though.. 16:22:36 @ssages 16:22:36 You don't have any new messages. 16:22:45 I suppose it's edit distance since it seems to allow deletions. 16:22:59 @bamessages 16:22:59 You don't have any new messages. 16:23:23 But note that: 16:23:24 @messag 16:23:24 Maybe you meant: messages messages? 16:23:39 Even though it has only one edit-distance-2 expansion (the one without ?). 16:23:46 Because of the no-typos-but-prefix handling. 16:23:58 i think it's not really the quality of the game itself, but the lies the game helps your mind momentarily tell itself 16:24:19 @massag 16:24:20 Unknown command, try @list 16:24:25 @massage 16:24:25 barts_ said 15m 7s ago: honk 16:24:33 thats what i think i enjoy in fiction 16:24:44 @massages 16:24:44 You don't have any new messages. 16:24:53 @massage? 16:24:53 Maybe you meant: messages messages? 16:25:07 oh, right 16:26:36 i guess that with your eyes, you can see yourself and you can see others 16:27:04 with your ears you can hear yourself and you can hear others.. etc etc.. but with your mind you can hear your thoughts but you can't hear any others 16:27:25 it's so bizzare 16:28:39 -!- FreeFull has joined. 16:28:51 so in a video game you see this sprite and you can say that sprite is me, everything else isn't 16:32:50 i guess you just have to be in the right mood, like with anything 16:33:17 -!- augur has quit (Remote host closed the connection). 16:34:09 link's awakening was really fun 16:34:13 i got stuck at some point 16:34:22 and it took me years to figure out how to get past 16:34:33 i h8 open plan games for this 16:34:58 like if you're sitting there thinking about video games as some philosophical metaphor like i am then you probably need a break from them 16:36:14 -!- atrapado has joined. 16:36:28 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 16:45:26 -!- barts has joined. 16:46:32 -!- Jafet1 has joined. 16:46:33 -!- aaaaaa has joined. 16:48:19 -!- atrapado has quit (Disconnected by services). 16:48:27 -!- aaaaaa has changed nick to atrapado. 16:48:47 -!- barts_ has quit (Ping timeout: 246 seconds). 16:48:49 -!- Jafet has quit (Ping timeout: 246 seconds). 16:51:15 barts: What point dod you get stuck at? 16:51:23 In Link's Awakening 17:02:09 There was a Scottish-Norwegian war? 17:04:00 probably 17:04:06 This 17:04:07 Why 17:04:10 Why this 17:04:13 Oh god 17:04:17 I'm tumblring on IRC 17:04:31 if nothing else, I think they would've been at war during WW2 17:04:43 No, there was a war called the Scottish-Norwegian war 17:04:48 In the 13th century 17:05:29 oh, it was *called* that? so it wasn't actually Scotland and Norway at war? 17:05:56 Well, it was both 17:18:37 -!- Arc_Koen has joined. 17:18:48 hello 17:18:51 -!- augur has joined. 17:18:52 brb 17:19:42 -!- augur has quit (Read error: Connection reset by peer). 17:20:07 -!- augur has joined. 17:23:24 -!- Phantom_Hoover has joined. 17:40:43 fungot: say something funny 17:40:44 olsner: sicp 1ed has the pattern matcher would close over the value of the current 17:41:49 fungot, say something sad 17:41:50 Phantom_Hoover: and you can use almost anything as an excuse 17:41:58 Hey, I'm still brb'ing 17:42:04 Guess I'll brb some more 17:42:07 fungot, i said 'sad' not 'uncomfortable' 17:42:08 Phantom_Hoover: many hellos!!! fnord head on fnord. 17:42:41 fungot: say something fnarfful 17:42:42 olsner: wife thought it might be possible to use 8-bit values in colourmap. :) 17:42:57 silly wife 17:45:12 Yes, the whole idea is beyond bizarre. 17:45:23 8-bit values, in colourmap, with fungot's reputation? 17:45:24 fizzie: that's what she said... i know where jesus the monster truck? 17:46:19 or was it actually fungot that the monster truck there? 17:46:20 olsner: eval ( eq? programmer riastradh)) 17:46:22 fungot, somewhere in the middle east i should thing 17:46:23 Phantom_Hoover: does anyone know a short bf program for 10 million steps? 17:46:25 *think 17:47:28 ^style 17:47:29 Available: agora alice c64 ct darwin discworld europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 17:47:50 "irc", was that from #perl? 17:48:54 -!- atriq has quit (Ping timeout: 240 seconds). 17:51:38 olsner: #esoteric, #scheme and a tiny bit from IRCnet's #douglasadams. 17:51:44 ^style irc 17:51:45 Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams) 17:52:01 Riastradh is/was a #scheme regular. 17:52:40 And eq? is/was (but most likely is) a Scheme predicate. 17:55:19 not that I know anything about scheme, but yes 17:57:16 -!- atriq has joined. 17:58:30 !forth s" gforth" environment? [if] type [then] 17:58:31 0.7.0 17:58:38 (Just checking the version.) 17:59:47 gforth development isn't terribly breezy, 0.7.0 is the latest and it's from Nov 2008. 18:00:53 what about kforth 18:03:23 it doesn't support 'char' thing but is otherwise nice 18:13:34 -!- nortti- has quit (Ping timeout: 240 seconds). 18:28:35 Phantom_Hoover: does anyone know a short bf program for 10 million steps? 18:28:36 itidus21: i think we have a shortage of paths but is much more interesting 18:30:36 -!- Taneb has joined. 18:30:45 -!- atriq has quit (Ping timeout: 256 seconds). 18:31:50 -!- Taneb has changed nick to atriq. 18:31:58 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 18:34:26 I'm sorry, did you say "a short bf program"? that sounded wrong 18:34:52 Brainfuck? 18:34:55 Short? 18:35:07 ^bf +[+]. 18:37:50 Short, but isn't likely to run for exactly ten million steps. 18:38:15 And fungot can't output the \0 character since that doesn't go through IRC. 18:38:16 fizzie: i'm annoyed by both. technically it's not necessary in russian in that context?). i believe the internet works on cr/ lf is the most basic tasks 18:38:54 I think there are some reasonably short but "useful" (well...) programs inside that bot. 18:38:58 ^show 18:38:58 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 18:39:12 The echo/rev kind of things are pretty simple to do. 18:39:29 ^echo Do you hear an echo? 18:39:30 Do you hear an echo? Do you hear an echo? 18:47:12 ^srmlebac Hello? What is this? 18:47:13 Hlo hti hs?its aW?le 18:47:20 Oh, scrambler 18:48:40 ^scramble scramble 18:48:41 srmlebac 18:49:08 ^scramble uenlsbcmra 18:49:09 unscramble 18:49:13 They're all kind of related. 18:49:26 It's mostly about bouncing between the two ends of the string. 18:49:30 ^show scramble 18:49:30 >>,[>,]<[<]>[.>>]<[>>]<2[.<2] 18:50:01 ^show srmlebac 18:50:02 >>,[>,]<[<]>[.>>]<[>>]<2[.<2] 18:50:13 Oh, they're even that close. 18:50:30 Also these must be old, because it hasn't combined the >>s. 18:50:34 -!- ais523 has joined. 18:51:05 ^def scramble bf >>,[>,]<[<]>[.>>]<[>>]<<[.<<] 18:51:06 Defined. 18:51:08 ^show scramble 18:51:09 >2,[>,]<[<]>[.>2]<[>2]<2[.<2] 18:51:30 There, it's a bit shorter. 18:51:50 >> is exactly the same length as >2 18:51:57 Yes, well, I meant in memory. 18:52:09 The ^show output is just a textual dump. 18:53:39 In memory it's in two-cell pairs where one cell gives the command (<> or +- or [ or ] or , or .) and the other the argument (count for <> or +-, the jump destination for [ or ]), so >2 is two cells whereas >> is four. 18:54:17 -!- Phantom_Hoover has joined. 18:54:41 ^def tmp bf ------------------------------------------------------------------------------------------------------------------------------------------------------ 18:54:41 Defined. 18:54:44 ^show tmp 18:54:44 +106 18:55:25 From what I recall, ^show selects +/- (or ) based on which would give the smaller number; internally it's always as-if the command were + or >. 18:55:39 (It has a wrapping tape.) 19:09:05 -!- carado has joined. 19:09:18 -!- oerjan has joined. 19:16:43 I'm really proud of Fueue 19:19:52 smashing language, old chap 19:20:45 I'm scarily not old 19:21:01 Fermat's Last Theorem has been a theorem for longer than I've been a person 19:21:45 You mean forever? 19:21:58 Fermat, that young whippernsapper? 19:22:04 Since September 1994, yes. 19:22:39 It was a theorem before it was proved. 19:22:46 It was even *called* a theorem before it was proved. 19:22:56 Both of those are true! 19:23:04 atriq is just trying to disguise the fact he's http://tvtropes.org/pmwiki/pmwiki.php/Main/ReallySevenHundredYearsOld 19:23:11 My god 19:23:16 I'm a page on TVTropes 19:23:39 -!- Sanqui has changed nick to Sanky. 19:24:11 oerjan: oh, that esolang with the 10% bug was brainfuck 19:24:35 a little known fact about brainfuck 19:24:59 it was first a bug in the interpreter that chopped off the first + (hello world starts with 10 of those, and uses the number 10 as a base to generate the characters) 19:25:28 so I worked around that by adding another + and left the modified program as a trap for my future self 19:25:48 when run in the corrected interpreter, that program gives a 10% bug in the other direction 19:27:01 ah 19:30:17 oerjan: I have two solutions to fix thue's input issue 19:30:45 1) input one character instead of one line. this way the programmer can make sure to treat characters in a way that doesn't allow code injection 19:31:41 2) allow the programmer to define an alphabet to use in the program, and a subset of that alphabet as the input alphabet 19:32:08 oerjan: all brought back because Arc_Koen started doing the bf in thue thing, and I decided to figure out how my last ubuntu upgrade broke my apache config 19:33:47 for 2), the alphabet can be something else than the usual ascii - to make it usable on a regular computer you need to "transcribe" your alphabet as ascii (if it's too big, use several chars to code one symbol), and the user's input is in ascii but with a transcription function that transforms it into your input alphabet 19:34:41 olsner: so I'm your muse? :-) 19:36:26 oerjan: incidentally, the only broken part was that I forgot how to use the thing 19:38:22 Arc_Koen: hmm, I guess :) 19:39:43 fwiw, I didn't write that bf interpreter, but it is written in thue and I have no real idea how it works... thought it would be interesting to try and figure it out while debugging its breakage 19:40:04 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 19:41:11 Arc_Koen: (1) is what Itflabtijtslwi does. 19:41:32 * oerjan realizes he did not have to think about how to spell that this time 19:42:22 it flabt ijts lwi 19:44:54 olsner: if you really want to debug a bf interpreter in thue I'd be glad to give you mine once it's over 19:45:04 but it's kind of a boring thing to program 19:45:17 the idea is *very* simple, but it takes a loooooot of substitution rules 19:47:10 I think when I'm done I'll try to program in Definer, or another similar string-rewriting language that does allow for "variables" 19:47:18 or, like, pattern-matching 19:48:17 I think mod_rewrite uses PCRE 19:49:08 ais523: did thutubot have a bf implementation? 19:49:45 for instance in the interpreter if I want to have some symbols travel through others, I say something like "if a symbol is enclosed in { } brackets, then it moves to the left", but I have to write the substition rules for all symbols {+}, {-}, {>}, etc., for all symbols they can meet 0{+}::={+}0, 1{+}::={+}1, 0{-}::={-}0, etc 19:49:59 and to make things worse it's completely irreadable 19:50:15 (espacially if one of the symbols is a : or a =) 19:51:38 it's like how i made the first loop in /// before i found the copying twice trick 19:51:46 heh, avoid using : and = then :P 19:52:21 olsner: well i'm kind of short in symbols and I don't want to use words too much 19:52:30 no wait, that was even more insane. 19:52:40 an incredibly verbose interpreter would be a bit funny though 19:52:47 I use = as the operator that checks if a cell is equal to 0 19:53:06 (and debuggable, if it's constantly explaining exactly what it's doing) 19:53:26 hmm, if you had said that sooner I might have made it completely full of words 19:54:01 as in, even input would have had to be in the form increment decrement move left move right input output begin loop end loop 19:54:13 but now I've written too much to want to restart anything 19:54:13 hm you could say the first /// loop was attempting to use a thue method in a language not suited for it. 19:54:31 does /// use string-rewriting? 19:54:36 yes. 19:54:53 it's even simpler than thue. 19:54:56 hmm, /// eats everything up until the third / after applying a rewrite rule? 19:55:18 or before... 20:02:23 basically /// is both string-rewriting and self-modifying code 20:03:54 with the latter the only way to do real flow control 20:04:57 and looping requires quine-like techniques 20:11:01 /// is the best language 20:14:40 erh, earlier today we told someone that was eodermdrome 20:14:50 THAT WAS EARLIER TODAY 20:15:19 -!- Phantom_Hoover has joined. 20:15:32 also, /// is already implemented. 20:16:07 hmm, I might decide to implement /// soon 20:16:43 there might even be a more efficient implementation than the perl one. possibly by User:Nthern. 20:16:56 * oerjan never tested that. 20:17:20 more efficient than perl? wow! 20:17:47 the perl one keeps scanning the string from the beginning, whether or not there can be new matches there 20:18:00 -!- atriq has quit (Quit: Leaving). 20:18:38 for some substitutions that's gonna hurt. 20:19:29 it was just a quick hack to get a working implementations, after all. 20:19:33 *-s 20:20:02 it just _barely_ manages to run the BCT interpreter without hitting one of perl's internal limits. 20:20:40 (regexp recursion depth) 20:23:07 afaik Nthern is the only other person who has succeeded at programming in /// 20:23:14 hmm, what is it that uses recursion in those regexps? 20:24:27 s!^/((?:[^/\\]|\\.)*)/((?:[^/\\]|\\.)*)/!!s is the one which tended to crash 20:25:38 couldn't you make it [^/\\]+ to match longer chunks? 20:25:48 it is possible it doesn't use recursion in all perl versions, i think the ?: 's were an attempt to simplify it 20:26:15 olsner: except the BCT interpreter uses only / and \ characters :P 20:26:37 aah, sounds appropriately evil 20:27:12 it seemed like the logical thing to aim for, after getting basic "readable" looping going 20:27:30 oerjan: so my brother drops a pair of shorts in the clothes washer and just leaves them there, i don't even know when... makes no reference to it... this is what i live with 20:27:39 that's after initial syntactic desugaring btw. 20:28:00 after syntactic salting? 20:28:00 itidus21: HOW DESPICABLY EVIL 20:28:28 It's also possible to optimize some Perl regexps a whole lot with suitably placed (?>...)s. (It's a kind of a forced never-backtrack construct.) 20:28:35 * oerjan always checks the washing machine for forgotten clothes before using it. 20:29:12 oerjan: but they havent been washed... evidenced by their dryness 20:29:17 fizzie: i recall the perl version i used wasn't the newest one 20:29:33 itidus21: HOW DESPICABLY EVIL 20:30:24 It's possible (?>...) is reasonably new; it's quite far down in the manual, at least. 20:31:26 The *+ construct can be an easier way and I think it's earlier too. 20:31:40 *+ ? 20:31:41 oerjan: personally i don't even care.. i wash my stuff at laundromat lately.. but my mom comes along saying "can you turn on washing machine for me? running out of clean towels" because the knob is busted she can't actually turn on the machine herself 20:32:19 so i tell her about the shorts and she just carries them off into her room.. "ok ive emptied it" 20:32:33 oerjan: *+ and ++ and ?+ and {n}+ and so on are the "possessive" versions of the quantifiers. 20:32:55 oerjan: "Match as much as possible and never give anything back" is what they do. 20:32:57 so.. if i get depressed sometimes.. it's not baseless 20:33:07 oh. so it's not just * and + combined 20:33:45 /a++a/ e.g. can't ever match, because a++ gobbles all the a's. 20:34:54 Not that I know how well the regex engine can do without the hints in your original example, and whether the potential backtracking points matter. But it's a case where you know exactly what to match. 20:35:40 itidus21: hypocritically speaking, i'm pretty sure a healthy person wouldn't be depressed by such events. 20:36:37 "For instance, the typical "match a double-quoted string" problem can be most efficiently performed when written as: /"(?:[^"\\]++|\\.)*+"/ as we know that if the final quote does not match, backtracking will not help." (perlre example on them.) 20:36:40 oerjan: ain't noone healthy in this house 20:37:10 although perhaps it's a sign that we're at least a bit on the autistic spectrum 20:37:32 lol hypocritically speaking 20:37:35 (disclaimer: DO NOT USE FOR MEDICAL ADVICE) 20:37:36 oh no 20:37:47 regexps are awesome for writing gobbledygook like "(?:[^"\\]++|\\.)*+" 20:39:08 fizzie: that _does_ look eerily similar 20:41:10 oerjan: ironically for me facing my fears means doing someone elses laundry 20:43:09 -!- TeruFSX has joined. 20:47:42 hmmm 20:48:09 a fueue itnerpreter in thue would actually be shorter that a brainfuck one 20:48:31 cause fueue has only one structure (that is, code and date are together) 20:50:06 oerjan: your proof that fueue is turing complete, does it work if numbers are bounded? 20:51:18 oh screw that I can do it with unbounded numbers *rolls his sleeves up* 20:51:27 > 64^3 20:51:28 262144 20:53:22 > 64 `xor` 3 20:53:23 Ambiguous type variable `a' in the constraint: 20:53:23 `Data.Bits.Bits a' 20:53:23 a... 20:53:31 67 20:53:44 fizzie: aww, changing * to *+ didn't help, at least with the perl version installed here (5.10.0) 20:55:44 > Data.Bits.xor 3 4 20:55:45 Ambiguous type variable `a' in the constraint: 20:55:45 `Data.Bits.Bits a' 20:55:45 a... 20:55:51 Wtf 20:56:07 > 64 `xor` 3 :: Word 20:56:08 67 20:56:10 It works fine with ghc/ghci 20:56:17 Arc_Koen: my proof doesn't use number arithmetic at all, there's a lonely 1 used for a delaying trick 20:56:29 :t xor 20:56:30 uh 20:56:30 forall a. (Bits a) => a -> a -> a 20:56:42 you mean YOU DON'T NEED NUMBERS at ALL??? 20:56:58 shocking 20:57:03 indeed, that 1 could probably be changed to something else :) 20:57:27 putStrLn "hello" `xor` putStrLn "world" 20:58:18 Arc_Koen: it's only using the functional parts of fueue in an essential way 20:58:26 arc_koen: class (Eq a, Num a) => Bits a 20:59:48 FreeFull: ghci uses the extended defaulting option, which defaults numeric types in more general circumstances 21:00:51 fizzie: btw http://oerjan.nvg.org/esoteric/slashes/longsubst.sss is a simple program triggering the bug 21:01:03 Ah, ghc does error out 21:01:22 it _should_ print hello if working 21:01:48 oh and some newlines, i didn't bother removing them 21:01:52 olsner: so i'm gonna make a verbose thue fueue interpreter 21:02:03 Arc_Koen: have fun! 21:02:22 fun? I'm doing it for SCIENCE 21:02:35 Arc_Koen: well you need numbers for output, but you can consider it TC even without if you consider final queue contents 21:02:36 oerjan: If I can manage to remember, I'll try some things out when I'm not typing via the phone. 21:02:50 hmm, yeah, ok 21:03:46 oerjan: would brainfuck be tc with cell contents being unbounded, but without the - instruction? 21:04:08 I'm thinking it doesn't change anything 21:04:27 like, you can have a cell you call "zero" which you increment instead of decrementing every other cell 21:05:07 Arc_Koen: as long as the tape still is unbounded, it might work 21:05:19 hmm I don't think we need that 21:05:24 for instance take 4-cell brainfuck 21:05:46 don't use the fourth cell, except to emulate - 21:06:11 (so if you're in the first cell, instead of - you write >+>+>+) 21:06:24 (well >+>+>+>) 21:06:34 Arc_Koen: um you can never get information out of a cell if you cannot get it back to zero 21:06:43 oh, that's true 21:06:45 other than that it is nonzero 21:07:27 so how would it work if the tape was unbounded? 21:08:32 in that case there ought to be a way to move data further on the tape, to the still zero parts 21:09:43 so you would encode the cells of a brainfuck with - as sequences of 0's and nonzeros 21:10:02 haha 21:10:04 nice 21:10:21 -!- boily has quit (Quit: Poulet!). 21:10:35 hmmm I'm not convinced though 21:10:51 well i'm reminded of Sceql 21:14:00 -!- monqy has joined. 21:14:01 anyway i'd imagine a memory layout like 0 ...arbitrary non-zero trash... 0 first bf cell 0 second bf cell 0 ... last bf cell 0 0 ... 21:14:33 hm make that 0 0 between the trash and first cell too 21:15:02 oh and a 0 0 somewhere around the current cell. 21:15:41 hmm... I think apache does potentially evil things with leading slashes in uris 21:21:28 "Use with extreme caution, as it may result in loop." :) 21:22:37 (it could if there wasn't a limit on the number of matching rules and if the server didn't run out of memory so quickly) 21:23:53 ...arbitrary non-zero trash... 0 (0 (1 1*))* 0 (0 (1 1*))* 0 0 0... 21:24:52 well gnight 21:25:11 night 21:25:21 (the fueue interpreter might not be shorter than the brainfuck one because it has so much moving around) 21:25:41 tricky 21:26:02 wait i've not even finished browsing the logs yet... 21:26:26 like, the 'fadd' function sends a 'check arithm' marker to see if it has correct arguments, then the marker comes back as 'ok arithm' or 'noop' 21:26:44 if it's noop then fadd must move through the whole queue 21:27:26 if it's ok arithm then it's a nightmare of adding two numbers, then the results still has to move through the whole queue 21:27:45 if thue had WRAPPING that would be so easy 21:28:45 oerjan: I'm not sure it's healthy browsing the logs... it's like every moment you're not on the chan you have to live twice (once out of the chan and once reading the log) 21:29:00 you're gonna get old TWICE AS FAST 21:29:14 of course an easy remedy would be to stay on the chan as often as possible :-) 21:29:17 AAAAAAAAAAA 21:29:18 anyway bye 21:30:04 -!- carado has quit (Quit: Leaving). 21:31:31 @tell Arc_Koen If you want things "easy", go Thutu or something. (Disclaimer: only lookes at Thutu briefly.) 21:31:31 Consider it noted. 21:31:34 I got tired of keeping that in the input buffer, waiting for the quit. 21:32:20 AAA you just shifted the balance fo need sleep / got plenty things to do 21:32:20 Arc_Koen: You have 2 new messages. '/msg lambdabot @messages' to read them. 21:34:23 hum, you know what, thutu can wait 21:34:35 @messages 21:34:35 oerjan said 1d 1h 43m 33s ago: did you mean to remove an a from the kipple truth-machine program? i don't know kipple so... 21:34:36 fizzie said 3m 4s ago: If you want things "easy", go Thutu or something. (Disclaimer: only lookes at Thutu briefly.) 21:34:49 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 21:35:51 It's super-promising when you look up an obscure error on Google and the first result is “Pig Latin Reference Manual” 21:40:49 ouyay on'tday aysay 21:51:10 -!- TeruFSX_ has quit (Read error: Connection reset by peer). 21:51:55 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 21:53:00 Keccak won the SHA-3 competition 21:54:15 http://www.nist.gov/itl/csd/sha-100212.cfm 21:54:37 What, so soon. 21:54:59 -!- kmc has set topic: I, for one, welcome our new hash function overlords | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 21:55:55 Keccak does sound like a proper name for an alien overlord. 21:56:07 LORD KECCAK. 21:56:40 Keccak sucks as a palindrome. 21:56:41 yeah 21:56:56 it's pronounced "kashyyyk" 22:17:06 -!- TeruFSX has quit (Ping timeout: 245 seconds). 22:25:10 Hm. 22:25:18 -!- atrapado has quit (Quit: Leaving). 22:25:23 It is astoundingly difficult to Keccak-hash something right now. 22:25:35 I'm looking for an implementation that I can just say “here's a file, what's its hash” 22:25:36 Nope. 22:26:00 my university has a nick cage appreciation society 22:26:12 i hope this is a homestuck joke and not something sincere 22:26:35 http://guyism.com/wp-content/uploads/2012/07/best-resume-ever.jpeg 22:28:15 gregor: Add the future-snapshots repository and install sha3sum. 22:28:27 Perfect! 22:28:32 future-snapshots/20131001 should work nicely. 22:28:52 The implementation is publicly available, but it's all test suites, no tools. 22:33:20 you should smoke a bowl of hash in honor of this occasion 22:42:19 -!- jiella has quit (Quit: Leaving.). 22:55:06 -!- TeruFSX has joined. 22:57:11 -!- Jafet1 has quit (Quit: Leaving.). 23:07:04 -!- FreeFull has quit (Quit: Zzzzzzzzzzzz). 23:09:19 Hmm, it's not a Merkle-Damgård hash. 23:18:35 -!- Jafet has joined. 23:20:20 Gregor: http://keccak.noekeon.org/KeccakReferenceAndOptimized-3.2.zip 23:20:47 pikhq_: Try using that to get a hash of a file. 23:20:49 pikhq_: I dare you. 23:21:40 Ass! 23:21:57 Why would you make the test program something other than a read file and shove it into the hasher? 23:23:50 Okay, I'm *sure* it's a perfectly reasonable hash algorithm, but the implementation was written by an incompetent. 23:24:21 They're Belgian *shrugs* 23:26:41 http://keccak.noekeon.org/specs_summary.html Well, there's enough you could probably write it yourself. 23:29:17 All I was going to do was hash the topic. 23:29:23 The joke is long dead by now ;) 23:29:27 -!- TeruFSX has quit (Read error: Connection reset by peer). 23:29:55 Still annoyed. 23:35:27 -!- augur has quit (Remote host closed the connection). 23:37:55 Actually, I'm impressed at how simple this hash algorithm can be. 23:46:32 DCB6B8BD29813DA1A9B56667D751A6D444ECFC5B0F67D6EB85DEF9E 23:46:48 That's SHA3-224 of the topic. 23:47:02 How 'bout just “I, for one, welcome our new hash function overlords” 23:47:28 E581A6F9E364E179B336A2C6D6831D4B50CD7739C7E1565E3EBF2 23:47:47 -!- Gregor has set topic: I, for one, welcome our new hash function overlords | E581A6F9E364E179B336A2C6D6831D4B50CD7739C7E1565E3EBF2 | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 23:47:58 pikhq_: How are you computing it? 23:48:11 SHA3 looks much more complicated than SHA1 to me. 23:48:26 shachaf: Grabbed "readable keccak" and shoved the string into it. 23:48:44 Oh, *readable*. 23:48:48 Sounds promising. 23:48:53 http://www.mjos.fi/dist/readable_keccak.tgz 23:49:04 It's 106 lines of C. 23:49:28 A bit more if you want to make it useable as a general-purpose library, of course. 23:49:50 But I doubt it'd go over 200 if you don't try optimizing it. 23:50:13 OK, it's not so bad. 23:50:20 It still has a lookup table. :-( 23:50:27 Tiny one though. 23:53:24 Ah. Part of why the other keccak implementations are complex is that they support all possible parameters of the algorithm... 23:53:38 What I pasted their suffices for the SHA3 ones. 23:53:50 s/their/there/ 2012-10-03: 00:11:13 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:24:49 -!- ais523 has quit. 00:34:24 -!- copumpkin has joined. 00:36:21 -!- augur has joined. 00:45:12 -!- Jafet1 has joined. 00:47:35 -!- Jafet has quit (Ping timeout: 256 seconds). 00:55:47 -!- Jafet1 has quit (Ping timeout: 260 seconds). 01:11:14 I need a good night's slep 01:12:58 Keccak is not appropriate for password hashing, right? 01:13:07 It's fast, and good password hashing is slow? 01:13:20 Not on its own. 01:13:27 you should run your passwords through something like PBKDF2 01:13:36 Presumably PBKDF2-SHA3 is fine. 01:13:40 which is a fancy way of saying "iterate the hash many times" 01:13:49 But so is bcrypt etc. 01:13:56 (and probably do other things, but I don't know if those are important for uses other than deriving crypto keys) 01:13:59 kmc: PBKDF2 also xors the iterations together, at least. 01:13:59 PBKDF2? 01:14:05 Sgeo: yes, PBKDF2 01:14:40 you can read about PBKDF2 in a multimedia hypertext encyclopedia using a global network of packet-switched communications 01:14:47 food, bbl 01:20:22 o.O someone submitted a hash algorithm to the contest maliciously? 01:21:05 Sgeo: I should hope so. 01:21:16 Otherwise how can you tell if the process is doing its job? 01:21:33 -!- Jafet has joined. 01:21:56 Oh, someone just modified one of the entries to be malicious, as a proof of concept I guess 01:21:58 afaict 01:25:36 -!- Jafet1 has joined. 01:25:52 -!- Jafet has quit (Ping timeout: 246 seconds). 01:30:04 -!- Jafet1 has changed nick to Jafet. 01:30:27 > length "E581A6F9E364E179B336A2C6D6831D4B50CD7739C7E1565E3EBF2" `div` 2 01:30:28 26 01:41:20 that's funny 01:47:38 also funny: one of the SHA-3 competitors has already seen widespread real world use 01:47:48 MD6 was used by the Conficker worm 01:47:58 if you enter one of those competitions do you get mysterious advice from the NSA, a la DES? 01:48:02 oh john tromp also won the ioccc 01:49:34 that's weird i thought he was on the esolang wiki somewhere, but no 02:04:36 -!- oerjan has quit (Quit: Good night). 02:35:55 Gah, screwed up my *printing* routine. XD 02:36:19 E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 02:37:13 -!- Lumpio- has quit (Ping timeout: 245 seconds). 02:37:52 -!- pikhq_ has set topic: I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 02:40:28 > length "E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2" `div` 2 02:40:29 28 02:41:53 Yup, SHA3-224. 02:43:51 > showIntAtBase 2 ("01"!!) (28*8) "" 02:43:52 "11100000" 02:48:10 -!- Nisstyre-laptop has joined. 03:03:42 -!- Lumpio- has joined. 03:04:32 -!- TeruFSX has joined. 03:29:15 -!- hagb4rd has joined. 03:31:51 -!- Jafet has quit (Ping timeout: 244 seconds). 03:39:30 -!- Jafet has joined. 04:13:37 this is such a pretty place to be, i've just stumbled upon it..lovely 8bit canvas demo -> http://www.effectgames.com/demos/canvascycle/ 04:44:37 -!- carado has joined. 04:51:28 -!- carado has quit (Remote host closed the connection). 05:04:20 -!- Jafet has quit (Quit: Leaving.). 05:13:08 -!- Jafet has joined. 05:39:17 http://www.youtube.com/watch?v=JWToUATLGzs 05:56:08 -!- carado has joined. 06:25:39 -!- const has quit (Ping timeout: 276 seconds). 07:03:35 -!- hagb4rd has quit (Quit: hagb4rd). 07:04:36 -!- epicmonkey has joined. 07:23:15 -!- carado has quit (Remote host closed the connection). 07:30:56 -!- mig22 has joined. 07:33:51 -!- atriq has joined. 07:40:10 i am working on a piece of hardware which can take any wave and output an analog sync clock 07:40:18 well, sine-like wave 07:40:24 that reminds me i wanted to try a metronome 07:42:25 -!- kinoSi has quit (Read error: Connection reset by peer). 07:42:52 -!- kinoSi has joined. 07:48:12 -!- monqy has quit (Quit: hello). 07:50:18 oh the video just loaded 07:50:33 the metronomes become synchronized because of a phenomenon called soft syncing 07:51:26 it happens because they are all coupled in angular momentum 07:52:23 in fact the whole swivel is a single energy pool which tries to maximize its use of that energy 08:10:37 -!- atriq has quit (Ping timeout: 246 seconds). 08:44:30 -!- coppro has quit (Ping timeout: 264 seconds). 09:01:22 -!- Phantom_Hoover has joined. 09:20:59 -!- Jafet has quit (Ping timeout: 246 seconds). 09:41:56 -!- Jafet has joined. 09:49:29 -!- Phantom__Hoover has joined. 09:49:31 -!- Phantom__Hoover has quit (Client Quit). 09:59:54 -!- Phantom__Hoover has joined. 10:10:08 -!- kinoSi has quit (Read error: Connection reset by peer). 10:10:34 -!- kinoSi has joined. 10:10:57 -!- Arc_Koen has joined. 10:11:15 heeello 10:18:54 -!- Phantom__Hoover has quit (Quit: Leaving). 10:20:30 Heel-o. 10:38:03 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 10:49:48 -!- carado has joined. 11:11:04 -!- barts has quit (Ping timeout: 246 seconds). 11:13:03 -!- barts has joined. 11:26:31 -!- Phantom_Hoover has joined. 11:38:31 -!- yours_truly has joined. 11:40:32 -!- Nisstyre has quit (Ping timeout: 255 seconds). 11:40:49 -!- Nisstyre-laptop has quit (Ping timeout: 260 seconds). 11:46:02 -!- carado has quit (Quit: Leaving). 11:55:34 -!- Nisstyre has joined. 11:58:49 -!- copumpkin has quit (Ping timeout: 246 seconds). 11:59:24 -!- copumpkin has joined. 12:03:33 -!- mig22 has quit (Quit: mig22). 12:29:43 “House of Marley Positive Vibration Rasta”, “color: rasta” http://www.thomann.de/fi/house_of_marley_positive_vibration_rasta.htm 12:36:32 ion: According to fcolor, #a37f58 is the color of "rasta" after 10 images (190 to go). 12:37:34 (Some of these results are a bit nonrelevant-looking.) 12:38:32 http://users.ics.aalto.fi/htkallas/rasta.png and so it goes. 12:39:08 I conclude that it mostly means something vaguely brownish. 12:39:19 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 12:45:44 -!- Slereah has quit (Ping timeout: 252 seconds). 12:45:56 -!- Slereah has joined. 12:57:51 -!- MoALTz has joined. 13:00:56 -!- boily has joined. 13:20:18 http://www.ling.helsinki.fi/~fkarlsso/genkau2.html 13:22:00 "This page has been glanced at by [Counter datafile "/usr/local/etc/Counter/data/sample3.dat" must be created first!] visitors external to our department" 13:22:53 Page view counters, where have they all gone? 13:26:55 -!- Phantom_Hoover has joined. 13:31:37 -!- itidus20 has joined. 13:35:30 -!- itidus21 has quit (Ping timeout: 264 seconds). 13:35:36 -!- coppro has joined. 13:35:37 -!- itidus20 has changed nick to itidus21. 13:37:19 oh hey quintopia maybe you can help me 13:38:13 I'm trying to understnad the hello world program in http://esolangs.org/wiki/Platts 13:39:01 1) what are the two zeroes in the initial string for? 13:39:48 2) when B produces Hello World!, the output mode is off, so why is it printed? 13:40:24 or are every ever produced strings printed everytime that a string is produce while the output mode is on? 13:41:28 so if the production rules were A> B|Hello World! H>J J|K K! for instance, the Hello World would be printed twice? 13:41:43 (once by H>J and once by J|K) 13:42:50 -!- kinoSi has quit (Read error: Connection reset by peer). 13:43:17 -!- kinoSi has joined. 13:43:45 For 2), isn't output mode off at first, and toggled on by the "A>" production, leaving it on for "B|Hello World!"? 13:44:16 ohhhhhhh right 13:44:20 I hadn't considered that 13:46:01 A0B0 -[toggle output mode on]-> 0B0 -[implicit empty string]> B0 -[output "Hello World!"]-> Hello World! -[toggle output mode off]-> Kello World! -[halt], I guess. 13:46:26 Whoops, without forgetting the latter 0. 13:46:43 Unless they mean something else, I'unno. 13:49:04 Or, hm, right; if it's a 2-tag system, those 0s get deleted too. 13:50:27 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 13:51:52 A0B0 -[toggle output mode on]-> B0 -[output "Hello World!"]-> Hello World! -[toggle output mode off]-> llo World!K -[implicit empty-string rules]-> K -[halt], in that case. 13:52:00 (I read it as just rewriting at first.) 14:04:18 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 14:05:27 nah, I don't think it's string-rewriting 14:05:44 I think A produces empty string and toggle output mode on 14:05:51 0 produces empty string 14:06:02 B produces Hello World!, which is printed 14:06:20 oh hum and then I don't know if it's 0's turn or H's turn 14:06:34 Arc_Koen: It's a 2-tag system, it says so right up there. 14:06:41 Any symbols not explicitly assigned production rules in the program listing are implicitly assigned a production of the empty string. 14:07:08 See http://esolangs.org/wiki/Tag_system -- they always delete m (in this case, 2) symbols from the left, and append the production to the right. 14:07:12 hmmmm ok 14:08:13 I didn't notice at first, since I just went "oh, production rules". 14:13:38 -!- Phantom_Hoover has joined. 14:29:56 -!- copumpkin has joined. 14:32:09 hi Arc_Koen 14:40:22 -!- xiaoding has joined. 14:40:29 -!- xiaoding has left. 14:41:57 fizzie's second production sequence is correct 14:41:58 hi 14:42:27 yep apparently the issue was just that I didn't know what a tag was 14:42:43 -!- kmc has set topic: I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | http://codu.org/logs/_esoteric/ |. 14:42:47 -!- kmc has set topic: I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 14:47:52 -!- aloril_ has quit (Ping timeout: 250 seconds). 15:03:50 -!- aloril_ has joined. 15:05:14 -!- yours_truly has quit (Ping timeout: 240 seconds). 15:16:03 -!- xiaoding has joined. 15:16:58 -!- xiaoding has quit (Read error: Connection reset by peer). 15:17:29 -!- xiaoding has joined. 15:17:43 -!- xiaoding has left. 15:18:07 -!- augur has quit (Remote host closed the connection). 15:21:40 -!- aloril_ has quit (Ping timeout: 250 seconds). 15:29:56 -!- FreeFull has joined. 15:30:20 -!- xiaoding has joined. 15:30:35 -!- xiaoding has left. 15:31:32 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 15:36:30 -!- aloril_ has joined. 15:41:34 -!- aloril_ has quit (Read error: Operation timed out). 15:42:21 -!- Phantom_Hoover has joined. 15:55:04 -!- aloril_ has joined. 16:03:05 -!- aloril_ has quit (Ping timeout: 244 seconds). 16:11:24 -!- augur has joined. 16:19:16 -!- aloril_ has joined. 16:21:48 -!- aloril_ has quit (Read error: Operation timed out). 16:36:02 -!- aloril_ has joined. 16:43:08 -!- aloril_ has quit (Ping timeout: 250 seconds). 16:43:10 Rats (1984) - Trailer http://youtu.be/2zbl4_xkORc 16:47:08 -!- ogrom has joined. 16:57:16 -!- aloril_ has joined. 17:03:30 -!- aloril_ has quit (Ping timeout: 250 seconds). 17:05:25 -!- sivoais has quit (Quit: Lost terminal). 17:14:26 -!- coppro has quit (Ping timeout: 255 seconds). 17:14:33 -!- sivoais has joined. 17:15:14 -!- epicmonkey has quit (Ping timeout: 246 seconds). 17:20:23 -!- aloril_ has joined. 17:27:18 -!- carado has joined. 17:32:31 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 17:38:44 -!- atriq has joined. 17:43:15 -!- ais523 has joined. 17:51:08 Goddammit haskell 17:51:31 ghci thinks 25*0.036 is 0.8999999999999999 17:51:36 :: CReal 17:52:09 :: Rational 17:52:29 Floating-point numbers are the devil. 17:53:02 Nothing wrong with floating-point numbers (except for denormals and NaN) as long as you use them appropriately. 17:53:05 zomg irb thinks the same thing. 17:53:11 And Python! 17:53:21 ion: *Ahem*. Floating point *values*. 17:53:49 on windows calculator, 0.8999999999999999 / 0.36 = 2.4999999999999997222222222222222 17:54:07 I blame haskell for using an inexact default representation of fractional values 17:54:13 > (25*0.036 :: CReal, 25*0.036 :: Rational) 17:54:14 (0.9,9 % 10) 17:54:43 `runc int main(void) { printf("%.20f", 25*0.036); } 17:54:44 What is CReal in 17:54:45 freefull: What should pi be in the exact representation of fractional values? 17:54:48 0.89999999999999991118 17:54:49 Rational is nicer than CReal if you're just talking about rationals. 17:55:01 ion: An infinite value of course 17:55:19 Infinite in length I mean 17:55:53 0.9 is definitely representable accurately without too much data though =P 17:56:08 in base-10 17:56:30 In any base, using the right representation 17:57:04 In binary you can say 1001/1010 17:57:30 There, accurate representation of 0.9 17:57:41 :: Rational 17:58:07 pi is representable using only two bytes of data. 17:58:08 Funny that you're discussing this in here. 17:58:18 shachaf: In base pi =P 17:58:21 My latest FB post: The worst part of floating point math is not the fact that 0.1 + 0.2 yields 0.30000000000000004, but trying to explain to people why their language is horribly broken if 0.1 + 0.2 does NOT yield 0.30000000000000004. 17:58:26 In Base English. 17:58:49 -!- Phantom_Hoover has joined. 17:58:55 > toRational (25*0.036 :: Double) 17:58:56 2026619832316723 % 2251799813685248 18:00:06 If you "cast" the end result to Rational, and you don't put :: Double in anywhere or anything similar, will the entire computation be done using rationals? 18:00:39 That's not a cast. 18:00:45 But yes. 18:01:26 That's why I put it in quotes 18:01:27 =P 18:01:36 @type 0.036 18:01:37 forall t. (Fractional t) => t 18:01:52 Rational is a member of Fractional, right? 18:02:02 Or whatever the term is 18:02:17 Haskell doesn't work that way, FreeFull. 18:02:42 Tell me more then 18:04:55 -!- augur has quit (Remote host closed the connection). 18:05:52 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 18:06:44 Rational is Ratio Integer, and there is an instance (Num (Ratio a), Integral a) => Fractional (Ratio a), which is maybe an answer, of sorts. But maybe a real Haskeller will explain it all. 18:06:50 -!- augur has joined. 18:07:12 > toRational (pi :: Double) 18:07:13 884279719003555 % 281474976710656 18:07:15 -!- augur has quit (Remote host closed the connection). 18:07:23 > toRational (exp 1 :: Double) 18:07:24 6121026514868073 % 2251799813685248 18:07:56 ion: That should show all those irrational-pi people. 18:09:30 > toRational (pi :: CReal) 18:09:31 *Exception: CReal.toRational 18:09:34 Aw. 18:12:33 -!- hagb4rd has joined. 18:12:41 -!- coppro has joined. 18:14:03 * Sgeo wonders if socket.io is/should be a sufficient motivation to use Node.js even if I don't want to use Javascript server-side 18:14:32 Oh there exists socket.io for other languages 18:15:04 -!- jiella has joined. 18:15:14 one script to rule them all 18:18:09 Sgeo: Oh, but you DO want to use JavaScript server-side. 18:27:41 do you? 18:32:14 http://blog.nelhage.com/2012/03/why-node-js-is-cool/ (it's not about performance) 18:32:52 it's not about javascript either 18:33:38 is it about doing cooperative multitasking by hand? 18:33:54 kind of but not really 18:33:59 Hahaha X-D 18:34:50 fungot: What's it all about, really, in the end? 18:34:51 -!- variable has joined. 18:34:51 fizzie: i need this terminal for something else in mind 18:35:12 fungot: Okay, be that way. I didn't want an answer anyway. 18:35:13 fizzie: what now? :) ( of course that ignores the fact that i have 18:35:36 oh, "a sweet spot in terms of what developers are willing to put up with" 18:36:26 it's a framework which more or less forces you to write network libraries in a composable way 18:36:27 olsner: That's the best description of anything I have ever heard. 18:36:32 which is something people traditionally do poorly 18:36:54 it is not the theoretically best way of doing so, but it's a thing that exists now that a lot of people use 18:37:18 that is the tl;dr of that article 18:41:37 -!- hagb4rd has quit (Quit: hagb4rd). 18:47:44 is there a tl;dr language? 18:51:34 tl;dr: 99 bottles of beer 18:55:24 itidus21: Yes, it's called C++. 18:55:48 ISO-9899 bottles of beer 18:56:43 steal_underpants(); [...] return profit; 18:57:11 -!- hagb4rd has joined. 18:58:02 An ISO 9001 bottle of beer is quality-managed. 18:58:30 http://www.savingadvice.com/images/blog/generic-beer.jpg 18:59:19 An ISO 8601 bottle of beer has a standardised date format. 18:59:36 an ISO 3103 bottle of beer is actually tea 18:59:50 I like how the image accompanying ISO 9000#Contents of ISO 9001 is "ISO 9001 certification of a fish wholesaler in Tsukiji" http://upload.wikimedia.org/wikipedia/commons/thumb/d/d5/ISO_9001_in_Tsukiji.jpg/609px-ISO_9001_in_Tsukiji.jpg 18:59:53 which ISO describes the ISO? 18:59:56 It's so relevant. 19:00:07 ISO is also a demogroup. 19:00:37 "ISO 8128-2:1993: Apple juice, apple juice concentrates and drinks containing apple juice -- Determination of patulin content -- Part 2: Method using thin-layer chromatography" 19:02:21 http://www.iso.org/iso/home/store/catalogue_tc/catalogue_tc_browse.htm?commid=47918&published=on 19:03:30 (Or at least kind of a group.) 19:05:20 kmc: Did you purchase a copy of ISO 8128-2 already? 19:05:45 With that sort of a name, I'm sure it's flying off the shelves. 19:07:37 i don't have any CHF :/ 19:08:01 What is patulin 19:08:18 Oh, it's a toxin produced by moulds 19:08:27 the swiss see a pretty woman they say ein, zwei, drei and try to push her down some ice 19:09:13 kmc: I don't get it 19:10:15 it's a quote from cool runnings 19:10:48 ah, cool runnings 19:13:40 -!- Jafet has quit (Ping timeout: 252 seconds). 19:14:04 -!- atriq has quit (Ping timeout: 260 seconds). 19:47:38 -!- atriq has joined. 19:53:42 @messages? 19:53:42 Sorry, no messages today. 19:53:49 @messages 19:53:49 You don't have any new messages. 19:54:01 @messages? 19:54:01 Sorry, no messages today. 20:14:25 -!- oerjan has joined. 20:17:37 I conclude that it mostly means something vaguely brownish. <-- THAT'S RACIST! 20:17:49 My new tattoo http://i.imgur.com/HH89J.jpg 20:18:06 "dishouner"? 20:18:26 "whoosh"? 20:18:42 "is there a joke I'm missing" 20:18:52 "brownish" 20:19:03 oerjan: It's not racist when it's determined by an impartial algorithm. 20:19:22 fizzie: that's what the segregationists said! 20:23:46 > 25 * 0.036 20:23:47 0.8999999999999999 20:23:57 > 0.9 20:23:58 0.9 20:24:57 > 0.9 - 25 * 0.036 20:24:58 1.1102230246251565e-16 20:25:32 > ((25*0.001)*36, 25*(0.001*36)) 20:25:33 (0.9,0.9000000000000001) 20:25:59 > ((25*0.001)*36, 25*(0.001*36), 25*(36*0.001)) 20:26:00 (0.9,0.9000000000000001,0.9000000000000001) 20:26:08 `addquote My latest FB post: The worst part of floating point math is not the fact that 0.1 + 0.2 yields 0.30000000000000004, but trying to explain to people why their language is horribly broken if 0.1 + 0.2 does NOT yield 0.30000000000000004. 20:26:11 866) My latest FB post: The worst part of floating point math is not the fact that 0.1 + 0.2 yields 0.30000000000000004, but trying to explain to people why their language is horribly broken if 0.1 + 0.2 does NOT yield 0.30000000000000004. 20:26:21 > ((25*0.001)*36, 25*(0.001*36), 25*(36/1000)) 20:26:22 (0.9,0.9000000000000001,0.8999999999999999) 20:26:32 -!- ogrom has quit (Quit: Left). 20:26:33 Posted Using FB2IRC Technology® 20:26:42 > 0.1 + 0.2 20:26:43 0.30000000000000004 20:26:53 > 0.1 + 0.2 :: Float 20:26:55 0.3 20:27:01 > 0.1 + 0.2 :: Rational 20:27:03 3 % 10 20:27:15 > 0.1 + 0.2 :: Quadrupal 20:27:16 Not in scope: type constructor or class `Quadrupal' 20:27:20 > 0.1 + 0.2 :: Quadruple 20:27:21 Not in scope: type constructor or class `Quadruple' 20:27:23 : 20:27:24 ( 20:27:30 My frown slipped 20:27:39 what's quadruple 20:27:56 http://en.wikipedia.org/wiki/Quadruple-precision_floating-point_format 20:28:00 ah 20:28:21 It's a thing which exists 20:29:17 > pi :: Rational 20:29:18 Quadruped-precision 20:29:18 No instance for (GHC.Float.Floating GHC.Real.Rational) 20:29:18 arising from a us... 20:29:28 i thought you might be misspelling Quaternion (not that i think lambdabot has that) 20:29:35 > 1 :: Quaternion 20:29:36 Not in scope: type constructor or class `Quaternion' 20:29:37 -!- MoALTz has quit (Quit: Leaving). 20:29:41 > pi :: CReal 20:29:42 3.1415926535897932384626433832795028841972 20:29:59 :t showCReal 20:30:00 Int -> CReal -> String 20:30:09 > showCReal 100 pi 20:30:10 "3.141592653589793238462643383279502884197169399375105820974944592307816406... 20:30:48 > showCReal 0 pi 20:30:49 "3" 20:30:56 > showCReal (-1) pi 20:30:57 "*Exception: Negative exponent 20:31:07 i was hoping for an unlimited option 20:31:27 > show CReal 0 pi 20:31:28 Not in scope: data constructor `CReal' 20:31:30 > showCReal 1000000000 pi 20:31:32 > showCReal 0 pi 20:31:33 "3" 20:31:35 mueval: ExitFailure 1 20:31:35 mueval: Prelude.undefined 20:31:45 > showCReal 1000000000 pi 20:31:46 WHICH IS WHICH 20:31:50 mueval: ExitFailure 1 20:31:50 mueval: Prelude.undefined 20:31:55 Okay 20:32:02 showCereal 20:32:47 For just $280000 I'll be able to read a webcomic offline when I'm 20! 20:32:59 :) 20:33:31 a bargain! 20:33:54 these are zimbabwean dollars, right? 20:34:10 Nah, US 20:34:20 I've organized a kickstarter to help me reach it 20:35:01 > toRational (25*0.036) 20:35:03 2026619832316723 % 2251799813685248 20:35:16 http://www.kickstarter.com/projects/14293468/homestuck-adventure-game 20:35:18 There it is 20:35:21 atriq: sounds legit 20:35:29 i mean, before you linked it. 20:35:36 Heh 20:39:55 If you "cast" the end result to Rational, and you don't put :: Double in anywhere or anything similar, will the entire computation be done using rationals? <-- that means no, btw 20:40:29 because toRational takes a Fractional as argument, which _still_ defaults to Double. 20:40:46 oerjan: I wasn't using toRational 20:40:49 I was using :: Rational 20:41:06 "Yo, the output is Rational" 20:41:06 oh it was fizzie who did that. 20:42:05 :t toRational 20:42:06 forall a. (Real a) => a -> Rational 20:42:14 make that Real, not Fractional 20:42:18 :t realToFrac 20:42:19 forall a b. (Real a, Fractional b) => a -> b 20:42:19 :t fromRational 20:42:20 forall a. (Fractional a) => Rational -> a 20:43:45 realToFrac combines both toRational and fromRational 20:44:10 :t fromIntegral 20:44:11 forall a b. (Integral a, Num b) => a -> b 20:45:08 while fromIntegral combines toInteger and fromInteger. so those two are the only ones you need for usual numeric "casts". 20:46:13 > toRational (pi :: CReal) -- hm... 20:46:15 *Exception: CReal.toRational 20:46:23 CHEATING SCUM 20:46:48 what's CReal? 20:47:07 lambdabot's unbounded "real number" type 20:47:10 -!- ion has quit (Ping timeout: 252 seconds). 20:47:17 from some module on hackage 20:47:49 > toRational (0.2 :: CReal) -- hm... 20:47:50 *Exception: CReal.toRational 20:48:04 -!- atriq has quit (Quit: Leaving). 20:51:12 > toRational pi 20:51:13 884279719003555 % 281474976710656 20:52:23 > logBase 2 281474976710656 20:52:24 48.0 20:52:52 it's just converting the binary form of the Double to an exact Rational 20:53:13 > 1e1000000000000000 :: Double -- is this bug still there... 20:53:18 mueval: ExitFailure 1 20:53:18 mueval: Prelude.undefined 20:53:21 -!- ion has joined. 20:53:22 yep it is :P 20:54:07 > 1e1000 20:54:08 Infinity 20:54:15 it crashes instead of producing an Infinity value because it follows the haskell standard precisely and converts to an out-of-memory Rational first :) 20:55:12 > 1e1000 :: Rational 20:55:14 100000000000000000000000000000000000000000000000000000000000000000000000000... 20:57:05 someone recently made a ghc extension so 1e1000 can produce an Integral value 20:57:25 :t 1e1000 20:57:26 forall t. (Fractional t) => t 20:57:36 :t 1e100000000000000000000000 --hm... 20:57:51 thread killed 20:58:06 heh the expansion happens even before type checking 21:01:15 =P 21:01:37 :t 1e100000000000000000000000 --double checking that 21:01:52 thread killed 21:01:57 :t 1e1000 21:02:00 forall t. (Fractional t) => t 21:02:54 Whoa 21:03:55 :t 1e(1e(1e(1e(1e(1e(1e(1e10))))))) 21:03:59 forall t t1 t2 t3 t4 t5 t6 t7. (Num (t -> t1), Num (t2 -> t), Num (t3 -> t2), Num (t4 -> t3), Num (t5 -> t4), Num (t6 -> t5), Num (t7 -> t6), Fractional t7) => t1 21:04:11 :t 1e(1e(1e(1e(1e(1e(1e(1e10)))))))) 21:04:13 parse error on input `)' 21:04:18 > 1e 21:04:19 > 1e(1e(1e(1e(1e(1e(1e(1e10))))))) 21:04:23 mueval-core: Time limit exceeded 21:04:23 mueval-core: Time limit exceeded 21:04:26 > 1e 21:04:30 1 21:04:36 :t 1e 21:04:37 forall t. (Num (Expr -> t)) => t 21:05:13 hmm? 21:05:19 :t 1 e 21:05:28 forall t. (Num (Expr -> t)) => t 21:05:48 it's not actually parsed as one token 21:06:05 but if there's a number after the e it gets parsed as a literal? 21:06:11 :t 1e1 21:06:12 :t 1 e 100 21:06:19 forall t. (Fractional t) => t 21:06:20 forall t t1. (Num (t1 -> t), Num t1) => t 21:08:10 haskell has a general greedy lexing rule, although i think there are corner cases ghc gets "wrong" (that no sane person will use) 21:08:45 :t Just.if True then 1 else 2 21:08:49 parse error on input `then' 21:09:07 > (e) 1 2 21:09:11 mueval-core: Time limit exceeded 21:09:15 i think that should technically notice that if is a keyword 21:09:28 > e 1 2 21:09:30 Couldn't match expected type `t1 -> t2 -> t' 21:09:30 against inferred type ... 21:09:31 -!- augur has joined. 21:10:01 Lambdabot seems to do e differently 21:10:08 yes. 21:10:13 :t e 21:10:15 Expr 21:10:20 > a+b+c+d+e 21:10:23 a + b + c + d + e 21:11:01 it has a primitive symbolic expression type which all letters are defined as 21:11:34 > f+g+h 21:11:37 Ambiguous type variable `a' in the constraints: 21:11:37 `GHC.Num.Num a' 21:11:37 ari... 21:11:46 except those 21:11:51 > f+g+h :: Expr 21:11:53 f + g + h 21:12:09 > (f+g+h) (i+j+k) :: Expr 21:12:11 f (i + j + k) + g (i + j + k) + h (i + j + k) 21:12:17 -!- augur has quit (Remote host closed the connection). 21:12:20 sweet 21:12:50 and it also has its weird numeric instances for functions, which combines nicely with that 21:13:42 but there are so many additions it gets confusing. 21:14:29 > 1e(1e(1e(1e(1e(1e(1e(1e10))))))) 21:14:34 mueval-core: Time limit exceeded 21:14:46 i really don't understand why that times out 21:15:05 > 1e(1) 21:15:11 mueval: ExitFailure 1 21:15:11 mueval: Prelude.undefined 21:16:00 > 1 e 1 21:16:04 mueval-core: Time limit exceeded 21:16:05 ghci fails on anything that doesn't follow the somethingesomething format 21:16:27 -!- carado has quit (Remote host closed the connection). 21:16:30 That is, together, no spaces, and no brackets for the somethings 21:16:54 oh, the somethingsomething format 21:16:59 FreeFull: yes. because it will parse 1e1 as 1 e1 and if you haven't defined e1... 21:17:06 er 21:17:20 i mean 1esomethingnot1 21:17:34 :t 1 e 1 21:17:41 1e gets parsed as a 1 and then an e 21:17:41 forall t t1. (Num (t1 -> t), Num t1) => t 21:18:27 > 1 e 1 :: Integer 21:18:34 mueval: ExitFailure 1 21:18:34 mueval: Prelude.undefined 21:18:43 this is weird 21:18:52 :t \x -> 1 x 21:18:58 > fromIntegral (1 e 1) :: Integer 21:19:02 forall t t1. (Num (t -> t1)) => t -> t1 21:19:03 mueval-core: Time limit exceeded 21:19:20 > 1 2 21:19:24 mueval-core: Time limit exceeded 21:19:38 i think lambdabot may simply be overworked 21:19:47 :t 1 2 :: Integer 21:19:50 Integer 21:19:56 > 1 2 :: Integer 21:19:58 1 21:20:05 > 1 2 21:20:07 1 21:20:13 > fromIntegral (1 e 1) :: Integer 21:20:16 1 21:20:20 let's overwork it again! 21:20:23 > 1e(1e(1e(1e(1e(1e(1e(1e10))))))) :: Integer 21:20:24 1 21:20:27 yay! 21:20:35 > 1e(1e(1e(1e(1e(1e(1e(1e10))))))) 21:20:36 1 21:20:52 > 1 e 1 21:20:54 1 21:20:55 finally it worked 21:21:04 hmm, is 1 e 1 supposed to be 10? 21:21:40 no, 1e1 is 21:21:42 > 1e1 21:21:46 mueval-core: Time limit exceeded 21:21:48 > 1e1 21:21:51 10.0 21:22:10 1e1 was what I was thinking about, I just overspaced it a bit 21:22:58 it's equivalent to fromRationl (10%1) 21:23:03 *fromRational 21:23:36 hmm, because all floating point literals go through fromRational? 21:24:19 yep 21:26:55 > 1e(1e(1e1)) 21:26:59 mueval-core: Time limit exceeded 21:27:06 > 1e(1e1) 21:27:10 mueval-core: Time limit exceeded 21:27:14 > 1e10 21:27:16 1.0e10 21:27:22 Cheat =P 21:27:32 FreeFull: technically that should _never_ evaluate the part in parentheses. lambdabot is just generally overworked. 21:27:39 > 1e undefined 21:27:43 mueval-core: Time limit exceeded 21:27:45 > 1e undefined 21:27:46 -!- Phantom_Hoover has joined. 21:27:47 1 21:28:20 for a function, lambdabot's instances make 1 = const 1 21:28:47 > (1) 1 21:28:49 "pointwise arithmetic", is the term 21:28:49 1 21:29:04 :t e 21:29:06 Expr 21:29:36 > 1 (Just "floccinaucinihilipilification") 21:29:41 mueval-core: Time limit exceeded 21:29:43 > 1 (Just "floccinaucinihilipilification") 21:29:44 1 21:30:51 > fix 1 21:30:56 mueval-core: Time limit exceeded 21:30:57 > fix 1 21:31:01 mueval-core: Time limit exceeded 21:31:02 > fix 1 21:31:04 1 21:31:35 someone swat whoever is giving lambdabot fatigue for me 21:32:10 oerjan: you are responsible for the swattings in here 21:33:52 but they're probably not in this channel! 21:34:08 @channels 21:34:08 Unknown command, try @list 21:34:30 like everything else with lambdabot, there's a command which is impossible to remember the name of 21:35:59 there is more than one... what's the name of the command that starts yhjul? 21:38:42 > 1 1 1 1 1 1 1 21:38:46 1 21:39:12 @yhjul 21:39:12 "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\" 21:39:18 boring 21:39:24 @yh 21:39:24 Just 'J' 21:39:28 the real name is longer 21:39:28 @y 21:39:28 Maybe you meant: yarr yhjulwwiefzojcbxybbruweejw yow . ? @ v 21:39:37 tharr you go 21:39:46 @yhjulwwiefzojcbxybbruweejw 21:39:46 "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\" 21:39:51 aah, hello again old friend 21:39:57 > fix show 21:39:58 "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\... 21:40:14 @c 21:40:14 Maybe you meant: check choice-add choose clear-messages compose . ? @ rc v 21:40:23 @w 21:40:23 Maybe you meant: web1913 what where where+ wiki wn world02 . ? @ v 21:40:31 where lambdabot 21:40:35 @where lambdabot 21:40:35 http://haskell.org/haskellwiki/Lambdabot 21:40:46 @s 21:40:46 Maybe you meant: shootout show slap smack source spell spell-all src . ? @ v 21:40:55 @shootout 21:40:55 @smack oerjan 21:40:55 http://shootout.alioth.debian.org/gp4/benchmark.php?test=all&lang=all 21:40:55 go slap oerjan yourself 21:41:01 @shootout 21:41:01 http://shootout.alioth.debian.org/gp4/benchmark.php?test=all&lang=all 21:41:26 > fix fix 21:41:27 Occurs check: cannot construct the infinite type: a = a -> a 21:41:28 that sounds like something that should just have been in @where 21:41:48 @list shootout 21:41:48 dummy provides: eval choose id read show dummy bug get-shapr faq paste learn map shootout botsnack thanks thx thank you ping wiki oldwiki docs source fptools hackage googleit 21:41:59 @list list 21:42:00 system provides: echo list listchans listmodules listservers uptime 21:42:03 @listchans 21:42:03 ##freebsd ##logic ##math ##proggit ##villagegreen #agda #arch-haskell #codez #darcs #esoteric #fedora-haskell #friendly-coders #functionaljava #gentoo-haskell #gentoo-uy #ghc #happs #haskell # 21:42:04 haskell-blah #haskell-books #haskell-br #haskell-fr #haskell-freebsd #haskell-in-depth #haskell-overflow #haskell-pl #haskell.au #haskell.cz #haskell.de #haskell.dut #haskell.es #haskell.se #haskell. 21:42:04 tw #learnanycomputerlanguage #lesswrong #macosx #macosxdev #rosettacode #scala #scalaz #scannedinavian #snapframework #tanuki #teamunix #unicycling #uscs2010 #xmonad #yi weird# 21:42:14 there it was 21:42:28 That's a lot of chans 21:42:34 yes 21:42:37 @get-shapr 21:42:37 shapr!! 21:42:56 Is the constant e in Haskell? 21:42:57 shapr isn't even online 21:43:02 I hope this command works something like the bat signal 21:43:03 > exp 1 -- sort of 21:43:05 2.718281828459045 21:43:12 -!- kinoSi has quit (Read error: Connection reset by peer). 21:43:39 -!- kinoSi has joined. 21:44:06 Good enough 21:44:11 > exp 1 :: CReal 21:44:13 2.7182818284590452353602874713526624977572 21:44:56 What is CReal in 21:45:12 @hackage numbers 21:45:12 http://hackage.haskell.org/package/numbers 21:45:21 not to be confused with Numbers 21:45:28 which someone added to maximize confusion 21:49:02 hackage is case sensitive? :( 21:49:16 well, package names 21:50:32 numbers sure produces a lot of warnings when installed 21:58:58 is wolfram a unit? 21:59:42 i don't think so, it's another name for the element tungsten 21:59:51 (no.. and it will only be a unit for anything over my dead body) 22:00:08 lol 22:01:05 some say Wolfram is the unit of ego 22:01:09 lol lol 22:01:31 > During the dinner discussion leading up to this definition the foreword to one of the Mathematica books was mentioned, where Stephen Wolfram (in third person) wrote "Stephen Wolfram is the creator of Mathematica and is widely regarded as the most important innovator in scientific and technical computing today." In honour of this self-assessment I suggest we call the unit of ego the Wolfram. 22:01:32 : parse error on input `of' 22:02:15 in theory ego should be measurable right? 22:02:23 it i 22:02:25 *it is 22:02:35 the wolfram is a rigorous system of ego 22:03:12 i guess it needs to be related to other things before it becomes useful 22:03:25 that quote was from the first hit, the second hit was http://www.wolframalpha.com/input/?i=size+of+stephen+wolfram%27s+ego 22:03:38 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 22:05:42 IT DOESN'T ANSWER THE QUESTION. USELESS CRAP. 22:05:47 indeed 22:06:30 it should say 1 Wolfram, but I suppose that kind of self-deprecating humor is incompatible with his ego 22:07:29 do they actually have these things in america http://www.sheldoncomics.com/archive/121002.html 22:07:58 lmao @ "http://www.wolframalpha.com/input/?i=size+of+stephen+wolfram%27s+ego" 22:08:14 that is a funny url 22:09:05 ...i just realized what to call the unit of obviousness, here. 22:09:21 oerjan: what's that? 22:09:33 olsner: it starts with i and ends with s 22:09:50 is it obvious? 22:10:01 no, obvious doesn't start with i. 22:10:08 obviously 22:11:10 i get it :D 22:11:31 i guess it was sort of obvious. 22:12:13 but that starts with s! 22:12:20 i wonder if enough people used that query on wolfram whether it would show up in the wolfram offices 22:13:02 it is conceivable that at least one of the quotes about units of ego have been forwarded 22:13:04 in the wolfram offices, wolfram's ego is the elephant in the room 22:15:09 in the wolfram offices, it takes physical form and walks around in the shape of an elephant 22:15:58 stephen+ego Development of this topic is under investigation... 22:15:59 no 22:16:04 i'm.. not sure what that means 22:16:05 wolfram's ego is the office 22:16:23 if you're working for wolfram, you enter his ego every day from 9 til 5. 22:16:59 it's like that star trek episode where they think there's an entity helping a starbase, but it turns out the entity *is* the starbase 22:17:08 olsner: i think you ruined the joke. :( 22:17:18 maybe 22:17:24 what was the joke? 22:17:42 olsner: which episode was that 22:17:49 barts: the first one 22:17:52 the first tng one? 22:17:52 a pun on "elephant in the room" and the size of wolfram's ego 22:17:54 do i know barts? 22:18:10 no man, they thought the entity was killing the base 22:18:28 but it was helping other entities of its kind which were the base 22:18:34 or something like that 22:18:45 there were two entities 22:18:48 yeah 22:18:52 and also a colony 22:18:57 farpoint? 22:19:01 yea 22:21:12 there are probably other episodes with similar plots as well 22:21:37 also, no one answered my question of whether they really have these crazy things in america http://www.sheldoncomics.com/archive/121002.html 22:22:25 -!- hagb4rd has quit (Ping timeout: 256 seconds). 22:22:25 those 'muricans be crazy 22:22:39 I think they do 22:23:00 we do 22:23:27 they arent that sharp though 22:23:54 americans? 22:26:41 -!- hagb4rd has joined. 22:26:48 money > math 22:26:53 :D 22:27:37 oops.. i almost forgot the link i was reading wasn't posted in here 22:27:55 > "money" > "math" 22:27:56 True 22:28:17 apparently wolfram's new kind of science recommends mathematica.. and someone is annoyed by it 22:28:21 SO IT'S SETTLED 22:29:53 i think.. maybe he should see a psychologist 22:30:36 oerjan: i'm not sure, but i dont think it's illegal to carry these around 22:30:39 http://www.bondorseals.com/more_info/cable_and_hose_bridges/cable_and_hose_bridges.htm 22:32:04 when i was young i had a remote control car with a kind of bridge it could lower under itself 22:32:49 i forget the idea 22:33:00 quintopia: i don't quite see the relevance 22:33:26 oerjan: to place over those traffic bumps from the linked comic 22:33:50 itidus21: ok, but that doesn't in any way detract from the bumps' insanity 22:33:57 I had some of those flipping cars. 22:34:51 There's a spring-loaded lever kind of thing that activates after a bit of travel, and makes the car jump and flip over and sometimes even land the right way up. 22:35:12 Or possibly snap on your fingers when arming, or some other such thing. 22:35:38 i guess the point is americans are so crazy that you have to use these crazy things to prevent them from driving against one-way roads. 22:37:07 -!- copumpkin has joined. 22:37:49 unless the real point is americans are so crazy they _think_ other americans are that crazy. 22:38:06 * oerjan meta-disappears -> 22:38:22 oerjan: Aren't those things parking-lot-entrance related more than just generic one-way-street related? Not that I *know* anything. 22:41:36 oerjan: They installed one of those "giant metal pole rises up from the street" traffic control devices at the ends of a mostly-pedestrian street (vehicles that need access get a remote to lower it, and it auto-lowers if trying to exit the street); a day later it rose up when a taxi was right over it. 22:42:00 I think they said it was some kind of a set-up bug that they fixed. 22:42:08 -!- ion has quit (Ping timeout: 246 seconds). 22:43:51 -!- ion has joined. 22:47:20 i am more interested in the unsolicited humour than reality when i say there is no operation which satisfies x in the equation (> (x wolfram) (in mathematicians_wolfram_admires)) 22:47:52 -!- boily has quit (Quit: Poulet!). 22:48:24 except perhaps x = NOT 22:49:19 -!- jiella has quit (Quit: Leaving.). 22:52:02 itidus21: formulating mathematics in lisp syntax rarely works for humour, especially when it's utterly logically meaningless. 22:53:28 and makes no sense as lisp either 22:55:22 what i tried to say is really in bad taste 22:55:30 so im glad its meaningless 22:56:14 we all know what you meant 22:56:42 you just put some brackets around it, we're not buzzing and giving off smoke 22:56:50 im sorry 22:56:52 i am 22:57:16 -!- augur has joined. 22:57:27 i know it couldn't be more hypocritical, since obviously i needed quite an overinflated ego to say it, and also that i am a god awful mathematician 22:57:43 incidentally i am also an awful integer 22:57:48 no iti 22:57:55 you have the exact opposite of an inflated ego 22:58:17 i try to self deprecate to keep it down 22:58:58 thus achieving an effect about as annoying 23:01:18 yea i probably make it seem uncool to make fun of wolfram 23:02:16 i layed down and thought about it, i guess its just a business thing.. 23:04:47 government:president::employees:employer::animators:director etc 23:11:42 analogies:bullshitter 23:11:53 * oerjan is in _that_ mood today. 23:12:41 the mood where you finally ban iti for fuck's sake 23:12:46 itidus21:full of shit always 23:13:04 i enjoy it tho 23:13:14 let him have #esoteric-iti 23:13:22 i don't understand what *he* gets out of it, but i enjoy it 23:13:29 as it stands he spends too much time dragging down the discussion 23:13:54 it's fun for a while and all but he's still making the channel that much worse by being here and he's clearly never going to change 23:14:30 oh dear, i seem to have triggered Phantom_Hoover into _his_ mood. 23:15:47 -!- monqy has joined. 23:15:55 the self deprecation doesn't help 23:16:06 it's one thing to occasionally overstep your knowledge and admit that you are doing so 23:16:14 oerjan: Wouldja like some popcorn? 23:16:36 -!- Jafet has joined. 23:16:53 it's another thing to say completely wrong worthless things all the time, with the stated knowledge that they are completely wrong 23:16:54 I find that if I'm doing badly at a game, and say how much I suck, I start doing better 23:17:31 that basically amounts to admitting "i like the sound of my own voice and i don't care what you get out of it" 23:18:22 it's not that I don't care 23:18:35 but that sound is so nice and pleasant! 23:25:58 oerjan: if you had the restriction "for all loops, the current cell must be the same at the beginning of every iteration of that loop" to brainfuck, does it change tcness? 23:26:19 you told me it didn't, for 3-cell brainfuck, but do the proofs for the other forms of brainfuck still hold? 23:28:22 Arc_Koen: For bounded-cell-size unbounded-tape brainfuck, it vaguely sounds like that'd limit the amount of accessible memory to something that depends on the amount of >s in the program. 23:28:43 oh, of course 23:30:22 well that's a confirmation that I'm too tired right now 23:30:41 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:31:12 I wanted to prove that pbrain was tc even without the [ ] loops 23:32:11 and assuming the > didn't need to disobey that restriction I could've said it was obvious but I'll guess it'll need a little more work 23:32:28 so have a good night and see you guys 23:36:58 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 23:44:25 -!- itidus21 has left ("Leaving"). 23:45:46 -!- FreeFull has quit (Quit: Sleep). 2012-10-04: 00:26:31 -!- copumpkin has quit (Ping timeout: 260 seconds). 00:27:06 -!- copumpkin has joined. 00:50:26 anyone have a link for watching the US Presidential debate, something i can pass to mplayer rather than using some Flash player? 00:54:55 -!- sivoais has quit (Quit: Lost terminal). 01:22:33 -!- oerjan has quit (Quit: Good night). 02:01:37 -!- DHeadshot has joined. 02:11:17 -!- Jafet has quit (Quit: Leaving.). 02:20:06 -!- Jafet has joined. 02:24:09 -!- sivoais has joined. 02:49:58 that was a boring debate 03:11:04 Damned fat overlords 03:11:12 @let rc=let z n=replicate n(replicate 24 '0')in(fst.head.readHex)<$>transpose("008800880000088888088808":z 7++"000808800088800000088088":z 3++"088880880080808880808808":z 1++["088080808800888008008800","12a0b119a89abb9320aa1018"]);rot=[[0,36,3,41,18],[1,44,10,45,2],[62,6,43,15,61],[28,55,25,21,56],[27,20,39,8,14]] 03:11:13 Defined. 03:11:58 @let kr::[[Word64]]->[[Word64]];kr a=foldl r a rc where r a rc=let c=foldr1 xor<$>a;d=zipWith xor(last c:c)$(`rotateL` 1)<$>tail c++[head c];a'=zipWith(map.xor)d a;b'=zipWith(zipWith rotateL)a' rot;b=[[b'!!(3*(y-3*x)`mod`5)!!x|y<-[0..4]]|x<-[0..4]];a''=zipWith3(zipWith3(\x y z->xor x(complement y.&.z)))b(tail b++b)(drop 2 b++b)in(xor(a''!!0!!0)rc:tail(a''!!0)):tail a'' 03:12:00 Defined. 03:12:20 > map(map(`showHex`"")) $ k $ replicate 5 (replicate 5 0) 03:12:21 Couldn't match expected type `a -> b' 03:12:22 against inferred type `Simple... 03:12:27 > map(map(`showHex`"")) $ kr $ replicate 5 (replicate 5 0) 03:12:29 [["f1258f7940e1dde7","ff97a42d7f8e6fd4","eb5aa93f2317d635","5e5635a21d9ae61... 03:43:19 -!- Jafet has quit (Quit: Leaving.). 04:05:18 -!- mig22 has joined. 05:20:29 -!- Tod-Autojoined has joined. 05:20:43 -!- TodPunk has quit (Read error: Connection reset by peer). 05:25:00 -!- Jafet has joined. 07:26:23 -!- epicmonkey has joined. 07:40:45 -!- ais523 has quit. 08:37:26 -!- mig22 has quit (Quit: mig22). 09:01:49 -!- ais523 has joined. 09:07:00 -!- mig22 has joined. 09:19:34 http://bash.org/?953518 09:26:21 hmm, based on what I saw on reddit, I think we have a new lesser-known programming language: http://www.floopsy.com/post/32660494624/programming-language-objective-corporatespeak 09:26:25 or at least, something in the same mold 09:26:57 ion: that's got to be fake, right? 09:27:00 as in, someone lying on IRC 09:27:03 (which happens all the time) 09:27:09 There's LYING on IRC?! 09:27:27 It was on the Internet, it must be true. 09:27:41 ion: because if someone were wrong on the internet, they would have been corrected? 09:27:44 It reminds me of the "im gunan hack a street light" story. 09:27:53 fizzie: ? 09:28:02 ais523: http://www.nndb.com/people/523/000095238/ 09:28:02 why does it have to be fake 09:28:21 people have explosives 09:28:31 too contrived, really 09:28:47 and it seems unlikely someone would keep armed landmines in their shed 09:28:54 where would you keep them? 09:28:58 in your house? 09:29:01 I'd keep them unarmed 09:29:05 if I kept them at all 09:29:35 oh i assumed they weren't armed and exploded for some other reason 09:30:57 things tend to not really spontaneously explode 09:31:00 if they were actually in their explosionous state for fun then i guess i agree that it has to be fake 09:31:04 admittedly, landmines might be an exception 09:31:38 well i don't know how hard it is to accidentally blow up a landmine 09:31:51 i suppose it's as hard as they could make it be minus 5 09:32:05 if a landmine blows up accidentally, it's not really doing its job 09:32:22 apparently in the world wars, people used to simply dismantle anti-tank landmines by hand 09:32:29 because they were designed to blow up against tanks, not people 09:32:38 the minus five is because they do explode if you accidentally activate them. 09:33:50 in general people like to avoid arming explosives until they're in a situation where you wouldn't mind them exploding 09:34:29 but you could still do it by accident 09:34:45 bloop 09:34:47 bloop 09:34:54 bloop 09:34:57 bloop 09:35:00 bloop 09:35:01 bloop 09:35:02 bloop 09:35:02 bloop 09:35:03 bloop 09:35:05 yay 09:35:15 [12:34:56] bloop 09:35:47 ais523: Speaking of landmines, Finland signed the Ottawa Treaty pretty recently; it took effect in July this year. (There's long been debate about it; after all, "everyone else" signed it in like 1997.) 09:37:09 Well, except for some relatively unknown places like, let's see, USA or Russia. 09:37:49 http://en.wikipedia.org/wiki/List_of_parties_to_the_Ottawa_Treaty -- we're second-latest, apparently. 09:38:40 fizzie: sorry to embarrass you but those are in fact rather big and known places. 09:38:49 please read a newspaper and not an oldspaper. 09:39:19 oklopol: Well, uh, is this "China" thing one too, then? 09:41:43 -!- ais523 has quit (Read error: Connection reset by peer). 09:42:00 -!- ais523 has joined. 09:44:50 -!- hagb4rd has quit (Ping timeout: 244 seconds). 09:58:37 -!- monqy has quit (Quit: hello). 10:02:57 -!- Arc_Koen has joined. 10:04:07 -!- ais523_ has joined. 10:04:36 -!- ais523 has quit (Read error: Connection reset by peer). 10:05:39 hello 10:28:50 -!- ais523_ has quit (Read error: Connection reset by peer). 10:29:01 -!- ais523_ has joined. 10:45:28 -!- ais523_ has quit (Read error: Connection reset by peer). 10:45:37 -!- ais523_ has joined. 11:08:47 -!- barts_ has joined. 11:11:38 -!- barts has quit (Ping timeout: 244 seconds). 11:24:32 -!- impomatic has joined. 11:29:29 -!- carado has joined. 11:31:47 -!- ogrom has joined. 11:36:34 doesn't mediawiki have an easy way to display the intersection of two categories? 11:53:02 -!- impomatic has left. 11:53:02 -!- DHeadshot has quit (Read error: Connection reset by peer). 11:53:55 -!- ais523_ has quit (Ping timeout: 260 seconds). 11:57:41 -!- ogrom has quit (Quit: begone). 11:58:35 -!- copumpkin has quit (Ping timeout: 260 seconds). 11:59:10 -!- copumpkin has joined. 12:24:55 -!- augur has quit (Remote host closed the connection). 12:26:39 -!- MoALTz has joined. 12:28:15 -!- ais523_ has joined. 12:28:40 -!- ais523_ has changed nick to ais523. 12:31:36 -!- Phantom_Hoover has joined. 12:36:50 -!- DHeadshot has joined. 12:37:13 -!- ais523 has quit (Ping timeout: 246 seconds). 12:37:16 -!- ais523_ has joined. 12:37:27 -!- ais523_ has changed nick to ais523. 12:38:00 -!- boily has joined. 12:44:29 -!- ogrom has joined. 12:51:52 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 12:53:54 -!- augur has joined. 12:58:59 -!- Phantom_Hoover has joined. 13:03:02 Hmm, on the one hand, Onion Radio has a funny headline for something, on the other hand, it's Onion Radio which consistently sucks 13:09:29 I think the voice just grates on me 13:09:58 -!- Indecipherable has joined. 13:15:33 -!- Indecipherable has quit (Quit: used jmIrc). 13:21:49 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:27:48 -!- carado has quit (Remote host closed the connection). 13:29:54 olsner: well Im think I'm done with the bf interpreter 13:30:42 (actually I realized the way I was doing was probably not the best; I was storing the brainfuck code around the current cell, which made it quite boring to implement > and < 13:30:55 so I started all over, storing the brainfuck code around the whole tape 13:31:07 and I'm done! except for . and , which are currently no-ops 13:35:34 If you're interested, the code is there: http://sprunge.us/gddK note that I haven't tested it yet, I'll write a thue interpreter in C with the optimization of keeping the substitution rules in a list, always putting the last used rule on top, and always trying rules in the order they are listed (that should make the brainfuck interpreter much faster as every operation uses only a few rules, for instance you don't need to try al 13:35:35 "move to next cell" related rules when you're in the middle of incrementing the current cell) 13:36:51 and I apologize about not writing comments in it; I guess once I have tested it I'll add a "readme" or something 13:41:24 -!- Frooxius has joined. 13:41:35 -!- copumpkin has joined. 13:43:54 -!- kinoSi has quit (Read error: Connection reset by peer). 13:44:21 -!- kinoSi has joined. 13:49:50 -!- Tod-Autojoined has quit (Read error: Connection reset by peer). 13:54:51 -!- mig22 has quit (Quit: mig22). 13:57:08 -!- TodPunk has joined. 14:36:07 -!- boily has quit (Ping timeout: 240 seconds). 14:40:00 -!- boily has joined. 15:00:51 -!- Arc_Koen has quit (Quit: Arc_Koen). 15:07:39 -!- atriq has joined. 15:08:07 @messages? 15:08:08 Sorry, no messages today. 15:08:52 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 15:09:07 -!- Phantom_Hoover has joined. 15:21:46 -!- ogrom has quit (Quit: Left). 15:44:07 I need to quickly make Data.FamilyTree awesome 15:52:03 -!- ais523 has quit. 15:59:32 -!- atriq has quit (Remote host closed the connection). 15:59:36 -!- oerjan has joined. 16:00:05 R.I.P. my favorite café/restaurant :( 16:01:24 -!- atriq has joined. 16:06:40 Time to learn GEDCOM 6! 16:07:38 @tell doesn't mediawiki have an easy way to display the intersection of two categories?<-- hm i think i may have wanted that yesterday when failing to find out if a kind of brainfuck derivative existed. or maybe not, not sure what the other category should have been. 16:07:39 Consider it noted. 16:09:04 i think i'd really have wanted a list of summaries for everything in the category. 16:09:24 -!- Slereah has quit (Ping timeout: 260 seconds). 16:12:48 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 16:16:08 -!- atriq has quit (Remote host closed the connection). 16:22:43 -!- atriq has joined. 16:23:08 -!- Slereah has joined. 16:37:44 -!- ogrom has joined. 16:42:12 > 2 * 3 * 47 * 61 * 67 * 103 16:42:13 118711002 16:43:38 > nubBy (((>1).).gcd)[2..] 16:43:41 [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... 16:45:05 > drop 10 $ nubBy (((>1).).gcd)[2..] 16:45:08 [31,37,41,43,47,53,59,61,67,71,73,79,83,89,97,101,103,107,109,113,127,131,1... 16:47:33 -!- FreeFull has joined. 16:50:27 * oerjan leaves this to Arc_Koen. 16:54:56 -!- Vorpal has joined. 16:57:36 -!- elliott has joined. 16:57:42 fizzie: You know that P.E.R.L. language, right? 16:59:34 That's not helpful. 17:04:51 what did fizzie do now 17:11:00 -!- Phantom_Hoover has joined. 17:11:25 Python is so simple, someone who doesn't know the language can help someone who knows more about it than they do 17:13:26 FreeFull: i think i did that with ruby once 17:16:00 but aren't most modern imperative languages like that, anyhow. 17:21:24 it depends on whether it was a Python question or a programming question where you happen to be using Python 17:21:45 Python, Ruby, Lua, Javascript all have quirks which won't be obvious to outsiders 17:22:01 i find this disturbingly nonrecursive http://www.mezzacotta.net/garfield/?comic=1234 17:22:35 "So there's an infinite number of parallel universes, eh?" "Nope, just the two!" 17:22:53 * oerjan recalls that's a futurama quote 17:23:59 right you are 17:25:02 obviously the other parallel universe has another parallel universe 17:25:41 apparently the only person who has ever quoted that on the internet is kmc 17:25:53 20:20:47 "so there's an infinite number of parallel universes, eh?" 17:25:53 20:20:50 "nope, just the two" 17:26:16 he was making references before it was cool 17:26:51 well maybe i misremember the quote 17:27:01 elliott: given that i have never seen the actual episode afaik, i find that unlikely. 17:27:17 https://www.google.co.uk/search?q=%22So+there's+an+infinite+number+of+parallel+universes%2C+eh%3F%22+%22Nope%2C+just+the+two!%22 17:27:38 oerjan: maybe you first saw it in that #haskell log 17:27:44 -!- carado has joined. 17:27:46 maybe kmc is hallucinating an episode of futurama that never happened 17:27:47 poyhaps 17:27:54 maybe we 17:27:57 are the futurama episode??? 17:28:03 well i _may_ have read the wikipedia plot outline :P 17:28:04 whoa man 17:28:11 "Woah, it's like that drug trip I saw in that movie I watched on that drug trip!" 17:28:12 oerjan: http://esolangs.org/w/index.php?title=Befunge&curid=1005&diff=34105&oldid=32786 17:28:19 oerjan: hey can you give me a reason not to revert this edit 17:28:23 it's like when i was little and was afraid i lived in a film 17:28:34 elliott: that i already did so 17:28:56 oerjan: woah u r pro 17:29:11 oerjan: i should just give the root password to you and resign 17:29:29 although if it had properly halted on EOF, i probably wouldn't have 17:29:46 it's sort of ugly 17:30:02 not very DRY, is it 17:30:16 is there a joke 17:30:31 oh i guess it does literally repeat itself 17:33:14 -!- elliott has changed nick to Wensle. 17:33:20 -!- Wensle has changed nick to elliott. 17:33:51 your secret identity has been revealed! 17:34:00 so secret we've never heard of it 17:34:13 yes, that is definitely why I changed my nick 17:34:32 i knew! 17:35:02 i think they should breed a more silent dog. 17:35:19 it's called a dead dog, oerjan 17:35:20 and then neuter the rest. 17:35:26 they're really bad at learning new tricks 17:35:33 no no, it's called a good dog! 17:35:55 it's called a dog with no mouth 17:36:17 i have no mouth but i must bark 17:36:32 aka a tree 17:37:23 *and 17:38:20 what 17:38:23 what is the nad 17:38:24 and 17:38:42 The but, I'd presume 17:39:23 good presumption 17:39:25 all this talk of butts and 'nads 17:39:35 i wasn't going to touch that 18:17:43 I made a hexaflexagon today 18:17:51 And let someone play with it. 18:17:59 She almost destroyed time and space. 18:18:35 I just want to know how she made it a pentagon. 18:20:09 nice, slicehost just gave me $10 18:20:14 by slicehost I mean rackspace 18:26:30 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 18:26:53 hi elliott 18:27:00 Why are you using slicespace now? 18:27:41 why do you think I am 18:28:00 For sweet, sweet vengeance? 18:28:18 swengeance 18:32:08 -!- epicmonkey has quit (Ping timeout: 246 seconds). 18:45:52 -!- ogrom has quit (Quit: Left). 19:12:13 -!- Phantom_Hoover has joined. 19:14:18 I have a vague memory, possibly of a dream, involving GHC's internal definition of IO 19:14:30 yikes 19:14:34 @src IO 19:14:35 Source not found. That's something I cannot allow to happen. 19:14:37 It was something like # State # -> (Effect, # State 19:14:38 #) 19:14:46 it used to be in lambdabot 19:15:29 newtype IO a = IO (State# RealWorld -> (# State# RealWorld, a #)) 19:15:44 I was... 19:15:46 Closish 19:16:06 Where did I see that? 19:16:27 http://www.haskell.org/ghc/docs/latest/html/libraries/ghc-prim-0.3.0.0/src/GHC-Types.html#IO 19:16:41 why is it State# RealWorld instead of just RealWorld or RealWorld#? 19:16:50 Oh, okay 19:17:12 because ST s uses State# s 19:17:16 To keep state threads, separately 19:17:29 (ST s) and IO have identical runtime representations and this is useful in various ways 19:17:43 the type parameter to State# is a phantom type; (State# x) and (State# y) have the same representation 19:18:06 aah, right 19:18:09 anway I guess you could push the phantom out to ST itself but you would get marginally less checking in the library internals 19:18:50 People were talking about using the fancy new DataKinds with ST to restrict the parameter to the State# 19:39:29 Oh god 19:39:43 I've got into an argument about which is better, IWC or xkcd 19:40:07 the first thing that comes to mind is 'when?' 19:40:26 In total 19:40:29 Overall 19:40:39 (I'm firmly on the side of IWC) 19:41:30 iwc then, the rot's been in xkcd for about half its run even by conservative estimates 19:42:40 what's iwc 19:46:07 `? iwc 19:46:17 iwc? ¯\(°_o)/¯ 19:46:26 i-something web comic? 19:46:33 irregular 19:46:35 `learn iwc contains puns! Puns galore! Puns after puns after puns! Also science! 19:46:38 I knew that. 19:46:48 a legacy name considering it ran like clockwork for a decade 19:47:00 It was the first webcomic I ever read 19:47:13 Without it, I probably wouldn't be in this channel 19:47:22 I probably wouldn't be in this community! 19:47:39 The Hexham Coincidence wouldn't exist! 19:48:41 also: it's made with lego 19:49:17 kmc: iwc is intermezzo war crime 19:49:17 oh that thing 19:49:25 that would be a good name for a band 19:49:34 No it wouldn't 19:49:42 It'd be an alright name for an album 19:51:50 i think kmc is right and atriq is wrong 19:51:54 who wants to join intermezzo war crime 19:51:57 so far it is me and kmc 19:52:01 we play warcrimecore 19:52:13 it is like polka except you commit war crimes at the same time 19:52:41 i'll join 19:52:46 what kind of war crimes are we talking 19:53:06 we could start out with an EP where we waterboard someone on every song and then go up from there to global thermonuclear war 19:54:26 elliott: I'd join if there were no drums or guitars. 19:54:31 our war crime is that we misappropriate the logo of the international committee of the red cross 19:54:58 shachaf: does polka have drums and guitars 19:55:00 i honestly have no idea 19:55:04 I don't know. 19:55:10 I think it's mostly accordion 19:55:27 kmc: that is a bit far for me 19:55:30 kmc: have you no limits 19:55:32 OK, as long as it's a chromatic button accordion. 19:55:44 kmc: that would be post-warcrimecore territory 19:56:01 It can be Russian or French. 19:56:32 elliott, idk, the red cross are dicks 19:57:50 Okay, it's emerged that both me and the person I was talking to 19:57:57 ENJOY BOTH WEBCOMICS IN QUESTION 19:58:07 :O 20:02:09 http://xkcd.com/1114/ this one is funny 20:02:15 mostly for the title text 20:02:40 I thought you hated xkcd 20:03:25 that one is pretty lame 20:03:26 elliott hates everything. 20:04:10 people don't generally agree on which ones are good 20:04:13 kmc: OTOH you're pretty lame 20:04:17 so it evens out 20:04:20 snap 20:07:50 `quote pun 20:07:53 173) [spam] Any flavored hell can pee on the pig pen, but it takes a real football team to throw a slyly optimal formless void at a hole puncher. \ 442) Look, I often walk my dog through a field with cows in it. And I punched myself in the face once. \ 585) But whereas the Zune UI makes one think "I want to kill myself", the Windows CE UI makes one think "I want to kill myself, but first kill my parents 20:07:59 @quote pun 20:08:00 monochrom says: Welcome to #haskell, where your questions are answered in contrapuntal fugues. 20:08:07 @quote \bpun\b 20:08:08 kmc says: Right, for example Either (pun not intended) 20:08:16 @quote \bpun 20:08:16 poetix says: < poetix_>: In ancient Athens, they used to punish adulterers by forcing radishes up their rectums < boegel>: poetix_: sounds like fun ! 20:08:27 @quote \bpuns?\b 20:08:27 monochrom says: Co dawg, we heard you like records so we put record puns so you can omit field names while you name fields. 20:08:34 @quote \bpuns?\b 20:08:34 olsner says: pun indented 20:08:38 @quote \bpuns?\b 20:08:38 monochrom says: Co dawg, we heard you like records so we put record puns so you can omit field names while you name fields. 20:09:07 Need more puns. 20:10:48 `quote pun 20:10:51 173) [spam] Any flavored hell can pee on the pig pen, but it takes a real football team to throw a slyly optimal formless void at a hole puncher. \ 442) Look, I often walk my dog through a field with cows in it. And I punched myself in the face once. \ 585) But whereas the Zune UI makes one think "I want to kill myself", the Windows CE UI makes one think "I want to kill myself, but first kill my parents 20:15:23 -!- glogbackup has joined. 20:31:16 -!- Vorpal has quit (Ping timeout: 246 seconds). 20:35:06 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 20:37:07 -!- Phantom_Hoover has joined. 20:39:48 t 20:39:49 y 20:40:15 hey oklopol 20:40:37 i started doing maths at uni does it start being interesting at some point 20:41:10 depends on your university i guess 20:41:31 also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:41:46 what have you taken sofar 20:42:02 or what are you taking i guess you haven't finished anything 20:44:07 i've had like 1 lecture in analysis, 2 in differential equations, 2 in geometry and 2 in 'foundations' which is like first principles 20:44:47 the first geometry one was the closest to being interesting iirc 20:45:47 At least here I think it goes approximatly so that it starts being interesting when it stops being part of the basic math courses for all kinds of folks and starts being courses with actual names. 20:46:07 Possibly. I didn't do it (much). 20:46:40 analysis is kinda bleh 20:46:47 differential equations are kinda bleh 20:46:49 unfortunately i have to share all of those except probably foundations and analysis 20:46:56 i had to sit on the stairs for geometry 20:46:57 geometry is somewhat bleh 20:47:08 foundations sounds great 20:47:12 i'm sure it's bleh 20:47:28 `addquote t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:47:32 867) t y also i didn't say t \ y on purpose, i just accidentally hit the keyboard with my head 20:47:54 hm... 20:47:55 it was kind of interesting too but too much time was spent going over easy stuff like doing euclid's proof rigorously 20:48:06 `quote [ ]< 20:48:09 1) I used computational linguistics to kill her. \ 2) EgoBot just opened a chat session with me to say "bork bork bork" \ 3) Hmmm... My fingers and tongue seem to be as quick as ever, but my lips have definitely weakened... More practice is in order. \ 4) that's where I got it rocket launch facility gift shop \ 5) GKennethR: he should be told 20:48:34 also one of you fuckers infected me with constructivism, now i have an inner voice screaming whenever contradiction is used 20:48:44 `delquote 867 20:48:44 -!- augur has quit (Remote host closed the connection). 20:48:48 ​*poof* t y also i didn't say t \ y on purpose, i just accidentally hit the keyboard with my head 20:48:56 `addquote t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:49:00 867) t y also i didn't say t \ y on purpose, i just accidentally hit the keyboard with my head 20:49:18 `revert 20:49:21 Done. 20:49:24 wait... 20:49:27 constructivism lol 20:49:35 `addquote t y also i didn't say t\\ny on purpose, i just accidentally hit the keyboard with my head 20:49:38 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:49:42 nice addquote bug 20:49:43 it actually turned \n into a newline 20:49:51 We have a thing where there's this set of courses "Math X1" .. "Math Xn" where X is like C for CS people and L for physics/etc. people and so on (there's maybe six different letters?) and 'n' depends on the letter but is usually about 2-4, and those are mandatory parts, and nobody I know of has accused them of being especially interesting. 20:50:48 elliott: actually that has to be in `quote not `addquote... 20:50:53 `quote 867 20:50:56 867) t y also i didn't say t\\ny on purpose, i just accidentally hit the keyboard with my head 20:51:19 oh dear 20:51:22 `revert 20:51:25 Done. 20:51:29 could you please redo that a couple more... oh 20:51:35 `addquote t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:51:38 867) t y also i didn't say t \ y on purpose, i just accidentally hit the keyboard with my head 20:51:39 thanks i guess. 20:51:40 `quote 867 20:51:44 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:52:01 `quote 867 20:52:02 `quote 867 20:52:03 `quote 867 20:52:04 `quote 867 20:52:05 it gives the right `quote, but some other commands are buggy in printing it 20:52:07 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:52:15 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:52:36 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:52:36 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:52:54 oh also at one point a guy felt it necessary to ask the lecturer why he'd switched from double-striking the middle stroke of N rather than the left one 20:53:08 when did i first come here? 20:53:20 lol 20:54:01 `quote accidentally 20:54:04 170) elliott: it's hard to debug havoc on your mirror if you accidentally hit r, then a character could be multiple words long, depending on the task. \ 295) BYE dbc WE'LL BE SURE TO ACCIDENTALLY MENTION YOUR NICK OFTEN \ 761) oops I accidentally deleted the universe looks weird when you put a verb after accidentally like that \ 867) t y also i didn't 20:54:06 who are Aftran, Slereah, Quas_NaAart, AnMaster and Warrigal? 20:54:13 `quote accidentally hit 20:54:16 170) elliott: it's hard to debug havoc on your mirror if you accidentally hit r, then a character could be multiple words long, depending on the task. \ 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 20:54:21 anmaster is now vorpal 20:54:23 ok 20:54:34 Warrigal is now tswett 20:54:35 although vorpal is now thankfully fairly inactive 20:54:45 slereah is still slereah 20:54:52 that I see. 20:55:24 Phantom_Hoover: We had a lecturer whose blackboard variables initially had superscript indices, at the end had subscript indices, and in-between had kind of midscript indices. (I may have mentioned this before.) 20:55:58 you do have had to done that. 20:56:00 I don't think anyone really commented, though. 20:56:08 i think i was like :DDDDD 20:56:18 but that's like my version of whatever dude 20:56:22 Except maybe to clarify that the meaning didn't change. 20:56:29 oh 20:56:45 i thought you meant like you have the right to say it again because we didn't laugh the first time 20:57:18 err or wait i have no idea what you're talking about 20:57:19 Oh, no; I mean, at that time, when it happened, for reals. 20:58:10 As opposed to Phantom_Hoover's friend who is interested in the details of the art of doublestriking. 20:58:15 -!- boily has quit (Quit: Poulet!). 20:58:48 `cat bin/addquote 20:58:51 ​#!/bin/sh \ [ "$1" ] || exit 1 \ printf "%s\n" "$1" >>quotes \ echo $(qc | cut -d' ' -f1)") $1" 20:59:50 `which qc 20:59:54 ​/hackenv/bin/qc 21:00:27 do you have questions about the quote system 21:00:50 yes, why do `addquote and `delquote print \n as newline 21:00:56 in the quote 21:01:54 no fucking clue 21:01:58 does it happen on just addquote or on quote too 21:02:04 not on quote 21:02:51 oerjan: so if you do addquote foo\nbar 21:02:54 and then quote 21:02:56 it shows right? 21:02:57 demonstrate pls 21:02:59 yes 21:03:04 `quote 867 21:03:08 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 21:03:13 LIKE THAT 21:04:07 `cat bin/quote 21:04:10 ​#!/bin/sh \ allquotes | if [ "$1" ]; then \ if expr "$1" + 0 >/dev/null 2>&1; then \ sed "$1q;d" \ else \ grep -P -i -- "$1" \ fi \ else shuf -n 1; fi 21:04:27 `run echo 'echo "$1"' >bin/fuck 21:04:30 No output. 21:04:31 `fuck you\ntoo 21:04:34 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: fuck: not found 21:04:35 i am guessing echo is doing it wrong 21:04:37 ugh 21:04:43 `run echo "#!/bin/sh" >bin/fuck 21:04:46 No output. 21:04:47 `run echo 'echo "$1"' >>bin/fuck 21:04:49 No output. 21:04:57 `fuck you\ntoo 21:05:01 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/fuck: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/fuck: cannot execute: Permission denied 21:05:06 oerjan: fuck you 21:05:09 `run chmod +x bin/fuck 21:05:12 No output. 21:05:13 `fuck you\ntoo 21:05:13 yw 21:05:16 oerjan: when does \n get printed as a newline? 21:05:35 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/fuck: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/fuck: cannot execute: Permission denied 21:05:36 olsner: by the `addquote itself, and by `delquote 21:05:43 holy shit 21:05:44 `fuck you\ntoo 21:05:47 you \ too 21:05:59 oerjan: does it get showed as foo \ bar 21:06:00 or foo\bar 21:06:01 `echo you\ntoo 21:06:04 you\ntoo 21:06:10 it's sh 21:06:12 i am in control 21:06:15 foo \ bar 21:06:16 `run fuck 'foo\nbar' 21:06:19 foo \ bar 21:06:27 ok 21:06:33 `cat bin/delquote 21:06:35 ​#!/bin/sh \ id=$1 \ expr "$1" + 0 >/dev/null 2>&1 || exit 1 \ head -n $((id-1)) quotes >quotes.new \ tail -n +$((id+1)) quotes >>quotes.new \ diff quotes quotes.new >/dev/null && exit 1 \ echo "*poof*$(quote $id | cut -d')' -f2-)" \ mv quotes.new quotes \ 21:06:44 echo there too 21:06:47 oerjan: the problem is "$1". i don't know how to fix that. 21:06:48 it's not ecoh 21:06:50 it's not echo 21:06:51 it's sh 21:06:58 elliott: but it works with the printf in `addquote 21:06:59 change fuck to printf %s and you'll see 21:07:09 `cat bin/fuck 21:07:12 ​#!/bin/sh \ echo "$1" 21:07:15 `run echo '#!/bin/sh' >bin/fuck 21:07:18 No output. 21:07:23 `run echo 'printf "%s" "$1"' >>bin/fuck 21:07:25 No output. 21:07:26 `run chmod +x bin/fuck 21:07:30 No output. 21:07:31 `fuck everything\nok 21:07:34 everything\nok 21:07:59 ugh 21:08:00 what 21:08:02 You really showed him there! 21:08:02 ok fine 21:08:14 oerjan: i will tell you how to fix add & delquote but you have to do it because i am not using sed any more 21:08:23 change 21:08:23 echo $(qc | cut -d' ' -f1)") $1" 21:08:24 to 21:08:34 printf "%d) %s" $(qc | cut -d' ' -f1) "$1" 21:08:35 what, what did sed do to you? 21:08:37 and change 21:08:45 echo "*poof*$(quote $id | cut -d')' -f2-)" 21:08:46 to 21:08:54 seems unfair to suddently just "not use sed any more" 21:08:56 printf "*poof*%s" "$(quote $id | cut -d')' -f2-)" 21:10:57 as if i remember how to do literal substitutions in sed 21:12:06 `run sh -c "echo 'also\na'; /bin/echo 'silly\noption'" 21:12:10 also \ a \ silly\noption 21:14:20 -!- atriq has quit (Quit: Leaving). 21:15:47 oerjan: just get the files from `url 21:15:52 and then use `fetch/`run mv 21:15:55 on a modified version 21:16:15 I can break them with sed, I really can. 21:17:24 `cat bin/addquote 21:17:27 ​#!/bin/sh \ [ "$1" ] || exit 1 \ printf "%s\n" "$1" >>quotes \ echo $(qc | cut -d' ' -f1)") $1" 21:20:07 fizzie: feel free to fix it also 21:20:37 `run sed -i '4s/.*/printf "%d) %s" $(qc | cut -d' ' -f1) "$1"/' /bin/addquote 21:20:41 sed: -e expression #1, char 35: unterminated `s' command 21:20:47 oops 21:20:49 `run cp bin/addquote bin/addquote_; sed -ie 's/echo/printf "%d) %s"/;s/") / "/' bin/addquote; cat bin/addquote 21:20:52 ​#!/bin/sh \ [ "$1" ] || exit 1 \ printf "%s\n" "$1" >>quotes \ printf "%d) %s" $(qc | cut -d' ' -f1) "$1" 21:21:00 Does that look okkay? 21:21:30 I think it at least looks as prescribed. 21:21:33 `run rm bin/addquote_ 21:21:36 No output. 21:22:19 Backups are so like one of those circus guys walking on a wire except with a safety rope. 21:22:20 oh whatev 21:22:36 -!- monqy has joined. 21:22:39 `addquote Backups are so like one of those circus guys walking on a wire except with a safety rope. 21:22:42 868) Backups are so like one of those circus guys walking on a wire except with a safety rope. 21:23:58 also `delquote 21:24:25 `addquote `delquote 869 21:24:28 869) `delquote 869 21:25:00 Quotes should get an identifier based on a cryptographic hash of their contents. 21:26:01 `addquote test\nho 21:26:05 870) test\nho 21:26:10 monqy: hello 21:26:11 `delquote 870 21:26:14 at least one quote before 869 is about to be deleted, changing the number of that quote and ruining the joke 21:26:15 ​*poof* test \ ho 21:26:23 `run sed -ie 's/echo "\*poof\*/printf "*poof*%s" "/' bin/delquote 21:26:26 No output. 21:26:32 `addquote test\nho 21:26:36 870) test\nho 21:26:37 See, no hands, I mean backups. 21:26:40 `delquote 870 21:26:41 elliott: hello 21:26:44 ​*poof* test\nho 21:26:50 YAY 21:26:58 oerjan: Quotes are serious business. 21:27:45 elliott: helo 21:28:39 OF COURSE 21:28:49 monqy: you cheated tho 21:29:05 thread killed tho 21:29:38 sounds like that character in doctor who 21:33:01 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 21:40:24 doctor tho 21:44:14 -!- Frooxius has quit (Ping timeout: 260 seconds). 22:00:27 -!- copumpkin has joined. 22:10:39 desmond:/scratch/users/htkallas 14T 14T 0 100% /fs/scratch/users/htkallas 22:10:46 Well, that's not good. 22:11:13 Especially the parts of there being 0 bytes free and 100% of usage. 22:11:49 -!- carado has quit (Quit: Leaving). 22:12:03 It's the "work" directory, I'm sort of guessing someone had a runaway script. 22:14:50 (Perhaps I should check that someone != self.) 22:21:19 Huh, 51G in /work. Time to clean up, perhaps, but not a giant chunk of 14T. 22:25:16 -!- augur has joined. 22:26:39 dammit, warwick's nick cage appreciation society are slippery customers 22:33:39 Phantom_Hoover: you have to get them while you think they're taking a break 22:34:11 i'm not sure where they meet, what they do or indeed who any of them are 22:34:21 the student union website is infuriatingly uninformative 22:34:31 maybe i can find the president and grill him for information 22:34:41 -!- augur has quit (Read error: Connection reset by peer). 22:34:50 maybe they meet by _not_ meeting 22:35:42 -!- augur has joined. 23:09:28 shachaf: http://www.reddit.com/r/haskell/comments/10ynff/regarding_top_and_bottom_in_haskells_type_system/ 23:09:38 shachaf: this was a great post when i just read it but then it got even better when i saw who wrote it 23:10:42 oerjan: oh hey you are maybe the reason I saw http://www.msr-inria.inria.fr/events-news/feit-thompson-proved-in-coq 23:10:56 might well be 23:11:05 my only reddit post so far 23:11:38 although i heard of it in here 23:11:43 the classification of simple groups is the coolest proof 23:12:13 elliott: How did I know? 23:12:54 elliott, it's not a single proof... 23:13:14 elliott: You should post talking about (forall a. a) and (exists a. a) 23:13:18 Phantom_Hoover: what is your definition of a "proof"? 23:13:32 wikipedia agrees with me: "The proof of the theorem consists of tens of thousands of pages in several hundred journal articles written by about 100 authors, published mostly between 1955 and 2004." 23:14:11 well ok, but that's a pretty broad use of 'proof' 23:14:27 elliott: Too late, cmccann posted. 23:14:46 also that seems to be one tiny subsection of the entire classification? 23:15:10 Phantom_Hoover: what would you call the proof of the theorem, then? 23:15:59 can we stop this quibble, i should never have mentioned t 23:16:01 *it 23:16:03 oerjan: "Hm is it automatically true that whenever MT is a monad transformer, there exists a function of type (Monad m) => MT Identity a -> MT m a ?" 23:16:17 oerjan: it "should" be true, but it's not in MonadTrans 23:16:21 oerjan: edwardk has a package with it 23:16:24 Key & Peele: Dubstep http://youtu.be/5Kod1q39ddE 23:16:39 oerjan: what you actually want is something like (Monad m) => (forall a. m a -> n a) -> MT m a -> MT n a IIRC 23:16:42 but that's not Haskell 2010 23:17:22 yeah someone made a post about that shortly afterwards, i think 23:17:51 oerjan: that was some dumb tailcalled or tekmo post that suggested something wrong iirc. but edwardk replied with the right thing 23:19:16 I cleared about 8 gigs of space, came back ten minutes later, and now it's all gone again. 23:19:32 the clutter is breeding 23:19:50 Phantom_Hoover: it's a tiny subsection, but it was the proof that got mathematicians to realize they didn't need to make proofs short, which probably helped immensely with the rest :) (also some direct consequences for making the rest of the program possible, iirc) 23:20:30 if you are talking about feit-thompson 23:20:43 Quite often these "someone's rogue script fills all space" problems tend to "auto-resolve" in the sense that the script dies when the disk is full, and therefore won't fill any newly freed storage. 23:20:53 I suppose this time someone has produced a robust enough space-waster. 23:21:18 How big is Haskell on the metaprogramming thing? 23:21:42 depends what you mean by metaprogramming 23:21:48 and also the rest of those words, but mainly metaprorgamming 23:21:51 * oerjan suddenly realizes elliott may be stalking him on reddit 23:22:06 oerjan: fear me. 23:22:29 elliott: The kind where you often end up with domain-specific languages 23:23:25 FreeFull: I would say it's incredibly big on that. 23:23:31 pretty big, in several different ways 23:23:33 however I'd also not identify that with metaprogramming 23:23:46 Ok 23:23:51 in that there are several ways to do EDSLs, and only some of them look like metaprogramming to me, and Haskell's methods don't really 23:24:02 template haskell doesn't? 23:24:06 (I would also say Haskell's methods are a better way of doing it, though) 23:24:11 I know Racket is really big on DSLs 23:24:20 Template Haskell? More like Terrible Haskell. 23:24:20 oerjan: yes, template haskell looks like metaprogramming to me. however, i would not build a DSL in Haskell by using template haskell 23:24:25 unless I was doing something weird 23:24:31 but I don't like TH, so I'd probably do it another way instead 23:24:45 thus, several different ways. 23:25:04 elliott: It's the very foundation of Haskell DSLs! 23:25:31 FreeFull: the monad thing you keep hearing about is also a kind of DSL method. 23:25:44 well can be used that way 23:26:08 oerjan: Don't do that. :( 23:26:31 Silly monad mysticism doesn't need to be promoted through vague statements that won't make any sense to start with. 23:26:45 and on the entirely other side are the template haskell based quasi-quotes which allows you to make any syntax you want. (as long as you don't need the string |] in it.) 23:29:30 -!- SimonRC has quit (Ping timeout: 264 seconds). 23:41:00 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:41:43 -!- SimonRC has joined. 23:44:55 -!- kinoSi has quit (Read error: Connection reset by peer). 23:45:23 -!- kinoSi has joined. 2012-10-05: 00:04:43 -!- Sgeo has quit (Ping timeout: 260 seconds). 00:07:11 -!- Jafet has quit (Quit: Leaving.). 00:51:12 -!- Jafet has joined. 00:51:46 -!- augur has quit (Remote host closed the connection). 01:10:18 -!- Sgeo has joined. 01:46:43 -!- augur has joined. 02:29:50 -!- Jafet has quit (Quit: Leaving.). 02:38:14 -!- Nisstyre has quit (Ping timeout: 240 seconds). 02:44:46 -!- oerjan has quit (Quit: Good night). 02:53:54 -!- Nisstyre has joined. 03:00:06 -!- fungot has quit (*.net *.split). 03:00:06 -!- nvt has quit (*.net *.split). 03:00:06 -!- shachaf has quit (*.net *.split). 03:00:23 -!- elliott has quit (Read error: Connection reset by peer). 03:01:06 -!- MoALTz_ has joined. 03:03:54 -!- MoALTz has quit (Ping timeout: 240 seconds). 03:05:32 -!- nvt has joined. 03:05:32 -!- shachaf has joined. 03:15:03 -!- augur has quit (Remote host closed the connection). 03:37:30 :( 03:37:37 I may have just convinced my group to use node.js 03:37:58 Everyone in the group knows Javascript, and it's sort of the home of socket.io 03:39:48 you could do much worse than node.js 03:41:44 * kmc wrote his first non-trivial program for Node last night 03:42:06 (but it's a command-line batch tool and not a network service or anything like that) 03:52:40 -!- Jafet has joined. 03:53:20 -!- DHeadshot has quit (Read error: Connection reset by peer). 03:54:05 -!- mig22 has joined. 04:01:33 kmc: Twist: A lot of non-trivial JavaScript code runs fine with Node. 04:10:48 -!- augur has joined. 04:24:03 what am i twisting? 04:27:44 i don't get it 04:28:31 I guess it's possible that you never wrote non-trivial JS node before. 04:29:09 Or only code that depended on the DOM, or something. 04:30:08 But "non-trivial Node program that doesn't use network libraries" sounds a lot like "generic JS code". 04:31:52 it used Node-specific filesystem libraries 04:32:25 I guess that exists too. 04:32:33 Do they have non-blocking chdir? 04:32:44 they have notblocking lots of stuff 04:32:47 i don't know about chdir 04:32:55 Non-blocking DNS is actually an issue. 05:02:51 I don't tend to write much JS 05:10:01 -!- FreeFull has quit. 05:25:40 -!- evincar has joined. 05:45:30 -!- kinoSi has quit (Read error: Connection reset by peer). 05:45:57 -!- kinoSi has joined. 06:32:53 -!- evincar has left. 06:52:17 has anyone had a Devonshire tea before? 06:59:29 i found a mistake in the proof 06:59:36 of feit-thompson 07:11:43 one of the comments said "spurrious" 07:11:46 that's not a word 07:12:54 Oh no, the foundations of mathematics are crumbling as we speak. 07:17:05 fizzie: are they? 07:17:30 i guess. 07:17:42 I'm pretty sure. It's all due to that "spurrious". Oh, if only... 07:55:48 -!- ais523 has joined. 07:58:51 -!- ais523 has quit (Client Quit). 07:58:58 -!- ais523 has joined. 08:04:43 This Machine Creates ANYTHING http://youtu.be/OHyygU1cU0k 08:06:44 -!- DHeadshot has joined. 08:22:11 -!- epicmonkey has joined. 08:24:30 -!- ais523 has quit (Read error: Connection reset by peer). 08:24:42 -!- ais523 has joined. 08:26:40 -!- copumpkin has quit (Ping timeout: 246 seconds). 08:27:14 -!- copumpkin has joined. 08:35:32 -!- ais523_ has joined. 08:37:13 -!- ais523 has quit (Ping timeout: 245 seconds). 08:37:54 -!- ais523_ has changed nick to ais523. 08:53:26 <…> User request of the month: "I accidentally posted /usr/share/dict/words to a bug report and now it shows up for every search because it contains all the words. Can you clean that up?" 09:01:11 How do you accidentally do that? 09:12:15 -!- ais523 has quit. 09:15:43 -!- copumpkin has quit (Ping timeout: 246 seconds). 09:16:17 -!- copumpkin has joined. 09:34:57 http://mashable.com/2012/10/02/ew-has-smartphone-inside/ 09:45:32 -!- kinoSi has quit (Read error: Connection reset by peer). 09:46:00 -!- kinoSi has joined. 09:46:43 (What kind of information system still uses naïve keyword search?) 09:52:13 -!- monqy has quit (Quit: hello). 10:21:41 DEFCON 17: More Tricks For Defeating SSL http://youtu.be/ibF36Yyeehw 10:34:28 -!- carado has joined. 11:08:50 -!- barts has joined. 11:12:02 -!- barts_ has quit (Ping timeout: 256 seconds). 11:37:11 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 11:44:43 -!- Frooxius has joined. 11:58:41 -!- copumpkin has joined. 12:13:15 -!- Phantom_Hoover has joined. 12:38:43 -!- sivoais has quit (Ping timeout: 246 seconds). 12:44:12 -!- Arc_Koen has joined. 12:49:07 -!- sivoais has joined. 12:50:27 hello 12:52:32 -!- Jafet has quit (Read error: Connection reset by peer). 12:52:40 -!- Jafet1 has joined. 12:54:54 -!- Jafet has joined. 12:55:00 -!- Jafet1 has quit (Read error: Connection reset by peer). 12:57:15 @messages 12:57:15 You don't have any new messages. 12:57:39 @tell oerjan I see in the logs you've tried to message me but lambdabot doesn't seem to agree 12:57:39 Consider it noted. 13:03:11 @tell oerjan anyway yeah, it was also about the brainfuck derivatives; I'd never have made brainfunct if I had found pbrain or others like that before 13:03:11 Consider it noted. 13:04:19 -!- boily has joined. 13:07:12 Huh. The soft drink vending machine made a very long "whirr-clunk-whirr-clunk-whirr-clunk-kaplonk" solo, and then dumped out two bottles for the price of one. 13:07:24 I suppose I should theoretically return the other. 13:14:23 how so 13:14:49 I don't think "handing out a bottle" is a reversible operation 13:17:56 Because it would be STEALING. 13:18:02 vending a bottle is like an md5 hash. here you had a collision. 13:18:05 I think it has a "in case of trouble, call" sticker on it somewhere. 13:18:30 I mean, I'd certainly be complaining loudly if I had gotten 0 bottles. 13:19:06 Also maybe the bookkeeping will now become all confused and it's ALL MY FAULT. 13:19:37 Well, up to a degree. Maybe not quite all. Unless I pressed the button wrong somehow. 13:24:35 fizzie: how about you keep the extra bottle in your refrigerator 13:24:47 and if one day you get no bottle, you can use it instead 13:26:43 It has a "best before" date, I'm sure. 13:27:57 Jan 25, 2013. 13:27:59 that shouldn't be a problem if you make a regular use of that vending machine: everytime you buy a bottle, place it in your refrigerator and drink the old bottle instead 13:28:09 Oh, of course. 13:28:32 this way, instead of having one really-out-of-date bottle, you'll have a lot of nearly-out-of-date bottles! 13:28:46 Maybe I'll just drink it early and resolve not to complain if I ever get no bottles. 13:28:55 Asymptotically, it's the same thing anyway. 13:29:11 yes but IT PERTURBS YOUR CONSOMMATION 13:29:41 I do that with tickets when taking the tube, though 13:29:46 -!- carado_ has joined. 13:30:07 -!- carado_ has quit (Client Quit). 13:30:10 -!- carado has quit (Remote host closed the connection). 13:30:23 -!- carado has joined. 13:30:38 a lot of people here take it without paying, because they find the penalty when caught is less that what they gain by not paying the fare 13:31:35 I had always been honest with it; I always pay my tickets, and it's happened once or twice that the vending machine at my station was out of order, so I traveled without a ticket, and bought one once arrived at destination 13:32:04 except one time the machine was out of order and I got caught (even though I would have paid afterwards :( ) 13:32:26 I believe a lot of people do that here too. I mean, the "go without paying" thing. 13:32:35 They've been steadily increasing the penalty amount, though. 13:32:49 I think it's now at 80 EUR; it used to be 56 EUR or something not too long ago. 13:33:00 so I made a count of the money I lost because of the penalty, and started not paying my tickets, deducing the money I gained everytime from the money I had lost 13:33:15 and now I'm back to paying my tickets again 13:33:17 And it was 250 FIM before EUR, I think. 13:33:33 That's ingenious. 13:33:35 well when I had to pay it it was 40 EUR here 13:33:44 How much is a ticket? 13:34:14 well that depends where you take it; tickets inside paris are about 1.70 (or they were last time I checked, but prices keep getting higher every year) 13:34:36 but I live in the suburbs, so tickets that cover all zones from my town to paris are about 4.00 13:34:50 (or 3.something when buying then 10 at a times) 13:35:51 I was amazed when I went to london, they had this "oyster card"; you put money on it and everytime you took the tube it was deduced 13:35:59 on our last day we wanted to take a bus 13:36:10 the driver told me there was no money left on my oyster card 13:36:18 in france that would probably have meant that I couldn't take it 13:36:28 but in London he gave me an "unpaid fare notice" 13:36:58 on which it was written that I had taken the bus for free but was expected to go to any station and pay for it 13:37:53 I made a copy of it, and when I paid I gave the copy so I could keep the original because that's just so wonderful, that system would *never* work in france 13:38:13 We don't have anything like that. 13:38:23 Though you can buy tickets from buses and such with cash. 13:38:33 The prices are a bit more than when paying with the card, though. 13:39:21 well yes that's always possible, but that was our last day and we had given all our leftover cash as tip in a coffee shop 13:39:37 Oh, the gaps seem to be larger than I remembered. 13:40:00 It's 4.50 eur vs. 3.47 for the Helsinki/Espoo/Vantaa regional ticket, or 2.70 vs. 1.86 for the single-city one. 13:40:21 (a *great* coffee shop; I'll probably go there once again next time I visit london) 13:42:08 I seem to recall that the Belgian railways had some kind of a differentness when it comes to the no-ticket fees. 13:43:27 Oh, right; if you didn't inform the train staff that you don't have a ticket, but agree to pay it, you don't get a penalty notice, just a 12.50 EUR surcharge to the regular ticket price. 13:43:47 ah, we have that in france too 13:44:14 the guy who must check tickets walks through the whole train twice 13:44:23 But if you don't agree to pay (or can't pay, I suppose) there's a penalty notice plus a penalty fare of 30/60 EUR (under/over 18 years), and then you have 14 days to go pay it yourself at any station. 13:44:26 the first time he does nothing, just showing himself 13:44:36 And then if you still don't go and pay it, "your file will be sent to Central Customer Services and incur administrative charges of € 200". 13:44:42 and if you have a problem with your ticket (or if you don't have one) you're supposed to talk to him at that moment 13:45:33 According to these Belgian rules you need to tell the train staff before actually boarding. 13:45:56 "If you don’t have a valid ticket and you can't pay on the train or provide evidence of your identity or address, the NMBS/SNCB obviously won't be able to allow you to remain on board. The staff may therefore invite you to leave the train at the next stop, or even call in the police." 13:46:02 I like the "invite you to leave the train". 13:46:13 "Sorry, I have to decline your kind invitation." 13:46:22 "This is not where I'm going." 13:48:34 "After being sentenced and ordered into custody, De'Avalon ["a marriage celebrant, self-styled witch and alternative therapies practitioner"] appeared to be sticking by her pagan-immunity theory even in the face of this pretty solid evidence that human laws do in fact apply to her. 'I decline your offer, your Honour,' she said as she was being led away." 13:48:41 http://www.loweringthebar.net/2011/06/witch-who-said-our-laws-do-not-apply.html 13:54:19 -!- carado has quit (Ping timeout: 246 seconds). 13:57:20 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 13:59:21 -!- AnotherTest has joined. 13:59:31 Hello 14:00:30 Hello. We were just talking about Belgian railways. 14:00:47 oh yes 14:00:49 strike 14:00:54 Oh, is there? 14:01:03 There was one, yesterday 14:01:08 I did not know that. 14:20:50 -!- AnotherTest has quit (Read error: Connection reset by peer). 14:21:03 -!- AnotherTest has joined. 14:32:06 -!- AnotherTest has quit (Quit: Leaving.). 14:32:29 -!- AnotherTest has joined. 14:33:53 @tell atriq I probably already asked you that, but how does Nandypants/Noryshorts handle end of file? 14:33:53 Consider it noted. 15:03:23 I feel like when I use PubNub, I'm cheating 15:03:54 Writing code that seems like it should require a server-side component, and ... well, using someone else's very general server, I guess. 15:08:07 -!- epicmonkey has quit (Ping timeout: 246 seconds). 15:23:58 -!- Phantom_Hoover has joined. 15:41:56 -!- Vorpal has joined. 15:44:06 @tell Oerjan remember when you modified cat in http://esolangs.org/wiki/Minifuck-2D ? I think you removed a space between ! and @ that might have been important 15:44:06 Consider it noted. 16:26:14 -!- augur has quit (Remote host closed the connection). 16:27:55 -!- FreeFull has joined. 16:28:17 -!- atriq has joined. 16:31:18 @messages? 16:31:19 atriq: You have 1 new message. '/msg lambdabot @messages' to read it. 16:31:21 Wow 16:31:35 YOU HAVE FRIENDS 16:31:40 I wonder who that might be 16:31:45 I think it's you 16:32:09 so what do I say? 16:32:24 But yeah, Nandypants handles EOF in the same way as brainfuck, ie. implementation defined 16:32:48 so there should be something said about it 16:32:52 especially in the cat example 16:33:08 also I was in the middle of writing an interpreter and I had to stop because I didn't know what to do about end of file 16:33:50 Either input -1 or 0 seems to be the convention 16:34:58 or "leave it as it is" 16:35:09 waiiiiit nandypants uses bits 16:35:14 Yeeees 16:35:28 oh, ok 16:35:56 I still think you should write a note about it 16:39:04 oh, I was hoping you would say "it assumes eof is coded by..." 16:49:45 anyway, see you later 16:50:06 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 17:07:01 -!- augur has joined. 17:16:12 -!- augur has quit (Read error: Connection reset by peer). 17:16:34 -!- augur has joined. 17:24:43 kmc: They're playing _The Big Lebowski_ at the theatre tomorrow night. Should I go see it? 17:27:56 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 17:31:30 have you seen it before? 17:32:01 I've seen parts of it, I think. 17:35:22 you should go see it 17:35:32 i've never seen it in an actual theatre 17:39:09 «Wear your best "Dude" bathrobe and receive $1 off popcorn!» 17:40:58 *one* dollar? 17:41:25 Well, in about two years, I'll be able to read Homestuck offline! 17:41:42 why in two years? 17:42:04 Who knows? 17:42:06 Magic! 17:45:42 Do you happen to know tools that'd google-translate .srt subtitles files? I remember writing a script for this once, but can't seem to find it; apparently it doesn't have "sub" in the name. 17:46:49 Oh, srttrans.pl. 17:46:55 Well, that makes sense. 17:48:02 -!- variable has quit (Ping timeout: 252 seconds). 17:49:31 -!- atriq has quit (Ping timeout: 246 seconds). 17:59:46 i think the google translate API was taken down :/ 18:00:23 -!- Phantom_Hoover has joined. 18:01:24 Is there a Babelfish API? 18:09:03 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 18:10:59 kmc: The script just produces a empty-line-separated-paragraph output to translate manually, then takes a similar input, and adds the original subtitle timing infos back in. 18:11:12 So I translated via the website. 18:11:35 Calling it a translation script is a bit exaggerationary, I suppose. 18:12:27 ah 18:12:45 well at that rate you could probably also use the same interface the web page uses, and fully automate it 18:12:51 without needing an API per se 18:13:14 -!- Phantom_Hoover has joined. 18:13:28 oh, exaggerationary 18:13:39 -!- atriq has joined. 18:16:18 -!- augur has quit (Remote host closed the connection). 18:22:50 -!- Taneb has joined. 18:23:40 -!- atriq has quit (Ping timeout: 246 seconds). 18:28:43 -!- Taneb has quit (Remote host closed the connection). 18:37:44 -!- augur has joined. 18:47:47 -!- AnotherTest has quit (Quit: Leaving.). 18:50:23 -!- AnotherTest has joined. 18:51:51 -!- AnotherTest has quit (Client Quit). 18:53:28 -!- AnotherTest has joined. 18:54:57 -!- AnotherTest has quit (Client Quit). 18:55:06 -!- AnotherTest has joined. 18:58:12 -!- AnotherTest has left. 19:02:44 -!- oerjan has joined. 19:03:53 @messages 19:03:53 Arc_Koen said 6h 6m 14s ago: I see in the logs you've tried to message me but lambdabot doesn't seem to agree 19:03:53 Arc_Koen said 6h 42s ago: anyway yeah, it was also about the brainfuck derivatives; I'd never have made brainfunct if I had found pbrain or others like that before 19:03:53 Arc_Koen said 3h 19m 47s ago: remember when you modified cat in http://esolangs.org/wiki/Minifuck-2D ? I think you removed a space between ! and @ that might have been important 19:05:13 @tell Arc_Koen Stupid me, I left the <>'s around your nick when pasting into @tell... 19:05:13 Consider it noted. 19:06:18 hi oerjan 19:06:22 hi olsner 19:35:41 -!- zzo38 has joined. 19:41:29 Is it a terribad idea to use Javascript's Math.random() to get a unique key? 19:42:04 -!- Nisstyre has quit (Ping timeout: 252 seconds). 19:42:24 It depends where the Javascript code is being executed, and what the key is being used for. 19:42:36 As well as the implementation of Javascript used. 19:45:23 and possibly the phase of the moon. 19:47:37 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 19:55:08 -!- augur has quit (Remote host closed the connection). 20:11:49 -!- copumpkin has joined. 20:12:53 -!- elliott has joined. 20:13:00 does anyone use arch 20:13:07 no. 20:13:12 absolutely no one. 20:14:16 oerjan: ok. then op me 20:14:47 I think one person uses arch 20:14:57 elliott: Lern2NixOS 20:14:59 (I don't) 20:15:01 Like roconnor 20:15:08 All the cool people NixOS 20:15:12 Isn't that right, oerjan? 20:15:16 nixos is perfect, unfortunately it is also shit 20:15:20 i considered using it for a while 20:15:29 perfect shit :) 20:15:52 * oerjan notes that searching for /// on esolang takes you directly to the main page. 20:16:02 * oerjan whistles innocently 20:16:14 oerjan: aren't you the wiki admin? 20:16:17 yes 20:16:22 oerjan is the reason it is broken 20:16:25 and he should fix it 20:16:31 it is **very** unprofessional 20:16:46 olsner: elliott seems to be thinking so. probably from going mad trying to fix the /// bug. 20:16:58 elliott: Help me simplify this GHC bug! 20:17:01 Do you have 7.6? 20:17:05 sort of 20:17:07 > 7.6 20:17:08 7.6 20:17:11 Try :t fmap fmap fmap join join join 20:17:12 i can't decide how to get my 7.6 20:17:30 $ /opt/ghc.old/bin/ghci 20:17:30 /opt/ghc.old/bin/ghci: line 2: /opt/ghc/bin/ghc-7.6.1: No such file or directory 20:17:30 n/m 20:17:37 :t fmap fmap fmap join join join -- OKAY 20:17:38 Occurs check: cannot construct the infinite type: 20:17:38 m = (->) (m (m a)) 20:17:38 Probable cause: `join' is applied to too many arguments 20:17:47 shachaf: BOO 20:17:49 oerjan: THAT'S NOT 7.6 20:18:00 wat 20:18:04 oerjan: Should I flood the channel a bit? 20:18:11 shachaf: are you telling me it works in 7.6? 20:18:15 No. 20:18:18 Prelude Control.Monad> :t fmap fmap fmap join join join 20:18:18 :1:1: 20:18:18 Occurs check: cannot construct the infinite type: 20:18:18 m1 = (->) (m1 (m1 (m0 (m0 a0)))) 20:18:18 Expected type: (m0 (m0 a0) -> m0 a0) 20:18:18 -> ((m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:20 -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:22 -> (m1 (m1 (m0 (m0 a0))) -> m1 (m0 (m0 a0))) 20:18:24 -> m1 (m1 (m0 (m0 a0))) 20:18:26 -> m0 a0 20:18:28 Actual type: (m0 (m0 a0) -> m0 a0) 20:18:30 -> ((m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:32 -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:34 -> (m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:36 -> m1 (m1 (m0 (m0 a0))) 20:18:38 -> m0 a0 20:18:40 The function `fmap' is applied to five arguments, 20:18:42 but its type `(((m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:44 -> m1 (m1 (m0 (m0 a0))) -> m0 a0) 20:18:46 -> ((m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:48 -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:50 -> (m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:18:52 -> m1 (m1 (m0 (m0 a0))) 20:18:54 -> m0 a0) 20:18:54 Lol 20:18:56 -> ((m0 (m0 a0) -> m0 a0) 20:18:58 -> (m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:19:00 -> m1 (m1 (m0 (m0 a0))) 20:19:02 -> m0 a0) 20:19:04 -> (m0 (m0 a0) -> m0 a0) 20:19:06 -> ((m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:19:08 -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:19:10 -> (m1 (m1 (m0 (m0 a0))) -> m1 (m1 (m0 (m0 a0))) -> m0 (m0 a0)) 20:19:12 -> m1 (m1 (m0 (m0 a0))) 20:19:14 -> m0 a0' 20:19:16 has only six 20:19:18 In the expression: fmap fmap fmap join join join 20:19:20 "The function `fmap' is applied to five arguments, but its type has only six" is pretty great 20:19:21 thanks elliott 20:19:23 Way to pastespam the channel 20:19:28 the wiki could have a rewrite rule that makes esolangs.org/// into a /// interpreter 20:19:59 FreeFull: well you know 20:20:01 FreeFull: fuck rules 20:20:02 FreeFull: fuck the police 20:20:04 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 20:20:06 Mahna Mahna Killer http://youtu.be/ELAFDkXog-s 20:20:07 irc anarchy forever 20:21:10 olsner: it _used_ to link to the language article. 20:21:21 :t :t fmap fmap fmap join join 20:21:22 parse error on input `:' 20:21:24 oops 20:21:25 oerjan: how boring 20:21:28 :t fmap fmap fmap join join 20:21:29 forall (m :: * -> *) a (m1 :: * -> *). (Functor m1, Monad m, Monad m1) => m1 (m1 (m (m a))) -> m1 (m a) 20:21:33 esolangs.org/// did *not* 20:22:15 by esolangs.org///, obviously I meant esolangs.org//// 20:23:32 :t fmap (fmap join) join 20:23:33 forall (m :: * -> *) a (f :: * -> *). (Monad m, Functor f, Monad f) => f (f (m (m a))) -> f (m a) 20:24:08 :t fmap join (join join) 20:24:09 Occurs check: cannot construct the infinite type: 20:24:09 f = (->) (f (f (m (m a)))) 20:24:09 Probable cause: `join' is applied to too few arguments 20:24:27 :t join join 20:24:28 Occurs check: cannot construct the infinite type: 20:24:29 m = (->) (m (m a)) 20:24:29 Probable cause: `join' is applied to too few arguments 20:24:50 The function `g' is applied to four arguments, 20:24:53 but its type `(a0 -> ((r0 -> r0 -> a0) -> a0) -> c0) 20:24:55 has only four 20:25:13 oh that's the ghc bug? 20:25:23 Sort of a bug. 20:25:28 13:19 "The function `fmap' is applied to five arguments, but its type has only six" is pretty great 20:27:17 shachaf: it doesn't work if you manually simplify it to :t fmap (fmap join) join join, :t fmap join (join join), or :t join . join join ? 20:28:03 by work, i mean still gives that bug 20:28:13 Nope, none of those do it. 20:28:38 You get the bug with let j f x = f x x, fmap fmap fmap j j j 20:28:49 Also with fmap (.) (.) undefined j j 20:29:25 fancy 20:29:39 :t let j f x = f x x in fmap (.) (.) undefined j j 20:29:40 Occurs check: cannot construct the infinite type: t = t -> t -> t1 20:29:40 Expected type: (t -> t -> t1) -> (t -> t -> t1) -> a 20:29:40 Inferred type: (t -> t -> t1) -> t -> t1 20:30:57 oerjan: Q 20:31:07 elliott: A 20:31:21 oerjan: Should I use the [testing] repo to get a 7.6.1 package, or use my self-compiled binary? 20:31:35 yes, clearly. 20:31:59 oerjan: Which? 20:32:09 (i know you didn't actually expect a serious answer) 20:32:39 oerjan: I did. 20:32:43 why, you should use the haskell platform! 20:32:54 it's what i do. i should probably upgrade, though. 20:33:38 More like the Haskell Catsdom. 20:33:45 Because fascist cats rule the universe. 20:34:22 i thought dogbert had settled that they were fascist squirrels. although maybe catbert paid him to say it. 20:34:31 oerjan: Do you want to see a bad reddit post? 20:34:34 oerjan: Here you go! http://www.reddit.com/r/coding/comments/11052z/its_amazing_how_microsoft_can_just_shit_on/ 20:34:55 based solely on the title part of the url, i guess "no". 20:35:14 as in, it's precisely the kind of title i tend to skip. 20:35:23 Don't forget \t for tabs, and that F2 renames files. When I stumble upon these things, I put them on http://efficientgeeks.com/[1] , although I won't renew that domain. 20:35:30 mmm spam 20:37:03 oerjan: Is the wiki fixed yet? 20:37:31 shachaf: and it disappears if you replace the first fmap with (.) i take 20:37:39 oerjan: Yep. 20:37:42 Although... 20:37:50 13:22 Hah, this is funny. 20:37:50 13:22 g :: Functor f => f ~ (->) r => f (b -> c) -> f ((a -> b) -> a -> c) 20:37:53 13:22 g :: (r -> b -> c) -> (r -> (a -> b) -> a -> c) 20:37:55 13:22 You'd expect those to be the same, wouldn't you? 20:37:58 13:22 ghci gives the same :t for them. 20:38:01 It happens with the first g but not with the second g 20:38:06 for g (.) undefined join join 20:38:26 shachaf: Remember that time we got GHC to type two identical things differently or something? 20:38:28 That wacky bug. 20:38:36 elliott: With the parentheses? 20:38:39 No. 20:38:41 Where you got an (a => b) in the wrong place. 20:38:47 Like, you god a -> b => c or something. 20:38:48 *got 20:38:52 Lol 20:40:08 shachaf: hm so it might be something which happens when f ~ (->) r appears as a constraint during type checking? 20:41:05 oerjan: Also happens with g :: f (b -> c) -> f ((a -> b) -> a -> c); g = undefined; blah = g (.) undefined j j 20:42:07 shachaf: well that would also cause f ~ (->) something to appear during type checking, wouldn't it? 20:42:32 I guess it tries to unify them. 20:42:34 Or something. 20:42:39 I dunno, man! Simplify it for me! 20:42:48 I thought perhaps the monad type for FamicomHDL should be: type Mapper = ContT [Command] ((->) Int); 20:42:54 What would you think? 20:43:32 the g's given type takes 1 argument at least. but it's used with 4. 20:45:14 * oerjan is wildly guessing, of course, and has no intention of installing 7.6. 20:45:25 oerjan: Install 7.6! :-( 20:45:39 4 is not 1, so that's obviously the numbers you're looking for 20:46:17 olsner: Can you /nick to something that doesn't start with o? 20:46:23 shachaf: no 20:46:36 data Command = Case Word8 (Word8 -> [Command]) | Command ByteString | Wire Pin Pin Connection | Part x => Part Int x; 20:46:36 But oerjan :-( 20:46:40 colsner 20:46:42 Is this OK? 20:46:52 coolsner 20:47:06 I think you shouldn't change it 20:47:30 -!- boily has quit (Quit: Poulet!). 20:47:46 don't worry, I won't 20:48:22 shachaf: it's not like i have a clue what to do next, anyway. 20:49:15 oerjan: You should change your nick. 20:49:18 Maybe to Ørjan 20:49:34 No, I don't think you should change it either. 20:49:39 Øh nø 20:49:40 Ørjan Erroneous Nickname 20:49:49 Errøneøus 20:51:46 Probably because of some møøse or something 20:52:59 -!- copumpkin has joined. 20:53:08 beware the erroneous moose 20:53:50 -!- oerjan has set topic: BEWARE THE ERRØNEØUS MØØSE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 20:57:48 -!- augur has joined. 21:04:46 oerjan: What is friends 21:04:58 hi FireFly 21:05:04 How's #stackoverflow? 21:07:31 Nice enough, thus far 21:08:42 Did you know I got banned from that channel? 21:09:17 elliott: UNREVEALED NEMESISES (NEMESES?) 21:09:34 I did not. What was the reason? 21:10:10 shachaf: tell us 21:10:32 olsner: Being rude. 21:10:38 It's true! 21:10:55 hmm, I guess you are rude 21:11:01 someone ban shachaf! 21:13:15 ban olsner 21:13:17 oerjan: What am friend? 21:13:50 elliott: ban elliott 21:13:56 * oerjan cans shachaf |_| 21:13:56 (by elliott I mean me) 21:15:21 * oerjan fans shachaf \|/ 21:15:49 * oerjan tans shachaf /¤ 21:16:04 * oerjan pans shachaf ===\__/ 21:16:29 * oerjan sans 21:17:01 oerjan++ 21:18:34 -!- atriq has joined. 21:19:31 he looks like a regular, but i think it may be atriq 21:20:05 oh, was atriq the rot13 of taneb? 21:20:13 Of ngevd 21:20:20 !rot13 atriq 21:20:23 ngevd 21:20:31 !rot13 taneb 21:20:32 gnaro 21:20:35 !rot13 olsner 21:20:35 byfare 21:20:41 whoa, dude 21:20:46 !rot13 oerjan 21:20:47 brewna 21:20:47 That is the best nick by far. 21:21:00 atriq: Better than rot13 shachaf? 21:21:12 !rot13 shachaf 21:21:12 funpuns 21:21:23 O.O 21:21:24 !rot13 FireFly 21:21:24 SverSyl 21:21:25 What fun puns 21:21:29 olsner är en sådan byfare 21:21:34 !rot13 zzo38 21:21:34 mmb38 21:21:40 zzo38: /nivk mmb38 21:21:54 !rot13 lambdabot 21:21:55 ynzoqnobg 21:22:50 I wonder if oerjan and shachaf swapped nicks earlier, because the one currently calling itself "oerjan" fits better with funpuns 21:22:57 !rot13 nick 21:22:57 avpx 21:23:00 /avpx mmb38 21:23:14 !rot13 archaeopteryx 21:23:14 nepunrbcgrelk 21:23:24 !rot13 EgoBot 21:23:25 RtbObg 21:23:51 !rot13 nepungrelk 21:23:52 archateryx 21:23:55 BZT 21:24:49 !rot13 elliott 21:24:49 ryyvbgg 21:25:11 >> sort "firefly" 21:25:15 so he's secretly welsh, ok 21:25:26 > sort "firefly" 21:25:27 "effilry" 21:25:53 FireFly: hello 21:26:02 Hi 21:26:04 !rot13 Phantom_Hoover 21:26:04 Cunagbz_Ubbire 21:26:12 > sort "ant" 21:26:13 "ant" 21:26:20 elliott: zomg 21:26:23 ubbire is probably how you say umpire with a cold 21:26:25 That's what avpx means. 21:26:29 !rot13 zomg 21:26:29 mbzt 21:26:47 !rot13 FreeFull 21:26:47 SerrShyy 21:26:52 !rot13 OMGWTFBBQ 21:26:52 BZTJGSOOD 21:26:53 shachaf: means? 21:27:20 elliott: There's a #haskell person with the nick avpx 21:27:29 !rot13 effilry 21:27:29 rssvyel 21:27:40 ok, effilry is better 21:28:08 !rot13 fizzie 21:28:09 svmmvr 21:28:10 effilry is like rivalry but for effils 21:28:39 !rot13 Gregor 21:28:39 Tertbe 21:28:49 shachaf: oh right 21:28:53 i thought it sounded familiar 21:28:55 !rot13 Richards 21:28:55 Evpuneqf 21:28:57 !rot13 bertle 21:28:57 oregyr 21:29:02 !rot13 avpx 21:29:02 nick 21:29:17 !rot13 !rot13 21:29:18 ​!ebg13 21:29:20 shachaf: didn't you quit #haskell? 21:29:28 !rot13 haskell 21:29:29 unfxryy 21:29:35 !rot13 ernie and bert 21:29:36 reavr naq oreg 21:29:38 !rot13 fry 21:29:39 sel 21:29:42 @rot13 oregano 21:29:42 Unknown command, try @list 21:29:42 !ebg13 should be the inverse of rot13 21:29:45 !rot13 oregano 21:29:46 bertnab 21:29:52 olsner: I ought to. 21:30:31 !rot13 tarragon 21:30:32 gneentba 21:30:40 !rot13 dragon 21:30:40 qentba 21:30:55 !rot13 electron 21:30:56 ryrpgeba 21:30:59 !rot13 smeghead 21:31:00 fzrturnq 21:31:03 I'm surprised by how often the result is pronounceable. 21:31:04 !rot13 proton 21:31:04 cebgba 21:31:22 if you say so, Mr. Tertbe 21:31:42 !rot13 higgs boson 21:31:43 uvttf obfba 21:31:50 I think “Tertbe” is perfectly pronounceable. 21:31:58 !rot13 Gregor 21:31:58 Tertbe 21:32:03 So is Evpuneqf, though less so because the “q” is terribad. 21:32:08 ...was i appearing to disagree? 21:32:21 just glottal it up 21:32:40 !rot13 Malcom Gray 21:32:41 Znypbz Tenl 21:32:48 Wow. Really got a loser with that one X-D 21:33:03 That first name is actually pronounced “Snips” though. 21:33:03 !rot13 IRC 21:33:03 VEP 21:33:05 -kf works fine, I'm a bit sad that no language I know uses that combination though 21:33:14 like the initial ng 21:33:15 !rot13 Mitt Romney Barack Obama 21:33:16 Zvgg Ebzarl Onenpx Bonzn 21:33:28 no obvious loser, alas 21:33:44 Ebzarl Ngekf 21:33:55 !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie 21:33:56 Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr 21:34:03 !rot13 Ngekf 21:34:04 Atrxs 21:34:10 Nccyrwnpx will definitely eat your soul. 21:34:12 oh, they're all named after rot13'd welsh words 21:34:18 So will Gjvyvtug Fcnexyr. 21:34:30 lol 21:35:05 Syhggreful is sorta pronounceable 21:35:07 `addquote !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:35:07 Puzzle: What word's meaning is preserved under rot13? 21:35:16 oerjan: FOLLOW THE GUIDELINES 21:35:18 870) !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:35:21 shachaf: shachaf 21:35:30 elliott: elliott 21:35:36 elliott: none of the double spaces were mine 21:35:43 shachaf: The word is "shachaf". 21:35:50 oerjan: No, but you forgot the double spaces between each message 21:35:53 elliott: The word is "elliott". 21:36:21 elliott: wait those are double? i checked just the other day and ARGH 21:36:31 `quote 3 21:36:36 3) Hmmm... My fingers and tongue seem to be as quick as ever, but my lips have definitely weakened... More practice is in order. 21:36:37 Wait, that one will be too early. 21:36:37 are there guidelines? 21:36:38 `quote 100 21:36:42 100) okay I see it now, quines do exist 21:36:52 `quote 101 21:36:54 !rot13 quine 21:36:55 dhvar 21:36:55 101) Darn, now I can't acknowledge the reference you were making. 21:36:59 `quote 200 21:36:59 olsner: The guideline is that if you do it wrong, elliott will have a screed and fix it. 21:37:03 200) oerjan: What, can girls aim their penises better? 21:37:06 `quote 300 21:37:07 Come on. 21:37:10 300) elliott: well what i would do if i were omniscient and omnipotent would be to create an immortal woman with perfect tits and bang her for the rest of eternity 21:37:13 lol 21:37:14 `quote 350 21:37:18 350) Felix's home page and Falcon's home page are actually the same page 21:37:20 All the multiples of 100 are one-liners. 21:37:22 `quote 380 21:37:25 380) what would you ever need petrol for newsflash: it doesn't actually taste that good 21:37:28 There. 21:37:39 elliott: i did `quote [ ]< to check and the first example that showed up had one space :( 21:37:48 `quote [ ]< 21:37:51 1) I used computational linguistics to kill her. \ 2) EgoBot just opened a chat session with me to say "bork bork bork" \ 3) Hmmm... My fingers and tongue seem to be as quick as ever, but my lips have definitely weakened... More practice is in order. \ 4) that's where I got it rocket launch facility gift shop \ 5) GKennethR: he should be told 21:38:03 `run quote $((RANDOM % 870 + 1)) 21:38:05 oerjan: The old quotes fail to follow the platonically perfect formatting standards. 21:38:06 369) but touchscreens should feel like poking a boob 21:38:16 zomg, random quotes 21:38:20 There should be a command for that. 21:38:22 hm that's not useful... 21:38:29 shachaf: Uh... 21:38:29 `quote 21:38:33 393) "system is fairly sane imagine if the roomba was called the Robotic Magic Vacuum would you object to that being trademarked I mean phrase trade" oops 21:38:35 `run quote $((RANDOM % 870 + 1)) 21:38:36 `quote 868 21:38:37 `run quote $((RANDOM % 870 + 1)) 21:38:37 `run quote $((RANDOM % 870 + 1)) 21:38:38 `run quote $((RANDOM % 870 + 1)) 21:38:38 `run quote $((RANDOM % 870 + 1)) 21:38:47 105) I am an inherently pornographic being. 21:38:52 671) * oerjan concludes that unsafeCoerce has no effect on strictness 21:39:15 @quote 21:39:15 Plugin `quote' failed with: getRandItem: empty list 21:39:17 @quote 21:39:17 DukeDave says: what, if your kids start doing drugs? or worse, business school 21:39:19 @quote 21:39:19 Plugin `quote' failed with: getRandItem: empty list 21:39:20 @quote 21:39:20 co_dh says: I don't like it, but I don't know why. 21:39:21 @quote 21:39:21 @quote 21:39:21 PhilWadler says: The essence of XML is this: the problem it solves is not hard, and it does not solve the problem well. (POPL2003) 21:39:21 cypherx says: Oh god, C++ is like a lamprey in my urethra. 21:39:23 @quote 21:39:23 c_wraith says: I either just got the most awesome piece of spam ever, or am being secretly recruited into the stargate program 21:39:26 @quote 21:39:26 PatrickRobotham says: GHC has more flags than the united nations. 21:39:28 hmm, `quote on its own outputs a random quote, doesn't it? 21:39:28 @quote 21:39:28 dave_m says: < Bobstopper> Assuming the universe will eventually die of heat death, counting will cease when that happens. So if you start counting now, you'll probably find the largest number (so 21:39:29 long as nobody else has found a larger one yet) < Cale> what about faster ways to produce larger numbers? < Bobstopper> not after the heat death you can't :P < dave_m> don't you tell me what I can't 21:39:29 do after the heat death of the universe 21:39:31 @quote 21:39:31 ryan[WIN] says: forth is like if assembly had sex with math 21:39:32 396) as always in sweden everything goes to a fixed pattern: thursday is queueing at systembolaget to get beer and schnaps, friday is pickled herring, schnaps and dancing the frog dance around the phallos, saturday is dedicated to being hung over 21:39:32 868) Backups are so like one of those circus guys walking on a wire except with a safety rope. 21:39:32 564) When the moon hits your eye like a big pizza pie, that's a monad. 21:39:33 834) I couldn't survive an apocalypse. I don't even have any bitcoins. 21:39:33 @quote 21:39:33 monochrom says: no, you're thinking imperatively. when thinking functionally, you just worry one element, and let recursion worry the rest 21:39:36 @quote 21:39:36 PreauxPhoto says: catpants: you are lucky i like you, today at lunch i was going to come up behind you kiss you on the neck, pinch you nipple and say "cant wait till out date tonight" but i figured 21:39:36 that one of those guys was your boss 21:40:30 564) When the moon hits your eye like a big pizza pie, that's a monad. 21:40:34 IMO someone should @remember this so it gets in HWN. 21:40:42 elliott: No. 21:40:52 I didn't ask you. 21:40:54 Monad quotes = the devil 21:41:05 OTOH, you're the devil. 21:41:19 `run echo quote $(($$ % 870 + 1)) # the qupidote 21:41:22 quote 277 21:41:23 shachaf: better than stereo quotes 21:41:30 `quote stereo 21:41:33 No output. 21:41:36 Whoop, forgot the echo. 21:41:44 @quote surround 21:41:44 baristaTam says: Well, I suppose I shouldn't surround myself in a place full of hate. I think bringing kindness into the world is a value, and this channel seems to spew the opposite. 21:41:46 `run quote $(($$ % 870 + 1)) # the qupidote, rehashed 21:41:50 277) Phantom_Hoover: if the list is in random order, like poor ehird here 21:42:06 $$ isn't very random. 21:42:09 olsner: have you considered writing a book about sweden 21:42:12 396) as always in sweden everything goes to a fixed pattern: thursday is queueing at systembolaget to get beer and schnaps, friday is pickled herring, schnaps and dancing the frog dance around the phallos, saturday is dedicated to being hung over 21:42:14 this would be a good opening 21:42:17 haha elliott remember when you were in random order 21:42:22 those were the days 21:42:23 shachaf: Especially on that system. 21:42:24 dunno what to grep for, iirc many of the stereo quotes got purged anyway due to not being very good 21:42:31 `quote 869 21:42:34 869) `delquote 869 21:42:40 `quote 870 21:42:44 870) !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:42:49 `run echo $$ 21:42:50 `run echo $$ 21:42:51 `run echo $$ 21:42:55 276 21:43:01 `delquote 870 21:43:12 elliott: I have considered writing a book, but not about sweden 21:43:13 ​*poof* !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:43:13 276 21:43:16 276 21:43:21 `run echo $$ 21:43:21 `run echo $$ 21:43:21 `run echo $$ 21:43:21 `run echo $$ 21:43:22 `run echo $$ 21:43:23 What are the odds! Three times 276. 21:43:24 olsner: What would it be about? 21:43:26 `addquote !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:43:30 elliott: not sweden 21:43:31 276 21:43:32 fizzie: 100% 21:43:33 elliott, Hexham 21:43:40 shachaf: Still 100% (are the odds) 21:43:45 !rot13 sweden 21:43:47 olsner: thanks 21:43:47 870) !rot13 Fluttershy Rainbow Dash Rarity Applejack Twilight Sparkle Pinkie Pie Syhggreful Envaobj Qnfu Enevgl Nccyrwnpx Gjvyvtug Fcnexyr Cvaxvr Cvr oh, they're all named after rot13'd welsh words 21:43:49 fjrqra 21:43:59 Gregor: 100 is one of the evens. 21:44:03 276 21:44:08 276 21:44:13 276 21:44:14 276 21:44:19 `quote wait 21:44:25 96) fungot!*@* added to ignore list. AnMaster: i'd find that a bit annoying to wait for an ack. \ 261) Phantom_Hoover: I have just one tvtropes page open in elinks, but my tvtropes.txt "queue" has 38 tvtropes.org URLs waiting for processing. \ 294) Ohheywait, I can make it a raytracer instead of a photon tracer so long as I run time backwards. \ 304) elliott, it was an 21:44:28 !rot13 fjord 21:44:30 swbeq 21:44:42 !rot13 fnord 21:44:42 sabeq 21:44:45 !rot13 esoteric 21:44:45 rfbgrevp 21:44:47 !rot13 botspam 21:44:48 obgfcnz 21:44:51 !rot13 sweden is awful 21:44:51 fjrqra vf njshy 21:45:54 !rot13 quebec 21:45:54 dhrorp 21:46:06 -!- fungot has joined. 21:46:17 -!- kinoSi has quit (Read error: Connection reset by peer). 21:46:22 ^rot13 competition! 21:46:23 pbzcrgvgvba! 21:46:23 fungot: mix up this botspam with other botspam please 21:46:23 olsner: well indv change was easy for you 21:46:24 `quote 867 21:46:27 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 21:46:30 fizzie: Why do things other than fungot exist? 21:46:31 elliott: seabot's karma lowered to -1. 21:46:35 help 21:46:45 -!- kinoSi has joined. 21:46:49 !rot13 fungot 21:46:49 shatbg 21:46:50 olsner: it's just one of those 21:47:06 yay, doublebot spam 21:47:07 oerjan: Did you fix quote and delquote? 21:47:18 `run sed -i '867s/ fungot: Are you feeling well. You're making too much sense. 21:47:19 fizzie: i'll just check the last step 21:47:21 No output. 21:47:25 Scary. 21:47:25 elliott: fizzie did... 21:47:27 Whose bot is fungot? 21:47:28 shachaf: it's rather like the way uu did time. had a menu open and a file name. ( define my-ip ( lambda ( a b ( integer 0 fnord) 21:47:30 `quote 867 21:47:31 oerjan: So no, then. 21:47:33 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 21:47:38 oops 21:47:40 By quote I mean addquote. 21:47:41 `revert 21:47:43 Done. 21:47:48 `run sed -i '867s/ fizzie: Yours? 21:47:52 No output. 21:47:53 `quote 867 21:47:55 shachaf: Yaas. 21:47:57 867) t y also i didn't say t\ny on purpose, i just accidentally hit the keyboard with my head 21:48:07 fizzie: You should make fungot join #cslounge! 21:48:07 shachaf: thanks for the explanations, by the way, when running an infinite loop", and it has its own toplevel, doesn't it?) 21:48:27 what's #cslounge? 21:48:40 A channel that had a bot which is presently offline. 21:48:51 Running low on nonsense. 21:48:59 fungot: who is your owner? 21:49:00 FireFly: ( the *parser optimizer has a bug? for shame :( :()) 21:49:06 It sounds something like a very serious place. 21:49:07 (that'd surely work) 21:49:14 fizzie: Do you remember Way Back, with fungot, and Minecraft? 21:49:16 elliott: anyhow, i think there'll be some tag somewhere a long the line is ' back off, man: i'm a scientist. 21:49:27 fungot: TAKE ME TO YOUR LEADER HUMON 21:49:28 fizzie: not questioning that. gambit-c is looking especially attractive now that 4.0 is basically here 21:49:29 fizzie: That's why I want theb ot in there. 21:49:51 fizzie: I miss Minecraft. 21:49:53 fizzie: Can you add a feature to fungot where you can specify the first word of the sentence? 21:49:54 shachaf: clearly a program without interpretation. 21:50:02 fungot: clearly. 21:50:03 shachaf: well, you could expedite the development of t until orbit, and racked in the dough. c and pythong have a clear cmd on your computer 21:51:09 fizzie: I thoroughly oppose such a feature. 21:51:11 fungot is perfect. 21:51:12 elliott: help me correct some steps? my stack code used 2n cause it had to, and i don't 21:51:24 fizzie: You should add the feature! 21:51:31 elliott: fungot disagrees! 21:51:31 oerjan: i'll shut up 21:51:33 It makes bots over 14 times better. 21:51:42 `pastelogs fungot 21:51:43 elliott: since most of us have day jobs... 21:51:47 fungot: do you want to be 14 times better? 21:51:48 olsner: and you probably understand it better. if it's short you can just lex level? is low high enough? o.o :d 21:51:48 shachaf: It's kind of been on the (tail end of the) potentially-todo list. It's just that currently it has no real way to turn words back to tokens, just the other way around. The Perl script version can specify the initial context already. 21:51:52 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.32533 21:52:23 write a perl to befunge compiler first then? 21:52:30 fizzie: Have you even touched fungot in years? 21:52:31 elliott: are you changing any of the others like event-monitor, though. 21:52:44 2008-08-14.txt:10:36:35: PISS OUT MY ASS 21:52:45 elliott: that file is malloc used 21:52:46 Good fourth statement. 21:53:04 (The babbling internally works in terms of 28-bit integers, and only just before output that list of integers is turned to a string of words.) 21:53:14 2008-08-14.txt:15:09:48: optbot; What do you think of fungot? 21:53:15 elliott: i could implement io monads and make it available via http? i hope not 21:53:18 fizzie: Did you really use "nick;"? 21:53:21 Or maybe 21-bit integers, I forget exactly. 21:53:22 ALSO REMEMBER OPTBOT? I loved optbot. 21:53:26 #esoteric used to be great. 21:53:39 elliott: You know when it stopped being great, right? 21:53:46 what did OPTBOT do? 21:53:52 olsner: OPT 21:53:57 elliott: I think I might have used it. And I also fixed that one bf interp bug, but I suppose that was at least a year ago. 21:53:59 shachaf: OPT!? 21:54:21 `pastelogs optbot 21:54:26 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.20890 21:54:27 ^ignore 21:54:28 ^(EgoBot|HackEgo|toBogE|Sparkbot|optbot|lambdabot|oonbotti|cuttlefish)! 21:54:29 ^ remembers optbot too. 21:54:42 -!- oerjan has quit (Quit: Trackpad wacky). 21:54:51 fizzie: IMO you should remove that in remembrance. 21:55:12 `cat bin/pastelogs 21:55:13 "bonobos are fucking ehird`" 21:55:14 ​#!/bin/sh \ cd /var/irclogs/_esoteric \ \ pasterandom() { \ if [ "$1" -gt 150 ]; then \ echo "No." \ exit \ fi \ for i in $(seq "$1"); do \ file=$(shuf -en 1 ????-??-??.txt) \ echo "$file:$(shuf -n 1 $file)" \ done | paste \ } \ \ if [ "$1" ]; then \ if expr "$1" + 0 >/dev/null 2>&1; then \ pasterandom "$1" \ else \ lines=$(grep -P -i -- "$1" 21:55:24 Hm, I don't remember getting fungot to spam #ubuntu. 21:55:25 elliott: can you put that in /usr/ share/ dict/ words, and it's not not a that have no side effects /me grins grits fnord waits wants wanes waves raves raven) 21:55:27 But apparently I did! 21:55:58 -!- oerjan has joined. 21:56:20 `WELCOME OERJAN 21:56:23 OERJAN: 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.) 21:56:26 THANKS 21:56:28 grins grits fnord waits wants wanes waves raves raven 21:56:42 MY TRACKPAD SEEMS TO WORK AGAIN 21:56:55 JOYFUL TIMES INDEED 21:56:55 oerjan: Remember how optbot stood for Oerjan's Terrible Puns Bot? 21:56:59 When it was otpbot. 21:57:01 But then it became optbot. 21:57:02 i assume it was a cosmic ray 21:57:04 elliott: yes. 21:57:13 oerjan: The Golden Age of #esoteric, right? 21:57:14 `Welcome 21:57:17 right 21:57:18 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: Welcome: not found 21:57:20 and then it was a drama bomb 21:57:31 Phantom_Hoover: That was literally years later when a bunch of stupid people started being in the channel. 21:57:52 oerjan: Kids don't appreciate history nowadays, right? 21:58:07 -- Socrates 21:58:18 oerjan: See? A kid wouldn't know who Socrates is! 21:58:26 (slightly translated from the greek) 21:58:44 Why did you comment Socrates out 21:58:56 It's social "comment"ary. 21:59:08 Why did you decrement Socrates? 21:59:12 -- Freefull is so stupid he cannot read this 21:59:19 16:00:50: It refers to a PENIS, I think. Usually things on IRC do. 21:59:22 fizzie: Thank's. 21:59:37 olsner-- 22:00:01 @karma olsner 22:00:02 olsner has a karma of 1 22:00:03 Whoa. 22:00:07 That needs to be much higher. 22:00:08 olsner++ 22:00:08 olsner++ 22:00:08 olsner++ 22:00:08 olsner++ 22:00:09 olsner++ 22:00:10 olsner++ 22:00:12 olsner++ 22:00:14 olsner++ 22:00:16 olsner++ 22:00:18 olsner++ 22:00:20 @karma 22:00:20 olsner++ 22:00:20 You have a karma of 11 22:00:22 olsner++ 22:00:24 @karma olsner 22:00:24 olsner has a karma of 13 22:00:29 @karma+ olsner 22:00:29 olsner's karma raised to 14. 22:00:31 13 is an unlucky number. 22:00:57 wow! I have karma, now I can do at least 14 evils before I turn officially evil 22:01:05 @karma 22:01:05 You have a karma of 32 22:01:11 @karma elliott 22:01:11 elliott has a karma of 22 22:01:15 @karma dons 22:01:15 dons has a karma of 1 22:01:19 @karma sorear 22:01:19 sorear has a karma of 0 22:01:21 @karma chameleon 22:01:21 chameleon has a karma of 0 22:01:24 @karma larrywall 22:01:24 larrywall has a karma of 0 22:01:29 @karma timtoady 22:01:29 timtoady has a karma of 1 22:01:32 @karma preflex 22:01:32 preflex has a karma of 1 22:01:35 @karma lambdabot 22:01:35 lambdabot has a karma of 7 22:01:36 @karma oerjan 22:01:36 oerjan has a karma of 8 22:01:44 @karma olsnoerjaner 22:01:44 olsnoerjaner has a karma of 0 22:01:49 @karma funpuns 22:01:49 funpuns has a karma of 0 22:01:55 "have", lambdabot. "have". 22:01:56 funpuns++ 22:02:41 oerjan: Wake up monqy, would you? 22:02:44 I have a Linux question. 22:02:52 monqy: WAKE UP 22:03:04 monqy: go to sleep monqy 22:03:08 lambdabot-- 22:03:12 @karma lambdabot 22:03:12 lambdabot has a karma of 6 22:03:16 @karma+ lambdabot 22:03:16 lambdabot's karma raised to 7. 22:03:16 @karma+ lambdabot 22:03:16 lambdabot's karma raised to 8. 22:03:16 @karma+ lambdabot 22:03:16 @karma+ lambdabot 22:03:16 lambdabot's karma raised to 9. 22:03:17 @karma+ lambdabot 22:03:17 lambdabot's karma raised to 10. 22:03:17 @karma+ lambdabot 22:03:17 lambdabot's karma raised to 11. 22:03:18 lambdabot's karma raised to 12. 22:03:18 @karma+ lambdabot 22:03:20 lambdabot's karma raised to 13. 22:03:20 @karma+ lambdabot 22:03:22 elliott: Stop it. 22:03:22 lambdabot's karma raised to 14. 22:03:22 @karma+ lambdabot 22:03:24 lambdabot's karma raised to 15. 22:03:24 @karma+ lambdabot 22:03:25 @ignore + elliott 22:03:26 lambdabot's karma raised to 16. 22:03:26 @karma+ lambdabot 22:03:28 lambdabot's karma raised to 17. 22:03:28 @karma+ lambdabot 22:03:30 lambdabot's karma raised to 18. 22:03:30 @karma+ lambdabot 22:03:32 lambdabot's karma raised to 19. 22:03:32 @karma+ lambdabot 22:03:33 @ignore - elliott 22:03:34 lambdabot's karma raised to 20. 22:03:34 @karma+ lambdabot 22:03:36 lambdabot's karma raised to 21. 22:03:36 @karma+ lambdabot 22:03:38 lambdabot's karma raised to 22. 22:03:38 @admin - elliott 22:03:39 @karma+ lambdabot 22:03:40 lambdabot's karma raised to 23. 22:03:40 @karma+ lambdabot 22:03:41 @ignore + elliott 22:03:42 lambdabot's karma raised to 24. 22:03:42 @karma+ lambdabot 22:03:44 -!- zzo38 has left. 22:03:44 I love lambdabot. 22:03:45 maybe we could raise karma in private messages instead of in the channel? 22:03:46 @admin - shachaf 22:04:00 olsner-- 22:04:02 elliott: What happens in #esoteric ought to stay in #esoteric 22:04:06 elliott-- 22:04:09 You're officially unlucky now, olsner. 22:04:10 Don't lambdabot karmaspam 22:04:13 @karma elliott 22:04:13 Phantom_Hoover++ 22:04:15 @karma olsner 22:04:15 olsner has a karma of 14 22:04:21 shachaf: I was adjusting lambdabot's karma to be correct. 22:04:31 shachaf: Also I once spammed lambdabot in /msg to take down lambdabot's karma from 40-50 or so to 0. 22:04:34 So this is just giving back, see? 22:04:38 I forget why I did that. 22:04:42 @slap elliott 22:04:42 * lambdabot hits elliott with an assortment of kitchen utensils 22:04:42 But I remember having a good reason. 22:04:50 Also, take me off ignore. 22:05:51 shachaf: If you don't take me off lambdabot ignore I'll... I'll reduce your karma!!!!! 22:06:30 oerjan: Remember when HackEgo had a karma system? 22:06:32 `karma oerjan 22:06:34 Maybe it still does. 22:06:37 oerjan has 0 karma. 22:06:44 @ignore - elliott 22:06:46 `cat bin/karma 22:06:49 ​#!/bin/sh \ echo "$1 has $(lib/karma "$1") karma." 22:06:58 @admin + elliott 22:06:59 Not enough privileges 22:07:05 oh, I expected it to just print "$1 has 0 karma" 22:07:08 > putStrLn "I am dissapoint" 22:07:09 22:07:11 olsner: That's a good idea. It should. 22:07:16 > a <- putStrLn "I am dissapoint" 22:07:17 not an expression: `a <- putStrLn "I am dissapoint"' 22:07:20 @admin + elliott 22:07:20 Not enough privileges 22:07:25 shachaf: It's like you don't even care about your karma. 22:07:30 elliott: Don't @admin - me :-( 22:07:31 @karma 22:07:31 You have a karma of 32 22:07:33 > "I am dissapoint" 22:07:34 "I am dissapoint" 22:07:36 @admin + elliott 22:07:46 !rot13 I am disappoint 22:07:47 V nz qvfnccbvag 22:08:46 FreeFull: What are you full of? 22:08:52 * oerjan swats FreeFull for speling -----### 22:08:53 Freedom 22:09:06 FreeFull: Whoa. 22:09:09 FreeFull: Are you American? 22:09:12 No 22:09:17 America isn't actually free 22:09:54 Good point. 22:09:54 it's free for a small fee 22:09:57 So, you're European. 22:10:03 feeful 22:10:31 Jupiterian 22:10:43 Jupiter isn't in Europe, FreeFull. 22:10:57 sausage lovers are the wurst 22:11:13 Europa is around Jupiter though! 22:11:18 elliott: Yes it is? 22:11:21 It's in Romania. 22:12:03 !rot13 cha-cha-cha 22:12:03 pun-pun-pun 22:12:04 https://gist.github.com/3036120 22:12:11 (not mine) 22:12:58 shachaf: Well, uh, Europe is the national anthem of Kosovo. 22:13:08 uh-lliott 22:13:39 kmc: Can you believe Raymond Smullyan was giving a talk in NYC today? 22:18:20 !rot13 Raymond Smullyan 22:18:21 Enlzbaq Fzhyylna 22:27:21 I'm starting to really appreciate the Reader monad, now that I see two different Clojure libraries do different things to essentially support it. 22:27:38 reader monad sux 22:27:44 implicit configurations thru reflection 4 lyfe 22:28:13 -!- hagb4rd has joined. 22:29:35 -!- monqy has joined. 22:29:39 mmmm i forgot how great reflection's api is 22:29:45 oh hey oerjan thanks 22:30:47 monqy: you still use arch right 22:30:57 ye 22:30:57 monqy: You have 12 new messages. '/msg lambdabot @messages' to read them. 22:31:04 you got me,.... 22:31:08 Who doesn't run Arch these days! 22:31:13 Unless you want a stable system or something 22:31:29 monqy: "tricked u" 22:31:32 monqy: but it was actually a legit question 22:31:35 monqy: do you use [testing] 22:31:39 i dont think so 22:31:43 damn 22:31:44 can you check 22:31:46 i need soul guidance 22:31:46 elliott, the usage of Reader monad I'm talking about isn't for configuration, it's more for building up a computation that will receive an argument in the future. 22:31:56 async stuff 22:32:02 Sgeo: well ok 22:32:08 reflection is still the coolest tho 22:32:16 also you can still sort of do that with reflection but whatever 22:33:30 monqy: remember reflection 22:34:13 That was the thingy you did with edwardk, right? 22:34:18 which reflection 22:34:21 That was crazy and shouldn't work but did? 22:34:23 reflection is a big word 22:34:34 class Reifies s a | s -> a where reflect :: proxy s -> a 22:34:35 reify :: a -> (forall s. Reifies s a => Proxy s -> r) -> r 22:34:36 that reflection 22:34:38 is this the kind of reflection they used for the 4-colour theorem 22:34:41 someone's like operating the heavy lawnmowing machinery so im bad at remembering 22:35:08 implicit configurations, oleg, that reflection 22:35:15 yeah i vaugely remember it 22:35:21 it's cool. 22:35:25 i have nothing to say about it, it is just cool 22:35:42 if i made a language it'd support reflection without the zany implementation hacks!! 22:36:16 monqy: (/etc/pacman.conf will have an uncommented [testing] block if you use it) 22:36:34 its commented out 22:36:39 is testing good 22:36:43 well, 22:36:48 [testing] has ghc 7.6.1 22:36:51 elliott, is it the kind of reflection they used for the 4-colour theorem in coq 22:37:00 monqy: but it's an all-or-nothing thing you have to take all the possible unstability with it!!! 22:37:02 instability 22:37:04 What's it used for? 22:37:07 monqy: so im trying to decide between 22:37:14 My brain needs a break from thinking 22:37:15 using my /opt/ghc with the binary package of 7.6.1 22:37:17 or just enabling [testing] 22:37:19 atriq, proving the 4-colour theorem, presumably 22:37:25 elliott: im bad at decisions yw 22:37:29 Phantom_Hoover: i doubt it is that kind of reflection 22:37:32 monqy: help 22:37:45 monqy: i was hoping you'd go "oh yeah i totally use reflection" 22:37:45 elliott: yw 22:37:46 elliott, idk, curry-howard and all that 22:37:54 er 22:37:56 monqy: i was hoping you'd go "oh yeah i totally use testing" 22:37:58 monqy: "for my packages" 22:38:01 monqy: "life on the edge with monqy" 22:39:19 elliott, I'm reading the pdf associated with reflection 22:39:26 And it sounds vaguely familiar 22:39:30 As though I've read it before 22:39:41 atriq: the pdf's implementation is quite bad btw 22:39:46 reflection has a simpler but less portable one 22:39:50 and a simplified version of the paper's 22:39:53 as a fallback 22:39:55 I'm trying to work out what it's meant to be implementing 22:39:57 (though it depends on 8-byte pointers) 22:43:02 Hmm 22:43:06 It doesn't like :T 22:43:14 By which I mean ":t" 22:43:33 atriq: what do you mean 22:43:46 Prelude Data.Reflection> :t reify 12 (\p -> reflect p + reflect p) 22:43:46 :1:7: 22:43:46 No instance for (Num a) 22:43:46 arising from the literal `12' 22:43:46 In the first argument of `reify', namely `12' 22:43:46 In the expression: reify 12 (\ p -> reflect p + reflect p) 22:43:48 Prelude Data.Reflection> reify 12 (\p -> reflect p + reflect p) 22:43:50 24 22:43:59 > 24 - 42 22:44:00 -18 22:44:04 -!- zzo38 has joined. 22:44:20 Oh, I think it's the monomorphism restriction or something attacking me again 22:44:46 atriq: Try reify (12 :: Integer) (\p -> reflect p + reflect p). 22:45:00 Works dine 22:45:02 *fine 22:45:02 It's actually defaulting and fundeps and stuff. 22:45:06 I need sleep 22:45:21 NES/Famicom PPU has a restriction although tiles are 8x8 pixels, attributes are 16x16 pixels (2x2 tiles) so I thought of idea, making up a puzzle game based on this, if you push objects together in a 2x2 area with colors from different palettes, the objects will not move..... 22:46:22 Do you like that idea? 22:46:37 It sounds interesting 22:49:27 atriq: I think :t reify (12 :: Integer) should also work. 22:49:51 It does... 22:51:10 I thought of putting a border around each 2x2 area,but then you would also need four tiles in the pattern table for each possible piece in the game, unless something can be done with sprite 0 hit to switch pattern tables so you only need two tiles in each pattern table for each possible piece, but I don't know if you can modify the sprites during rendering 22:51:46 I've never tried to make NES games, so I wouldn't know 22:51:47 Another idea would be to use the sprite overflow flag somehow 22:51:49 And goodnight 22:51:50 -!- atriq has quit (Quit: Leaving). 23:03:53 -!- Vorpal has quit (Ping timeout: 245 seconds). 23:13:57 monqy: i'm scared of [testing] 23:14:04 me too 23:14:07 monqy: but i really want to recompile my xmonad :( 23:14:15 monqy: right now im just relying on the one i compiled with old ghc.......... 23:14:18 i don't even have an xmonad(1) 23:14:33 i just modified my xinitrc to run ~/.xmonad/xmonad-x86_64-linux 23:14:54 yikes 23:16:59 if i press mod-q i get an error message saying it can't find xmonad in $PATH 23:19:29 Why don't you symlink that to somewhere that is in $PATH 23:19:53 well it wouldn't work 23:19:56 it needs ghc for mod+q to work 23:37:08 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 23:39:23 oerjan: Realtime Solitaire 23:40:30 oerjan: Realtime Solitaire 2.0 23:40:43 oerjan: Realtime Solitaire 3.0 23:40:57 Sense the patterns to unlock New Real Realtime Solitaire 4.0 23:58:56 area man constantly telling everyone he doesn't have an xmonad(1) 2012-10-06: 00:01:11 area man kmc 00:02:34 is that an advice animal or something 00:02:59 the dangerous new trend putting teens at risk 00:08:16 -!- FreeFull has quit (Ping timeout: 252 seconds). 00:15:51 elliott: i like solitaire kind of games precisely because they're _not_ realtime, thankyouverymuch 00:17:24 oerjan: There's sometimes a clock. 00:17:30 (For scoring.) 00:17:34 blasphemy! 00:18:00 oerjan: Faketime Solitaire 00:18:54 oerjan: THE AXIOMS OF SOLITAIRE: 1. Solitaire 00:18:59 2. Sloitaire 00:19:05 4. Slaloterre 00:19:12 5. French-German Solitaire Spanish English Happening Manual 00:19:41 siilotare 00:20:28 Well you know oerjan Finnish Solitaire is banned for a reason 00:20:56 Facetime Solitaire. (Also called 'a mirror'.) 00:20:57 they're too solitary already 00:21:32 esiltoria 00:21:45 FINNISH SOLITAIRE aka "The Hidden Death". 00:21:54 Finnish Solitaire has killed millions since its founding in 1964. 00:22:24 `? funpuns 00:22:28 funpuns? ¯\(°_o)/¯ 00:22:29 `? shachaf 00:22:32 shachaf sprø som selleri 00:22:35 What? 00:23:42 twah 00:24:38 o⃥rjan 00:26:41 `? shachaf 00:26:45 shachaf sprø som selleri 00:39:21 -!- augur has quit (Ping timeout: 256 seconds). 00:40:24 -!- augur has joined. 00:41:36 -!- Nisstyre-laptop has joined. 00:44:40 -!- Phantom_Hoover has joined. 00:57:45 -!- mds2 has joined. 01:01:35 -!- mds2 has left ("ERC Version 5.3 (IRC client for Emacs)"). 01:06:31 -!- copumpkin has quit (Ping timeout: 244 seconds). 01:07:07 -!- pumpkin has joined. 01:25:33 -!- Sgeo has quit (Ping timeout: 245 seconds). 01:28:29 -!- Sgeo has joined. 01:29:43 -!- Frooxius has quit (Ping timeout: 245 seconds). 01:41:51 A lot of the OEM crapware on this computer broke 01:42:06 But there's one that... well, I think the important part is actually in hardware, so it doesn't really matter 01:46:00 -!- variable has joined. 01:46:15 -!- invariable has joined. 01:46:22 -!- variable has quit (Remote host closed the connection). 01:46:38 -!- invariable has changed nick to Guest37703. 01:53:30 ARMv2 seems OK, not as complicated as newer versions, and there does exist the open-source Amber core which is ARMv2. How fast could it run? Does anyone sell ARMv2 at fast speeds? 01:55:52 Has Amber been tested for compatibility with a real ARMv2? 01:56:07 -!- aloril_ has quit (Ping timeout: 244 seconds). 01:58:54 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 02:05:54 Huh. 02:06:06 Minesweeper contests don't accept the official version of Minesweeper 02:06:28 wut 02:06:28 Is there something wrong with the official version? 02:07:01 zzo38, yes 02:07:11 http://www.minesweeper.info/wiki/Board_Cycles 02:08:40 -!- aloril_ has joined. 02:08:45 Winmine (the name of the official version) uses a smaller than theoretically possible number of boards, iiuc 02:09:40 OK now I can see what is wrong, and why the official version should be unacceptable. 02:10:20 http://www.minesweeper.info/wiki/Winmine_Congress 02:10:41 The Winmine Congress was established in response to controversy over the Dreamboard and Board Cycles. Seven members were elected to resolve these problems. Founded 31 Oct 2002, it dissolved 8 Mar 2004. It has since been superceded by the International Minesweeper Committee. 02:14:53 6 years of research to figure out how minesweeper generates boards? 02:58:43 -!- oerjan has quit (Quit: Good night). 03:02:18 One thing I do know about the Windows Minesweeper (because I have tried it and figured it out) is, if the square you click first has a bomb, the bomb will be moved elsewhere. 03:02:59 thanks winmine 03:03:41 winmine.exe 03:03:52 zzo38: How do you know? 03:03:57 Maybe you were just extremely lucky. 03:06:05 -!- Guest37703 has quit (Changing host). 03:06:06 -!- Guest37703 has joined. 03:06:10 -!- Guest37703 has changed nick to const. 03:09:29 -!- const has left. 03:21:54 -!- hagb4rd has quit (Ping timeout: 246 seconds). 03:32:27 shachaf: I tried it many times, and I used the cheat code, which sets the top-left pixel of the screen black if there is a bomb there, so I figured out 03:32:45 Oh, the cheat code. 03:32:48 xyzzy something 03:32:50 shift-enter 03:33:16 That's been documented 03:39:41 -!- Nisstyre-laptop has quit (Quit: Leaving). 03:42:41 -!- Nisstyre-laptop has joined. 03:44:59 -!- Nisstyre-laptop has quit (Remote host closed the connection). 04:23:40 -!- Nisstyre-laptop has joined. 04:34:06 -!- TodPunk has quit (Read error: Connection reset by peer). 04:34:18 -!- TodPunk has joined. 04:38:21 -!- elliott has quit (Remote host closed the connection). 05:13:01 -!- rodgort` has quit (Ping timeout: 246 seconds). 05:15:49 -!- rodgort has joined. 05:23:05 -!- Nisstyre-laptop has quit (Remote host closed the connection). 05:25:13 -!- Nisstyre-laptop has joined. 05:36:55 xsetroot -solid pink -cursor_name gumby 05:39:56 I think the DotFami mapper codes actually form a idempotent commutative monoid, rather than just being a monoid. 06:04:07 Does the order of the commands matter in a hardware description language such as Verilog or VHDL? Does it matter if you repeat a command? 06:37:55 -!- ogrom has joined. 06:45:13 I sent some file to Famicompo Mini vol.9 see if it work 06:54:15 the minesweeper wiki is somewhat incredible given what a silly game it is. it's the best game ofc but pretty damn silly nevertheless. 06:54:59 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 07:17:09 -!- Vorpal has joined. 07:21:38 Do you know of any NES/Famicom emulator which includes net play but also has a mode to display only odd frames on one computer and only even frames on other? 07:26:23 It's NP complete. oklopol! It's almost as interesting as sudoku! 07:31:46 If you add a successor operator to Hofstadter's BlooP and/or FlooP programming languages, you can do without IF, QUIT BLOCK, addition/multiplication operators, and comparison operators. 07:49:55 In 2001, the Italian "International Campaign to Ban Winmine" voiced strong concern over the game, contending that it is an "offense against the victims of the mines" and those who risk their lives to clear them. 07:49:58 xD 07:51:11 i love how some people are like so stupid that you wish they were less stupid because their stupidity is so overwhelming that it's be equally funny to watch if it was reduced but they wouldn't be as stupid. 07:52:20 on the other hand i suppose that may have just been a well-executed joke 07:53:59 Jafet: sudoku, like minesweeper, is fun only if your speed-solving simple games. the difference is minesweeper games are always easy but there are a lot of clicks to be made. a simple sudoku takes like 5 seconds so bleh. 07:54:38 hard sudoku puzzles are just annoying, there's too much data so a simpleton like me cannot really extract a meaningful mathematical problem, or at least expect it to have an interesting solution. 07:55:24 i have yet to see a meaningful minesweeper puzzle that isn't just an obvious encoding of another type of problem, and no problems arise naturally in random minefields. 07:55:35 *you're 07:57:13 you very quickly learn to check in about 10 seconds whether there are solvable cells on the "advanced" board, and this can easily be kept in memory so actually you never have to stop to think. 07:57:42 (i mean kept in memory and updated as you go) 08:00:30 " Do you know of any NES/Famicom emulator which includes net play but also has a mode to display only odd frames on one computer and only even frames on other?" ...what 08:01:50 oklopol: What about what? 08:02:33 why would there be such a mode 08:03:25 I think it might be useful for some things 08:05:25 I think it might be not useful for some things but it might be useful for some other things. 08:06:11 Yes, OK 08:07:29 can you tell me some things for which it would be useful to have a NES/Famicom emulator which includes net play but also has a mode to display only odd frams on one computer and only even frames on other? 08:07:42 *frames 08:11:21 -!- monqy has quit (Quit: hello). 08:11:49 Such as multiplayers games with separate screens. It could be done on a TV screen as well; it does not have to be only on the emulator. 08:12:13 hmm right 08:12:17 i guess that's a fun hack 08:13:11 The similar thing can also be used for stereovision. 08:47:37 -!- zzo38 has quit (Remote host closed the connection). 09:02:19 -!- FreeFull has joined. 09:40:31 -!- hagb4rd has joined. 10:11:06 -!- Phantom_Hoover has joined. 10:40:26 -!- carado has joined. 10:43:03 -!- DHeadshot has quit (Ping timeout: 245 seconds). 11:08:52 -!- barts_ has joined. 11:11:54 -!- barts has quit (Ping timeout: 240 seconds). 11:21:03 -!- ogrom has quit (Quit: Left). 11:43:32 -!- carado has quit (Quit: Leaving). 11:53:05 -!- Arc_Koen has joined. 11:53:45 hello 11:53:46 Arc_Koen: You have 1 new message. '/msg lambdabot @messages' to read it. 11:53:49 @messages 11:53:50 oerjan said 16h 48m 36s ago: Stupid me, I left the <>'s around your nick when pasting into @tell... 11:55:06 -!- carado has joined. 12:40:06 -!- ogrom has joined. 12:49:23 -!- atriq has joined. 12:50:44 -!- pumpkin has changed nick to copumpkin. 13:01:17 -!- carado has quit (Quit: Leaving). 13:01:28 @messages? 13:01:28 Sorry, no messages today. 13:01:31 Yay! 13:12:51 -!- ogrom has quit (Quit: Left). 13:14:44 -!- atriq has quit (Ping timeout: 246 seconds). 13:18:18 -!- aloril_ has quit (Ping timeout: 276 seconds). 13:19:54 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 13:30:52 -!- aloril_ has joined. 13:43:59 -!- Phantom_Hoover has joined. 13:47:22 -!- kinoSi has quit (Read error: Connection reset by peer). 13:47:49 -!- kinoSi has joined. 14:02:50 -!- sivoais has quit (Read error: Connection reset by peer). 14:03:33 -!- sivoais has joined. 14:09:05 "After these deadly results, British intelligence leaked falsified information implying that the rockets were over-shooting their London target by 10 to 20 miles. This tactic worked and for the remainder of the war most landed in Kent due to erroneous recalibration.[37] 14:09:05 " -- [[V-2] 14:09:08 *]] 14:09:27 competent nazis 14:11:16 I like that story :) they trusted the double agents more than their (correct) radio location thingy 14:11:38 also apparently the v-2 programme cost more than the manhattan project 14:12:07 rockets = hard, throwing plutinium together = easy 14:12:33 silly olsner 14:12:43 gun-type assemblies don't work with plutonium 14:13:29 I think they're all based on some kind of throwing together of stuff, doesn't have to be gun-type 14:14:10 implosion assemblies are more about squeezing 14:15:44 I saw a ted talk about the norden bombsight a while ago, iirc it cost about half of the manhattan project 14:30:59 -!- oerjan has joined. 14:32:13 atriq: why are you happy when you have no messages? 14:34:33 @tell I think the DotFami mapper codes actually form a idempotent commutative monoid, rather than just being a monoid. <-- i think an idempotent commutative monoid may the same as a semilattice 14:34:33 Consider it noted. 14:34:37 argh 14:34:50 @tell zzo38 I think the DotFami mapper codes actually form a idempotent commutative monoid, rather than just being a monoid. <-- i think an idempotent commutative monoid may the same as a semilattice 14:34:50 Consider it noted. 14:35:16 `pastelogs oerjan_?> [@]tell < 14:35:24 -!- atriq has joined. 14:35:55 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.23392 14:35:56 @tell zzo38 *may be 14:35:56 Consider it noted. 14:36:23 `pastelogs oerjan_?> [@]tell < 14:36:33 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.21919 14:36:41 oerjan: It keeps happening. 14:38:22 what, the @tell < or HackEgo not working properly? 14:38:50 @tell zzo38 Does the Haskell compiler know that equality is reflexive? <-- it actually isn't, for Double (NaN) 14:38:50 Consider it noted. 14:39:30 i hope zzo38 doesn't get confused by me resending answers from back in january 14:39:35 oerjan: Both. 14:39:45 -!- atriq has quit (Ping timeout: 244 seconds). 14:39:49 there were only those three, however. 14:40:11 oerjan: But if you only take into account the seconds when they sent, that's like one every second. 14:40:24 DEEP 14:43:52 @src Monoid 14:43:52 class Monoid a where 14:43:52 mempty :: a 14:43:52 mappend :: a -> a -> a 14:43:52 mconcat :: [a] -> a 14:44:00 @tell zzo38 Actually, a it's a semilattice with a bottom element (the mempty). 14:44:00 Consider it noted. 14:44:15 @tell zzo38 *-a 14:44:15 Consider it noted. 14:46:35 @tell zzo38 From wikipedia: "A bounded semilattice is an idempotent commutative monoid." 14:46:35 Consider it noted. 14:49:42 -!- elliott has joined. 14:49:48 fizzie: Hey, you use the console sometimes, right? 14:50:08 a master of consolation 14:50:53 Not so often these days. And I'm making foods at the moment. 14:51:05 a master of cuisine too! 14:51:22 fizzie: Man, you and your foods. 14:51:34 People DIE if food is not made. 14:51:42 Or so they say, anyway. 14:51:48 fizzie: Yeah well, I'll die if my console remains unable to display Unicode characters!!! 14:51:53 Think about ME for a change, fizzie. 14:52:31 unicode characters are a vital part of elliott's immortality scheme 14:53:09 wait, wasn't i also supposed to eat -> 14:53:53 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 14:53:55 From what I recall from the days I actually used it, it's relatively easy to make it use UTF-8, but there seemed to be some kind of an issue fitting more than about 512 characters in a font. 14:54:11 fizzie: Weeeell, I'm using Terminus. 14:54:20 "ter-u20n". I assume the u is for Unicode??? 14:54:32 Anyway the fancy e in "caf[fancy e]" is just displaying as a square on the console. 14:54:48 There's this keymap option like "FONT_MAP=8859-2" that apparently you're meant to set appropriately for the font. 14:54:53 But I don't know what it's supposed to be for this one. 14:55:08 Alternatively maybe I am using the wrong Terminus?? 14:55:13 There are also a bunch with three digits and no "u". 14:55:21 Is that just the accented e? I'd think that'd be in the console selection. 14:55:28 Yes, the accented one. 14:55:31 The fancy French e. 14:55:55 Maybe I want, e.g. ter-120n. 14:55:56 -!- carado has joined. 14:56:00 Or ter-220n. 14:56:06 Or ter-520n. 14:56:13 Who even knows what these numbers and letters are??? 14:56:24 I guess there might be documentation somewhere? 14:57:16 ter-2* iso02, cp1250 ISO8859-2, Windows-1250 14:57:19 ter-u* koi8u KOI8-U 14:57:28 It doesn't seem to be the 'u' you want. 14:57:33 ter-1* iso01, iso15, cp1252 ISO8859-1, ISO8859-15, Windows-1252 14:58:00 That one is borderline reasonable. 14:58:02 ter-v* all listed above all listed above and many others (about 110 and many others language sets), 8 foreground colors 14:58:24 That one sounds funny, I wonder how it works. 14:59:29 It also claims the PSF has the "Unicode data"; I vaguely indeed recall that was a thing. 14:59:42 That, and a console set to UTF-8 mode, should mean the code page doesn't actually matter. 14:59:56 Though I suppose the koi8u version wouldn't necessarily have an accented e. 15:01:37 fizzie: So, er, which prefix of 12579cdfgkpux do I want? 15:02:55 -!- ogrom has joined. 15:04:16 I think '1' is like the most general-purposey, unless you have that 'v' thing and it works. 15:04:45 fizzie: I don't appear to have a v thing. :( 15:05:08 It also claims the PSF has the "Unicode data"; I vaguely indeed recall that was a thing. That, and a console set to UTF-8 mode, should mean the code page doesn't actually matter. 15:05:13 So, er, does that mean I can't use this or something? 15:05:15 (Is that the v thing?) 15:06:22 No, I just mean you shouldn't necessarily need to tell the thing about the code page, if it's using UTF-8 and has the Unicode code points in the PSF, since it'd pick characters using the code points. And I understood that applied to all the PSF versions, not just the mysterious v. 15:07:07 fizzie: So if I pick the 1 thing I should get the full Unicode coverage? I mean, as full as Terminus has to start with (e.g. in X). 15:07:18 Or is the character set still limited? 15:07:42 Well, it would be limited to 512 characters in any case, as far as I know. 15:07:52 how did you end up having to choose variants of terminus? 15:07:52 Ah. :( 15:08:04 olsner: Well, you know, Linux console. 15:08:08 iirc, I just installed it and since then it works 15:08:23 On the other hand, Terminus' README says it has 879 characters in total, so 512 is not a lot less. 15:08:38 I don't know whether the '1' variant only has the code pages it mentions or what, though. 15:08:58 There are tools to dump a list of characters in a PSF file, you could check with one. 15:09:08 I think I'll just live in ignorance. 15:09:17 I have no idea how systemd vconsole things are used to configure fonts, anyway. Back when I fiddled with these I just had the consoletools package. 15:09:18 but otoh, I don't use the linux console so I wouldn't notice if that part is completely broken 15:09:49 fizzie: Wait, when did I say anything about vconsole? 15:10:11 elliott: The hits for "FONT_MAP" said things about it. I suppose it could be something else. 15:10:21 It's kind of a generic-sounding term. 15:10:28 Oh, right. 15:10:44 fizzie: Well, I'm just migrating my Arch system from rc.conf to this vconsole.conf thing, but I happened to set Terminus as my console font at the same time. 15:11:01 fizzie: I'm not actually using systemd, but they're deprecating most of rc.conf and telling you to move settings to all these little files to prepare for switching over to systemd. 15:12:28 There's something called "FONT_UNIMAP" too, apparently. But from what I recall, in UTF-8 mode -- which is certainly the only reasonable mode these days -- the mappings weren't really relevant. 15:12:59 fizzie: Also, uh, wish me luck in upgrading to GRUB2. 15:13:07 Sort of scared. 15:13:16 Good luck. It went well for me. 15:13:25 Mature and well-tested technology and all that. 15:13:56 :: grub-common and grub are in conflict. Remove grub? [y/N] y 15:13:57 RIP 15:14:22 Anyway as long as you can boot from something external maybe things won't become too unfixable. I had that one laptop that couldn't boot from anything else than the internal HD, fiddling with its boot setup was always so tense. 15:14:23 Usually the post-MBR gap (after the 512 byte MBR region and before the start of the 1st partition) in many MBR (or msdos disklabel) partitioned systems is 31 KiB when DOS compatibility cylinder alignment issues are satisfied in the partition table. However a post-MBR gap of about 1 to 2 MiB is recommended to provide sufficient room for embedding GRUB2's core.img (FS#24103). It is advisable to use a partitioner which supports 1 MiB partition align 15:14:23 ment to obtain this space as well as satisfy other non-512 byte sector issues (which are unrelated to embedding of core.img). 15:14:23 If you do not dual-boot with MS Windows (any version) in BIOS systems, it is advisable to switch to GPT partitioning - GUID_Partition_Table#Convert_from_MBR_to_GPT 15:14:25 Um. 15:14:33 fizzie: Do I need to understand all this? 15:14:53 Also is it really telling me to switch from MBR to GPT on a regular system? That sounds sort of like a bad idea. 15:15:04 Maybe they want to be futuristic. 15:15:09 I mean, lots of things don't even support GPT, do they?? 15:15:15 They want you to do UEFI too :P 15:15:27 You don't exactly need "lots of things" to support it do you 15:15:34 Your hardware, bootloader and kernel mostly. 15:15:42 Hardware being the hard part (no pun intended) 15:15:54 Well, no, but it sounds like it'd be an awful pain if I ever, e.g., wanted to install an OS that has no clue what GPT is. 15:15:55 I couldn't be bothered with GPT 15:16:07 What kind of OS doesn't even support GPT these days 15:16:17 why the heck did they EVICT my favorite restaurant? 15:16:19 But anyway I guess I shouldn't be surprised that Arch advice is putting bleeding-edge high-techness over practicality.. 15:16:20 The mentioned MS Windows in BIOS systems maybe. :p 15:16:21 * oerjan screams 15:16:51 *hell 15:17:02 oerjan: you probably didn't eat there often enough 15:17:10 olsner: almost every day :( 15:17:13 They probably had rats in the food. 15:17:16 wait, what is "hell" replacing there 15:17:23 elliott: heck 15:17:28 oh 15:17:36 oerjan: don't they usually give notice of these kinds of things 15:17:38 "they" 15:17:42 oerjan: maybe they got evicted for letting people like you in 15:18:20 elliott: well yes, i've known it for a few months, but two days ago they actually closed :( 15:18:43 :( 15:19:08 [[ 15:19:08 There are 3 ways to install GRUB(2) boot files in BIOS booting: 15:19:09 #Install_to_440-byte_MBR_boot_code_region (recommended) , 15:19:09 #Install_to_Partition_or_Partitionless_Disk (not recommended), 15:19:09 #Generate_core.img_alone (safest method, but requires another BIOS bootloader like grub-legacy or syslinux to be installed to chainload /boot/grub/i386-pc/core.img). 15:19:10 ]] 15:19:18 fizzie: Sometimes I think about switching back to Debian. 15:19:48 nice, installing grub to boot grub is a recommended solution 15:20:06 if you interpret "safest method" as a recommendation 15:20:34 One of them is explicitly flagged as "recommended", I think that's the... recommended one. 15:20:47 Oh wow, "sudo grub-install --target=i386-pc --recheck --debug /dev/sda" produces a lot of output. 15:21:20 Debian's GRUB 2 installer initially did that #3 and configured the existing GRUB <2 to chainload the core.img; then when you had booted a couple of time and were certain it works, you were meant to call a script that actually put the GRUB 2 in the MBR. 15:21:38 That's sily. 15:22:52 fizzie: Okay I think it is done??? Let's try 15:23:01 And that was the last we heard of him. 15:23:35 -!- elliott has quit (Remote host closed the connection). 15:23:50 fizzie: they got impeccable marks on all the recent hygiene controls. (in trondheim they have to put the result form visible in the restaurant.) 15:24:29 no, i am going to believe it was pure greed by the landowner. (they're being replaced by a pharmacy.) 15:24:35 oerjan: Ooh, they should do that here too. Does it have to be "prominently visible" or something? 15:24:41 Like, neon lights and signs. 15:24:42 fizzie: yeah 15:24:50 well, not neon lights :P 15:25:07 -!- elliott has joined. 15:25:24 The local IKEA's restaurant has a diploma on the wall about how they do "organic" things. 15:25:44 So, um, it works, but it runs in a really really freaky resolution. 15:26:05 Like, it is stretching a 4:3 (but larger than the "plain old BIOS text") resolution to my widescreen... screen. 15:26:08 Oh, and some gas station in Norway where we stopped had a whole wall full of all kinds of yellowed diplomas about marketing seminars from 1989 or whatever. 15:26:15 Is there any hope of getting it the same resolution as my Linux console? 15:26:19 Or is that too fancy to ask of a bootloader. 15:26:23 (1336x768 or something.) 15:26:53 They at least used to be somewhat limited to modes listed by the BIOS in question. 15:27:09 Yes, but this is GRUB2. It's so fancy, and the future. 15:27:43 Visual Configuration 15:27:43 In GRUB2 it is possible, by default, to change the look of the menu. Make sure to initialize, if not done already, GRUB2 graphical terminal, gfxterm, with proper video mode, gfxmode, in GRUB2. This can be seen in the section #Correct_GRUB2_No_Suitable_Mode_Found_Error. This video mode is passed by GRUB2 to the linux kernel via 'gfxpayload' so any visual configurations need this mode in order to be in effect. 15:27:43 Setting the framebuffer resolution 15:27:43 GRUB2 can set the framebuffer for both GRUB2 itself and the kernel. The old vga= way is deprecated. The preferred method is editing /etc/default/grub as the following sample: 15:27:46 GRUB_GFXMODE=1024x768x32 15:27:48 GRUB_GFXPAYLOAD_LINUX=keep 15:27:50 fizzie: See? This looks super fancy. 15:27:53 "The VESA widescreen resolutions are not standardized, and I have never once been able to get one working from Grub2. I have heard it's possible, if using an Intel GFX chip and some semi-complicated VESA soft-patching", says some guy. 15:28:01 "You can choose one of these resolutions: 640×480, 800×600, 1024×768, 1280×1024, 1600×1200, 1920×1200" 15:28:05 None of those are the right resolution. :( 15:28:10 fizzie: Well I am using an Intel chip. 15:28:24 "Some times for Intel graphic adapters neither # hwinfo --framebuffer nor vbeinfo will show you the desired resolution. In this case you can use 915resolution hack. This hack will temporarily modify video BIOS and add needed resolution. See 915resolution's home page" 15:28:31 fizzie: Maybe I can use this to enable the true resolution?? 15:28:43 You can certainly *try*. 15:29:01 It's of course even possible your VESA BIOS has the widescreen resolution modes listed directly. 15:29:17 In which case I suppose just stating the mode should work. 15:29:24 fizzie: If this breaks horribly how will I boot things??? I don't even know wher my External Bootable USB Medium(TM) is. 15:29:34 Do you think grub has some kind of fallback if you specify an invalid resolution. 15:30:02 If you have it doing the right thing unattended, you can just touch nothing if it's messed up. 15:30:28 Right. Hokay then. 15:30:41 And anyway I suppose if the BIOS call to switch modes says "I don't like this" it's likely to just keep whatever resolution it was, or choose some "safe" default. 15:30:47 fizzie: Maybe I should install coreboot so I can get my BIOS to use the right resolution too!!! 15:30:50 I assume it supports fancy things like that. 15:31:11 # note that you can use only modes which your graphic card supports via VBE 15:31:12 # you can see them in real GRUB with the command `vbeinfo' 15:31:14 I guess I could try this also. 15:31:22 -!- Nisstyre-laptop has joined. 15:31:28 That's true, you could try that. 15:31:34 But I won't! 15:31:40 -!- elliott has quit (Remote host closed the connection). 15:33:04 now, last time we heard from him for _real_! 15:34:57 obviously *this* time he's really gone 15:35:07 yeah. 15:38:28 -!- elliott has joined. 15:38:35 Okay, since that's the case, those onions aren't going to dice themselves. -> 15:38:35 Intel chipset detected. However, 915resolution was unable to determine the chipset type. 15:38:39 :'( 15:38:40 Oh, dangnabbits. 15:38:41 darn, null hypothesis failed again! 15:38:50 Well, the onions still won't. 15:38:51 Well, I mean, you can go do whatever. But I might cry. 15:40:06 isn't it more likely that fizzie will cry, given the task at hand? 15:40:14 elliott: due to the onions? the onions are in finland 15:40:34 fizzie: I bet you're here. 15:40:46 [[ 15:40:46 Next, our purpose is to overwrite mode 30. (You can choose what ever mode you want.) In the file /etc/grub.d/00_header just before the set gfxmode=${GRUB_GFXMODE} line insert: 15:40:47 915resolution 30 1440 900 15:40:47 ]] 15:40:48 the hexham onion chop of 2012 15:40:50 Does it matter which mode you pick??? 15:40:52 Could something bad happen. 15:41:04 staffed entirely by finns 15:41:06 more famous last words 15:49:00 isn't it great how all of Linux functionality is reimplemented from scratch in GRUB just so you can use it for two seconds before you boot Linux? 15:49:34 GNOME for GRUB™ 15:49:58 * shachaf off to Seattle soon. 15:50:01 yeah, DON'T YOU JUST LOVE how modern operating systems require other operating systems to boot? 15:50:06 kmc: I don't like bootloaders. 15:50:17 elliott: Let me guess, @'s bootloader is @? 15:50:23 shachaf: Yes. :( 15:50:29 olsner: It's not really an operating system when all it can do is boot a kernel 15:50:36 grub can do more than that. 15:50:38 @s all the way down 15:50:38 Maybe you meant: shootout show slap smack source spell spell-all src . ? @ v 15:50:40 I think it even has a game of some kind. 15:50:48 COMMERCIAL AT 15:50:53 That's @'s full nam, right? 15:50:57 But seriously, if you have any kind of complexity in terms of reading files -- like say, encryption, LVM-type stuff, or whatever -- then your bootloader inevitably becomes more and more like your OS. 15:51:13 And eventually you've just rewritten your OS except weirder and with less functionality, except that this time it also has a boot sector. 15:51:23 FreeFull: just because all you use it for is booting another kernel, that doesn't mean it's not an OS 15:51:24 Yuck. 15:52:40 and it's not true that GRUB can only boot a kernel 15:52:47 doesn't GRUB2 have a turing complete scripting language 15:52:51 and filesystem read/write 15:52:53 and network capability 15:52:59 someone should write a webserver for GRUB2 15:52:59 When life gives you onions, make onionade. Okay, gone again. 15:53:13 so that you can log into the machine you just booted and select the kernel through an AJAXy web interface 15:53:16 just because 15:53:20 (bbl) 15:53:33 grub2 comes with a shell that can actually do stuff, that makes it really clear that it's an OS 15:55:03 -!- atriq has joined. 15:55:15 -!- elliott has quit (Remote host closed the connection). 15:55:21 GRUB2 is *definitely* an OS. 15:55:28 I use syslinux 15:55:29 Perhaps a relatively light-weight OS, but even so. 15:55:37 FreeFull: And that's not an OS. :) 15:55:47 I use 3D glasses 15:55:54 syslinux isn't (afaik), but DOS is an OS 15:56:06 I don't use DOS though 15:56:20 syslinux is essentially DOS's bootloading scheme adapted to Linux. 15:56:53 isn't syslinux an actual DOS application? 15:57:29 olsner: Though it might work on DOS, syslinux is the FAT bootloader, done in normal FAT bootloader style. 15:57:49 It also refers to the class of similar bootloaders, including isolinux and extlinux... 15:58:05 loadlin is the DOS program. 15:58:05 A part of syslinux can be used to boot linux from DOS, but you don't need dos to boot using syslinux 15:58:25 oh, ok 15:58:30 Uh, syslinux doesn't have loadlin I don't think? 15:58:35 I have the normal MBR -> second stage -> linux setup 15:58:41 Without a separate boot partition 15:59:46 Well. I guess syslinux itself almost counts as an OS. Because it can bootload COM files too. 16:00:03 Or "COM32" files. 16:00:11 (which is exactly what it sounds like) 16:00:20 pikhq_: com files are plain x86 code 16:00:23 No header or anything 16:00:34 I am very well aware. 16:00:49 Kernels are x86 code too =P 16:00:56 So I heard you like bootloaders 16:01:09 FreeFull: By that notion DOS is a bootloader. 16:01:27 Well, DOS does more than just loading executables 16:01:41 It provides an API for doing stuff 16:01:58 So does syslinux. 16:02:28 -!- jix has quit (Remote host closed the connection). 16:02:35 A very, very limited subset of DOS and a couple things handy for adding functionality to the boot process. 16:03:35 The difference is that DOS by default asks the user what to do, while syslinux by default follows the configuration =P 16:04:09 Cannot find /dev/sda1. Abort, retry, fail? 16:04:10 Also, 16:04:21 Also, I don't know if it's possible to go back to syslinux once the com32 file is done 16:04:56 It's an operating system with continuation passing, duh 16:10:07 -!- elliott has joined. 16:10:48 fizzie: Do you know how to change the Linux console cursor? 16:10:51 By the way, don't forget the third copy of a subset of an operating system that needs to be implemented in the firmware. 16:10:53 Like, pre-shell-opening. 16:11:08 I know you can put some funny escape codes in your bashrc or whatever, but that doesn't help for the login prompt and whatnot. 16:11:11 VITALLY IMPORTANT THINGS. 16:14:18 Does anyone know where I can get help with a problem with Ubuntu Unity without people telling me that Unity sucks? 16:14:28 Unity sucks. 16:14:48 atriq: not here, apparently 16:15:00 Evidently 16:15:09 Obviously 16:16:25 atriq: Try http://askubuntu.com/. 16:16:47 I don't exactly know how to elucidate my problem 16:17:05 it's not working? stop using it, problem solved. 16:17:10 atriq: Well, that's a problem. 16:17:21 atriq: You could ask for help on http://english.stackexchange.com/! 16:18:54 Do you know how to take a screenshot with the mouse cursor displayed? 16:19:26 Uhh, not really. I think it's possible, though. 16:19:28 I think scrot can do it. 16:19:38 Once settled in, ferrets quickly establish their territory and set the house rules: What's theirs is theirs, what's yours is up for grabs. 16:19:55 -!- elliott has quit (Remote host closed the connection). 16:25:19 huh, http://english.stackexchange.com/ exists 16:27:11 those people are such cycles 16:27:34 http://islam.stackexchange.com/ 16:34:43 -!- ogrom has quit (Quit: Left). 16:40:13 -!- Frooxius has joined. 16:49:16 -!- ogrom has joined. 16:50:23 -!- elliott has joined. 16:50:45 fizzie: hello 16:52:38 elliott: There's a set of escape codes that date from the VGA console days, I'm not sure if they still do the same thing in fbcon. They can set the hardware console to underscore/lower-third/lower-half/lower-two-thirds/full-block, or turn on the soft cursor that has the same shapes but also a color. 16:52:55 I only have the vgacon. 16:53:20 fizzie: Thanxe. 16:53:35 fizzie: Do you know how much of the average /var/log is produced by syslog? 16:53:36 fizzie: I think Linux does emulate them 16:53:43 Not fully certain though 16:53:46 FreeFull: I wouldn't be surprised. 16:53:51 fizzie: I've gotten systemd working but it doesn't seem to have this syslog compatibility shim thing running. 16:54:03 fizzie: So I'm wondering if I want to get that working or whether I could just do without any syslog support whatsoever. 16:54:18 The codes aren't for some reason listed in the usual console_codes man page (or if they are, I didn't notice) but googling found http://linuxgazette.net/137/anonymous.html that lists them. 16:54:19 If you tell me what the escape codes are I can find out 16:54:33 FreeFull: \e[?4c should make a half-block. 16:54:54 fizzie: (The escape codes aren't the problem; the main problem is that I can't figure out how I can get that to run before login(1) or such.) 16:55:37 fizzie: Works 16:56:11 -!- Phantom_Hoover has joined. 16:56:25 Changing the number to 1 turns it off entirely 16:56:31 As for /var/log all the usual things (auth, daemon, dmesg, mail.{log,info,warn,err} and so on) I think tend to go through syslog; only "major" things like Samba, HTTP servers and so on have their own logging. At least in the systems I have. 16:56:39 FreeFull: Yes, it should. 16:56:57 FreeFull: 1-6 should be a steadily growing thing from invisible to full block. 16:57:27 fizzie: I guess I should probably get this working then. 16:57:27 Yep, it does that 16:57:49 (VGA hardware cursor is specified in terms of scanlines, so it's not really exposing the full functionality; VGA cursor can be a middle-of-the-cell thing, or an overline. 16:57:49 fizzie: The wiki page is just all 16:57:49 [[ 16:57:50 Since version 38 systemd has an own logging system, the journal. 16:57:50 By default, running a syslog daemon is no longer required. To read the log, use: 16:57:50 ]] 16:58:14 I know absolutely nothing about systemd. Except that I hear it's all the rage. 16:58:20 As in, popular. 16:58:29 Well, uh, does this look sane to you? https://wiki.archlinux.org/index.php/systemd#Journald_in_conjunction_with_a_classic_syslog_daemon 16:58:49 I don't even know what that would do exactly. 16:58:58 I think the goal is to get syslog stuff filtered through into the systemd(tm) journal(tm). 16:59:05 -!- oerjan has quit (Quit: leaving). 16:59:06 But I don't really know how to do that because I'm incompetent. 17:00:31 I think -- based on http://lwn.net/Articles/474968/ -- that systemd is "syslog-compatible" out of the box in the sense that it provides a /dev/log applications can log to, and those already go to wherever it is the journal goes. 17:01:06 But if you want a traditional syslogd sorting the messages and outputting /var/log/whatever as it is configured to, you'll just start the traditional syslogd and make it read that /run/systemd/journal/syslog and then it also gets all that stuff. 17:01:27 I suppose if you're not terribly interested in how the logs are organized, letting systemd do the whole thing is okay too. 17:01:35 Assuming it writes the journal somewhere. 17:02:05 "Note that the journal will store log data only on /run/log/journal which makes it volatile. If a subdirectory /var/log/journal is created the journal will instead store its data on /var, thus making the journal persistant." 17:02:28 You might do that and then use that systemd-journalctl thing that can output human-readable things or JSON or whatever, it sounds very modern. 17:03:24 I mean, unless you have a traditional syslogd configuration you're interested in keeping. 17:04:06 I think -- based on http://lwn.net/Articles/474968/ -- that systemd is "syslog-compatible" out of the box in the sense that it provides a /dev/log applications can log to, and those already go to wherever it is the journal goes. 17:04:09 Oh, I do have a /dev/log. 17:04:15 I was trying nc -u 127.0.0.1 514. 17:04:24 The Googles told me that's how you sent a message to syslog. 17:04:25 Did they mislead me? 17:04:28 That's often not enabled by default. 17:04:33 Right. 17:04:37 Or, well, I don't know how often, but at least sometimes. 17:04:52 I don't think I need /var/log/whatever. I mean, I don't really look at them often, and I think systemd has its own stuff to read the logs. 17:05:10 Yes, it seems to have a thing that can produce things from the journal in all kinds of formats. 17:05:24 There's this "journalctl" that just spews a bunch of output to a pager when run as root, at least. 17:05:31 Including all the sudo logs and whatnot. 17:05:34 So I suppose it is working fine. 17:05:40 Yes. So it sounds like it's working okays. 17:05:57 But you can do that thing referred to above if you want to make the journal persistent and not wiped out at each boot. 17:06:07 Right, I heard about having to do the mkdir thing. 17:06:14 s/\s+/ /g 17:06:22 Well, I guess I'll uninstall sysvinit. 17:06:24 You know, living on the edge. 17:06:56 For the record, I don't seem to have an UDP-listening syslogd either. It's not really necessary except when wanting to collect logs over the network from other boxes. 17:07:09 I think my VDSL2 modem can send stuff to a listening syslogd. 17:07:27 Except it doesn't write anything very interesting in the log last I looked. 17:07:34 Right. 17:07:46 The thing I found was all about testing a syslog server with a separate IP and so on. 17:08:32 "B0 Line Rate - Downstream (Kbps): 99998" 17:08:35 That sounds a bit dubious. 17:08:45 (I went to look at the box's webif.) 17:09:21 "Slow boot? Blame systemd! 17:09:21 No, this is not a disparaging or bashing article of the new Linux boot process technology designed to replace the older, classic System V init daemon." 17:09:27 Good thing you didn't give it a sensationalised title, then! 17:10:13 Huh, I wonder if someone has done something to our internets. Upgraded hardware or something. 17:10:31 It reports attainable down/upstream rates as 123180/46260 Kbps. 17:10:49 They used to be something like 70M/... well, I don't remember what the upstream was. 17:11:01 Hokay, so I want to do "sudo systemctl enable dhcpcd@eth0.service", I think. 17:12:26 Then "sudo systemctl enable cronie.service". 17:12:26 -!- sivoais has quit (Read error: Connection reset by peer). 17:12:54 Then alsa-store.service and alsa-restore.service. 17:13:03 The unit files have no [Install] section. They are not meant to be enabled using systemctl. 17:13:03 HELP 17:13:15 -!- sivoais has joined. 17:13:16 Oh, it's default. 17:13:46 RIP DAEMONS=(network crond alsa). 17:14:09 fizzie: Isn't the FUTURE EXCITING? 17:15:25 It's almost enough for me to also try entering the future. But not quite. 17:15:46 I could do the stupid thing and try out the open-source nv driver one of these days, though. 17:15:52 fizzie: My system boots up in, like, seconds now!!! 17:15:55 Seconds! 17:16:03 fizzie: PARALLEL. 17:16:10 :: systemd-sysvcompat and sysvinit are in conflict. Remove sysvinit? [y/N] y 17:16:14 THE FUTURE 17:16:21 Amazzing. 17:16:28 I just saved 0.09 MiB by entering the future! 17:16:58 I should set up ntp. 17:17:01 I don't think I actually have it here. 17:17:03 And ntp is very future. 17:17:06 Debian went "parallel" with sysvinit+dependency-based boot ordering quite a while ago, I believe. 17:17:13 You should set up a GPS clock. 17:17:18 There was a picture not long ago. 17:17:19 elliott: don't do it, ntp will just adjust your system time back into the present 17:17:52 fizzie: It's actually silly-yet-amazing. 17:17:58 fizzie: Yes, but did you know that systemd is EVEN MORE PARALLEL? 17:18:01 fizzie: They create a makefile and run it with make -j 17:18:05 fizzie: It starts up services BEFORE THEIR DEPENDENCIES. 17:18:24 elliott: http://imgur.com/a/WtaOp if you didn't see it, it's what ion did. 17:18:42 fizzie: (By opening a fake socket on the same port or whatever as the dependencies, and then holding everything that comes in there until the thing actually starts, and then forwards it on.) 17:19:05 pikhq_: Oh. I assumed the "Makefile-based init" or whatever message that came up on every boot meant something... more reasonable. 17:19:05 I really need to get better at naming types 17:19:13 If you set up NTP, you'll get a stratum-2 time at best; if you have your own GPS receiver you'll be stratum-1. 17:19:20 Can I be stratum-0? 17:19:46 Only if your NTP server *actually is* an atomic clock. 17:19:46 If your computer is an atomic clock, maybe. 17:19:49 pikhq_: (Do they really do that?) 17:20:01 elliott: Yes, that's how make-based init works. 17:20:09 fizzie: What if I buy an atomic clock and plug it into my computer? 17:20:11 I bet they're cheap nowadays. 17:20:14 It's the future, after all. 17:20:20 elliott: Then the clock is stratum-0 and the computer stratum-1. 17:20:27 (They're weird that way.) 17:20:54 fizzie: What's the difference between a computer with an atomic clock on its motherboard and a computer with a wire running to an atomic clock? 17:20:58 Or is the former stratum-1 too? 17:21:08 What's the opposite of Separation? 17:21:12 (in a marriage context) 17:21:14 elliott: Possibly it is. I'm not really sure. 17:21:18 If you have a display on your atomic clock so you can measure the time it's reading, is that display stratum-0 or stratum-1? 17:21:23 (or, more generically, in a relationship context) 17:21:25 atriq: Matrimony? 17:21:27 :P 17:21:33 Starting to think there's no such thing as stratum-0???? 17:21:39 I guess the actual, like, atoms are stratum-0. 17:21:40 pikhq_, not quite 17:21:42 But they don't really know what time it is. 17:21:45 Perhaps Conjugation 17:21:47 elliott: It's kind of a philosophical question, I suppose. 17:22:07 OKAY LET'S TRY THIS. 17:22:10 -!- elliott has quit (Remote host closed the connection). 17:22:25 what's elliott doing 17:22:36 Trying to achieve enlightenment 17:22:51 leaving for the last time over and over again 17:27:08 ah, we had a word for that back at rationalwiki 17:29:43 -!- elliott has joined. 17:29:48 fizzie: HELP. 17:29:56 fizzie: I feel so future that I want to switch to GPT. 17:30:12 I tried that, didn't boot 17:30:16 "It's your funeral" is I think the phrase. 17:30:29 But it does sound like a natural thing to do. 17:30:38 and the GPT data is all hidden and stuff, so getting rid of it is surprisingly tricky 17:30:54 -!- hagb4rd has quit (Ping timeout: 246 seconds). 17:31:32 I'll try setting up ntp to, you know, stave it off. 17:32:07 Aaaargh 17:32:11 I'm not quite sure what GPT is supposed to give you that the good ol' crap doesn't 17:32:18 olsner: A sense of the future. 17:32:20 Who can I poke about the GEDCOM specs 17:32:44 I might easily consider GPT if setting up a computer right now. 17:33:03 i wish i could consider things like that 17:33:05 I'm not so sure about breaking an existing setup in order to do that. 17:33:27 my laptop has like 3 mystery partitions that i can't bring myself to risk messing with 17:33:37 Phantom_Hoover, can I ask you annoying questions regarding the GEDCOM specifications? 17:33:44 fire away 17:33:57 On the laptop that was set up maybe a year or so ago there was mostly the issue that it needed to dual-boot to Windows and it was a BIOS system. 17:34:16 In the definition of FAMILY_EVENT_STRUCTURE, what does the [Y|] represent? 17:34:37 the void in the soul of the sinner 17:34:39 -!- jiella has joined. 17:34:58 `welcome jiella 17:35:04 jiella: 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.) 17:35:22 jiella, a small jier 17:36:03 jiella, did you want welcoming? 17:36:43 Err. 17:36:47 Not really. 17:36:53 This attention is kind of creepy. 17:37:02 Are you in Finland? 17:37:10 are you in hexham 17:37:12 `? finland 17:37:15 Finland is a European country. There are two people in Finland, and at least nine of them are in this channel. Corun drives the bus. 17:37:16 Why do you ask? 17:37:27 no reason 17:37:29 just curious 17:37:45 Because this is one of the English-language channels with the largest Finn density 17:38:01 Also Hexhamite density 17:38:04 Also, dinner, bbl 17:38:05 -!- atriq has quit (Quit: Leaving). 17:38:59 also this is what we do to all new people 17:39:06 we are a lonely bunch 17:39:11 But I'm not new. 17:39:16 Not really. 17:39:25 hi jiella 17:39:25 I've been here more or less for... four years now? 17:39:32 Hexham or Finland? 17:39:41 we also do it to people we haven't seen lately 17:39:46 and some people we have 17:39:46 Finland. 17:39:50 `WELCOME jiella 17:39:54 JIELLA: 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.) 17:40:08 `? sweden 17:40:12 Sweden is the suburb capital of Norway. It's where all the Nobel prizes are announced, except the Math Prize. 17:40:20 `? norway 17:40:23 I was getting cold so now I'm compiling GHC to warm me up. 17:40:24 Norway is the suburb capital of Sweden. It's where the Nobel Peace Prize is announced. 17:40:40 `? denmark 17:40:43 denmark? ¯\(°_o)/¯ 17:40:44 jiella, so uh what nick did you use before 17:40:49 `? iceland 17:40:52 iceland? ¯\(°_o)/¯ 17:41:01 `? scotland 17:41:04 scotland? ¯\(°_o)/¯ 17:41:09 Several. You won't remember them. I say something perhaps every six months or so. 17:41:20 are you sftp 17:42:07 .. you're not going to go through a bunch of nicknames, are you? 17:42:13 yes 17:42:24 sshc 17:42:25 elliott: What are you doing here? 17:42:28 This isn't your channel. 17:42:30 @fresh 17:42:30 Haht 17:42:36 shachaf: fizzie let me 17:42:39 in 17:42:41 isn't that right fizzie 17:42:44 @help fresh 17:42:44 fresh provides: freshname 17:42:45 -!- Nisstyre-laptop has quit (Remote host closed the connection). 17:42:48 @fresh 17:42:49 Hahu 17:42:52 wrong 17:42:56 @help freshname 17:42:56 freshname. Return a unique Haskell project name. 17:43:06 @fresh 17:43:06 Hahv 17:43:38 $ sudo systemctl enable ntpd.service 17:43:39 ln -s '/usr/lib/systemd/system/ntpd.service' '/etc/systemd/system/multi-user.target.wants/ntpd.service' 17:43:40 The most futurest. 17:43:41 @fresh 17:43:41 Hahw 17:43:49 @freshname 17:43:49 Hahx 17:44:00 Uh, I wonder how to get it to enable it now/. 17:44:05 It just increments the letter 17:44:37 -!- Nisstyre-laptop has joined. 17:44:39 elliott: Is HEAD GHC building for you? 17:44:45 I don't build HEAD. 17:44:47 reinventing init seems to be almost as much fun as adding levels of boot loaders 17:44:58 olsner: Well, in fairness, init is pretty terribly-designed. 17:45:07 systemd is better. Not perfect, but... better. 17:45:08 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 17:45:28 At least it just runs a bunch of stuff dependency-wise in parallel rather than the tangle of tasks old init does. 17:45:39 sure, but everything sucks anyway, so why add the choice of new kinds of suckage 17:46:13 -!- Nisstyre-laptop has joined. 17:46:23 I suppose it would be alright if there was one better init instead of a hundred 17:46:30 It's faster suckage, olsner. 17:47:22 Ah, "sudo systemctl start multi-user.target" did it. 17:47:23 and that's a good thing 17:47:33 -!- zzo38 has joined. 17:48:08 fizzie: Hey, how do I tell if my luck is... uh... ntp'd? 17:48:14 ntpd is running, but I don't know if it's... thinging. 17:49:40 ntptime seems to print some stats about that 17:49:55 olsner: Thank you, fizzie. 17:50:11 fizzie: "Startup finished in 5173ms (kernel) + 11636ms (userspace) = 16810ms". 17:50:18 Does YOUR system start up in 16810 ms??? 17:50:24 lrwxrwxrwx 1 shachaf shachaf 9 Sep 6 15:26 /home/shachaf/.ghc/ghci_history -> /dev/null 17:50:44 elliott: how often do you start your system? 17:50:50 olsner: Like, EVERY DAY. 17:50:54 I need the fastest suckage. :( 17:51:00 elliott: My *distro* boots in 3. :) 17:51:16 pikhq_: I don't believe your distro boots in 3 ms. 17:51:19 3s 17:51:23 That's not ms!! 17:51:29 3000ms Happy? 17:51:48 Phantom_Hoover: No. At least I don't think so. 17:53:08 at normal rebooting rate my system has about 25 minutes to boot before it spends more time booting than your 16810ms system 17:53:09 pikhq_: I'm actually never happy. 17:53:35 -!- Ginto8 has joined. 17:53:55 elliott: Upstart needs some kind of an extra thing to collect statistics, so I don't really know. (I did see a recent systemd user be all "look at all these statistics I get by default" on me, I think you can get very detailed boot-timings out of it.) 17:54:51 At least I'm under the impression the Ubuntu box has upstart involved. The Debians don't really get booted. 17:55:39 Yes, I can do this: http://sprunge.us/dIMG 17:55:42 It also works with bootchart, apparently. 17:56:01 -!- hagb4rd has joined. 17:59:13 fizzie: Do I have to do something special to check whether my BIOS supports GPT? 17:59:21 I don't really know what can go wrong. 17:59:58 I'd guess that it doesn't .. then again it might have it, or if it has support the support might not work 18:00:10 oh, and if the gpt support is there and works, it might only be able to boot windows 18:00:12 elliott: If it's a BIOS, it doesn't. 18:00:22 However, BIOS also doesn't support DOS partitions. 18:00:37 The BIOS's concept of partitioning is "load the first sector"... 18:00:53 If you're not using UEFI, you simply need an MBR that groks GPT. 18:01:00 pikhq_: Right. 18:01:09 pikhq_: And I guess GRUB2 does that. 18:01:17 (Do you use GPT??? Maybe I can be "ahead of the pack".) 18:01:24 Currently I don't. 18:01:28 My next system will. 18:01:37 Is there some kind of hack you can do to get Windows booting from GPT? 18:01:39 I'm still on an LVM setup. 18:01:44 Some kind of chainloading nonsense or the like. 18:02:13 (Also will this break /dev/sda2 and the like? I remember those having different names on OS X, which uses GPT.) 18:02:30 Uh, no, pretty sure Windows only supports booting from GPT if booted from UEFI... 18:04:08 It shouldn't. Linux's partition numbering is not based in DOS partitioning, but rather its generic partition handling code. Aside from that low level bit in the kernel, GPT is indistinct from all other partition formats. 18:04:41 Including BSD disklabels, classic Mac OS partitions, and anything else anyone was crazy enough to implement. 18:05:08 Right. 18:05:18 I would sort of like to not totally lock myself out of booting Windows. 18:05:24 Though I suppose I'm not likely to actually do so. 18:05:29 Is there a way to convert GPT back to MBR? :p 18:06:57 gdisk's "g" command. 18:07:08 Oh, awesomer. 18:07:15 You could create a "hybrid MBR"... 18:07:23 Is that like what Boot Camp does on OS X? 18:07:25 FreeDOS boots much faster 18:07:25 zzo38: You have 7 new messages. '/msg lambdabot @messages' to read them. 18:07:27 Yes. 18:07:30 It makes an MBR and synchronises that with the GPT or something. 18:07:33 Is that well-supported on Linux? 18:07:36 ?messages? 18:07:36 zzo38: You have 7 new messages. '/msg lambdabot @messages' to read them. 18:07:38 ?messages 18:07:39 Sgeo said 1m 8d 51m 9s ago: Now you have a message. 18:07:39 oerjan said 3h 32m 48s ago: I think the DotFami mapper codes actually form a idempotent commutative monoid, rather than just being a monoid. <-- i think an idempotent commutative monoid may 18:07:39 the same as a semilattice 18:07:39 oerjan said 3h 31m 42s ago: *may be 18:07:39 oerjan said 3h 28m 48s ago: Does the Haskell compiler know that equality is reflexive? <-- it actually isn't, for Double (NaN) 18:07:41 oerjan said 3h 23m 38s ago: Actually, a it's a semilattice with a bottom element (the mempty). 18:07:43 oerjan said 3h 23m 23s ago: *-a 18:07:43 ?messages 18:07:45 oerjan said 3h 21m 3s ago: From wikipedia: "A bounded semilattice is an idempotent commutative monoid." 18:07:47 You don't have any new messages. 18:07:47 All I remember is it is sort of a pain when they get out of sync. 18:08:30 Linux appears to be fussy if the first partition on disk is not EFI. 18:09:03 Erm, not GPT. 18:09:22 Actually, yeah. As part of its GPT support it needs the first partition to be an EFI partition. 18:09:35 Right. 18:09:38 However, if that's the case it'll just ignore the DOS partitions. 18:09:44 (I assume that doesn't mean I have to run EFI?) 18:09:56 It doesn't mean that at all. 18:10:04 That's just the partition EFI would read from if it existed. 18:10:33 Right. 18:10:36 -!- atriq has joined. 18:11:50 And Windows will gleefully ignore the GPT partitions. 18:13:21 Hahah. And FreeBSD has the best hybrid MBR support possible. 18:13:39 Faced with a hybrid setup, it parses both the GPT and classic partition headers. 18:13:46 And you get device files for both. 18:14:06 that sounds bad if they are duplicates 18:14:21 It also has logic preventing badness. 18:14:27 ok 18:14:40 pikhq_: Why doesn't Linux do that? 18:14:44 FreeFull: Beats me. 18:14:50 Oh, wait, duh. 18:15:02 Because Linux's partition numbering scheme doesn't quite handle that case well. 18:15:09 Hmm 18:15:27 /dev/sdaN doesn't work nicely for parallel partition numbers 18:15:50 /dev/da0pN and /dev/da0sN does, though. 18:18:09 I am REALLY bad at coming up with names 18:18:40 pikhq_: Couldn't it just use more numbers 18:19:07 FreeFull: Still doesn't quite seem right. Some of those numbers will refer to the same blocks. 18:19:25 pikhq_: Do you know of a login manager that doesn't depend on ConsoleKit? 18:19:33 Login manager. I mean display manager thing. 18:20:14 I don't think LXDE does. 18:20:28 There's also XDM. 18:20:50 I... guess I could use XDM. 18:20:58 -!- elliott has quit (Remote host closed the connection). 18:24:09 -!- elliott has joined. 18:24:16 pikhq_: You use systemd, right? 18:24:23 Nah. 18:24:40 I use stock init ATM, at one point I'd like to distro-like-crazy and use runit. 18:25:18 pikhq_: Can you start using systemd so I can ask questions about it? :p 18:25:53 I'd rather not. I'm not much of a Lennart fan. :P 18:26:13 (to fix problems with pulseaudio, do: apt-get remove pulseaudio ) 18:26:24 pikhq_: I prefer purge 18:26:36 pikhq_: Also, I'm not entirely convinced that doing that won't fix problems even if pulseaudio isn't installed 18:26:51 I use systemd 18:26:54 Not pulseaudio though 18:26:56 pikhq_: I don't like PulseAudio, but systemd is quite nice. 18:26:59 At least so far. 18:27:14 IIRC runit doesn't actually work properly as PID 1? 18:27:55 -!- monqy has joined. 18:27:58 FreeFull: Do you happen to use Arch also? 18:28:18 Yes 18:29:02 elliott: Yeah, but PID 1 does not need to do much. 18:29:29 FreeFull: Do you happen to know if I still need "fsck" in the HOOKS list in /etc/mkinitcpio.conf if I'm using systemd, since it seems to run its own systemd-fsck thing by itself? (Although it also seems to only run it on /dev/sda1, which might have something to do with /dev/sda2 being JFS...) 18:29:47 -!- ogrom has quit (Quit: Left). 18:29:50 elliott: I have no idea 18:30:01 http://sprunge.us/QAQe That does everything init needs to do. 18:30:04 FreeFull: Well, you were almost useful :P 18:30:04 elliott: Tried asking in #archlinux? 18:30:16 pikhq_: Well, no, but I don't like the idea of having an /etc/rc.start or whatever that "just" sets up filesystems and the network and so on... those can fit perfectly fine into a dependency-ish system like systemd does. 18:30:44 FreeFull: I probably should, yes. But I'll try floundering about messing with it for a bit more first. 18:30:58 for(;;) wait(&status); is all PID 1 does for the rest of the system run, FWIW. 18:31:16 -!- copumpkin has quit (Ping timeout: 248 seconds). 18:31:25 Yes, I know that much. 18:31:31 Still, you have an /etc/rc there which is the real problem. 18:31:52 -!- copumpkin has joined. 18:31:54 elliott: Ideally, perhaps. But systemd's approach appears to be "shove everything into a single process that, if it fails, crashes the *entire system*"... 18:32:12 pikhq_: That, uh, applies to every PID 1. 18:32:16 Yes. 18:32:27 Hence why PID 1 should be for(;;) wait(&status); 18:32:34 Nearly impossible to crash. 18:32:45 If it does crash, your system is already FUBAR'd. 18:32:57 monqy: What's *your* opinion on this? 18:33:18 I'd love for a better dependency-based boot scheme though. 18:33:26 I just don't feel systemd is the correct approach. 18:33:47 It does *resemble* the correct approach, but still... 18:34:24 pikhq_: Well it's less maintenance than having to manually fiddle about with a monolithic /etc/rc, even if it's theoretically less stable in the worst case. 18:35:28 hi opinion on what 18:35:48 monqy: Damn. 18:35:54 monqy: I was hoping to trick you again. 18:36:13 only 1 message 18:36:13 I've also got issues with PID 1 dbus. 18:36:16 tsk tsk tsk 18:37:30 monqy: Tsk yourself, I've been too busy living in the future. 18:38:31 -!- sirdancealot has quit (Read error: Connection reset by peer). 18:38:35 -!- atriq has quit (Quit: Leaving). 18:38:58 I've also got this weird thing where I want everything using *less* code... I mean, I find zlib offensive. 18:39:49 monqy: I'm so far in the future that /etc/rc.conf stopped existing :'( 18:40:10 -!- sirdancealot7 has joined. 18:42:51 i still have /etc/rc.conf but all that's in it is the DAEMONS array 18:43:40 monqy: I don't even have that!! 18:43:43 My /etc/inittab also disappeared. 18:46:15 monqy: Also I can do fancy things like this!! http://sprunge.us/gSGG you can't see it there but "active (running)" is green 18:48:00 -!- jiella_ has joined. 18:49:22 -!- elliott has quit (Remote host closed the connection). 18:49:31 -!- jiella has quit (Ping timeout: 260 seconds). 18:54:37 -!- elliott has joined. 18:55:57 pikhq_: OK well do you use GRUB 2 19:03:32 Yes. 19:03:46 Yay. 19:04:07 Do you know how to get it to skip the menu and just boot up in three seconds unless I press ESC? I've tried setting up the hidden menu stuff, but it ends up doing the countdown, and *then* showing the menu once the countdown expires. 19:04:11 Which seems... wrong. 19:06:24 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 19:08:39 fizzie: Also do you still use that crazy dzen2 dbus thing? 19:12:59 elliott: Regarding the earlier, I plead the saunath of not answering. 19:13:16 But people dual-boot Windows on systems with a dual GPT + MBR-emulation setup. 19:13:24 It's a bit arguable whether that makes any sense. 19:13:32 Regarding the latter, yes. 19:14:54 Everyone keeps saying I should adopt the XMonad view of there being a single set of workspaces shared between the monitors, but I'm just so stuck with this IndependentScreens thing. 19:15:11 (Okay, "everyone" here means like one person who wasn't even talking to me. But still.) 19:19:20 "The latest versions [of caesium clocks] are accurate to better than 1 part in 10^15, which means they would be off by about 2 seconds since the extinction of the dinosaurs 65 million years ago --" two seconds?! 19:19:33 -!- ogrom has joined. 19:23:09 fizzie: Why does passing -fn '-*-terminus-medium-r-*-*-20-*-*-*-*-*-*-*' do the wrong thing? :( 19:23:20 It shows me DejaVu Sans at 20 pixels or whatever. 19:23:23 To dzen2, I mean. 19:24:13 I don't know, but I've been having really stupid problems with dzen2 compiled to support xft when trying to use the usual X logical font descriptors like that. 19:24:27 I blame fontconfig. It might not be its fault, but I still blame it somehow. 19:24:57 (When you compile dzen2 to "support Xft", it actually uses Xft for everything. In *theory*, it should be possible to use bitmap fonts and XLFDs, but...) 19:25:08 Terminus:pixelsize=20 does the same thing. 19:25:20 If you're going to be using '-*-terminus-medium-r-*-*-20-*-*-*-*-*-*-*' exclusively, there's an easy fix of just compiling it without Xft support. 19:25:36 Ubuntu for example has a default fontconfig file hidden deep in /etc that disables all pixel fonts. 19:25:53 /etc/fonts/conf.d/70-no-bitmaps.conf that is. 19:26:08 If you're going to be using '-*-terminus-medium-r-*-*-20-*-*-*-*-*-*-*' exclusively, there's an easy fix of just compiling it without Xft support. 19:26:14 The "easy fix" involving "not using the standard Arch binary package for it". 19:26:22 Well, there's that. 19:26:37 I do have some somewhat suspicious 29-replace-bitmap-fonts.conf and 70-no-bitmaps.conf files. 19:27:09 Hokay, unlinking the latter has helped. 19:27:17 Yeah. It's possible to per-user "undo" those by suitable configuration in ~/...whateveritwas, but fontconfig configuration is such pain. 19:27:19 Now dzen2 uses some really shockingly beyond-belief godawful font by default. 19:27:47 I'm just using scalable fonts these days. *shame* 19:27:49 fizzie: Feel my pain: http://i.imgur.com/mgTSb.png 19:27:59 Well, I don't mind scalable fonts, of course. 19:28:02 I think I've seen that thing. 19:28:03 The Terminus thing is a long story. 19:28:09 -!- atriq has joined. 19:29:09 I used the SunOS console font for a while on some moderately-high-DPI screen. 19:29:25 -!- Phantom_Hoover has joined. 19:29:25 I don't think it had a very good Unicode support though. 19:30:16 I do wonder if that open-source Source Code from Adobe is any good at my point sizes and resomolutions. 19:30:18 important question, am i joinspamming 19:30:49 fizzie: Is there, uh, a nice way to get dzen2 to start at the bottom? 19:30:58 Also I don't like Source Code; it's way too wide and not tall enough. 19:31:52 Maybe not a "nice way"; it has -x -y -w -h parameters, but you'd need to do some math for "bottom". 19:32:27 The sort of complicated math of y=screenheight-barheight. 19:33:12 fizzie: Alsoalso what was that thing you needed to do to align text rightmost in new dzen2? 19:33:14 Some fancy code. 19:33:27 I'll grep for it, I can't remember ever. 19:34:12 There's an undocumented "make a fixed-width block of left/middle/right-aligned text" command ^ba -- sorta-described at http://dzen.geekmode.org/dwiki/doku.php?id=dzen:mainindex and not included (I believe) in the dzen2-0.8.5 stable version -- that can help. Then again, it might not; it's strictly fixed-width. 19:34:24 I don't know what source the Arch version uses. 19:34:28 git. :p 19:34:37 Well, that's good. 19:35:20 I'm not entirely sure the example is right and not missing an underscore for the alignment specifier. But maybe it is. 19:35:51 else if(!strcmp(buf, "_RIGHT")) 19:35:51 *a = ALIGNRIGHT; 19:35:55 Is there an xmonad helper function thingy that just runs a shell line and returns the output? ISTR there is. 19:35:56 That does look a bit _ey. 19:37:46 XMonad.Util.Run has some helpers. I don't see exactly that there, maybe it was somewhere else. 19:39:10 I think System.Process might have something reasonably usable non-XMonad-specific too. Like readProcess. 19:39:27 "readProcess forks an external process, reads its standard output strictly, blocking until the process terminates, and returns the output string." 19:40:34 Hmm, there's spawn :: MonadIO m => String -> m () in XMonad.Core. 19:41:01 I'll try readProcess. 19:45:04 elliott: Oh, right, XMonad.Util.Run has a runProcessWithInput. 19:45:17 elliott: I skipped it because of the name, but it also returns the output, and you can just give "" as the input. 19:45:22 That might be it. 19:46:05 It's :: MonadIO m => FilePath -> [String] -> String -> m String so it should work in IO or X or so on. 19:48:20 Oh, logCmd "date +'%H:%M'" works for my purposes. 19:49:13 Oh, so does date "%H:%M". 19:49:36 Though apparently it... only updates when you switch workspaces. 19:50:50 The logHook should be called every time you switch focus, too. 19:51:06 But not really much more oftener than that. 19:54:16 -!- sebbu- has joined. 19:54:30 I get these "dhclient: Discarding packet with bogus hlen."s nowadays. 19:55:18 -!- Deewiant has quit (*.net *.split). 19:55:18 -!- sebbu has quit (*.net *.split). 19:55:19 -!- zzo38 has quit (*.net *.split). 19:55:19 -!- pikhq_ has quit (*.net *.split). 19:55:19 -!- EgoBot has quit (*.net *.split). 19:55:19 -!- mroman has quit (*.net *.split). 19:56:13 -!- zzo38 has joined. 19:56:14 -!- pikhq_ has joined. 19:56:14 -!- EgoBot has joined. 19:56:14 -!- mroman has joined. 19:56:43 Hmm, I can't figure out what the width should be to have this work properly. 19:56:50 This is a very silly thing. 19:57:05 fizzie: (Do you know of any way to get it called more cmmonly?) 19:57:06 *commonly 19:57:13 I guess I might have to use your dbus thing if I want a clock and things. 19:57:23 EgoBot is on a different server to Gregor and HackEgo? 19:58:23 Being connected to a different server isn't very interesting, the server you get connected to is more or less random. 19:58:27 elliott: I think generally speaking "most people" use xmobar; it's got widgets like clocks in addition to the xmonad-reading bits. 19:58:32 Apparently there was both a Homestuck meetup and a Hetalia meetup in Newcastle together 19:58:38 *today 19:59:47 fizzie: I can't use xmobar because of shachaf. 20:00:20 -!- Nisstyre-laptop has quit (Remote host closed the connection). 20:01:43 elliott: Well, the dzen2 minority then use different kinds of "multiplexing" scripts, I believe. 20:02:09 Right. 20:02:27 dmplex has some kind of official status. 20:02:38 In that it's at the dzen site and so on. 20:02:48 Got a link? 20:02:56 -!- Nisstyre-laptop has joined. 20:02:57 http://dzen.geekmode.org/dwiki/doku.php?id=dzen:multiplexer has a link. 20:03:02 I haven't used it at all. 20:03:59 Does it really use a named pipe. 20:04:33 Well. It reads from the standard input. But the example setup does seem to use one. 20:04:59 I don't know, I've got that stupid dbus thing. And I don't have a clock anyway. 20:05:45 XMonad has timers -- well, XMonad.Util.Timer does -- and some real xmonad person would probably know some kind of a hack that'd make it call the logHook when one fires. 20:06:08 -!- oerjan has joined. 20:07:35 -!- Deewiant has joined. 20:14:00 lifthrasiir, are you following the League of Legends world championship 20:16:55 racist 20:17:08 Phantom_Hoover, are you? 20:17:28 yes 20:17:35 do you want to join my racist club 20:22:13 I forgot a ventilation window open while i was away. Some temperatures and the PC clock’s offset to GPS time from the same period: (yeah, all the things run too hot, i haven’t got around to doing something about the ventilation) http://heh.fi/collectd/img/temperature http://heh.fi/collectd/img/time-offset-gps 20:24:18 ion: that's disappointing, i was assuming you had discovered a temperature correction to relativity 20:32:30 `learn Scotland is a country in northern Britain. It is known for having no true inhabitants. 20:32:33 I knew that. 20:32:48 oerjan: fix 20:32:56 what NOW 20:32:58 `learn Scotland is a country in northern Britain. It is known for having no true inhabitants. Phantom_Hoover looks after the FREEDOM. 20:33:02 I knew that. 20:33:03 oerjan: ". " 20:33:06 atriq: ". " 20:33:12 sheesh 20:33:14 `learn Scotland is a country in northern Britain. It is known for having no true inhabitants. Phantom_Hoover looks after the FREEDOM. 20:33:18 I knew that. 20:33:36 `? england 20:33:39 england? ¯\(°_o)/¯ 20:33:43 although i'm looking after it in england these days 20:34:09 England is where the crumpets live 20:34:45 `learn England is a country in southern Britain, with capital Hexham. The people there are all punctuation fascists. ais523 looks after the Turing machines. 20:34:48 I knew that. 20:35:26 `learn England 20:35:30 I knew that. 20:35:30 `? england 20:35:33 England is a country in southern Britain, with capital Hexham. The people there are all punctuation fascists. ais523 looks after the Turing machines. 20:35:37 no!! 20:35:40 yay! 20:36:10 `run ls wisdom/en* 20:36:14 wisdom/endofunctor \ wisdom/england 20:36:29 -!- sebbu- has changed nick to sebbu. 20:36:29 -!- sebbu has quit (Changing host). 20:36:29 -!- sebbu has joined. 20:37:43 `run rm -rf wisdom 20:37:46 No output. 20:38:00 `run ls wisdow/en* 20:38:03 ls: cannot access wisdow/en*: No such file or directory 20:38:22 Sorry D: 20:38:28 `? england 20:38:32 england? ¯\(°_o)/¯ 20:38:35 `revert 20:38:38 Done. 20:38:41 `? england 20:38:45 England 20:38:50 aaaaa 20:39:07 `? scotland 20:39:11 Scotland is a country in northern Britain. It is known for having no true inhabitants. Phantom_Hoover looks after the FREEDOM. 20:39:43 `learn Scotland is a country in northern Britain. It is known for having no true inhabitants. The official religion is hatheism. Phantom_Hoover looks after the FREEDOM. 20:39:46 I knew that. 20:40:17 `learn England is [EXPUNGED]. 20:40:21 I knew that. 20:40:24 `run echo "I like pie" >> wisdom/pie 20:40:28 No output. 20:40:30 `? pie 20:40:34 I like pie 20:40:44 `run echo "I like pie" >> wisdom/pie 20:40:48 No output. 20:40:49 `? pie 20:40:52 I like pie \ I like pie 20:41:09 fungot: Do you like position-independent executables? 20:41:11 fizzie: and resource files as ascii have the same feelings, too. i'm pretty sure you'd just use fnord in load or on the author's part, mostly. direct to-c translation, no gc ( iirc) from the console 20:41:17 I see, "\n" becomes " \\ " 20:43:15 `learn pi is a very round number. 20:43:19 I knew that. 20:43:26 `revert 20:43:29 Done. 20:43:31 puntastically round 20:43:32 `? pi 20:43:36 pi? ¯\(°_o)/¯ 20:43:38 `learn pi is a very round number. 20:43:41 I knew that. 20:44:34 `? oerjan 20:44:37 Your evil overlord oerjan is a lazy expert in future computation. Also a lying Norwegian. 20:44:45 `? FreeFull 20:44:48 FreeFull? ¯\(°_o)/¯ 20:45:20 `learn FreeFull is either full of freedom or free of fulldom, we are not sure. 20:45:23 I knew that. 20:45:59 `run echo -ne "F\rr\re\reFull likes messing around way too much" >> wisdom/FreeFull 20:46:02 No output. 20:46:07 `? FreeFull 20:46:11 FreeFull is either full of freedom or free of fulldom, we are not sure. 20:46:21 Has to be lowercase then 20:46:23 `rm wisdom/FreeFull 20:46:26 Can you make a hardware description language based only on multiplexers? There is a esolang software programming language Muxcomp which is design of a computer based only on multiplexers. 20:46:26 No output. 20:46:28 `run echo -ne "F\rr\re\reFull likes messing around way too much" >> wisdom/freefull 20:46:32 No output. 20:46:37 `? FreeFull 20:46:41 FreeFull is either full of freedom or free of fulldom, we are not sure. \ F.r.e.eFull likes messing around way too much 20:47:09 :P http://thedailywtf.com/Articles/Known-Bad-Code.aspx 20:53:58 I'm in a Skype group call with someone who's asleep 20:54:13 k 20:54:19 are they snoring? 20:54:25 She was whimpering 20:54:28 hmmmm 20:54:32 She's woken up again, thoguh 20:55:03 She's asleep agaiN! 20:55:23 She's... 20:55:26 Started apologizing 20:55:29 In her sleep 20:56:17 so imagine I'm programming in C; I create a string with char *p = malloc(strlen(s) * sizeof(char)); and later I make this string shorter (possibly much shorter), can I do something like free(p+k+1); where k is the new length? 20:56:43 Okay, apparently she's got a head injury and blacks out from time to time 20:56:57 Doctor says it's either gonna last a month or it's permanent 20:56:57 Arc_Koen: No, but you can call realloc on it. 20:57:14 It's not guaranteed to actually free up any storage, of course. 20:57:19 Arc_Koen: sizeof(char) is 1, and you're forgetting to allocate a byte for the null 20:57:25 Those, too. 20:57:44 olsner: the null already is in s 20:57:51 Arc_Koen: But not counted by strlen. 20:57:58 oh 20:58:11 but it worked?! 20:58:15 If doing realloc, remember that it's also allowed to move the string, invalidating any other copies of the pointer you might have lying around. 20:58:21 Well, undefined behaviour is allowed to work. 20:58:28 Quite often allocation isn't all that exact anyway. 20:59:13 -!- ais523 has joined. 20:59:59 ais523: elliott is evil, he censored my reveals of english secrets! 21:00:52 oh dear 21:01:01 there are 10 episodes of the armando ianucci shows 21:01:14 fizzie: I have no idea what I'd use realloc for; I only wanted to free the remaining of the string because my paranoid aspy told me placing a new '\0' in the middle of the string would cause the remaining to be lost forever 21:01:32 "free the remaining of the string" makes no sense 21:01:56 elliott: well imagine I use malloc to get a string of 1000 characters 21:02:09 I know what you mean, but it makes no sense. 21:02:11 Arc_Koen: "free the remaining of the string" is what you could do with realloc; resize the block of memory to fit exactly the new string. 21:02:23 and then I decide only the first 10 are relevant, so I place a '\0' after the tenth character 21:02:24 Arc_Koen: But if you're not worried about memory consumption, there's really no reason to do it. 21:02:31 placing a magic value in the middle of a string will indeed have magic effects on the rest of the string 21:02:48 Arc_Koen: If you free(p) it will free what was allocated, and doesn't care about the contents of those bytes. 21:02:51 ok I guess I won't do it then 21:03:08 fizzie: that's why I wanted to free(p+k+1) 21:03:39 Arc_Koen: Uh. I'm not quite getting it. 21:03:56 Arc_Koen: You can't free p+k+1, because it is not a thing that was allocated by malloc. 21:04:01 -!- ogrom has quit (Quit: Left). 21:04:02 fizzie: If you do p[10] = 0 to truncate a string then Arc_Koen is saying free(&p[11]). 21:04:04 yeah, ok 21:04:08 (But that's not how allocation works.) 21:04:13 fizzie: Hey, what border widths and colours do you use in xmonad?? 21:04:22 SURVEY. 21:04:38 free can only take the exact pointer that's returned by malloc 21:04:39 elliott: Yes, I got that much. But I just explained that free(p) will free all of p even if you put a 0 in there, so it felt somehow incongruous to get an answer of "that's why I want to free the trailing part". 21:04:43 Or by calloc 21:04:45 Nothing else 21:04:55 FreeFull: Not true. 21:04:55 FreeFull: Also one that was returned by realloc. 21:05:00 FreeFull: free can also take NULL IIRC. 21:05:06 That, too. 21:05:10 Well, yeah, NULL too 21:05:21 If it gets NULL, it just returns successfully 21:05:27 so, about that +1 I forgot in the malloc (for the null character), the fact that the program still worked well without it, does it mean it happened to have placed that '\0' on a not-free byte without causing a segfault? 21:05:31 FreeFull: realloc(NULL, 42); is equivalent to malloc(42); and then you can later free that pointer. 21:05:42 Arc_Koen: Yes 21:05:45 yeah, free on NULL is a no-op ... lots of people miss that and add one or more layers of null checks just because 21:05:50 Well, not necessarily, but it is possible 21:05:59 elliott: I'm using a border width of 1 and colors that I don't think I have configured. It's some kind of a grey for non-focus, red for focus. 21:06:23 so I just destroyed a char from my computer? I thought that was what segfaults were supposed to prevent! 21:06:28 fizzie: Anything not allocated by the C *alloc functions then =P 21:06:33 Arc_Koen: It's also possible that malloc for some reason returned a bit more than what you asked for, and the byte was in fact free. 21:06:52 Arc_Koen: segfaults are caused by going onto an unmapped page of memory 21:07:01 pages are fairly coarse-grained units, typically 4kB or more 21:07:17 they are nowhere near exact bounds checking 21:07:56 FreeFull: I was going to be all "and then in C11 there's aligned_alloc" on you but your wildcard matches that too. :/ 21:08:11 Arc_Koen: FSVO "destroyed". 21:08:23 Arc_Koen: All you did was overwrite memory you weren't supposed to have btu were given anyway. 21:08:23 Yay globs 21:08:31 Arc_Koen: Nobody else was affected, just you. 21:08:34 *but 21:08:54 ok, so I did not overwrite a byte I wasn't given? great :) 21:09:04 there are only so many bits in the world, and every run of this program has destroyed 8 of them 21:09:12 Arc_Koen: Depends on how big the string is 21:09:28 Arc_Koen: Well, you overwrote a byte that you owned. It might have been part of some other string in your process, but not part of any other process. 21:09:50 If the strlen happens to match the alignment, then the \0 will overwrite something else 21:09:53 (FSVO "owned".) 21:10:02 (As far as C is concerned you were trespassing.) 21:11:04 Yes, it's certainly not a thing to do, and can be fatal to the program itself. 21:12:01 FreeFull: your allocation is probably rounded up at least to the nearest multiple of 4 or 8 (the alignment) 21:12:04 er 21:12:10 *Arc_Koen: 21:12:58 well I switched to strncpy that should shut down the paranoia for now 21:13:17 and malloc might want to use even larger blocks to avoid fragmentation? i don't actually know whether it does. 21:13:56 there are many mallocs, each making different tradeoffs 21:14:35 pikhq_: I forget, did I ask you about that GRUB 2 menu thing? 21:15:36 there are only so many bits in the world, and every run of this program has destroyed 8 of them <-- 2nd law says that's approximately true 21:16:10 yeah, I somewhat failed to not make sense there 21:17:07 unless his program was reversible, of course. 21:17:16 Arc_Koen: strncpy is a function that's somewhat hard to use right, FWIW. It's somewhat sad that strncpy is not to strcpy what e.g. strncat is to strcat. 21:18:44 unsigned int p_length = strlen(argv[1]); char *p = malloc((p_length + 1) * sizeof(char)); strncpy(p, argv[1], p_length); 21:19:16 meh, use memcpy with p_length+1 instead 21:19:21 I've never used strcat before so i'm not sure how I should feel about strncpy 21:19:29 this is one of the cases where you know exactly how much to copy 21:19:38 apparently to get gstreamer faac support i have to apt-get install gstreamer0.10-plugins-really-bad 21:19:51 :-) 21:20:07 you know it is very important to respect software patents while transcoding illegally acquired copyrighted TV shows 21:20:15 Verily. 21:20:23 Arc_Koen: Well, that's safe. But it's easy to forget \0s at the end of strings with strncpy; and when it's done safely like that, it's often still needlessly inefficient because if the source string is shorter, it will still pad the whole destination with \0s. 21:20:37 Arc_Koen: Oh, and yes, s/safe/unsafe/ 21:20:50 Arc_Koen: Since it doesn't put the \0 there. You've just left a space for it. 21:20:59 WHAT 21:21:01 If you follow it with a p[p_length] = 0 it's safe. 21:21:28 Arc_Koen: That's what strncpy does. It writes up to 'len' bytes, and if the source string is that long (or longer) the destination won't contain a \0. 21:21:42 so I should've, like, used "strncpy(p, argv[1], p_length+1);" ?? 21:21:44 is there any case where you really want to zero out the rest of the buffer? 21:22:17 so that strncpy would say "oh look, argv[1] is one byte too short, let's put an extra '\0'" 21:22:26 Arc_Koen: Well, that would've been safe, but in general no, because that won't put a \0 in the buffer if the source string is longer. 21:22:30 00:21 ,cc char *s = "alongstringhere"; char buf[4] = {1,2,3,4}; strncpy(buf, s, (sizeof buf) - 1); printf("is there a null byte in buf? %d %d %d %d...", buf[0], buf[1], buf[2], buf[3]); 21:22:34 00:21 fizzie: is there a null byte in buf? 97 108 111 4... 21:22:59 If you call the above with "sizeof buf" without the - 1, you'll get "alon" in the characters and still no \0. 21:23:06 That's why it's such a sucky function. 21:23:35 I second olsner's suggestion of using memcpy of p_length+1 since you really do want an exact copy of the original. 21:23:45 (Or 'strdup' if you can live with its unportability, I suppose.) 21:23:53 (It does both the allocation and copying.) 21:24:08 is strdup unportable? 21:24:14 olsner: It's not standard C. 21:24:16 unsigned int p_length = strlen(argv[1]); char *p = malloc((p_length + 1) * sizeof(char)); memcpy(p, argv[1], p_length + 1); 21:24:40 ah, it appears to be posix not c 21:24:43 olsner: So I suppose that depends on what "portable" means. It's certainly POSIX and common elsewhere too. 21:25:15 Arc_Koen: that looks well and proper. Though I'd drop the sizeof(char). 21:25:35 I thought that was something I should always write 21:25:49 like using '0' instead of 48 21:25:50 Arc_Koen: It's by definition 1. "sizeof" of anything else is measured in terms of how many 'char's there are in it. 21:25:59 sizeof(char) is something you should never write :) 21:26:02 ok 21:26:14 I'm sure there are some people that will still argue for it. 21:26:29 Like, "if you change the array type then you'll remember the sizeof multiplication when it was there already". 21:26:45 Though those people would have you writing char *p = malloc((p_length + 1) * sizeof *p) instead. 21:26:50 hey, that's true 21:26:54 (Which is I guess fair enough.) 21:27:05 what if I decide to replace all occurrences of "chat" with "int" 21:27:14 (that's the kind of dumb things I do) 21:27:18 kmc: transcoding :( 21:27:28 Oh yeah, I will change my string array to be an array of cake_t instead! 21:28:20 what's wrong with transcoding elliott 21:28:57 it's yucky 21:28:59 feel free though! 21:29:00 yes there is a quality loss but in this case i am scaling down by 40% so i think there's more quality loss there ;P 21:29:04 It's borderline possible that someone might go along changing things to wchar_t's (or char32_t's or something) and also the string literals and forget to fix the allocation. But still. 21:29:39 phone won't play 720p h264 :/ 21:29:54 and the screen is only 800x480 anyway ;P 21:29:57 - COMING IN 1991 - NEVADA SMITH IN... "JOURNEY TO THE CENTER OF THE EARTH" GEORGE BROUSSARD - AUTHOR 21:30:15 I don't know if the game referenced was actually made. 21:30:40 kmc: Watching things on phones is weird. 21:31:39 "Things on phones" is probably some kind of fetish site. 21:31:56 Now she's softly calling out for Kankri 21:31:58 There's things like pictures of a brick on top of a phone there. 21:32:08 atriq: What's a "Kankri"? 21:33:05 fizzie: I don't suppose you happen to use GRUB 2 with menu-hidey options? 21:33:25 atriq: Oh, never mind; I found out already. "Kankri is a village development committee in Rukum District in the Rapti Zone of western Nepal. At the time of the 1991 Nepal census it had a population of 4210 people living in 851 individual households." 21:33:32 Weird thing to call out for, though. 21:33:56 fizzie, I believe she's referring to the Homestuck character 21:34:06 https://help.ubuntu.com/community/AndroidVideoEncoding#MPEG4_.28standard.29_encoding this person's ffmpeg options seem highly suspect 21:34:10 fizzie, you've not been keeping up have you 21:34:30 Phantom_Hoover: Very much a negative. 21:34:42 atriq appears to be listening to some sort of homestuck erotica 21:34:56 out of character for him, but perhaps it has satellite appeals 21:34:59 One of my friends suffers from a head injury 21:35:07 This leads her to black out from time to time 21:35:46 I'm in a group Skype call with her, and she's been blacking out a lot 21:36:20 uh 21:36:22 that sounds somewhat serious 21:36:24 Phantom_Hoover: I think I'm somewhere like end of act 5. 21:36:28 she should probably be in hospital 21:36:35 fizzie, you haven't even watched cascade have you 21:36:35 Phantom_Hoover: So about 1200 pages behind. 21:36:35 Apparently Kankri refers to her boyfriend, who cosplays Kankri 21:36:39 you're a year behind 21:36:39 Phantom_Hoover: No. 21:36:42 Phantom_Hoover: Yes. 21:37:00 you don't even know about half the cast any more 21:37:03 She's seen a doctor and there's nothing they can do 21:37:05 Phantom_Hoover: True. 21:37:09 -!- elliott has left ("Leaving"). 21:37:31 Phantom_Hoover: But I'll catch up any day now. 21:37:35 what, they can at least guess a little and prescribe some drugs 21:37:35 -!- monqy has left. 21:37:44 atriq, damn, what kind of head injury was this 21:37:47 something antiepileptic perhaps? 21:37:56 Slammed into a locker by a chav 21:38:19 i am: glad i don't live in hexham 21:38:25 She doesn't. 21:38:32 She's elsewhere 21:38:38 fuck i'm in england now 21:38:40 There's only about 3 readers of Homestuck in Hexham 21:38:54 You're in Coventry. Coventry's practically France. You're safe. 21:39:17 there was a dead body in the woods nearby! 21:39:30 Was it your body? 21:39:48 hmm possibly 21:40:21 There was someone knifed about 400 metres from here a while ago. 21:40:38 There was someone hammered to death in Hexham last year 21:41:23 Alcohol kills 21:41:37 switch statements in C don't need a default: condition, right? 21:42:05 Arc_Koen: I think if you don't supply a default, it just does nothing for that case 21:42:37 Arc_Koen: Right. 21:42:40 that's what I thought to and it worked; then I thought "maybe it does need it" so I added one and it crashed 21:42:44 atriq, what happened to the chav 21:42:58 Nobody knows 21:43:09 (that is, "default: }" caused a syntax error) 21:43:14 Mainly because she, due to the head injury, forgot which chav it was. 21:43:33 Arc_Koen: That's because a label needs to point to a statement. 21:43:41 Arc_Koen: "default: ; }" would be legal, if useless. 21:43:51 the perfect crime (i am the worst) 21:43:53 Arc_Koen: (If there is no matching case and no default, the switch body is just skipped.) 21:44:39 default: break; } 21:44:42 cocaine's a hell of a drug 21:44:56 FreeFull: Well, that's also legal and also useless. 21:45:09 Did you know S-Lang allows you to supply a number to break, so you can break out of nested loops 21:46:01 FreeFull: Did you know Perl allows you to supply a label to break, so you can break out of a particularly labeled enclosing loop? 21:46:17 There was something else with a numeric multilevel break, too. 21:46:30 PHP, right. 21:46:38 "break accepts an optional numeric argument which tells it how many nested enclosing structures are to be broken out of." 21:46:46 Probably others too, of course. 21:47:35 (Okay, in Perl's case it's "last" and not "break", but anyway.) 21:47:44 fizzie: a goto is C's labelled break =P 21:48:09 FreeFull: Sure, though the label goes in the other end. 21:48:35 yeah, i like perl's labeled break 21:49:04 LOOP: while (...) { ...; last LOOP; ... } vs. while (...) { ...; goto GET_ME_OUT_OF_HERE; ... } GET_ME_OUT_OF_HERE: ... 21:49:47 goto is a fine solution except that some programmers will run screaming in horror at any mention of goto 21:49:55 It's CONSIDERED HARMFUL. 21:49:59 i know, right? 21:50:30 this is because like forty years ago, some propaganda was needed in order to convince programmers to use anything that *isn't* goto 21:50:43 back when structured programming was a controversial new idea 21:51:05 goto is used in the Linux kernel for handling errors 21:51:12 And it's cleaner than any other C solution 21:51:33 and people like hard rules because it absolves them of the need to think 21:51:34 -!- elliott has joined. 21:51:52 fizzie: I don't suppose you happen to use GRUB 2 with menu-hidey options? 21:52:05 The one useful hard rule for not writing bad code is "Don't write code, ever" 21:52:06 which is why it's "goto is evil!!!!!" and not "goto is sometimes useful but should be avoided generally" 21:52:07 elliott, I have significant evidence suggesting that I'm going to play a video game that will destroy the world. 21:52:15 If you don't write code, you can't write bad code :) 21:52:18 Please advise. 21:52:19 elliott: I'm not sure what options those are. 21:52:23 atriq: hi 21:52:30 also the teaching of programming updates at a glacial speed compared to actual programming practice 21:52:33 fizzie: Well, uh, do you get a menu when you start up GRUB? 21:52:45 elliott: I do. So I suppose I'm not. 21:52:48 elliott: You always get a menu if you hold shift while grub is loading 21:52:48 perhaps in 2012 warning students over the evils of goto should not remain a high priority 21:52:53 FreeFull: Yes. 21:53:17 Java doesn't even have a goto 21:53:36 goto is a reserved keyword just so people can't use it 21:53:37 atriq, are you playing sburb 21:53:54 yeah instead you use an AbstractSingletonControlFlowProxyFactoryIteratorBeanProxy 21:54:06 much cleaner than goto 21:54:31 FreeFull: It does have the labeled break, though. 21:54:52 Similar to Perl's, with a label of the iteration statement to break out from. 21:54:53 Multi-level break is just a delimited continuation anyhow. 21:54:58 pikhq_: Did I ask you yet, I forget. 21:55:20 no it's not 21:55:59 -!- jix has joined. 21:57:02 kmc: Sure it is. 21:57:29 not first class 21:57:42 Wrong "is". 21:57:50 continuations are so general that it's not meaningful to say "foo is just continuations" unless you mean that it's equally powerful 21:58:05 every single control flow feature can be described as a limitation of continuations 21:58:08 * elliott objects to the conflation of "continuations" and "delimited continuations". 21:58:13 The latter are much more well-behaved. 21:59:09 x: goto x; 21:59:20 -!- zzo38 has quit (Remote host closed the connection). 21:59:56 what? continuations aren't powerful 22:00:00 you can do anything without continuations 22:00:04 Phantom_Hoover, quite possibly. 22:00:27 coppro pro troll mode 22:00:45 One of my internet friends, who reads MS Paint Adventures, has been suffering mysterious blackouts where she remains surprisingly lucid, although significantly more emotional. 22:01:10 -!- elliott has left ("Leaving"). 22:01:19 atriq: are those two things related? 22:01:51 Adding to this is the fact that I have thrown enough money at the Homestuck Vidoe Game kickstarter to receive a physical copy 22:01:52 * oerjan swats coppro for chasing away elliott -----### 22:02:00 atriq, oh well 22:02:07 can i come too or am i too old and square now 22:02:14 is there a shell redirection command similar to | and >, but which redirect as the "argv[1]" of the next command? 22:02:16 If you get a copy! 22:02:22 oh dear 22:02:28 Arc_Koen: $(foo)? 22:02:45 coppro: I think you need to add "" somewhere 22:02:57 possibly 22:03:12 Maybe not 22:03:37 Phantom_Hoover, I'm pretty sure you're, if anything, slightly younger than me, and just a victim of the difference between the education system in Scotland and in England and Wales. 22:04:09 If memory serves. 22:04:14 "$( foo )" 22:04:33 This seems scarily TemplateHaskell 22:04:34 Spaces for clarity and not necessary 22:04:35 atriq, erm right 22:05:09 coppro, FreeFull: I'm not sure what you mean 22:05:38 But yes, if we both receive copies of SBurb, I will certainly invite you to my session. 22:05:51 $(foo) is the same as the old school `foo`, but nicer syntax which nests properly 22:06:07 Arc_Koen: $( ... ) puts the redirection output as the literal argv[1] string. if you want argv[1] to be a filename containing the output, try <( ... ) 22:06:23 Arc_Koen: rather than foo | bar 22:06:31 and nested quoting is a lot less hairy with "$(foo "bar baz")" 22:06:33 bar "$(foo)" 22:06:37 (in bash, uses a named pipe) 22:06:50 "`"`"`"`" 22:08:47 it's not quite a named pipe in bash on linux 22:08:56 so, if sceql is a sceql interpreter and truth-machine.sceql a program in sceql, I can type ./sceql $(cat truth-machine.sceql) and it will work? 22:09:22 oh, "or the /dev/fd method of naming open files" 22:09:29 yeah 22:09:49 Arc_Koen: more quotes 22:09:57 procfs contains files which look like symlinks to nonexistent paths, but you can still open and use them 22:09:58 there might be spaces in that sceql file 22:10:01 it's weirdness 22:10:05 yes there are 22:10:06 oh, right 22:10:14 Arc_Koen: that depends on whether the sceql interpreter takes a program string or a filename as argument 22:10:22 it takes a string 22:10:28 then yes 22:10:46 Arc_Koen: There are often also reasonably small limits of how much things you can push through the command line arguments. Like, "four kilobytes" kind of small. 22:10:56 (I don't know how long sceql programs tend to be.) 22:11:47 (POSIX guarantees 4096 characters as the sum total of arguments. Some systems of course are happy with more.) 22:11:54 hmmm well it doesn't seem to work, but that could be because of a bug in the interpreter, or in the sceql program 22:12:11 linux had a fun denial of service bug relating to huge command lines 22:12:20 Admittedly, if the interpreter takes a string, there's not much you can do to get around the command line length limit. 22:12:23 olsner: did you just say the spaces in the program file will split it into several arguments? 22:12:43 no, I just implied it 22:13:19 oh, ' quotes don't work because they take $(...) directly as the string, but " quotes work 22:13:24 thank you guys 22:13:30 argv is an array of pointers to strings; they can all point to the same string if you like 22:13:58 so userspace can construct a huge command line and pass it to execve 22:14:01 A true bash person would recommend you use ./sceql "$(< truth-machine.sqecl)" instead. 22:14:08 -!- elliott has joined. 22:14:10 without actually using much memory in userspace 22:14:13 ("The command substitution $(cat file) can be replaced by the equivalent but faster $(< file).") 22:14:44 but the kernel would not realize they are the same string, and so would allocate a huge amount of memory in the new process 22:14:58 yes it's important to micro-optimize your shell scripts for speed 22:15:16 one time i posted a shell script which used an unnecessary 'cat' 22:15:22 it brought shame upon my entire family 22:16:24 kmc: I, uh, don't suppose you use GRUB 2. 22:16:27 alias cat < 22:16:30 wait 22:16:37 $(cat <(cat <(cat <(cat <(cat file))))) 22:16:43 Fuuuck 22:16:44 alias cat='<'? 22:16:56 Don't do $(< /dev/urandom) 22:17:22 Phantom_Hoover: good job concatenating files with that 22:17:27 s/job/luck/ 22:18:42 Someone should inject in all cat binaries a thing that'd collect aggregate statistics on which fraction of cat invocations actually concatenate things. 22:18:58 % echo $( Europe/Helsinki Europe/Helsinki 22:19:12 % cat Europe/Helsinki 22:19:17 Europe/Helsinki 22:19:17 weeeeeeee interpreter works fine now 22:19:27 < isn't exactly equivalent to cat anyway 22:19:53 The latter works identically without the “cat”, too. 22:20:10 freefull: Yeah, e.g. cat -A is useful. 22:20:23 If you do < somefile on its own 22:20:35 It won't print that to the terminal 22:22:48 % Europe/Helsinki 22:22:53 Europe/Helsinki 22:25:15 ion: Which shell is this? 22:25:19 zsh 22:25:26 Fancy-schmancy. 22:26:36 0 freefull@freefull-hp:~$ 0 freefull@freefull-hp:~$ 22:26:52 Inventive hostname. 22:26:58 That's significantly less fancy, too. 22:27:34 zsh's behaviour seems less consistent. 22:27:40 elliott: I tried =P 22:27:46 If the command "defaults" to copying stdin, then ";" should act as "cat". 22:28:03 My hostnames come from Pan Sonic song names. They tend to be short and kind of interesting. 22:28:10 feh 22:28:13 stupid set theorists 22:28:33 bunch of twats 22:28:45 Bash doesn't like a ; without a command 22:28:54 -bash: syntax error near unexpected token `;' 22:29:19 "ooh I've got a great idea. Let's make these things called ordinals and cardinals. All cardinals are ordinals, but not the other way around. Let's also call some ordinals 'limit ordinals' and some cardinals 'limit cardinals' all cardinals will be limit ordinals but not all limit ordinals will be cardinals. Limit cardinals will be rare and magical.' 22:29:31 maybe I should start naming my computers in welsh 22:30:04 "let's go further and call all non-limit ordinals successor ordinals, and all non-limit cardinals successor cardinals. Then all successor cardinals are limit ordinals!" 22:30:59 Which of the ordinals and cardinals are limit ordinals/cardinals? 22:37:02 Let's make these things called ordinals and cardinals. All cardinals are ordinals, but not the other way around. 22:37:14 the concept of a subset annoys you, coppro? 22:38:22 Other than cardinals being limit ordinals, which you said 22:39:19 Phantom_Hoover: No, it's the confusing terminology which annoys me 22:40:30 FreeFull: \aleph_\alpha is a limit cardinal if and only if \alpha is a limit ordinal 22:40:36 what annoying terminology 22:40:38 some authors exclude \aleph_0 from the limit cardinals as well 22:40:51 Phantom_Hoover: The use of confusingly similar noun phrases 22:41:02 you mean 'limit' 22:41:04 in particular, there are non-limit cardinals that are limit ordinals 22:41:53 coppro: So is \aleph_(\aleph_0) a limit cardinal? 22:41:58 yeah, and? 22:42:13 'limit' depends on the structure of the thing it's applied to 22:45:01 Phantom_Hoover: The statement "Is \aleph_1 limit?" is nonsensical 22:45:11 The interpretation of limit does not depend on what you apply it to, it depends on context 22:45:17 FreeFull: Yes 22:45:20 ... 22:45:31 \aleph_{\aleph_\alpha} is a limit cardinal for all ordinals \alpha 22:45:56 yes coppro when you can interpret \aleph_1 as a cardinal or ordinal you DO need to specify which kind of limit you're talking about 22:46:02 yes 22:46:07 that is what annoys me 22:46:22 i suspect coppro will _really_ hate category theory, then. 22:46:26 i don't see the problem here at all 22:46:39 why would you assume structural properties cross over between subsets like that 22:46:39 is it so great an obstacle to have to add 'cardinal' or 'ordinal' to the end of your question 22:46:41 thingy 22:47:01 or topology - whether a set is closed _does_ depend on the surround space. 22:47:09 *surrounding 22:47:32 oerjan: actually, I don't have that much of an issue with category theory 22:47:37 The issue I have is just that I confuse the two 22:47:46 is hexham near wales? 22:47:48 even when the context is provided, sorting things out in my brain is difficult 22:47:51 olsner, no 22:47:55 not at all 22:48:05 elliott: I don't. It just is annoying to me that I have to expend mental effort to think about the distinction 22:48:16 it's very far from wales 22:48:30 olsner: yes 22:48:32 coppro, wat 22:48:57 you'd have to think about whether you meant the cardinal or ordinal anyway 22:49:27 i mean 22:49:56 if you asked "is aleph 1^2 == aleph 1" the answer would be different depending on if you meant the cardinal or ordinal 22:49:59 coppro: when you have two different topologies on the same space, you get the same trouble with limits there too. norm topology vs. weak *-topology comes to mind. 22:50:12 oerjan: yeah, topology annoys me 22:50:16 elliott: so you all have a welsh accent then? that is awesome 22:50:18 Phantom_Hoover: but it would be more intuitive 22:50:21 'sall 22:50:26 coppro, stick to cs please 22:50:35 Phantom_Hoover: dude, I'm a math major 22:50:37 wat 22:50:42 all this time 22:51:00 coppro the mathsochist 22:51:21 switch to cs then, you may have an easier time of it 22:53:59 Phantom_Hoover: no thanks 22:54:02 graph theory is too awesome 22:54:05 also set theory 22:54:07 also logic 22:56:31 set theory assignment was easy this week, which is a nice relief 22:56:47 I want to put dnolen and jimduey in a particle collider and collide them. 22:59:47 would that work 22:59:56 they must be pretty small 23:00:20 who and who 23:02:07 elliott, dnolen wrote a delimited continuations thing for Clojure, and jimduey wrote an actually decent monads implementation for Clojure 23:02:19 so 23:02:45 Want to use reset/shift like syntax for using monads, rather than do notation 23:03:06 what does that mean 23:03:13 applicative notation can only describe applicatives 23:03:22 though of course you only need a syntactic construct for join 23:03:25 but then it gets very messy 23:04:08 A function that takes a value v :: (Monad m => m a) and does v >>= current_continuation 23:05:03 that doesn't really make any sense 23:05:08 since do notation is precisely a CPS translation 23:05:23 anyway going by the first few tweets on https://twitter.com/jimduey I wouldn't wish being collided with him on anyone 23:05:54 But do notation is possibly an _ugly_ CPS translation 23:06:00 what 23:06:58 reset/shift may be prettier 23:07:27 But do notation is possibly an _ugly_ CPS translation 23:07:29 what does this mean 23:07:45 elliott, it means I think do notation is ugly. 23:08:10 do notation is *literally* foo >>= current_continuation 23:08:47 But it's ugly to use. 23:09:14 ok 23:12:58 How is reset/join applicative in nature? 23:13:03 If that's what you're saying 23:13:24 Aaargh 23:13:29 Trying to write music 23:13:36 I've got a big build-up going 23:13:43 But I've got nothing for it to build up to 23:14:24 plagiarise! 23:14:40 atriq: have it end after the build-up 23:14:42 ~avant-garde~ 23:16:14 I thought applicative notation can only describe applicatives was supposed to be an analogy, but now I'm assuming not 23:16:35 well you want a nested, rather than linear, notation, yes 23:16:42 which sounds like applicative notation to me 23:17:54 Hmm 23:18:01 Good point 23:18:38 for instance (| const (putStrLn "hello") (putStrLn "world") |) 23:18:50 (| const (putStrLn "hello") (| const (putStrLn "world") (putStrLn "again") |) 23:18:51 er 23:18:52 (| const (putStrLn "hello") (| const (putStrLn "world") (putStrLn "again") |) |) 23:19:01 join (| putStrLn getLine |) 23:19:02 But what about with let? 23:19:30 (| const (putStrLn "name:") (| const (join (| putStrLn getLine |)) (putStrLn "ok") |) |) 23:19:37 probably that is unbalanced, it is too unspeakably ugly for me to check 23:19:39 (Clojure's let binds sequentially) 23:19:42 Sgeo: with let that is do notation 23:19:47 let a = foo; b = bar; c = quux; in d 23:19:47 --> 23:19:53 do { a <- foo; b <- bar; c <- quux; d } 23:20:31 But I'm thinking make them usable together nicely... although hmm, my idea of "nice" may be slightly warped 23:20:56 i agree 23:21:25 Still, would be nice to write code that mostly isn't written monadically-aware except for the parts that are 23:22:01 sounds like you want an effect system 23:22:11 a la eff, McBride's Frank, and so on 23:24:27 Thanks for pointing me to that stuff 23:25:08 np 23:25:12 it is not really "production ready" 23:25:20 also edwardk doesn't think it'll work well at all 23:32:16 Goodnight! 23:32:18 -!- atriq has quit (Quit: Leaving). 23:35:13 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 23:47:29 -!- kinoSi has quit (Read error: Connection reset by peer). 23:47:57 -!- kinoSi has joined. 23:48:48 Sgeo: elliott: is that filinski stuff relevant to this? (never read it.) 23:49:22 http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.8213 23:50:27 oerjan: maybe, not sure 23:50:28 oerjan, looks very relevant to what I was thinking of 23:50:39 Not sure if it's at all relevant to effects 23:52:54 That's interesting, the undelimited + one piece of state = delimited thing 23:55:25 i've read some critique of that, though. specifically that it only works if you don't mix it with using undelimited continuations in any _other_ way. 23:56:36 -!- Vorpal has quit (Ping timeout: 276 seconds). 23:56:57 http://okmij.org/ftp/continuations/undelimited.html 23:57:08 -!- Phantom_Hoover has joined. 23:58:00 "Many applications that use call/cc also contain mutable cells holding continuations, betraying the well-known Filinski's emulation of delimited control via call/cc and a mutable cell." 2012-10-07: 00:06:46 What is "Undoing Dynamic Typing"? 00:08:46 it's a euphemism for correcting really bad spellers hth 00:09:49 -> 00:10:02 oerjan: q 00:12:44 The paper uses "untyped" too m.. oh 00:12:56 I guessed untagged wouldn't be strongly typed 00:13:04 Hrm 00:34:07 -!- augur has quit (Remote host closed the connection). 00:39:10 -!- augur has joined. 00:43:55 -!- jiella_ has quit (Quit: Leaving.). 00:45:09 elliott: a 00:45:52 oerjan: q :) 00:46:17 elliott: n 00:46:35 r 00:46:45 yw 00:53:04 pikhq_: Is it true that Windows 8 only supports GPT? 01:00:53 It turns out delimc sucks 01:01:17 As in, it breaks if you don't use all the vars in the namespace where you want to use the stuff 01:02:10 As in, if import Data.Maybe worked but import qualified Data.Maybe as M didn't 01:03:46 -!- elliott has quit (Remote host closed the connection). 01:05:18 -!- elliott has joined. 01:07:43 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:20:09 elliott: Why because of me? 01:20:22 I forget. 01:24:11 * Sgeo is slightly unsure how to fix the issue 01:24:17 But I see what's causing it 01:27:16 I know how to fix it. 01:34:57 -!- hagb4rd has quit (Quit: hagb4rd). 01:39:50 -!- hagb4rd has joined. 02:30:31 * oerjan adds Gemooy to his TC belt 02:32:25 oerjan: congrats :) 02:32:28 -!- elliott has quit (Remote host closed the connection). 02:33:13 oerjan: Is that the belt of things you've type checked? 02:33:16 Or type checkers? 02:33:23 elliott: 19:28 Is there a reason that "a newtype constructor cannot have an existential context" in GHC? 02:33:32 no, it's the belt of things i've proved Turing complete 02:38:23 -!- elliott has joined. 02:39:20 Has oerjan been proved Turing Complete? 02:39:53 sounds dangerous 02:44:01 oerjan: your proof of 3-cell BF worked out, right? 02:45:06 yes 02:45:18 nice 02:45:22 ... wtf 02:45:23 http://esolangs.org/wiki/Collatz_function 02:45:32 I am now saddened 02:45:48 apparently the fact that the cartesian product of nonempty sets is nonempty is a consequence of the axiom of choice 02:45:52 :( 02:46:05 s/a consequence of/equivalent to/ 02:46:06 coppro: of _infinitely_ many, mind you 02:46:16 coppro: why would that make you sad 02:46:32 also, that's really sort of obvious. 02:46:58 oerjan: yeah, it is 02:47:05 elliott: I don't know 02:47:56 -!- elliott has quit (Remote host closed the connection). 02:58:08 Blah. 02:58:48 Major things such as Clojure vars being very much like Common Lisp symbols in some crucial ways should probably be documented in a place showing differences between Clojure and other lisps 03:03:03 -!- elliott has joined. 03:13:14 oerjan: hi 03:13:35 g'day 03:15:20 oerjan: should i convert my partitions to gpt 03:15:52 YES! 03:16:07 oerjan: help 03:16:21 general protection taunts, right? 03:16:50 yes. 03:25:00 -!- elliott has quit (Quit: Leaving). 03:25:13 -!- elliott has joined. 03:27:50 -!- elliott has quit (Remote host closed the connection). 03:32:49 -!- Frooxius has quit (Ping timeout: 246 seconds). 03:42:31 -!- elliott has joined. 03:46:26 -!- elliott has quit (Remote host closed the connection). 03:48:29 -!- baki^ has joined. 03:49:03 -!- baki^ has left ("dumplings you do, dumplings you don't"). 03:50:47 so I hear two stacks is enough to be tc 03:50:59 yep 03:51:14 let's try to build something out of two stacks that's not tc 03:51:22 actually I was thinking of using a deque 03:51:33 a deque alone is enough to be tc 03:51:54 with functions like "pop" and "push", and an instruction "toggle" to specify to which end of the deque those functions apply 03:52:52 with two stacks if you can do something like push2(pop1()) it is easy to emulate a tape; but here you can't 03:52:59 -!- elliott has joined. 03:53:27 (because you need to toggle before you can push to the other end; so you can't be pushing one side and popping the other at the same time) 03:54:31 if you are going to prevent the information from getting across some other way, you need to limit branching 03:55:41 I'm starting to see why Clojure exceptions suck so much 03:55:42 :< 03:55:44 to prevent stuff like "if pop() = 0, then toggle and push(0)"? 03:56:04 yeah 03:58:17 you may end up with essentially two coroutines that cannot do anything with each other other than yielding... 03:58:46 with no data passing 03:59:07 yep I was writing it down and it felt kind of lame 03:59:46 well there are boring ways to make something not turing complete 03:59:54 like putting a bound on space or time usage 04:00:08 which also includes any real system 04:07:22 -!- oerjan has quit (Quit: Good night). 04:07:58 http://sprunge.us/died 04:13:54 died 04:15:01 well sprunge just found a name for that language 04:24:11 elliott: I honestly don't know. 04:24:25 yaey 04:25:01 hmmmm actually I could just consider Super Stack! deprived from its cycle/rcycle instructions 04:25:15 it still has rev to reverse the entire stack 04:26:34 -!- elliott has quit (Remote host closed the connection). 04:31:04 anyway gnight 04:31:12 -!- Arc_Koen has quit (Quit: Arc_Koen). 04:31:41 -!- copumpkin has quit (Ping timeout: 255 seconds). 04:32:19 -!- copumpkin has joined. 04:34:41 -!- hogeyui has quit (Ping timeout: 244 seconds). 04:36:05 -!- zzo38 has joined. 04:47:49 -!- hogeyui has joined. 04:50:23 If you think the note about not moving the article about FurryScript to the main namespace is wrong, you can remove it, like you would remove other wrong things on wiki. 05:10:08 -!- ogrom has joined. 05:23:49 -!- hagb4rd has quit (Ping timeout: 260 seconds). 05:44:12 -!- Nisstyre-laptop has quit (Remote host closed the connection). 05:53:35 every time flash plugin crashes, take a drink 06:02:49 -!- Nisstyre-laptop has joined. 06:07:30 i'll just fondle myself in this leftover panel 06:08:14 just watched an ad for internet explorer featuring dubstep 06:08:35 kmc: every time pulseaudio causes a problem, take a drink 06:11:43 now i have two problems :( 06:17:43 I wrote on a paper once how to make double negation elimination in (Kleisli (Cont r)) and yes I can see easily how to work. I wrote: ((x->(0->r)->r)->(0->r)->r)->(x->r)->r I think this is the way, isn't it? 06:18:17 (I figure out pretty easily how to write such a function of such a type since we have 0 is initial object here. 06:27:28 -!- copumpkin has quit (Ping timeout: 246 seconds). 06:28:03 -!- copumpkin has joined. 06:39:39 -!- copumpkin has quit (Ping timeout: 256 seconds). 06:40:15 -!- copumpkin has joined. 06:51:53 -!- zzo38 has quit (Remote host closed the connection). 06:58:09 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 07:01:38 kmc: I don't think I get the film. 07:01:46 (Were you the one who recommended it to me?) 07:37:54 is there any language with a brainfuck-style tape and : a) a mov instruction b) a goto instruction c) the ability to copy the location of the instruction pointer into the current tape pointer 07:39:34 x86 07:44:52 -!- atriq has joined. 07:46:08 (comp bind-cont bind-cont) 07:46:14 Hello! 07:46:17 Aaaargh! 07:46:18 That should be join in my syntax 07:46:18 Oh no! 07:46:19 I think 07:47:08 atriq, hmm? 07:47:13 I said "Hello" 07:47:42 Hi 08:03:09 You know, I'm actually really surprised that Fueue is Turing-Complete 08:11:38 -!- ais523 has quit. 08:14:19 -!- MoALTz__ has joined. 08:17:30 -!- MoALTz_ has quit (Ping timeout: 264 seconds). 08:19:28 atriq: why? 08:20:00 When I made it, I looked at it and thought "This is impossible to do anything with" 08:20:02 $ obviously gives rise to flow control 08:20:07 "It's an utterly ridiculous language" 08:44:05 -!- MoALTz_ has joined. 08:47:24 -!- MoALTz__ has quit (Ping timeout: 260 seconds). 08:54:22 -!- MoALTz__ has joined. 08:57:19 -!- MoALTz_ has quit (Ping timeout: 245 seconds). 09:02:30 -!- atriq has quit (Ping timeout: 264 seconds). 09:30:26 -!- atriq has joined. 09:48:30 -!- kinoSi has quit (Read error: Connection reset by peer). 09:49:18 Anyone know where I can get help with MuseScore? 09:49:28 -!- kinoSi has joined. 10:06:24 -!- Vorpal has joined. 10:24:49 -!- ogrom has quit (Quit: Left). 10:32:49 -!- Arc_Koen has joined. 10:33:05 hello 10:34:04 Hey 10:37:10 -!- MoALTz__ has quit (Quit: brb). 10:37:27 has someone done some work about equivalency between programming languages in terms of complexity? 10:38:21 -!- MoALTz has joined. 10:38:27 I feel stupid everytime I try to prove something TC by emulating brainfuck, when that something looks much more powerful than brainfuck 10:39:11 -!- Phantom_Hoover has joined. 10:42:31 Prove it TC by emulating Underload 10:42:46 Or Eodermdrone 10:42:57 Or a turing machine 10:43:08 If you write an Eodermdrone interpreter you are officially esolanger of the year 10:43:19 Of 2008, anyway 10:44:27 -!- Frooxius has joined. 10:53:10 yeay, 2008 was the best year 10:54:29 hey, do you have a translation for "suite presque nulle" into english? it means "an (infinite) sequence (x0, x1,...) for which there exists N such that for every n > N, xn = 0" 10:54:40 (so basically it's an infinite sequence that's not so infinite after all) 10:55:11 literally, "suite presque nulle" means "almost zero sequence" 11:08:59 -!- barts has joined. 11:10:11 -!- Jafet has quit (Quit: Leaving.). 11:12:13 -!- barts_ has quit (Ping timeout: 256 seconds). 11:19:35 The term "almost all zero" seems to be used in the context of sequences sometimes. 11:24:35 Could it be a geometric sequence with a ratio between -1 and 1 (exclusive), or is it something else? 11:25:20 > [1,2,3,4] ++ repeat 0 11:25:22 [1,2,3,4,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,... 11:25:40 Something like that? 11:31:16 > map x [1..] where x n = 2^(n-1) 11:31:18 : parse error on input `where' 11:31:36 > let x n = 2^(n-1) in map x [1..] 11:31:37 [1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192,16384,32768,65536,131072,... 11:31:43 Woops 11:31:51 > let x n = (1/2)^(n-1) in map x [1..] 11:31:53 [1.0,0.5,0.25,0.125,6.25e-2,3.125e-2,1.5625e-2,7.8125e-3,3.90625e-3,1.95312... 11:31:59 Something like this 11:37:15 no it means a sequence where a finite sequence contains all non-zero elements of the sequence 11:37:34 So something like what atriq did then 11:38:06 not necessarily, the non-zero elements could be interspersed with many zeros as well 11:38:33 > [1,2,0,3,0,4] ++ repeat 0 11:38:35 [1,2,0,3,0,4,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,... 11:39:32 > repeat 0 ++ [1,5,4,0,2] 11:39:32 -!- atehwa has quit (Ping timeout: 248 seconds). 11:39:34 [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,... 11:40:20 -!- atehwa has joined. 11:40:59 If there's a finite number of zeros, though, then one of them is the last zero, and that n > N, xn = 0 holds. 11:41:50 hmm, did you mean non-zero? 11:41:59 -!- Frooxius has quit (Quit: ChatZilla 0.9.89-rdmsoft [XULRunner 1.9.0.17/2009122204]). 11:56:44 【MMD】みんなのリズム天国　霊夢のレスラー会見　パーフェクトプレイ http://youtu.be/k9wt5TrI7II 11:56:46 -!- Frooxius has joined. 11:57:48 olsner: Yes. 12:01:35 http://i.imgur.com/tRUUT.jpg 12:02:01 The tRUUT is out there. 12:17:49 ion: i agree. 12:30:20 yes, what barts said 12:30:28 so you can say "almost all zero"? 12:30:41 like, "an almost all zero sequence" or something? 12:31:19 or "that sequence is almost all zero" 12:38:19 Or the members/elements of this sequence are almost all zero". 12:39:59 "-- let R = (r1,r2,...) range over all sequences of non-negative integers which are almost all zero." -- from a random paper. 12:45:59 -!- jiella has joined. 12:46:01 -!- jiella has left. 12:46:15 -!- jiella has joined. 12:48:09 -!- Jafet has joined. 13:12:07 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 13:26:18 -!- mig22 has quit (Quit: mig22). 13:30:16 -!- ogrom has joined. 13:42:36 -!- atriq has quit (Quit: Leaving). 13:50:50 -!- MoALTz has quit (Read error: Connection timed out). 13:51:47 -!- MoALTz has joined. 14:10:13 -!- MoALTz has quit (Read error: Connection timed out). 14:15:16 -!- jiella has quit (Quit: Leaving.). 14:16:23 -!- atriq has joined. 14:16:51 -!- MoALTz has joined. 14:16:54 I don't recall seeing itidus20 in a whie 14:19:39 -!- MoALTz has quit (Client Quit). 14:19:57 I hope he's okay 14:22:18 -!- atriq has quit (Quit: Leaving). 14:24:42 -!- MoALTz has joined. 14:25:55 -!- Ginto8 has quit (Ping timeout: 246 seconds). 14:38:45 -!- MoALTz_ has joined. 14:41:14 -!- MoALTz has quit (Ping timeout: 240 seconds). 14:51:22 Apparently Icaros comes with a lolcode interpreter 14:52:00 -!- Phantom_Hoover has joined. 14:56:27 fizzie: that would be an error, you cannot enumerate all such sequences with natural numbers. 14:56:35 fizzie: you should inform the author about this. 14:58:16 FreeFull, what is icaros and how can i kill the people involved 15:01:07 Phantom_Hoover: Why kill the people involved? 15:01:13 It's a distribution of Aros 15:01:21 lolcode is an abomination 15:01:26 http://www.icarosdesktop.org/ 15:10:14 anyone knows where the names "qdeql" and "sceql" came from? 15:19:50 barts: I don't think it was saying that it could; just that R ranges over all such sequences, and r1, r2, ... are the elements of R. 15:26:05 -!- elliott has joined. 15:45:08 shachaf: which film? 15:46:15 Why did my client join this channel? 15:46:15 elliott: You have 1 new message. '/msg lambdabot @messages' to read it. 15:46:22 I don't think I have it on autojoin... 15:53:07 -!- atriq has joined. 15:58:08 @messages? 15:58:09 Sorry, no messages today. 16:10:55 so really nobody has implemented eodermdrome? 16:11:11 it seems like it should not be that hard to produce a slow implementation 16:11:11 No 16:11:25 oklopol began, according to the lore of #esoteric 16:11:30 But never finished 16:11:32 kmc: i think the problem is that the slow implementation is way too slow 16:11:48 kmc: or maybe just that everyone who is the kind of person who would implement it is the kind of person who wants to use the fancy algorithms to make it fast 16:12:07 well my fancy algorithm would be "someone else's SAT solver" 16:12:17 that is so cheating 16:13:11 well ;P 16:14:13 elliott, what makes reify 6 (\p -> reflect p + reflect p) better than (\p -> p + p) 6? 16:14:39 atriq: they're not the same thing 16:14:44 the "p" value is irrelevant 16:14:54 it is its *type* that matters 16:14:57 p there is just Proxy 16:15:03 it's just Proxy of the right type 16:15:09 let me get an example i hpasted ages ago 16:15:27 atriq: http://hpaste.org/66715 16:16:07 atriq: basically in this example, you can think of the p in "forall p. (Reifies p MyConfig) => ..." as a *value* of type MyConfig 16:16:14 just it exists at the type level 16:16:16 lifted there by reify 16:16:20 and brought back down by reflect 16:18:10 I'm not really understanding this 16:19:12 that's ok, I didn't either :p 16:19:25 atriq: basically, think of reify as turning a value into a type, and reflect as turning a type into a value 16:19:41 when you do reify 6 (\p -> ...), p :: Proxy s (for some s we *don't know*) 16:19:49 you can think of that s as an Integer at the type level 16:19:51 so p :: Proxy 6 16:20:10 Okay 16:20:10 and since you have (Reifies s Integer), you can do reflect p :: Integer 16:20:15 but the value p doesn't matter 16:20:21 you only get passed the value p so you have a way to get at the type 16:20:25 meanwhile: * voidf (befd1cd9@gateway/web/freenode/ip.190.253.28.217) has joined #haskell how to return the type in a function? 16:20:31 atriq: imagine if the proxy wasn't there 16:20:34 you'd have 16:20:38 reify :: a -> (forall s. Reifies s a => r) -> r 16:20:44 but of course that's invalid, because you don't reference "s" anywhere 16:21:20 atriq: anyway a compelling example is modular arithmetic 16:21:47 atriq: with reflection, we can have a type (Mod p Integer) 16:21:51 atriq: which represents integers, mod p 16:21:57 Okay 16:22:01 atriq: and it can be an instance of Num 16:22:05 Oh, I see 16:22:12 because we use reflection to reify the p being used into the type parameter p there 16:22:23 I think I hpasted that too, let me find it 16:22:50 atriq: http://hpaste.org/66565 16:23:00 actually it's (Mod Integer p) there 16:23:04 Actually, I was wondering how you could do that the other day 16:23:07 which is slightly inferior: you can't give it a Functor instance 16:23:11 but whatever 16:23:11 Wow 16:23:38 atriq: note that although "modular n = r where r = Modular (n `mod` modulus r)" appears to be circular, it is actually just a silly trick 16:23:45 atriq: modulus doesn't examine its value, it only cares about the type 16:24:02 so we just use that circularity because Modular (n `mod` modulus ...) happens to have the type we want to give modulus (i.e. n `Mod` p) 16:24:05 to get the modulus value 16:24:13 anyway look at the commented-out modulo definition instead 16:24:22 it does more or less the same thing but without the hack 16:24:30 oh! 16:24:31 i lie 16:24:37 modular turns an integer into the mod form 16:24:42 modulo' takes it out 16:25:00 modulo is just modulo' but less general 16:25:05 but modulo is the actual useful one, so look at it instead 16:25:07 atriq: anyway basically you can do: 16:25:34 atriq: ((4 + 4) * 2) `modulo` 8 :: Integer 16:25:44 atriq: and get 0 16:25:56 but it's not just mod, because the mod is done at each step, of course, like regular modular arithmetic 16:26:12 atriq: and, as a bonus, the "4" and "2" inside actually have a type that encodes the 8 16:26:21 so you can't mix them with regular Integers or so on without conversion 16:26:41 anyway reflection is sort of confusing but once you get the hang of it, it is very cool 16:26:47 I think the original Oleg paper also did the modular arithmetic thing 16:31:13 I think I understand it 16:31:14 now 16:31:26 kmc: you might enjoy this GHC dark magic: http://hpaste.org/66699 16:31:30 (oleg's reimplementation of reflection) 16:32:06 atriq: (you may also find the simpler modular arithmetic definition it comes with helpful for understanding it) 17:12:34 -!- atriq has quit (Ping timeout: 260 seconds). 17:18:45 -!- atriq has joined. 17:21:39 -!- jiella has joined. 17:29:19 -!- zzo38 has joined. 17:31:15 -!- oerjan has joined. 17:40:01 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 17:41:45 no, i finished eodermdrome 17:42:07 it's just graph rewriting, it's not hard to do. but also what elliott said. 17:42:51 -!- ogrom has quit (Quit: Left). 17:44:10 " has someone done some work about equivalency between programming languages in terms of complexity?" at least between different models of computation 17:44:50 at least iirc i finished it, it's definitely gone in any case. 17:46:02 oh, you finnished it? 17:47:05 yes 17:47:08 Does "finnishing" mean the same as finishing and subsequently misplacing the finished thing? 17:47:14 yes 17:47:20 or finishing and violently deleting 17:47:24 gave it some koskenkorva and didn't speak a word to it for years. 17:47:31 hmm 17:47:34 that's a nice definition 17:47:44 fizzie's that is 17:54:59 yes, I think it's funnier if you imagine a more violent end than just misplacing it though 18:00:10 olsner: What are you implying there! Finns aren't violent. 18:02:18 oh, of course not 18:03:15 RARRR I HIT YOU WITH AN AXE FOR IMPINGING ON MY HONOR 18:03:31 Sorry, in retrospect that's more of a Norwegian thing to do. 18:03:40 yeah, everyone knows the finn's weapon of choice is the knife 18:04:26 I suppose. Though we do have a certain amount of ax-related crime too, I believe. 18:04:44 It's like, the people living in cities knife each other, while the people living in the countryside use axes. 18:04:50 But we're not a violent people. 18:05:18 Back when I quoted from Finnish songs a while ago there was an axe involved. 18:05:22 In the lyrics, I mean. 18:07:21 Maybe I should learn how a complicated library works before trying to fix it. 18:10:25 fizzie: There was the one axing incident in the metro in Helsinki though. 18:13:10 -!- Phantom_Hoover has joined. 18:13:46 kmc: _The Big Lebowski_ 18:13:51 axe and you shall receive 18:14:12 jiella: Well, I'm sure. It was a sort of a generalization. 18:14:26 There's probably been a large number of stabbings in the countryside, too. 18:14:29 axe not for whom the bell tolls 18:15:05 it's natural to use an axe when you're out chopping down trees anyhow 18:16:02 i never heard of any incidents with axes in uk undergrounds 18:16:26 oerjan: Don't put all your eggs in one baxet. 18:16:29 fizzie: are finns ever happy 18:16:43 17:41:45: no, i finished eodermdrome 18:16:48 wasn't your interpreter crazy slow 18:16:51 Olen metsuri ja olen kunnossa! Nukun koko yön, ja työskentelen koko päivän! 18:17:45 elliott: I'm a Finn and I am sometimes. 18:18:53 amazingly, google translate seemed to have no problem at all with that sentence 18:19:30 It's reasonable cogent. Though the translation of the "I'm okay" part is maybe not the best one for that context. 18:19:48 fizzie: Tja, mainly I find it funny that the only axe killing I can remember was done in a Helsinki metro... You can't really get any more urban than that in Finland. 18:20:02 fizzie: when i used "OK" it gave OK in the answer, so i changed it. 18:20:24 *translation 18:20:46 oerjan: "And have buttered scones for tea" => "Ja on voideltuun teeleipiä teen" -- "And has buttered scones for tea" => "Ja on buttered teeleipiä teen". 18:20:55 oerjan: I have no idea why it doesn't know about "buttered" in the second case. 18:21:51 it's because a single person cannot have buttered scones 18:22:07 But it's in the first person in the first case. 18:22:09 you need to be at least two to share the joy 18:22:15 oh. 18:22:21 First person singular, I mean. 18:22:33 On Wednesdays I go shoppin' / And have buttered scones for tea. 18:22:55 oerjan: certainly a single person can 18:23:01 it's not _entirely_ unlikely someone put that exact text into google translate before. 18:23:10 coppro: shush, you 18:23:21 "I cut down trees. I wear high heels." => "Olen kaataa puita. En käytä korkokenkiä." 18:23:26 Sometimes it inverts the meaning. 18:23:43 this conversation would be more interesting if I knew finnish 18:25:01 you don't know finnish? 18:25:43 fizzie: it reinverts it in the other direction too... 18:26:44 "En käytä korkokenkiä. Käytän korkokenkiä." => "I wear high heels. I use high heels." 18:26:54 Machine learning in action. 18:28:10 Älä ammu, tulemme rauhassa! 18:28:27 if it were an _evil_ machine, it would invert that. did it? 18:28:38 No. 18:28:46 hm, fiendish. 18:29:04 finndish 18:29:05 "We come in peace, we shoot to kill" also goes through moderately right. Though the latter part is just atrocious grammar. 18:29:18 ("Tulemme rauhassa, me ampua tappaa.") 18:30:42 oerjan: But "I wear shoes" turns into "I don't wear shoes". 18:31:01 oerjan: And "I wear hats" to "I don't wear hats". 18:31:17 But "I wear cloths" is approximately "I clothes". 18:31:26 With the e in the source, too. 18:31:41 "I wear pants" => "I don't wear pants". Well, it's reasonably consistent. 18:31:50 -!- monqy has joined. 18:31:58 so it has some trouble with finns wearing things. probably because of all the sauna. 18:32:30 Plain "I wear" turns (understandably) into "I don't wear/use". (The word has both meanings.) 18:33:01 so that you can reuse the same sentence to say what you're wearing inside and outside the sauna? 18:33:27 nah you need to use the saunative case 18:33:34 Maybe I should fix some of those translations and see if it takes. 18:34:27 Well, it remembered it for me. 18:34:55 Aw, no longer when I cleared the whole input text. 18:37:42 hey, do you have a translation for "suite presque nulle" into english? it means "an (infinite) sequence (x0, x1,...) for which there exists N such that for every n > N, xn = 0" 18:37:48 eventually zero, i think 18:38:08 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 18:39:00 > 1:2:3:(repeat 0) 18:39:01 [1,2,3,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,... 18:39:26 @tell Arc_Koen "eventually zero sequence" 18:39:27 Consider it noted. 18:39:34 > seq ([1..]++[0,0..]) 18:39:35 Overlapping instances for GHC.Show.Show (t -> t) 18:39:36 arising from a use of `... 18:39:51 :t seq 18:39:52 forall a t. a -> t -> t 18:40:06 :t ([1..] ++ [0,0..]) 18:40:07 forall t. (Num t, Enum t) => [t] 18:40:12 seq is the strictness forcing primitive 18:40:19 Oh, wrong thing 18:40:28 also, the parentheses around repeat 0 are redundant 18:40:33 > subsequences [1,2,3] 18:40:34 [[],[1],[2],[1,2],[3],[1,3],[2,3],[1,2,3]] 18:40:45 oerjan: But what are all the instances of Show (t -> t) that lambdabot has? 18:41:11 > subsequences ([1..]++ repeat 0) 18:41:13 > print "a" 18:41:13 can't find file: L.hs 18:41:16 argh 18:41:17 18:41:22 L.hs? 18:41:33 FreeFull: race condition, i think 18:41:42 race with someone doing @let? 18:41:55 or with me, i dunno 18:42:05 hi oerjan 18:42:07 My query got this at about the same time: 21:41 Plugin `more' failed with: thread killed 18:42:14 hɨ 18:42:23 fizzie: it has one instance that is like that IO one, and which used to be used. but then a conflicting one got accidentally imported from some other module. 18:42:49 and it's impossible to fix that without removing one of the imports completely 18:43:02 > subsequences ([1..]++ repeat 0) 18:43:02 not that everything in lambdabot that _could_ be fixed, has been. 18:43:04 [[],[1],[2],[1,2],[3],[1,3],[2,3],[1,2,3],[4],[1,4],[2,4],[1,2,4],[3,4],[1,... 18:43:16 oerjan: Apparently there's something from smallcheck-0.4:Test.SmallCheck according to that @more. 18:43:19 FreeFull: [1..]++ repeat 0 = [1..], it never gets to the second part 18:43:21 Of course it's never going to get to the zeroes, but you get the point 18:43:53 if you use a bounded number instance, it might, though 18:44:03 Int, in theory, although it'll take a while 18:44:56 > (reverse . take 10 . reverse) [(1::Int8)..] 18:44:58 [118,119,120,121,122,123,124,125,126,127] 18:45:00 Fancy. 18:45:56 blah. 18:46:00 fuck intervals 18:46:03 bleh? 18:46:05 singing is hard 18:46:14 oh not intervals in math... 18:46:17 does anyone know whether Windows 8 will actually require GPT or not 18:46:24 elliott: gpt? 18:46:28 * oerjan was thinking coppro was really struggling there 18:46:29 gpt 18:46:44 http://en.wikipedia.org/wiki/GUID_Partition_Table 18:46:49 coppro: listening to someone failing at singing is even harder, hth 18:47:29 oerjan: well that's precisely what I'm doing 18:47:31 failing at singing, I mean 18:48:15 so i hope for humanities sake that you're out of earshot. 18:48:22 *humanity's 18:48:27 i want a game to play 18:48:28 elliott: Hasn't that Consumer Preview version been out a while now? You'd think someone would have mentioned this in the interwebs. 18:49:06 Does it depend whehter you are also, singing just intonation or equal temperament or whatever, and also what range you sing (soprano, alto, tenor, bass, and whatever else)? 18:49:08 well i googled 18:49:11 but the results weren't so useful 18:49:39 zzo38: i am _pretty_ sure it depends on range. 18:50:05 like, i wouldn't recommend anyone listening to my soprano. 18:50:11 *listen 18:50:35 zzo38: I am a baritone 18:50:53 It is why I play piano, I can play the soprano, alto, tenor, and bass, all at the same time. 18:51:04 indeed 18:51:07 coppro: O, OK, yes I forgot that one. 18:51:27 barely tones 18:52:55 I knew someone who sing all ranges 18:53:06 all? 18:53:10 *unlikely* 18:54:00 Up to the highest soprano and down to the lowest bass. Her chorus was best one and always won any contests they were in at singing good. 18:54:29 It is because they sing all range. 18:54:55 *unlikely* 18:55:13 i read that Ivan Rebroff had an enormous range 18:55:13 I could believer, perhaps, that she could sing down to the bottom of a contralto range 18:55:25 but that's a good octave above a bass 18:56:51 oerjan: 4.5 octaves apparently 18:57:16 "Ivan Rebroff (31 July 1931 – 27 February 2008) was a German singer, allegedly of Russian ancestry, with an extraordinary vocal range of four and a half octaves, ranging from the soprano to bass registers.[1]" 18:58:03 I find it particularly hard to believe for a woman because you can extend your range upwards with falsetto 18:58:24 but you can't significantly extend it downward in the same fashion 18:58:34 ... falsetto hurts 19:03:22 @tell Arc_Koen "almost all zero" is ambiguous since it might mean some kind of zero density, but still infinite number of indices. 19:03:22 Consider it noted. 19:04:44 @tell Arc_Koen for the non-zeroes, i mean. 19:04:44 Consider it noted. 19:04:55 oerjan: It might be ambiguous, but it was being used in the "finite nonzeros" sense in the webtubes. 19:05:25 ...it's the kind of ambiguity that might differ between field. 19:05:52 "eventually zero" does seem perhaps slightly more popular, though. 19:06:29 http://en.wikipedia.org/wiki/Almost_all lists both meanings. 19:06:33 -!- monqy has quit (Read error: Operation timed out). 19:06:46 (as well as some for non-sequences) 19:08:00 oerjan: I don't see it mentioning sequences at all. 19:08:55 well, the subset of natural numbers ones 19:09:07 which is isomorphic to speaking about sequences >:) 19:09:26 "A simple example is that almost all prime numbers are odd. (Two is a prime number.)" 19:09:36 "Thus, almost all positive integers are composite (not prime), however there are still an infinite number of primes." 19:09:39 -!- Phantom_Hoover has joined. 19:10:03 oerjan: Hokay. 19:10:07 -!- monqy has joined. 19:10:22 monqy: special occasion? 19:10:30 oh you timed out before 19:10:32 what 19:10:37 yes 19:10:50 elliott: special occasion for you tho? 19:11:03 monqy: apparently I put #esoteric on autojoin by mistake 19:11:12 happens to everyone 19:11:33 monqy: well before like yesterday I joined eight channels by hand every time I opened xchat 19:11:36 so 19:11:49 happy happenings 19:17:30 -!- Nisstyre-laptop has joined. 19:19:44 -!- atriq has quit (Ping timeout: 260 seconds). 19:25:43 Then make a macro for each group of channels you want to join, perhaps? 19:26:05 I think xchat must support macros, isn't it? 19:26:26 /alias dontdothiseveragain join #esoteric 20:14:12 -!- Vorpal has quit (Ping timeout: 248 seconds). 20:19:53 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 20:22:15 -!- ais523 has joined. 20:35:46 -!- Phantom__Hoover has joined. 20:39:16 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 20:51:34 -!- atriq has joined. 20:54:14 How can I alter the volume of my computer using ssh? 20:54:25 Volume as in loudness 20:54:31 Not as in length cubed 20:54:49 ssh SPEAK LOUDER 20:55:02 Oh, that's helpful 20:55:07 i know 20:55:30 It could not resolve hostname 20:56:30 how incompetent 21:00:12 -!- Nisstyre-laptop has joined. 21:02:31 I've ssh'd to my other computer 21:02:45 Is it possible to get files from it over here? 21:03:19 I think there is "scp" command to copy files between computers using SSH? 21:03:58 -!- aloril_ has quit (Read error: Operation timed out). 21:04:43 Actually, all I really want to do is make my computer an alarm clock 21:05:09 I was thinking a cron thingy to start rhythmbox 21:06:15 -!- nortti has quit (Read error: Operation timed out). 21:10:16 I found a mistake in line 154, 155, 164, 165 of one of the files included with FurryScript; it says instead of so results in wrong output. I will fix it now. 21:10:57 Copy-paste error? 21:11:26 I don't know why; but I fixed it now. 21:12:27 -!- nortti has joined. 21:12:48 Why am I using ssh to access the computer in my bedroom to mess with GHCi? 21:13:03 :t flip flip (repeat ()) . scanl . (const .) 21:13:05 forall a. (a -> a) -> a -> [a] 21:13:06 Actually, I figured it out: It was in the original file, but I renamed it to for some reason (I fail to remember) and did not correct all of the references to it. 21:13:18 iterate in terms of scanl 21:13:33 And flip and repeat and const 21:13:38 and (.) and () 21:13:41 But mostly scanl 21:14:03 atriq: Are you at home? If so shouldn't you just go into your bedroom to access the computer directly? 21:14:08 Why am I using ssh to access the computer in my bedroom to mess with GHCi? <-- you're probably distantly related to Rube Goldberg somehow 21:14:17 -!- aloril_ has joined. 21:14:27 zzo38, I don't exactly own a screen. 21:14:39 :t flip flip 21:14:40 forall (f :: * -> *) a b. (Functor f) => a -> f (a -> b) -> f b 21:14:40 I borrow the family computer's screen sometimes, but my mum's using it 21:14:58 b -> (a -> b -> c) -> a -> c 21:15:10 :t flip 21:15:11 forall (f :: * -> *) a b. (Functor f) => f (a -> b) -> a -> f b 21:15:28 I suppose that's one way of doing flip 21:15:58 caleskell is _slightly_ generalized.... 21:16:07 atriq: Yes it is one thing I thought might have been, if that computer lacks a console for any reason you need to access it remotely. 21:16:12 So... you need Functor for C and B, Applicative for K and S, and Monad for W 21:16:12 that flip is sometimes useful 21:16:32 What's I in this sence 21:16:34 :t id 21:16:36 forall a. a -> a 21:16:46 iirc i prefer to call that flip strong 21:16:47 ask from Reader 21:16:49 You can make up I using S and K 21:16:52 since I think it's equivalent to a proof that all Functors are strong? 21:16:56 :t undefined :: Functor f => f a 21:16:57 forall (f :: * -> *) a. (Functor f) => f a 21:17:05 Wait 21:17:12 Is that empty? 21:17:16 No. 21:17:19 Can't be. 21:17:20 no, that's undefined 21:17:30 Yes. 21:17:34 > undefined 21:17:35 *Exception: Prelude.undefined 21:17:35 it isn't anything 21:17:41 I meant 21:17:42 :t empty 21:17:43 Ambiguous occurrence `empty' 21:17:43 It could refer to either `Control.Applicative.empty', imported from Control.Applicative 21:17:43 or `Text.Regex.Posix.empty', imported from Text.Regex.Posix at State/L.hs:55:0-22 21:17:51 :t empty :: Alternative f => f a 21:17:52 Ambiguous occurrence `empty' 21:17:52 It could refer to either `Control.Applicative.empty', imported from Control.Applicative 21:17:52 or `Text.Regex.Posix.empty', imported from Text.Regex.Posix at State/L.hs:55:0-22 21:18:03 :t Control.Applicative.empty 21:18:04 forall (f :: * -> *) a. (Alternative f) => f a 21:18:34 :t ap return return 21:18:35 Ambiguous type variable `m' in the constraint: 21:18:35 `Monad m' arising from a use of `return' at :1:10-15 21:18:36 Probable fix: add a type signature that fixes these type variable(s) 21:19:02 :t scanl 21:19:03 forall a b. (a -> b -> a) -> a -> [b] -> [a] 21:20:45 :t (scanl . (const .)) `flip` repeat () 21:20:46 forall b. ([()] -> [()]) -> [b] -> [[()]] 21:20:49 oops 21:24:47 :t scanl . (const .) 21:24:48 forall b a. (a -> a) -> a -> [b] -> [a] 21:25:15 :t (fix .) . scanl . (const .) 21:25:16 forall a. (a -> a) -> a -> [a] 21:25:31 > ((fix .) . scanl . (const .)) (+1) 0 21:25:33 [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,... 21:26:19 :t unfoldr . (.) Just . ap (ap . ((,) .)) id 21:26:20 forall a. (a -> a) -> a -> [a] 21:26:31 iterate in terms of unfoldr 21:26:53 @unpl unfoldr . (.) Just . ap (ap . ((,) .)) id 21:26:54 (\ h -> unfoldr (\ c -> Just (((\ t y -> (\ ac -> ((,)) (t ac)) >>= \ v -> y >>= \ u -> return (v u)) >>= \ m -> (\ e -> e) >>= \ l -> return (m l)) h c))) 21:26:59 Yes 21:27:04 I meant... 21:27:19 :t \f -> unfoldr (\a -> Just (f a, f a)) 21:27:20 forall a. (a -> a) -> a -> [a] 21:28:34 -!- augur has quit (Remote host closed the connection). 21:29:47 :t \f -> unfoldr (Just . join (&&&) . f) 21:29:48 No instance for (Arrow (,)) 21:29:48 arising from a use of `&&&' at :1:27-31 21:29:48 Possible fix: add an instance declaration for (Arrow (,)) 21:29:52 argh 21:30:14 :t join (&&&) 21:30:15 forall (a :: * -> * -> *) b c. (Arrow a) => a b c -> a b (c, c) 21:30:33 :t \f -> unfoldr (Just . join (&&&) f) 21:30:34 forall b. (b -> b) -> b -> [b] 21:30:49 oh right 21:31:16 :t unfoldr . (Just .) . join (&&&) 21:31:17 forall b. (b -> b) -> b -> [b] 21:31:34 Doing it in terms of foldr... 21:31:37 Tricky 21:31:59 foldr is like breaking up lists, not building them 21:32:16 I have a feeling it's possible 21:32:20 Does (,) form a semigroupoid (category except identity)? 21:33:10 zzo38, so you want (.) :: (b, c) -> (a, b) -> (a, c) 21:33:28 what is id :: (a, a) 21:33:33 atriq: Yes and associative 21:33:37 oh 21:33:40 elliott: Nothing, which is why it is not a category 21:33:41 i didn't read what zzo38 said 21:33:52 elliott: barely avoiding a swat there 21:34:04 it's not an instance of http://hackage.haskell.org/packages/archive/semigroupoids/3.0/doc/html/Data-Semigroupoid.html 21:34:05 so I bet no 21:34:19 thanks science 21:34:24 Let's go with the simple (_, c) . (a, _) = (a, c) 21:34:35 well that is literally the only way you can define that type 21:34:47 For associativity, we need (a . b) . c = a . (b . c) 21:34:52 atriq: Yes that is what I thought. 21:34:56 looks pretty associative to me :P 21:35:19 let a = (1, 2), b = (3, 4), c = (5, 6) 21:35:37 a . b = (3, 2) 21:35:46 (a . b) . c = (5, 2) 21:36:08 b . c = (5, 4) 21:36:22 a . (b . c) = (5, 2) 21:36:24 Associative 21:36:29 Hurrah 21:36:39 @check let (_, c) . (a, _) = (a, c); (.) :: (Int, Int) -> (Int, Int) -> (Int, Int) in \x y z -> x . (y . z) == (x . y) . z 21:36:40 "OK, passed 500 tests." 21:36:55 So it's a semigroupoid 21:37:00 oerjan: you realise atriq's proof was fully rigorous right :P 21:37:04 since 1, 2, 3, 4, 5, 6 are just variables there 21:37:29 elliott: well i would if i had been looking at it while constructing the quickcheck 21:37:45 imo type faster 21:37:46 What is this semigroupoid normally called in mathematics? 21:38:02 @scheck let (_, c) . (a, _) = (a, c); (.) :: (Bool, Bool) -> (Bool, Bool) -> (Bool, Bool) in \x y z -> x . (y . z) == (x . y) . z 21:38:03 "OK, passed 500 tests." 21:38:11 @list scheck 21:38:11 No module "scheck" loaded 21:38:13 isn't scheck just check 21:38:14 @list check 21:38:15 check provides: check 21:38:17 @smallcheck 21:38:17 Unknown command, try @list 21:38:20 i realized 21:38:29 You could make it into a category by adding an identity, like newtype X a b = X (Maybe (a, b)); 21:38:45 Just like you can make a semigroup into a monoid like that too 21:38:58 heh 21:39:28 zzo38: you'd have an identity between non-neighboring elements too, then 21:39:31 Maybe (a, b) is the weirdest category I ever heard of 21:39:37 is it useful for anything 21:39:41 *non-equal 21:39:42 Probably not! 21:40:22 oerjan: Yes I know it allows it, unless you make a GADT to make such thing prohibited 21:40:22 zzo38: oh that doesn't work when a is not b 21:40:51 how would you compose a Nothing in X a b with a Just in X b c 21:41:18 I can see how it won't work now, which is why it has to be a GADT instead. 21:41:22 -!- FreeFull has quit (Quit: Sleeptime). 21:41:24 you need a GADT for this to work, yeah 21:41:27 oerjan: data X a b where X :: Maybe (a, a) -> X a a 21:41:29 "p e r f e c t" 21:41:40 Is it one of these thingies? http://hackage.haskell.org/packages/archive/data-lens/2.10.2/doc/html/Control-Category-Product.html 21:41:49 elliott: ERRR... 21:41:54 data X :: * -> * -> * where { Id :: X a a; Pair :: a -> b -> X a b; }; 21:41:57 No, it isn't 21:42:01 Mystery solved 21:43:05 oerjan: what 21:43:20 oerjan: it's a category! 21:43:26 O KAY 21:44:00 If anyone can find a use for this, I'll be amazed 21:44:05 Yes I see elliott's code is a category, but it is the wrong one. 21:44:54 monqy: http://hpaste.org/75855#a75927 21:44:57 Goodnight 21:44:59 -!- atriq has quit (Quit: Leaving). 21:45:07 ⊸ 21:47:15 ⅋ is pretty crazy too 21:47:24 monqy: standard linear logic symbols!! 21:47:26 THE JOKE IS: linear logic is crazy 21:50:43 do you k now how this thing works im too lazy to figure it out 21:51:08 and im guessing overture is an alternative to prelude?? 21:51:18 ye but you can just ignore the overture thing I don't think it uses anything special from it 21:51:33 it's stream processing except it's done w/ linear logic!! 21:51:55 i forget whatever i knew about linear logic 21:54:37 What is this category that I wrote about, is called, in a mathematics? 21:59:48 zzo38: i'm not sure but it's also the product of two simpler ones: one with Hom(A, B) = A and one with Hom(A, B) = B 22:02:30 -!- Frooxius has quit (Ping timeout: 264 seconds). 22:04:46 the former is Const, is it not? although it isn't listed as an instance in that semigroupoid package 22:05:05 OK 22:12:36 I love the Internet Standard Content Rating System 22:12:42 it has two categories: SFW and NSFW 22:14:15 standard eh 22:14:45 can I give a five star and two thumbs up rating 22:18:24 -!- sirdancealot7 has quit (Read error: Connection reset by peer). 22:23:30 -!- augur has joined. 22:25:02 you _may_, but you cannot. 22:28:51 oops, did I forgot to sign 22:28:51 Arc_Koen: You have 3 new messages. '/msg lambdabot @messages' to read them. 22:28:56 woooooouh people love me 22:29:07 my guess: three of those people are Oerjan 22:29:07 they might all be "fuck you" 22:29:15 _might be_. 22:29:15 @messages 22:29:16 oerjan said 3h 49m 49s ago: "eventually zero sequence" 22:29:16 oerjan said 3h 25m 53s ago: "almost all zero" is ambiguous since it might mean some kind of zero density, but still infinite number of indices. 22:29:16 oerjan said 3h 24m 31s ago: for the non-zeroes, i mean. 22:29:46 @tell elliott fuck you 22:29:47 Consider it noted. 22:29:50 hmmm right 22:30:36 @ask oerjan <3 22:30:37 Consider it noted. 22:30:42 i wouldn't want elliott to be disappointed 22:30:42 oerjan: You have 1 new message. '/msg lambdabot @messages' to read it. 22:30:48 @messages 22:30:48 elliott asked 12s ago: <3 22:30:53 ooh 22:31:09 I think in france we have a consensus that subsets of a countable set cannot have a measure zero if they are themselves infinite 22:31:58 Arc_Koen: "measure" is a technical term which does not work well with the whole space being countable. if you want any uniformity. 22:31:59 or maybe we just assume that something more complicated than "a sequence with a finite number of non-zeroes" deserves a more complicated name than "suite presque-nulle" 22:32:56 though I guess the sequence (1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, ...) could be considered to have not many non-zeroes as well 22:33:02 Arc_Koen: the wikipedia article on "Almost all" mentions as an example that Almost all integers are composite 22:33:14 for one of the meanings. 22:33:25 er, all natural numbers, i guess. 22:33:49 "Almost all" is sometimes used synonymously with "all but [except] http://en.wikipedia.org/wiki/Finite_set many" (formally, a http://en.wikipedia.org/wiki/Cofinite set) or "all but a http://en.wikipedia.org/wiki/Countable_set" (formally, a http://en.wikipedia.org/wiki/Cocountable set); see http://en.wikipedia.org/wiki/Almost. 22:33:56 errh, pardon my horrible pasting 22:34:22 yep, sometimes. and sometimes it's used completely differently. 22:34:30 but yeah that sentence at the beginning of the article basically means "what 'almost all' means depend on the context" so it's not very helpful 22:35:06 it _is_ very helpful, it tells you it's ambiguous :P 22:35:31 what isn't 22:35:47 "eventually" >:) 22:36:14 also, yeah, it's been a while since the last measure theory class I attended 22:36:39 (which is kinda sad, in a sense) 22:37:05 oerjan: (1, 2, 0, 3, 4, 5, 6, ...) is eventually 0! 22:37:16 come to think of it, you could probably use it for all but a meagre set, too... 22:40:16 oops... once more I felt short of being loyal to my earlier "let's get to bed early tonight" resolution 22:41:15 i usually do that. 22:41:32 sometimes by half a day. 22:41:34 go to bed early? 22:41:47 no, fall short. 22:42:52 I think esolangs.org owes me sleep 22:43:19 i think it has very little to pay with 22:44:33 well I usually spend more time volunteering than actually working, so I guess my time isn't so expensive 22:44:51 also, Ndeql looks evil. 22:45:00 hehe :) 22:45:10 oh crap 22:45:24 oh no, nothing 22:45:43 anyway, I didn't know what qdeql and sceql stood for so I just replaced the first two letters 22:46:10 Arc_Koen: sorry, i cannot offer refunds 22:46:18 i don't know either 22:46:26 I bet graue offered refunds. elliott worst wiki admin 22:46:56 only if you managed to catch him online. 22:46:59 that's disappointing, at least when I volunteer I get free lunches or stuff 22:48:27 oh those were graue's languages, not cpressey's 22:48:41 might be hard to find out what they stand for, then 22:49:35 Oerjan: although Ndeql's evilness was kind of an accident, I had that "random variable" idea in mind for a while and yesterday I wrote a sceql interpreter and I thought the two ideas would be perfect for each other 22:52:57 oh I just noticed today, Category:Stack-based and Category-Queue-based are subcategories of Category:Languages, but Category:Deque-based isn't and I must say, discriminating mixed-race like that, it's RACISM, mate 22:53:24 anyway have a good night 22:53:48 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 22:54:05 -!- Arc_Koen has joined. 22:54:09 hi 22:54:25 hmmm something wrong with auto-reconnect server, or something 22:54:27 someone is very good at falling short 22:54:57 IT'S AN OMEN AND YOU MUST STAY 22:55:13 it's weird it only does that for freenode 22:56:17 nope, i don't have a clue how to tame Ndeql's randomness 22:57:37 proving it cannot be tamed would be enough to tame it 22:57:51 that's true 22:58:33 oh i know! 22:58:36 (I would say I just proved it could be tamed but Gödel says no) 22:59:14 dangit Gödel 22:59:19 there is absolutely guarantee against one particular variable _never_ being the one involved in anything, _except_ for being used for all the \ commands. which means it is always possible for all loops to be skipped. 22:59:26 *no guarantee 22:59:56 ok 23:00:07 now to fix that 23:00:35 "the \ command can only select variables which are not 0" 23:00:50 ...i think that might have other problems :) 23:00:51 there, you have your guarantee WHAT DO YOU MEAN "it's worse" 23:01:56 hi 23:02:02 about that "two stacks but no communication" silly idea: I had loops based on whether the register had been modified or not 23:02:17 sounds dangerous 23:02:31 sprunge.us/died or something 23:02:48 oh it did? well good riddance. 23:03:09 (so I decided to name that language "died") 23:04:20 however a better version: http://sprunge.us/FXJc 23:06:10 ok I'd really like to follow the omen but that's probably not a good idea so gnight 23:12:10 (well as for the conditionals that allow to pass information from one side to the other - I might be ok with that if it's not too easy to do, or if for any other reason the language is not tc) 23:12:18 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 23:18:00 http://sprunge.us/CSTT Hooray, it sucks! 23:18:26 yes 23:20:11 huray 23:20:21 ps what does this do 23:20:23 gzip 23:21:04 Because I was stupendously lazy with the IO, it doubles in speed if linked against musl. 23:21:14 (apparently glibc getchar is slow?) 23:23:50 pikhq_: Should I buy a UEFI motherboard? 23:24:08 elliott: Is it possible to not anymore? 23:24:14 -!- sirdancealot7 has joined. 23:24:16 A language sucking in certain ways doesn't mean I should abandon it, does it? 23:24:17 MS is pushing UEFI pretty hard. 23:24:56 pikhq_: I... assume so? 23:25:05 It would be pretty weird if the entire computer inventory stopped selling BIOS motherboards over night. 23:25:07 Am I really that behind? 23:25:09 Deewiant??? 23:25:25 elliott: IIRC they sell mobos that can be toggled between UEFI and BIOS. 23:25:26 Sgeo: Are you using the language because it is a useful tool or because it is a community? 23:25:45 If the former, yes, if those ways affect how you are coding in a negative way that other languages do not. If the latter, it doesn't matter. 23:26:14 pikhq_: Do you have to deal with this "Secure" Boot nonsense if you do UEFI? 23:26:17 Or is that a separate thing? 23:26:41 elliott: That's a separate thing. 23:27:14 Well. Technically, it's a feature of UEFI... 23:27:29 But anyways. On x86, Microsoft is mandating that it be optional. 23:27:33 So you needn't bother. 23:27:38 Thicrosoft. 23:29:21 -!- augur has quit (Read error: Connection reset by peer). 23:29:58 -!- augur has joined. 23:30:23 I should make up a BIOS which is complete PC BIOS, public domain, and Forth interpreter built-in which is also used to configure it, and then I think it would be completely OK. It can then be made the computer which has a jumper to enable UEFI, to enable BIOS, and to enable both. 23:30:48 I agree. 23:31:11 me too 23:32:10 I think it would be better than what is currently have, isn't it? Especially if it is also BIOS one function is to download an operating system over the internet, so that you can install an operating system even if you do not have a disk, or use it to emulate a VT100 terminal, or whatever 23:33:25 You can even write, in forth, an ipmi like operating system. Oh wait. 23:33:38 What is a ipmi like operating system? 23:34:08 pikhq_: I forget, does btrfs support shrinking? 23:34:19 I dunno 23:34:54 Well, I suppose real IPMI runs on separate hardware 23:39:38 International Microwave Power Institute? 23:39:42 Oh, whoops 23:49:27 -!- kinoSi0 has joined. 23:52:05 -!- kinoSi has quit (Ping timeout: 246 seconds). 23:59:35 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 2012-10-08: 00:02:09 Sgeo: yes 00:05:39 -!- jiella has quit (Quit: Leaving.). 00:14:46 -!- DHeadshot has joined. 02:01:01 Deewiant: I forget, what do you use for AUR stuff? 02:25:06 -!- oklofok has joined. 02:28:04 -!- oklopol has quit (Ping timeout: 248 seconds). 02:33:41 -!- augur has quit (Remote host closed the connection). 02:36:56 -!- elliott_ has joined. 02:37:00 -!- elliott has quit (Read error: Connection reset by peer). 02:50:41 -!- augur has joined. 03:04:52 -!- augur has quit (Remote host closed the connection). 03:13:23 -!- augur has joined. 03:15:08 -!- augur has quit (Remote host closed the connection). 03:31:54 -!- augur has joined. 03:32:56 -!- augur has quit (Remote host closed the connection). 03:38:05 -!- augur has joined. 03:45:26 -!- augur has quit (Remote host closed the connection). 04:13:30 What hardware description languages specify gates explicitly instead of specifying arithmetic and assignments and so on? 04:15:51 -!- oerjan has quit (Quit: Good night). 04:31:28 "If ever you are by far the best, or the most interested, student in a classroom, then you shouldfind another classroom." 04:31:31 :/ 04:31:38 :/ 04:31:56 * Sgeo feels like it's sort of too late to start finding another classroom 04:32:02 Why? And also why are the improper characters? 04:32:50 zzo38: SPICE 04:32:57 Sgeo: are you still at that shitty university 04:33:01 also JSim, the thing used by MIT 6.004 04:33:07 elliott_, yes, for my last semester before I graduate. 04:33:22 Sgeo: do i get to gloat about how i told you so 04:33:22 in which you design a RISC processor at the level of individual logic gates 04:33:31 or would that be insensitive...... 04:34:57 yeah that's good advice for jobs as well 04:35:49 * Sgeo is very used to being the best in his class 04:36:06 Although Intro to Drawing is giving me a major slap in the face in that area. 04:37:38 haha 04:40:34 kmc: Isn't SPICE for analog designs? What does JSim? 04:40:53 JSim does both analog electrical and digital logical simulation 04:40:58 it uses SPICE-like syntax for both 04:41:41 i don't know if it is used outside of 6.004 04:41:48 -!- augur has joined. 04:41:56 it is a pretty basic program but well-suited to the course 04:42:03 Can any of them be compiled to make a hardware ASIC or to program a CPLD or FPGA? 04:42:25 not as-is 04:44:58 If not as-is, then how is it? 04:46:57 well, there's no fundamental reason you couldn't write a compiler from JSim language to VHDL or something 04:47:37 it is probably a silly thing to do 04:47:43 Can it not compile directly into the binary formats? 04:47:50 JSim? no, i don't think so 04:47:53 Doesn't VHDL work at the gate level? 04:47:56 it is just a simulator for teaching purposes 04:48:38 Jafet: kinda, you specify arithmetic / logical expressions, but not how to realize them with individual gates 04:48:41 that's my understanding 04:49:00 ask ais523 :P 04:58:05 -!- augur has quit (Read error: Connection reset by peer). 04:59:34 -!- augur has joined. 05:03:28 i wonder if automatic lint/style checking can be harmful in some cases 05:03:39 my reasoning is thus: 05:03:54 the value of these tools isn't that style violations are actually that important 05:04:03 it's that they catch cases where programmers are generally not paying attention 05:04:10 bad style is just a symptom of that 05:04:52 but if you have an automatic style check on commit, you might consider that passing the check satisfies your obligation to pay attention 05:05:04 and the result is bad code which is harder to spot 05:06:00 Besides which, style violations are easy to notice. 05:06:35 depends 05:07:34 when i run such a tool on a reasonable size codebase, it usually finds a bunch of violations, and a few real bugs 05:08:31 the real reason lint is useless is because it complains about the shit you don't care about and doesn't complain about the shit you do 05:08:38 i'm talking about tools which don't just check, like, how many spaces you indent, but will catch undefined variables in python, accidentally global things in javascript, etc 05:08:41 anyway kmc your argument is also an argument against compiler warnings in general 05:08:50 i don't know whether pointing this out will change your opinion or not 05:09:55 no because compiler warnings (and static typing and test cases) have a much higher hit ratio for finding important problems 05:11:58 if you have a tool which finds lots of important problems, then for sure you want to run it all the time 05:12:53 but with something like lint checking, maybe there's a 'false sense of security' problem, where people focus on making the lint checker's irrelevant complaints go away rather than actually reviewing their code 05:16:53 i don't know, this is something i'm thinking about in a specific context and maybe doesn't make sense generally 05:23:04 what's the difference between clang's fanciest warnings and lint 05:23:10 sincere question 05:23:43 i don't think there is a fundamental difference between lint checking and compiler warnings 05:23:46 Can Haskell's type checking cause a false sense of security? 05:24:03 just a practical difference in the tools we use for each 05:24:03 yes 05:24:17 Sgeo: yeah 05:24:18 Sgeo: totallyInnocentFunction = unsafeCoerce 05:24:40 there is a lot of thread-unsafe code on hackage 05:24:56 thanks to uncareful use of C bindings 05:25:15 this is just an example where types don't help you much 05:25:24 also all the common partial functions like 'head' etc 05:26:59 “Some programmers like to use the GCC ‘-Wall’ option, and change the code whenever it issues a warning. If you want to do this, then do. Other programmers prefer not to use ‘-Wall’, because it gives warnings for valid and legitimate code which they do not want to change. If you want to do this, then do. The compiler should be your servant, not your master.” 05:28:36 And then there's GNU, who stick -Werror in the CFLAGS. 05:28:53 i think the people who like to ignore warnings will more often than not be idiot macho ninja rockstar hackers who don't have any good reason to do the weird things they do 05:29:32 pikhq_: that's not a bad move if you carefully select your warnings 05:29:46 Jafet: clang has -Weverything 05:29:51 they probably do these things based on some misunderstood C folklore from 30 years ago rather than an understanding of current systems and compilers 05:29:56 Jafet: it turns on all the warnings. all of them. 05:30:27 coppro: binutils builds with -Wall -Werror by default. 05:30:51 pikhq_: I forget what's in -Wall honestly 05:30:53 it's a stupid flag 05:30:58 i have done a lot of strange things with gcc and I almost always get it to build cleanly with -Wall, and feel that the solutions which make gcc happy are better 05:31:21 Yes. And -Wall -Werror just adds to it. 05:31:23 like "lol compiler, shut up about aliasing", no, lol programmer, learn the aliasing rules and when to use a union instead of pointer casts 05:31:47 I usually have it on, granted, but it's more stupid because of the name than because of the warning 05:31:57 kmc: yeah, that should be an error really 05:32:12 (I know it can't be conformant and be an error, but since when has GCC cared anyway :P ) 05:32:28 pointer casts aren't even conformant like that are they 05:32:47 C compilers let you do so many things which are fundamentally nonsense yet basically stand up to casual testing 05:33:16 this is a good reason to pay attention to warnings 05:33:45 elliott_: they are conformant, but will likely lead to UB at runtime 05:34:16 elliott_: arguably a compiler could refuse to translate a program which is guaranteed to produce UB, but if it's only a possibility, it can't refuse 05:34:17 elliott_: There's rules governing how pointer casts may be performed. 05:34:51 For instance, casting an arbitrary data pointer to a char pointer is *always* valid... 05:35:12 Some warnings are good, some warnings I don't like and want to turn off. And, some warnings I want to be errors instead (such as converting a pointer to integer without an explicit cast), but they don't seem to have options for all warnings individually 05:35:30 And casting from a char pointer to another type might be valid. 05:35:36 pikhq_: yes i know this much 05:35:46 coppro: well UB is not conformant, right 05:35:53 zzo38: clang does 05:36:02 elliott_: That's a philosophical question, really. :P 05:36:07 elliott_: Yes, but only if it will occur. 05:36:29 elliott_: If the program won't cause UB in its execution, it must execute correctly. If it will cause UB if executed, the program can do whatever 05:36:40 (it can even fail to do the things that would lead to the UB) 05:36:42 coppro: O, well, GNU doesn't and yet some targets are only supported by GNU, such as MMIX. I wanted MMIX on LLVM as well but they don't do that. 05:37:09 coppro: so a program which adds two signed numbers is conformant if you give it two that don't overflow, but non-conformant if you give it two that overflow? 05:37:12 (say it takes them from argv) 05:38:11 elliott_: right, and if it's run with two numbers that overflow, it doesn't even need to get that far. It could exec("nethack") instead of doing anything else. 05:38:13 elliott_: Yes. Hence why "UB = non-conformant" is a philosophical question. 05:38:51 it is conformant in the sense that a conforming implementation must correctly translate it, and the result must correctly execute if it does not cause UB. 05:39:18 If a TU is not conformant, a conforming implementation must issue a diagnostic, but then is free to do whatever 05:39:22 coppro: i feel there is some self-contradiction here 05:39:46 (so a truly conforming implementation will warn about all extensions, except a few like pragmas where implementations are specifically allowed to define behaviour) 05:42:08 Surely not; determining if a TU invokes UB in C is identical to the halting oracle... 05:42:27 pikhq_: Not UB; that's conforming. 05:42:49 void halts() { /* arbitrary function body that may or may not return; */; *NULL = 0; } 05:43:13 Erm 05:43:15 the implementation must translate that 05:43:53 And if control flow will always hit the end, then the implementation, according to you, must issue a diagnostic. 05:44:07 no 05:44:10 That is to say, a conformant implementation must determine if arbitrary C halts. 05:44:19 I meant for something like "int * int = 3;" 05:45:01 So, you mean a conforming implementation must issue a diagnostic on *parse errors*? 05:45:19 That's not what you said, you just said "if a TU is not conformant", in a context where you were saying "UB = not conformant"... 05:45:27 No, UB is conformant. 05:45:34 What parse error? 05:45:35 in that an implementation must translate it. 05:45:45 pikhq_: A parse error or a semantic error or anything else that violates the requirements 05:45:55 Okay, then. Now we're on the same page. 05:46:02 What semantic error, then? 05:46:12 What's TU? 05:46:31 Except, of course, that most C extensions would not be *parse* errors in C, but rather explicit UB. 05:46:40 Is it requires to specify what parse error, instead of just if it is error or not? 05:46:40 pikhq_: __attribute__ comes to mind 05:46:42 __attribute__(()) invokes undefined behavior. 05:46:45 zzo38: No. 05:46:59 pikhq_: what? 05:47:12 pikhq_: that does not seem right 05:47:25 if programs with UB were not conformant that'd make the whole concept of UB a bit meaningless I think 05:47:43 __* is a reserved name; using it in any context is UB. 05:48:17 it's unclear what 'reserved' means 05:48:26 Sgeo: translation unit 05:48:51 "Reserved" means "using this is UB". That's what it's defined as. 05:49:08 pikhq_: really? Not as making the code ill-formed? 05:49:41 -!- kinoSi0 has quit (Read error: Connection reset by peer). 05:50:09 -!- kinoSi has joined. 05:50:32 pikhq_: huh 05:51:14 pikhq_: well an example I can think of is 'signed overflow is defined' 05:51:23 no wait, that's runtime 05:51:24 uh 05:51:33 "If the program declares or defines an identifier in a context in which it is reserved, or defines a reserved identifier as a macro name, the behavior is undefined." 05:51:36 Aaaah 05:51:46 So, iff you try and #define or #undef __attribute__ it's UB. 05:51:51 Otherwise, it's... ? 05:53:17 ah, GCC statement expressions are a good example 05:53:21 if you don't define it yourself, you'd be referencing something that isn't necessarily defined? 05:53:32 olsner: Right. 05:54:00 unless by random chance magic it happens to be there, and then I guess you just have no way to know what it does 05:54:19 sure, but a conformant compiler will tell you that something happened! 05:54:37 of course, a diagnostic could easily be "i dont want to live any more" 05:56:56 Hmm. There are in fact a decent number of syntax errors that are UB. 05:57:20 "The initializer for a scalar is neither a single expression nor a single expression closed in braces" invokes UB. 05:58:13 It is UB for a source file to be both nonempty and not end with a newline. 05:58:50 a number of those UBs are, AIUI, due to old implementations with weird behaviours 05:58:51 but an empty source file is ok? 05:58:57 olsner: Yes. 05:59:06 pikhq_: you know trigraphs? 05:59:21 However, the empty quine will be UB. Because that does not define main. 05:59:23 coppro: Yeah. 05:59:49 It is UB for there to be an unmatched ' or " 06:00:59 It is UB for an identifier to start with a digit. 06:01:16 > length "aaaaaaaaaaaaaaaaaaaa" 06:01:17 20 06:01:24 > length "monqy" 06:01:25 5 06:01:26 > length "hi monqy" 06:01:27 8 06:01:32 coïncidencë? 06:01:37 pikhq_: They are in C++11 because of IBM 06:01:47 > length "shachaf" 06:01:48 7 06:01:50 coppro: Fuck 'em 06:01:51 > length "funpuns" 06:01:52 7 06:01:58 Surely they can update to UTF-EBCDIC 06:02:03 the IBM reps reportedly said "We're sorry. We really wish we could take them out, but we have actual code that depends on these actually being in the standard." 06:02:51 herp, if they need their code to follow the latest standard they should just update it 06:03:14 olsner: Have you considered being more like oerjan? 06:03:52 shachaf: in what way? 06:04:37 it's not something I've considered per se, but I'm always open for suggestions if you want me to change my behavior 06:04:46 Maybe shuffle your nick around. 06:04:49 oerlsn 06:04:56 oh, that would only be confusing 06:04:59 shachaf: have you considered being less like shachaf 06:05:11 but then he wouldn't be shachaf now would he 06:05:12 !rot13 olsner 06:05:14 elliott_: have you considered being more like monqy 06:05:14 byfare 06:05:23 right, I did that the other day 06:05:25 !rot13 monqy 06:05:25 zbadl 06:05:36 !rot13 mrmistermonkey 06:05:36 zezvfgrezbaxrl 06:05:52 funpuns = best nick 06:06:08 wow zezvfgrezbaxrl is my secret name how did you know 06:06:40 !rot13 mistermysterymonkey 06:06:41 zvfgrezlfgrelzbaxrl 06:07:20 elementary my dear monqy 06:17:17 huh 06:17:28 the supreme court of canada issued "an order in the nature of mandamus" 06:17:36 I wonder what the distinction between that and actual mandamus is 06:17:41 you're a mandamus 06:28:14 that could explain a lot 06:31:31 coppro: It appears that's a *US* legal term? 06:32:20 I'm going to declare "fuck if I know" 06:32:53 pikhq_: it's not purely US 06:33:02 "A strictly conforming program shall use only those features of the language and library specified in this International Standard.3) It shall not produce output dependent on any unspecified, undefined, or implementation-defined behavior, and shall not exceed any minimum implementation limit." 06:33:21 pikhq_: mandamus is an order by a court to a government agency to perform some action 06:34:53 pikhq_: most notably when a court refuses to hear a case citing lack of decision; the court has refused to hear the case so it is not a decision which can be appealed, so a higher court can issue mandamus to force it to hear the case 06:39:08 pikhq_: olsner: An empty source file is not ok: the syntax is "translation-unit: external-declaration | external-declaration translation-unit" and there's no way for external-declaration to be empty. 06:39:27 (And yes, it makes the bit about nonempty source files and newlines a bit bizarre.) 06:42:21 I suppose the intent is arguable, though. But at least GCC folks have interpreted it so that the translation unit as a whole must be parseable as the nonterminal called 'translation-unit', and hence rejects the empty file. 06:42:42 pikhq_: but it can generally be used for anything. One example I can find is ordering a municipality to impose tax 06:45:11 coppro: I was referring to "nature of mandamus" in particular 06:45:30 "Mandamus" appears to be a UK-derivative legal system term. 06:47:35 pikhq_: ah, no 06:48:13 pikhq_: The context is that the court ordered the government to do something, but said it was "of the nature of mandamus" 06:48:45 http://scc.lexum.org/en/1994/1994scr3-1100/1994scr3-1100.html 06:48:46 what 06:49:06 that's... terse 06:50:23 You mean TERSE™. 06:50:36 It's a trade mark of JimNeiL. 06:51:03 thank you for that knowledge 06:51:06 I feel smarter already 06:51:39 coppro: I declare that legal systems are overly obtuse. 06:51:51 I think empty source files ought to be allowed in C, but they shouldn't compile into an executable since there is no main. It should just make a object file which does nothing if linked with other files, as if that file is not there. 06:51:53 And that they need replaced with a suffusion of yellow. 06:52:56 Isn't it more logical this way? 06:53:29 pikhq_: I'm sorry. I don't think you have the necessary jurisdiction. 06:53:40 pikhq_: Perhaps you should ask a court to do that. 06:53:55 zzo38: You can have a source file that says "typedef int foo;" -- that's almost as good. It compiles into an object file, and since the typedef only has file scope and doesn't make any external-linkage objects or anything, it's quite close to "not there". 06:54:17 (Okay, admittedly it might end up in the debugging information.) 06:55:10 fizzie: Well yes I suppose you can work around in that way, but still I think it would just be more sensible to allow an empty source file. 06:55:17 coppro: But I a sovereign citizen! 06:55:25 I do not recognize the jurisdiction of the courts! 06:55:32 I do not consent! 06:55:48 pikhq_: how do I sign up? 06:57:04 zzo38: I suppose many compilers already do, since it is indeed more logical. GCC does unless compiling with "-pedantic", and as mentioned, the standard isn't very explicit about it. 06:57:39 clang seems to accept it always. 06:57:47 -!- ais523 has quit. 06:58:29 Does clang not have the pedantic mode? 06:58:36 zzo38: it does 06:58:55 Then they should fix it, isn't it? 06:59:35 Well, their interpretation of the standard might be different. The part in the translation phases about an empty source file is arguably evidence that empty translation units should be okay too. 07:00:17 Actually, how coincidental. 07:00:25 Date: Wed Jun 6 12:25:21 2012 "Add pedantic warning -Wempty-translation-unit (C11 6.9p1)." 07:00:36 (My version here at work is older than that.) 07:00:57 OK 07:10:25 You mean TERSE™. 07:10:26 It's a trade mark of JimNeiL. 07:10:26 <3 07:10:40 -!- DHeadshot has quit (Read error: Connection reset by peer). 07:10:54 -!- DHeadshot has joined. 07:23:07 Last Dungeons&Dragons session I have played is incomplete, so no experience points yet. But still I think I have thought of what to do next in this time between sessions. It is a bit like you can in chess by mail, you have a lot of time to figure out. Except, chess doesn't have hidden information, and with chess by mail this happens after every move instead of just a session. 07:24:50 Therefore, some of my strategies are similar to that of chess. (But not always) 07:30:06 So it can include: zwischenzug, zugzwang, fork check, discovered check, smothered mate, and so on. 07:34:09 Since we are very outnumbered, we can use this to our advantage. 07:35:51 (It wouldn't work if we weren't outnumbered.) 07:39:32 Do you know the "grotesque" chess problem where the white has only one king and one pawn (still on the starting row), and black still has sixteen pieces, and white will win? 08:15:04 -!- zzo38 has quit (Remote host closed the connection). 08:27:53 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 09:07:54 -!- MoALTz_ has quit (Ping timeout: 264 seconds). 09:10:19 -!- MoALTz has joined. 09:26:57 -!- monqy has quit (Quit: hello). 09:37:58 -!- DHeadshot has quit (Read error: Connection reset by peer). 09:38:03 -!- DH____ has joined. 10:02:19 -!- copumpkin has quit (Ping timeout: 260 seconds). 10:02:53 -!- copumpkin has joined. 10:54:08 -!- ais523 has joined. 11:02:29 -!- ais523 has quit (Read error: Connection reset by peer). 11:02:43 -!- ais523 has joined. 11:06:23 -!- mig22 has joined. 11:09:02 -!- barts_ has joined. 11:12:24 -!- barts has quit (Ping timeout: 260 seconds). 11:15:12 -!- ais523 has quit (Ping timeout: 246 seconds). 11:26:09 -!- epicmonkey has joined. 11:28:48 -!- ais523 has joined. 11:31:36 ais523: q q q qqq qq q q qqq q 11:31:58 pikhq_: Hey, is Nvidia or ATI better supported by Linux this month? 11:42:01 -!- elliott_ has quit (Remote host closed the connection). 11:43:43 -!- elliott has joined. 11:55:23 hi elliott 11:55:42 quick sanity check: is banning / and .. enough to avoid all directory traversal attacks on UNIX? 11:55:51 working on the automarker script again, looking for exploits 11:55:54 maybe 11:55:57 possibly not 11:56:15 this is in a field that's /meant/ to be an email address 11:56:19 but you know how loose the email RFC is 11:56:28 (specifically, the address-part of the address) 12:01:11 oh, I guess there's NUL, but I'm pretty sure that's not allowed in an email address (and will be rejected by the email address parser I grabbed) 12:01:38 -!- Frooxius has joined. 12:03:10 hmm, I've thought of a brilliant exploit, actually 12:03:18 but I doubt the students will come up with it 12:03:24 (not in the filename thing, in something else) 12:03:37 what is it 12:04:11 basically, the program could bypass one of its checks by outputting its own SHA-1 hash 12:04:27 which you could accomplish with a sufficiently clever modification of a quine 12:04:45 note that you can't use any libraries for this, so the marker would probably notice the SHA-1 code as it scrolled past 12:05:43 I can't imagine why that would happen 12:06:08 basically, because we're linking the student's code to provided code 12:06:14 we want to check that the provided code has run 12:06:22 so we give it the SHA-1 hash of the student's code 12:06:24 to output 12:07:23 I guess we could just use a random string 12:07:42 "Found dependencies: Capture::Tiny, Throwable::Error, Email::Abstract, Moose" 12:07:49 hmm, this is going to take a while to install… 12:08:04 there are downsides to emergency use of CPAN 12:22:39 ais523: have i told you about cpanminus 12:22:40 i forget 12:22:48 it has made my life less hellish 12:23:33 -!- ais523_ has joined. 12:23:44 -!- ais523 has quit (Read error: Connection reset by peer). 12:23:52 -!- ogrom has joined. 12:25:06 ais523: have i told you about cpanminus 12:25:07 i forget 12:25:08 it has made my life less hellish 12:25:34 Less hellish, but sometimes loopy, I'd say. 12:26:09 well ais523_ doesn't count as real fizzie 12:26:25 Few things count as real fizzies. 12:27:24 how many 12:28:02 I don't know, I haven't counted. 12:29:20 elliott: I'm using cpanminus 12:29:22 also local::lib 12:29:23 -!- ais523_ has changed nick to ais523. 12:29:29 luckily the two play together well 12:29:36 although it's a pain to get initially set up without root 12:30:00 -!- Kiwitinker has joined. 12:35:50 `welcome Kiwitinker 12:36:09 Kiwitinker: 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.) 12:37:10 hi 12:39:02 -!- Kiwitinker has left. 12:39:20 that was pointless 12:39:42 The welcoming procedure sure saves a lot of time, though. 12:39:52 yes 12:39:59 btw, what's that hash in the topic the hash /of/? 12:40:24 You will need to break SHA-3 to find out, I suppose. 12:40:40 (Perhaps that's why it's in the topic.) 12:40:42 or ask someone who was present for the hashing 12:40:47 although, that's an SHA-3 hash? 12:40:52 I assumed those would be alphanumeric or something 12:41:01 and it looks like an SHA-2 hash based on the length 12:41:08 SHA-3 lengths are equal to SHA-2. 12:41:20 And SHA-3 was the topic when the hash was added, so I kind of assumed. 12:41:29 That's what the "new hash function overlords" is referring to. 12:41:51 yes 12:43:01 Yup, SHA3-224. 12:43:06 That's what it's claimed to be. 12:44:13 Apparently it's a hash of "I, for one, welcome our new hash function overlords". 12:44:21 aha 12:44:27 was that checking the logs, or guessing the input? 12:44:42 Checking the logs. 12:44:51 To find the hash algorithm; it was mentioned, nearby. 12:49:12 is there a nonbreaking version of  ? 12:50:55   is kinda. 12:51:14 It's the U+202F NARROW NO-BREAK SPACE, "a narrow form of a no-break space, typically the width of a thin space or a mid space". 12:51:22 thanks 12:51:25 (But that's a bit vague.) 12:52:10 -!- Phantom_Hoover has joined. 12:55:38 fizzie: well it looks right, anyway 12:56:03 -!- ogrom has quit (Quit: Left). 12:58:42 -!- ogrom has joined. 13:02:49 -!- ais523 has quit (Read error: Connection reset by peer). 13:03:22 -!- ais523 has joined. 13:16:11 -!- ais523 has quit (Read error: Connection reset by peer). 13:16:28 -!- ais523 has joined. 13:16:32 [14:15] hmm, I take it Haskell doesn't have ignore in its standard library, on the basis that it's completely useless? 13:16:33 [14:15] or did someone put it there anyway? 13:16:35 :t ignore 13:16:36 Not in scope: `ignore' 13:16:43 not in Prelude, at least 13:17:32 ais523: what type? 13:26:07 fizzie: by the way what function got chose as sha-3 13:26:10 i assume you are Wise enough to Know 13:27:11 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:28:01 -!- ais523 has quit (Read error: Connection reset by peer). 13:28:08 -!- ais523_ has joined. 13:29:40 elliott: That kcckkaekekcakce one. 13:29:43 elliott: Keccak. 13:29:53 The one that sounds like Korean laughter. 13:32:02 -!- ais523_ has changed nick to ais523. 13:37:34 -!- heroux has quit (Ping timeout: 240 seconds). 13:46:12 fizzie: Did that one have any ~famous names~? 13:48:33 elliott: I don't know who's famous in crypto-circles; but I mean it's not the Schneier one. These people were from STMicroelectronics. 13:49:02 Oh, and it's also not that Grøstl thing that had some reasonably known dude I believe. 13:49:03 -!- copumpkin has joined. 13:49:04 one advantage of keccak that people are mentioning is that it's completely different from sha-2 13:49:14 so they think it's unlikely they'll both be broken the same way 13:49:27 And the other is the parallelizability and efficiency in especially hardware implementations. 13:50:30 Keccak is one of those spongey things, so for once it's not a Merkle-Damgård construction. 13:51:00 fizzie: is it meant to be particularly efficient or particularly inefficient? 13:51:03 efficient, I guess 13:51:09 Efficient, yes. 13:51:15 we have block ciphers for the inefficient hashes 13:51:58 It's got some kind of a "tree mode" thing that's supposed to be even more parallelizable; there are GPU implementations already. 13:51:59 -!- DH____ has quit (Read error: Connection reset by peer). 13:52:21 -!- DHeadshot has joined. 13:52:24 And supposedly it's especially efficient when it comes to speed/area considerations in dedicated hardware. 13:52:28 -!- Arc_Koen has joined. 13:53:17 And the software implementation, while maybe not the fastest of SHA-3 candidates, wasn't too bad either. 13:53:45 fizzie: I guess Schneier and Bernstein are cryptofamous to me and nobody else. :p 13:53:45 I think I saw something like 12.5 cycles/byte mentioned. 13:53:52 How do you pronounce Keccak anyway? 13:54:02 Rijndael was bad enough. 13:54:24 elliott: I think you pronounce the double c as a k, and don't let the vowels interact with each other 13:54:29 elliott: According to kmc, "it's pronounced 'kashyyyk'", but... 13:54:52 That *was* right after references to LORD KECCAK and so on. 13:54:59 "8068" is the least common PIN -- that'll probably change now that the fact is published. 13:55:52 the world's least memorable 4-digit number? 13:56:00 no 13:56:02 that's easy to remember 13:56:02 I don't know, it's like 8086 with a swapped second pair. 13:56:04 it's the least common PIN 13:56:08 least pressnice number. 13:56:10 now I'll never forget it 13:56:12 I should use it 13:56:25 if anything 13:56:26 You should use it as your personal PIN number. 13:56:35 i don't get to choose mine :/ 13:56:36 then if someone tries to spy on me while I put it in I'll say aah, you'll never get it, it's the least common PIN number in the world! 13:56:45 fizzie: fuck you 13:56:48 fizzie: I use PNG graphics too!! 13:56:59 It's good to use portable PNG graphics files. 13:57:01 I'll put my fucking PIN number in the fucking ATM machine and you won't complain 13:57:12 On the network. 13:58:38 hello 14:01:30 -!- ogrom has quit (Quit: Left). 14:11:04 fizzie: Pungent Nocturnal Gerbils. 14:20:26 -!- augur has quit (Remote host closed the connection). 14:25:11 penis nads genitals lol haha 14:47:49 -!- Jafet has quit (Quit: Leaving.). 14:50:08 -!- FreeFull has joined. 14:57:40 -!- augur has joined. 15:00:59 -!- augur has quit (Remote host closed the connection). 15:01:16 -!- atriq has joined. 15:01:28 -!- Jafet has joined. 15:01:46 @messages? 15:01:46 Sorry, no messages today. 15:01:48 Yay 15:09:52 -!- augur has joined. 15:10:45 -!- mig22 has quit (Quit: mig22). 15:15:07 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 15:25:12 Did we work out what to call that category last night? 15:25:55 friend 15:40:00 Yay 15:40:12 So not the Product Semigroupoid or something like that 15:43:14 -!- ogrom has joined. 15:46:11 friend is a better name 15:47:51 Indeed it is 15:59:10 -!- sebbu has quit (Ping timeout: 260 seconds). 15:59:55 ...I need better friends 16:00:02 elliott, will you be my friend? 16:02:45 I'm experiencing Ship-to-ship combat in the TVTropes sense 16:02:49 Of REAL PEOPLE 16:02:53 SOME OF WHOM ARE ME 16:03:10 I... think I will elect to not get involved. 16:03:20 You could try being friends with fizzie??? He's nice! 16:03:30 btw, Gay Dads is a way better ship than Alladin 16:03:36 -!- sebbu has joined. 16:04:23 fizzie: Have fun! 16:09:21 -!- Phantom_Hoover has joined. 16:11:37 How do OpenOffice and LibreOffice differ? 16:13:21 Most of the developers moved to LibreOffice 16:13:37 atriq: LibreOffice was going to be “the” followup to OOo until Oracle decided to give it to Apache. It's not clear where OOo is going now, but LibreOffice has made a lot of code cleanups, and hypothetically things are much smoother (I haven't noticed any difference). Most of the developers and distros jumped ship before the OOo->Apache switchover. 16:15:52 atriq: One has an "Open" and the other a "Libre". 16:17:42 Wait, LibreOffice is no longer the followup to OOo? 16:18:31 Sgeo: LibreOffice came about when it looked like Oracle was just going to let it stagnate, but instead they gave the rights to the Apache foundation. 16:21:41 -!- esowiki has joined. 16:21:42 -!- glogbot has joined. 16:21:43 -!- glogbackup has left. 16:21:45 -!- esowiki has joined. 16:21:46 -!- esowiki has joined. 16:21:55 -!- FireFly has joined. 16:23:03 The Apache Foundation seems to do a lot of stuff that's not web server stuff 16:23:14 They maintain some sort of convenience library for I/O stuff in Java 16:23:28 Yeah, they do all sorts of shit. 16:23:29 And ... a packaging system for Java 16:23:32 Emphasis on “shit” 16:23:55 They have that Google Wave thing which was actually quite cool but nobody understood it 16:24:02 -!- zzo38 has joined. 16:24:17 Ride the Google Wave dot Com 16:24:51 * Sgeo is sort of in the Java ecosystem now, for better or worse 16:25:21 Sort of In the Java Ecosystem Now: The Game of the Movie 16:25:39 Yeah, I'm kinda in the Java ecosystem too right now. 16:25:44 P.S. I work at Oracle, lol 16:26:16 Sort of In the Java Ecosystem Now/Kind of In the Java Ecosystem Now, double concept album about being resp. sort of and kind of in the Java ecosystem now. 16:27:06 I would buy that album. 16:27:08 And then return it. 16:27:45 one day I will make it and it will be a modern masterpiece 16:28:50 new JavaEcosystemManagerFactory().getJavaEcosystemManager(new DefaultJavaEcosystemFactoryConfig()).add(new JavaEcosystemElement(Sgeo)).add(new JavaEcosystemElement(Gregor)) 16:29:05 ; 16:29:16 prospective song titles: Ant (What the Fuck is This Shit? Is that XML?); I Don't Fucking Understand Maven, Guess it's Back to Ant; Hey, It's Alright, I Never Cared About GUI Toolkits that Are Worth a Damn Anyway 16:29:57 Leiningen is good... until you want to use a standalone .jar in your project. 16:30:01 kmc: new EcosystemManagerFactoryFactory(new JavaEcosystem()).createEcosystemManager(new JavaEcosystemConfiguration(JavaEcosystemConfiguration.CONFIGURATION_PARAMETERS.DEFAULT)) 16:30:16 Damn These Folks Are Some Windows-Using Bullshit 16:30:18 Oops, misused my factory factory. 16:30:38 kmc: new EcosystemManagerFactoryFactory().createEcosystemManagerFactory(new JavaEcosystem()).createEcosystemManager(new JavaEcosystemConfiguration(JavaEcosystemConfiguration.CONFIGURATION_PARAMETERS.DEFAULT)) 16:30:48 Wanting to Release a Java Package but Not Having a Domain Name to Name the Package With Blues (Pt. I) 16:30:58 i hope you are all imagining these songs in your head 16:31:07 Also, does Swing really suck that much? And if it does, is it usability issues or fundamental issues? Because if the former, there's a Clojure library called Seesaw. 16:31:07 import static cx.goatse.*; 16:31:30 elliott: I don't think your suggestion "took". 16:31:41 Sgeo: Now if only Clojure didn't suck that much… 16:32:10 :/ 16:32:33 ouch 16:33:10 i would buy that album and then return it but first i would rip it but only to 96 kbps mp3 16:33:10 JVM-Hosted Languages Trilogy: Pt I. Clojure (Hey, This is Almost Lisp); Pt II. Scala (Hey, This is Almost Haskell); Pt III. Conclusion (Wow, They're All Shit) 16:33:30 you forgot rhino!!!!!!!!!111 16:33:50 hi is it make fun of java o'clock 16:34:07 gdoo mgornin etlliot 16:34:09 kmc: Downloading an Illegal Pirated Copy of the Timeless Classic "Sort of In the Java Ecosystem Now/Kind of In the Java Ecosystem" Using HotJava 16:34:23 if you are in the java ecosystem you have to use hotjava 16:34:26 those are the rules 16:35:06 kmc: also if i included rhino it wouldn't be a trilogy 16:35:10 and i don't know what comes after trilogy 16:35:17 i'm here to provide the soul dammit 16:35:26 The HHGG trilogy is not a trilogy. 16:35:38 elliott is the sole provider 16:35:54 The first Xanth trilogy has 3³ books. 16:36:02 They're all pretty much the same. 16:37:38 has anyone actually used hotjava 16:37:38 i have 16:41:25 elliott: Clojure is your argument for the popularity of Lisp? All seven Clojure users thank you. I never said Lisp is popular eh But it's the only dialect that actually has got some uses outside of academia and long-forgotten companies. Yes, by soon-to-be-long-forgotten companies. * Sorella uses it at work D: 16:47:52 clojure is like haskell but worse and also less popular 16:48:08 Clojure isn't really like haskell 16:48:18 it was a not entirely serious comparison 16:48:22 they both try to do stm! only one succeeds 16:55:39 elliott: Do you know how MonadFix works? 16:56:00 And RecursiveDo. 16:56:05 -!- AnotherTest has joined. 16:56:16 Hello 16:56:35 shachaf: Sort of. 16:56:36 Bye. 17:01:00 -!- elliott has quit (Ping timeout: 260 seconds). 17:02:34 ais523: Have you read my suggestion for the wiki? What do you think? 17:09:40 I think you can make a writer monad with Codensity and it can also be done with CodensityAsk. 17:10:20 -!- kinoSi0 has joined. 17:10:22 -!- TeruFSX_ has joined. 17:10:47 -!- kinoSi has quit (Read error: Connection reset by peer). 17:12:47 -!- TeruFSX has quit (Ping timeout: 240 seconds). 17:18:01 -!- epicmonkey has quit (Ping timeout: 246 seconds). 17:18:50 For example: newtype X y z = X { runX :: y -> z -> z }; type Writer x = CodensityAsk (X x); write x = CodensityAsk (\(X a) f -> a x $ f ()); runWriter (CodensityAsk f) = f (X $ \a (b, c) -> (a : b, c)) ((,) []); 17:20:35 To make a write monad with Codensity, you could make up a "write only" class. 17:29:31 -!- ogrom has quit (Quit: Left). 17:33:48 -!- AnotherTest1 has joined. 17:34:19 -!- AnotherTest has quit (Read error: Connection reset by peer). 17:37:19 -!- variable has joined. 17:37:33 -!- augur has quit (Remote host closed the connection). 17:37:42 -!- variable has changed nick to Guest89785. 17:38:02 -!- Guest89785 has quit (Changing host). 17:38:02 -!- Guest89785 has joined. 17:38:04 -!- Guest89785 has changed nick to trout. 17:39:58 > dec 0xbe631ff0 17:39:59 Not in scope: `dec' 17:40:17 > 0xbe631ff0 17:40:18 3194167280 17:40:29 > 0b100101 17:40:31 Not in scope: `b100101' 17:40:44 > 0771 17:40:45 771 17:40:51 ^ I wanted to resize the stack to that :( 17:40:59 > 0o771 17:41:00 505 17:41:04 If you wanted octal. 17:41:23 Sadly, I don't think it does binary literals. But there's always the things that read strings. 17:43:51 > fst . head $ readInt 2 isDigit digitToInt "100101" 17:43:53 37 17:44:47 There only seems to be premade readOct, readDec and readHex. Poor binary numbers, nobody likes 'em. 17:45:08 !perl print oct("0b100101"); 17:45:10 37 17:45:24 Except maybe Perl and a few other guys. 17:45:49 Now that you say 17:45:55 -!- AnotherTest1 has changed nick to AnotherTest. 17:45:56 -!- augur has joined. 17:45:59 can you do that in C? 17:46:04 happy canadian thanksgiving 17:46:12 AnotherTest: What, 0b000 literals? Not standardly. 17:46:29 binary numbers are being discriminated! 17:46:41 GCC has an extension for 0b, unsurprisingly. 17:47:38 No printf formatting specifiers for binary in glibc, though, as far as I know. 17:48:36 !c printf("%ld\n", strtol("111", NULL, 2)); 17:48:39 7 17:50:08 Now do it the other way around. 17:50:17 Yeah, that's the problem, innit :) 17:51:53 The ##c bot has a %b that's like %o/%u/%x except with binary. (Glibc has a mechanism for hanging custom hooks on unused -- maybe used, too -- conversion specifiers.) 17:53:17 !c printf("%n", *(0)); 17:53:18 Does not compile. 17:53:31 !c printf("%n", (void *)0); 17:53:34 ​./interps/gcccomp/gcccomp: line 52: 17997 Segmentation fault /tmp/compiled.$$ 17:53:35 dereference (0)? 17:54:11 Dereferencing NULL is fun >_> 17:54:18 The weirdo printf specifier that writes to memory. 17:54:31 wut 17:54:47 Wow 17:54:58 %n does that. 17:55:04 Yeah, just read X-D 17:55:08 I believe there's been a number of related security bugs. 17:55:09 oh 17:55:28 Why does printf have a command to write to memory? That doesn't make sense. 17:55:46 zzo38: It writes the number of so-far output characters there. 17:56:05 zzo38: I believe it's meant for tricky aligning of things and so on. 17:56:17 I think it would make more sense to just use the result of printf doesn't it already do that? 17:56:30 Yes, but that's the total string. 17:56:39 You can stick %n in the middle. 17:56:58 You can call printf more than once, too. 17:56:58 -!- hagb4rd has joined. 17:57:18 Deewiant: Sure, but it's inkonkkenient. 17:58:38 !c int i, j; printf("%d%n%d%n", 123, &i, 456, &j); printf(" - %d %d", i, j); 17:58:40 123456 - 3 6 17:59:26 !c int i = printf("%d", 123), j = printf("%d, 456)"; printf(" - %d %d", i, j); 17:59:27 Does not compile. 17:59:32 Oops. 17:59:34 Well, anyway. 17:59:37 There was some bit in the standard related to sequence points or something that was only meaningful because of %n, I think. Maybe even a footnote. 17:59:58 Something about there being a sequence point after each conversion specifier. 18:00:17 I don't see why %n would have any relevance to sequence points. 18:00:23 So you can have %n writing into a string later printed with %s and it's well-defined. 18:00:37 If crazy. 18:01:05 … but %n doesn't write into a string, and if you did %n%d, then the %d would receive the old value. 18:01:21 But that has nothing to do with %n, it's just arguments being evaluated well before it's dereferenced. 18:01:24 %n can write into a string of you point it at one. 18:01:34 Is %n allowed to write a single byte value? 18:01:48 fizzie: OK, but that still has nothing to do with sequence points, it just has to do with the algorithm used by printf. 18:02:19 Gregor: But if there wasn't a sequence point after the %n you couldn't say whether it was the old or new value. 18:02:47 fizzie: That's not a sequence point, sequence points define the order of evaluation of subexpressions within a single expression. 18:02:58 fizzie: That's just steps in the algorithm of printf. 18:03:22 There are sequence points between statements, you know. 18:03:23 Let me quote it for you. 18:03:51 Yes, of course there are, that's what makes statements statements, but sequence points are what define the semantics of the C /language/, not C library functions. 18:04:21 s/are what// 18:05:30 Uh, after I clean up some cat puke. 18:08:34 "The formatted input/output functions shall behave as if there is a sequence point after the 18:08:38 actions associated with each specifier.274) 18:08:39 274) The fprintf functions perform writes to memory for the %n specifier. 18:08:53 C11 7.21.6p1 and the footnote. 18:09:03 Why… would they word it that way X_X 18:09:39 Well, I suppose that's not worse a way to word it than anything else, but it confuses a language issue with a library issue. 18:10:10 Since you can't know anything about what goes on in the algorithm of printf, presumably they wanted to guarantee there's a sequence point in-between. I mean, a sequence point is defined to mean that all side effects have completed. 18:10:18 "The presence of a sequence point 18:10:18 between the evaluation of expressions A and B implies that every value computation and 18:10:22 side effect associated with A is sequenced before every value computation and side effect 18:10:25 associated with B. 18:10:28 And so on. 18:11:54 “Since you can't know anything about what goes on in the algorithm of printf” 18:12:04 Of course you can, the C spec is defining its behavior! 18:12:46 I'm not sure what that means. 18:13:03 Do they still make ARMv2? 18:14:44 fizzie: You're saying that the C spec can't know anything about what goes on in the algorithm of printf, when it's /defining/ printf. It can choose to be as lax or precise in that description as it would like. This is an imperative language, it should be defining the imperatives, not trying to define it as if this were a functional language and then throwing sequence points, a trick to add precision to the language semantics, to the description of the implementat 18:14:44 ion of a function. 18:15:14 Gregor: I'm not sure how it should be "defining the imperatives" there. 18:16:18 Gregor: I mean, it's defining certain actions that are associated with the conversion specifiers, and some of those actions involve side effects like writing to memory, so it's defining in which order those actions are sequenced, using the terminology related to those side effects. 18:17:18 * ion of a function. 18:18:03 ion: "ion of function" could be your kind-of title. 18:18:16 Is the VAX printf only using BCD? 18:18:59 zzo38, did you think of a name for yesterday's category? 18:19:33 atriq: No, I did not. 18:19:52 atriq: how's your userpage? 18:19:54 well people page 18:20:35 Nonexistant 18:20:37 Um 18:20:42 I'm not very interesting 18:20:43 Well 18:20:55 I walked backwards to my maths lesson today for the hell of it 18:21:54 -!- hagb4rd has quit (Ping timeout: 256 seconds). 18:23:02 atriq: what did you do? 18:23:15 atriq: Physically walked backwards? 18:23:45 Arc_Koen: are you responsible for the latest TDWTF entry? 18:23:48 or is it a different Koen? 18:24:10 (07:05:39 PM) AnotherTest: ais523: Have you read my suggestion for the wiki? What do you think? 18:24:49 The idea was to have infoboxes 18:25:50 AnotherTest, yes 18:26:04 atriq: explain! 18:26:09 My ankles started hurting after a while 18:27:09 atriq: So you walked backwards through the corridors of your school or something? 18:27:12 I walked backwards out of the library, up the staircase, waited outside a door for a bit, then into the classroom and sat down 18:27:29 aha 18:27:52 Then after the lesson I walked backwards out of the room, down a staircase, up the staircase again, along a corridor, down a different staircase, along another corridor, and back into the library 18:28:07 atriq: Weren't you at all afraid that someone would videotape (uh, I mean... mpeg-4-solid-store...) your walking, and then play it backwards, generating the illusion that you were walking forward? 18:28:29 Not really. 18:28:32 and all your friends said "oh, that's perfectly normal, no reason to put this on youtube"? 18:28:42 There's worse videos of me on the internet 18:29:05 2009 and 2010 were weird years for me 18:29:20 Walk backwards in the hallway with clock. 18:29:51 atriq: how so? 18:30:44 a lot of backwards-walking? 18:31:19 Do I want to tell you? 18:31:26 Hmm 18:31:32 It sounds as if you do. 18:31:46 Youtube "Cool kid plays air drums" and "Cool kid plays air drums 2" 18:32:03 aha 18:32:14 Ooh, you've been one of the cool kids. 18:32:16 Your lucky I don't have flash 18:32:24 HTML 5? 18:32:33 doesn't always work 18:32:43 I hope it does 18:32:50 doesn't 18:32:56 This is bullying? 18:32:56 -!- hagb4rd has joined. 18:33:55 -!- ogrom has joined. 18:34:18 it is 18:34:35 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 18:34:42 It was me not caring about my personal image 18:36:48 If you're randomly walking backwards these days, it doesn't sound all that terribly careful nowadays either. 18:37:04 Indeed 18:37:28 Maybe you should consider not doing that? 18:38:25 I realized RogueVM has some things similar to VAX. Unlike VAX, you are allowed to use PC as the destination and as an index, though. RogueVM can use immediates as a destination, has its own instruction set for converting numbers to ASCII (but with a different byte length!), you can use any addressing mode with any istructions, etc 18:38:25 (07:05:39 PM) AnotherTest: ais523: Have you read my suggestion for the wiki? What do you think? ← sorry, that line is entirely too zzo38 and I'm having problems reading it as a result 18:39:08 ais523: Is having infoboxes a good idea or not? 18:39:49 In VAX, "Something like tstl (pc)+ can also be assembled, which is like a literal (same specifier), but reads from part of the following instruction." RogueVM also works like that for literals too 18:39:50 -!- DHeadshot has quit (Read error: Connection reset by peer). 18:40:18 ais523: on wikipedia, programming language pages (and many other stuff) have these boxes at the right side of the page. I think it would be nice to have general information about a language in there. 18:40:25 I've since then carefully constructed a personal image based on being weird 18:40:47 And not caring about my personal image 18:41:08 AnotherTest: Perhaps it might if they also have a database search so that the infoboxes can also be used in database tables and queries, perhaps? 18:41:26 zzo38: sounds good, if it's possible 18:41:40 -!- ais523 has quit. 18:41:46 -!- ais523_ has joined. 18:41:58 zzo38: I don' t know much about mediawiki software and it's features 18:44:15 I think it's useful when looking something up quickly. Eg. you want to know which languages influenced C++, in that case you can find it really fast on wikipedia 18:44:31 For esoteric languages this would be useful too 18:44:59 I don't think MediaWiki has it built-in but extension could be added. (With Hackiki, such extensions are just normal articles that anyone can write.) 18:45:39 Anyway, bye 18:45:53 ais523_: let me know what you think / whether it's possible 18:46:08 -!- AnotherTest has quit (Quit: Leaving.). 18:50:43 -!- hagb4rd has quit (Quit: hagb4rd). 18:59:22 -!- augur has quit (Remote host closed the connection). 18:59:49 Hm. There exist Turing machines that halt in some models of ZFC, but not others. 19:02:09 Isn't that annoying? 19:04:03 What is ZFC in this context? 19:04:14 the set theory? 19:04:31 Yep. 19:05:06 If a Turing machine does not halt, but ZFC cannot prove that it does not halt, then there exists a model of ZFC in which it *does* halt. 19:05:18 How can Turing machines half in some models of ZFC but not others? 19:05:36 How does that work? 19:06:31 Define a "strange Turing machine" as one that does not halt, but, in a given model of ZFC, does halt. 19:06:46 In such a model of ZFC, a strange Turing machine halts after a non-standard number of steps. 19:07:03 Where a "non-standard number" is a number that exists in the model of ZFC, but not in the "real world". 19:07:19 OK. 19:07:35 Do you have examples? 19:08:16 An example of a non-standard number? No. 19:08:33 But here's a set theory that formally defines the predicate "standard": http://en.wikipedia.org/wiki/Internal_set_theory 19:08:42 Or, at least, gives axioms for it. 19:09:31 And people say maths is hard. 19:10:15 Not only non-standard numbers, I mean examples of strange Turing machine and such model of ZFC and so on. 19:10:22 Ah. 19:11:17 Well, it's impossible to prove that a Turing machine is strange, but an example of a strange Turing machine *may* be the one that searches for a counterexample to Goldbach's conjecture, and halts when it finds one. 19:12:11 -!- Phantom_Hoover has joined. 19:12:23 That Turing machine is strange if and only if Goldbach's conjecture is both true and unprovable. 19:12:53 If that Turing machine *is* strange, then ZFC + "Goldbach's conjecture is false" is a consistent system. 19:13:21 @_@ 19:14:15 what does strange mean 19:14:43 Phantom_Hoover: a "strange Turing machine" is one that does not halt, but, in some model of ZFC, does halt. 19:15:05 O.o 19:15:22 Or, more mundanely: it's one that does not halt, but which we cannot prove does not halt. 19:17:45 Hmm 19:17:58 If the Product type is a Semigroupoid 19:18:08 Is the Coproduct type a Cosemigroupoid? 19:18:42 it's a cosmic groupie 19:18:47 What even is a cosemigroupoid 19:18:55 I suddenly wish that mathematics had a sophisticated nomenclature like chemistry does. 19:19:01 It's a googlewhack, for one 19:23:00 I don't know what a cosemigroupoid is 19:23:14 Is a Cocategory a thing? 19:23:32 Evidently 19:23:59 I don't know what cocategory is either 19:24:08 How about a cogroupoid? 19:24:17 Or for that matter, a groupoid? 19:24:23 Would that be a category with inverse? 19:24:33 inv :: (a ~> b) -> (b ~> a)? 19:27:59 Yes, I think so 19:30:14 -!- augur has joined. 19:30:40 :t inv x y = y x 19:30:41 parse error on input `=' 19:30:46 :t let inv x y = y x 19:30:48 : not an expression: `let inv x y = y x' 19:32:14 -!- oerjan has joined. 19:36:18 :t let inv x y = y x in inv 19:36:19 forall t t1. t -> (t -> t1) -> t1 19:36:23 :t flip id 19:36:25 forall a b. a -> (a -> b) -> b 19:36:53 :t flip 19:36:55 forall (f :: * -> *) a b. (Functor f) => f (a -> b) -> a -> f b 19:37:14 :t flip (fmap (+ 1) [1,2,3]) 19:37:15 forall a b. (Num b) => a -> [b] 19:37:21 > flip (fmap (+ 1) [1,2,3]) 6 19:37:23 [2,3,4] 19:37:26 :O 19:37:33 > flip (fmap (+ 1) [1,2,3]) undefine 19:37:34 Not in scope: `undefine' 19:37:35 > flip (fmap (+ 1) [1,2,3]) undefined 19:37:37 [2,3,4] 19:38:17 :t flip . ($) 19:38:18 forall a b a1. (a1 -> a -> b) -> a -> a1 -> b 19:39:24 why don't you require another argument... 19:39:35 oh wait it's a list 19:40:19 :t flip (fmap (+ 1) [1,2,3]) 19:40:20 forall a b. (Num b) => a -> [b] 19:40:46 oh right it's because of lambdabot's Num (a -> b) instance 19:41:48 @src flip 19:41:48 flip f x y = f y x 19:41:52 ... 19:41:59 that's not the one lambdabot uses, obviously :P 19:42:12 :t flip 19:42:13 forall (f :: * -> *) a b. (Functor f) => f (a -> b) -> a -> f b 19:42:19 :t \f a -> fmap ($ a) f 19:42:20 forall a b (f :: * -> *). (Functor f) => f (a -> b) -> a -> f b 19:42:56 :t \f -> flip fmap . id 19:42:57 forall t a b (f :: * -> *). (Functor f) => t -> f a -> (a -> b) -> f b 19:43:03 :t \f -> flip fmap f . id 19:43:05 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 19:43:22 :t \f -> (.) (flip fmap f) id 19:43:23 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 19:43:39 :t flip (.) id . flip fmap 19:43:41 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 19:43:45 PERFECTION 19:43:52 :t flip fmap id . flip fmap 19:43:53 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 19:43:59 Wait 19:44:02 um... 19:44:02 IMPERFECTION 19:44:30 -!- ogrom has quit (Read error: Connection reset by peer). 19:44:56 :t \f -> (. f) . fmap . ($) 19:44:57 forall (f :: * -> *) a b (f1 :: * -> *). (Functor f, Functor f1) => f (f1 a) -> (a -> b) -> f (f1 b) 19:45:10 eek 19:45:38 oh wait 19:45:43 :t \f -> (. f) . fmap . flip id 19:45:44 forall (f :: * -> *) b (f1 :: * -> *) a. (Functor f, Functor f1) => f (f1 (a -> b)) -> a -> f (f1 b) 19:45:46 :t \f a -> flip fmap f ($ a) 19:45:48 forall b (f :: * -> *) a. (Functor f) => f (a -> b) -> a -> f b 19:45:56 :t \f a -> flip fmap f . ($) 19:45:57 forall t a b (f :: * -> *). (Functor f) => f a -> t -> (a -> b) -> f b 19:46:01 NO 19:46:07 :t \f -> flip fmap f . ($) 19:46:09 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 19:46:14 NO NO NO 19:46:28 @pl \f a -> fmap ($ a) f 19:46:28 flip (fmap . flip id) 19:46:37 YES 19:46:48 flip in terms of flip 19:46:49 OKAY 19:47:10 :t let flip = flip (fmap . flip id) in flip 19:47:11 Occurs check: cannot construct the infinite type: f = (->) (f a) 19:47:11 Probable cause: `flip' is applied to too many arguments 19:47:11 In the expression: flip (fmap . flip id) 19:47:16 FANCY 19:48:17 Did anyone find a use for the Product Semigroupoid? 19:48:36 not that i recall 19:49:03 although i think i found that the Product Semigroupoid is a product of semigroupoids. 19:49:04 Is that even a remotely correct name? 19:49:31 well it's (,) 19:50:08 (those semigroupoids being Const and Dual Const, in some sense) 19:50:59 (just notice that the semigroupoid operation on the fst and snd elements are independent 19:51:03 ) 19:53:09 but with something like lint checking, maybe there's a 'false sense of security' problem, where people focus on making the lint checker's irrelevant complaints go away rather than actually reviewing their code 19:53:52 maybe it is most helpful if there is a requirement to pass lint before an _actual_ code review even starts 19:54:11 which would mean that code review won't be bogged down in trivialities 19:54:15 yeah 19:54:29 that makes a lot of sense 19:54:43 we aren't doing code reviews currently :/ 19:54:52 not bad for something i made up on the spot >:) 19:55:33 which reminds me, itidus2[01] is still absent 19:55:53 i hope it's nothing serious 19:56:46 * oerjan wishes freenode didn't reset the dates on the ban list 19:57:49 also that irssi didn't put it in the channel window 20:02:33 well a bunch of people told him off for being full of shit 20:02:42 which i think has happened at least 100 times before 20:02:46 but maybe it took this time 20:03:47 it would have been nice if it gave him a clue rather than chase him away, though 20:04:01 but i guess that rarely works 20:04:43 hm he is on freenode somewhere. 20:06:09 Is it possible to call C++ code from Haskell using the FFI? 20:06:24 Or is it just C code? 20:07:30 atriq: not directly, no. 20:07:40 Eugh. 20:07:44 How about UnrealScript? 20:08:18 i think the general advice is to make a small C interface 20:08:33 Heh, much, much more trouble than it's worth 20:11:43 "According to "The Haskell 98 Foreign Function Interface 1.0" report -- you import a C++ function by simply specifying the calling convention cplusplus. Unfortunately, no haskell compiler actually supports this calling convention, so we have to use the C calling convention instead." 20:12:06 "The standard method for dealing with this is to write C++ code that uses extern "C" to export the methods unmangled. Of course, you still have to uniquify the method names, but *you* get to pick the names instead of letting the compiler do whatever wacky method it wants." 20:12:23 and then the rest of the haskellwiki page describes something much more hairy. 20:17:01 atriq: my impression is that calling any other language from haskell or vice versa usually goes via their common C interface 20:17:56 and that this still sometimes leaves the problem of getting one of them to accept not being the main program 20:19:08 (well haskell doesn't have to be, but then you have to get the ghc runtime system set up with the right C calls.) 20:19:50 ais523_: I have no idea what TDWTF is 20:19:57 The Daily WTF 20:20:40 yup that's what google told me 20:20:44 a site showcasing bad code. by what i hear, often badly :) 20:21:39 hmmm I guess I don't use C often enough to find that "block" special 20:21:41 if you know how your compiler is going to name-mangle C++ functions *and* if the C++ calling convention is compatible with the C one, then you can call them directly 20:21:44 but it's not recommended 20:22:17 (and for my defense there's another Koen on freenode) 20:22:53 -!- ais523_ has changed nick to ais523. 20:22:59 how can there be more than one Koen 20:23:29 that's actually a pun on my name which works pretty well in french 20:24:39 because it sound like "qu'une", which basically means "only one" (except une is the feminine form) 20:25:27 ceci n'est pas une qu'une 20:25:32 oerjan: what about "If no variable is nonzero, skip to the matching END." for ndeql's begin 20:25:42 oops, pardon my accidental boldness 20:26:12 oerjan: you just said "this is not an only one" 20:27:58 Arc_Koen: i think that would make [-] clear all variables, right? (although using unpredictable time doing so.) which i think may mean you can somehow treat all the variables as a single bit in a usable way. 20:28:10 Arc_Koen: it was a pun on "Ceci n'est pas un pipe" 20:28:29 er 20:28:33 * \-/ 20:28:51 oh, ok 20:29:26 oerjan: nope, that wouldn't 20:29:50 why not? it wouldn't quit the loop until they're all zero. 20:29:56 because decrement wraps 20:30:03 oh 20:30:05 ohhhhh right 20:30:19 well, yes 20:30:19 well yes, but i'm assuming it would statistically hit all zero _eventually_. 20:30:43 right, so in fact any loop is either an infinite loop or a loop that sets all variables to zero 20:30:49 yeah 20:31:32 although still still doesn't make it easy to put predictable things in the deque ... _some_ variable could be zero when you try to put a nonzero there 20:31:36 *this still 20:31:42 it's a queue 20:32:02 sorry, confusing a bit with your other language 20:32:32 hehe 20:33:07 adding instructions to affect the other side of the queue in ndeql would probably not change much, though 20:34:36 hmmmmmm what about: a deque with "pop", "push", "toggle", a register, and cannot toggle inside loops 20:34:53 (but the register is always accessible, so information can pass from one side to the other) 20:35:29 and maybe conditionals (which don't loop) inside which you can toggle 20:37:13 hm i'm thinking \\-/=\ ... // might be a way to get something dequeued in a usable way... 20:40:20 i'm wondering if you could check if the sum of the variables is odd or even 20:40:40 "until all variables are zero: (set them all to zero, dequeue one element (enqueuing a zero), and then until all variables are zero, do something that has no effect if the selected variable is zero, but which does what we want to do AND set all variables to zero if the selected variable is the right one )" 20:41:42 ndeql_oracle(\--/) checks if the sum is odd or even 20:41:54 fancy 20:42:06 not _quite_ what i had in mind :) 20:43:18 hmmm 20:43:48 ok here's a lead: if we can find a way to determine whether a loop allows for all variables to be set to zero or not 20:44:17 then we have proven that ndeql is not turing complete 20:45:04 i think my brain is overloading again 20:46:09 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 20:47:29 it doesn't like to think about things that are changing underneath it. 20:48:01 oh, yeah 20:48:05 that's what I play go and not chess 20:48:40 i thought go had change, but i haven't actually played it :) 20:48:41 (that and the fact that go is objectively SO MUCH more better than chess) 20:48:52 but of course 20:49:02 weeeeeell uh there do exist several rules 20:49:15 depending of the country you're in and the wather 20:49:17 weather 20:49:17 * oerjan sort of got tired of chess 20:49:27 Arc_Koen: i meant the board changing. 20:49:31 oh 20:49:43 i don't think the rules change in chess either. 20:49:56 wait, why am i thinking like this, i used to play nomic... 20:50:00 There are many variants of chess and go, some combined both, some changing the rules during the game or changing the geometry of the board, some with hidden information, etc 20:50:31 well japanese rules and french rules for go are much closer than shogi and occidental chess are 20:50:54 oh, this summer we tried the "phantom rengo" side tournament during the european congress 20:51:33 * oerjan considers trying to eat -> 20:51:44 that was a lot of fun (though the rules were not exactly "symmetric" for both teams, so white always won 20:52:26 "phantom go" means you don't see your opponent's moves (but if you try to play somewhere where there is already a stone, the referee will tell you it's a forbidden move and you can place an opponent's stone there to remember) 20:53:08 and rengo is just go with a partner (you play once, your opponents play, your partner plays, your opponents play, then only it's your turn) 20:53:37 so phantom rengo: you see your own moves and one of your opponent's moves, but neither your partner's moves neither your other opponent's moves 20:53:42 that was really fun :) 20:54:23 problem is, in phantom go it's possible to do some sort of "scams", moves that are usually stupid and easily reprehensible, but in phantom go you're hoping your opponent won't guess what you did 20:54:57 and here in phantom rengo, if the person who plays right after you is the opponent who can see your moves, you can't do that 20:55:22 but if it's the other opponents, then maybe he won't guess it, and maybe your partner will guess it, so scamming is possible 20:56:08 and unfortunately you can't set the order of turns in a way that doesn't advantage one team (that is, one of the teams will be able to scam every move, and the other will never be able to) 20:56:38 so they said "the weaker team must take white (and have that huge advantage" 20:56:48 unsurprinsigly, the weakest team won the tournament 20:57:13 oerjan: why did you stop playing nomic? 20:57:34 What if you play balanced marseillais phantom rengo? 20:58:07 never heard of balanced go or marseillais go 21:00:50 there are some funny stuff about the rules of go, though 21:00:57 for instance, it is possible to repeat the position 21:01:24 they could have just say "it's forbidden to play a move that repeats a position" but nooooo that would have been too simple 21:02:22 so they started by saying "you cannot take back an opponent's stone immediately after it was played, in that very precise shape [diagram here]" (and the shape in question is called a ko and is the most frequent way to repeat a position 21:02:46 but then if you combine three kos on the board, you can repeat the position without immediately taking back the stone! 21:03:11 they could have just say "ok, it's forbidden to play a move that repeats a position" but nooooo that would have been too simple 21:03:27 so they said "if the position is repeated three times because of a triple ko, the game is null" 21:03:32 I want to set up a one-time cron thing 21:03:39 Like an alarm clock 21:04:02 BUT it's actually possible to repeat the position in other ways (though honestly I have never see them in actual games) 21:04:17 atriq: what's a cron thing? 21:04:45 http://esolangs.org/wiki/Alarm_Clock_Radio 21:06:17 so eveyr country made its own set of rules, addressing all problems in a different way 21:06:33 Arc_Koen, Linux utility used to time commands 21:09:20 you want 'at' 21:09:39 echo mplayer -really-quiet -loop 0 ~/wakeup.mp3 | at 09:00 21:10:29 Thanks 21:11:17 I have never heard of balanced go or marseillais go either, but I have heard of balanced marseillais chess. 21:12:28 Goodnight 21:12:29 -!- atriq has quit (Quit: Leaving). 21:17:58 -!- Phantom_Hoover has joined. 21:20:40 oh, yes, we do that sometimes 21:20:53 I've even played "inflation go" a few times 21:21:15 black plays one move, white plays two, black plays three, etc. 21:21:56 it's kind of silly though, because it becomes quickly so easy to capture that you have to waste all your moves to protect yourself 21:22:42 I have another idea: Three players go where each player cannot see the stones belonging to the player who plays before him in the turn order, but you can see your own and the next player's stones. 21:23:17 nice 21:23:18 oerjan: What will you consider trying to eat? Go stones? 21:23:31 well actually multiplayer go is already quite original in itself 21:23:47 hm i didn't get around to that eating yet. 21:23:48 and we never play it because of that stupid "there's no third color" limitation 21:24:22 but playing multiplayer go is definitely on my list of things to do at least one in my life 21:24:24 That is because you don't have the stones, I guess, then buy more stones and paint them a different color, or use the computer 21:24:33 it will surely be slices of bread, though. 21:24:54 yes, another thing on my list is "write a go program that can support many many many variants" 21:25:19 oerjan: i have CHOCOLATE 21:25:33 technically so do i 21:25:52 but i'm not going to eat that for a meal 21:25:54 I'm not sure I want to know why there's a "technically" in that sentence 21:26:24 Arc_Koen: Because otherwise it looks too short. And actually you do want to know and this is the reason. 21:26:26 technically you may not 21:27:00 I'm so transparent 21:27:08 technically i am insane 21:27:33 technically this is a sentence 21:27:52 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 21:29:03 well, technically it lacked a capital and a period 21:29:20 technically i expected that comment 21:30:10 well technically you got what you paid for! 21:30:15 oh wait no you didn't 21:31:23 technically i don't think i paid 21:37:53 -!- pikhq has joined. 21:38:00 -!- pikhq_ has quit (Ping timeout: 252 seconds). 21:42:53 btw, I had an interesting idea for a potentially interesting BF derivative a while back 21:42:59 eliminate . and , because they're unnecessary 21:43:03 then create one command that does + or - at random 21:43:11 and one that does < or > at random 21:43:15 leaving [ ] the same as before 21:43:31 preferably using bignum cells, but it doesn't really matter 21:43:50 you can zero cells with [+] and nonzero them with [+]+ so you can simulate a binary tape 21:43:55 it's the < and > I'm less sure about 21:44:02 (tape infinite both ways, obviously) 21:47:28 [14:15] hmm, I take it Haskell doesn't have ignore in its standard library, on the basis that it's completely useless? 21:47:37 what is that supposed to do 21:48:05 ignore x y = y 21:48:16 i was asking ais523 21:48:21 (Just making shit up, ignore me ;) ) 21:48:32 although that would be const id 21:48:50 Does Haskell have a "computed NEXT FROM" monad? 21:49:12 ais523: ^ 21:53:04 ais523: in the Ndeql discussion above i had the idea that you might be able to use parity, this might apply to your derivative too 21:54:52 [>] seeks to the nearest zero cell either to the left or to the right 21:57:10 [++>] seeks to an even cell, although not necessarily the closest one 21:57:17 *a closest 21:57:41 :t flip const 21:57:43 forall b a. a -> b -> b 21:58:42 -!- ais523 has quit. 21:58:59 But "const id" is more right, as evidenced by 21:59:00 * oerjan swats ais523 in absentia -----### 21:59:01 @. pl djinn a -> b -> b 21:59:01 f = const id 21:59:24 i guess ais523 used ignore 22:01:58 @quote ddarius partial.application 22:01:58 ddarius says: (f x) is a partial application iff f x == (curry (uncurry f) x) 22:02:44 useful. 22:02:47 -!- TeruFSX_ has quit (Read error: Connection reset by peer). 22:04:01 -!- copumpkin has joined. 22:04:03 -!- TeruFSX has joined. 22:04:29 :t curry 22:04:31 forall a b c. ((a, b) -> c) -> a -> b -> c 22:09:17 oerjan: why did you stop playing nomic? <-- too much real life intervening, i think. 22:09:23 Gregor: ocaml has "ignore x = ()", though that may not be a useful combinator 22:09:52 if that's what he meant, then haskell _does_ have such a thing. 22:09:54 :t void 22:09:55 Not in scope: `void' 22:10:08 In a pure lazy language, it's stunningly pointless :) 22:10:11 ... lambdabot is getting _old_. 22:10:44 @djinn Not (Not (Either (Not a) a)) 22:10:44 f a = void (a (Left (\ b -> a (Right b)))) 22:10:52 Prelude Control.Monad> :t void 22:10:52 void :: Functor f => f a -> f () 22:10:55 this one. 22:11:01 @hoogle void 22:11:01 Foreign.Marshal.Error void :: IO a -> IO () 22:11:01 Control.Monad void :: Functor f => f a -> f () 22:11:01 package void 22:11:19 Oh, that void. 22:11:26 What about void :: Void -> a 22:11:40 Sure, at the level of /monads/ it makes sense. 22:11:42 that wouldn't be an ignore, would it? 22:11:51 oerjan: I agree that [>] will set the pointer to either the nearest nonzero cell to the right or to the left 22:12:00 but [++>] I'm not sure does what you say 22:12:21 Arc_Koen: i'm assuming only parity matters for the last one 22:12:24 at least not without embarrassing side effects 22:12:29 ohhhh ok 22:13:38 i'm not sure that helps much though 22:14:05 hmmm you can emulate finite-tape brainfuck easily 22:14:22 Arc_Koen: how so? 22:14:48 hum wait my brain is wrong 22:15:10 yeah no that doesn't work at all 22:15:17 and even if it did that would be only 2-cell brainfuck 22:15:50 I'm not gonna explain because it doesn't make any sense anyway 22:16:29 i'm still slightly miffed over ais523 leaving immediately after proposing it. 22:18:03 I think that's a nonnegligible danger about being interested in math or other sciences 22:18:24 when someone presents you with a problem late in the evening and YOU CANNOT SOLVE IT 22:18:38 and you know there is no way you're gonna sleep until you solve it 22:18:46 oh right, can ruin some sleep yeah 22:19:13 although in this case it's more like i'm stubbornly avoiding trying any more, because he left. 22:19:58 when I was younger I used to go to the same place near the beach every summer; at the harbour there was (among other tourist shops) a magician 22:20:22 he performed tricks and sold them 22:20:27 busking 22:20:40 most were easy to understand (not necessarily the precise trick, but at least the idea) 22:20:43 a fine anglamerican tradition 22:20:58 but there was one with a piped card deck that was just mind blowing 22:21:07 did you know theree is a busking forum? 22:21:17 with a whole subforum devoted to svengali pitch? 22:21:26 busking, right 22:21:43 except he was not showing his talent so much as his pre-made piped objects 22:22:10 so this numero lasted for about a minute or two 22:22:22 "piped"? 22:22:30 during which the piped card deck was laying inside its box, on the table 22:22:31 gaffed probably 22:22:41 ^oerjan 22:22:47 are you insinuating my vocabulary is not wide enough to tell that story? :( 22:23:07 it's nonstandard at least 22:23:10 please continue 22:24:00 yeah so the numero went on *without the magician touching the cards* 22:24:04 * oerjan swats quintopia for explaining with an equally obscure synonym -----### 22:24:15 (so basically he was just talking) 22:24:28 and he asked a member of the audience to think of a card 22:24:39 oerjan: gimmicked, then 22:24:50 OKAY 22:24:55 that card was the only face up one? 22:25:05 EXACTLY 22:25:07 or face down possibly 22:25:16 face down, actually 22:25:24 invisible deck then. 22:25:31 after the first time that I saw him perform this I couldn't sleep 22:25:37 I came back everyday 22:25:52 that was unfortunately one of the tricks he performed the least often 22:25:59 well 22:26:06 i'm sorry about your insomnia 22:26:16 after some time I decided to buy it 22:26:27 so i asked if he could perform it one last time 22:26:35 and while he did it I UNDERSTOOD 22:26:40 and it's ruined now. 22:26:55 the downside of magicianhood 22:27:03 you can no longer be a magical spectator 22:27:08 unless the magician is very very good 22:27:24 but invisible deck is an astounding trick 22:27:28 I mean, other tricks, you *know* that there is a trick, so I'm rarely dazzled or anything (though that didn't stop me from watching his show every year) 22:27:30 i have a brainwae deck myself 22:27:38 *brainwave 22:27:48 but in this he didn't so much as touch the cards 22:27:53 g2g 22:28:15 I've never heard of all the terms you're using 22:28:57 clearly the box was hollow and there was an assistant gnome hiding under the table. hth. 22:29:54 which is why he did it so rarely, couldn't afford the gnome all the time. 22:30:27 oh my you just understood the most mind blowing trick I've ever seen WITHOUT EVEN WATCHING IT 22:30:35 i did? :P 22:30:47 yup that's exactly how it worked 22:30:59 well except for the part involving a gnome 22:31:00 XD 22:32:00 my jokes: now omniscient too 22:32:41 omnijan 22:34:18 real food this time -> 22:34:22 (maybe) 22:35:40 -!- heroux has joined. 22:35:41 funny how that "delay" instruction is so rarely included in esolangs but so present in esoprogrammers 22:38:37 random things to do when bored: write a banana scheme program that returns true or false depending on whether the riemann hypothesis is correct or not 22:41:37 -!- Gregor has set topic: BEWARE THE ØRJANIST MØØSE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 22:41:52 Please read Chris Pressey's message http://esolangs.org/wiki/User_talk:Zzo38/FurryScript 22:42:12 I think this is a good idea. 22:43:02 What did you think is good idea? 22:43:59 to move furryscript to main namespace 22:44:13 Then write that on the talk page I linked to, please. 22:44:22 I think you have account, isn't it? 22:45:26 the only thing i was wondering is if it an esolang or not 22:45:29 wait, are we expecting Chris Pressey to take my opinion on that matter into account? You have no idea what good it does to my self-confidence! 22:45:32 *+is 22:45:57 yeah i prove his languages TC and he barely notices 22:46:03 Arc_Koen: I don't know, but if you write it there, it can be decided who does and who does not take your opinion on that matter into account. 22:46:18 oerjan: Yes that is too what I was wondering the same thing, which is why I replied as I did there. 22:47:26 oerjan: but you do that to everyone, maybe he'd notice if you stopped proving his languages tc! 22:47:32 What makes FurryScript furry anyway 22:47:44 All the fur. 22:47:45 Duh. 22:48:17 FreeFull: The name of the first file which was written with it, although recently I found some more mistakes in it that I fixed; the original had many more mistakes but I fixed most of them. 22:52:15 -!- Nisstyre-laptop has joined. 22:52:35 hey if we all go edit the page at the same time, are we gonna erase other people's edits? 22:52:59 Arc_Koen: I don't think so; I think MediaWiki has stuff in it to prevent that from happening. 22:53:10 or is mediawiki gonna do something like warning us "beware, that page has already been edited since you clicked the edit link" 22:53:40 yeah, I think I've heard that from somewhere (something about concurrent programming) but I have no idea how it can work 22:54:23 I mean, if I make a minimal edit on one part of a page and someone makes a minimal edit on another part of that page, I could understand how both edits are "compatible" but otherwise... 22:54:58 It will warn you. 22:55:24 Arc_Koen: it _does_ try to split into compatible edits, but it will simply warn you otherwise, and you have to merge them manually. 22:56:20 which can be a pain. 22:56:22 so for instance if two people add truth-machine implementations on the truth-machine page, there will be no warning? 22:57:10 as long as they are in separate sections, i don't think so. at least it works that way for undoing stuff. 22:57:36 oh, you can revert an old edit without reverting more recent edits? nice 22:57:47 yep 22:58:12 i recall experiencing that if two people make the exact same edit, neither will get a warning. 22:58:47 Who will it show up as? 22:58:47 although only the first to save is credited. 22:58:55 I see 23:04:32 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 23:06:20 -!- Frooxius has quit (Ping timeout: 246 seconds). 23:17:03 -!- fungot has quit (Ping timeout: 245 seconds). 23:19:23 that has happened to me with git commits as well 23:20:11 a coworker and i both make the exact same change, they push to master, i rebase onto master 23:20:23 instead of showing a merge conflict, git just drops my commit 23:20:41 because it has the same git-patch-id as one of the commits it's rebasing past 23:27:30 Is rebase a history mutating thing? 23:27:47 Erm, well, I guess everything is, but isn't there something that tampers with history beyond just adding new stuff at the end 23:28:11 -!- monqy has joined. 23:28:23 * Sgeo mutates monkey 23:28:25 monqy 23:28:41 Is there some way to make up the "computed NEXT FROM" monad in Haskell? 23:30:59 zzo38: my guess is "yes" 23:31:13 Do you even know how? 23:31:22 well, except what's NEXT FROM 23:31:43 It is something in CLC-INTERCAL, like COME FROM but you can return to where it came from 23:32:13 If it's a control flow concept, the Cont monad exists, and out of that you can build many control structures. 23:32:41 I did think of that, if it is something with continuation monad 23:34:33 hm... 23:36:13 if you have something like do { label 1 (...); x <- someStatement; nextFrom (someThingEvaluatingTo1) (someStatement) } then a problem would seem to be that you cannot get a value for x if you skip over the action setting it... 23:37:07 so i think you'd have to restrict it to a list of resultless actions 23:37:24 same problem with just COME FROM and GOTO, of course 23:38:06 I know that if it is a Kleisli morphism it has that problem, so it would have to be a not Kleisli morphism, if you would otherwise to need like that 23:38:28 i don't know what that is anyway 23:40:04 but i think you could make something that worked with a structure like runLabels [ Label 1 (...), Unlabeled (...), NextFrom (someThingEvaluatingTo1) (...), ... ] 23:40:55 so that runLabels can parse the general position of everything before starting running subactions 23:42:33 GOTO backward may work though even with the "getCC" and stuff I have, where the function runCC = runCT <*> id; can do a goto backward to the getCC 23:43:05 well yes, backward jumps don't have that problem 23:45:25 runLabels wouldn't even need a different monad, i think. it's just a control structure that can be used in any monad. 23:45:31 To do forward, either you would have some kind of fake result to check and then to go back, or to make it something other than Kleisli morphisms, such as haivng nextFrom :: Label -> m x -> m x 23:46:52 -!- Phantom_Hoover has joined. 23:47:14 Or like nextFrom :: Label -> M x -> M x -> M x you need both monads arguments I think 23:49:26 Or maybe you want to be able to compute the label inside the monad too 23:49:54 well of course, otherwise it's not much of a computed NEXT FROM 23:50:19 Well yes 23:50:47 on the other hand you don't want the label computation to be able to mutate values 23:50:53 just read them 23:51:08 Yes, although depending on the monad it may make possible that any value it changes is not changed. 23:53:09 Or maybe you want: nextFrom :: M Label -> M () -> M x -> M x; 23:58:56 the yafgc comic seems to have got a real schedule slip 23:59:38 Sgeo: the short answer is "yes, rebase mutates history" but to actually understand what that means you have to understand a few things about git 2012-10-09: 00:00:33 git commits are immutable objects; they are named by their SHA1 hash so there is no way to mutate one unless you find a SHA1 collision ;) 00:01:21 each commit refers to its parent(s) also by hash, so in that sense, history is completely immutable 00:01:51 but you can always take some sequence of commits, and construct a new sequence of commits which does something similar but different 00:01:56 I think "rewrites history" is more accurate than "mutates history". 00:02:48 and then you can switch your branch to use the new history rather than the old one 00:03:17 because a branch is not an immutable object, it's a named pointer into the database of immutable objects 00:03:59 a branch is literally just a text file in .git/refs/heads with a hex SHA1 hash in it 00:04:06 that is also why branches are so cheap to create 00:05:15 For example getCC/runCC can be like: runReaderT (runContT (do { liftIO $ putStrLn "Hello!"; la <- getCC; v <- liftIO $ getLine; n <- ContT (\f -> ReaderT $ \q -> runReaderT (f $ succ q) (succ q)); liftIO $ putStrLn (v ++ ":" ++ show n); when (v /= "" && n < 10) $ runCC la; }) return) 0 00:05:29 getCC = callCC (return . fix)? 00:05:40 shachaf: No. getCC = callCC (return . CT); 00:05:51 What's CT? 00:05:52 (Where CT is just a newtype wrapper) 00:06:39 runCC = runCT <*> id; (where runCT is the field of that newtype wrapper, and CT is the constructor) 00:06:53 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:07:17 Sgeo: so rebase takes my local commits, and creates a new sequence of commits as though I had applied those patches to the current upstream, and then sets my local branch to point at the new history 00:07:24 (in this case. rebase can do many other things as well) 00:07:32 rebase -i is awesome. 00:07:36 yeah 00:08:09 with rebase -i and add -p, you can really make your history look nice 00:08:39 I suppose it is even possible for the result type of a continuation monad to be another continuation monad, or if you use the proper newtype wrappers, even the same one, inside of some other monad or something like that too, even 00:08:43 imo the point of version control history is to tell a logical story about how the code got from point A to point B 00:08:58 I,I git historectomy 00:09:14 -_- 00:09:37 I and I 00:10:21 * shachaf is at SEA. 00:10:30 how's that working out for you 00:10:38 Better than last time. 00:10:55 I got randomly selected to have my laptop checked, though. 00:11:04 what did they do? 00:11:04 Fortunately they only checked the outside. 00:11:14 were you flying into the US from another country? 00:11:16 Rubbed something over it and put it in a machine, I think. 00:11:26 I'm flying SEA->SFO 00:11:54 ah 00:22:18 -!- zzo38 has quit (Remote host closed the connection). 00:26:38 oerjan: that wasn't a typo! that was me not speaking english 00:26:52 i guessed. 00:31:14 funny thing: my other recent edit was on the total BF talk page and included "whereas it will have been replaced by a 0" where I guess a "with" could (should?) be substituted for the "by" 00:32:03 dcStupidTheta :: ThetaType,-- The context of the data type declaration 00:32:48 i think both are allowed there 00:33:56 Arc_Koen: the term is "For what it's worth" hth 00:34:09 what did I say 00:34:13 "worse" 00:34:24 oh crap 00:34:32 that was completely unintended 00:34:42 "For what I'm worth" would have been intended 00:34:43 freudian slippery slope 00:35:13 ...but would still have been unidiomatic. 00:35:46 oh, not-logged-in users cannot check the fancy little 'm' box 00:36:05 indeed. 00:37:16 hey is there an easy way to have non-printable characters printed to the console? 00:37:45 the cat program I wrote works almost correctly in my interpreter 00:38:17 i don't use consoles much 00:38:38 what do you program in 00:38:50 uh, wait, console might not be the english term 00:38:55 the shell 00:38:56 gvim and winghci, mostly 00:39:30 although i do use it for my shell account where i've got my web page 00:39:34 (and mail) 00:40:13 terminal window is the usual term, i think. i thought you meant like "linux console", which elliott has been asking about a lot recently 00:40:26 and which i haven't used for years. 00:41:23 well it the same thing as a linux console, isn't? 00:41:23 Arc_Koen: perl -e "print (chr 7);" would be one way? :P 00:41:36 except that I'm not using linux 00:41:40 kmc: Did you ever get your Stripe CTF 2.0 shirt? 00:42:00 i thought linux console referred to what you have if you're using linux but not running a GUI 00:42:12 oerjan: well humI meant I'd like to know whether my program doesn't print some garbage 00:42:13 http://pastebin.com/cLx669wc 00:42:15 maybe i've misunderstood 00:42:40 here you can see it seems to be working correctly except for that question mark that appears 00:42:50 ah so you want to _check_ for non-printable characters 00:42:54 and which usually means I've printed a character the terminal window doesn't recognise 00:42:56 yes 00:43:13 of course I could just modify the interpreter to print numerci values instead of characters 00:43:41 Arc_Koen: i think piping into hexdump is useful for that 00:44:54 not that i've used it before, or understand the format, but it should tell exactly what the output was 00:45:31 echo 'a' > hexdump 00:45:36 that does... nothing 00:45:41 `echo 'a' > hexdump 00:45:47 |, not > 00:45:50 ​'a' > hexdump 00:45:55 you just made a hexdump file :P 00:46:21 well it said hexdump 'A' 00:46:21 hexdump: A: No such file or directory 00:46:21 hexdump: A: Bad file descriptor 00:46:31 echo 'a' | hexdump 00:47:39 echo 'a' | hexdump -C might be better, it prints the printable ones readably too 00:48:48 00000000 63 65 63 69 20 65 73 74 20 75 6e 20 74 65 73 74 |ceci est un test| 00:48:49 00000010 0a ff |..| 00:48:49 00000012 00:48:50 and the rest as .'s, it seems 00:49:11 `echo 'a' | hexdump 00:49:15 ​'a' | hexdump 00:49:15 Arc_Koen: ok so you have a stray ff at the end 00:49:27 the 0a is just a newline 00:49:56 `run echo 'a' | hexdump 00:49:59 0000000 0a61 \ 0000002 00:50:07 oh right 00:50:18 that was weird... 00:50:31 well the program does contain the value 255 as a marker 00:50:37 oh wait no, that was without -C 00:50:37 (because of the ever-growing thing in sceql) 00:50:45 Arc_Koen: yeah, but it got printed at the end 00:50:50 echo 'ceci est un test' | hexdump -C 00:50:51 00000000 63 65 63 69 20 65 73 74 20 75 6e 20 74 65 73 74 |ceci est un test| 00:50:51 00000010 0a |.| 00:50:51 00000011 00:50:56 yes that's not supposed to happen 00:51:16 besides, the number of outputs in the sceql program is exactly one less that the number of inputs 00:51:26 which seemed logical since the last input was end of file 00:52:30 but if the 255 is printed as well, there should be as many outputs as inputs 00:52:40 -!- Jafet has quit (Quit: Leaving.). 00:52:51 huh 00:53:40 -&=\&*_\-=_/-=/ 00:53:54 as you can see, one * inside the loop, one & inside the loop, and one & outside the loop 00:53:59 so one more & 00:54:26 and it doesn't seem to be the interpreter's fault since other programs work fine 00:57:04 have you checked other programs with hexdump? 01:01:54 simple hello world program:00000000 48 65 6c 6c 6f 2c 20 77 6f 72 6c 64 21 0a |Hello, world!.| 01:01:55 0000000e 01:02:11 Arc_Koen: oh hm, shouldn't you have *& rather than &* 01:02:26 I think not but I'll think about it 01:02:41 the first character read will never be printed 01:02:44 the idea is that input enqueue the input at the back of the queue (cause it's a queue) 01:02:45 oh wait 01:02:52 right 01:03:05 while output has the side effect of going to the next element 01:03:16 hum, wait 01:03:45 right, so 01:03:50 we have 255 as a marker 01:04:06 and the program basically does "enqueue the next input just after the marker" 01:04:29 so at the beginning of a loop, the marker is at the end and the previous input (which hasn't been printed yet) is at the front 01:04:44 if you output it, it will go after the marker and you don't want that 01:04:56 so first you input the next char, then only you output 01:05:22 [prev ... 255] INPUT OUTPUT [... 255 curr prev] 01:05:56 then you have a loop that will go through the '...' which are all the older inputs 01:05:57 -!- Jafet has joined. 01:06:23 the loop says "while the front byte is not 255, go to next" 01:06:53 INC BEGIN while not 255 DEC NEXT INC END DEC 01:06:56 i think the program should work... 01:07:20 that's what I thought too, but apparently the 255 is outputted 01:07:39 well then there must be something wrong with the interpreter. 01:07:41 ok i'll try it with the interpreter linked below 01:08:28 `run echo {}[] | iconv -f iso646-fi 01:08:31 iconv: illegal input sequence at position 0 01:09:06 haha, very funny 01:09:09 ./sceql_ref '-&=\&*_\-=_/-=/' 01:09:09 Unable to open file 01:09:14 `run echo {}[] 01:09:17 ​{}[] 01:09:52 it takes a file, not a program string. 01:09:58 yes I know 01:10:04 that's why it was funny 01:10:12 okay 01:10:28 so command > name just creates a new file? 01:10:41 yes, with the output of command 01:10:53 I was about to try echo '-&=\&*_\-=_/-=/' > ./sceql_ref 01:11:00 it will also happily overwrite an old one 01:11:13 oops :) 01:11:37 DON'T DO THAT 01:12:25 echo 'this is a test' | ./sceql_ref cat.ttt 01:12:25 this is a test 01:12:33 oh I forgot the hexdump 01:12:40 but no question mark, so I guess it works fine 01:12:44 gggggh 01:12:56 mayhaps 01:13:10 yet, it works fine :( 01:13:19 so there is something wrong with the damn interpreter 01:13:28 sad trombone 01:14:44 I was so proud that it was shorter than the reference interpreter and yet accepted both single-char command and plain text 01:15:12 like, you could have a program "INC _ iozguqn INC" and it would still perform three increments 01:16:48 ok I'll try the same program but with 254 as a marker instead 01:17:03 and if it doesn't work I'LL TRY 253 01:18:22 ./sceql_ref cat2.txtsceql 01:18:22 Program contains no instructions 01:18:28 right. 01:19:21 -!- Nisstyre-laptop has quit (Quit: Leaving). 01:22:16 oooook 01:22:22 so with 254 as a marker 01:22:28 it still prints an extra 255 01:23:43 :þ 01:24:39 fancee 01:25:15 so here's my resolution: at 3:30 in the morning I will NOT debug a sceql interpreter in C 01:26:33 is it 3:30 in the morning for you 01:26:44 well 3:26 01:26:56 wait does that mean I have four minutes to debug it 01:27:05 yes 01:27:07 that's a little short 01:27:12 3:27 now 01:27:17 a real rockstar ninja hacker could do it 01:27:26 sic transit gloria resolutionum 01:27:27 just chug some redbull and bro out to some killer kodez 01:30:05 And so you code 01:31:44 well my time is up gnight 01:32:22 fyi the parser doesn't seem to be the problem 01:32:25 * Sgeo vaguely wonders what sceql is 01:32:47 * oerjan vaguely suggests searching the wiki 01:32:55 `man sceql 01:32:59 man: can't open the manpath configuration file /etc/manpath.config 01:33:27 -!- SimonRC has quit (Ping timeout: 260 seconds). 01:33:27 basically you have a queue and you can push stuff to it 01:33:28 the people have spoken: sceql has awful documentation. 01:33:52 Hmm, maybe that would give me some good Clojure practice 01:34:06 yes I'm sure you'll find closure by programming in sceql 01:34:15 Although elliott once said that he would not use interpreters written in Clojure, and that scared me off from Clojure for a long time 01:35:44 oh hey btw if someone would be so kind as to tell me whether this is good programming style or not: http://pastebin.com/5dmVMpcq 01:36:05 appart from the fact that there are no comments 01:37:00 there are two functions : the function instruction returns the instruction pointed to by the array index (with the side effect of modifying the index if the instruction was not just one char) 01:37:32 and the function parser which takes a sceql program and overwrites it with a parsed sceql program 01:40:16 -!- SimonRC has joined. 01:40:59 and I don't know the functon instruction looks slightly like a hack 01:41:12 Clojure seems like it would be... overkill, somehow 01:42:16 anyway gnight 01:42:19 Night Arc 01:42:37 (only fifteen minutes between the first and second gnights, not bad) 01:42:46 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 01:48:02 heh Arc_Koen's quit message is something I said here recently 01:48:17 I'm not a fan of instruction(). 01:49:19 -!- TeruFSX has quit (Ping timeout: 260 seconds). 01:49:25 shouldn't that use some kind of string comparison instead of all that character/pointer stuff 01:50:25 I'd think so. 01:52:04 memcmp looks useable 01:57:19 @tell Arc_Koen you might want to use something like if (*i + 3 < l && !memcmp(&(p[*i+1]), "EXT", 3) { for that 01:57:19 Consider it noted. 01:59:07 -!- FreeFull has quit (Ping timeout: 240 seconds). 01:59:17 i guess that's the same as p + *i + 1, and that p and *i could be combined somehow, but i'm not a C style expert. 01:59:21 -!- FreeFull has joined. 01:59:57 can pointers be compared usefully with < ? 02:00:59 oh hm there's that undefined behavior if you go too far outside the allocated memory. 02:03:29 -!- MoALTz has quit (Ping timeout: 256 seconds). 02:21:28 -!- FreeFull has quit (Ping timeout: 260 seconds). 02:21:48 -!- FreeFull has joined. 02:35:29 -!- zzo38 has joined. 02:59:02 monqy, tswett arpdoop 03:11:55 yeah, C guarantees that a pointer one past the end of an array is a valid value, for use in comparisons like this 03:12:21 but more than one past the end is probably UB 03:12:47 of course you're not allowed to dereference that pointer to one past the end of the array 03:17:44 -!- Nisstyre-laptop has joined. 03:21:43 -!- copumpkin has quit (Ping timeout: 244 seconds). 03:22:19 -!- copumpkin has joined. 03:24:22 -!- oerjan has quit (Quit: Lost terminal). 03:38:35 -!- oerjan has joined. 03:55:32 2^32 channels and nothing on... 03:56:13 -!- Jafet has quit (Quit: Leaving.). 04:02:55 -!- mig22 has joined. 04:24:36 -!- Jafet has joined. 04:45:56 -!- oerjan has quit (Quit: Good night). 05:29:35 -!- aloril_ has quit (Ping timeout: 260 seconds). 05:42:19 -!- aloril_ has joined. 05:46:08 oh, that reminds me of a funny bug I found... some function was taking a buffer pointer and length, but in a context where it was "known" it wouldn't overflow it was being used with INT_MAX as the buffer length 05:47:07 leading to some funny effects when the buffer address had ... certain values 06:05:05 -!- Nisstyre-laptop has quit (Quit: Leaving). 06:06:07 how's that 06:08:57 I haven't seen the thing in question, but I would guesstimate it had something to do with buf+len < buf (or a test of p < buf+len with p in the buffer falsely failing) with len of INT_MAX and buf too high up. 06:09:23 yeah, somewhere in the function there was some "safety" check to see that the pointer was still inside the buffer 06:22:56 -!- TheJimmyJames has joined. 06:37:00 -!- sirdancealot7 has quit (Ping timeout: 252 seconds). 06:44:58 -!- sirdancealot7 has joined. 06:47:42 -!- ogrom has joined. 07:00:23 -!- epicmonkey has joined. 07:06:01 -!- monqy has quit (Quit: hello). 07:17:59 -!- sirdancealot7 has quit (Ping timeout: 256 seconds). 07:20:19 -!- epicmonkey has quit (Ping timeout: 246 seconds). 07:20:35 -!- sirdancealot7 has joined. 07:24:10 -!- donmarquis has joined. 07:27:27 -!- FreeFull has quit. 07:30:24 -!- sirdancealot7 has quit (Ping timeout: 260 seconds). 07:41:50 -!- Jafet has quit (Quit: Leaving.). 07:43:27 -!- sirdancealot has joined. 07:49:56 -!- ogrom has quit (Quit: Left). 07:56:22 -!- TheJimmyJames has quit (Read error: Connection reset by peer). 07:58:48 -!- TheJimmyJames has joined. 07:59:00 -!- TheJimmyJames has quit (Client Quit). 08:18:34 -!- Jafet has joined. 08:20:15 -!- zzo38 has quit (Remote host closed the connection). 08:31:45 -!- epicmonkey has joined. 08:44:03 -!- jiella has joined. 09:49:40 -!- Phantom_Hoover has joined. 09:51:30 -!- kinoSi0 has quit (Read error: Connection reset by peer). 09:51:58 -!- kinoSi has joined. 09:58:35 -!- MoALTz has joined. 09:59:47 -!- Jafet has quit (Quit: Leaving.). 10:08:19 -!- Lumpio- has quit (Ping timeout: 246 seconds). 10:46:39 -!- Arc_Koen has joined. 10:46:51 hello 10:46:51 Arc_Koen: You have 1 new message. '/msg lambdabot @messages' to read it. 10:46:56 @messages 10:46:57 oerjan said 8h 49m 38s ago: you might want to use something like if (*i + 3 < l && !memcmp(&(p[*i+1]), "EXT", 3) { for that 10:54:40 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 10:56:43 -!- Lumpio- has joined. 10:57:09 -!- donmarquis has quit (Ping timeout: 276 seconds). 11:09:07 -!- barts has joined. 11:10:58 -!- epicmonkey has quit (Ping timeout: 246 seconds). 11:12:07 -!- barts_ has quit (Ping timeout: 245 seconds). 11:13:17 -!- Jafet has joined. 11:22:08 -!- epicmonkey has joined. 11:46:08 -!- atriq has joined. 11:46:13 @messages? 11:46:13 Sorry, no messages today. 11:46:43 Can anyone recommend a C++ tutorial for someone coming from Haskell with the aim of using the Unreal Development Kit? 11:48:13 @ping 11:48:13 pong 11:49:23 @pong 11:49:24 pong 11:50:27 -!- epicmonkey has quit (Ping timeout: 276 seconds). 11:54:12 -!- atriq has quit (Ping timeout: 245 seconds). 12:05:31 -!- epicmonkey has joined. 12:08:55 -!- atriq has joined. 12:08:59 -!- elliott has joined. 12:13:35 elliott, Unreal Development Kit. Haskell. How much point is there trying to get both at once if I have a reason to use the former? 12:13:57 atriq: "get" both? 12:14:06 Use the UDK in Haskell 12:14:35 that sounds difficult 12:15:24 Yes. 12:16:03 To do it, I'd need to use Haskell's FFI to do C code which does C++ code which does the UDK 12:16:25 i wouldn't bother 12:16:30 sounds like a full-time project to get them talking raelly 12:16:32 *really 12:16:39 i wouldn't use udk in the first place tho 12:16:52 I have a reason to that is out of my control 12:17:03 what is the reason 12:17:27 One of my friends is making a team for a competition organised by Epic Games 12:17:57 surely using haskell is banned somehow 12:18:06 Nah, you just need to use the UDK 12:18:38 And now I will leave to look for clothes. 12:18:41 Goodbye. 12:18:42 -!- atriq has quit (Quit: Leaving). 12:18:54 RIP TANEB 12:21:55 hey, if I design an esolang and it turns out to be very very similar to something that already exist, what do I do? 12:22:13 I create a page nonetheless (with reference to the other in a "see also" section), or not? 12:22:46 you can create it if you want to 12:22:59 you don't even have to mention the similarity if you don't want to, although someone else might notice and add it 12:23:15 whether it's worth adding despite the similarities is up to you 12:23:36 we have languages that are identical to others with only minor syntactic changes, after all, although they're not very well-liked (brainfuck equivalents) 12:26:16 yes it happens to be a brainfuck derivative :( I thought about it yesterday, and of course something similar already exists (I think all brainfuck derivatives already exist) and I'm thinking it feels counterproductive to make pages for all brainfuck derivatives I can think of, because everyone can think of them 12:26:33 (I would probably not have asked if it was not a brainfuck derivative) 12:28:41 well, brainfuck derivative =/= brainfuck equivalent 12:28:53 but it's hard to say more without knowing more about your language, really 12:29:16 well the idea is that the code is contained in the data tape 12:29:34 the tape is finite (initially as long as the program itself) 12:29:50 there are two pointers, both initially pointing to the same cell (the instruction pointer and the data pointer) 12:30:10 the tape is circular, and there is an instruction to create a new cell (so that memory isn't bounded) 12:30:25 that seems a lot more interesting than other BF derivatives 12:30:27 what is the similar language? 12:30:27 of course "self-modifying brainfuck" already exists 12:30:49 though it doesn't have a finite tape 12:31:28 it sounds different enough 12:31:33 not like there's limited space on the wiki, anyway 12:31:45 ok, I'll create a page then 12:31:47 thank you 12:32:12 I've written a pretty detailed description, but I have no name 12:41:50 -!- augur has quit (Remote host closed the connection). 12:46:30 circlefuck 12:47:04 thank you 12:47:07 yw 12:48:40 Qq q q q qqq qq Qq q q qqq 12:49:34 od name too 12:49:41 *good name too 12:50:22 "These images are epic, it's like Reddit, only on github!" -- actual github comment 12:51:40 sounds like twitter, only on livejournal 12:54:55 -!- DAZ44 has joined. 12:55:24 -!- DAZ44 has left. 12:56:29 -!- DAZ44 has joined. 12:56:32 -!- DAZ44 has left. 12:58:12 `run echo "@tell DAZ44 $(welcome DAZ44)" 12:58:24 ​@tell DAZ44 DAZ44: 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.) 12:59:37 oh, that thing still 12:59:38 pfft 13:12:52 -!- augur has joined. 13:13:52 -!- augur has quit (Read error: Connection reset by peer). 13:14:16 -!- augur has joined. 13:16:24 -!- Phantom_Hoover has joined. 13:21:12 -!- ais523 has joined. 13:30:48 -!- boily has joined. 13:44:46 -!- Nisstyre has joined. 13:46:08 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:51:57 -!- Guest86966 has joined. 13:52:34 -!- trout has quit (Ping timeout: 244 seconds). 14:03:31 -!- epicmonkey has quit (Ping timeout: 246 seconds). 14:08:25 -!- copumpkin has joined. 14:16:24 -!- epicmonkey has joined. 14:20:00 -!- atriq has joined. 14:22:49 hurmpf I almost did it again 14:23:06 @masseges? 14:23:06 Sorry, no messages today. 14:23:17 really, I can't write "followed with"? 14:23:58 I think it's "followed by"? 14:31:23 -!- Nisstyre has quit (Ping timeout: 260 seconds). 14:32:37 What's the context? 14:43:08 uh well in both cases it was a character in a string, followed by another character 14:43:10 or something 14:43:33 and well I naturally write "followed with" but apparently I should write "followed by" 14:43:45 I don't know, "followed with" sounded like english 14:45:13 English is a ridiculous language 14:45:30 -!- Nisstyre has joined. 14:45:36 So true. 14:45:39 It's Vikings who spoke French trying to talk to Germans in Latin 14:45:55 -!- jiella has quit (Quit: Leaving.). 14:46:00 (actually almost true) 14:47:02 While I could talk for about 5 minutes about the history of the English language, I'm not going to. 14:49:31 that language have existed for centuries or millenia, and you can only talk about its history for five minutes?! 14:49:37 you must talk really fast 14:52:13 fsvo millenia 14:53:50 -!- mig22 has quit (Quit: mig22). 15:07:14 -!- Slereah has quit (Ping timeout: 240 seconds). 15:07:33 -!- Slereah has joined. 15:07:41 i spoke english before it was cool 15:10:53 kmc: do you know anything about ancient versions of borland turbo c++ 15:11:37 -!- ais523 has quit (Ping timeout: 246 seconds). 15:12:30 kmc: this is a non-philosophical question 15:14:29 no 15:14:37 but i did use openwatcom c yesterday 15:17:39 kmc: wow 15:17:39 kmc: why 15:17:50 to compile a dos program 15:18:23 my friend wrote a program for AVR that blinks some LEDs in patterns to induce hallucinations 15:18:31 and i decided to convert it to a DOS program that blinks the screen 15:18:34 for no particular reason 15:19:13 does it work 15:19:33 kinda 15:19:49 i also used openwatcom c for http://mainisusuallyafunction.blogspot.com/2010/10/programming-jvf-2010.html 15:20:39 define kinda 15:20:43 did you only sort of hallucinate 15:20:46 yeah 15:20:49 -!- ais523 has joined. 15:20:57 it doesn't really work unless it fills the entire visual field 15:21:16 it produces standing waves in the primary visual cortex 15:21:25 which sounds like star trek but there are actual neuroscience papers about this 15:21:32 (my friend is a co-author on one of them) 15:22:23 oh, how naive i was back when i wrote this 15:22:25 i thought "public domain" 15:22:29 was a thing 15:22:53 public static void doMain() 15:23:03 gaah 15:25:55 -!- elliott has quit (Ping timeout: 246 seconds). 15:26:18 it's funny to read old code and pick apart my old style 15:26:56 it's only indented two spaces 15:27:24 and i thought "while (foo) { }" is more readable than "while (foo);" 15:27:26 i am not sure now 15:28:50 -!- elliott has joined. 15:29:45 kmc: Don't you hate it when you get disconnected from IRC and your replies to things get dropped and also you miss other things other pepole say?? 15:29:50 yeah 15:29:53 clearly should make unrelaible internet connections illegal 15:30:04 that's why i run irssi on ec2 and connect to it with mosh 15:30:18 kmc: You need an endorsement line on that advertisement. 15:30:29 i'm keegan and i approved this message 15:30:34 ANYWAY kmc: i like the comments on that entry 15:30:46 I would use irssi except I hate irssi's interface. 15:33:50 -!- MoALTz has quit (Ping timeout: 244 seconds). 15:35:42 I don't know of any good IRC clients. 15:36:00 elliott: what about @ 15:37:42 -!- atriq has quit (Read error: Operation timed out). 15:38:14 -!- atriq has joined. 15:43:40 aha, http://www.ousob.com/ng/borcpp/ng365.php 15:45:59 oh crap, forgot lunch 15:59:36 -!- MoALTz has joined. 16:11:01 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 16:13:36 The new bitbucket look… 16:13:38 is Facebook 16:13:40 X_X 16:13:52 This is sad. 16:16:51 doesn't look anything like facebook 16:17:24 Mmm hmm. 16:18:45 well they're both blue 16:22:24 Top blue bar with logo on the left, search and account dropdowns, user pages are timelines, project pages (now like “Pages” on Facebook) expect your project to have a face—err, logo—placed exactly where Facebook puts it. 16:26:33 -!- Phantom_Hoover has joined. 16:32:12 -!- FreeFull has joined. 16:32:40 Why... 16:32:49 Why am I looking at the Tumblr tag for Haskell? 16:33:14 Huh, when did the bitbucket redesing thing happen? 16:33:17 Must've been very recent 16:34:27 -!- zzo38 has joined. 16:35:38 -!- ais523_ has joined. 16:35:44 -!- ais523 has quit (Disconnected by services). 16:35:46 -!- ais523_ has changed nick to ais523. 16:36:20 FireFly: Today. 16:36:28 FireFly: Opinions? 16:39:22 The whole "pretend to be Facebook" thing seems a bit silly, what with the colour scheme and whatnot 16:39:57 -!- AnotherTest has joined. 16:40:02 Hello 16:40:29 Hey 16:40:50 Though on the brighter side of things, I do like the icons for various actions in the newsfeed 16:41:41 Yeah, there are lots of little improvements that help things, I overall prefer the new UI. 16:41:57 It's just that if I recommended Bitbucket to a friend right now, I'm 100% certain that they'd ask me why it's trying to be Facebook. 16:42:39 Indeed 16:43:28 -!- epicmonkey has quit (Ping timeout: 246 seconds). 16:46:10 > 0xbe440ff0 16:46:12 3192131568 16:46:40 Beaaoffo. 16:50:24 -!- Guest86966 has quit (Changing host). 16:50:24 -!- Guest86966 has joined. 16:51:08 -!- Guest86966 has changed nick to Guest86967. 16:51:33 -!- Guest86967 has changed nick to constant. 16:58:21 @ping 16:58:22 pong 16:59:53 -!- ogrom has joined. 17:38:06 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 17:47:52 -!- epicmonkey has joined. 17:51:24 -!- ais523 has quit. 17:51:36 -!- ais523 has joined. 17:54:37 -!- Phantom_Hoover has joined. 18:21:54 ok. who the hell manes their web browser browsex? 18:21:59 *names 18:24:14 -!- ais523 has quit (Read error: Connection reset by peer). 18:24:25 -!- ais523 has joined. 18:24:40 -!- AnotherTest has quit (Quit: Leaving.). 18:41:52 A really desperate person with a forehead fetish 18:43:39 harr harr, brow sex 18:44:46 A win32 programmer. 18:45:24 Too much RegisterClassEx and CreateWindowEx and such. 18:45:42 fed up with Browse? try BrowseEx! 18:45:58 (or BrowseExW if you want unicode support) 18:46:01 that's browseex, olsner 18:46:25 Or maybe they found the developer at ExpertsExchange. 18:46:54 elliott: oh, ok 18:47:16 Brows, named by someone *right* after calling creat. 18:53:38 expertsexchange? 18:54:20 lol 18:56:53 It used to be at expertsexchange.com, I believe. 18:57:01 They added a dash later. 18:58:13 damn 18:58:38 that would be awesome url 18:59:32 There's also Pen Island at penisland.net -- they sell pens. 18:59:47 That was deliberate, I'm sure. 18:59:49 It's rather likely to be intentional, though. 18:59:51 Yes. 18:59:59 There's Who Represents 19:00:14 :P 19:00:18 I mean, the slogan for Pen Island is "Your Pen Is Our Business". 19:00:36 how many people looking for penisland will end up buying a pen after coming to pen island? 19:03:01 There's also the Holland's Hit Festival site at hollandshitfestival.nl. 19:03:31 Oh, and that Therapist Finder service. 19:04:00 is there a list? 19:04:02 hmm, Holland Hit Festival sounds like it would be better english, as well as a less unfortunate domain name 19:04:19 olsner: The site is all in Dutch anyway. 19:04:39 nortti: There are several articles. Probably someone has made a combined list too. 19:04:50 ok 19:05:00 "Worst domain names" is a good search keyword I'd guess. 19:10:32 They seem to tend to be titled "unintentionally bad", but many of them are probably not. 19:10:35 http://www.boredpanda.com/worst-domain-names/ has 30, that's long-ish. 19:10:47 Oh, I remember that Powergen Italia page from before, too. 19:11:06 oh, that one is actually funny 19:16:38 lol 19:23:03 -!- ogrom has quit (Quit: Left). 19:25:50 -!- ais523_ has joined. 19:25:57 -!- ais523 has quit. 19:28:09 -!- ais523_ has changed nick to ais523. 19:30:01 My Dungeons&Dragons character has now advanced one experience level up. 19:30:13 Hell yes. 19:32:37 zzo38: So now you're zz939? 19:32:45 s/9/o/ 19:33:24 shachaf: No, my Dungeons&Dragons character is actually named Iuckqlwviv Kjugobe and did not change his name. 19:33:42 Iuckqlwviv, nice name 19:34:24 I usually use the name Kjugobe, although the DM cannot pronounce either. 19:34:34 > sequence [map pred,map succ,rot13] "Iuckqlwviv Kjugobe" 19:34:36 ["Htbjpkvuhu\USJitfnad","Jvdlrmxwjw!Lkvhpcf","Vhpxdyjivi Xwhtbor"] 19:35:36 Vhpxdyjivi Xwhtbor sounds good 19:35:56 You know what else is a nice name? 19:35:59 The name comes from the following algorithm (I programmed it on my graphing calculator): Roll d6, 1=stop, 2,3=vowel (use d6), 4,5,6=consonant (use d20), and then repeat. 19:35:59 oerjan 19:36:07 olsner: You should /nick oerjan2 19:36:38 shachaf: I am not related to oerjan, so that would be confusing 19:36:55 olsner: You would be if you /nicked oerjan2! 19:36:57 ∎ 19:37:02 no, I would not 19:37:07 Yes you would. 19:37:13 would not 19:37:13 You'd be related by having almost the same nick. 19:37:24 I have 290833 experience points in total, by now. 19:37:34 -!- myndzi has joined. 19:37:36 > 290833 / 4159 19:37:37 69.92858860302958 19:37:39 Coïncidence? 19:37:40 Er. 19:37:48 > 290833 / 4951 19:37:48 ...what? 19:37:50 58.74227428802262 19:37:54 *There*. 19:37:56 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 19:37:57 ...what? 19:37:58 Coïncidence? 19:38:06 What are you trying to calculate? 19:38:15 Your XP/4951 19:38:19 Why? 19:38:28 Accounting for inflation. 19:38:42 what is the significance of 4951? 19:38:52 what does it mean? 19:38:54 There is no inflation involved. 19:38:58 Sure there is. 19:39:07 XP used to be worth much more way back when. 19:39:22 DMs just give it out indiscriminately these days. :-( 19:39:24 Are you trying to convert it to a different system? 19:41:19 assuming your xp starts at 1, I'd say the inflation-adjusted xp is always 1 19:41:20 Yes. 19:41:27 No, my XP starts at zero. 19:41:35 -!- ais523 has quit. 19:41:46 oh, ok, I don't know how to deal with zero 19:41:58 Do you know how to divide by zero? It is difficult, because dividing by zero is not allowed. 19:42:45 So you have to use limits and whatever, and to know when it is applicable and not applicable to the calculation. 19:42:48 Fascists. 19:42:58 zzo38: yeah, that stuff is tricky 19:42:59 zzo38: I know how to divide by infinitesimals. 19:43:05 Which is basically the same thing. 19:43:18 -!- myndzi has quit (Quit: .). 19:44:04 In Icosahedral RPG, 1XP is worth ten of D&D3.5e XP, I think. 19:44:23 How much is that in US dollars? 19:44:26 But D&D3.5e is older than Icosahedral RPG, so they aren't always worth more in the past. 19:44:27 -!- myndzi has joined. 19:44:55 fizzie: I don't know. In gold coins, 1XP (in D&D3.5e) = 5gp, so I don't know what you would convert gold coins to United States currency. 19:45:16 -!- myndzi has quit (Client Quit). 19:45:28 -!- FireFly has quit (Changing host). 19:45:28 -!- FireFly has joined. 19:45:28 -!- epicmonkey has quit (Ping timeout: 246 seconds). 19:45:50 How heavy is 1 gp? 19:45:56 1/50 pound 19:46:39 "5*(1/50 pounds) of gold" W|A €399.79 current commodity price. 19:47:02 But that seems like in euros? 19:47:06 -!- myndzi has joined. 19:47:12 Didn't you want it in US? 19:47:31 Well, close enough. Apparently it's $514.62. 19:47:44 W|A automatically selects currency units by geoip trickery, I believe. 19:48:31 It automatically selects many things by geoip trickery, I think. Will it use geoip to figure out the sunrise/sunset times, and to figure out the hour angle of the sun, and so on? 19:49:14 Does it even deal with hour angle directly, or do you need to convert it from right ascension? 19:49:39 -!- jix has quit (Ping timeout: 260 seconds). 19:49:40 I haven't tried to ask any astronomical questions about it. 19:50:05 But "sunrise" gives me today's sunrise in Espoo, Finland, which is the city I'm in, at least. 19:50:32 I know right ascension and declination works, although you cannot seem to specify J2000 and so on. In addition, it doesn't seem to work with ecliptic coordinates, except with the very limited query "astrological sign". 19:52:25 (You will get the ecliptic longitude of the sun, but only the sign and not the degrees within the sign; it doesn't seem very useful with such low precision (only 12 slices of the circle), and aren't W|A supposed to be scientific?) 19:55:12 I think it would make more sense to treat "astrological sign" as an angular unit rather than a query in itself (of course it could automatically expand "astrological sign" by itself into "ecliptic longitude of sun in astrological signs", which is what I think it ought to do). 19:58:54 O, and even if you do request astrological signs, it should tell you the degrees past the beginning of the sign, too. 20:00:00 Well, it's a perpetual work-in-progress, I suppose. Maybe some day it will. 20:00:53 Actually I think we should work together to make the FOSS version of a similar thing in Haskell. 20:01:21 Therefore it might start with not quite as good, but eventually becomes much better much quicker. 20:02:36 -!- oerjan has joined. 20:03:17 oerjan: Did you know that if you made a FOSS version of Wolfram|Alpha, but in Haskell, it would quickly be much better than that crippled thing Wolfram has. 20:03:38 hasn't someone been working on that for a while 20:03:39 obviously. 20:03:55 But not right away; it would take some time first, and then it would improve more quickly than Wolfram|Alpha improves. 20:03:57 i think someone made a version of mathematica, and then was hired by wolfram 20:04:10 i don't think it matters what language you use here 20:04:29 i think most of the value in W|A is in a billion hard-coded special rules for understanding various kinds of data 20:04:37 I don't mean it would quickly become better, I mean it would eventually improve much more quickly, so eventually it probably would be better, at least at some things, if not all. 20:04:46 your choice of programming language might make those rules a bit easier to write but it won't mean you magically don't need to write them 20:04:52 kmc: They "curate" it. That's a hip verb nowadays, or so I am to understand. 20:06:03 kmc: Well, yes, you would still need to write it, but with the Haskell it could be made if you have installed it you can enter English queries or you can use Haskell queries within GHCi, or a combination of both, yes you do need some rules for various kinds of data, default units, whatever else, etc 20:06:19 yeah everyone and their dog will be banging down your door to write queries in haskell 20:06:54 I asked Wolfram Alpha about Wolfram Alpha, but it just printed some rather banal statistics about wolframalpha.com; daily page views and index page size in KiB and a HTML element hierarchy graph. 20:08:46 kmc: Well, you would need to have GHC installed if you want to write the queries in Haskell codes, but anyone who uses it and does have may find it useful. 20:11:12 And yes I did think I read about it once someone was doing that in Haskell. 20:11:14 zzo38: afaict the basic problem is that to improve faster than WA there need to be enough people able and willing to write queries in haskell to overtake the actual paid Wolfram employees doing the same for WA. 20:11:57 but magical haskell magic will make them 1000x more efficient! 20:12:24 surely you're not suggesting that some problems are hard or tedious no matter what programming language you use 20:12:34 oerjan: Someone can certainly pay someone if they use the system within their own company, to make improvement, if anyone ever does do for payment. 20:12:51 kmc: h8r 20:12:54 But some things are hard, regardless of programming language, is the case, anyways. 20:13:05 sk8r 20:13:08 sh8chaf 20:13:16 how goes it shachaf 20:13:26 * shachaf is back in CA. 20:13:40 A shaChAf. 20:14:51 shalifornia 20:15:13 kmc: This is your last week of not being Old, by the way. 20:15:23 Use it well. 20:15:40 When does Old start? 20:16:11 Sunday. 20:17:34 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 20:19:18 `run echo "lambdabot: @tell elliott You can probably do it like this." 20:19:23 lambdabot: @tell elliott You can probably do it like this. 20:19:24 Consider it noted. 20:19:34 oerjan: hi oerjan 20:19:41 oerjan: You have a pretty good nick. 20:19:45 hi shachaf 20:19:50 why thank you 20:19:56 ørjan would be better. 20:20:06 But within the confines of IRC you can't do much better than oerjan. 20:20:31 œ 20:20:36 * shachaf should probably do résuméy things. :-( 20:20:40 That's terribly unpleasant. 20:21:02 also i've had the nick oerjan since 1992/1993 or so. 20:21:25 oerjan: That's just around the time I got the nick Shachaf! 20:23:30 or maybe even earlier, come to think of it. 20:23:45 Nobody ever calls me atriq. 20:23:48 1991? 20:23:50 That was a good year. 20:23:56 For a start I'd get mixed up with Patrick 20:24:15 ^rto13 patriq 20:24:23 ^rot13 patriq 20:24:29 !rot13 patriq 20:24:31 cngevd 20:24:34 i had the username eigil after my mud character initially, i don't remember exactly when i switched. 20:25:11 presumably when i started using the account for mail and/or usenet. 20:25:34 Hey. 20:25:43 fizzie: HEY YOURSELF 20:25:47 WHAT'S WITH FUNGOT 20:25:58 Yes, that was the "hey". 20:26:11 -!- fungot has joined. 20:26:15 ^rot13 patriq 20:26:15 cngevd 20:26:45 ^rot13 patrick 20:26:46 cngevpx 20:26:50 ^rot13 fungot 20:26:50 shatbg 20:26:55 -!- Phantom_Hoover has joined. 20:27:11 cnegvpx %rax; pshufd 20:27:16 !rot13 Phantom_Hoover 20:27:16 Cunagbz_Ubbire 20:27:41 pshufd? 20:27:53 Oh, that shuffles 16-bit values? 20:28:34 Do you know where to buy the fast ARMv2 chips? 20:29:49 (rather than the slow ones) 20:30:08 (O, and they should also be RoHS compliant, if that is possible.) 20:31:39 `run echo "lambdabot: @tell elliott You can probably do it like this." 20:31:40 elliott: You have 1 new message. '/msg lambdabot @messages' to read it. 20:31:40 clever 20:32:30 elliott: Just imagine oerjan told two bots to each tell two bots to @tell you something. 20:32:36 In the form of a small tree. 20:32:41 Then it would be a four-leaf clever! 20:33:31 pshufd shuffles 32-bit values. packed-shuffle d-oublewords. 20:33:41 Oh, right. 20:33:51 Because a "word" is 16 bits. 20:35:05 !c sizeof "word" 20:35:09 No output. 20:35:14 Yay! 20:35:44 -!- copumpkin has joined. 20:36:23 !c printf("%d", sizeof "word") 20:36:25 5 20:37:26 !c printf("hi") 20:37:29 hi 20:37:40 !c printf("@tell elliott oh no :'(") 20:37:43 ​@tell elliott oh no :'( 20:37:55 Womp womp, I win. 20:38:13 hi copumpkin 20:38:20 hi 20:38:22 How's Boston? 20:38:39 !c printf("\001ACTION tests\001") 20:38:41 ​.ACTION tests. 20:38:43 I think you need to put "lambdabot: " at front otherwise there will be zero-width space at front. 20:38:45 Someone tried to get me to get a job in NH the other day.q 20:38:55 "more boston than boston" 20:39:05 ("boston" means "cold") 20:39:20 ("boston" `means` "cold") 20:40:05 means(Boston,Cold). 20:40:47 boston isn't cold. when i was there it was about 30 degrees celsius. 20:41:03 shachaf: cold and grey 20:41:23 NH or Boston? 20:41:27 both 20:41:54 Oh, you went to university in NH, didn't you. 20:42:21 and hello 20:43:36 -!- jix has joined. 20:49:21 kmc: 'screen' doesn't support non-BMP codepoints. :-( 20:49:23 * shachaf is annoyed. 20:50:19 -!- hagb4rd has joined. 20:51:00 yeah :( 20:51:11 they are racist against ancient sumerians and elves and such 20:51:42 And mathematicians. 20:51:51 fuck mathematicians 20:52:24 kmc: Don't be racist. :-( 20:52:37 to please mathematicians you have to include codepoints for bold italic fraktur double-strike lower case greek 20:53:06 Huh? 20:53:20 Is asking for codepoints like "ℂ" too much? 20:53:27 unicode has a bunch of copies of the latin and greek alphabets with different font-ish attributes 20:53:30 (That one happens to be BMP.) 20:53:40 because while to normal people these are just font distinctions, to a mathematician they are semantically different characters 20:53:46 Bold and italic is silly, but double-struck isn't *that* silly. 20:53:59 and so they get different codepoints according to unicode's philosophical notion of what a character is 20:54:13 double-struck was invented as a way of writing bold on a blackboard 20:54:26 but now we have bold, double-strike, and bold double-strike 20:54:27 -!- Frooxius has joined. 20:54:39 ℋ 20:54:58 Hmm, there are some great letters here. 20:55:43 What would you have mathematicians do? Use *multi-character identifiers*? 20:56:08 nah i'm just on a rant 20:56:18 perhaps they could become more like programmers and accept multi-letter identifiers 20:57:02 -!- ais523 has joined. 20:57:57 -!- augur has quit (Remote host closed the connection). 20:58:36 I’d love that. 20:58:51 They already have sin, cos etc. 20:59:28 instead of bold double-struck comic sans inverse “s” and “c”. 21:00:06 Oh, man, we need COMIC SANS codepoints. 21:02:15 yes 21:02:44 http://www.ctan.org/tex-archive/macros/latex/contrib/comicsans 21:03:25 * Mathematics using Comic Sans wherever possible 21:03:59 -!- atriq has quit (Quit: Leaving). 21:05:18 The documentation .pdf is in Comic Sans. 21:05:33 I saw, yes. 21:05:44 Its example of math in comic sans brings a tear to my eye. 21:06:22 A tear of JOY? 21:06:43 I can't decide. 21:11:38 But I am printing that bit and posting it on my cubicle. 21:12:18 don't miss page 5 21:14:01 -!- monqy has joined. 21:21:25 * boily foolishly opens the PDF and attempts to read it... 21:22:00 monqy: do you like comic sans 21:22:24 SanDisk should make a music player called Comic Sansa. 21:22:48 yes 21:22:48 monqy: You have 26 new messages. '/msg lambdabot @messages' to read them. 21:22:59 elliott: 21:22:59 oh no :'( 21:23:08 monqy: what happened 21:23:19 it's going to get thread killed just watch 21:23:24 14:23:19 Plugin `tell' failed with: thread killed 21:23:33 elliott........................... 21:23:54 monqy: Are they all gone now? 21:24:14 yes, forever 21:28:28 Do you still have to download a .exe and extract the font from it using cabextract? 21:28:35 -!- augur has joined. 21:28:51 hey i owned a sansa something or other 21:28:56 it was shite until i installed rhythmbox 21:30:06 franz i am, i am franz, do you like comic sans 21:30:38 -!- nooga has joined. 21:30:56 i'm writing a C compiler in ruby 21:31:08 and you know what? it's quite pleasant 21:31:18 better than writing a ruby compiler in C 21:31:24 -!- boily has quit (Quit: Poulet!). 21:31:36 despite the fact that it's terribly wrong and lame 21:31:55 does your C compiler have a hip name and a nice looking website full of references to popular internet memes 21:31:55 Writing compilers in high-level languages makes perfect sense… 21:32:12 Gregor: you must be a terrible programmer with a small penis 21:32:13 ;) 21:32:26 i was looking for a good compiler targetting 65c816 21:32:37 which I could easily modify 21:32:56 and then i just grabbed this: https://github.com/oggy/cast , and started prototyping 21:33:00 why 65c816 21:33:07 to the point that it actually compiles something 21:33:27 because 21:33:56 http://integratedredstone.wikispaces.com/RedPower+Control 21:34:39 Why not just write Forth? 21:34:51 write forth and multiply 21:34:56 Why not just write Fythe? 21:35:00 Hurp hurp 21:35:36 wait, that's not an esolang? 21:35:36 Gregor: Sadly, RP doesn't ship with a Fythe interpreter. 21:36:24 oh it's Gregor's, and he even registered an .org domain 21:37:02 Is it Gregor.org? 21:37:20 "Hamdee Fythe, Real Estate Agent." 21:37:25 no, fythe.org 21:37:36 a pretty good name, that 21:38:05 (hamdee fythe) 21:39:01 * oerjan imagines him being the evil capitalist ruling hexham, montgomery burns style 21:44:32 forth is already there 21:44:44 i want C cross compiler 21:45:57 "Your program lacks a main function. What a stupid error." 21:46:16 although maybe that would be a cross linker 21:46:47 nah 21:46:52 heh 21:47:05 my compiler emits ACME assembly 21:47:18 and ACME does not produce linkable objects 21:47:26 so linking is... uh 21:47:28 firth of forth 21:47:33 on asm level 21:47:43 does it have a BEEP BEEP instruction 21:48:05 no, but it has "halt and catch fire" instruction 21:48:15 good, good 21:48:33 does it actually 21:48:35 catch fire 21:48:43 i think i've seen that 21:49:00 but since i currently work with the emulator emulator 21:49:13 oh, i heard you like emulators! 21:49:33 how ironic 21:50:23 c compiler written in ruby targets a virtual machine running on a virtual machine 21:51:26 Oh, I remember that Powergen Italia page from before, too. <-- XD 21:51:48 General Italia 21:51:50 nooga: It's like several dozen spoons when all you need is a butter knife. 21:52:04 shachaf: but it's fun 21:52:14 -!- kinoSi has quit (Read error: Connection reset by peer). 21:52:42 -!- kinoSi has joined. 21:54:08 -!- Jafet has quit (Quit: Leaving.). 21:57:21 and the spoons aren't even ironic 21:57:31 oerjan: Is the knife ironic? 21:57:47 nope, it's plastic 21:58:00 Wow. What a shame. 21:58:41 smørkniv 22:00:30 smør is an awesome word, sounds like smar, which means technical lube in Polish 22:01:45 monqy, elliott arpdoop 22:02:00 Phantom_Hoover too 22:02:02 right, ørjan? 22:02:27 oh no an arpdoop 22:02:47 i've just accidentally ardpoop 22:04:18 this is terrifying 22:06:20 nooga: could be a cognate? 22:07:36 maybe 22:10:55 * oerjan hasn't found out how to get good norwegian etymology from the internet yet 22:11:18 for a word that isn't shared with a big language 22:11:38 What is ACME assembly? 22:12:12 especially that verb 'smarować' derived from 'smar' is used with both bread and, for example, mechanisms 22:12:41 same with norwegian "smøre" 22:13:10 yay 22:14:20 > let f 'a' = "rp"; f 'r' = "do"; f 'p' = "op"; f 'd' = "ar"; f 'o' = "pd" in fix (('a':).(f=<<)) 22:14:22 "arpdooparpdpdoprpdooparoparpdopdooparpdpdoprpdopdoprpdooparpdoparpdpdoprpd... 22:15:37 WHAT! 22:15:52 i just googled ACME assembler for zzo38 and look: http://www.esw-heim.tu-clausthal.de/~marco/smorbrod/acme/ 22:16:28 smør everywhere 22:19:24 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 22:21:38 monqy: hello 22:21:43 helllo 22:22:52 helo 22:22:58 hall 22:23:04 hal 22:24:21 Just what do you think you're doing, Dave? 22:25:00 -!- ion has set topic: BEWARE THE Ø̈RJANIST MØ̈Ø̈SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | http://codu.org/logs/_esoteric/ | http://esolangs.org/wiki. 22:26:00 * oerjan wonders what changed 22:28:44 * oerjan detects a zero temperature in friday's forecast 22:28:58 i guess this is the end then. no one could possibly survive that. 22:35:56 eh 22:40:16 -!- nooga has quit (Ping timeout: 246 seconds). 23:12:45 -!- FreeFull has quit. 23:38:21 -!- carado has quit (Quit: Leaving). 2012-10-10: 00:31:54 -!- Frooxius has quit (Ping timeout: 264 seconds). 01:06:12 'The entire council of the city of Reggio Calabria in southern Italy is dismissed to stop it from being taken over by the mafia, officials say.' 01:27:34 I need to finish DS9 at some point 01:32:32 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:36:25 Does ClojureScript count as a Lisp? 01:36:39 ClojureScript macros are in a different language (Clojure). 01:37:08 Time for argue-about-words-o'clock. 01:38:53 Scheme macros are also in a different language (usually) 01:38:57 I guess Scheme isn't a Lisp... 01:39:27 It depends if the macros are in a different language? 01:39:49 Hmm, what makes a Lisp a Lisp? 01:39:57 I don't know 01:40:08 Sgeo: The main question is how much Paul Graham has written about it. 01:40:22 the term "Lisp" can be endlessly redefined to win the current argument 01:40:25 that's the beauty of it 01:40:52 I guess he doesn't write about Lisp anymoer. 01:42:22 * Sgeo should reread LoperOS person's rant about Clojure 01:42:27 I think I disagree with it 01:43:12 So. For various reasons I got shoved into a "UNIX programming" class. ... Holy mother of shit we have to use *C shell*? 01:43:29 Yes. /bin/csh 01:43:40 Am I going to need to learn COBOL next? 01:43:43 "It promotes no, mandates - the use of undigestable foreign matter in Lisp code: primitives on which you cannot pop the hood to reveal intelligible innards." 01:43:44 Seriously, what the fuck. 01:44:20 Does he believe that the hardware we run on should operate on conses? 01:44:32 probably 01:45:04 easyware 01:45:26 Sgeo: http://www.loper-os.org/?p=55 01:45:47 my encyclopedic knowledge of bad loper os posts finally comes in handy 01:46:46 hi elliott 01:46:50 I thought you quit #esoteric 01:50:44 I do think that Clojure is uncomfortably closer than it should be to Java at times, but I don't think it's really that horrible. 01:50:57 *C shell does not have functions*. 01:51:09 pikhq, any chance that they're called something else? 01:51:09 *They made a language worse than Bourne shell.* 01:51:22 Sgeo: No. The closest it *has* is aliases. 01:51:38 C shell is literally devoid of functions. 01:52:19 "No car crash, however brutal, will ever produce piles of loose protons and neutrons." 01:52:22 i don't think that's true 01:52:29 is there really nothing in a car which can burn hot enough to produce plasma? 01:53:34 Doesn't Joel talk about abstractions 01:53:45 oh dear, this seems to be a complicated question 01:53:50 Sgeo: Joel talks about a lot of shit 01:54:00 There may be some abstractions (e.g. TCP) in which leaks of the abstraction are inevitable 01:55:00 we just need the car to crash with randall munroe's baseball 01:55:22 * Sgeo initially skipped the word "about" in what kmc said 01:55:31 either way, really 01:55:54 magnesium engine block will burn at 3,000 K 01:56:09 nobody can give me a straight answer as to what temperature air turns into plasma 01:56:35 kmc: A billion degrees. 01:56:48 isn't cool 01:58:18 i hear there is cold plasma too 01:59:31 Sgeo: what's special about TCP there? 01:59:57 do you mean the fact that it can't overcome an indefinite period of 100% packet loss? 02:00:02 Yes 02:00:48 csh builtins cannot be pipes. 02:00:52 s/pipes/piped/ 02:01:58 Java methods are not functions in Clojure 02:02:08 pikhq's thing is probably worse 02:03:13 And its errors don't include line numbers. 02:05:08 -!- Sanky has quit (Ping timeout: 245 seconds). 02:05:32 Who designed C shell, and can I beat them? 02:05:55 * Sgeo again sees a comparison with Clojure :/ 02:08:41 -!- ais523 has quit. 02:19:00 Bill Joy. 02:19:05 Okay, I'm happy with beating him. 02:20:16 a joyful beating, check 02:20:56 Oh dear, he's partly to blame for NFS. 02:20:59 Now I have to beat him. 02:21:21 NFS: because file systems are stateless. 02:27:55 Wait, NFS is reviled? 02:29:10 haha Sgeo 02:29:14 such a joker 02:30:36 :/ 02:42:52 19:42 it's like I am stuck misusing the do monad 02:44:00 misusing the do monad, doo dah doo dah 02:44:23 Newbie misunderstandings are quote-worthy now? 02:44:57 since it's cornihilio it's much more likely that the type is right and the 'do' is wrong 02:45:09 Sounds like the people are familiar with this person? 02:45:42 this person has no heart 02:46:18 This person is all heart. 02:46:39 no, that would coromnisio 02:46:50 *+be 02:48:06 Sgeo: NFS is horrific. 03:03:56 -!- hagb4rd has quit (Ping timeout: 255 seconds). 03:07:53 zzo38: Hey, man. 03:08:04 You know who makes the puns around here, right? 03:08:08 !rot13 shachaf 03:08:09 funpuns 03:08:09 !rot13 zzo38 03:08:10 mmb38 03:08:21 -!- mig22 has joined. 03:08:26 mmb51 03:08:29 `welcome mig22 03:08:32 * oerjan just deals out punishment -----### 03:08:33 mig22: 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.) 03:08:45 `rot13 mig22 03:08:48 zvt22 03:09:04 МиГ-22 03:09:10 `rot13 Sgeo 03:09:13 Ftrb 03:09:22 so easy to pronounce 03:09:26 ─────███ 03:09:30 ^rot12 kmc 03:09:37 oops 03:09:41 ^rot13 kmc 03:09:41 xzp 03:09:55 xeegan zpallister 03:10:02 ^rot13 ▚▞▚▞▚▞▚▞▚▞▚▞▚▞▚▞ 03:10:03 ▚▞▚▞▚▞▚▞▚▞▚▞▚▞▚▞ 03:11:08 @yarr 03:11:08 I'll crush ye barnacles! 03:11:11 kmc Does "mc" really stand for "Mc"? 03:11:16 yeah 03:11:29 kmc: That's so lame. 03:11:38 haters gonna hate 03:11:41 Just like you!!!! 03:11:44 snap 03:11:55 -!- zzo38 has left. 03:12:02 ヾ(⌐■_■)ノ♪ 03:12:06 Not good enough for zzo38. 03:19:07 >+<[>-<-]>[<+>-]< 03:27:56 kmc: noob answer here but, i think you mean type checking, and that happens before. if a function gets bound, it becomes a new type, and the next type you feed it needs to be compatible. if a function is fed proper types but pruposely used in the wrong context, that's a failure of semantics. 03:28:43 very good sir 03:28:51 shall i warm up sir's crack pipe 03:29:05 kmc: a function that could take functions could do that 03:29:08 i think sir is cracked enough 03:29:10 kmc: something along the lines of f :: (a->b) -> a 03:29:14 kmc: monads should be suitable for this 03:29:28 are you livetweeting #haskell or what 03:29:33 yes 03:29:40 jesus really 03:29:40 this isn't twitter though kmc 03:29:41 it's irc 03:29:46 shall i warm up sir's crack pipe, as they say 03:29:56 elliott is trying to make you leave the last channel you're still in. :-( 03:30:04 that was all one person if that makes it better 03:31:00 shachaf: how long has this person been here 03:31:09 oh they're just reffering to the monadic context in general now i understand 03:31:11 ps by here i mean #haskell 03:31:28 elliott: A while. 03:31:52 elliott: You're such a geneous. 03:32:36 kmc: Do you know that you still beat me in "number of words said in #haskell"? 03:32:52 3x 03:33:30 elliott beats me too. 03:33:47 shocking. 03:34:02 shachaf: does anyone beat me 03:34:14 elliott: Of course. 03:34:33 who 03:34:35 dons? 03:35:39 I used to write all these specialized monomorphic functions and I couldn't use any free theorems. Then I started writing more general types for my functions and it was all, like, "welcome to parametri city". 03:36:02 elliott: Probably. 03:36:43 Oh, I measured wrong. It's not quite 3x. 03:36:58 dons is almost at 2 million words. 03:39:02 elliott: haveyouread OutsideIn(X) 03:39:19 no 03:44:22 elliott: I prefer the less well-known "double-negation with newline in the middle" translation. 03:44:43 shachaf: Er. What. It's strictly weaker. 03:45:31 elliott: You know how you used to be here every day but now you're only here every 7 days? 03:45:37 It's strictly weeker. 03:45:47 ok you got me 03:46:12 elliott: Do you believe cps :: (a -> b) -> (b -> r) -> a -> r yet? 03:46:31 define believe 03:46:51 You said it should be a -> (a -> r) -> r before. 03:47:56 i don't know 03:48:19 ((b -> r) -> (a -> r)) is a CPSed (a -> b) 03:51:41 * Sgeo decides not to ask a stupid and tangentally-related question 03:54:39 no paypal i do not need a loan to buy 5 tee shirts 03:58:44 -!- TeruFSX has joined. 04:00:04 -!- zzo38 has joined. 04:08:29 1 lakh rupees isn't cool, you know what's cool? 1 crore rupees 04:11:34 I can only assume that kmc is either playing a game or drunk. 04:11:57 neither 04:12:12 well i'm not more playing a game than usual 04:12:17 it's all, like, games, man 04:13:31 * Sgeo fines kmc for one crore crore rupees 04:15:41 why does http://en.wikipedia.org/wiki/South_Asian_numbering_system skip the crore crore row... 04:22:24 kmc: you're , game 04:30:53 besides Sgeo, you know that it's illegal to be drunk on the internet 04:32:01 -!- Sanky has joined. 04:32:09 @type flip (.) 04:32:10 forall a b (f :: * -> *). (Functor f) => f a -> (a -> b) -> f b 04:32:15 @type flip (Prelude..) 04:32:16 forall b c a. (a -> b) -> (b -> c) -> a -> c 04:33:36 :t (>>>).($) 04:33:38 forall a b c. (a -> b) -> (b -> c) -> a -> c 04:37:48 when carnage is insufficient, mr. munroe adds more zeroes. 04:38:22 kmc isn't playing a game more than usual. 04:38:25 Nor drunk more than usual. 04:39:02 I feel like I should learn how type checking/inference works properly. 04:39:52 badly 04:42:48 shachaf: Did you read Typing Haskell in Haskell? 04:47:36 kmc: Nope. 04:47:43 That's probably a good one to read. :-) 04:47:57 Of course GHC's type system is barely Haskell these days. 04:51:58 sure 04:52:23 i wasn't sure if you meant the general idea of type checking/inference, or specifically ghc haskell with all the bells and whistles 04:52:38 implementing type inference for simply typed lambda calculus is fun and not hard 04:53:08 hindley milner is only a bit harder, i think 04:53:28 and then you add type classes and polymorphic mutual recursion and you have haskell 04:53:41 and then you take about 2 mg of LSD and you have GHC Haskell 04:54:06 What do you do to end up with Agda? 04:54:57 Sometimes making these things more general makes them simpler. 04:54:57 well, i know nothing about how inference works in agda, to the degree it exists 04:55:01 yes 04:55:08 as far as checking goes that is true 04:55:34 Agda's value inference is probably better than its type inference... 04:55:50 @quote cmccann agda 04:55:51 cmccann says: someone should implement a dependently-typed unsafeCoerce in Agda, you'd have to provide a proof that the coercion is invalid 04:55:53 @quote cmccann agda 04:55:53 cmccann says: the most common solution to prevent runtime errors in Agda is by not running the program 04:56:33 :3 04:56:59 Colon three. 04:57:05 That's another one of those that I don't get. 04:58:29 There's no fundamental reason not to have "exists" in Haskell, is there? 04:58:37 I heard there's a fundamental reason not to have it in GHC. 05:01:01 which is? 05:02:02 By heard I mean edwardk mentioned something about it being incompatible with the way GHC does type checking at dinner once. 05:02:07 heh 05:02:25 So I don't really know. 05:02:25 "I asked Karp in the elevator and he said it was probably NP-complete" 05:02:54 Pretty much. 05:03:19 It was almost exactly a year ago. He's coming back next week for the same event! 05:03:37 Maybe I'll have the opportunity to ask him again. 05:08:51 zzo38: Where did your CodensityAsk type come from? 05:09:12 I like it. 05:10:30 shachaf: Do you like reflection? 05:10:33 That's a great library, that. 05:10:37 That wonderful person elliott worked on it. 05:10:53 elliott: I don't understand reflection. 05:11:05 It's probably good, though. 05:11:15 What does it do? 05:11:36 shachaf: Actually I just made it up 05:11:52 shachaf: Have you ever wanted to be able to express the type "Integer mod 42" in such a way that the 42 is encoded in the type? 05:11:55 zzo38: Right, but in what context? 05:11:57 So you don't have to write a Num instance for every single number. 05:12:01 elliott: Sure! 05:12:04 That you'd want to modulo it by. 05:12:33 shachaf: Okay, then look at "newtype M s a" onwards in http://hpaste.org/66699. Ignore the reflection implementation, it's just Oleg's low-level hack to accomplish it. 05:12:58 shachaf: Basically you can lift an arbitrary value to a (phony; the actual "type" is nothing and doesn't matter to you) type that you get an instance for. 05:13:04 That instance lets you give a proxy for that type, and get the value back. 05:13:09 So you can write interfaces that depend on values. 05:13:15 shachaf: I was first think of Yoneda with a class constraint, and then to use not a class constraint but rather a value instead. 05:13:21 shachaf: It can also be used to replace Reader like that, but in a way that omits all the monadic plugging. 05:13:28 shachaf: It's like implicit parameters, but without all their weirdnesses. 05:13:36 (And you don't have to implement it in the compiler.) 05:13:40 Hence, 05:13:42 reify :: a -> (forall s. Reifies s a => Proxy s -> r) -> r 05:13:48 class Reifies s a | s -> a where reflect :: proxy s -> a 05:13:49 And then I realize that you can use it to make a MonadPlus from any comonad. 05:14:05 shachaf: Do you understand me now? 05:14:11 elliott: OK. 05:14:26 zzo38: Nope. 05:14:30 elliott: Did you see CodensityAsk? 05:14:43 shachaf: Here's an example of it replacing Reader: http://hpaste.org/66715 05:14:49 Pfft, reflection is way cooler than CodensityAsk. 05:14:50 shachaf is now completely confused and thinks Reifies is a CodensityAsk type 05:15:06 CodensityAsk = best type 05:16:11 oerjan: Oops, isn't Reifies a class instead?? 05:16:21 zzo38: he is _very_ confused. 05:16:25 See, even zzo38 knows the deal about reflection!! 05:16:27 He knows what's up. 05:17:06 zzo38: Can you express CodensityAsk as a CodensityAsk type? 05:17:12 reflection lets you be down with what's up 05:19:05 shachaf: I suppose you can use (CodensityAsk (IdentityT f)) but I don't know if that is what you meant 05:19:22 (But you can do that with anything really) 05:22:44 zzo38: What's CodensityAsk (Cont r)? 05:23:49 shachaf: I don't know, but it is something. 05:24:29 However, notice that you don't need to use a functor there, it can be anything, such as (CodensityAsk Predicate) to make up the infinite search monad. 05:25:01 zzo38: CodensityAsk is "pretty damn awesome", confirms another channel. 05:29:11 zzo38: Is it really related to Codensity, though? 05:29:40 Codensity m a = forall z. (a -> m z) -> m z 05:33:40 shachaf: Well, kind of, but not really. I just didn't know what other name to put. 05:34:06 It is a monad in the same way that Codensity is a monad. 05:34:31 Which is also the same way that Cont is a monad, too. 05:34:32 -!- oerjan has quit (Quit: Good night). 05:42:01 -!- zzo38 has quit (Quit: Good night (again)). 06:10:56 @ask zzo38 Is this the CodensityAsk Monad (>>=)? m >>= f = CA $ \q k -> runCA m q (\x -> runCA (f x) q k) 06:11:01 Consider it noted. 06:20:25 -!- barts has quit (Quit: leaving). 06:24:36 Today I learned that YKK is a company 06:49:29 -!- nooga has joined. 06:49:37 pikhq: what's a good cpu these days 07:08:22 -!- epicmonkey has joined. 07:26:10 -!- epicmonkey has quit (Ping timeout: 246 seconds). 07:31:22 elliott: 68000 07:31:49 Much more powerful than the 6502. 07:32:04 thanks 07:32:11 You’re welcome. 08:01:37 -!- Jafet has joined. 08:02:03 @tell zzo38 Oh, I guess so. 08:02:04 Consider it noted. 08:20:54 -!- TeruFSX has quit (Read error: Connection reset by peer). 08:44:04 -!- epicmonkey has joined. 09:53:01 -!- kinoSi has quit (Read error: Connection reset by peer). 09:53:30 -!- kinoSi has joined. 10:21:05 kmc: http://www.dustingetz.com/2012/10/09/can-haskell-prove-that-a-program-will-not-crash.html 10:22:43 so in effect, an expression of type int -> int, will only crash in the same ways that math can ‘crash’ on pencil and paper. 10:22:49 Which means that if we’re confident that our program isn’t ⊥ (do you really worry about the halting problem in your business application?), if your program passes the type checker, it will not crash. ever. (Unless it runs out of memory, or you unplug it, …) 10:22:51 what a guarantee 10:23:59 i can offer a hard guarantee that if your program won't crash it won't crash 10:24:10 how much more could you ever want or need 10:25:19 http://www.dustingetz.com/2012/10/07/monads-in-python-identity-maybe-error.html 10:26:02 oh no 10:26:13 "business logic is crystal clear. hook it up to a flowchart software or something. 10:26:13 " 10:26:16 heeeeeeeeeeeeeeeeeeeeeeeeeeeeelp 10:27:23 Strange Loop 2012 talk - Monads for normal people in python (slides), monads for normal people in python and clojure 10:30:35 -!- monqy has quit (Quit: hello). 10:38:53 -!- ais523 has joined. 10:40:05 -!- Phantom_Hoover has joined. 10:48:57 -!- ogrom has joined. 11:01:41 -!- copumpkin has quit (Ping timeout: 248 seconds). 11:02:14 -!- copumpkin has joined. 11:04:31 -!- Arc_Koen has joined. 11:04:43 hello 11:05:56 nenholoe 11:06:01 ais523: hi 11:06:38 -!- ais523_ has joined. 11:06:48 -!- ais523 has quit. 11:08:09 "! End of file on the terminal... why?" 11:09:06 hey, has anyone seen itidus lately? 11:18:22 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 11:18:44 good question 11:18:58 maybe he got bored 11:19:19 -!- Phantom_Hoover has joined. 11:30:12 He got called "full of shit always", "spends too much time dragging down the discussion", "making the channel that much worse by being here and [..] clearly never going to change", and took off half an hour later; this was about 156 hours ago. 11:30:42 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds). 11:54:09 Deewiant: sounds like the #esoteric I know 11:55:00 nice looks like oerjan started it 11:55:04 don't see that every day!! 11:55:55 22:47:20: i am more interested in the unsolicited humour than reality when i say there is no operation which satisfies x in the equation (> (x wolfram) (in mathematicians_wolfram_admires)) 11:56:01 Right, there was some stuff before those quotes, too. 11:56:01 that might just be the best opening sentence to an argument ever 11:56:17 22:28:17: apparently wolfram's new kind of science recommends mathematica.. and someone is annoyed by it 11:56:17 22:29:53: i think.. maybe he should see a psychologist 11:56:21 going to miss these gems 11:56:58 22:55:22: what i tried to say is really in bad taste 11:56:59 22:55:30: so im glad its meaningless 11:57:07 i should probably feel bad for laughing at all this a lot 11:57:22 -!- copumpkin has quit (Ping timeout: 252 seconds). 11:57:55 -!- copumpkin has joined. 11:58:07 Deewiant: Well, only two of those were PH rather than the three I expected, that's quite exciting. 11:58:18 maybe #esoteric does change sometimes! 12:01:41 What, he didn't even reply. I want my money back. 12:05:46 -!- ais523_ has changed nick to ais523. 12:06:26 elliott: Mathematica ancedote: writing the 2,3 turing machine functions in mathematica, they were orders of magnitude slower than the equivalent Perl 12:06:34 (and Perl is not the right language to write those in) 12:08:13 ais523: err, you told me this five years ago 12:09:08 ais523: why do I remember you telling me something about Mathematica five years ago 12:09:50 because it's amusing? 12:10:08 Ha. Ha. Ha. 12:10:18 ais523: well I wouldn't go *that* far [LAUGH TRACK] 12:10:25 -!- ais523 has quit. 12:10:34 did I upset him 12:10:36 @tell ais523 i'm sorry 12:10:37 Consider it noted. 12:10:42 -!- ais523 has joined. 12:10:50 @tell ais523 i take it back, i'm not sorry at all 12:10:50 Consider it noted. 12:10:56 -!- boily has joined. 12:11:05 hmm 12:11:06 ais523: You have 3 new messages. '/msg lambdabot @messages' to read them. 12:11:09 @messages 12:11:09 AnotherTest asked 9d 19h 8s ago: On Wikipedia, programming language pages have "info boxes" which show some basic but useful information. Maybe we could do this on the esolangs wiki too? (To give 12:11:10 you an idea of the information that the boxes would contain; I was thinking of: paradigms, creator, year of creation, derived from, influenced by, influenced, specification, reference implementation 12:11:10 etc. 12:11:10 elliott said 32s ago: i'm sorry 12:11:10 elliott said 19s ago: i take it back, i'm not sorry at all 12:11:32 I don't think you need to apologise for whatever you were trying to apologise for 12:11:43 ais523: well I wouldn't go *that* far [LAUGH TRACK] 12:11:43 * ais523 has quit () 12:11:44 did I upset him 12:11:44 @tell ais523 i'm sorry 12:11:44 Consider it noted. 12:11:44 * ais523 (~ais523@unaffiliated/ais523) has joined #esoteric 12:11:46 @tell ais523 i take it back, 12:11:50 i stopped being sorry because it became clear you did not actually get upset! 12:11:52 therefore i don't have to be worry 12:12:44 aha 12:14:52 -!- copumpkin has quit (Ping timeout: 244 seconds). 12:15:27 -!- copumpkin has joined. 12:32:48 -!- Phantom_Hoover has joined. 12:37:13 -!- ais523 has quit (Read error: Connection reset by peer). 12:37:19 -!- ais523_ has joined. 12:37:53 -!- ais523_ has changed nick to ais523. 12:41:14 -!- ogrom has quit (Quit: Left). 12:47:34 -!- Slereah_ has joined. 12:49:34 -!- Slereah has quit (Ping timeout: 246 seconds). 13:10:44 wtf: http://thedailywtf.com/Articles/The-Killing-Job.aspx 13:16:23 -!- ais523 has quit. 13:17:44 I have a week’s worth of stats from my server that’s in the NTP pool. The connection speed has been set as 3 Mbit/s in the pool settings, the average usage is less than 0.5 kB/s. http://heh.fi/collectd/img/ntp-bytes 13:18:22 ion: Haha, you actually have that GPS thing in an NTP pool? 13:18:37 elliott: My server has been in the pool for ages. 13:21:13 ion: Well, I only got told about this server thing a few days ago by someone or other in here. 13:21:17 I am "out of" "the" "loop". 13:24:34 ion: Do you happen to know if there's any particularly easy way to compare my system's idea of the time with your server's? 13:24:38 That'd be exciting!!! 13:24:41 (FSVO exciting.) 13:24:51 I'm synchronised with ntp myself though, so it might be... uninspiring. 13:25:21 elliott: “server ntp1.heh.fi iburst” 13:25:51 ion: I take it that's not a shell command. 13:25:53 elliott: Which servers are you using, btw? {0,1,2,3}.{your area}.pool.ntp.org? 13:25:57 elliott: A ntp.conf line 13:26:09 It's, uh, literally whatever the Arch default is. Let me check. 13:26:20 [012].pool.ntp.org. Thoroughly uninspiring. 13:26:36 I guess there is probably some trickery to give me geographically-appropriate servers for those? 13:27:44 0) Vendors are working against the pool rules by using that by default; they should be {0,1,2,3}.arch.pool.ntp.org. 1) Why {0,1,2}, not {0,1,2,3}? 2) I think it probably has some GeoIP stuff, but i guess it’s best to use {0,1,2,3}.{your area}.pool.ntp.org. 13:29:08 0) Who starts numbering their lists from 0? I'm hereby renumbering 0 as 1. 1) I'd report it as a bug, except, uh... I'm lazy, and I doubt they'd care. 2) God knows, but that's how it is. 3) Right. Modifying configurations is so 2011, but maybe having super accurate time is 2012 enough to counter it out. 13:29:26 I like how http://pool.ntp.org/ has a decent chance of getting you some quaint time server website. 13:29:41 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 13:29:57 hehe 13:30:14 ion: I'm not sure what the vendor thing is about, though. It seems a rather arbitrary distinction. 13:30:49 Should Linux from Scratch recommend you use lfs.pool.ntp.org, even though you're mostly doing things yourself and don't really have any association with LFS? 13:30:56 Admittedly Arch is a bit heavier-weight than that, but still. 13:31:27 * elliott notes that http://www.pool.ntp.org/en/use.html doesn't mention anything about it either :p 13:31:36 I guess http://www.pool.ntp.org/en/vendors.html is it. 13:31:38 Sometimes some vendor’s device/software is faulty in some way and DoSes the pool. That way they can limit the issue until the bug is fixed. 13:31:48 "Time usually just advances." Deep. 13:31:49 lfs should provide instructions for calibrating with a sundial 13:32:06 ion: I think Arch just ships unpatched ntpd with a default configuration file. 13:32:16 They don't patch stuff all that much. 13:32:28 Also by ntpd I think I mean openntpd? 13:32:52 If an LFS/whatever *user* configures their ntpd they’re free to do whatever they want. But vendors coming with some kind of a default configuration should get a subdomain. 13:33:04 Is there much practical use for having network calibrated time, anyway? 13:33:06 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:33:06 No, I mean whatever this "ntp" package is. 13:33:28 Jafet: Well, you get a clock that's right. That's pretty valuable. 13:34:13 ion: Right. So where do you draw the line between a user copy-pasting an example configuration file from a website, and a user telling a tool (e.g., package manager pacman) to copy-paste an example configuration file for them? Admittedly it's somewhat more obvious in the case of something big and supported and official like Ubuntu. 13:34:35 So, why is that valuable. 13:35:21 Jafet: Well, time is a thing. 13:35:28 I think all sorts of Official(tm) stuff uses NTP. 13:35:31 Protocols that require roughly the same time on both ends are able to work. Filesystem etc. timestamps will be correct. 13:35:35 "Therefore, air traffic control was one of the first applications for NTP." -- see, that's official. 13:36:02 You won’t be late for work when using your computer’s clock. 13:36:18 That's assuming your office is on the same time! 13:36:54 I think protocols should start by negotiating time, rather than assuming the same time. 13:37:15 There's also the whole thing where it's nice for you, as a person, to know what time it is. 13:37:37 Unless you want every conversation about when to do a certain thing to involve negotiating two different clocks that are 15 minutes off because nobody synchronises their time. 13:37:43 Yeah, add time-dependency to the protocol so the attacker is unable to replay authentication packets… but let her dictate what time it is. 13:37:50 Seems nicer to have just one program (i.e., ntp) do the conversations about agreeing on what a time means. 13:38:41 "Someone with a watch can always tell the time. Someone with two watches is never sure." 13:39:05 Someone with two ntp-synchronized watches? 13:39:23 I think Jafet may be engaged in some leg-pulling. 13:42:53 -!- FreeFull has joined. 13:43:41 -!- Phantom_Hoover has joined. 13:48:29 nortti: :-D 13:50:41 ion: bitches don't know about mah nonce 13:51:26 ion: what? 13:51:48 ah ok 13:53:22 “We can use y to help us obtain an estimate of x, but we cannot necessarily take the information from y at face value because it is corrupted by noise. The measurement is like a politician. We can use the information that it presents to a certain extent, but we cannot afford to grant it our total trust.” :-D 13:54:35 Politicians, unfortunately, don't tend to be gaussian. 13:54:44 -!- copumpkin has joined. 13:55:21 heh 14:06:57 -!- mig22 has quit (Quit: mig22). 14:15:28 -!- sirdancealot has quit (Ping timeout: 246 seconds). 14:26:06 -!- MoALTz has quit (Quit: Leaving). 14:27:04 -!- jiella has joined. 14:33:47 -!- MoALTz has joined. 14:40:08 -!- sirdancealot7 has joined. 14:40:43 -!- kmc_ has joined. 14:40:57 -!- ineiros has joined. 14:41:27 -!- tswett_ has joined. 14:45:46 -!- kmc has quit (*.net *.split). 14:45:50 -!- yiyus has quit (*.net *.split). 14:45:50 -!- ineiros_ has quit (*.net *.split). 14:45:50 -!- tswett has quit (*.net *.split). 14:53:58 -!- yiyus has joined. 14:58:01 -!- sirdancealot7 has quit (Ping timeout: 246 seconds). 14:59:24 -!- sirdancealot7 has joined. 15:01:14 -!- augur has quit (Remote host closed the connection). 15:22:31 -!- MoALTz has quit (Ping timeout: 245 seconds). 15:23:00 -!- MoALTz has joined. 15:26:45 -!- sirdancealot7 has quit (Ping timeout: 248 seconds). 15:46:18 -!- augur has joined. 15:59:40 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 16:08:26 uh 16:08:27 what 16:09:08 struct S x, y; x = y; just blindly mempcys contents from x to y? 16:10:19 in C? yes 16:10:23 what else would it do 16:10:36 in C++ you can define the behavior by overloading operator= 16:10:46 -!- kmc_ has changed nick to kmc. 16:11:15 -!- Phantom_Hoover has joined. 16:11:26 the default in C++ is basically that it does "x.a = y.a; x.b = y.b;" for all the fields 16:11:43 well 16:11:45 which might in turn invoke a user-defined operator= or recursively invoke that default rule 16:11:54 so Plain Old Data in C++ effectively gets memcpy'd too 16:12:22 i never use plain structs 16:12:31 always pointers to structs 16:12:47 I never use pointers to structs 16:12:54 always pointers to pointers to structs 16:12:58 i don't always use structs, but when i do, i use pointers to them 16:13:05 right 16:17:27 -!- elliott has quit (Ping timeout: 240 seconds). 16:29:57 nooga: It's not guaranteed to memcpy. In particular, it need not copy padding. 16:32:29 it movs on x86 16:33:02 if the struct fits into 32 or 64 bits (in x86-64) 16:33:04 i think 16:33:29 i've just read what clang produced for my test program 16:33:48 Yes, well, but the point was that it doesn't need to copy all the bytes. Of course it can, and maybe probably will. 16:34:35 "When a value is stored in an object of structure or union type -- the bytes of the object representation that correspond to any padding bytes take unspecified values.51) ... 51) Thus, for example, structure assignment need not copy any padding bits." 16:40:06 uhum 16:42:44 It will frequently, perhaps always, be more efficient to copy the padding anyway. 16:43:07 (Irrelevant statement GOOOO) 16:43:53 it will always be most efficient to choose the most efficient alternative 16:44:15 Impressive. 16:45:52 actually no, choosing can be costly ... skip directly to *using* the most efficient alternative 16:50:02 -!- Jafet has quit (Ping timeout: 245 seconds). 16:51:04 -!- epicmonkey has quit (Ping timeout: 246 seconds). 16:58:07 -!- ogrom has joined. 16:58:26 -!- zzo38 has joined. 17:05:53 -!- Jafet has joined. 17:12:12 i like this channel 17:16:49 OK 17:16:49 zzo38: You have 2 new messages. '/msg lambdabot @messages' to read them. 17:16:55 Are you sure? 17:16:58 lambdabot ?messages 17:17:03 ?messages 17:17:03 shachaf asked 11h 6m 1s ago: Is this the CodensityAsk Monad (>>=)? m >>= f = CA $ \q k -> runCA m q (\x -> runCA (f x) q k) 17:17:03 shachaf said 9h 14m 58s ago: Oh, I guess so. 17:17:53 Yes, it is almost a kind of Codensity monad. 17:21:52 hmm, is it just me or has the internet been more boring than usual the last few weeks? 17:22:32 -!- Jafet has quit (Ping timeout: 255 seconds). 17:22:33 I'd say it is interestingly boring. 17:23:37 lol: http://thedailywtf.com/Articles/Taking-a-Dump.aspx 17:25:58 ah, that did temporarily restore my faith in the internet 17:27:30 http://fu.x14.eu/#WTF,funny,pics,4chan here You go 17:28:21 nortti: hah 17:33:41 -!- zzo38 has quit (Remote host closed the connection). 17:36:47 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 17:39:49 -!- sirdancealot7 has joined. 17:42:11 -!- ogrom has quit (Quit: Left). 17:43:45 ion: https://groups.google.com/forum/?fromgroups=#!topic/bahaskell/QJi4bU0cFi4 17:46:38 uh 17:47:41 i never did that but I always thought that I can ((unsigned int*)0x54aa4f02) = 100; 17:48:07 sure, you "can" do that 17:48:08 "can"? 17:48:43 it's not legal lvalue according to clang 17:48:54 oh, you're missing a * 17:49:00 wait 17:49:01 right 17:50:28 typo 17:52:39 -!- Phantom_Hoover has joined. 17:56:38 -!- augur has quit (Read error: Connection reset by peer). 17:57:07 -!- augur has joined. 17:58:48 -!- mean has joined. 18:03:19 shachaf: There’s going to be a Google hangout? 18:11:45 ion: I think that's the plan. 18:11:52 It's like recording, except for the recording bit. 18:12:34 I hope it also gets recorded. 18:17:51 You can record the G+ stream! 18:20:09 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 18:20:25 -!- Arc_Koen has quit (Quit: Arc_Koen). 18:38:40 -!- atriq has joined. 18:39:11 @messages? 18:39:11 Sorry, no messages today. 18:39:16 Yay! 18:39:20 ? 18:40:19 Means I don't have to deal with anything 18:41:21 -!- Phantom_Hoover has joined. 18:43:40 @tell atriq Deal with a thing, please. 18:43:40 Consider it noted. 18:43:49 @clear-messages 18:43:50 Messages cleared. 18:43:54 @tell fizzie I REFUSE 18:43:54 Consider it noted. 18:44:01 @clear-messages 18:44:01 Messages cleared. 18:44:06 This was a productive thing to do. 18:44:19 I hope I didn't have any messages in the meanwhile there. 18:45:21 That would have been bad 19:02:35 SmoothLife is a family of rules created by Stephan Rafler. It was designed as a continuous version of Conway's Game of Life - using floating point values instead of integers. http://youtu.be/KJe9H6qS82I 19:02:54 Didn't Phantom_Hoover make something like that? 19:02:56 Wait, that was chess 19:03:03 shachaf: I’m sure the stream will be of much worse quality than what can be recorded on-site. 19:03:25 Yeah, continuous chess. 19:03:44 That's pretty cool. 19:03:49 As an actually playable game, or as ... something to observe 19:04:02 Can I read about SmoothLife rather than watch a video? 19:04:13 http://arxiv.org/abs/1111.1567 19:04:28 Me and oko played a game of continuous chess... once. 19:04:44 Who won? 19:04:52 I think me? 19:05:03 he won the first game because i let him change the rules 19:05:21 Can I assume by flotrary ratiiece of shit right now. 19:05:25 , my computer is being a piece of shit right now. 19:05:25 , my computer is being a piece of shit right now. 19:05:31 Yes 19:05:43 and also i mustn't've worked out the final version of the rules for moving through enemy piece 19:06:27 What I intended to say was, can I assume that by floating point values, you mean arbitrary reals or rationals? 19:07:16 http://arxiv.org/pdf/1111.1567v2.pdf 19:07:21 flotrary ratiiece, what a wonder phrase. 19:09:54 Phantom_Hoover, that paper looks like it was made after Gemini? 19:10:05 ...what of it? 19:11:01 Just that the paper mentions large constructions and changes to the GoL rules made in the search of a non-orthogonal non-diagonal "glider" 19:11:12 (I think the paper is abusing the term "glider", isn't it?) 19:11:23 no 19:11:37 I have a fear that in two thousand years the only source for historians learning about our civilization will be Tumblr 19:11:52 'glider' is often used the same way as 'spaceship' when talking about general cas 19:12:15 Ah 19:12:52 To demonstrate the problem: http://froyuh.tumblr.com/post/33310816271/katherinebloginson-frankenzned 19:13:32 -!- ais523 has joined. 19:13:39 that is a pretty cutting commentary on our civilisation though 19:13:47 also spell civilisation like a briton you twat 19:14:13 I spell how I want to spell: no more, no less. 19:14:34 you're not spelling enough 19:16:13 I believe on an older version of my user page I mentioned I spoke en-GB-oed, in which -ize and -ization are accepted 19:19:07 -!- oerjan has joined. 19:21:04 nice looks like oerjan started it <-- i was _not_ the one to say he made the channel worse. i think. 19:22:22 * oerjan might be gone a few(?) days himself, got to get something done about my bad feet... 19:22:57 Has anyone any itinews? 19:23:13 hmm, the TV is currently talking about one of those questions that makes your head hurt 19:23:22 basically, it's to do with Fairtrade ingredients 19:23:46 he isn't on freenode under his two usual nicks, anyway. (he was last time i checked.) 19:24:01 some companies have apparently been buying both Fairtrade and non-Fairtrade ingredients, and putting the non-Fairtrade ingredients in their Fairtrade products and vice versa 19:24:17 such that they're using the same amount they would have used otherwise 19:24:26 ...right. 19:24:54 the question is, is this unethical in any way? the issue in my head is that the only difference between fairtrade and non-fairtrade is the price the company paid the farmers 19:25:02 and they're receiving the same amount of money any way 19:25:40 reminds me of the green electricity market - current doesn't care where it comes from :) 19:26:29 -!- mean has quit (Read error: No route to host). 19:26:52 -!- oerjan has quit (Quit: Ribbit). 19:33:04 -!- oerjan has joined. 19:34:42 ion: Probably. 19:35:22 ion: You should ask about recording! 19:35:53 :t let m >>= f = \q k -> m q (\x -> (f x) q k) in (>>=) 19:35:54 forall t t1 t2 t3 t4. (t -> (t1 -> t2) -> t3) -> (t1 -> t -> t4 -> t2) -> t -> t4 -> t3 19:35:58 ion: I guess you'd have to join the list. Should I ask? 19:38:29 oh i guess there's a forall on the (t1 -> t2) vs. t4 part 19:38:43 no wait 19:38:47 kallisti, I need to make someone who's trying to be cool by pretending to be a discordian look like an idiot 19:38:54 Advice? 19:39:21 `log newtype CA 19:40:03 No output. 19:40:06 `log newtype CA 19:40:19 2012-10-10.txt:19:39:21: `log newtype CA 19:40:47 `pastelogs zzo38>.*CA 19:40:53 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.25933 19:41:16 darn 19:41:38 `pastelogs zzo38>.*\ 19:41:45 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.906 19:42:26 `pastelogs zzo38 codensityask 19:42:30 er 19:42:32 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.30825 19:42:34 `pastelogs zzo38.*codensityask 19:42:41 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.29654 19:44:10 shachaf: If you don’t mind asking, i’d appreciate it. 19:45:19 of course the housemate has to start humming precisely when my brain is _just_ out of reach of grasping this. 19:45:48 * Sgeo has a habit of humming 19:45:59 * oerjan hires a hitman to take out Sgeo 19:46:07 it's for the good of humanity! 19:46:20 -!- epicmonkey has joined. 19:47:17 oh well, it's just the universe's way of telling me not to get anywhere near codensityask. 19:47:20 -!- augur has quit (Read error: Connection reset by peer). 19:47:41 -!- augur has joined. 19:47:55 * oerjan hires a hitman to take out the universe 19:49:32 Challenge accepted. 19:50:16 Quick or slow painful death? 19:50:26 quick. we are not monsters either. 19:50:46 besides, i don't want slow painful death on my karma. 19:50:56 Is CodensityAsk a zzo38 invention? 19:51:04 yes 19:51:12 What's CodensityAsk? 19:51:14 it's in that last paste 19:53:08 -!- augur has quit (Read error: Connection reset by peer). 19:53:31 -!- augur has joined. 19:54:49 -!- augur has quit (Read error: Connection reset by peer). 19:55:14 -!- augur has joined. 19:55:15 I don't see how that's a functor 19:55:53 Unless you don't use the function at all 19:56:02 In which case, it's a ridiculous Proxy 19:57:02 \m/ \m/ 19:57:14 * tswett_ nods solemnly. 19:57:59 zzo38 claims it's a monad always 19:58:13 but sadly my brain cannot get close to it 19:58:57 \m/ \m/ 19:59:03 say it isn't so :( 19:59:33 ^celebrate 19:59:34 \o| |o| |o/ \m/ \m/ |o/ \o/ \o| \m/ \m/ \o| |o| |o/ 19:59:43 OUR PARTY IS RUINED 20:00:47 Who was it who did that anyway? 20:00:55 myndzi 20:08:34 19:38 < atriq> kallisti, I need to make someone who's trying to be cool by pretending to be a discordian look like an idiot 20:08:40 IT'S TOO LATE 20:08:41 no, I am not very good at this 20:08:48 insult their mother? 20:08:50 hm, no.... 20:08:54 I HAVE PROMISED NEVER TO TALK TO HIM EVER AGAIN 20:09:07 my usual razor-sharp wit fails me, now. 20:09:23 -!- tswett_ has changed nick to tswett. 20:09:28 One of my friends was telling me a story today 20:09:31 though a maternal insult is always a reliable choice. 20:09:48 About how, one christmas, she received a DVD and was struggling to open it 20:10:04 So she asked her brother to give her a knife or a pair of scissors 20:10:07 And he replied: 20:10:19 "Don't worry. We can use my razor-sharp wit!" 20:10:24 That's the story 20:12:40 -!- hagb4rd has joined. 20:12:56 kallisti: your mom is a reliable choice 20:26:48 -!- ais523_ has joined. 20:27:38 -!- ais523 has quit (Ping timeout: 245 seconds). 20:27:43 -!- ais523_ has changed nick to ais523. 20:35:29 -!- hagb4rd has quit (Ping timeout: 256 seconds). 20:45:15 -!- boily has quit (Quit: Poulet!). 20:52:18 -!- epicmonkey has quit (Ping timeout: 276 seconds). 21:02:04 -!- Jafet has joined. 21:05:41 -!- atriq has quit (Quit: Leaving). 21:29:15 -!- Nisstyre-laptop has joined. 21:33:30 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 21:34:18 -!- Nisstyre-laptop has quit (Ping timeout: 264 seconds). 21:53:44 -!- kinoSi has quit (Read error: Connection reset by peer). 21:54:10 -!- kinoSi has joined. 21:55:40 -!- hagb4rd has joined. 22:09:46 -!- augur has quit (Remote host closed the connection). 22:22:15 -!- Arc_Koen has joined. 22:23:35 -!- FreeFull has quit (Quit: Sleep). 22:29:38 oerjan: any new thoughts on ais523's non-deterministic brainfuck? 22:32:26 -!- nooga has quit (Ping timeout: 252 seconds). 22:33:00 which one was that again 22:33:33 i guess my current thought is that it was rather forgettable :P 22:33:52 Arc_Koen: 22:33:58 ^ 22:34:02 oops sorry 22:34:26 nothing to be sorry about, i just took a while answering 22:34:37 + > [ ] with [ ] identical to brainfuck and + is randomly + or - and > is randomly > or < 22:38:23 well, nothing new, no. 22:38:43 i think it may be particularly hard to use >< 22:39:10 What's the point? 22:39:30 to see if it's still possible to do anything in it, presumably 22:40:43 -!- augur has joined. 22:44:05 it may be simpler starting with boolean cells (and + always flipping the bit) 22:44:27 http://samuelhughes.com/boof/ 22:44:54 and then maybe use [>] to move to nearest zero cell, digfill-style 22:50:12 i just don't see any way to reliably return to a cell. 22:51:07 well if you're on a cell with all the cells to the right zero and the cell to the left 1 22:51:31 i mean if there is a nontrivial pattern of cell values. 22:51:33 hmmm that doesn't even work if the cell you're in is 1 22:52:09 well if we can find a pattern that makes it possible, then we *only* need to make programs that keep that pattern 22:53:33 anyway, gnight 22:53:39 night 22:55:45 -!- copumpkin has joined. 23:04:07 urrrh why is there no sum or successor function with type char in ocaml 23:06:48 > map succ "I dunno, use haskell >:P" 23:06:49 "J!evoop-!vtf!ibtlfmm!?;Q" 23:07:19 -!- jiella has quit (Quit: Leaving.). 23:08:01 it doesn't have sum though, not that summing unicode codepoints makes sense. 23:08:03 ibtlfmm, huh? 23:08:39 shachaf: you didn't get zzo38's language name before? :) 23:08:53 oerjan: Sure I did. 23:09:20 oerjan: note that < and > all do at least move 23:09:25 so you always know if you're on evens or odds 23:09:35 this may make it possible to maintain two numbers on the stack, somehow 23:11:10 err 23:11:12 two numbers 23:11:14 full stop 23:11:16 on odds and evens of the tape 23:11:23 yeah 23:11:49 Well, not if you use > in a loop... 23:11:51 the problem is that the value of the numbers is pretty fuzzy and hard to determine 23:11:55 shachaf: if you do [>] 23:12:16 then you're moving until you find some blank cell that has no blank cells between it and your current location 23:12:18 if you do [>>] 23:12:24 it's the same except for respecting oddness/evenness 23:12:28 i am not sure there is a reliable way to distinguish more than even vs. odd numbers, zero is a subset of even but can you reliably set some cell to non-zero even? 23:13:02 oerjan: [+] 23:13:04 err 23:13:05 [+]+ 23:13:09 reliably sets it to 1 or -1 23:13:17 non-zero _even_ i said 23:13:51 there is definitely no way to distinguish 1 from -1, by symmetry 23:14:22 (not that i think you meant that) 23:14:41 I'm not convinced you can reliably distinguish 1 from 2 without an infinite loop 23:14:55 on one of the cases 23:15:09 but let's see 23:15:36 something along the lines of [+]++[>] seems promising 23:15:43 except you can't figure out where the pointer is afterwards 23:15:46 and you'd need to put it in a loop 23:15:55 that could easily keep it as 0 23:15:57 yes 23:16:05 the idea is you loop until the [>] runs and moves the pointer 23:16:09 but you can't detect whether it moved or not 23:16:30 you could just do [[+]++[rest of program here]] 23:16:35 but that doesn't repeat 23:16:43 sort of a limited cps 23:16:49 yes 23:16:56 well, it /does/ repeat, if you only have one of them 23:17:06 you could drop out of the main loop to set cells to 2/-2 23:18:22 hm an observation: if a run of non-zero's is even in length, then you _can_ reliably get to the zero at a chosen end 23:18:43 by [>>] or >[>>] 23:19:06 yes 23:19:15 from a known point inside it 23:19:16 no, not at a chosen end 23:19:22 left/right symmetry 23:19:27 oh, I see 23:19:31 by using the length as an indicator 23:19:36 yeha 23:19:38 *ah 23:19:51 err, couldn't you also end up one past the other end? 23:20:00 oh hm 23:20:04 darn 23:42:02 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 23:43:25 i wonder if this is somehow related to an idea i've had - a brainfuck variant where you can only apply + to 0 and - to 1, and any other use of them is undefined behavior 23:44:01 your language seems much easier 23:44:05 it's sort of an intersection of every bf cell size with unbounded tape, but still TC 23:44:17 yeah it has no >< problem 23:44:18 yeah, it's obviously TC 23:44:39 you can emulate boolfuck flip with 2 cells easily 23:46:19 the relation i thought of is just that your variant has those operations as + (or [+]+) and [+] respectively 23:56:51 +[>>]+[>>]+ creates a 10101 pattern and puts you at one end 23:58:01 +[>]+[>]+[>>]+ creates a 11101 pattern 23:59:56 neither [+]+ nor [+] cares about the original value 2012-10-11: 00:00:37 anyway, I have a feeling "CPS" is the way to go here 00:00:45 or at least, inside-out loop programming 00:00:47 if it's TC at all 00:01:04 you'd expect it to be just because it isn't obviously sub-TC 00:01:54 let's see 00:02:04 you can use alternating elements of the tape as two counters 00:02:20 you can increment them, the problem is decrement and zero test 00:03:24 to decrement, you'd need to find one end of the counter, then overwrite it with a 0 00:03:41 the problem is if the counter is actually 0, you'd just spend forever trying to find the end 00:03:48 even if you had a reliable inverted while, and I'm not sure you do 00:04:18 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:04:25 -!- Frooxius has joined. 00:31:08 -!- MoALTz has quit (Quit: Leaving). 00:54:46 -!- Jafet has quit (Quit: Leaving.). 01:03:40 -!- sivoais has quit (Ping timeout: 244 seconds). 01:06:23 -!- sivoais has joined. 01:14:40 -!- monqy has joined. 01:23:46 -!- monqy has quit (Quit: hello). 01:24:29 -!- hagb4rd has quit (Ping timeout: 256 seconds). 01:48:33 -!- Frooxius has quit (Ping timeout: 256 seconds). 01:48:58 -!- TeruFSX has joined. 02:04:00 -!- ais523 has quit. 03:02:16 -!- hagb4rd has joined. 03:09:33 -!- hagb4rd has quit (Ping timeout: 272 seconds). 03:11:12 -!- Wntrvnm has joined. 03:15:41 -!- hagb4rd has joined. 03:17:07 -!- TeruFSX_ has joined. 03:20:43 -!- TeruFSX_ has quit (Remote host closed the connection). 03:21:07 -!- TeruFSX_ has joined. 03:39:14 -!- hagb4rd has quit (Ping timeout: 260 seconds). 03:47:56 -!- monqy has joined. 03:50:34 -!- mig22 has joined. 03:52:33 -!- TeruFSX_ has quit (Read error: Connection reset by peer). 03:52:52 -!- TeruFSX_ has joined. 04:30:14 -!- Jafet has joined. 05:43:11 -!- hogeyui has quit (Ping timeout: 244 seconds). 06:00:24 kmc: 22:59 A new lambdabot isn't cool. You know what's cool? A new (U+E9278)bot. 06:01:16 kelvinbot is the coolest bot 06:05:39 zero kelvin bot. :3 06:06:00 I'm guessing that was the pun he was going for 06:06:23 olsner the psychic 06:06:24 yes but it is more solidified cool. 06:06:36 zerokelvinbot 06:07:39 some people want solid zero kelvin puns, but i say the helium 06:08:00 you say the helium? 06:08:37 Save the helium. 06:08:58 the helium deficit is simply ballooning 06:09:28 what other things is helium used for, really? 06:09:53 cooling. MR machines. 06:10:20 mad science. 06:12:14 diving 06:12:20 I should be doing more mad science 06:13:05 ((more mad) science) or (more (mad science))? 06:13:26 obviously both 06:13:56 also more science, so I have some science to put the mad in 06:14:02 {more (mad} science) 06:20:31 More ((more mad) science). 06:20:39 More, more, I'm still not satisfied! 06:44:52 -!- monqy has quit (Quit: hello). 06:49:39 -!- Jafet has quit (Ping timeout: 255 seconds). 06:51:32 -!- epicmonkey has joined. 07:24:47 -!- epicmonkey has quit (Ping timeout: 272 seconds). 07:53:38 -!- oerjan has quit (Quit: See you in a few days if I survive). 07:56:19 -!- oerjan has joined. 07:57:09 Just realized I probably shouldn't imply that I expect not to survive hospital :P 07:57:12 -!- oerjan has quit (Client Quit). 07:57:38 kmc: The examples in the end of http://mainisusuallyafunction.blogspot.com/2010/10/quantification-in-haskell.html aren't actually monoids (1/"foo" aren't identities). 07:58:09 I'm not sure whether that was meant to imply that Something was equivalent to SomeMonoid. 08:19:21 -!- TeruFSX has quit (Read error: Connection reset by peer). 08:30:04 -!- epicmonkey has joined. 08:37:46 -!- hogeyui has joined. 08:57:19 -!- nooga has joined. 09:18:18 -!- jiella has joined. 09:46:23 -!- Jafet has joined. 09:46:33 -!- MoALTz has joined. 09:47:19 -!- Kosnik has joined. 09:47:50 can anyone solve this riddle 09:52:41 -!- Kosnik has quit (Quit: Leaving). 09:53:14 I don't think anyone can. 09:53:27 A homotopy lattice on elliptic curve residues. 09:54:50 Oh, you solved it. 09:55:41 theproofistrivial.com 10:55:21 -!- Nisstyre has quit (Ping timeout: 276 seconds). 11:02:25 -!- ogrom has joined. 11:09:17 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 11:09:36 -!- Nisstyre has joined. 11:28:27 -!- Nisstyre has quit (Read error: Operation timed out). 11:41:42 -!- copumpkin has joined. 11:45:47 -!- Nisstyre has joined. 11:49:12 -!- epicmonkey has quit (Ping timeout: 260 seconds). 11:49:20 -!- boily has joined. 11:54:25 -!- Frooxius has joined. 12:01:14 -!- epicmonkey has joined. 12:04:16 Some sensor testing. http://heh.fi/tmp/imu-test 12:10:10 -!- ogrom has quit (Ping timeout: 255 seconds). 12:12:03 -!- ogrom has joined. 12:21:55 -!- hijack has joined. 12:22:24 -!- hijack has changed nick to mean. 12:32:13 -!- Arc_Koen has joined. 12:32:35 hello 12:32:49 -!- epicmonkey has quit (Read error: Operation timed out). 12:49:39 -!- epicmonkey has joined. 12:59:05 -!- Jafet has quit (Quit: Leaving.). 13:04:09 -!- Phantom_Hoover has joined. 13:09:34 -!- Jafet has joined. 13:25:53 -!- elliott has joined. 13:28:20 -!- mig22 has quit (Quit: mig22). 13:49:12 -!- ais523 has joined. 13:51:43 -!- ais523 has quit (Read error: Connection reset by peer). 13:51:56 -!- ais523 has joined. 13:54:43 -!- kinoSi has quit (Read error: Connection reset by peer). 13:55:10 -!- kinoSi has joined. 14:00:26 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds). 14:06:53 pikhq: How was it you said how to convert GPT to MBR? 14:07:01 * elliott 's system has been all too stable the past few days. 14:17:23 shachaf: Why isn't there a castStableName :: StableName a -> StableName b -> a -> Maybe b? 14:20:04 Or I guess castStableName :: StableName a -> StableName b -> p a -> Maybe (p b) is better. 14:20:28 (Implementation is Just through unsafeCoerce if (==).) 14:21:38 -!- ogrom has quit (Quit: Left). 14:30:19 -!- Phantom_Hoover has joined. 14:58:56 -!- ogrom has joined. 15:05:36 -!- ais523 has quit (Ping timeout: 256 seconds). 15:06:09 -!- Arc_Koen has quit (Quit: Arc_Koen). 15:18:15 -!- ais523 has joined. 15:33:30 -!- ogrom has quit (Quit: begone). 15:52:21 elliott: To annoy you. :-( 15:53:08 -!- augur has quit (Remote host closed the connection). 15:53:26 shachaf: Doesn't it annoy you too? 15:53:47 I've never wanted that function. 15:54:18 -!- ais523 has quit (Read error: Connection reset by peer). 15:54:20 It lets you do observable sharing, see? 15:54:22 And other things. 15:54:26 It's useful with existential types and stuff. 15:54:36 -!- ais523 has joined. 15:54:48 StableNames are for people who horse around while they're programming. 15:56:34 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 16:00:50 ais523: I think you should kick shachaf for that. 16:01:47 /xvpx funpuns 16:19:16 -!- Wntrvnm has quit (Quit: Stopping ZNC Daemon... [DONE] - http://github.com/Wintervenom). 16:20:12 -!- Wntrvnm has joined. 16:24:08 -!- mean has quit. 16:25:26 -!- augur has joined. 16:31:22 oh, that pun took a while to spot 16:32:34 -!- Nisstyre has quit (Ping timeout: 240 seconds). 16:34:14 -!- ais523_ has joined. 16:34:33 -!- ais523 has quit (Read error: Connection reset by peer). 16:34:36 -!- ais523_ has changed nick to ais523. 16:47:59 -!- Nisstyre has joined. 17:19:29 -!- epicmonkey has quit (Ping timeout: 272 seconds). 17:21:25 Which pun? 17:22:22 Ugh, even well-known libraries like Incanter sometimes feel like they were written by Clojure newbies 17:22:56 -!- ais523 has quit. 17:43:57 kmc: How many cores were in that machine you were talking about at ksplice? 17:44:36 48 17:45:05 four sockets, each with one of AMD's "Magny-Cours" processors 17:45:19 kmc: More like kscheisse, right? 17:45:37 Magny-Cours is French for Many-Cores 17:45:39 which are sold as 12-core processors but are actually two six-core processors in a multi-chip module 17:45:53 (for example, each socket has 2 NUMA domains and 2 L3 caches) 17:46:15 2 L3 caches? That's like an L6 cache! 17:46:23 i know, right? 17:46:35 kmc: I feel like you don't appreciate my jokes. 17:46:44 it is elliott 17:46:49 that's the joke 17:47:33 What did Ksplice need with 48 cores? 17:47:55 kmc: Hey, you're a joke. 17:48:06 shachaf: building kernels 17:48:10 kmc??? "No it isn't okay!!!" - mc 17:48:20 suddenly I burned you instead.......... 17:48:24 it's true that this work could be distributed across multiple machines 17:48:26 how does it feel 17:48:37 we did the biggest batch builds on EC2 spot instances 17:49:26 but in general it's easier to manage one machine, and one build script that runs on one machine 17:52:35 so we built the most parallel single machine we could using parts that are still vaguely commodity PC hardware 17:53:16 what ksplice 17:53:32 That works up to a point. 17:54:46 basically we decided the price premium of one integrated super beefy machine versus four reasonably beefy machines was less than the value of engineering effort to make the existing build scripts run in a distributed fashion 17:55:09 (or the engineering effort of making a local distributed setup that looks like EC2 enough to reuse the EC2 build scripts, which also had various problems) 17:55:40 this being a 12 person company and not someone like Google or Oracle with huge teams devoted to building and managing distributed systems 17:55:45 Making build scripts distributed is more trouble than you might think. 17:55:52 Even if you take Hofstadter's law into account. 17:56:18 i was pretty pleased with myself when i added distributed work to the script to re-encode my music library as ogg vorbis 18:09:57 -!- sivoais has quit (Ping timeout: 245 seconds). 18:12:46 building a ksplice update involves building the distribution's kernel using exactly their configuration and toolchain, then applying your patch and building it again 18:13:04 why? 18:13:07 i mena 18:13:10 mean* 18:13:12 what for? 18:13:28 you do get to use make's incremental build, but it still takes a fair amount of time 18:13:42 and you have to do this separately for each version of the base kernel the user booted into 18:13:46 nooga: do you know what ksplice is 18:17:06 some 18:17:11 linux kernel extension? 18:17:16 not really 18:17:27 It's more of a Windows NT kernel extension. 18:17:37 it's a technology for applying linux kernel updates to a running system, without rebooting or disrupting any processes 18:17:50 Oh, that ksplice. 18:17:59 Is ksplice dead? :-( 18:18:08 okay 18:18:11 and? 18:18:12 i worked for the company that developed this technology, and sold an updates service based around it 18:18:20 until that company was bought by oracle 18:18:30 now it is a feature of oracle linux premium support, but i don't work there anymore 18:18:38 i see 18:18:52 anyway ksplice works by comparing the compiled object files of the pre- and post-patch kernels 18:19:08 which is why you need to compile the kernel exactly as the distribution did 18:19:20 you don't need a special kernel to apply ksplice updates 18:19:55 then wikipedia is wrong 18:19:56 we had customers who had not rebooted their machines since before ksplice was created, and yet they could apply rebootless updates 18:20:09 pretty smart 18:20:17 'Using Ksplice does not require any preparation before the system is originally booted (the running kernel does not need to have been specially compiled, for example)' 18:20:26 does wikipedia contradict this somewhere else? 18:20:37 "Ksplice is an open source[2] extension of the Linux kernel " 18:20:42 yes 18:20:44 it is open source 18:20:47 i added that citation 18:20:52 but not an extension? 18:21:13 each update is a linux kernel module 18:21:20 oh 18:21:23 (actually, a few kernel modules) 18:21:32 it seems valid to call kernel modules "extensions" 18:21:54 also it is possible to build a kernel that has the core ksplice technology built in (or, it was possible at one point, anyway) but we did not expect our customers to have done so 18:22:08 -!- sivoais has joined. 18:22:11 we expected our customers to be using standard precompiled kernels from red hat, ubuntu, debian, etc. 18:23:14 actually, that's pretty nifty 18:23:32 yeah, it is really cool tech :) 18:24:27 are you one of the founders? 18:24:31 no 18:24:37 i joined only 8 months before the company was acquired 18:26:10 -!- FreeFull has joined. 18:26:12 i'm sure it was a nice job 18:26:22 hacking this stuff 18:26:27 -!- epicmonkey has joined. 18:26:30 yeah 18:26:32 it was really fun 18:26:49 i was kinda bummed when we got acquired by compuglobalhypermegacorp 18:27:01 but i made a decent amount of money off it 18:27:01 -!- ais523 has joined. 18:28:33 that's the best part usually 18:28:53 Money is overrated. 18:29:15 it's nice to have some extra 18:30:21 i guess money is overrated 18:30:32 but the value of having money is that you can adopt the attitude "money is overrated" 18:30:39 if you don't have money then it does not seem overrated 18:30:44 there were times 18:30:56 tthat i was an uneployed student 18:31:11 and couldn't afford bread 18:31:14 once :D 18:31:31 i do feel like my quality of life does not change much past some fairly low income level, but that level is still very high by global standards 18:31:33 nothing too bad - but it was an important experience 18:31:35 i think 18:31:44 sometimes students can get free food :) 18:31:45 Money is overrated beyond a certain point, I mean. 18:32:28 but money saved is also more time you don't have to work later 18:32:40 and longer you can survive without getting a job in the future 18:32:44 Maybe I'm just trying to convince myself. 18:32:48 and you can also give it to someone who needs it more 18:33:25 i like having some cash buffer 18:33:47 it's a matter of 18:34:15 not worrying about the small stuff 18:34:43 you cannot even focus if you fear that you won't be able to pay rent 18:34:49 or something 18:36:38 yeah 18:36:44 exactly 18:37:02 being poor is expensive 18:37:38 if you're poor you can't afford the time or equipment to cook at home, can't buy food or anything else in bulk 18:37:54 poor people in rich countries eat lots of terrible cheap fast food 18:38:02 hehe 18:38:09 i live in Poland 18:38:12 and it's like 18:38:27 if you're poor you probably spend a lot of your time on transit getting from your house in the middle of nowhere to various jobs 18:38:39 basically being poor is expensive and exhausting 18:38:46 majority of ppl earn from 600 to 1200 bucks 18:38:48 i think 18:38:54 are poor people in Poland fat or thin? 18:38:59 and gas is like 2 bucks per litre 18:39:02 i think poland is rich enough that the poor people should be fat but i'm not sure 18:39:07 bread is 1 buck 18:39:28 dinner in a decent restaurant is 20-30 bucks 18:39:41 beer in a pub 2-4 18:40:03 rest ona 55sqm flat is 400-600 18:40:25 kmc: thin :D 18:42:00 living here is quire expensive when you look at the earnings 18:42:24 i think living in london is cheaper, provided that you work for pounds 18:43:03 haha wow 18:43:07 where in poland are you? 18:43:18 Poznań 18:43:56 cool 18:44:07 i was in poland briefly in august 18:44:11 didn't make it that far west though 18:44:28 where have you been? 18:44:30 it's crazy how much housing prices differ by area 18:44:54 my parents have a nice big four bedroom house in suburban iowa and I think their mortgage is about the same per month that I pay to rent one bedroom in cambridge massachusetts 18:45:12 yeah 18:45:49 i was in kraków and warszawa 18:46:12 and surrounding areas 18:46:12 kraków is nice and warszawa is awful 18:46:19 yeah 18:46:23 that's kinda what i thought too 18:46:32 west > east :D 18:46:44 i saw the wieliczka salt mine 18:46:46 that was really cool 18:46:55 * shachaf has never been to .pl. 18:47:29 yeah, been there too 18:50:12 * nooga has never been to USA 18:50:26 but I'm working on fixing that 18:50:34 cool, where will you go? 18:50:35 * FreeFull has been to two salt mines. Wieliczka and Bochnia 18:51:09 san francisco, sv 18:51:34 nooga: That's the place to be! 18:51:36 (So I hear.) 18:51:43 sv? 18:52:07 sillicon valley :D 18:52:11 ah 18:52:15 san francisco is really nice 18:52:20 SV not so much. 18:52:29 i'm working on some tech for language pattern recognition and I was invited 18:52:35 silicon valley is south of there and I don't think there's much to see if you don't have friends working there 18:52:38 ah, cool 18:52:45 our guys have founded a company there 18:52:47 there are a few interesting computery museums down that way 18:52:57 that's what i'm waiting for :D 18:53:37 -!- itidus21 has joined. 18:53:38 @quote luite optic 18:53:38 luite says: I'm really interested in both practice and theory of optics and wave mechanics, so I'll be coming over from Europe for Edward's lecture on lenses and transversals. 18:53:46 That's next week! 18:53:56 hah 18:54:07 hello guys! just taking a break from here.. just joined by muscle memory since i join all rooms manually 18:54:48 muscle memory huh? :D 18:55:47 btw. I wonder when was the first time I joined this fine channel 18:55:58 something around... uh... 2005? 18:58:10 the the most interesting thing i have been trying to do is to take a bitmap which could be viewed as an image in black and white, and compress it into colours 18:58:23 [2004-12-23 10:04:58] -!- VonTroba is now known as nooga 18:58:30 According to my logs. 18:59:09 With a join just 17 seconds before. 18:59:24 thanks fizzie 18:59:29 i'm curious in such things as to whether it's possible for human brain to learn to see simple shapes as colours 18:59:43 well i mean the opposite 19:00:17 interesting 19:00:44 one particularly interesting part is that only the edges of things really change colours 19:01:05 can you provide an example? 19:01:20 ill show my paint image.. its a bit ridiculous 19:04:43 -!- nys has joined. 19:06:33 it's this http://oi49.tinypic.com/35hlsh0.jpg 19:08:00 itidus21: Can you do better than 8 pixels per byte raw B&W data? 19:12:07 humm.. my theory is that using 2 or 3 bits per pixel like that that it would be possible to learn to watch objects move by changing colour 19:12:43 beyond that, it was just a weird idea i had to try 19:13:30 i guess even in black and white objects move by changing colour 19:14:30 with 24bits it could represent 16 million patterns per pixel of course 19:19:51 yeah 19:20:35 definately human brain can comprehend that 19:22:19 yeah, the human brain is like smart 19:23:28 i was thinking about the way resolution affects the number of frames in an animation 19:23:35 and then i ended up on that .. 19:25:04 to be honest i think images compressed by colour would be nightmare fuel 19:28:27 http://attrition.org/errata/charlatan/hakin9/nmap.html lfmao 19:29:33 "Furthermore, we reduced the effective tape drive throughput of our stochastic overlay network. Similarly, we tripled the effective floppy disk space of our Internet-2 overlay network." 19:31:10 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 19:35:52 -!- Wntrvnm has quit (Quit: Stopping ZNC Daemon... [DONE] - http://github.com/Wintervenom). 19:38:51 -!- Wntrvnm has joined. 19:40:38 https://docs.google.com/viewer?a=v&q=cache:_j0_-BRo0MAJ:raisama.net/ufpr/tg/paper.pdf+&hl=pl&gl=pl&pid=bl&srcid=ADGEESivOHOM_O0aEfZ-Wn_XOroe2qgQBYM2XLaGHn75VcvILppGL9BrWLyhX124vxLTxQJL3_GNMAAqhrdoUN-Qv_VkT78Utvb8edLqnMQ8EBlOrDS1QlLt6h8HooGIqL9AppSDbZun&sig=AHIEtbRjm2-pxwjJXi3NaH-FXk2vqaZPyQ LULZ 19:45:25 -!- epicmonkey has quit (Ping timeout: 246 seconds). 19:51:22 -!- pikhq has quit (Ping timeout: 246 seconds). 19:56:42 -!- pikhq has joined. 19:58:48 -!- pikhq has quit (Remote host closed the connection). 20:09:26 -!- pikhq has joined. 20:30:55 -!- jiella has quit (Quit: Leaving.). 20:36:35 -!- jiella has joined. 20:41:53 -!- atriq has joined. 20:42:00 @messages? 20:42:00 Sorry, no messages today. 20:42:05 Yay 20:42:29 @tell atriq BOO. 20:42:30 Consider it noted. 20:55:54 @massagas 20:55:55 You don't have any new messages. 21:02:52 -!- boily has quit (Quit: Poulet!). 21:08:10 itidus21, I've missed you! 21:08:11 atriq: You have 1 new message. '/msg lambdabot @messages' to read it. 21:10:22 @ask atriq good hello 21:10:23 Consider it noted. 21:10:58 My god 21:10:59 atriq: You have 1 new message. '/msg lambdabot @messages' to read it. 21:11:00 You're right 21:11:10 I've replaced the "Hello" with a different hello 21:11:16 @clear-messages 21:11:17 Messages cleared. 21:11:22 Huh? 21:11:28 Oh. 21:23:34 Is there a term for the restriction of brainfuck where comments and whitespace aren't allowed? 21:30:08 Yes, it's called ++++++++++++++[>+++++++>++++++++>+><<<<-]>.>++.<-.++++++++.+++++.--------.>+++.<---.++++++++.>>----. 21:32:51 -!- augur has quit (Remote host closed the connection). 21:40:07 -!- Phantom_Hoover has joined. 21:45:17 Goodnight, everyone 21:45:17 -!- atriq has quit (Quit: Leaving). 22:10:43 -!- augur has joined. 22:30:28 branfuck 22:31:06 -!- jiella has quit (Quit: Leaving.). 22:31:08 Hot. 22:31:51 branfuck has 800% your daily recommended allowance of dietary fiber 22:32:44 When absorbed via the penis, that's about 80%! 22:32:56 no it's over 9000% 22:40:21 borp 22:46:43 -!- Phantom__Hoover has joined. 22:49:01 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 22:51:53 kmc: more like dietary fuckber 22:52:23 -!- nooga has quit (Ping timeout: 246 seconds). 22:52:58 fuckbear? 22:56:18 #esoteric: From any topic to gay porn in three steps or less. 22:59:46 That seems like an abusable property. 23:00:36 Like, say, next time someone needs to fill a gay porn folder. 23:00:37 :P 23:01:24 no pikhq 23:01:30 pick out your own gay porn 23:01:33 don't be lazy 23:15:02 But lazy is what I do best 23:42:54 -!- sirdancealot7 has quit (Ping timeout: 240 seconds). 23:46:02 -!- sirdancealot7 has joined. 23:46:34 -!- Jafet has quit (Quit: Leaving.). 23:49:19 -!- ais523 has quit. 23:50:36 -!- sirdancealot7 has quit (Excess Flood). 23:51:39 -!- sirdancealot7 has joined. 23:51:59 * pikhq WTFs at Ōgami 23:55:41 -!- copumpkin has joined. 2012-10-12: 00:00:56 -!- sirdancealot7 has quit (Ping timeout: 260 seconds). 00:01:50 -!- sirdancealot7 has joined. 00:10:19 -!- MoALTz has quit (Ping timeout: 245 seconds). 00:24:40 -!- monqy has joined. 00:29:16 monqy: hello 00:29:26 i beat you to the punch this time 00:29:33 monqy: 2 fast 2 monqy 00:33:47 -!- Frooxius has quit (Ping timeout: 245 seconds). 00:36:36 -!- itidus21 has left ("Leaving"). 00:43:39 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 01:01:28 -!- zzo38 has joined. 01:04:33 Does this Haskell type meaningful anything to you (I wrote it while trying to figure out something else): (forall y. forall z r. (x -> Cont r z) -> Cont r ((z -> x') -> y)) -> y) 01:05:44 Oh hey itidus was here 01:22:36 -!- Wntrvnm has left ("http://wintervenom.github.com - http://wintervenom.us.to"). 01:28:14 -!- heroux has quit (Ping timeout: 260 seconds). 01:30:25 The control schemes I like for platform games are using the shift keys to move, space to jump, and any of Z X C V B N M , . / to shoot. 01:30:43 However I know only of a few games implementing this. 01:50:13 -!- Jafet has joined. 02:01:08 http://i.imgur.com/bFXM6.jpg 02:04:28 zzo38: That's not good because you might accidentally press both Shift keys at the same time. 02:04:33 Then it'll change your keyboard layout. 02:22:05 shachaf: It was a DOS program so it didn't do that, and anyways it won't change the keyboard layout if you don't have it configured like that 02:25:10 Am I allowed to slap library writers who don't understand the most advertised feature of the language they're writing a library in? 02:25:19 Incanter uses STM, but uses it wrongly. 02:25:29 Do tell? And, yes. 02:27:45 The defop function in incanter.infix alters several refs, but each alteration is in its own dosync block 02:27:56 https://github.com/liebke/incanter/blob/master/modules/incanter-core/src/incanter/infix.clj#L42 02:28:15 If there are several ... hold on, I have deja vu 02:28:18 and you're sure they intended for it to be atomic? 02:28:33 I don't know if they intended for it to be anything 02:28:59 déjà 02:29:47 Hmm, when I was reading it before, I thought there could be a negative consequence, but looking at it now, I don't think so 02:30:36 it seems like more transactions might have higher overhead and lower uncontended throughput, but fewer big transactions might have more likelihood of livelock 02:30:45 that's just a vague guess 02:30:57 also it might not be correct for Clojure because their STM implementation is not lockless 02:32:11 Even if that last dosync runs later, it's still finding the highest value in the precedence table and putting it in highest precedence 02:34:17 -!- Bike has joined. 02:40:56 -!- heroux has joined. 02:53:37 My team has 24 winning streak so far. 02:54:17 My team has 25 winning streak. 02:54:25 I think I win this one, zzo38. 02:55:48 -!- monqy has quit (Quit: hello). 02:56:10 Regardless of winning streak you might win or lose. 02:56:21 My team is "heads". 02:56:23 I beat someone with more winning streak than I have. 02:56:51 Did you cheat? 02:58:28 -!- nys has quit (Quit: quit). 03:00:41 No. 03:01:32 zzo38: Did you play Zork Zero? 03:02:49 No. 03:03:27 zzo38: That's a good game. 03:03:30 You should play it! 03:03:56 Hmm. 03:05:35 -!- mig22 has joined. 03:05:43 you should play trial of the clone 03:10:44 Wait, Chrome just goes ahead and downloads a .exe but warns me that .jars can harm my computer? 03:11:48 Perhaps you did not configure it? 03:12:14 zzo38: Did you play Double Fanucci? 03:12:52 I don't have any cards to play Double Fanucci. 03:12:59 What about in the computer? 03:13:38 No. 03:14:21 Eww, the Incanter executable ships with Clojure 1.2 03:37:50 This sentence claims to be an Epimenides Paradox, but it is lying. 03:51:00 zzo38: I don't believe you 03:52:28 Neither do I. 03:52:41 I don't believe me either! 04:12:59 -!- Nisstyre has quit (Ping timeout: 260 seconds). 04:22:48 -!- Nisstyre has joined. 04:25:59 -!- monqy has joined. 04:26:52 hello elliott 04:28:28 -!- FreeFull has quit. 04:28:34 hello monqy 04:28:40 i am elliotts 04:29:53 o 04:32:14 -!- donmarquis has joined. 04:32:33 monqy: hi 04:32:34 elliott: You have 1 new message. '/msg lambdabot @messages' to read it. 04:32:35 help 04:32:59 @ask elliott what did the message say 04:33:00 Consider it noted. 04:43:13 -!- donmarquis has quit (Quit: Leaving). 04:45:11 -!- elliott has quit (Ping timeout: 255 seconds). 04:49:20 http://hackage.haskell.org/packages/archive/Agda/latest/doc/html/src/Agda-Auto-Auto.html#auto 04:50:17 Hmm. National Coming Out Day. *shrug* Guess I'll use the last hour of it to say "I'm bi", though I think I might have said that previously here? 04:50:20 Feh, not that it matters. 04:50:27 No real IRC sexytimes here. 04:50:34 Maybe some rape of the brain. 04:50:46 pikhq: I didn't know you were a functor. 04:50:53 shachaf: Smartass. 04:52:50 My Dungeons&Dragons player has played Double Fanucci, though, but lost five perica (a form of currency in the Japanese manga "Kaiji", used by underground slave colony, worth one tenth of one yen) at it. 04:54:15 shachaf: Did you know if you were a functor? 04:54:27 Is it a endofunctor? 04:55:10 Glad to see everyone here has appropriate levels of apathy about sexuality. 04:59:35 Agda.Utils.Impossible 05:01:09 hey all our brainfucking is strictly consensual 05:01:16 brainfucking and brickbraining too 05:01:53 Malbolge touched me in naughty places 05:02:01 malbolge is kinky 05:02:23 -!- monqy has left. 05:04:07 Astronomical twilight is of importance in this Dungeons&Dragons game now. 05:08:36 To win this game, we have to take advantage of everything, including the phase of the moon. 05:14:51 http://www.reddit.com/r/politics/comments/11cmsi/paul_ryan_admits_romney_win_would_lead_to_world/ if I ever needed any proof that Democrats can sensationalize things too 05:15:47 But everyone knows $other is evil, and $us is good! 05:16:07 And that's why I should be supreme overlord of everything. 05:16:16 I am your overlord! 05:20:47 I think there should be no supreme overlord of everything. But maybe some thing, OK 05:21:42 "There is no life, truth, intelligence, nor substance in matter. All is infinite Mind and its infinite manifestation, for God is All-in-all. Spirit is immortal Truth; matter is mortal error. Spirit is the real and eternal; matter is the unreal and temporal. Spirit is God, and man is His image and likeness. Therefore man is not material; he is spiritual." 05:21:52 Christian Science is weirder than I thought. 05:22:10 that's weird? 05:22:22 How is that Christian or science? 05:22:44 Beats me, but that's Christian Science for you. 05:24:04 Bike: Given that it suggests that *matter* is not *real*? Yeah, that's weird. 05:24:33 it's just platonism. 05:25:35 Most religious folk go for dualism. Y'know, where minds are magic. 05:26:16 or "spirits", here. 05:26:54 Eh. 05:29:56 Point is, it's gibberish that's either false or devoid of meaning, and I find it deserving of mockery. 05:30:21 * Sgeo finds anything that tells people to reject modern medicine as deserving of utmost hatred. 05:30:45 oh, go for it. I just meant that it's old and venerable 05:31:04 That Plato came up with it first doesn't mean shit. :) 05:31:11 quite. 05:31:22 Only silly people think Plato was actually right about everything. 05:31:50 He just managed to think about things before a lot of other people is all, really. 05:35:03 Some people are monism other are dualism, but my opinion is I think monism and dualism are both wrong. 05:35:56 What do you think is right? 05:38:06 I think the mind, matter, are one with the universe, so really everything is one with the universe, however, the universe itself is just mathematics, which includes things other than those which might be physical. All is mathematics. However, even the universe may be exist just because people observe, and yet the people exist because is part of universe, it is something like a causality loop. 05:39:19 Of course this is just philosophy, including of metaphysics and stuff like that, not reality. However, it is my opinion based on what I know about physics. 05:40:08 i think there's a bit turtle whose poop is planets 05:40:13 *big 05:42:33 Because if nothing exists, then something might exist there is nothing to make nothing to exist! As someone has said, they couldn't decide whether nothing or something to exist, so they decided to toss a coin. But to toss a coin, it has to exist, so the choice is already made for them. Something exists because something is a cheater. Of course this is all metaphorical, but the point stands. 05:44:02 This recording of the Dungeons&Dragons game (I have typed out the Oct.9 session today) contains footnotes such as "Why does Kjugobe's note have a reference to a footnote in this book?" 05:44:17 zzo38: That sounds essentially like philosophical materialism, combined with the idea that the universe is a lawful place, combined with the idea that the simulation hypothesis is valid, and the idea that that simulation doesn't really need to be *run* for the universe to exist in some sense. 05:44:29 ... Bit of a conjugation of ideas there, but eh 05:45:44 I think it is not a simulation, but mathematics. Some mathematics may be uncomputable. In addition, some equations may have multiple solutions or no solution. And then, there are even more complexities than this. It doesn't necessarily all correspond to physical objects, even though all is the same mathematics. 05:45:59 So they are the same as the ones that do. 05:46:28 So, let's sum that up a bit more cleanly. 05:46:49 "The universe can be expressed mathematically." 05:46:54 Yes. 05:47:11 That's... Basically materialism, isn't it/ 05:47:12 ? 05:48:00 I think it is like materialism but my ideas have some differences and more things too. But I don't know "materialism" exactly. 05:48:52 "Materialism" in the modern sense is more-or-less "All that is, is physics." 05:49:06 OK 05:49:19 (there's technically other sorts, but that's the sort most people really care about) 05:49:49 s/most people/most people who discuss ontology/ :P 05:55:41 -!- kinoSi has quit (Read error: Connection reset by peer). 05:56:08 -!- kinoSi has joined. 06:54:13 -!- epicmonkey has joined. 06:57:07 -!- nooga has joined. 06:59:15 -!- Bike has quit (Quit: (dyn)). 07:04:06 -!- mig22 has quit (Quit: mig22). 07:20:08 -!- epicmonkey has quit (Ping timeout: 245 seconds). 07:44:30 -!- mig22 has joined. 07:55:15 -!- KingOfKarlsruhe has joined. 08:01:18 -!- monqy has joined. 08:13:27 -!- zzo38 has quit (Remote host closed the connection). 08:18:18 -!- KingOfKarlsruhe has quit (Read error: Connection reset by peer). 08:22:42 -!- monqy has quit (Quit: hello). 08:42:18 -!- Phantom_Hoover has joined. 08:48:08 -!- epicmonkey has joined. 09:12:27 -!- ais523 has joined. 09:22:51 -!- ais523 has quit (Read error: Connection reset by peer). 09:23:04 -!- ais523 has joined. 09:23:49 so, randomly-walking brainfuck 09:24:03 I think that it's TC given arbitrary control flow (conditional goto is enough) 09:24:13 but it seems very difficult to convert that to [] loops 09:43:47 -!- ais523_ has joined. 09:43:48 -!- ais523 has quit (Read error: Connection reset by peer). 09:50:01 -!- Jafet has quit (Quit: Leaving.). 09:55:43 -!- kinoSi has quit (Read error: Connection reset by peer). 09:56:10 -!- kinoSi has joined. 10:06:13 -!- ais523_ has quit (Read error: Connection reset by peer). 10:06:19 -!- ais523_ has joined. 10:11:06 -!- Jafet has joined. 10:43:29 -!- ais523_ has quit (*.net *.split). 10:43:42 -!- kmc has quit (*.net *.split). 10:43:42 -!- Slereah_ has quit (*.net *.split). 10:44:31 -!- nortti has quit (*.net *.split). 10:44:31 -!- EgoBot has quit (*.net *.split). 10:44:31 -!- mroman has quit (*.net *.split). 10:44:31 -!- augur has quit (*.net *.split). 10:44:31 -!- oklofok has quit (*.net *.split). 10:44:31 -!- glogbackup has quit (*.net *.split). 10:44:31 -!- nooga has quit (*.net *.split). 10:44:31 -!- myndzi has quit (*.net *.split). 10:44:31 -!- atehwa has quit (*.net *.split). 10:44:31 -!- Gregor has quit (*.net *.split). 10:44:31 -!- Nisstyre has quit (*.net *.split). 10:44:31 -!- copumpkin has quit (*.net *.split). 10:44:31 -!- tswett has quit (*.net *.split). 10:44:31 -!- kallisti has quit (*.net *.split). 10:44:36 -!- lambdabot has quit (*.net *.split). 10:44:40 -!- pikhq has quit (*.net *.split). 10:44:46 -!- Jafet has quit (*.net *.split). 10:44:48 -!- yiyus has quit (*.net *.split). 10:44:52 -!- ion has quit (*.net *.split). 10:44:54 -!- Cryovat has quit (*.net *.split). 10:46:09 -!- heroux has quit (*.net *.split). 10:46:09 -!- sirdancealot7 has quit (*.net *.split). 10:46:09 -!- Deewiant has quit (*.net *.split). 10:46:09 -!- fizzie has quit (*.net *.split). 10:46:09 -!- TeruFSX_ has quit (*.net *.split). 10:46:09 -!- constant has quit (*.net *.split). 10:46:09 -!- epicmonkey has quit (*.net *.split). 10:46:09 -!- Sanky has quit (*.net *.split). 10:46:09 -!- jix has quit (*.net *.split). 10:46:09 -!- quintopia has quit (*.net *.split). 10:46:09 -!- FireFly has quit (*.net *.split). 10:46:09 -!- TodPunk has quit (*.net *.split). 10:46:09 -!- chickenzilla has quit (*.net *.split). 10:46:28 -!- kinoSi0 has joined. 10:47:11 -!- ais523_ has joined. 10:47:11 -!- glogbackup has joined. 10:47:11 -!- Arc_Koen has joined. 10:47:11 -!- Jafet has joined. 10:47:11 -!- ais523 has joined. 10:47:11 -!- epicmonkey has joined. 10:47:11 -!- nooga has joined. 10:47:11 -!- Nisstyre has joined. 10:47:11 -!- heroux has joined. 10:47:11 -!- sirdancealot7 has joined. 10:47:11 -!- copumpkin has joined. 10:47:11 -!- augur has joined. 10:47:11 -!- pikhq has joined. 10:47:11 -!- TeruFSX_ has joined. 10:47:11 -!- yiyus has joined. 10:47:11 -!- tswett has joined. 10:47:11 -!- kmc has joined. 10:47:11 -!- Slereah_ has joined. 10:47:11 -!- Sanky has joined. 10:47:11 -!- jix has joined. 10:47:11 -!- myndzi has joined. 10:47:11 -!- constant has joined. 10:47:11 -!- FireFly has joined. 10:47:11 -!- oklofok has joined. 10:47:11 -!- nortti has joined. 10:47:11 -!- atehwa has joined. 10:47:11 -!- Deewiant has joined. 10:47:11 -!- mroman has joined. 10:47:11 -!- EgoBot has joined. 10:47:11 -!- TodPunk has joined. 10:47:11 -!- ion has joined. 10:47:11 -!- quintopia has joined. 10:47:11 -!- lambdabot has joined. 10:47:11 -!- kallisti has joined. 10:47:11 -!- fizzie has joined. 10:47:11 -!- Gregor has joined. 10:47:11 -!- Cryovat has joined. 10:47:11 -!- chickenzilla has joined. 10:47:23 -!- ais523 has quit (Ping timeout: 272 seconds). 10:47:23 -!- ais523_ has changed nick to ais523. 10:47:25 Messy. 10:47:32 -!- glogbackup has left. 10:47:32 fizzie: through a NAT and the University's firewall? 10:47:32 ais523: It's what all the popups say. 10:47:32 -!- kinoSi has quit (Ping timeout: 240 seconds). 10:47:32 computers always send their IP whenever they contact anything, unless you spoof it (in which case you don't get a reply) 10:47:32 although "broadcast" is a little different 10:47:32 BROADCASTING an IP ADDRESS and HACKING, I tell you. 10:47:32 -!- ais523 has quit (Changing host). 10:47:32 -!- ais523 has joined. 10:47:32 That's better. 10:47:32 btw, both freenode and synirc were netsplitted at the same time 10:47:32 I wonder if it was for the same reason? 10:48:37 That's funny, IRCnet was slightly, too. 10:49:12 At least approximately at the same time; maybe it was slightly earlier. 10:49:14 13:38 -!- Netsplit *.pl <-> ircnet.eversible.com 10:49:33 Eversible is somewhere in the states (united), I believe. 10:50:01 fungot: You awake? I think you're connected to some us server too, right? 10:50:02 fizzie: i think she turned around but why? can i spend my time solving different kinds of numbers. i do. see: fnord/ fnord 10:50:30 Solving different kinds of numbers sounds like a reasonable hobby for a computer program. 10:51:33 yes 10:59:39 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds). 11:01:17 -!- ais523 has quit (Ping timeout: 256 seconds). 11:12:38 Ah ha, more splittery on the IRCnet side. 11:12:46 Someone must have it against IRC networks today. 11:19:53 -!- augur has quit (Remote host closed the connection). 11:27:07 -!- nooga has quit (Ping timeout: 245 seconds). 11:27:30 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 11:56:47 -!- augur has joined. 12:07:05 -!- boily has joined. 12:39:50 -!- Jafet has quit (Quit: Leaving.). 12:48:45 -!- nooga has joined. 13:21:57 -!- elliott has joined. 13:51:19 http://austriantimes.at/news/Around_the_World/2012-10-10/44722/Holy_Shit 15:06:52 always amusing when a food is labeled "96% fat free" 15:06:58 sounds better than "4% fat" 15:07:47 heh 15:08:34 It means you're only paying for 4% of the fat. 15:08:40 The rest is subsidized by the non-fat. 15:08:43 what a deal 15:10:04 elliott: @shachaf, I assume that you were referring to my answer (correct me if I am wrong). Yes it does copy the array first and then does the in-place shuffle, however, fixing this is simply exchanging thaw with unsafethaw 15:12:55 shachaf: If the implicit question is whether HaskellElephant ever says anything that makes sense, the answer is no. 15:13:37 Who's that? 15:14:25 Come on, you literally just quoted them. 15:14:43 Yes, but in the grander scheme. 15:18:02 -!- Phantom_Hoover has joined. 15:19:10 Some person who posts bad Haskell questions on SO. 15:19:12 shachaf: I like ilango's answer. 15:19:19 I like it so much I'm going to click the "delete" button on it. 15:19:45 You have magical delete powers? 15:20:52 yes. 15:21:01 Needs two more votes to make it happen though. 15:21:12 *Yes. 15:21:38 elliott: Memorized any good codepoints lately? 15:22:01 None. 15:23:06 I woke up before 08:00 today. 15:23:09 It's ridiculous. 15:31:21 I don't do that. 15:31:54 Ridicule? 15:33:18 Wake up. 15:33:33 I am awake. :-( 15:34:05 -!- zzo38 has joined. 15:35:27 -!- atriq has joined. 15:35:28 -!- AnotherTest has joined. 15:35:33 Hello 15:35:38 Hey 15:35:43 I also just got here 16:20:16 Is the HHGG TV series better than the movie? 16:21:46 is there a new tv series to go with the recent(ish?) movie, an old movie to go with the old tv series, or neither? 16:22:27 neither 16:22:47 ok, then I don't know because I haven't seen the tv series 16:23:05 but I think the movie can be watched in HD, so it must be better 16:27:47 The acting's a bit iffy 16:27:52 http://www.youtube.com/watch?v=ZMoi-nDd6cQ 16:28:52 the bbc h2g2 series is good 16:29:43 That's what I linked I think? 16:31:36 i think so too 16:32:10 I still think the acting's iffy 16:33:49 i don't remember anything about it, only that it was good 16:34:09 I think I like the book the best 16:40:20 I should probably buy And Another Thing at some point 16:41:40 -!- atriq has quit (Quit: Leaving). 16:48:28 -!- FreeFull has joined. 16:49:07 -!- augur has quit (Remote host closed the connection). 16:50:39 -!- mig22 has quit (Quit: mig22). 16:52:37 -!- augur has joined. 16:56:50 I think the reason I'm not laughing that much is because I pretty much know all the jokes 16:57:17 I bet there are plenty of new kinds of joke that would make you laugh 17:09:25 do you know that joke about the people who knew all the jokes? 17:10:12 there's a village somewhere where everyone knows all the jokes 17:10:42 in the local pub, occasionally someone exlaims "joke #46!" 17:10:55 and everyone would burst out laughing 17:11:19 but one day, a guy exclaims "joke #32!" 17:11:24 and nobody laughs 17:11:41 so that guy says "yeah, I've never known how to tell that joke." 17:17:35 -!- ssue has quit (Remote host closed the connection). 17:22:12 Try a number that is not in range 17:23:30 yeah that's a classic 17:23:43 they called it #67 17:25:14 And the fact that there were only 52 jokes when they declared that one #67 is, itself, #53. 17:36:24 -!- ogrom has joined. 17:37:33 -!- atriq has joined. 17:38:48 I mean something other than a positive integer. 17:39:11 I wonder if Bill Bryson reads Homestuck 17:39:24 zzo38: What if you try an unnameable real number? 17:40:32 zzo38, if they tried a number that is not a natural number, they'd get confused by your surrealist humour 17:40:44 2+7i is a very complex joke 17:40:59 -4 is a bit negative 17:44:16 (lim(x->infinity) 1/x) isn't very funny. 17:44:45 fwiw, my original statement was in the context of knowing the jokes used in HHGG 17:45:20 no-one respects context in here 17:46:20 No wonder Smalltalk isn't very well used in here; everyone disrespects thisContext. 17:46:59 hilarious Sgeo 17:47:11 I don't do smalltalk 17:47:17 Sgeo: ps what. who is bill bryson even. 17:47:24 not Smalltalk either 17:47:31 elliott, non fiction author who is currently in hexham 17:47:44 why is bill bryson in hexham 17:47:50 Beats me 17:47:51 elliott, why are you asking me who Bill Bryson is? 17:47:59 non-(fiction author who is currently in hexham) 17:48:06 oh 17:48:07 He is in Hexham for the single purpose of beating me 17:48:08 atriq said it 17:48:14 can you guys stop having nicks of the same length 17:48:21 ok the same length give or take one 17:48:22 4==5 17:48:36 -!- atriq has changed nick to atriqWhoIsTanebA. 17:48:42 atriqWhoIsTanebA: beating you at what 17:48:44 hey, none of us has the same nick length as any other participant 17:48:49 except them/ourselves 17:48:55 -!- atriqWhoIsTanebA has changed nick to atriq. 17:49:09 elliott, other definition of "beating" 17:49:13 If by participant you mean chatting person 17:49:21 atriq: ok 17:49:23 Because boily and augur have nicks length 5 17:49:32 GUYS 17:49:34 HEXHAM NEWS 17:49:34 http://www.hexhamcourant.co.uk/news/man-killed-by-falling-tree-1.1004001?referrerPath=news 17:49:35 I was only counting everyone after the "who is bill bryson even" line 17:49:48 Wait, Hexham actually exists? 17:49:57 Yeah 17:49:59 shachaf: no it doesn't 17:50:01 shachaf: no 17:50:06 `? hexham 17:50:09 even imaginary places have newspapers duh 17:50:16 Hexham is a European town. There are nine people in Hexham, and at least two of them are in this channel. Taneb looks after the ham. 17:50:31 -!- boily has changed nick to not5nick. 17:50:33 What's a Taneb? 17:50:50 A Taneb is kinda like an atriq, but younger 17:50:53 `? boily 17:50:56 boily may be French or something. We are not sure about the rest. 17:51:09 I'm not boily, because I don't have a 5-length nick :p 17:51:17 so wait 17:51:23 does everyone in the channel have a different nick length now 17:51:24 that's spooky 17:51:27 * not5nick is not sure about the effectiveness of his subtle camouflage 17:51:31 hi elliott 17:51:39 elliott: yes, everyone 17:51:53 I can only assume that log is not an everyone. 17:51:54 help 17:51:55 clog 17:51:55 @quote 17:51:56 JohnyBoy says: so have a nice goodspeed 17:51:59 But your username is given as "~boily" and I can see your NICK command above too 17:52:05 nice quote 17:52:13 zzo38: darn! foiled! 17:52:18 elliott and shachaf are the same length 17:52:20 aaaah 17:52:31 it's not completely obvious since the displayed nick lengths are rounded to the closest integer 17:52:33 This clearly means they are one and the same! 17:52:48 @quote 17:52:49 null says: = true 17:52:50 (swap! olsner inc) 17:53:00 @forget null = true 17:53:00 Done. 17:53:03 `addquote it's not completely obvious since the displayed nick lengths are rounded to the closest integer 17:53:03 @quote 17:53:04 butt2 says: "I'd butt linux on the butt, I'd like to give buttad a try" 17:53:06 871) it's not completely obvious since the displayed nick lengths are rounded to the closest integer 17:53:08 Sgeo: swap!? 17:53:09 atriq: Not only are "elliott" and "shachaf" the same length, but so are the usernames and cloaks 17:53:18 Hence Hexham is in Finland, hence I'm in Finland! 17:53:22 im shachaf 17:53:45 I released version 5 of FurryScript with a few bugfixes, and added documentation for some commands: RSC ALL GEN ARG TR TR- TRB TRB- REX REX- REX+ RNG LAH 17:53:55 elliott: no im shachaf!!!!!! 17:54:21 olsner, Clojure. If olsner is an atom, it atomically changes what the atom contains to (inc @olsner) 17:54:24 were shachaf 17:54:45 http://docs.python.org/library/doctest.html is cute 17:54:47 elliott: You turn into shachaf at the full moon? 17:54:53 Darnit 17:54:56 kmc: It is. 17:54:58 atomically changing an atom, that sounds good 17:55:00 * Sgeo was going to say that but in a worse way 17:55:05 10:55 The Moon is Waning Crescent (10% of Full). New moon in NetHack in 2 days. 17:55:26 but what's (inc @olsner)? 17:55:39 Good things then, I have the phase of moon and all ephemeris of all planets in my computer. 17:55:41 olsner incorporated? 17:55:53 @ is a bit of reader syntax that will expand to (deref olsner) 17:55:58 Which are the phases of the moon that are viewable mid-afternoon 17:56:04 I'm overthinking a song I heard once 17:56:16 why do I need to be dereffed before incorporation? 17:56:22 -!- variable has joined. 17:56:27 (inc 5) ; 6 17:56:39 (deref (atom 10)) ; 10 17:56:59 atriq: I don't know, maybe half moon? 17:57:19 zzo38: Maybe a Zork Zero Moon. 17:57:21 Remember Zork Zero? 17:57:24 With the moons? 17:57:34 -!- epicmonkey has quit (Ping timeout: 240 seconds). 17:57:40 Which half moon! 17:57:52 The inner half. 17:57:59 olsner: how is your os 17:58:30 elliott: no news 17:58:30 I have seen the Zork calendar, with various strange phase of moon 17:58:46 Dimwit's Birthday Observed. 17:59:13 Every Thursday, yes... But it is Friday today. 17:59:25 Aaah, a waxing moon 18:00:11 iirc, I was last setting up some boring stuff that'd allow running specific test-case programs on a fresh-booted kernel with qemu 18:00:21 zzo38: No, Zork Zero is shifted by one day. 18:00:46 oh, and that either requires qemu built from git because some stuff is broken, or a bunch of boring workarounds in my code 18:00:54 shachaf: O, is that because of the different leap years? 18:01:19 zzo38: Uh, I guess. 18:01:23 I was just making things up. 18:01:26 In the mid-afternoon perhaps the sun is in the 8th house, so perhaps the moon would be in the 11th house then, so it would be waxing half moon, if visible in the mid afternoon. 18:02:02 (Since they move counterclockwise around the zodiac) 18:02:20 (that is, forward.) 18:04:07 I think clockwise is forward, zzo38. 18:04:13 Have you ever looked at a clock? 18:04:46 On a clock, yes, clockwise is forward. However, on a horoscope, the angle increases counterclockwise. 18:04:57 -!- Gregor has set topic: BEWARE THE Ø̈RJANIST MØ̈Ø̈SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://esolangs.org/wiki. 18:05:07 (that is, ecliptic longitude) 18:05:36 -!- zzo38 has set topic: BEWARE THE RJANIST MSE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:05:42 Ø̈ 18:05:54 Ø̈Ø̈Ø̈ 18:05:59 Oops I forgot one letter 18:06:13 -!- zzo38 has set topic: BEWARE THE ORJANIST MOOSE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:06:24 Oops I forgot the slash 18:06:37 Ø̈h nø̈. 18:07:00 organist moose, now that's a sight 18:07:20 -!- Gregor has set topic: I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:07:23 beware the onanist moose 18:07:26 Womp womp. 18:07:40 why are the channel logs now naked grandmas? 18:07:42 what, no zardoz? 18:07:52 -!- zzo38 has set topic: BEWARE THE O/RJANIST MO/O/SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:08:02 kmc: shadyurl.com = best URL shortener 18:08:14 zzo38: Why did you duplicate the log link in the topic? 18:08:17 haha 18:08:28 oh, and someone should make a new zardoz joke 18:08:29 Why does MyWOT dislike 5z8.info 18:08:37 elliott: I did not duplicate it. Now you have both the picture and text logs. 18:08:43 fsvo "joke" 18:08:44 the .jpg isn't a picture 18:08:54 Sgeo: What's a MyWOT? 18:08:56 you're too biased to windows-centric file extensions, zzo38!! 18:09:00 It's a Clojure thing, isn't it? 18:09:11 Well, I didn't look so I don't know, I just know that .jpg is usually a picture (regardless of operating system). 18:09:15 Clø̈jure 18:09:41 -!- Gregor has set topic: BEWARE THE O/RJANIST MO/O/SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | ZARDOZ created ZARDOZ; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://esolangs.org/wiki. 18:09:42 zzo38: @ uses .jpg to hold filesystem metadata. 18:09:53 someone should've made that link point to naked grandmas after people had been taught it was just a link to the logs 18:10:35 Dear god 18:10:41 Bluh, shadyurl doesn't like data URLs 18:10:49 (URIs) 18:10:53 I'm analysing a song from a children's TV show completely out of context 18:11:19 Sgeo: Then don't use shadyurl, if it doesn't like data URLs. 18:12:09 -!- zzo38 has set topic: BEWARE THE O/RJANIST MO/O/SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | God made the natural numbers; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:12:19 Hay why did you remove the log 18:12:43 -!- zzo38 has set topic: BEWARE THE O/RJANIST MO/O/SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | ZARDOZ created ZARDOZ; all else is the work of ZARDOZ | Channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | http://codu.org/logs/_esoteric/. 18:12:53 zzo38 has a serious case of Not Getting the Joke, even though the joke was inspired by him. 18:13:01 zzo38, because it was there, but just looked different 18:13:42 shachaf, Web of Trust thingy, people vote on whether domains are suspicious or not 18:13:54 Sometimes people suck, but I do tend to rely on it 18:14:05 5z8.info is very suspicious. 18:14:11 That's not even a valid z-encoding! 18:14:23 xn--5z8.info 18:14:43 http://www.mywot.com/en/scorecard/geocities.com 18:15:06 Just ... read the comments 18:15:10 Well, it is a redirect but not a very good one, it says "expected /hookers_j0l4yf_nakedgrandmas.jpgsplit Arrayshort hookers_j0l4yf_nakedgrandmas.jpgQUERYhookers_j0l4yf_nakedgrandmas.jpg" on it! 18:15:30 -!- augur has quit (Read error: Connection reset by peer). 18:15:43 searching for z-encoding gave me "Zen Coding is a set of plug-ins for text editors that allow for high-speed coding and editing in HTML, XML, XSL, [...]" 18:15:52 -!- augur has joined. 18:16:01 but to be fair, the second hit was the ghc commentary 18:16:29 “Zen” and “XML” should not be allowed in the same sentence. 18:16:40 Then fix it to use xn--5z8.info if you think 5z8.info is no good 18:16:50 Except to say “those who have written XML can never achieve Zen.” 18:17:00 Gregor: Are you sure? 18:17:08 Quite. 18:17:19 https://www.mywot.com/en/scorecard/www.quote-egnufeb-quote-greaterthan-colon-hash-comma-underscore-at.info 18:17:23 I thought the path to Zen was avoiding Zen 18:17:35 Sgeo: wat 18:17:36 Where does it get the value from? I doubt someone's actually voted for that 18:18:23 it's almost as if you can't trust web of trust 18:19:14 ...I'm analysing a Eurobeat fansong of a children's TV show 18:19:16 It's also got a higher score than the more normal domain name https://www.mywot.com/en/scorecard/www.phlamethrower.co.uk 18:19:17 -!- Phantom__Hoover has joined. 18:19:38 NOW I MUST LEAVE FOREVER OR AT LEAST UNTIL PROBABLY TOMORROW EVENING 18:19:39 -!- atriq has quit (Quit: Leaving). 18:19:50 Even though in the latter case it claims to know where the server is, unlike the former 18:22:46 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 18:28:57 -!- Phantom__Hoover has quit (Ping timeout: 256 seconds). 18:35:39 Maybe someone did vote for it 18:36:17 The plugin doesn't really do exact numbers 18:36:26 yeah all those befunge haters on the internet 18:37:01 -!- zzo38 has set topic: BEWARE THE O/RJANIST MO/O/SE | I, for one, welcome our new hash function overlords | E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E1565E03EBF2 | ZARDOZ created ZARDOZ; all else is the work of ZARDOZ | New channel logs: http://5z8.info/hookers_j0l4yf_nakedgrandmas.jpg | Old-style channel logs: http://codu.org/logs/_esoteric/. 18:37:16 i am arthur frayne, and i am zardoz 18:38:03 -!- augur has quit (Remote host closed the connection). 18:38:22 i see "MOH/OH/SE" where the H's are reverse video which I guess means they are ^H? 18:38:23 i am not zardoz 18:38:41 I just see MO/O/SE 18:38:47 oh i get it 18:39:09 kmc: They are supposed to be backspace 18:39:12 ah, that thing where you use backspace to put characters on top of each other? 18:39:49 My computer shows them black-on-purple on the screen, but displays the slashed O properly on the printout. 18:40:01 For me it just says MO/O/SE 18:40:01 do you print out hardcopy logs of IRC? 18:40:09 (I mean the "H" with black on purple; the rest of the text in blue) 18:40:17 kmc: Sometimes. 18:40:23 kmc, you don't? 18:40:24 kmc: yes, and then he OCRs them and puts them on gopher 18:40:26 lol 18:40:29 yes 18:40:40 at one point i had a dot matrix printer as my linux system console 18:40:56 to diagnose a bug which crashed the graphics card 18:41:05 it slowed down the boot process quite a bit 18:41:51 Did you connect to IRC? 18:41:57 not on the printer 18:43:47 but why would you use an actual printer instead of e.g. connecting a null modem cable to another computer? 18:44:44 Reaching the billionth decimal digit of pi could help technologists and mathematicians because they can use the equation to create random number sequences. Random numbers are a driving force behind computer security, including everyday consumer-level protections, like in electronic banking. 18:45:00 because i didn't have another computer 18:45:25 or didn't have a null modem cable, or something 18:45:28 i don't remember exactly 18:45:54 more recently i have used netconsole for this 18:46:10 Can ARCFOUR be used for random number generator, though? 18:46:30 kmc: but you did have a dot matrix printer? 18:46:30 I don't think pi is best for random number since pi is always the same for everyone. 18:46:51 zzo38: The question is whether your computer is fast enough to compute it farther than anyone else. 18:46:56 olsner: yes 18:47:07 That's why we build supercomputers. 18:47:22 kmc: ok 18:47:32 RC4 has been used in some BSDs as (part of) a random number generator, IIRC. 18:47:40 shachaf: What you have to do is to make the computer reprogram its own hardware to calculate billion digits of pi 18:48:38 * shachaf likes the idea of a world where randomness is a scarce resource that has to be mined and such. 18:49:20 Deewiant: As part of? What other part did they use, then? 18:49:25 I guess the idea of people who carry one-time pad data is related. 18:49:39 uh, that's weird 18:50:15 http://samuelhughes.com/boof/ has "If the end-of-file character has been input, outputs a zero to the bit under the pointer." as part of the description of the ; (output) instruction 18:50:19 zzo38: I don't know, that's why it was in brackets. Perhaps it was the whole thing and there were no other parts. 18:50:43 do you think it's just a mistake and should be part of , (input) or is it some special feature? 18:51:20 shachaf: hmm... but the tricky part about one-time pad data is that you need the same randomness in two places, not that you need to collect a bunch of random? 18:52:41 olsner: Right, it's not the same thing. 18:53:36 in this randomscarce world of yours, would one random bit be a reasonable christmas present? 18:53:54 Deewiant: As it turns out, Famicom Hangman uses not only RC4 but also fails to initialize i and j (so it uses whatever happens to be in RAM at power on) and uses the microphone, and it runs several times per frame until the space-bar is pushed. 18:54:08 A friend and I once collected a CD's worth of random, to be used as a one-time pad in conjunction with an irssi script. 18:54:15 olsner: Only if kept it wrapped. 18:54:19 Sadly, it never really got used. 18:54:55 shachaf: no, you unwrap it to see that it's a random bit box, then you need to open that box to use the random bit 18:55:04 (It still appears to work fine even without a microphone; but it uses the microphone if it is available.) 18:55:05 it could be some kind of single-use electronic device too 18:58:07 Deewiant: Are you sure they wouldn't add microphone and that stuff to the random numbers too, if such things would be available? 18:58:11 if you don't disclose whether it's previously used or not, does that give you another bit of random? 18:59:48 -!- augur has joined. 19:01:15 shachaf: also, what happens if you roll a dice too often in this world of yours? 19:01:24 zzo38: I don't know. 19:01:28 olsner: A die? 19:01:39 A is an integer number of dice 19:01:52 Clever. 19:02:15 If you need to use a dice for encryption, maybe you should use a casino dice and make sure to rull against the wall 19:02:28 dice: the gift that keeps on giving random numbers 19:03:23 maybe in shachaf's world the physics of dice rolling is just very easily predictable 19:03:50 even in our world you can learn to throw a die to a particular side 19:03:58 yeah, or maybe dice roll slower and slower as their random supply runs out 19:04:15 I read about a "quantum dice" which always rolls doubles when rolled together, but act like regular dice when thrown individually. It probably doesn't exist; they just wanted to describe it. 19:04:36 Maybe everyone knows the entire state of the world at any point. 19:04:54 Except for the inside of their brain, which starts out deterministic but gets seeded with random data. 19:05:33 brains are the only sources of random data? 19:05:59 wouuuw I wrote exactly one fourth of the truth-machine implementations on the truth-machine page 19:06:15 (this is a placeholder for some kind of pun about zombies) 19:09:11 Remeber to go back and replace it with the actual pun some day. 19:09:12 How can brains be the only sources of random data, it is like physical like anything else? It must follow the same laws, although there is possibliity to cause different results just as mathematical functions can give different outputs by the different inputs. 19:09:15 -!- epicmonkey has joined. 19:09:37 -!- ogrom has quit (Quit: Left). 19:09:58 fizzie: feel free to remind me, but I'm good at neither puns nor zombies 19:10:53 maybe oerjan or funpuns can fill it in later 19:11:29 olsner: I seem to recall joke #32 was about zombies 19:11:32 Brains don't really depend on quantum effects for operation any more than a rock does 19:11:33 Arc_Koen, I wonder if I should try implementing in in $current_preferred_language 19:11:51 never heard of that language 19:11:57 but yeah, you should 19:12:25 Although most of these implementations are in esolangs 19:12:32 FreeFull: Well, yes, but rocks are simpler so the result is generally the same as anything. However, everything will depend on quantum effect, I think. 19:12:45 Including rock. 19:12:54 zzo38: That is part of my point 19:13:05 It must, since it is the same law of physics! 19:16:01 Sgeo: well, maybe we could add one in C in the intro 19:16:07 -!- AnotherTest has quit (Quit: Leaving.). 19:16:19 that could be clearer that the current pseudo-code 19:16:57 -!- ssue has joined. 19:17:13 How about haskell 19:17:41 Just write it in whatever you want; whatever is the clearest can be linked to from the intro, I suppose. 19:20:20 I'm thinking C is just a bit old, therefore doesn't have some of the convieniences =P 19:26:04 I think also that the I/O of FurryScript is not good enough to make truth-machine since it can only make input at beginning and output at the end. Possibly with lazy evaluation it could be done, but the current implementation does not use lazy evaluation. 19:26:34 it's the same problem with Kipple and a couple other languages 19:26:52 Squihy2K 19:27:22 http://esolangs.org/wiki/Truth-machine#Squishy2K 19:29:24 -!- Phantom__Hoover has joined. 19:29:49 -!- constant has quit (Quit: I found 1 in /dev/zero). 19:32:16 -!- zzo38 has quit (Remote host closed the connection). 19:34:32 -!- NihilistDandy has joined. 19:41:24 -!- not5nick has changed nick to boily. 19:57:37 -!- jiella has joined. 20:02:33 -!- NihilistDandy has quit (Quit: ["Textual IRC Client: www.textualapp.com"]). 20:29:18 -!- epicmonkey has quit (Ping timeout: 245 seconds). 20:29:32 OMG, I just realized that it is my destiny to create a web technology called AppleJAX. 20:44:56 :/ ponies 20:46:22 HELL 20:46:23 YES 20:46:24 PONIES 20:47:25 Gregor: :D 20:49:07 -!- Gregor has changed nick to Poniest. 20:49:16 Did somebody say “HELL YES PONIES”?! Yeah, I did! 20:49:29 :P 20:50:48 "Several languages exist which are based on rewriting strings, the most well-known being Thue." 20:50:49 anyone who understands what this does gets a virtual cookie: main(){char a[256],*b,*c[256],**d;int p;while(1){write(1,"$ ",2);for(b=a;*(b-1)!='\n';b++){read(0,b,1);}*b=0;d=c;*d++=a;for(b=a;b I thought it should be "the best-known being Thue" 20:51:03 bonus point to the first one who finds the buffer overflow 20:51:23 nortti: am I allowed to compile it? 20:51:28 no 20:51:47 or at least copy it into a text file and add proper indentation 20:51:51 yes 20:52:03 nortti: Is it cheating if I copy-paste it into a text editor and make it more readable? =P 20:52:09 no 20:52:24 there seems to be a suspicious fork() and execvp() in there. 20:52:25 don't forget that there is 1 space in there 20:53:00 *d++=a 20:53:07 what the heck of a way to code is that 20:53:36 Uhhh, that's pretty conventional. 20:54:10 uh, I don't know fork() or execvp 20:54:11 void strcpy(char*a,char*b){while(*b)*a++=*b++;*a=0;} 20:55:03 Arc_Koen: those are unix syscalls like read and write you should notice in there 20:56:00 hum, right, I don't know read and write either 20:56:07 I guess man will help me 20:56:11 yes 20:56:28 consult your nearest man page 20:56:36 well hum there is a builtin read function in the shell OF COURSE so it won't show me the C one 20:56:48 man man will tell me how to do that maybe 20:56:51 use man section name 20:57:27 in this case man 2 read 20:57:36 I can do that? 20:57:39 yes 20:58:08 wait, it tells me you have to #include a bunch of stuff 20:58:14 therefore your program should not work 20:58:20 why? 20:58:36 because there are no #includes in your program 20:58:48 I didn't need includes with unix v6 and I don't need then mow 20:59:07 and it only needs size_t 20:59:45 and as you see only a literal is used there 21:00:41 so following bad coding practices I left the #include out bcause I wanted to fit it in one line 21:03:58 -!- boily has quit (Quit: Poulet!). 21:06:36 in C if a function is not declared it is assumed to exist with an int return type and an arbitrary number of int arguments 21:06:39 or something? 21:06:55 it's more complicated than what I just said, I'm sure 21:07:46 anyway nortti i'm guessing it's a shell 21:07:52 i think you showed us before 21:08:10 There are specific rules regarding the default types of the parameters given the arguments, with the implication that those same types have to be compatible if you later give it a proper prototype. 21:08:13 also the write(',"$ ",2); and fork and execvp are good clues 21:09:04 but your shell does not do job control! 21:09:23 * nortti gives kmc a virtual cookie 21:09:36 now find the buffer overflow 21:09:51 well there are only so many places it could be :) 21:11:59 You never allocate a space for c 21:12:02 That can't be good 21:12:24 what do you mean? 21:12:35 >char a[256],*b,*c[256],**d 21:12:56 A pointer to a 256 char array 21:13:22 Unless I'm reading it wrong and it's a 256 array of char pointers 21:13:26 no it's the latter 21:13:36 Ok, nevermind then. 21:13:37 cdecl> explain char *c[256] 21:13:37 declare c as array 256 of pointer to char 21:13:42 <3 cdecl 21:14:08 Maybe I should get cdecl then =P 21:14:14 FreeFull: do you understand what pointers are put in c? 21:14:30 Let me look 21:14:37 -!- Phantom_Hoover has joined. 21:14:38 "*d=b+1;d++;" could be replaced with "*d++=b+1;" for extra obfuscation 21:14:53 hmm. missed that for some reason 21:14:57 you 21:15:01 you did it somewhere else aleady 21:15:02 already 21:15:04 * kmc can't type 21:15:06 but the aim is not to obfuscate 21:15:09 sure 21:15:20 it is just compact it 21:15:21 there is a difference between compact code and obfuscated code 21:15:22 yes 21:15:45 You could get rid of d and replace all occurences of it with c and it'd still work, right? 21:15:55 -!- carado has joined. 21:16:02 Actually no 21:16:03 char*a,b[9999];main(){gets(a=b);while(*a){a+=(b[*a]-=b[a[1]])?3:a[2];}puts(b+1);} 21:16:06 Because you d++; at one point 21:16:08 ^^ 21:17:05 nortti: Pointers to chars in a, right? 21:17:16 -!- Phantom__Hoover has quit (Ping timeout: 256 seconds). 21:17:24 also there is no way to exit the shell :D 21:17:24 FreeFull: yes 21:17:48 * nortti gives some extra points to kmc 21:18:02 forgot to include that in the puzzle 21:18:09 of course that would be as easy as if(!read(0,b,1))return; 21:18:11 is there a unix shell that emulates command.com? (or cmd.exe?) 21:18:17 Can't you ^C =P 21:18:28 yeah 21:18:39 yeah because it doesn't do job control ;P 21:18:54 but any other way than abusing it not handling signals 21:21:58 if no one finds the buffer overflow in 10 minutes I'm going to reveal it 21:23:21 it's just that long command lines will overflow 'a', right? 21:23:27 yes 21:30:43 * nortti gives kmc bonus points 21:34:31 oh, that was a boring one ... gets is an automatic buffer overflow 21:36:40 Mine has gets, not his. 21:38:08 ok 21:42:49 what does yours do Poniest 21:43:13 Don't feel like guessing, eh? X-D 21:43:23 well i ran it but it wasn't particularly enlightnening 21:43:33 You'd need very carefully-constructed input to use it. 21:43:45 It's an interpreter for a TC subleq-like language. 21:44:00 Although it is not itself TC since the memory is fixed at 9999 bytes. 21:45:42 -!- jiella has quit (Quit: Leaving.). 21:45:54 what a coincidence, my computer is also not turing complete :) 21:47:08 you can build a turing machine by making an EC2 instance which upgrades its own storage when necessary, and also has an endowment in government bonds or something, which will eventually cover the costs of additional computation 21:48:03 -!- carado has quit (Ping timeout: 245 seconds). 21:48:22 of course when amazon goes out of business you are still screwed :( 21:49:37 not if the machine moves to another internet fluffy weather thingy 21:49:37 I like how you blindly ran unreadable C code, btw. 21:50:07 it's ok, he probably ran it as root so it couldn't touch his user data 21:50:48 *nodnod* 21:51:17 it's not unreadable 21:51:30 i couldn't tell exactly what it does but i was fairly confident that it wouldn't do anything too nasty 21:51:49 the only system-ish calls are gets and puts 21:51:59 and it's too simple to be constructing a nasty payload and buffer overflowing it, or anything like that 21:52:04 though really 21:52:11 i am interested in how well you can hide these things 21:52:30 i want to run a contest kind of like http://underhanded.xcott.com/ 21:52:33 but more open-ended 21:55:45 kind of like ioccc but for malicious programs? 21:56:20 kind of, yeah 21:56:36 * Sgeo thinks that Lisps might be good for that because as far as I understand, indentation is crucial for readability, so false indentation might be able to trick readers, I think 21:56:44 for the most part programs in ioccc are obviously very hard to understand 21:57:02 i'm interested in programs which look like very straightforward implementations of one thing, but actually do some other malicious thing 21:57:08 oh, except that instead of inscrutable they should look harmless 21:57:10 there are a few IOCCC winners like that, though 21:57:12 yeah 21:57:24 also, it's easy to make a progra 21:57:25 I recall some Java-like thing 21:57:25 er 21:57:34 also, it's easy to make a program with a deliberate subtle security hole 21:57:43 but that's not so interesting either 21:58:01 so it's hard to delineate exactly what i'm looking for 21:58:21 leave it to the judges? :) 21:58:26 yeah :) 21:59:13 i started writing up guidelines 21:59:26 'Your program should conceal the malicious behavior from the user for as long as possible. It's especially impressive if you can make it look like an honest mistake even after it's been uncovered.' 22:00:00 kmc, that underhanded thing, were the submissions ever shown/judged? 22:00:04 For the airline one 22:00:09 not sure 22:00:14 i think not for that iteration of the contest 22:00:19 some previous years are on there though 22:01:19 i'm particularly interested in what psychological tricks you can play to make someone shrug and say "eh, this code is probably ok" 22:01:19 I think the underhanded contest was a bit boring because you had to solve one specific problem and make a specific kind of malicious behavior 22:01:23 yeah 22:01:25 i agree 22:01:30 -!- carado has joined. 22:05:39 actually, I think this kind of program goes well in the ioccc 22:06:32 although they might be surprised to get submissions that don't look obfuscated at all 22:07:06 also might be pissed if they try your program and it does something evil 22:08:10 It would be just fine to /tell/ them it does something evil. 22:08:26 In a way it's not similar to that submission that #defined a bunch of stuff to make Java-looking code run. 22:08:31 *not dissimilar 22:08:40 And in a way, it's not similar ^^ 22:14:18 -!- augur has quit (Remote host closed the connection). 22:14:58 yeah 22:15:06 my contest would definitely not be limited to C, though 22:15:18 i think a lot of different languages have a lot of different interesting ways to hide shit 22:15:56 i want to see a LaTeX document class that steals your SSH private key 22:16:16 to recover the key, the attacker has to print out the document and soak it in lemon juice 22:16:44 -!- Phantom__Hoover has joined. 22:18:23 "Note that some really nasty security holes result from similar acts of syntactic cleverness. Probably the biggest example is the format specifier bug, which exists because a zillion programmers think that writing printf( string ) instead of printf( %s, string ) is kinda neat." 22:20:05 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 22:26:05 oh I had never thought of writing printf(string) 22:26:08 thank you so much 22:26:25 X-D 22:33:52 -!- carado has quit (Quit: Leaving). 22:34:26 first thing in gitit user's guide: "Gitit is a wiki program written in Haskell. It uses Happstack for the web server" 22:34:37 cause if there's anything users care most about, it's what language and web framework was used to implement the site 22:34:55 gitit is pretty cool though 22:38:45 i like that i can download any page on my wiki as a LaTeX document, man page, or S5 slideshow 22:39:04 for that "not three shits were given" presentation look 22:44:49 -!- augur has joined. 22:57:51 it better not give you one of those LaTeX documents that steals your SSH private key 22:58:50 -!- Poniest has changed nick to Gregor. 22:58:53 Oh, it does. 22:58:58 Even the S5 presentation does. 22:59:18 * ion saved an idea for a rhythm in glorious General MIDI. http://heh.fi/tmp/test-20121013.midi 22:59:40 I suppose the man page does too 23:01:13 ion: how do i play general midi on linux again 23:01:45 elliott: xdg-open http://heh.fi/tmp/test-20121013.midi 23:01:54 i mean 23:01:56 hah, as if that would work 23:01:58 My estimation of that working: 0% 23:02:01 what player do i need to install for midis 23:02:03 Worksforme™ 23:02:04 *estimated chance 23:02:11 elliott: Totem plays it on my system. 23:02:21 What’s your default media player? 23:02:25 ion: … do you have a hardware MIDI synth? 23:02:28 no 23:02:47 Then your distro must configure timidity or fluidsynth as an alsa server by default, I suppose. 23:02:52 nope 23:03:02 pfft, totem 23:03:04 all these modern conveniences 23:03:20 oh, xdg-open opened the link in my browser, upon which my browser is offering to open the file using xdg-open 23:03:34 Try that 23:03:36 The answer is not “it's magic”, ion, there exists a sequencer somewhere X_X 23:04:07 I blit into the framebuffer just right and tune an AM radio to my monitor. 23:04:08 chockingly, I don't have a midi player installed 23:04:12 elliott: gst-launch-0.10 filesrc location=test-20121013.midi ! decodebin ! alsasink 23:04:28 apparently i actually have gstreamer 23:04:29 Then your distro must configure timidity or fluidsynth as an alsa server by default, I suppose. 23:04:31 but i doubt that will work 23:04:35 i have no midi synthesiser installed 23:05:19 This seems to be the thing it uses. /usr/lib/x86_64-linux-gnu/gstreamer-0.10/libgstwildmidi.so 23:05:41 oh wow, xdg-open's list of candidates lists 11 copies of Internet Explorer 23:05:57 It came from gstreamer0.10-plugins-bad 23:06:33 wildmidi, never heard of it. Uses GUS patches though, so it's shit. 23:06:43 elliott: http://codu.org/webmidi/ 23:06:46 what is gus 23:06:57 webmidi doesn't accept a url, worthless 23:07:12 derp, and I forgot to uncheck the "always use this program" thingy, so now all midi files open with internet explorer 23:07:19 lul 23:08:14 http://codu.org/webmidi/gen/22676115734515/22676115734515.ogg 23:08:19 (I don't seem to have IE installed) 23:09:28 i like how tinny this sounds 23:10:46 anyone remember the algorhythm thing 23:10:55 imo ion should generate a melody for thar rhythm with it 23:11:18 I’ll generate a melody using the algorithms in my wetware. :-P 23:11:38 no 23:11:40 humans are insufficient 23:11:54 nothing surpassed the algorhythms 23:12:06 elliott: GUS is a well-renouned sound card from the age before such things were standard equipment built into every PC 23:12:12 i forget what Gregor's really good one was called 23:12:15 olsner: oh gravisis 23:12:17 it had buffers and samples and fancy stuff 23:12:34 http://heh.fi/tmp/test-20121013.pdf 23:12:52 http://codu.org/masterpiecemachine/mp/Onerously%20Uptight%20Toccata this one 23:12:53 elliott: Onerously Uptight Toccata. 23:12:57 Gregor: please add a link that automatically webmidis it 23:12:59 so i can listen to it 23:13:13 elliott: http://codu.org/music/auto/Onerously%20Uptight%20Toccata.ogg 23:13:16 "Type: Masterpiece" 23:13:19 But I'll bear that in mind for this weekend and/or never. 23:16:12 i can't find the ones i made RIP 23:16:19 well i remember http://codu.org/masterpiecemachine/mp/Onerous%20Cake-Eating%20Festival%20Disallowment%20Barricade 23:16:23 but i forget what it sounds like because there's no ogg link 23:16:49 Womp womp. 23:17:11 First world too-lazy-to-just-download-it-then-upload-it-to-webmidi problems. 23:17:33 Gregor: http://codu.org/webmidi/gen/228332553116545/228332553116545.ogg doesn't work 23:17:40 http://codu.org/webmidi/gen/228332553116545/ 23:17:49 Well, I can't figure out why, as I'm at work, so nya ^^ 23:17:54 http://codu.org/webmidi/gen/228332553116545/log.txt 23:17:56 yes you can there's a log 23:18:03 Oh 23:18:09 Uh 23:18:13 That's an unhelpful log ^^´ 23:19:24 now i'm trying with chorium 23:19:26 but it's stuck as "queued" 23:19:31 http://codu.org/webmidi/gen/2288519420303/ 23:20:08 The queue isn't based on webmidi submissions, it's based on system load. 23:20:21 Webmidi is always prioritized lower than… just about everything else :) 23:20:36 ok now it finished and spat out a 0 second file 23:20:42 fuk this 23:21:16 i think this "Roe v_ Wade As An Analogy For Temperature" one is mine 23:21:54 Gregor: btw fluidsynth: warning: Failed to pin the sample data to RAM; swapping is possible. 23:21:55 this seems bad 23:22:07 It's irrelevant for rendering to a file. 23:22:23 http://codu.org/webmidi/gen/22981154128959/22981154128959.ogg this is amazing 23:22:24 And infrequently an issue even for live playback. 23:23:09 i think this may be the best thing i have ever made 23:23:54 And you didn't even make it. 23:23:55 *tsk tsk* 23:24:16 sure i did 23:28:06 A couple weeks ago I drove by a place called “Beverages and More”. I thought to myself, “what a bizarre niche”, and drove on. 23:28:19 Today I realized, of COURSE a place called “Beverages and More” would have Moxie. 23:28:28 In retrospect, I am a fool :'( 23:28:44 But in prospect, I will soon have Moxie! 23:29:06 elliott: your .ogg file sounds like it runs four times too fast 23:29:38 Arc_Koen: maybe you run four times too slow 23:29:42 how about this http://codu.org/webmidi/gen/23051228304267/23051228304267.ogg 23:30:39 also four~five times too fast 23:30:48 gonna go with you being too slow on this one 23:30:51 there might be something wrong with my player 23:31:38 does http://codu.org/music/auto/Onerously%20Uptight%20Toccata.ogg sound too fast 23:31:42 (it's meant to be 160 bpm) 23:32:11 yup 23:32:34 it's not just the sound - my player actually displays the time and every second it's incremented by 4 or 5 23:51:44 kmc: Any talk of extracting the interesting part of mosh into a library? 23:58:22 people talk of it, yes 23:58:29 by "the interesting part" do you mean the state sync protocol? 23:58:44 Yes. 23:59:28 well, it is already sort of a library 23:59:41 it lives in its own directory in the mosh source tree 23:59:47 and has a reasonably clean if completely undocumented interface 2012-10-13: 00:00:08 "Distributed as source code in a pre-extracted tar file" 00:00:10 KeithW is using it also for his awesome dynamic bitrate inferential flow control videoconferencing thingy 00:00:14 https://github.com/keithw/alfalfa 00:00:26 i think this may have started as a complete copy of the mosh repo... 00:00:32 but now it's a videoconferencing program 00:00:49 slash an academically relevant demonstration of something that could be turned into a videoconferencing program 00:00:51 The same SSP protocol! 00:01:29 yeah 00:01:34 I hope that's what SSP stands for. 00:01:38 er, with one modification 00:01:50 i forgot which though 00:02:22 supplemental super proteins 00:02:42 'The major modification we made to SSP to support Alfalfa is that in Mosh, “diff” and “patch” are round-trip operations, so the protocol is lossless. In Alfalfa, the “diffs” are lossy and the available length for a diff varies according to Sprout’s forecast window size.' 00:03:07 -!- sivoais has quit (Ping timeout: 244 seconds). 00:03:24 presumably you then re-apply the lossy diff locally, so that errors don't accumulate 00:03:52 here "diff" = MPEG-2 P-frames 00:04:20 -!- nooga has quit (Ping timeout: 245 seconds). 00:04:27 Sanyo’s “SSP” is the most horrible protocol i’ve ever seen. 00:04:38 it uses MPEG-2 not because that's actually a good choice for videoconferencing but because keith had to implement a custom variable bitrate encoder in like three days 00:05:08 basically, it uses bayesian estimation to figure out the maximum bitrate it can send with only a 5% chance of a delay larger than 100ms (i think) 00:06:48 I wish all software did that. 00:07:56 kmc: How're your adventures in JavaScriptland, by the way? 00:07:59 Or wherever it is you are. 00:08:08 pretty good 00:08:13 i am enjoying my job 00:08:18 MakingAUsefulThingland 00:08:24 we have been working on the thing for a month and a half and have made a ton of progress 00:08:34 Is the thing still secret? 00:09:15 yeah 00:17:57 kmc is making a bomb 00:18:02 in javascript 00:18:14 ø̈h nø̈ 00:19:00 ø̈ḧ¨n̈ø̈ 00:19:15 some days I just tell myself "hey let's go to bed now before it gets late" and then before I have successfully gone to bed I tell myself "hey I should take a look at that Emmental language it seemed really interesting" or anything of the like and it overwrites the previous resolution and IT'S 2:30AM ALREADY and today is one of those days 00:19:38 gnight 00:19:42 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 00:19:51 I woke up before 08:00 today! 00:19:53 It was crazy. 00:22:14 how'd you manage that? 00:23:00 It just happened. 00:23:30 Normally when I need to wake up early I set several alarm clocks and still have a lowish probability of it doing any good. 00:23:31 cool 00:23:35 how do you feel about this event? 00:23:49 I like waking up early. 00:23:55 When it happens on its own and I'm not tired. 00:29:14 waking up early is awful 00:29:22 there is no good reason for hours less than 12 to exist 00:30:07 -!- monqy has joined. 00:30:11 elliott: 01:00 is a perfectly good time to be awake. 00:30:33 elliott probably believes in Random Standard Time. 00:30:51 monqy: what is shachaf talking about 00:30:59 i don't know 00:31:09 elliott: RST goes from 06:00 to 29:59 00:31:10 thread killed btw 00:31:20 kmc probably knows more about it than I do. 00:31:39 monqy: dammit 00:31:43 shachaf: shut up let me war with monqy in peace 00:32:02 What war are you having? 00:32:08 lambdabot war? 00:32:33 it's a personal war 00:32:49 thread killed btw 00:32:59 shachaf: 06:00 is wrong anyway 00:33:03 since i'm often still up at that time 00:33:11 08:00 would be a reasonable roll-over probably 00:33:26 how does this command even work again 00:33:31 oh like that 00:33:36 @admin - elliott 00:33:38 @ignore + elliott 00:33:45 i guess monqy wins :'( 00:36:15 Oh, Phantom__Hoover elliott monqy et all, recent update if you didn't see it 00:36:26 *et al 00:36:37 hi 00:36:39 hi elliott 00:37:28 sghello 00:37:36 creative liberties, artistic license 00:37:47 monqy: i didn't know you coded perl 00:38:13 i used to know some perl but then i forgot it 00:38:22 i think i';ve only written one perl thing in my entire life 00:38:34 iused to forgot all perl but thenr i learned it :"( 00:38:48 monqy: http://en.wikipedia.org/wiki/Artistic_License 00:39:27 hi Sgeo 00:39:56 -!- fungot has quit (Ping timeout: 246 seconds). 00:39:58 never heard of it! 00:40:03 plenty about the other artistic license though 00:40:05 my favourite license 00:40:13 -!- sebbu has quit (Ping timeout: 246 seconds). 00:41:00 * Sgeo forgets whether there's a way for non-admins to privately message lambdabot to get it to say something in channel 00:41:22 There's obviously someone in here who can do it, shachaf I think? 00:41:29 no 00:41:58 lambdabot is lying. It's me. 00:42:27 shachaf vs shachaf, FIGHT! 00:43:09 "Whether or not the original Artistic License is a free software license is largely unsettled. It was criticized by the Free Software Foundation as being "too vague; some passages are too clever for their own good, and their meaning is not clear."" 00:43:10 shachaf is lying 00:43:28 elliott: stop @admin-ing me :'( 00:43:31 Too clever for their own good? Like some Perl code? 00:43:47 Like all Haskell code? 00:46:59 -!- sebbu has joined. 00:47:39 -!- sivoais has joined. 01:07:04 shachaf: Not all haskell code is clever =P 01:07:17 See: All Haskell code I've ever written 01:07:46 Not all things FreeFull says are clever. 01:08:07 shachaf: I say none of them are 01:15:04 -!- copumpkin has joined. 01:26:41 -!- glogbackup has joined. 01:26:41 -!- slbkbs has joined. 01:26:41 -!- slbkbs has quit (Changing host). 01:26:41 -!- slbkbs has joined. 01:26:49 -!- lambdabot has quit (Ping timeout: 256 seconds). 01:26:52 -!- EgoBot has quit (Remote host closed the connection). 01:27:03 -!- EgoBot has joined. 01:28:05 -!- HackEgo has quit (Ping timeout: 255 seconds). 01:28:42 -!- HackEgo has joined. 01:30:22 -!- slbkbs has quit (Quit: adieu). 01:33:57 -!- TeruFSX_ has quit (Read error: Connection reset by peer). 01:34:46 -!- TeruFSX has joined. 01:36:53 Common Lisp:Clojure::Tcl:??? 01:36:59 * Sgeo wants the ??? language 01:37:22 hi 01:38:36 Sgeo: ???=Clojure 01:39:10 Clojure has CL-style macros, when I think I really like Tcl-style I-don't-know-what-to-call-it 01:39:40 fexprs? Except, if Kernel is said to have fexprs, it's not quite it 01:40:27 Tcl: a Tcl-expr lisp. 01:40:27 :P 01:41:09 something about strings 01:42:42 I didn't say I like the string aspect 01:43:06 But the idea of being able to dynamically generate the code that a control structure will see 01:43:56 Although admittedly it hurts compilability and any code-walking ability 01:44:24 does it do anything good 01:44:40 it'd be pretty sad if something so crazy was entirely useless and just a huge mess for losers!!! 01:46:16 It comes to mind whenever I see someone complain about how some macro they want to use won't accept a variable containing a symbol or a vector in place of where the macro usually accepts a symbol or vector 01:51:41 -!- TeruFSX has quit (Remote host closed the connection). 01:53:04 -!- TeruFSX has joined. 01:57:33 Wait, why exactly am I chatting on the W:A chat as though anyone actually chats? 01:58:01 http://snooper.worms2d.info/ 01:59:29 why are you asking #esoteric, Sgeo 01:59:45 elliott: Twist: #esoteric is W:A caht. 02:08:55 `pastelogs omee 02:09:23 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.17397 02:20:55 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 02:49:01 -!- Jafet has joined. 03:08:00 I wonder if I should attempt to implement ALPACA in Clojure 03:12:03 alpaca meat is fairly tasty 03:12:45 whatever it is, it's better than nothing, unless it isn't 03:26:38 Why does catseye keep 404ing on me? 03:26:43 http://catseye.tc/projects/alpaca/doc/alpaca.html 03:26:56 The Game of Life link and the WireWorld link both 404 on me 03:27:11 Almost complained that ALPACA cheats, but that's REDGREEN not ALPACA cheating 03:27:25 good catch 03:27:50 do you think you have a chance at winning the: catch of the year award???? I think you do 03:28:12 you'll have to compete with the fishers but all they catch are fish 03:30:37 monqy: sometimes they catch other things by accident 03:30:42 I should do it in ClojureScript, not Clojure 03:30:59 Although I kind of hate ClojureScript. A "lisp" with macros in a different language and no eval. 03:31:06 do it in "clozure" 03:31:15 monqy: is the joke clozure common lisp 03:31:18 yes 03:31:23 great joke 03:31:51 can i have a joke monqy 03:32:07 no i'm fresh out 03:32:13 that was my final joke 03:32:15 the last one 03:32:22 sinister 03:32:26 what's the point of living if you don't have jokes to tell. 03:32:27 how about just a pub 03:32:30 or a pun 03:32:37 i meant a pun but a pub would also do 03:33:34 Is APALCA's only full documentation the Perl implementation? 03:34:34 apalca 03:34:47 *ALPACA 03:35:59 Oh, REDGREEN's source probably serves as documentation 03:36:30 o.O cpressey writes useful code? 03:42:03 -!- TodPunk has quit (Read error: Connection reset by peer). 03:42:15 -!- TodPunk has joined. 03:42:23 Can REDGREEN fish interact with the rest of the REDGREEN world? 03:42:46 e.g. the GoL simulation interacting with WireWorld 03:44:19 kmc: newtype Rec a = InR { outR :: Rec a -> a } is just Curry's paradox. 03:44:30 elliott: Nifty, eh? 03:48:09 shachaf: curry's paradox doesn't work because you have to mix logic with common sense to get the best results 03:48:11 a wise man once told me this 03:50:26 Those are the ingredients of a delicious curry. 03:55:31 -!- mig22 has joined. 03:57:03 -!- kinoSi0 has quit (Read error: Connection reset by peer). 03:57:31 -!- kinoSi has joined. 04:06:27 DuctTape is flammable. 04:07:05 i'll keep that in mind 04:07:16 -!- FireFly has quit (Ping timeout: 246 seconds). 04:12:40 let's train a new generation of programmers capable only of thinking functionally, leaving us with the high-paying procedural maintenance 04:16:46 hi 04:19:56 -!- FireFly has joined. 04:26:02 Oh, so Himera needs a server. 04:26:16 (Himera is a web-based REPL for ClojureScript) 04:27:15 Yes, this bothers me. 04:27:31 thanks for letting us all know, Sgeo 04:38:19 -!- copumpkin has quit (Ping timeout: 260 seconds). 04:38:54 -!- copumpkin has joined. 04:45:22 -!- elliott has quit (Ping timeout: 246 seconds). 05:07:21 Steam is Steamy. Good to know. 05:32:04 -!- copumpkin has quit (Ping timeout: 252 seconds). 05:32:14 -!- evincar has joined. 05:32:44 -!- copumpkin has joined. 05:36:03 Sgeo: ivan is alive? 05:36:34 shachaf, this is surprising to you? 05:37:38 Shouldn't it be? 05:45:41 -!- ogrom has joined. 05:49:11 -!- evincar has quit (Read error: Connection reset by peer). 05:53:41 -!- evincar has joined. 06:03:27 now running memtest86+ v4.20 06:03:34 test memory everyday 06:06:02 -!- evincar has quit (Read error: Connection reset by peer). 06:08:25 -!- evincar has joined. 06:47:44 -!- epicmonkey has joined. 06:52:50 achievement unlocked: mounted boot drive using only duct tape 06:54:24 * Sgeo keeps looking at redgreen.alp 06:54:48 -!- evincar has quit (Quit: leaving). 06:55:58 shachaf: that is roughly all i know about random standard time 06:56:18 What is? 06:56:26 what you said 06:56:29 Ah. 06:56:45 it goes from 06h to 29h, with the numbers under 24 lining up with normal time 06:57:04 actually I think in some real world contexts both 00h and 24h are used 06:57:09 to denote beginning or end of day resp. 07:30:27 -!- carado has joined. 07:46:18 -!- carado has quit (Quit: Leaving). 07:59:31 Why is my college so full of idiots 07:59:58 Apparently, a bunch of students ignored a fire drill, then ignored a seminar that they were required to attend because they didn't participate in the fire drill. 08:00:03 They are now expelled from the dorms. 08:00:56 -!- monqy has quit (Quit: hello). 08:20:44 Oh hey, I think I found a mistake in cpressey's REDGREEN implementation 08:21:44 Fish in water are supposed to follow GoL rules. But one fish surrounded by 8 fish will turn into air (not a GoL cell state) rather than water (GoL dead) 08:22:12 Unless the precedence of the state transitions is opposite of what I think it is 08:30:55 -!- Arc_Koen has joined. 08:33:55 No, I think I'm right and cpressey is wrong. 08:36:57 I do think it's first-matching, too. 08:37:23 Though you could just try it out. 08:38:05 what are we talking about 08:38:21 Arc_Koen: REDGREEN's ALPACA spe 08:38:27 Curse my fingers. 08:38:41 I was going to make that "Arc_Koen: Fish.", to be more mysterious. 08:38:46 fizzie, looking at the generated Perl also suggests it's first-matching 08:38:46 Now I spoiled the whole thing. 08:39:38 I just looked at the Perl generating the Perl, but it did, too. 08:39:54 fizzie: according to the logs the discussion about alpaca and redgreen started four hours ago 08:40:33 wait that's actually what you were talking about ? 08:40:56 Yes. 08:41:26 The Perl generating the Perl gives me a headache of confusion 08:49:37 -!- fungot has joined. 08:57:46 Does fungot speak REDGREEN? 08:57:46 Sgeo: and the same buttons to page up and page down in aterm. oh, you are just making a bad optimization for fun 08:58:00 bad optimizations for fun! 09:04:45 -!- Phantom_Hoover has joined. 09:11:32 -!- lambdabot has joined. 09:12:12 -!- Jafet has quit (Quit: Leaving.). 09:24:57 -!- Jafet has joined. 09:25:57 -!- nooga has joined. 09:31:43 AAAAAAAAAAAAAAAAARG 09:31:58 I think I accidentally erased the brainfuck interpreter I had written in thue 09:32:37 To the backups! 09:34:20 oh my god prison architect's in open alpha!!!!! 09:36:43 FreeFull: fortunately I pasted it to sprunge.us and copied the link here and it's in the logs 09:39:58 oh, it turns out § is not ascii 09:40:43 Why did you think it was? 09:41:12 I didn't think that was the problem 09:41:45 but it kinda screwed the file 09:41:59 replaced § with ¬ß (which is not ascii either, that's weird) 09:56:33 -!- FireFly has quit (Changing host). 09:56:33 -!- FireFly has joined. 10:22:09 let's not screw files, shall we? 10:28:47 Seven bits is not enough for miracles. At least ASCII has both upper- and lowercase. 10:35:51 -!- AnotherTest has joined. 10:35:55 Hello 10:43:01 you need only 6 bits for A-Za-z0-9, who needs the rest 10:57:42 -!- ogrom has quit (Quit: Left). 10:59:47 Sometimes a bit of punctuation is good too. 11:08:25 get access to GAME BREAKING BUGS 11:12:18 -!- Jafet has quit (Quit: Leaving.). 11:20:05 -!- sivoais has quit (Read error: Connection reset by peer). 11:20:24 -!- Jafet has joined. 11:20:48 -!- sivoais has joined. 11:32:10 -!- sivoais has quit (Read error: Connection reset by peer). 11:32:53 -!- sivoais has joined. 12:06:48 -!- itidus21 has joined. 12:10:24 this may seem odd but 12:10:51 * Topic for #esoteric is: BEWARE THE O/RJANIST MO/O/SE | 12:11:02 I, for one, welcome our new hash function overlords | 12:11:11 E5081A06F9E364E179B336A2C6D6831D4B50CD7739C7E156 12:11:19 5E03EBF2 | ZARDOZ created ZARDOZ; all else is the work of 12:11:30 ZARDOZ | New channel logs: http://5z8.info/hookers_j0l4yf_nak 12:11:42 edgrandmas.jpg | Old-style channel logs: http://codu.org/logs/_es 12:11:51 oteric/ 12:12:01 * Topic for #esoteric set by zzo38!~zzo38@24-207-49-17.eastlink.c 12:12:06 itidus21: it is looking more odd the further you go 12:12:15 a at Sat Oct 13 04:37:01 2012 12:12:38 the arbitrary line breaks are new information 12:13:32 oh, zzo probably put weird ascii in there 12:13:44 hmm 12:13:58 uh.. thats just the linebreaks based on the width of my xchat window 12:14:03 I was implementing the . instruction in my brainfuck interpreter in thue 12:14:08 Look at Dave. He's like "Okay. You can do this. DON'T hit the cymbals as hard as you fucking can!" 12:14:12 itidus21: so what is the odd thing? 12:14:44 the odd thing was me re-posting the topic with the linebreaks based on the width of my xchat window 12:14:50 -!- itidus21 has left ("Leaving"). 12:15:00 so I though "I'd do characters 32-126 manually, and characters above 128 can be detected easily since they have a 1 as their most significant digit 12:15:12 so I do all characters 32-126 manually 12:15:14 and then 12:15:36 I realize I did all that with the . marker right to the number 12:15:46 and the most significant digit is left to the number 12:16:13 (so i can't detect it) 12:16:39 hmm, so the oddest part about that whole thing was that nothing was odd in the first place 12:16:40 does that mean I have to do it all over again? 12:16:41 ... except itidus, I guess he's a bit odd 12:17:57 @tell itidus21 about that null stack you were so impressed about: I thought maybe a copy stack that would do exactly the opposite: instead of destroying everything that's pushed onto it (and being always empty) it keeps copy of everything that's popped from it (and is never empty) 12:17:58 Consider it noted. 12:19:19 ok one cheap way to cover my mistake without redoing everything manually is to consider ascii characters mod 128 12:19:45 that is, characters 128-255 would be equivalent to characters 0-127 12:20:17 or I could just say I don't care and trying to output a character outside the range 0-127 causes the program to halt 12:20:25 yeah that should be good enough 12:20:51 -!- spamdribble has joined. 12:21:44 -!- spamdribble has left. 12:26:03 -!- Frooxius has joined. 12:32:36 wouuuuuuuuh works with the Hello World program from the esolangs.org brainfuck page! 12:34:14 Arc_Koen: congratulations 12:34:37 I think I'm gonna send an email to the guy who wrote the thue interpreter I'm using 12:35:27 it allows to run the thue program step by step or at any speed and to see the current state of the program and that's a very valuable debugging tool 12:45:13 -!- AnotherTest has quit (Read error: Connection reset by peer). 12:45:27 -!- AnotherTest has joined. 13:01:47 -!- AnotherTest has quit (Quit: Leaving.). 13:03:27 -!- AnotherTest has joined. 13:08:24 -!- Jafet has quit (Quit: Leaving.). 13:28:33 Absolutely No Words http://youtu.be/pquYAEfbBFM 13:37:27 that's slightly disturbing 13:40:24 -!- iconmaster has joined. 13:46:01 -!- Vorpal has joined. 14:21:06 -!- Jafet has joined. 14:24:54 -!- iconmaster has quit (Ping timeout: 260 seconds). 14:32:35 -!- nooga has quit (Ping timeout: 256 seconds). 14:42:02 -!- Frooxius has quit (Quit: ChatZilla 0.9.89-rdmsoft [XULRunner 1.9.0.17/2009122204]). 14:42:14 -!- Frooxius has joined. 14:46:31 -!- iconmaster has joined. 15:05:16 -!- hagb4rd has joined. 15:06:16 hi 15:06:34 -!- iconmaster has quit (Ping timeout: 256 seconds). 15:07:57 -!- iconmaster has joined. 15:12:05 -!- FireFly has quit (Excess Flood). 15:19:05 -!- FireFly has joined. 15:20:26 -!- FireFly has quit (Excess Flood). 15:23:44 -!- FireFly has joined. 15:26:49 -!- mig22 has quit (Quit: mig22). 15:29:29 -!- nooga has joined. 15:42:45 -!- elliott has joined. 16:12:06 -!- iconmaster has quit (Ping timeout: 265 seconds). 16:13:20 -!- sirdancealot7 has quit (Read error: Connection reset by peer). 16:15:03 -!- iconmaster has joined. 16:34:44 hello 16:38:40 -!- AnotherTest has quit (Ping timeout: 246 seconds). 16:38:44 -!- iconmaster has quit (Ping timeout: 246 seconds). 16:43:52 -!- iconmaster has joined. 16:47:31 -!- nooga has quit (Ping timeout: 244 seconds). 16:56:23 -!- iconmaster has quit (Ping timeout: 245 seconds). 17:02:02 What the hell? 17:02:15 Facebook just told me that somebody I don't know accepted /my/ friend request. 17:05:39 :-D Someone had made a friend request to me ages ago, but i didn’t recognize the name immediately and didn’t get around to looking up who he was until today. It turns out it was you and i accepted. 17:07:04 Dafaq, why would I friend you, I hate you. I MEAN, NOTHING. 17:07:26 More tot he point, I don't remember ever doing this, or for that matter, ever friending anyone from #esoteric other than pikhq >_> 17:07:39 ion = pikhq 17:07:50 Nope. 17:08:46 Hmm, now I know what ion looks like. Just like I imagined, really. 17:08:55 Gregor: Only me? Hah. 17:09:23 I don't have “friends”, I only have “acquaintances I tolerate”. 17:09:29 :P 17:09:42 Date: Wed, 6 Jun 2012 17:36:14 -0700 Subject: Gregor Richards haluaa olla kaverisi Facebookissa. 17:10:06 haluaa olla kaferisi Facebookissa 17:10:21 June? May as well be 1960. 17:10:47 haruā orra kaferishi fēsubūkkissa 17:11:29 -!- Phantom__Hoover has joined. 17:11:35 -!- iconmaster has joined. 17:12:39 -!- ogrom has joined. 17:14:04 pikhq: Hey, if I break my system, fix it. 17:14:15 I have no idea what I'm doing, so I probabiy will break it. 17:14:34 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 17:14:38 Computers love coffee. 17:14:45 You should pour a whole pot on it. 17:15:29 pikhq: Weeeell, I'm removing my separate ext2 /boot partition and merging it into my JFS / at the same time as switching from MBR to GPT. 17:15:43 To make room for a 2 MiB partition GRUB2 apparently needs on GPT systems. 17:15:54 So I'm fairly certain my system is going to stop booting in a few minutes. 17:16:14 that does sound like something almost guaranteed to break your system 17:16:22 You *might* want to make a boot disk of some sort. 17:16:41 * FreeFull wonders what's up with people trying out GPT 17:16:46 pikhq: I think I have a USB drive with an Arch thing on it. 17:16:59 So probably I can just boot from that if it goes wrong. 17:17:03 No idea where it *is*, mind you. 17:18:05 FreeFull: I switched to GPT when my 3TB HD forced me to ;) 17:18:19 OK; writing new GUID partition table (GPT) to /dev/sda. 17:18:19 Warning: The kernel is still using the old partition table. 17:18:19 The new table will be used at the next reboot. 17:18:19 The operation has completed successfully. 17:18:25 Hey does anyone know how I can force the kernel to reload the partition table? 17:18:28 FreeFull: MBR is almost tolerable if you've got a small enough HD. 17:18:30 It's, uh, currently looking at my MBR table. 17:18:34 Gregor: How did it force you to? 17:18:35 FreeFull: And besides, this is new interestingness. 17:18:41 But the problem is I want GRUB to see the partition I just made or something. 17:18:45 FreeFull: mbr is limited to 2 tb 17:18:48 -!- micrypt has joined. 17:18:49 elliott: Erm. I dunno. 17:19:09 `WELCOME micrypt 17:19:09 -!- brownies has joined. 17:19:20 MICRYPT: 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.) 17:19:24 elliott: Can't you just have the boot partition setup 17:19:26 `WeLcOmE brownies 17:19:30 BrOwNiEs: 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.) 17:19:44 hello 17:19:48 Heh. Hi there, folks. 17:20:15 FreeFull: That doesn't help you if you cannot *represent partitions for the whole drive*. 17:20:21 Like what was done in the olden days when the BIOSes didn't support booting partitions larger than 528MB 17:20:23 micrypt: They don't actually ever talk about esolangs in here. 17:20:31 Oh nice, apparently tar doesn't save symlinks. 17:20:33 pikhq: I see 17:20:35 Or something. 17:20:37 No wait, it does. 17:21:16 elliott: There's other file types tar doesn't preserve, though. 17:21:47 Okay, let's reboot. 17:21:53 Does tar preserve fifos? 17:21:54 -!- elliott has quit (Remote host closed the connection). 17:22:27 Legacy tar only handles normal files, hard links, and soft links. Sane tar also preserves character specials, block specials, directories, and FIFOs.' 17:23:20 -!- elliott has joined. 17:23:26 It... booted perfectly. 17:23:28 I'm baffled. 17:23:33 You'll note it still doesn't handle named sockets. 17:23:36 elliott: Awesome. 17:23:45 elliott: Then BAM 17:23:55 It's not meant to be possible to fiddle about with that many things related to your boot process in one go and still have it work first try. 17:24:03 Maybe I messed up the conversion and it's still MBR??? 17:24:35 Okay, nope, gdisk says it's GPT. 17:24:58 I bet dmesg says what the kernel thinks it is. 17:25:02 you can have both GPT and MBR at the same time 17:25:11 olsner: Yeah, but gdisk says I just have the protective MBR thing. 17:25:29 pikhq: dmesg | grep -i gpt gives nothing. 17:25:36 olsner: Linux doesn't like that though 17:25:44 But the same applies to | grep -i mbr. 17:25:46 FreeBSD does but who uses FreeBSD? =P 17:25:47 I remember trying to set MBR back up after accidentally the GPT 17:26:28 FreeFull: Huh? Linux manages it fine, I thought. 17:26:58 FreeBSD does it a bit better than Linux, but Linux doesn't *utterly break* on hybrid MBR configs. 17:27:16 Linux only uses MBR or GPT, not both. 17:27:35 Sort of upset that I didn't get any fancy breakage. 17:28:05 Maybe I should enable [testing] for more fun. 17:28:06 Actually, from what I gather, the easiest way to check would be to see if /boot is a separate filesystem. 17:28:13 :) 17:28:28 yeah, partitioning and boot loader setup is so boring when it just works 17:28:43 pikhq: Yeah, there's no /boot mounted, it's definitely GPT... 17:28:53 how bad is it to use an SSD with the wrong sector size? 17:29:17 olsner: I think it's just slightly slower. 17:29:34 Oh hey, the ghc package got updated!!!!!!!!!!!!!!!!!!! 17:29:39 Time to blow away /opt/ghc and break everything. 17:29:41 elliott: It will show the GPT partitions, or the MBR partitions, but not both at the same time 17:29:47 elliott: 7.2 finally? 17:29:55 For the drive 17:30:12 And which ones it shows depends on if you booted it from GPT or MBR 17:31:44 shachaf: 7.6.1. 17:33:02 Eurgh, the package only provides Cabal 1.16.0. 17:33:07 So I guess upgrading probably won't work. 17:33:20 FreeFull: That seems OK though, since in hybrid configurations you keep the two tables synchronised. 17:33:56 At least, to the extent possible. 17:34:22 (presumably if you're using a gigantic HD in a dual boot config, you don't try to keep track of your partition that goes over the 2TB boundary) 17:35:42 * elliott is just going to not install Windows until using a UEFI system. 17:36:05 Probably the best option. 17:37:10 Not like the things I'd want a Windows partition for are viable on this machine, anyway... mostly games and this system is sort of crappy. 17:42:01 -!- brownies has left. 17:45:44 -!- micrypt has left. 18:06:51 * pikhq blinks 18:07:02 It is, uh. Technically possible to use EFI with MBR. 18:07:13 that sounds unwise 18:07:24 Your MBR partition scheme just needs to have an EFI system partition and it "just works". 18:08:09 About the only benefit I can see here is if you wanted to image a giant bunch of disks with the same OS install and have it work identically on BIOS and EFI. 18:08:33 And, hypothetically speaking, it's an OS that doesn't boot from GPT on BIOS. 18:15:34 hypothetically 18:17:03 *cough*fuckyouwindows*cough* 18:17:43 -!- micrypt has joined. 18:26:08 `ＷＥＬＣＯＭＥ micrypt 18:26:12 ​ＭＩＣＲＹＰＴ：　ＷＥＬＣＯＭＥ　ＴＯ　ＴＨＥ　ＩＮＴＥＲＮＡＴＩＯＮＡＬ　ＨＵＢ　ＦＯＲ　ＥＳＯＴＥＲＩＣ　ＰＲＯＧＲＡＭＭＩＮＧ　ＬＡＮＧＵＡＧＥ　ＤＥＳＩＧＮ　ＡＮＤ　ＤＥＰＬＯＹＭＥＮＴ！　ＦＯＲ　ＭＯＲＥ　ＩＮＦＯＲＭＡＴＩＯＮ，　ＣＨＥＣＫ　ＯＵＴ　ＯＵＲ　ＷＩＫＩ：　ＨＴＴＰ：／／ＥＳＯＬＡＮＧ 18:27:42 God, zenkaku Roman. 18:28:32 Hmm, I wish I could get rid of all these 32-bit libraries. 18:28:45 I guess Dwarf Fortress is still 32-bit only, though. 18:28:49 Have you considering replacing all with musl? 18:29:07 Speaking of, I really need to help finish glibc ABI compat on musl one of these days. 18:29:14 ｅｎｊｏｙ！ｚｅｎｋａｋｕ 18:29:29 Bah 18:29:30 pikhq: I don't see how musl helps. 18:29:41 elliott: It doesn't directly. 18:29:47 But it makes me happier. 18:29:55 That's like helping. 18:30:15 I sort of doubt musl's binary compatibility is good enough to use all of Arch's glibc-based binary packages with it. 18:30:28 Hence why I need to finish it. 18:30:45 Fair enough. 18:30:47 As far as I'm aware, the single largest gaping hole is the lack of the _FORTIFY_SOURCE functions. 18:31:15 What about those warnings you get about needing dynamically-loaded stuff if you statically link with glibc? Does musl have to do anything to support that kind of stuff? 18:31:24 Not that the packages are statically-linked, but you know what I mean. 18:31:37 What those are is functions in glibc that call dlopen... 18:31:40 In musl, they don't. 18:33:27 Of course, static linked glibc stuff won't work without those... 18:33:36 Betcha they could be stubbed without much trouble though. 18:34:05 ais523: kick shachaf 18:34:09 (mind, nobody, and I mean nobody, *actually static links against glibc*. It makes GHC's runtime look minimal.) 18:35:12 675k for "int main(){}" is a bit much. 18:35:15 I statically link against glibc sometimes. 18:35:45 That's 675k needed for glibc's *startup routines*. 18:36:14 And that's just the text segment. 18:36:43 The equivalent in musl is 1.5k for my current checkout. 18:36:46 11:35 Zeno knew how to halve his cake and eat it too. 18:38:10 Went down a couple bytes when I did a git pull... 18:38:25 I got 883kB for an empty main with whatever libc ubuntu has 18:38:42 854 with -Wl,--gc-sections 18:39:03 650 B for a dynamic linked program. 18:40:14 olsner: I'm arbitrarily just measuring the text segment. 18:40:22 oh, ok 18:40:58 -!- epicmonkey has quit (Ping timeout: 245 seconds). 18:41:16 If you only look at the binary size proper, static linked musl is the smallest. 18:41:41 there's no real reason that program should have anything more than an exit syscall in its text segment 18:41:58 olsner: Well, you still need the startup code. 18:42:22 How it works is _start runs, it sets things up for main, and only *then* does an exit syscall. 18:42:31 It's slightly more work than just _exit. 18:42:39 Still shouldn't be *that* much. 18:42:52 yes, but even that is not necessary for this program 18:43:04 The linker can't magically know that main is a no-op. 18:43:56 All it knows is it needs the startup code and the program's objects to be glued together into a single binary. 18:44:10 -!- epicmonkey has joined. 18:44:13 sure it can, but it's somewhat reasonable that the linker doesn't have that magic built in 18:45:03 s/somewhat/perfectly/ 18:46:04 The linker is getting handed headered machine code. You need a disassembler and some sort of assembly logic analyzer to determine what main is doing, and if any bit of the startup code is necessary. 18:46:20 That is to say, you'd basically be shoving compiler infrastructure into the linker. 18:47:25 link-time optimisation 18:47:34 Does not quite work like this, actually. 18:48:11 Here's the linker's knowledge of LTO: it's passed a .so that should be loaded, and should have objects filtered through it. 18:48:23 And, also, that .so isn't even looking at the machine code blob in the objects. 18:48:39 It's looking at compiler IR that was shoved in the object files. 18:49:20 i was joking mostly 18:49:21 It's more-or-less just deferring optimization passes and code generation until all the translation units are available at once. 18:49:28 i don't see much wrong with putting compiler logic in the linker, though 18:49:34 if anything i'd rather there be less compiler logic in the compiler 18:56:55 I wonder if Rust binaries are standalone enough to work as PID 1. 19:02:36 `W test 19:02:39 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: W: not found 19:05:08 -!- epicmonkey has quit (Ping timeout: 245 seconds). 19:07:53 pikhq: Is poppler or mupdf better these days? 19:10:00 -!- FreeFull has quit (Quit: New tmux). 19:10:28 mupdf: The muppet defragmenter. 19:15:31 -!- FreeFull has joined. 19:19:17 http://www.fileformat.info/info/unicode/char/1f648/index.htm 19:19:23 Uh. The image they give seems to be wrong 19:21:41 it's almost like the font they use doesn't have perfect unicode 6 coverage 19:24:45 preflex: seen kmc 19:25:06 Aww, according to Wikipedia, Mayan symbols are not yet in Unicod 19:25:09 Unicode 19:25:26 Unicod. Universal fishing. 19:26:40 Gregor, I don't count as being from #esoteric ? Or did I friend you? 19:26:56 Also, I should figure out how to contact cpressey 19:27:23 It's literally impossible to contact Chris. 19:27:27 He does not exist. 19:28:06 Sgeo: There is, however, a tentative allocation for Maya hieroglyphs in the SMP roadmap: http://www.unicode.org/roadmaps/smp/ 19:28:09 I don't see an email address on his about page 19:29:08 Sgeo: I think it went something like so that you write "cpressey" in blood on a mirror at midnight, and then... something. Some chanting was involved. 19:29:49 Oh right, write it three times. Don't remember the other details. 19:32:05 "And, because OpenZz thinks you are the input to a compiler, accumulating 10 of these errors will actually cause OpenZz to quit!" 19:32:19 So you can have 9 syntax errors and OpenZz will not quit? 19:32:25 That seems bizarre 19:33:19 I seem to recall some other compiler having a "more than K errors, giving up" rule too. 19:33:52 Though I don't know what "quit" means in that context. 19:34:31 I would've assumed "stops trying to make sense out of the file", as opposed to trying to report all errors. 19:34:38 http://catseye.tc/projects/zzrk/README.markdown.html 19:36:03 Well, it sounds a bit like that, then. 19:37:04 Like doing -fmax-error=10 to gcc. 19:37:17 -fmax-errors=10, I mean. 19:37:57 But surely an error is something that should make the compiler quit immediately? 19:38:49 I don't know how often he comes in here, so don't know how long a @tell would take 19:42:59 -!- nooga has joined. 19:43:22 Sgeo: I think most compilers actually would instead read the whole file and try to report all errors at once, instead of quitting at the first, and that's what people actually want. 19:43:32 Yes, gcc doesn't give up at the first error or anything. 19:43:33 Ah, good point 19:43:42 There's the whole field of error recovery in parsing to make that possible. 19:45:20 But there was some tool with a finite default to '-fmax-errors'-like behaviour, I just can't remember which it was. The error message was mostly neutral, but there was a slight hint of disparaging the programmer. 19:45:39 The limit was something like 500 or 1000 errors, after all. 19:47:23 GCC just says "compilation terminated due to -fmax-errors=2." which is kind of boring. 19:47:26 disparaging the programmer made me think INTERCAL, but I'm sure it would have a lower limit 19:49:09 -!- ais523 has joined. 19:49:17 No, this was some "serious" tool. 19:49:51 Oh, I'm probably just thinking of Valgrind's "go fix your program" message. 19:50:17 ==21573== More than 10000000 total errors detected. I'm not reporting any more. 19:50:20 ==21573== Final error counts will be inaccurate. Go fix your program! 19:50:30 That thing. It doesn't even quit. 19:50:37 ais523: kick shachaf 19:50:59 Or at least mingling that message and the as-yet unidentified compiler. 19:51:45 Valgrind's "go fix your program" is quite confusing 19:51:56 given that 10 million errors can happen very quickly, and often stem from the same cause 19:52:05 btw, I just received spam saying I'd been successfully unsubscribed 19:52:08 not sure from what 19:52:13 "This seems difficult at least, and not really necessary if we're willing to forego writing "Hunt the Wumpus" in Burro" 19:52:15 my guess is it's angling for replies asking wtf is going on 19:52:23 which would confirm the address as genuine 19:52:31 Aww, I wanted to write Hunt the Wumpus in Burro 19:52:36 (note: not really) 19:52:37 also, which one's Burro? 19:52:45 I'm sort-of losing track of all the esolangs we have nowadays 19:52:58 Brainfuck-like where every program has an antiprogram that when concatenated to the program results in a no-op 19:53:12 http://catseye.tc/projects/burro/doc/burro-1.0.html 19:53:29 right, that one 19:53:35 thought it might be 19:53:47 I remember talking to cpressey about it, because there was a mistake in it 19:54:31 JScript .NET has a syntax error "JS1197: Too many errors", but I'm sure I haven't used that. 19:55:28 ais523, how do I contact cpressey, there's a mistake in his REDGREEN implementation, I think 19:56:02 Oh, and Apple MPW C has "Too many errors on one line (make fewer)". 19:57:40 ≡ ≡ <> 19:57:52 That line should NOT have confused me as much as it did, even if it was only for seconds 19:58:17 -!- kinoSi has quit (Read error: Connection reset by peer). 19:58:44 -!- kinoSi has joined. 20:01:19 ais523, Burro question: Is it mandatory to have a / inside (), or can you have (e) and no / in there 20:02:01 I think you'd need a / or a \ because otherwise it wouldn't make sense 20:02:02 but I'm not sure 20:02:24 fizzie: I'm pretty sure I've used compilers that stop at a configurable number of errors, with "error: too many errors" 20:02:42 I think it's because they have bad error recovery and errors after the first few don't actually make sense anyway 20:02:47 or else that they fear a lot of duplicates 20:03:17 ais523: So am I, but I can't remember which ones they were. (GCC has an option for it too, but it is off by default.) 20:04:08 hmm, Borland C++ 4, perhaps 20:04:13 the compiler I grew up with 20:04:23 ais523, is there a way to contact cpressey? 20:05:00 -!- Phantom_Hoover has joined. 20:07:14 -!- Phantom__Hoover has quit (Ping timeout: 255 seconds). 20:08:28 Sgeo: I think he has an email address 20:08:48 * Sgeo is having trouble finding it 20:09:05 does the email link on his userpage work? 20:09:12 actually, probably not, given how often catseye moves 20:10:01 Oh hey REDGREEN is on Github 20:10:06 I could just do something there 20:10:15 Also on bitbucket. 20:10:27 They seemed to have identical commits. 20:10:47 It smells like some kind of an automatic thing to have both. 20:11:29 it's a VCS, right? 20:11:32 you can commit to multiple repos 20:11:39 *DVCS 20:11:45 the fact that they're different DVCSes shouldn't matter 20:12:32 Do I just gratuitously add myself to the comment at the top of the file in my fork, or just make the change? 20:13:18 ais523: Oh, Bitbucket also supports Git? I thought they only did Mercurial. 20:14:20 In which case there would have needed to be some kind of a thing, or a person doing all commits twice with the same messages and so on. 20:15:37 By "thing" I mean something like that hg-git that people use. 20:16:53 -!- hagb4rd has quit (Quit: hagb4rd). 20:17:09 "Sgeo opened this pull request in a few seconds 20:17:09 " 20:17:15 You know, I should probably test it... 20:17:57 -!- ogrom has quit (Quit: Left). 20:18:09 -!- pikhq_ has joined. 20:18:28 -!- pikhq has quit (Ping timeout: 248 seconds). 20:19:45 "Madison, a Term-Rewriting Proof-Checker" 20:19:56 Misread that as time-travelling proof-checker 20:20:27 "let's travel back in time to check if fermat really had a proof" 20:20:49 (that's probably gonna be very disappointing) 20:21:46 -!- atriq has joined. 20:23:24 fungot needs to be rewritten in Flobnar 20:23:25 Sgeo: you'll be doing summer homework. *then* i can come up with a good solution 20:23:55 That'd be fun 20:25:36 Hmm. So Flobnar is more functional than Befunge? 20:25:51 I'm trying to understand the distinction between a moving IP and "evaluate what's over there" 20:27:28 Yeah 20:28:07 "Evaluate what's over there" has a sort-of intrinsic "move back and do the next thing afterwards" 20:28:31 The arithmatic stuff helps me understand 20:28:58 What's Flobnar like? 20:29:06 Esoteric 20:29:20 Befunge but drunk 20:29:35 Sort-of Lisp-y 20:29:54 There is currently no text in this page. :/ 20:30:10 - This frequent relocation of our web address was done specifically to 20:30:11 47 20:30:11 - please [[Phantom Hoover]]. 20:30:21 "(And it's not implemented yet, but never mind that.)" 20:30:31 Phantom_Hoover: http://catseye.tc/node/Phantom%20Hoover.html 20:30:33 yr famous 20:31:29 whoa man 20:32:05 Blah, I think the introspection and self-modification should perhaps use relative coordinates 20:32:28 more famous than u 20:33:15 -!- jiella has joined. 20:33:22 And so mysterious! 20:33:37 never did i think i would rub shoulders with douglas hofstadter 20:33:50 i wonder if he'll lend me some of his harem of beautiful french women now 20:34:16 Maybe I should have opened an issue than just issue a pull request 20:34:21 Harems are overrated 20:34:22 *rather than 20:34:36 atriq, yeah, sure 20:34:40 not jealous at all 20:35:46 What is Befunge-93's : 20:36:12 Duplicate, I think 20:36:58 One of my friends hates me in her sleep 20:37:09 Dup, yes. 20:37:16 See, it has two dots. 20:37:17 kind of her to abstain from hating you when awake 20:37:23 more than most of us can manage 20:37:25 Yes, indeed 20:37:29 (At least that's always been my personal logic for it.) 20:38:46 I'm kind of bored right now 20:39:07 see, if you had a harem of beautiful french women you wouldn't be bored 20:39:12 !befunge "!olleh">:#,_@ 20:39:13 hello! 20:39:42 Phantom_Hoover, you're forgetting two things 20:39:49 I'm an asexual 20:39:54 And I don't speak French 20:40:13 uh you can be french and speak english 20:40:16 Beyond "Ou est le W/C? Je voudrais une baguette!" 20:40:18 also you can have asexual harems! 20:40:49 harem -haref / 20:41:17 harem haref? 20:42:10 :$@ 20:42:12 Is that 0? 20:42:19 hmm, I think I need new glasses 20:42:29 I think that would make sense, but not sur 20:42:31 e 20:42:43 Yes. Well,it has a 0 on stack at @. 20:43:44 But $ pops the stack 20:43:56 Yes, but only one of the 0s pushed by :. 20:44:00 -!- Phantom__Hoover has joined. 20:44:09 Should the stack be considered to have an infinite number of 0s? 20:44:52 If you like. Poppig an empty stack yields 0. 20:45:38 The spec (at least 93) isn't explicit about ':' on empty, but pushing two 0s is I believe most common. 20:45:39 The example cat program 20:45:42 Phantom__Hoover, you've cloned yourself! 20:45:52 Wouldn't that .. n/m 20:46:48 98 seems to be explicit about :. 20:47:04 "pops a cell off the stack, then pushes it back onto the stack twice, duplicating it". 20:47:06 * Sgeo was talking Flobnar 20:47:10 Oh. 20:47:20 Well, I haven't seen Flobnar. 20:47:27 http://catseye.tc/projects/flobnar/doc/Flobnar.falderal.html 20:47:34 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 20:50:08 -!- atriq has quit (Ping timeout: 245 seconds). 20:52:08 -!- atriq has joined. 20:52:37 atriq, it's so i can deal with all these french haremites 20:52:39 Ooh, that division by zero is funky. 20:52:58 "Enter Velo, a vaguely Ruby-inspired scripting language which unifies strings with code blocks, and scripts with object classes." 20:53:03 TCL??? 20:54:48 Well, partly like Tcl 20:55:17 -!- sivoais has quit (Ping timeout: 246 seconds). 20:56:46 -!- sivoais has joined. 21:21:47 -!- iconmaster has quit (Ping timeout: 255 seconds). 21:44:17 I don't get it 21:50:16 Help I'm answering things on Stack Overflow badly 21:51:28 Hey, I've got the Tumbleweed badge on Ask Ubuntu 21:51:34 the worst of crimes 21:51:46 And I still have this problem 21:53:09 i've spent my evening eating beef and drinking portuguese wine 21:53:17 nooga, in Tcl, Everything Is A String 21:53:26 Sgeo: awful 21:54:07 nooga: This includes code. 21:54:25 In Windows Powershell Strings Are Not Actually Strings 21:54:36 what's windows powershell? 21:54:56 Thingy included with Windows 7 21:55:05 Supposed to replace CMD.EXE or whatever 21:55:09 oh 21:55:53 microsoft finally noticed that unixy OSes had a serious command line shell for, llike, 40 years? 21:56:08 and tried to copy the idea? 21:56:28 that and more and wrong, I think 21:56:34 Tried to copy the idea and wrote it thinking that attaching hidden information to EVERYTHING was a brilliant idea 21:56:43 but I've never used powershell so I don't really know 21:56:54 i uess nobody ever used it 21:56:57 -!- atriq has changed nick to awesome. 21:57:05 even the, gah, windows sever powerusers 21:57:10 sewer 21:57:10 -!- awesome has changed nick to atriq. 21:57:12 danm 21:57:13 server 21:57:28 I used to answer stuff on stack overflow but I got bored when I got all the privileges :I 21:57:36 There's still badges but they're meh hard 21:58:25 Powershell manages to be more verbose than you reasonably want in a shell. 21:59:06 Today I actually tried to climb a building 21:59:19 :) 21:59:22 It's C# with a funny syntax. 21:59:25 echo *.txt|grep foo 21:59:27 is like 21:59:30 BECAUSE ADVENTURE 22:00:13 new-object Searcher::$search(call-static-method File::OfType("txt")) 22:00:15 ¬u¬ 22:00:18 Or something like that I don't know 22:00:30 hehee 22:00:32 ehehe 22:00:40 what a spectacular fail 22:01:24 BTW, because both POSIX and common systems permit some massive brain damage, "echo *.txt|grep foo" does not quite do what you think it does. 22:01:48 http://thebestpageintheuniverse.net/c.cgi?u=youre_not_a_nerd 22:02:26 ... I meant cat! 22:02:27 ¬u¬ 22:02:30 It's late. 22:02:40 Ok here's an actual example 22:03:04 Actually I don't know how to search .__. 22:03:10 But here's how to open a log: $AppLog = New-Object -TypeName System.Diagnostics.EventLog -ArgumentList Application 22:03:27 cool 22:03:31 they have $ 22:04:06 oh yes 22:04:07 pikhq: echo *.txt|grep foo seems to do what i thought it does. 22:04:29 ion: Consider the file -n.txt 22:04:49 Solution: don't name files like that 22:04:54 Or perhaps the file \n.txt (in C string notation "\\n.txt") 22:05:02 Sleepy time. 22:05:48 pikhq: That behavior is what i think it has. It’s not what i’d *hope* it had, but that’s another matter. :-P 22:05:51 Lumpio-: Solution, smack whoever thought echo should be anything but int main(int argc, char**argv){for(int i = 1; i < argc; i++)puts(argv[i]);} 22:06:19 atriq: was it a portable toilet? 22:06:23 or something bigger/ 22:06:29 pikhq_: that does not solve the bigger problem at all 22:06:30 (which, incidentally, remains a POSIX compliant echo.) 22:06:32 BIGGER 22:06:39 I didn't get very far, though 22:07:04 elliott: Nah, but it's *less* brain-damaged at least. 22:07:05 a gazebo? 22:07:26 'Course, second you add spaces to your filenames, it breaks like crazy. 22:07:29 * ion kills the gazebo 22:07:31 I got a couple meters off the ground before I realised that the column I was ascending led to a horizontal wall thing 22:07:33 well why fix echo when there is also every other command with options 22:07:36 pikhq_: btw that is not a compliant echo 22:07:38 nooga, a SHOPPING CENTRE 22:07:47 Oh, dur, puts does append newlines after everything. 22:08:11 ion? 22:08:30 No, I did not climb ion 22:08:36 int main(int argc, char**argv){for(int i = 1; i < argc; i++)printf("%s",argv[i]);puts("");} 22:08:48 Wait 22:08:49 pikhq_: try again 22:08:56 It was a leisure and retail complex 22:08:58 Whatever that is 22:08:59 i meant an arbour, not gazebo 22:09:07 i'm not even sure what gazebo is 22:09:10 Blah! 22:09:17 elliott: Let's not. 22:09:19 stupid word 22:09:28 A gazebo is like a tent on stilts 22:09:36 main = fmap unwords getArgs >>= putStrLn 22:09:37 elliott: Complaint echo does not have options, so what do you mean, "every other command with options"? 22:09:48 Except without walls 22:09:55 "Implementations shall not support any options." -- POSIX 22:10:00 ann arbor 22:10:08 well i mean "echo *.txt" not doing the right thing compared to globbing with any command that accepts options 22:10:10 -!- Phantom_Hoover has joined. 22:10:11 like cat *.txt or whatever 22:10:18 and don't complain about cat's options or i'll just find a command with options you like :P 22:10:25 pikhq_: btw echo *.txt actually works perfectly 22:10:25 No, I did not climb an arbor 22:10:28 since -n.txt is not -n 22:10:30 Why would you even IMPLY that 22:10:31 at least here 22:10:34 cat -- *.txt 22:10:36 (of course spaces still mess it up) 22:10:55 once I climbed an arbor 22:10:58 nooga: http://www.comedycorner.org/90.html 22:11:10 The above actually works. Perfectly. 22:11:16 an I was slightly drunk and then i fell because i was afraid of falling 22:12:03 define the above 22:12:10 cat -- *.txt 22:12:13 -!- Phantom__Hoover has quit (Ping timeout: 246 seconds). 22:12:16 if "cat -- *.txt" is an ok solution then surely "echo -- *.txt" is too 22:12:22 i.e. the problem isn't actually that echo has options there 22:12:34 Except echo does not support options. Not even -- 22:12:40 Isn’t echo officially deprecated in the POSIX spec? 22:12:43 ion: No. 22:12:53 I'm reading it. It is not deprecated. 22:13:32 The problem with the POSIX echo spec is that it doesn't match any existing implementation. 22:13:34 :) 22:13:49 it matches the one pikhq_ will write in one IRC line in three seconds 22:14:00 “New applications are encouraged to use printf instead of echo.” – echo(1posix) 22:14:14 Gregor: POSIX-but-not-XSI echo does map very well to sufficiently old UNIX. 22:14:20 ion: yeah, i was the Eric before a looked up the goddamn gazebo in my dictionary 22:14:29 ion: That is informative text, not a statement of deprecation. 22:14:49 ion: That's not the same thing as deprecation. 22:14:55 i wonder how's echo in Plan9 22:15:10 Also, the 1posix man pages are not the spec, but a derivative thereof. :P 22:15:27 elliott: Fun fact: It's impossible to write echo for GHC. 22:15:32 A compliant echo, that is. 22:15:33 hey ion 22:15:38 i hear you linked to maddox 22:15:41 eat shit and die? 22:15:54 As an answer to your question: feel free to. 22:16:21 hey man i'm just a soldier in someone else's war 22:16:26 Gregor: It appears to be POSIXly correct. 22:16:30 the war of the hoovers 22:16:35 shachaf: Because +RTS? 22:16:35 you can listen to repulsive idiots all you want 22:16:43 Though it does handle "-n" as the first operand. 22:16:59 How about with -rtsopts=none? 22:17:22 ion: z: RTS options are disabled. Link with -rtsopts to enable them. 22:17:22 No translations, though, so it's not XSI at all. 22:17:30 shachaf: duh 22:18:44 Also: int main(int argc, char**argv){for(int i = 1; i < argc; i++)printf("%s%c",argv[i],i==argc-1?'\n':' ');} 22:20:15 pikhq_: That doesn't print a newline for an empty command line. 22:20:17 pikhq_: fails to handle printf failing 22:20:20 also what shachaf said 22:22:44 I wonder what would happen if Kipple was working with queues instead of stacks 22:23:48 elliott: You forgot to mention the undefined behavior bit where it doesn't return 0. 22:24:05 main doesn't have to return 22:24:15 shachaf: that's ok 22:24:16 shachaf: C99 22:24:20 Isn't that a C++-only thing? 22:24:22 shachaf: In C99, if you reach the end of main you return 0. 22:24:23 no, C99 22:24:25 elliott: Fine. int main(int argc, char**argv){for(int i = 1; i < argc; i++)if(printf("%s%s",argv[i],i!=argc-1?" ":"")<0)return 1;return putchar('\n') != EOF;} 22:24:26 Oh. 22:24:27 it's dumb though 22:24:29 i dislike it 22:24:32 * shachaf is still in C89 land. 22:24:38 Or maybe "things that make any sense" land. 22:24:50 pikhq_: makes assumptions as to what a return value of 1 means 22:24:58 also known as "ancient C" land? 22:24:59 perhaps you want EXIT_FAILURE? 22:25:17 elliott: No. POSIX echo returns some value greater than 0 on an error. 22:25:29 hm 22:25:31 accepted 22:25:32 elliott: It does not have to have semantics other than being greater than 0. 22:25:52 hmm 22:26:29 pikhq_: what if argv[i] is NULL? can that ever happen? 22:27:22 No, for 0 < i < argc. 22:27:40 It even handles the argc == 0 case. 22:27:57 hrm 22:28:03 shachaf: No, it's not. It's initialized to 1 even if argc <= 1. 22:28:22 fizzie: huh? 22:28:26 "and even if Chris doesn't respond to your pull request for three or four years, at least your fork will be out there and available to anyone else who might be interested." 22:28:30 Oh, it was inside the loop. 22:28:31 Hmm, is that particularly likely? 22:28:35 I did not SEE. 22:28:46 Sgeo: yes. chris hates pull requests. and the web. 22:28:59 he quit IRC because he refuses to use any other protocol but ssh and gopher. 22:29:04 this is also why he cannot be contacted 22:29:40 pikhq_: anyway I guess that might be valid 22:29:48 I bet it's still not compliant. 22:30:01 maybe not 22:30:03 it seems fairly airtight though 22:30:10 i was tryign to think of overflow behaviours with argc but that seems ok too 22:30:13 *trying 22:30:23 Wait, which echo specification are we talking about here? 22:30:28 POSIX. 22:30:34 Not XSI, just POSIX. 22:30:38 All of them. Simultaneously. 22:30:42 (not really) 22:30:45 Where's the spec? 22:30:53 POSIX echo is boring though, judging by the echo(1posix) man page 22:30:55 http://pubs.opengroup.org/onlinepubs/9699919799/utilities/echo.html 22:31:17 Oh, part of that spec is XSI. 22:31:18 -n as the first operand is implementation-defined, as are instances of backslash in the operands. 22:31:32 And I define them to be "they are treated as ordinary strings". 22:31:40 pikhq_: looks like you have to deal with locales 22:31:45 given ENVIRONMENT VARIABLES 22:32:25 Not if you have no diagnostic messages. 22:32:34 elliott: I do so correctly, by having no diagnostic messages. 22:32:45 "Determine the locale for the interpretation of sequences of bytes of text data as characters (for example, single-byte as opposed to multi-byte characters in arguments)." 22:32:50 XSI-only. 22:32:54 shachaf: yes but that's XSI :( 22:32:56 Oh, right. 22:33:13 seems like this is more likely to be an invalid C program than non-compliant with the POSIX spec 22:33:29 Well, you need #include 22:33:33 But I guess that was implied. 22:33:37 I was taking that as read. 22:39:57 pikhq_: Now golf it. 22:42:27 int main(int a,char**b){int i=1;for(;i is continuing to printf after an error ok 22:44:38 are you allowed to execvp("/bin/echo", argv)? 22:44:51 olsner: No, because /bin does not need to exist. 22:44:59 I'm pretty sure that won't compile because argv isn't in scope. 22:45:02 I think I meant execv 22:45:39 /bin/echo is not guaranteed to exist, nor is /bin. 22:46:12 int main(int a,char**b){while(*b)printf("%s%c",*b,*b++?' ':'\n')>0||exit(1);} 22:46:18 is that correct 22:46:24 oh that should be *(b++) 22:46:46 I'm pretty sure the argv vector is not NULL terminated. 22:46:54 pikhq_: It is. 22:46:58 It is. 22:47:02 argv[argc] == NULL is in the C spec. 22:47:02 Okay then. 22:47:14 olsner: It is strictly conformant for all POSIX utilities to be shell builtins, and for the shell itself to not actually exist in the filesystem at all. 22:47:29 oh it should be *++b 22:47:31 not *(b++) 22:47:46 elliott: exit() isn't golf if you count the #include 22:47:54 pikhq_: ah, that kills any exec-based solution 22:48:00 shachaf: mm 22:48:05 olsner: just exec sh 22:48:14 I wonder if I should learn how to use yoob 22:48:24 elliott: that only works if the shell is in the filesystem? 22:48:37 or are you always able to exec sh? 22:49:00 elliott: Wait, what's your correct program? 22:49:10 int main(int a,char**b){while(*b)printf("%s%c",*b,*++b?' ':'\n')>0||exit(1);} 22:49:25 technically both mine and pikhq_'s programs are wrong 22:49:29 because printf can print only some output sometimes 22:49:50 So? 22:49:57 what do you mean so 22:50:19 elliott: Yours is wrong because it prints argv[0] 22:50:59 According to POSIX, all of the standard utilities must be executable via exec(), even if they are implemented as shell builtins. 22:51:01 good point 22:51:03 (what do you mean so) 22:51:06 Also doesn't handle the no argument case. 22:51:21 Except the "special" builtins, which needn't be. 22:51:30 elliott: Oh boy, when you run your code with argc==0, it prints the environment! 22:51:44 (On Linux/glibc/etc., that is. It's undefined behavior, of course.) 22:51:55 Also if you fix the thing that makes it not even compile. 22:52:08 So, it's valid to have the C compiler as a shell builtin, but a POSIX system must execute that shell builtin on exec("cc") 22:52:10 is '\n' guaranteed to equal 10 22:52:20 elliott: No. 22:52:37 There are no charset guarantees beyond what characters must exist. 22:52:44 shachaf: what makes it not compile 22:52:50 pikhq_: What about '\0' == 0? 22:52:54 pikhq_: that's not true. 'a' to 'z' are required to be adjacent IIRC 22:53:01 elliott: The || thing. 22:53:08 and i think '0'+n has to work? 22:53:09 shachaf: is that not valid? 22:53:16 Not according to clang. 22:53:22 Instead of figuring it out I replaced it with an if(). 22:53:24 NAME FOUR FICTIONAL JAKES 22:53:27 shachaf: You're handing a numeric literal there. 22:53:55 shachaf: Which of course works. '\0' is (char)0 22:54:16 OK, but are there guarantees like 'a' != 0? 22:54:27 elliott: *Very* certain '0'+n doesn't have to work. 22:54:36 shachaf: Don't think so. 22:54:43 pikhq_: i think you are wrong 22:54:45 elliott: Heck, that's not even true of EBCDIC systems. 22:54:50 well 22:54:53 I know there are some ordering guarantees 22:54:54 iirc 22:54:55 but that's it 22:55:12 Nor is 'a' through 'z' adjacency... 22:55:27 EBCDIC is cruelty. 22:55:31 To specify an integer character constant containing 22:55:31 the two characters whose values are 0x12 and '3', the construction 22:55:31 '\0223' may be used, since a hexadecimal escape sequence is terminated 22:55:31 only by a non-hexadecimal character. (The value of this two-character 22:55:32 integer character constant is implementation-defined also.) 22:55:36 I didn't know that was in C89. 22:55:45 Implementation-defined, but still. 22:55:49 Oh, 0 through 9 should be adjacent. 22:56:11 told you!! 22:56:12 There are no *other* ordering guarantees in POSIX. 22:56:34 And U+0 shall be '\0' 22:56:49 That is the only character with a fixed value. 22:58:35 pikhq_: What about the guarantee that if you order a copy of the POSIX spec, they'll send it to you? 22:58:39 I should hope that's a guarantee. 22:58:48 (POSIX volume 1, 6.1 "Portable Character Set") 22:58:57 shachaf: I don't think that's *in* POSIX. 22:59:04 True. 22:59:07 It's still a POSIX guarantee, though. 22:59:12 But you didn't say that. 22:59:18 I said "guarantees in POSIX". 22:59:25 ordering the spec should be undefined behavior 22:59:26 Oozlybub and Murphy is great so far 22:59:27 Not guarantees *about* POSIX. 23:02:28 wtf 23:02:29 TRIVIA PORTION OF SHOW 23:02:29 WHO WAS IT FAMOUS MAN THAT SAID THIS? 23:02:29 A) RONALD REAGAN 23:02:29 B) RONALD REAGAN 23:02:29 B) RONALD STEWART 23:02:31 C) RENALDO 23:02:41 ^^ in the Oozlybub and Murphy docs 23:02:55 Sgeo: What does that have to do with Clojure? 23:02:59 I reckon C 23:03:02 the correct answer is D) CAPTAIN PICARD 23:03:29 Sgeo: do you not "get" cpressey 23:03:55 elliott: WHAT IF!!! i do not "get" cpressey :'( 23:04:03 I don't even know who that is. 23:04:11 shachaf: you don't get anything 23:04:13 BURN THE BLASPHEMER 23:04:15 cpressey is the only esolanger worth a damn 23:04:21 well ais523 and oerjan too 23:04:23 elliott: I get abused! 23:04:24 By you! 23:04:27 shachaf: http://www.catseye.tc/projects/oozlybub-and-murphy/doc/oozlybub-and-murphy.html 23:05:12 hmm, that reminds me, I should start working on yonguilexiphonaugh some day 23:05:48 elliott: cpressey is more prolific than me, and oerjan is more profound 23:06:17 and AmBF/AmbiF (it has two official names) has really got me annoyed, because I'm still not sure if it's TC 23:06:23 the only thing it's missing is arbitrary effect at arbitrary point 23:06:28 I guess fizzie is good too for fungot 23:06:28 elliott: did they make it easier to use than a keyboard. 23:06:29 and you know how annoying /those/ things are to prove TC 23:06:43 but every esolanger beyond that is unnecessary 23:06:55 contemporary, that is 23:07:00 elliott: It's a good thing I'm not an esolanger, isn't it? 23:07:01 oh I forgot Keymaker, pah 23:07:08 shachaf: yes, not even 23:07:14 * shachaf is necessary. 23:07:28 ais523: Is arbitrary effect at an arbitrary point even well-defined? 23:07:31 I've always been suspicious of it. 23:07:31 no 23:07:34 arbitrary effect at arbitrary point is what's needed for quineness, right? Or, well, providing arbitrary effect at arbitrary point is necessary for a proof of the existence of a quine to hold, in addition to TC 23:07:45 Am I understanding correctly? 23:07:57 but it's a good explanation to use for "I've been able to create two bignum counters in this with increment, decrement, and zero test and I'm /still/ not sure it's TC" 23:08:00 Sgeo: ? 23:08:16 elliott: I basically consider the TCness rules as not a mathematical definition but a heuristic 23:09:22 elliott: anyway, this nondeterministic BF variant is definitely TC if you add conditional goto 23:09:26 I'd explain to oerjan but he isn't here 23:09:36 what is ambif btw 23:09:51 also the word I was thinking when I said "unnecessary" was actually "inessential" 23:10:06 elliott: it's like BF, with a tape infinite both ways and bignum elements; and + does - instead half the time, and < does > instead half the time (and vice versa) 23:10:13 (i.e. + and - are the same, and < and > are the same) 23:10:24 ais523: is this on the wiki? 23:10:26 no 23:10:31 I should probably add it some time but I'm lazy 23:10:42 anyway, the name is /pronounced/ like "am BF" or "ambi-F" 23:10:48 and it is spelled in such a way that you can't tell which it is, which is impossible 23:10:52 so I'm having issues titling the page 23:11:07 ais523: What's the point of the "vice versa"? 23:11:12 at least it's not spelled /// 23:11:14 Just get rid of - and > 23:11:21 shachaf: well, yes 23:11:43 Also get rid of , and . 23:11:45 ais523: make it so that [ does ] half the time too 23:11:55 elliott++ makes a good point. 23:12:05 shachaf: oh, I did get rid of , and . 23:12:07 just forgot to tell anyone 23:12:14 and that would make the thing even harder to deal with 23:12:20 i'd keep . 23:12:23 it doesn't harm semantics, right? 23:12:51 You can keep . as long as it does , half the time. 23:13:02 elliott: it doesn't 23:13:09 but you can't distinguish between n and -n 23:13:26 and above 2, can't distinguish between two numbers if they have the same parity 23:13:33 so you couldn't actually construct anything coherent to output 23:13:43 at least, can't non-destructively distinguish 23:13:49 and any distinction would be probabilistic as-is 23:13:52 ais523: make it normalise the output to what's observable, then 23:13:58 take abs as first step, obviously 23:14:06 yes 23:14:13 you should probably make it output bits, actually 23:14:17 just caring about 0 and non-0 23:14:18 -!- jiella has quit (Quit: Leaving.). 23:14:25 you can construct 0 and ±1 trivially 23:14:34 ais523: Just base it on boof 23:14:35 amboof 23:14:36 IMO use * and @ for +- and <>, I think some other derivative does that 23:14:37 there's some doubt as to whether you can reliably construct ±2, and if it's useful to do that 23:14:52 I guess we should work out the IPA for it 23:14:54 and use that in the title 23:14:57 elliott: Why would you use @ for <>? 23:15:09 @ doesn't exist yet. 23:16:18 /ˈæmbiːɛf/ 23:16:24 -!- atriq has quit (Quit: Leaving). 23:16:35 Does æ mean the thing which is pronounced as "ea"? 23:16:41 As in "and". 23:17:08 shachaf: it's basically what English people do when trying to pronounce short "a" 23:17:25 As in "and"? 23:17:34 yes, or "ambiguous" 23:17:37 so i'm trying to run the example brainfuck program used on the Dbfi page to test the self-interpreter's speeds 23:17:47 Wait, "ambiguous" isn't pronounced like "and". 23:17:53 /æmˈbɪɡjuəs/ /ænd/ 23:17:53 The 'a', I mean. 23:17:59 are according to Wiktionary 23:18:03 and I'm trying to run it in a brainfuck interpreter written in thue, itself ran in a thue interpreter in java 23:18:04 and I pronounce them the same way 23:18:09 how do they differ in your language? 23:18:16 and well it's been running for almost two minutes now 23:18:21 Arc_Koen: you can expect that to take a while 23:18:22 You = wiktionary = wrong :-( 23:18:35 thue has an inherent O(n) slowdown 23:18:38 I have no idea what that brainfuck program was supposed to do 23:18:41 shachaf: so how do they differ in your accent? 23:18:48 ais523: I thought this slowdown could easily be reduce 23:18:50 ais523: I'd pronounce the 'a' in "ambiguous" like the 'u' in "up". 23:18:56 wow 23:18:59 that's a weird accent 23:19:07 Or maybe I wouldn't. 23:19:11 by making a thue interpreter that, instead of selectng rules randomly, would "sort" them 23:19:18 umbiguous 23:19:19 It might not quite be like that, but it's certainly not like "and". 23:19:23 although pretty much any vowel can be pronounced as anything if you go looking around for weird accents 23:19:24 That's way drawn out. 23:19:32 Arc_Koen: you still have to see where the rules match 23:19:35 that is, always trying to apply rules from the top of the rule list, and always placing the last rule used on top of the list 23:19:38 I might pronounce it that was for a long word like "ambiguity". 23:19:38 true 23:19:45 I've said ambiguous in so many ways now that I've forgotten the right way to say it (if I ever knew any) 23:19:56 olsner: So have I. :-( 23:20:04 ais523: I might just be wrong. 23:20:08 writing a system to try first where the last change has been made might be slightly more complicated 23:20:11 (About how I say it.) 23:20:14 (took about three tries to get there) 23:20:17 Arc_Koen: so basically each interpreter step is proportional to the size of the internal state 23:20:21 that's what causes the O(n) slowdown 23:20:26 Thutu has the same problem for the same reason 23:20:27 but still, the sorting rules thing would make it much faster I think 23:20:32 despite running rules in deterministic order 23:20:53 is that the best that can be done, or is that just because the thue interpreters are not very good? 23:20:58 wait, uh 23:21:02 it's stopped (finally) 23:21:07 olsner: it's possible to optimise it in many practically useful special cases 23:21:08 and it DOESN'T DO ANYTHING 23:21:10 but not in general, IIRC 23:21:17 Arc_Koen: sure, benchmarks rarely do 23:21:22 unless you're running Crysis or something 23:21:25 well technically it tried to print the number 11001010 23:21:48 (note: I don't have a BF version of Crysis to check; Lost Kingdoms is normally considered the closest substitute) 23:21:51 but I only implemented the result of the . operator for ascii values 10 and 32-126 23:21:56 ais523: Do you pronounce "ambiguous" like "America"? 23:22:03 has anyone here actually completed Lost Kingdoms, btw? 23:22:06 shachaf: yes 23:22:23 ais523: So do I, I think. 23:22:24 the thue interpreter in java seems to be pretty slow too 23:22:34 So you pronounce "america" with "æ"? 23:22:40 And you pronounce "and" with "æ"? 23:22:40 (it allows me to see the internal state) 23:22:51 shachaf: yes 23:23:00 I only really have one sort of short "a" for the starts of words 23:23:07 but it does allow escaped characters in replacement rules, which is nice 23:23:46 ais523: You pronounce "and" like "america"? 23:23:49 And they call *me* crazy! 23:23:59 and an america start with the same vowerl 23:24:15 shachaf: only the first vowel 23:24:17 not the entire wordes 23:24:18 "vowerl" is the British spelling of "vowel", right? 23:24:20 *words 23:24:21 ais523: Well, yes. 23:24:37 shachaf: "er" for "e" in "vowel" is quite a common accent in the UK 23:24:43 although I'd typically pronounce it as "vowl" 23:24:53 it was a typo btw 23:25:23 elliott: Just like "colour", right? 23:26:55 huh, New York just banned soda 23:27:04 I thought it only banned large ones 23:27:08 yes 23:27:09 hi copumpkin 23:27:13 hi shachaf 23:27:24 what do you mean "banned soda"? 23:27:46 basically shops aren't allowed to sell more than 16oz at a time 23:27:51 copumpkin: Rec is pretty nifty. 23:27:55 sadly, I'm British, and as such am not entirely sure how much 16oz is 23:27:57 Rec? 23:28:00 how much is that in metric? 23:28:01 @src Rec 23:28:01 newtype Rec a = InR { outR :: Rec a -> a } 23:28:04 wasn't that "unless the customer asks"? 23:28:05 ais523: it's a lot 23:28:10 shachaf: oh, the non-termination type 23:28:10 ah, OK 23:28:19 elliott: Can you use newtype P = InP { outP :: forall a. P -> a } to write Y? 23:28:21 I thought 1 oz was about 30 grams 23:28:27 copumpkin: Yes. It's Curry's paradox. 23:28:28 shachaf: I think yes 23:28:29 let me try 23:28:32 Conversion result: 473.2 mL (milliliters), assuming oz is US fluid ounces. 23:28:33 hmm 23:28:34 nobody spoil 23:28:46 I thought they just banned the "if the customer doesn't say how much they want, then they want a huge one" policy 23:28:49 350ml is about standard for a small bottle of drink in the UK 23:28:50 or something 23:28:54 shachaf: hey how do I define P in lambdabot 23:29:03 which corresponds to 12oz 23:29:05 elliott: You don't. :-( 23:29:06 for the record our previous president made up a tax on soda 23:29:12 50cl is the normal soda bottle size here 23:29:26 @let newtype P 23:29:26 EmptyDataDecls is not enabled 23:29:34 @let newtype P = InP { outP :: forall a. P -> a } 23:29:34 TypeOperators is not enabled 23:29:36 olsner: I've seen 50cl bottles too, but they're rarely used for soda 23:29:37 waht 23:29:43 oh 23:29:44 is it the forall 23:29:45 elliott: @let doesn't work that way. 23:29:48 (although they'd be marked 500ml in the UK) 23:29:50 or, well 23:29:52 cans are 350ml 23:29:52 Orwell 23:29:53 @let newtype Test = Test Int 23:29:53 Invalid declaration 23:29:56 bottles are 500ml indeed 23:29:57 @let newtype Test = Test { test :: Int } 23:29:57 Invalid declaration 23:29:58 aw 23:30:00 but cans are more common 23:30:11 mostly I see fruit juice in the 500ml ones rather than soda, though 23:30:16 Cans are canon. 23:30:18 http://upload.wikimedia.org/wikipedia/commons/2/21/Double_big_gulp.jpg 23:30:24 "Because using a built-in operation store in this way saturates it, it cannot be used again. Typically you want to make a copy of the store first, and use that, leaving the built-in store unmodified." 23:30:38 Sgeo: which language? 23:30:39 I can imagine how bad things would be if a mainstream language was like that 23:30:43 http://catseye.tc/projects/xoomonk/doc/Xoomonk.falderal.html 23:30:44 copumpkin: Pft. That cup is still smaller than the person holding it. 23:30:47 according to this article the ban is for restaurants, "concession stands" and "other eateries" 23:30:59 I'm sure badly written libraries and programs would saturate important stores 23:31:06 anyway: fun fact: at the University, I can buy a 500ml bottle of carbonated water for 95p 23:31:13 and I can buy a 2l = 2000ml bottle for 55p 23:31:24 even from the same shop, I think 23:31:33 I'm not 100% sure of the logic behind this 23:32:07 ais523: «'Only you MUST eat them both, if you buy two,' said the Sheep.» 23:32:13 for a second there I thought 'p' meant 'pound' 23:33:41 Arc_Koen: that'd be massively expensive 23:33:44 1p = £0.01 23:33:50 yeayeah 23:33:54 and a dollar is usually somewhere between 60p and 70p 23:34:05 although it's probably somewhere really different right now because the world economy is in a mess 23:34:26 @google 1 usd in gbp 23:34:27 huh, 62.21p 23:34:28 http://www.x-rates.com/ 23:34:28 Title: Exchange Rates - X-Rates 23:34:31 it's prety much where you'd expect it to be 23:34:33 Useless bot. 23:34:33 *pretty 23:35:04 I somehow read p as cent 23:35:13 $1 is at ₪3.8288 23:35:19 I guess I forgot how england and america are actually different countries that just happen to speak the same language 23:35:26 Weird. 23:35:30 shachaf: which country's currency is that? 23:35:45 olsner: and also there's a distinction between England and the UK 23:35:49 which many Americans don't seem to realise at all 23:36:00 (some of them catch on when you mention the existence of Scotland) 23:36:02 @google ₪ 23:36:02 No Result Found. 23:36:07 Useless bot. 23:36:21 ais523: .il 23:36:30 right 23:36:39 At one point $1 was ~₪5 23:36:40 ais523: yeah, I will never learn how that distinction works 23:36:57 well my internal money converter is still using the values from my childhood: 1$ ~= 10f (french francs), 1€ = 6.56f, 1 swiss franc = 4f, and 1$ is slightly less than 1€ 23:37:13 ais523: To be fair, even people who live in the UK are confused on the finer points. 23:37:19 ais523: Including elliott. 23:37:42 -!- monqy has joined. 23:37:54 elliott: Remember when I confused you by talking about the Isle of Man or something? 23:37:56 shachaf: you can start a mindboggling flamewar by asking whether England is a country or not 23:38:05 mindboggling because nobody's entirely sure of which side of the argument they're on 23:38:14 ais523: I'm with Rosencrantz. 23:38:24 (and when thinking about it you get "10 is slightly less than 7" but those rates might come from different times so it's ok) 23:38:46 where's guidenstern? 23:38:49 GUIL (leaping up): What a shambles! We're just not getting anywhere. 23:38:49 ROS (mournfully): Not even England. I don't believe in it anyway. 23:38:50 GUIL: What? 23:38:50 ROS: England. 23:38:50 GUIL: Just a conspiracy of cartographers, you mean? 23:39:06 copumpkin: Dead. 23:39:09 damn 23:39:29 I suppose Rosencrantz probably is too then 23:39:33 I think the latest terminology is that the UK is a nation, or a state, and that England, Scotland, Wales are countries, and screw all the smaller constituents of the UK because classifying Northern Ireland is a political minefield and the other places are too small to bother with 23:39:36 copumpkin: Did you see R&G Are Dead? 23:39:41 but I'm not convinced I agree with it 23:39:51 I read it at some point and then watched a video of a performance 23:39:51 copumpkin: Well, he's in a box. Take that as you will. 23:39:56 I don't remember much 23:40:13 It's good. 23:40:54 ais523: UK is a kingdom, obviously 23:41:04 ais523: and where do you place Great Britain in all that? 23:41:05 ROS: We might as well be dead. Do you think death could possibly be a boat? 23:41:05 GUIL: No, no, no... Death is... not. Death isn't. You take my meaning. Death is the ultimate negative. Not-being. You can't not-be on a boat. 23:41:08 ROS: I've frequently not been on boats. 23:41:11 GUIL: No, no, no - what you've been is not on boats. 23:41:17 elliott, explain the kingdom of fife?? 23:41:20 Arc_Koen: Great Britain has already been placed. 23:41:23 Phantom_Hoover: imposter. 23:41:25 It's pretty solid where it is. 23:41:35 elliott: Impost*o*r. 23:41:53 shachaf: I was referring to ais523: I think the latest terminology is that the UK is a nation, or a state, and that England, Scotland, Wales are countries, and screw all the smaller constituents of the UK because classifying Northern Ireland is a political minefield and the other places are too small to bother with 23:41:54 Arc_Koen: Great Britain is reasonably simple, it's a geographical term referring to an island 23:41:57 it's a reasonably large island 23:42:05 and it contains England, and most of Scotland and Wales 23:42:10 "The 14 British Overseas Territories are under the jurisdiction of the United Kingdom, though they do not form part of it." 23:42:58 what's the english name for that dash in ń character? 23:43:01 What about the Underseas Territories? 23:43:10 so the UK is a state that contains countries... and the US are a country that contains states 23:43:13 nooga: acute 23:43:17 shachaf: they are secret and don't officially exist 23:43:29 we don't have acutes in our own language, but we have a word for them so we can talk about them in other languages 23:43:34 ais523: thx 23:43:40 They're at Lantis. 23:43:56 nooga: we're not really used to seeing them on n, though 23:44:06 mostly we use them to talk about French because the French are closest 23:44:07 ćóńś 23:44:09 I'm beginning to learn dutch and they have acutes, though they seem to be saving them for onomatopoeias 23:44:13 and we used to repeatedly have wars with them 23:44:16 these are Polish 23:44:45 how is ń pronounced? 23:45:01 It's ńot. 23:45:01 like... give me a second 23:45:10 There should be a modifier for silent letters. 23:45:23 I'm pretty sure we have that in french 23:45:32 shachaf: silent letters should simply be removed 23:45:36 That's so cliché, ais 23:45:46 like ni in night 23:46:15 so ń alone is a whole syllable? 23:46:24 Silent letters are what they read in silent films 23:47:00 it's platal nasal consonant 23:47:04 not a syllable 23:47:11 it just sounds like ni in night 23:47:20 no 23:47:21 sorry 23:47:26 ghhh 23:47:29 nile 23:47:33 noooo 23:47:40 oh 23:47:42 i know 23:47:55 maybe the sound isn't used in english at all 23:47:58 "ghhh"? that's a weird way to pronounce an n 23:48:39 Pater ghoster 23:48:50 http://en.wikipedia.org/wiki/%C5%83 23:48:53 no idea 23:49:24 Ń (minuscule: ń) is a letter formed by putting an acute accent over the letter N. 23:49:45 I'm so glad wikipedia can teach me those things every day 23:50:05 seems it's the same sound as ñ in spanish 23:50:11 http://en.wikipedia.org/wiki/File:Pl-kwiecie%C5%84.ogg 23:50:18 olsner: yep, pretty much 23:50:37 -!- Phantom__Hoover has joined. 23:50:48 ó is pronounced like Polish u, which is like english oo 23:51:31 i think ś and ć do not exist in english 23:53:25 we've also got ł,ż,ź,ą,ę and ł 23:53:44 lol 23:53:46 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 23:53:48 ł and ł 23:54:01 don't forget rz, sz and cz 23:54:12 mind me if I go off-topic for just one second? - do you know of a brainfuck program I could feed my interpreter with to check for potential bugs? (instructions +-><[] are supposed to be working properly, instruction . works if the current cell is either 10 or 32-126, and instruction , is considered a no-op) 23:54:15 brzeszczot 23:55:00 szcz is a nice combo 23:55:10 brzeszczot -> knife edge 23:55:18 a sharp word 23:56:16 chrząszcz brzmi w trzczcinie w strzebrzeszynie, to remind the most known tongue breaker 23:56:36 let me guess, that's polish for "hi"? 23:56:50 no, hi is cześć ;) 23:56:50 hrm aren't we supposed to throw some vowels into that before even considering trying to pronounce it? 23:57:20 http://www.muppetlabs.com/~breadbox/bf/quine.b.txt 23:57:36 Jafet: thank you! 23:58:32 -!- kinoSi has quit (Read error: Connection reset by peer). 23:59:01 -!- kinoSi has joined. 2012-10-14: 00:00:43 http://www.ivona.com/pl/?tk=C3b7IPvKHx ;D 00:01:12 we've got all kkinds of sounds, from soft to harsh 00:01:43 strzebrzeszynie sounded a lot easier than it looks 00:02:31 see? 00:03:27 It helps a bit that English already loads up on consonant clusters. 00:03:45 Going from consonant clusters to more consonant clusters isn't too bad. :) 00:04:08 nooga: what are the smurfs called in polish? 00:04:16 smerfy 00:04:22 oh that's disappointing 00:04:32 their original name is "schtroumpf" 00:04:39 ugly 00:04:44 "Strengths". 6 consonant sounds, 1 syllable. 00:05:10 i would write this as sztrumf 00:05:16 that's way too much consonants for french already, so I would have assumed polish would go further in that direction 00:05:44 Arc_Koen: It's French, though. 75% of all letters in French are silent. 00:05:46 :) 00:05:56 not untrue 00:06:22 rendeszvous -> randevu? 00:06:25 I bet that's actually pronounced something like "sump" 00:06:30 rendez* 00:06:36 though in that case the only unnecessary letter is the starting s 00:06:54 no, it's pronounced like english "shtroompf" 00:07:06 Oh, the obvious way. 00:07:14 it's belgian or dutch, isn't it? 00:07:16 ais523: can you suggest a way to break my system 00:07:21 yes it's belgian 00:07:36 olsner: In the French language, and from Belgium. 00:07:47 fries 00:07:52 mayonaise 00:07:57 ais523: I've been kind of flabbergasted after removing my separate ext2 /boot partition and putting it into my JFS / *and* converting my MBR partition table to GPT in-place with no recourse if it all goes wrong failed to break my system 00:08:02 ais523: so I'm looking for some excitement 00:08:07 dutch speaking french 00:08:10 belgium 00:08:19 but since the smurf people use the word smurf to replace almost every words, so making a weird word like schtroumpf was part of the fun, I guess - and english smurf took that out 00:08:37 elliott: Have you considered mastering a Freddie Mercury impression and touring rural southern US? 00:08:45 i watched smurfs as a kid 00:08:57 and we had this all word fun with that 00:09:00 elliott: install windows 00:09:06 Arc_Koen: Yeah, "Smurf" is utterly *mundane* for English phonotactics. 00:09:16 smerfowe, smerfować, smerfetka, smerfastycznie & stuff 00:09:44 nooga: this summer I was in germany for two weeks - in a biergarten (some kind of pub) the waiter addressed us in german, then english, then french, then dutch 00:10:03 you're Belgian? 00:10:08 and I was so impressed until I realized he was probably simply belgian 00:10:12 no, I'm frenched 00:10:14 french 00:10:17 oh 00:10:21 Arc_Koen: I doubt anyone here would fail to recognize "biergarten". 00:10:24 -!- javad3v has joined. 00:10:24 pikhq_: what do you think I'm doing with my life 00:10:32 olsner: that would be kind of hard, since windows only boots from gpt on uefi systems 00:10:35 olsner: (for no apparent reason) 00:10:35 Arc_Koen: did you have to try four languages before you were able to order a beer? 00:10:52 hay guys 00:10:58 olsner: no I think he was just showing off 00:11:02 elliott: sounds perfect for making your computer not boot then? 00:11:14 though the first biergarten I had a beer in I felt kind of insulted 00:11:16 The transparent interpretation "beer garden" is actually a term in English that means "biergarten". :) 00:11:26 olsner: well it has to be something that the documentation says will work 00:11:28 and that I do apparently correctly 00:11:48 I asked for three beers in german - the waiter answered in english - I answered back in english - then he switched to french 00:11:54 elliott: Not getting discriminated against, clearly. 00:11:55 i wrote my own langauge called "navi" you should check it out 00:12:03 -!- augur has quit (Remote host closed the connection). 00:12:04 try ogródek piwny for your beer gaden and suddenly it's not so apparent 00:12:07 elliott: Nor imitating awesomeness. 00:12:12 javad3v: Hmm. 00:12:14 Arc_Koen: maybe you have a bad french accent 00:12:21 javad3v: link? 00:12:25 (and an english accent to your german?) 00:12:45 well I wouldn't be surprised if it was transparent that I was only pretending to know german 00:13:17 but switching to french felt really bad, even though he probably just overheard me when I was talking to my friends 00:13:30 its not finished yet sorry. the onky acceptable phrases are "hey" and "listen". its a BF derivative 00:13:37 -!- augur has joined. 00:13:48 navi! 00:13:52 Phantom__Hoover 00:14:03 in ocarina of time there's this place where navi would buzz if you walk over some stuff 00:14:18 if you do it right she would start stuttering 00:14:18 @seen Phantom__Hoover 00:14:18 Unknown command, try @list 00:14:20 play the acarecrowa song 00:14:21 oh no 00:14:43 I spent almost an hour trying to keep her stuttering Hehehehehehehehehehehehehehey listen! the longest possible time 00:14:44 Acarecrowa? Is this some weird transliteration? 00:14:51 javad3v: does it have to be a bf derivative 00:14:53 Akarekurowa? 00:15:21 javad3v: why not make it stack-based or even queue-based instead of brainfuck 00:15:31 or even tree-based, we don't have many tree-based languages 00:15:51 songi meant scarecrow im one my nexus7 and the keypad is coveri g up the textbox 00:15:56 befunge derivative, lolcode derivative, hq9+ derivative, snack derivative, esme derivative 00:16:01 Jafet: for the record your quine hasn't printed anything out yet 00:16:25 Arc_Koen: What about a hashmap of stacks of queues of arrays of integers? 00:16:28 i literally wrote the language in 5 minutes 00:16:54 as in wrote its specification or wrote an implementation or what 00:17:01 -!- nooga has quit (Ping timeout: 244 seconds). 00:17:24 javad3v: if it's a brainfuck derivative people will probably be reading about it in 5 minutes then move to something else but if it's tree-based we're gonna spend a whole month talking about it 00:17:29 all i did was make a file reader and writer that would take in the brainfuck source code and translate each symbol into either hey or listen 00:18:07 random thought: do we have a language based on raising and catching exceptions? 00:18:11 its not realkh a language i guess lol 00:18:19 being written in five minutes is something common to almost every brainfuck derivative, yes 00:18:21 For the record, it's not my quine 00:18:50 elliott: (\x -> x x) (\x -> x x) is a quine, right? 00:19:05 shachaf: i don't think so 00:19:23 Jafet: the webpage says it's brian raiter's 00:19:30 elliott: But it reduces to itself! 00:19:45 I'd say it is 00:19:49 then it's probably an infinite loop 00:19:59 under some notion of output 00:20:04 Every quine is an infinite loop if you run it ove and over. 00:20:47 -!- nooga has joined. 00:20:50 well if your system is "reduce the initial expression as much as you can, and when you're done output the result" 00:21:00 It's a quine in the college bum's lambda calculus, where you only bother to do one reduction 00:21:10 oh, ok 00:21:45 Jafet: Eh. In the advanced version you don't do any reductions. 00:21:50 ok well I guess I should switch to a faster thue interpreter 00:22:33 Is there an esolang called WVO? 00:22:42 There should be, so you could write a WVO Quine. 00:22:48 im probably going to make a navi derivative of java next... 00:22:53 cool 00:22:57 i'm struggling with peephole optimizer 00:22:58 how are you going to do that 00:23:26 just translate reserved words into either hey or listen 00:23:44 cool cool 00:23:56 monqy: Is that a quine? 00:24:01 In "cool language" 00:24:26 yes 00:24:27 anyone want to download mg binary complier? it literaly complies and runs binary 00:24:54 ooh hey I have an idea for a brainfuck derivative 00:25:01 me too 00:25:09 i wrote it in mgblolobogoblol or whatevr its called 00:25:15 javad3v: what is your problem? 00:25:47 Lots of people make BF derivatives. How many people have made BF integrals? 00:25:48 umm i dont knoe are you talking aboug my grammar and w/e? 00:25:53 it's exactly the same as brainfuck except + is replaced with "smurf", - is replaced with "smurf", > is replaced with "smurf", < is replaced with "smurf", . is replaced with "smurf", , is replaced with "smurf", [ is replaced with "smurf" and ] is replaced with "smurf", 00:26:15 ha ha ha. 00:26:34 and now begins the very hard struggle to not make that a wiki page 00:26:36 javad3v: what is mgblolobogoblol 00:26:52 So, s/[\[\]><+\-.,]/smurf /g 00:26:56 mgblolobogotroll 00:27:06 whatevrr that language is thats named after a level in hell or whatever 00:27:15 well he is obviously full of shit 00:27:17 Malbolge 00:27:20 but it'd be nice to know exactly what he's full of shit about 00:27:25 Which is a properly awesome esolang. 00:27:53 *village idiot drools on you* 00:28:40 javad3v: would you like to share your mgblolobogoblol compiler 00:28:48 someone should make an esolang thats a fucked up fortran called "4chan"... 00:29:03 good joke? 00:29:10 `WELCOME JAVAD3V 00:29:20 JAVAD3V: 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.) 00:29:22 welcome javad3v 00:29:23 uh hi 00:29:52 javad3v: sorry but you have been mislead. this channel is actually about mysticism and spirituality. 00:30:08 oh well i know all about that too 00:30:12 *misled 00:30:18 read/read, lead/led 00:30:20 misleaded 00:30:31 mh lead 00:30:34 copumpkin: no, he's been, in the past, the abstract concept of the verb mislead 00:30:35 elliott: What about rivenicism 00:30:45 * copumpkin slaps elliott 00:30:47 copumpkin: misle/misled 00:30:53 so how about that jesus guy? 00:31:04 shachaf: of course 00:31:30 i work at google just so you guyss know 00:31:38 What happened to the "your behavior is not conducive to the desired environment" message? 00:31:41 I miss that one. 00:31:43 javad3v: good to know 00:31:50 i programmed their autonomous car thing 00:31:56 or our 00:31:58 great 00:32:01 can it drift? 00:32:03 TIL 00:32:07 autonomously? 00:32:16 yes i drove it 00:32:18 yes 00:32:19 ais523: can you kick javad3v 00:32:21 autonamously 00:32:30 javad3v: I did it better though 00:32:31 ais523: it would be ok if he was amusing but these are just boring lies!! 00:32:31 fuck no i cant esolang too 00:32:36 I programmed the curiosity rover 00:32:40 mine drives itself, but on mars 00:32:46 ais523: 0/10 not entertained 00:32:46 inpr 00:32:46 I *am* the curiosity rover. 00:32:49 i programmed a brainfuck derivative 00:32:55 mee to 00:32:58 you can do calculus on languages? 00:33:00 monqy wins. 00:33:05 and i'm drunk 00:33:09 and still behave 00:33:14 17:25 Lots of people make BF derivatives. How many people have made BF integrals? 00:33:15 i can do calculus 00:33:16 is the integral of your brainfuck derivative isomorphic to brainfuck? 00:33:20 mine translates the word "hello" to brainfuck codes 00:33:25 i think i win 00:33:27 I programmed jokes into copumpkin's mind. 00:33:29 shachaf: asshole 00:33:33 woa wo wos know you limits 00:33:38 no 00:33:43 shachaf: please don't repeat that too often, I'm probably not gonna sleep until I begin to find a way to make that have sense 00:34:05 copumpkin: Sorry. :-( 00:34:07 javad3v: Whoa, *nobody* can do calculus. :P 00:34:12 you'd better be 00:34:13 GASP 00:34:19 where's oerjan?! 00:34:24 he was always here 00:34:27 why not? 00:34:28 he's gone to sleep 00:34:32 no way 00:34:33 man 00:34:34 copumpkin: I'm not just sorry, I'm pathetic. 00:34:35 no way 00:34:36 It's true. 00:34:41 qqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 00:34:42 he never sleeps 00:34:58 or I've been misled by his comment "this is not how the alphabet works. good night" 00:35:00 Our Lord Oerjan hath need to give obeisance unto the cycle of time 00:35:12 qqqqqqqqqqqqqqqqqqqqqqqqqqqqqq q qqq qq 00:35:19 javad3v: you broke elliott 00:35:24 javad3v: plaese use your calculus to fix him 00:35:31 im making the channel better 00:35:38 with qs 00:35:44 q 00:35:47 try q:qs 00:35:50 javad3v: he thinks hes making the channel better but really hes not (he thinks that because hes broken because you broke him) 00:35:57 Q: Where does a general keep his armies? 00:36:02 A: In his sleevies! 00:36:04 okay tangent line of f(x) = 4x/x≥2 00:36:19 elliott: feeling better? 00:36:33 monqy: q 00:36:36 :[ 00:36:38 hum is the x≥2 in that formula some kind of boolean statement? 00:36:59 though "four x divided by false" sounds very wrong 00:37:00 It's a troolean statement. 00:37:00 i was looking for the power of symbol but i got lazy 00:37:07 It's called troolean because it's always true. 00:37:15 copumpkin: Did you see my pun from before? 00:37:18 troll science 00:37:23 you don't know it 00:37:25 javad3v: what's it like in virginia 00:37:34 bad:( 00:37:41 WV > VA 00:37:46 shachaf: I'm sorry I've only learned foolishean logic so far 00:37:53 lolololoolololololLoLOLOLo 00:38:00 what's so funny 00:38:03 wv are all inbred 00:38:07 i missed it because my eyes are bad 00:38:13 i'll ned you to point it out 00:38:13 oh no :'( 00:38:19 monqy: want a pun 00:38:19 ais523: hi 00:38:26 11:34 I found this to be a very nice informal intro: "Some of the best things in life are free; and some are not. Truth is free. Having proved a theorem, you may use this proof as many times as you wish, at no extra cost. Food, on the other hand, has a cost. Having baked a cake, you may eat it only once. If traditional logic is about truth, then linear logic is about food" 00:38:32 11:35 Unless you're Zeno. 00:38:35 11:35 Zeno knew how to halve his cake and eat it too. 00:38:36 at least we have uva and tech in VA 00:38:39 GOOD PUN 00:38:40 or 00:38:42 BEST PUN 00:38:51 Jafet: well it still hasn't printed anything so I'm shutting it off 00:39:22 UVA is pretty good for comp sci 00:39:32 apparently not 00:39:40 ais523: you're talking in #acehack you can't hide 00:39:40 y 00:39:42 ais523: stop hiding 00:39:48 ais523: come out of rehidement 00:39:59 I'm afraid that "sqrt(2) is irrational" pun is on top of my best puns list and a cake that's not even lying is never gonna top that 00:40:27 i dont get it 00:40:35 what a surprise 00:41:10 sqrt of 2 is like 1.2 or something 00:41:22 ais523: come on 00:42:21 my programming language programmes on a tree branch derivstive of the stack overflowing alu unit 00:42:42 wow mine too 00:42:43 directley 00:42:52 pff who would do it any other way 00:43:10 monqy: i do it indirectly :'( 00:43:33 for shame 00:43:54 javad3v: http://www.docstoc.com/docs/35998870/Towards-the-Syn-thesis-of-Vacuum-Tubes < here's an interesting paper for you 00:43:59 my programms gomright to the stack on an extra-hytercenary exchange unit derivived from the alu 00:44:01 i think you'll like it 00:44:33 read it 00:44:41 ais523: . 00:44:51 nexus7 doesnt have flash so i csnt 00:45:37 http://raisama.net/ufpr/tg/paper.pdf 00:45:49 grab a pdf version 00:46:03 k 00:46:56 huh 00:47:25 i already wrote a fully conciouss computer 00:47:34 ais523: !!!! 00:48:04 heres proof:[proof] 00:48:39 what language was assembly written in? 00:48:46 javad3v: do you realise how fucking dumb & stupid & unfunny you are 00:48:53 yes 00:48:53 i think that any AI would be more I than you, javad3v 00:48:57 javad3v: hi 00:48:57 like i realise you are bullshitting on purpose and that me saying this probably counts as a victory to you 00:48:58 but 00:48:59 ok 00:49:07 -!- ChanServ has set channel mode: +o ais523. 00:49:08 i think you have to pay special attention to just literally how unconvincing you are 00:49:16 ais523: sec 00:49:19 let me read scrollback, sorry, I was somewhere esle 00:49:20 you're really bad at trolling!! 00:49:20 *else 00:49:20 on the other hand 00:49:21 because im bored and my program didnt work so i came here 00:49:38 you'd pass a turing test 00:49:48 hello javad3v 00:49:54 thanks man i appreciate it 00:49:55 i hear you are making a brainfuck derivative 00:50:02 javad3v: well talking a load of nonsense isn't going to work very well, really 00:50:04 Phantom__Hoover: stop :D 00:50:05 Phantom__Hoover: i prepared a brick 00:50:07 trolling can be fun to watch 00:50:08 i already made one dude 00:50:12 but only if it's done well 00:50:39 its done well 00:50:45 no, I meant trolling 00:50:47 not BF derivatives 00:50:51 oh stop already 00:50:51 i wrote it in java 00:50:55 most people who think they've done one well are wrong 00:50:58 here's what's going to happen 00:51:02 i am going to find you 00:51:05 wherever you are 00:51:07 (I think I've done two well, but I may be wrong about that) 00:51:08 Phantom__Hoover: virginia 00:51:11 hth 00:51:22 im in , that was already stated 00:51:28 Phantom__Hoover: have you ever actually gone through with that threat? 00:51:41 ais523: do you have any evidence he has ever /not/ gone through with it? 00:51:47 once i find you 00:51:52 i live in the rotunda at UVA cause im the smartest one here 00:52:00 ais523: people with bricks for brains rarely talk, after all 00:52:11 i will smash this brick into your head so hard 00:52:11 javad3v: may i give you a trophy for being the smartest one here 00:52:14 "you deserve it" 00:52:15 elliott: I'd think we might hear about it if he got arrested 00:52:21 Phantom__Hoover: note that death threats are illegal 00:52:23 ais523: that just means he's really good at it 00:52:27 that says much about the UVA 00:52:35 whatever it is 00:52:36 you will think you're a flying house 00:52:44 ais523, when did i say i'd kill him 00:52:51 they paid me $100000 more than harvard offered so i chose UVA 00:52:58 killing him would be too kind 00:53:01 it's sort-of implied, most people can't survive their brain being replaced 00:53:13 maybe i only target those who can? 00:53:14 javad3v: anyway are you here to be constructive? I unstealthed my ops for a reason 00:53:16 scots can 00:53:23 "are you here to be constructive" 00:53:25 javad3v, shitty trolling counts for brickbraining too 00:53:25 great question 00:53:29 "oh, you got me... nope!" 00:53:32 elliott: I'm looking forward to the answer 00:53:36 yes i can here to talk about navi 00:53:38 ais523: i think it wouldn't change much 00:53:48 "truly my career of TROLLING is over" 00:53:49 javad3v: note: the answer is supposed to be comprehensible 00:53:51 my bf derivative 00:53:52 "i am undone" 00:53:55 javad3v, lemme guess, the commands are some permutation on 'hey' and 'listen' 00:54:00 Phantom__Hoover: yes that is literally what he said 00:54:02 when he came in here 00:54:03 yes 00:54:14 Phantom__Hoover: you didn't know that though -- you just made a bf derivative o nIRC 00:54:15 oh right 00:54:18 I really don't think the world needs that BF derivative 00:54:21 i wrote it in 5 minutes 00:54:25 Phantom__Hoover: i prepared a brick to replace your brain 00:54:29 that's not a brainfuck derivative, that's a brainfuck substitution 00:54:35 equivalent? 00:54:36 yeah i know 00:54:36 Phantom__Hoover: and those don't get brickbrained? 00:54:37 elliott, i don't have a brain, i'm a hoover 00:54:45 elliott, they get brickbrained 00:54:53 then they get put into the 11th circle of hell 00:54:58 i have a brain the size of einstej 00:55:04 ais523: Death threats are illegal? 00:55:06 hey listen brick brain translates to [+-] 00:55:07 which is basically a continuous rain of alternating bricks and brains 00:55:08 shachaf: sure 00:55:12 especially in the UK 00:55:14 where Phantom__Hoover is 00:55:17 nooga, fuck off 00:55:24 :D 00:55:29 javad3v, not once i'm through with you you won't 00:55:29 sorry, true story 00:55:56 when youre through with me it will be the size ofmyours probably ohhh 00:55:57 -!- Vorpal has quit (Ping timeout: 276 seconds). 00:56:02 [+-] doesn't do anything at all 00:56:09 that's right 00:56:22 i just said i don't have a brain 00:56:31 damn 00:56:35 einstej 00:56:44 fhata me 00:56:49 ais523: well technically it's a conditional statement "if the current cell is zero, carry on, otherwise get stuck here" 00:57:00 discoverer of twelve species of beetle 00:57:04 Arc_Koen: I meant as a whole program 00:57:08 ais523: could you please get rid of javad3v so we can get back to our nightly routine? 00:57:09 the current cell is 0 00:57:16 nooga: our nightly routine isn't so useful 00:57:17 no, please 00:57:22 but I don't think he's being useful anyway 00:57:32 I think the original idea was that cells contain unspecified values 00:57:33 ais523: imo op javad3v 00:57:36 it'd be nicer if he just left of his own accord, but I can kick him given that he clearly isn't being constructive 00:57:38 what language was assembly writte in? i must know 00:57:43 javad3v: navi 00:57:51 o 00:57:57 ais523, op javad3v, voice Gregor 00:58:01 javad3v: machine code, obvs 00:58:01 now that's meta! 00:58:03 and if it doesn't allow wrapping, then if the current cell is 255 it might set it to 254 00:58:12 Phantom__Hoover: I could voice Gregor 00:58:17 do it do it 00:58:17 at least, I can't think of a good reason not to 00:58:26 he's so upstanding! 00:58:32 has he done something wrong? 00:58:35 what language was c written . 00:58:37 he would be a credit to us all with his powers 00:58:41 uh 00:58:41 javad3v, b 00:58:43 -!- ais523 has kicked javad3v not being useful. 00:58:45 his endless voice powers 00:58:56 it's 6 PM in San Francisco 00:59:04 why is not Gregor here 00:59:04 ais523: if not being useful is a kick reason then boy howdy are my days numbered 00:59:12 elliott: you're more useful than javad3v was 00:59:14 Gregor is in SF? 00:59:15 wow 00:59:17 what a compliment 00:59:28 -!- ais523 has set channel mode: +v Gregor. 00:59:30 -!- ais523 has set channel mode: -o ais523. 00:59:31 ais523: I'm not sure "obviously" is accurate here - most people wouldn't make a difference between assembly and machine code 00:59:49 Arc_Koen: why not? they look pretty different, after all 00:59:54 they are not the same thing 00:59:59 whois codu.org says Portland. 00:59:59 shachaf: San Francisco is in the US, Gregor is in the US 01:00:01 especially since most assemblers have things like structs and macros and 01:00:04 also, asm is compiled and machine language is interpreted, usually 01:00:08 -!- javjav has joined. 01:00:08 because most people wouldn't look at them in the first place :) 01:00:15 hey guys 01:00:18 hi 01:00:19 ais523, remind me, are you in birmingham or manchester 01:00:19 javjav: wow 01:00:22 javjav: we just had someone from virginia! 01:00:25 whose name started with "jav" 01:00:27 i'm almost positive it's manchester 01:00:28 what a coincidence 01:00:30 thats not me 01:00:31 what a coincidence 01:00:40 dont ip ban me pls 01:00:47 i didn't even look up javjav's ip 01:00:51 i just assumed 01:00:52 "busted" 01:00:55 Yes, I'm in SFO. It is a good place to be. 01:00:56 huh 01:01:07 Phantom__Hoover: I'm in Birmingham 01:01:09 so about navi 01:01:10 javjav: just tell us 01:01:13 I was trying to think of a creative lie 01:01:15 navi? what's that 01:01:16 but I couldn't 01:01:17 ais523, omg i'm in coventry! 01:01:18 never heard of any navi 01:01:19 we could like 01:01:21 And it's 6PM on a Saturday, so I should be out having fun, but am instead here, alone in my apartment. 01:01:25 have the saddest esolang weekend 01:01:26 javjav: how did you end up in here... and why? 01:01:27 Phantom__Hoover: that is almost close enough to walk 01:01:29 but not at 2am 01:01:31 ais523: don't do it 01:01:35 ais523: he wants to replace your brain with a brick 01:01:41 he knows about your BF derivatives!! 01:01:42 i like esolangs 01:01:43 s/weekend/meetup/ 01:01:43 elliott: but my BF derivatives are actually good 01:01:53 ais523: "At some point, I shall snap and everyone who has posted a stupid Brainfuck derivative (read: a Brainfuck derivative) to this wiki will have their brains forcefully replaced with a large brick." 01:01:58 ais523: looks pretty unambiguous, friend 01:02:12 i didnt post mine to thenwiki 01:02:21 elliott: I could just meet him somewhere where there are plenty of people around 01:02:25 this is usual anyway 01:02:32 when meeting someone you only know from the Internet 01:02:38 ais523: i'll come to birmingham for irl intercal lessons as long as i can punch Phantom__Hoover 01:02:42 I guess the real question is are there BRICKS around? 01:02:43 perhaps i could charitably call them 'brainfuck variations' 01:02:44 monqy: you'll come too right 01:02:49 imdont get it, how are any of you being constructive?? 01:02:49 Arc_Koen: yes but they're mostly attached to buildings 01:02:53 javjav: we're not! 01:02:56 that's the big joke of #esoteric 01:02:59 elliott: no im too busy doing monqy things 01:03:00 none of us are ever constructive, ever 01:03:01 elliott, aren't you trapped in the body of a 10-year-old girl 01:03:09 elliott: I could be constructive right now 01:03:10 but i was kicked for that 01:03:12 monqy: how can anything be more important than irl intercal lessons with ais523 01:03:13 I even have something to talk about 01:03:19 javjav: you were kicked for just not getting the point 01:03:22 javjav: no you weren't, you just said you weren't javad3v 01:03:23 "I even have bricks to construct with" 01:03:26 javjav: stop lying about being kicked 01:03:32 you guys are so constructive i twitch when lecturers do proofs by contradiction 01:03:35 it was javad3v that was kicked 01:03:38 i died and was reborn 01:03:43 me too 01:03:46 into this new body 01:03:55 i didn't get a body :( 01:04:00 ok 01:04:02 i got your body 01:04:03 im sorry 01:04:10 give it back you little sot 01:04:13 no 01:04:13 my body 01:04:17 im not that sorry 01:04:23 -!- ChanServ has set channel mode: +o ais523. 01:04:24 Gregor: I didn't know you were in SF. 01:04:28 javjav, how close are you to monqy again 01:04:30 -!- ais523 has kicked javjav still doesn't get it. 01:04:39 Gregor: Are you a Haskell person? You should go to the bahaskell meeting next week! 01:04:49 monqy: how about return PH's body at the irl intercal lessons 01:04:52 "a perfect ocmpromise" 01:04:54 I'm not really a Haskell person. Not enough, anyway. 01:04:58 o do you use the "still doesn't get it" field to explain the kick to us or to him? 01:05:06 both 01:05:11 Arc_Koen: yes, both 01:05:14 Arc_Koen: neither 01:05:18 elliott: but how would i get there 01:05:21 he uses it to explain it to the president 01:05:23 -!- unambiguous has joined. 01:05:24 elliott: I'm happy to teach people INTERCAL any time I'm free, anyway 01:05:26 who personally reviews every kick on irc 01:05:30 ais523: gosh i wonder who this unambiguous person is 01:05:35 oh I wasn't aware of that 01:05:36 ais523: please don't ban them it's really funny to see them keep trying 01:05:47 just keep kicking 01:05:47 Gregor: Not enough as in you'd like to be more of one, or as in you have no reason to go to bahaskell? 01:05:47 unambiguous: you are aware your IP is in your hostname, right? 01:05:48 forever 01:06:02 shachaf: The latter. 01:06:04 my name is scott and im from northen ireland 01:06:07 elliott: actually I'm not entirely sure how to formulate the ban to affect only the correct people 01:06:18 and it's at least starting to get slightly amusing 01:06:22 unambiguous, unfortunately the only thing i hate more than brainfuck derivatives is northern ireland 01:06:35 im not from northern ireland 01:06:52 yes you're from northen ireland, you said that already 01:06:53 you could even say your place of origin is... ambiguous 01:06:53 fuck it 01:06:56 im from eastern india, baghdad to be exact 01:07:00 i'm going to sleep 01:07:08 i will get back when things settle 01:07:09 got to be more pleasant than northern ireland 01:07:17 hmm, are there any actual irish esolangers (northern or republic)? 01:07:23 TIL: Baghdad is in India X-D 01:07:26 nooga: how can you tell when to wake up? 01:07:27 im from VA 01:07:34 Gregor: just like Birmingham is in both the UK and the US? 01:07:42 ais523: i said that i will get back 01:07:48 not wake up 01:07:49 im in the rotunda 01:07:53 nooga: come on, this is fun 01:07:55 oh 01:07:57 nooga: so you'll come back while asleep? 01:07:58 "party" 01:08:14 have you met a guy there with a brain the size of einstej 01:08:18 ais523: Yes, with the exception that the Indian one isn't real. 01:08:18 i will wake up, eat breakfast, read the logs 01:08:19 http://esolangs.org/w/index.php?search=guinness seems to imply there are no irish esolangers 01:08:23 -!- ais523 has kicked unambiguous you keep getting kicked for a reason. 01:08:25 and then join the # again 01:08:59 Arc_Koen: good one, a bit 01:09:31 -!- Steven86 has joined. 01:09:35 http://esolangs.org/w/index.php?search=bomb suggests there are some northern irish ones though 01:09:49 Phantom__Hoover: not funny 01:09:51 lfmao 01:10:05 good night 01:10:14 Steven86: sup 01:10:15 my favorite esolang has to be chef 01:10:17 i did not aim for humour, merely offence 01:10:42 Phantom__Hoover: you're better than that 01:10:45 hi steven 01:10:47 does anyone here know chef? 01:10:51 `addquote i did not aim for humour, merely offence 01:10:55 872) i did not aim for humour, merely offence 01:10:59 elliott, not when it comes to northern ireland 01:11:02 hey monqy 01:11:06 have we played the quotes game anytime recently 01:11:10 `quote 01:11:11 `delquote 872 01:11:11 maybe we could get steven's input 01:11:11 `quote 01:11:13 `quote 01:11:14 `quote 01:11:16 `quote 01:11:20 What did Phantom__Hoover say? 01:11:21 153) < ais523> then running repeatedly until you get the right sequence of random numbers < ais523> and just completely ignoring the input <-- some people live their entire lives this way, i reckon 01:11:26 49) ??? Are the cocks actually just implanted dildos? Or are there monster dildos and cocks? Or are both the dildos and cocks monster? 01:11:27 elliott: bonus points if 872 is one of the random ones 01:11:30 Sgeo: it's in the logs 01:11:37 Oh, connecting bombs to Northern Ireland? 01:11:49 i thought this chsnne 01:11:56 490) oerjan: I'm not imaginative enough to write truly great slash fiction 01:11:59 19) there is plenty of room to have two heads 01:12:00 ​*poof* i did not aim for humour, merely offence 01:12:01 wtf is the context of 49 X-D 01:12:04 channel was about esolangs? 01:12:04 i thought this chsnne too 01:12:07 470) Tomorrow's computer viruses will extend robotic arms from your computer to fiddle with the SD card to infect it!! 01:12:09 Steven86: no 01:12:12 totally wrong 01:12:16 oh ok 01:12:24 ^welcome Steven86 01:12:25 Steven86 : 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 esote ... 01:12:25 this channel is about feudal japan 01:12:27 we're about neopagan spirituality 01:12:34 feudal japan and neopagan spirituality 01:12:36 and its applicability to feudal japan 01:12:49 whag about neonatzism 01:12:50 IMO 470 01:13:00 19 is bad, but it's there to provide context to the following quotes 01:13:02 ais523: you can kick him now 01:13:04 elliott: agreed 01:13:11 who? 01:13:14 -!- ais523 has kicked Steven86 User terminated!. 01:13:17 oh, hmm 01:13:20 user terminated 01:13:24 `delquote 470 01:13:26 that's my client's default kick message 01:13:28 ​*poof* Tomorrow's computer viruses will extend robotic arms from your computer to fiddle with the SD card to infect it!! 01:13:29 and I never bothered to change it 01:13:31 it's good 01:13:32 `quote 01:13:32 `quote 01:13:32 `quote 01:13:33 `quote 01:13:33 `quote 01:13:37 We need `unwelcome 01:13:47 148) You people. You people are so stupid. I'm making a SOCIOLOGICAL statement here. 01:13:58 elliott, why did you delete 872?? 01:14:08 well it wasn't funny 01:14:16 846) i just hit enter b/c its easier than ctrl+a del 01:14:22 -!- nooga has quit (Ping timeout: 244 seconds). 01:14:24 521) im hungary too...but cnnot eat until hours 01:14:26 48) no Deewiant No?! I've been living a lie yep. Excuse me while I jump out of the window -> 01:14:27 217) vorpal: a lot of people in AK fly quintopia, well getting a pilot cert is a lot more complex than a driving license :P being an AK resident is a lot more complex than a driver's license too 01:14:30 511 is bad 01:14:30 uh did you READ the quote? 01:14:32 btw, 153 is a programming technique I was seriously considering for /ˈæmbiːɛf/ 01:14:32 Arc_Koen: btw i think we do not have such a category 01:14:38 `quote 511 01:14:46 511) Maybe if you try diplomacy. Pointy steel diplomacy 01:14:48 which is /so/ its official name, now 01:14:51 monqy: itym 521 01:14:53 I mean, it always was 01:14:57 i quite like 521 because it says hungary 01:14:57 but that's how you write its official name down 01:15:04 elliott: yes i meant 521 01:15:05 `quote 521 01:15:08 521) im hungary too...but cnnot eat until hours 01:15:08 elliott: btw, will that name work on the wiki? or will it cause similar problems to ///? 01:15:13 ais523: thanks for reminding me that http://esolangs.org/wiki//// is broken 01:15:16 ais523: well I can fix that 01:15:18 it's just a configuration change 01:15:25 but it requires admitting to myself that I'm never going to finish setting up mailman 01:15:31 which requires emailing taral to tell him i can't do it 01:15:34 elliott: well that was kind of a rhetorical question anyway 01:15:39 which requires getting over procrastination + stress 01:15:45 oh, I sort-of thought you were running the lists atm 01:15:46 so probably it will happen in ten years 01:15:50 heh 01:16:24 -!- encapsulated314 has joined. 01:16:26 who is, then? still Taral, on a system that no longer exists? 01:16:46 yes 01:16:46 -!- micrypt has left. 01:16:53 `WELCOME encapsulated314 01:16:56 ENCAPSULATED314: 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.) 01:17:01 encapsulated314: Hi! Welcome to the Esolang channel. 01:17:05 encapsulated314: hello, this is a channel about esolangs 01:17:12 encapsulated314: Hey, we have a wiki at http://esolangs.org/wiki/Main_Page! 01:17:15 encapsulated314: hi there what's up 01:17:23 encapsulated314: have you heard of the gret new language "navi" it's what we'vre been talking about 01:17:23 encapsulated314: Good evening! This is a channel about esoteric programming language. 01:17:25 s. 01:17:28 * Sgeo vaguely hopes that this isn't some person stalking me 01:17:33 encapsulated314: What's up? Here we talk about esoteric programming languages! 01:17:34 it's a brainfuck derivative with "hello" and "listen" 01:17:45 monqy: have you ever actually played Ocarina of Time? 01:17:49 encapsulated314: Hey, how are you doing? Here we talk about the new & exciting happenings in the world of esoteric programming languages! 01:18:03 elliott is lying. 01:18:05 Kick him, ais523. 01:18:10 ais523: one time I got into the deku tree and got either stuck or bored 01:18:19 monqy: that's my ocarina of time experience too 01:18:19 how can you mock navi then 01:18:20 ais523: or I started and got there and realized I didn't want to play it 01:18:26 shachaf: I was going to wait for a random amount of time, and then kick him 01:18:28 you don't understand the depth of her character 01:18:29 * Sgeo has erm, heard of Ocarina of Time 01:18:34 Phantom__Hoover: I was thinking more of the misquote 01:18:38 I got further in majora's mask!!! all the way to uhh I forget what it's called 01:18:40 ais523: hey, kicking me is immoral 01:18:44 I think I got the compass in woodfall temple 01:18:44 I'm useful! 01:18:52 navi says hello as well 01:18:59 * Sgeo has watched Legend of Neil, for what little that's worth 01:19:07 monqy: all I remember about majora's mask is it had some realtime-based mechanic (related to the three days thing I think???) that really stressed me out 01:19:07 monqy: the funny thing is that tatl, the navi-version in majora's mask, actually does have quite some character depth, and even development 01:19:09 so I couldn't play it 01:19:14 whereas navi is just a tutorial fairy 01:19:23 i played oot but i was shit at it 01:19:25 elliott: yes, the world ends in three days 01:19:31 you can reset the world 01:19:31 monqy: I think it turned out I also misunderstood the mechanic as much more tight than it actually is 01:19:33 j] 01:19:34 later 01:19:36 erm 01:19:46 and get a bit further due to accumulated knowledge, also items for some reason 01:19:48 now the woodfall temple song is stuck in my head 01:19:49 i was too scared to actually fight things 01:20:02 ais523: all I remember is a day seemed to go by awfully quickly in real time!! 01:20:07 it does 01:20:09 so i just fucked around in towns 01:20:15 you can slow it down from the second cycle onwards 01:20:17 ais523: so I was scared I wouldn't be able to win in time 01:20:17 you can do a song to make days go by slower 01:20:18 play the song of time in reverse! 01:20:20 right 01:20:21 I didn't nkow that 01:20:23 the first cycle is the only one with real time pressure 01:20:25 I thought you just had to play fast!! 01:20:32 and even then there's huge amounts of slack 01:20:32 you still do 01:20:38 thats to skip half a day 01:20:47 encapsulated314: no 01:20:48 there are some sidequests that have to be completed in a single cycle 01:20:59 if you're going to give people factual advice about Majora's Mask, please don't get things muddled 01:21:00 yss 01:21:02 I also had windwaker I think 01:21:04 -!- ais523 has kicked encapsulated314 User terminated!. 01:21:05 but never played it much at all 01:21:11 you have to repeat the notes to skip half a day 01:21:19 playing it backwards slows it down 01:21:23 other things that get you kicked in #esoteric: giving misleading information about zelda games 01:21:24 to 1/3 normal speed 01:21:30 learning lots today 01:21:39 hmm, come to think of it i think my basic problem with the zelda games was that when i played them i wanted to be playing a tes game 01:21:41 elliott: it's more that if someone has proven themselves kickworthy 01:21:44 you can kick them for any reason at all 01:21:51 Phantom__Hoover: tes? 01:21:58 ais523: next time try kicking them as soon as they join before they say anything 01:21:59 the elder scrolls? 01:22:02 it'll be funny to see how they react the next time 01:22:06 after that I mean 01:22:08 it's quite a popular series 01:22:10 Phantom__Hoover: aha 01:22:14 just didn't get the acronym 01:22:31 I know of the series 01:22:39 it's also really badly broken, most of the games in it I mean 01:22:50 i know 01:22:53 such as the way in Morrowind that you can create potions that make you better at creating potions 01:22:57 and go exponential with it 01:23:02 the morrowingularity! 01:23:04 -!- obfuscatedC has joined. 01:23:36 fun fact, CHIM is actually a pile of yams and leather 01:23:39 ais523: you can also walk on floating paintbrushes, I hear 01:23:52 Phantom__Hoover: the silly thing is that that isn't even the fastest way to complete it 01:24:00 -!- ais523 has kicked obfuscatedC same person…. 01:24:08 everyone pretends it's all mystical and incomprehensible because it sounds cooler that wy 01:24:09 *way 01:24:25 ais523: or is that oblivion? 01:24:33 that's oblivion 01:24:56 there's a stat in both that affects your jumping height though 01:25:05 -!- IWontSayAWord has joined. 01:25:10 ais523: you don't have to kick this one 01:25:12 he won't say a word 01:25:20 and in morrowind there are 3 unique scrolls that let you jump clean across the game world 01:25:26 right 01:25:28 i've seen that speedrun 01:25:41 Phantom__Hoover: the difficulty is landing, right? 01:25:52 ais523, you need to use another one to land, yeah 01:25:59 (the developers put that in as a joke, but it turns out it is indeed possible to survive the landing) 01:26:01 what happens if you don't 01:26:04 do you die on landing 01:26:06 splat 01:26:10 mmm 01:26:13 what scroll lets you land 01:26:18 the one that lets you jump 01:26:32 the stat affects your jumping height and the distance you can fall before taking damage 01:27:22 so basically you can jump once, and after that it's just an elaborate way of committing suicide 01:27:56 also the game in general is just broken 01:28:23 especially if you know where to get the good equipment 01:29:07 * Sgeo wishes he knew for certain that the weird person repeatedly entering wasn't a particular person stalking him 01:29:24 Sgeo: you have a stalker? 01:29:27 actually, I can believe that 01:29:34 but we think it's just a troll 01:29:42 Sgeo: is your stalker in virginia 01:29:55 btw said person is in the channel 01:30:04 ais523, well, was being harassed on Facebook and via phone about a month or so ago. And no, not in Virginia 01:30:31 their ip geolocates to virginia 01:31:13 Ok 01:32:25 im not a stalker im just bored as fuck /end break of rules 01:33:08 ais523: kick IWontSayAWord for lying 01:33:10 (their name is a lie) 01:34:50 Sgeo, why were they stalking you 01:34:57 is everyone here communicating in skm 01:35:11 some way i cant see or aomething? 01:35:41 yes 01:35:48 we're communicating in sign language 01:36:00 i communicate in navi 01:36:05 -!- Jafet has quit (Quit: Leaving.). 01:36:22 heyheyeh 01:36:24 i communicate exclusively in braille. 01:36:26 Hey! Listen! 01:36:33 if you put your finger on your screen hard enough you can feel the bumps 01:36:47 monqy: i think that's just my finger hurting 01:36:49 IWontSayAWord: Hey! Listen! Hey! Listen! 01:36:51 help 01:36:53 monqy: ow 01:36:55 monqy: ow ow ow 01:36:57 monqy: make it stop!!!! 01:37:02 im pressing but it keeps hurting 01:37:06 heyheyheyheyheylistenheyheyhey 01:37:13 monqy: im dying of pain 01:37:25 ok, confirmed. he does speak navi 01:37:31 have you tried using your other finger 01:37:34 monqy: ok 01:37:41 hows france elliot 01:37:46 now they're both hurting!!! ow ow ow ow ow ow ow 01:37:46 ow 01:37:54 IWontSayAWord: it's great. the best countries are the ones i'm not in ow ow ow 01:37:58 maybe it's your computer screen that hurts 01:38:11 -!- Phantom_Hoover has joined. 01:38:21 sup 01:38:31 monqy: it's my life........... 01:38:32 my life hurts 01:38:38 im holding tab and watching the "Hoover" dance 01:38:52 Phantom_Hoover: 01:38:53 everyone here is from different countries 01:38:53 good dance 01:39:03 hehehe 01:39:06 IWontSayAWord: ais523 lives in france with me 01:39:09 that's a funny dance 01:39:24 also i live in hexham with comex 01:39:39 monqy lives with shachaf 01:39:46 monqy *is* shachaf 01:40:12 and shachaf is elliott and elliott is school 01:40:14 conclusion? 01:40:19 shaahshdfc is in the usa with me 01:40:33 -!- ais523 has kicked IWontSayAWord User terminated!. 01:40:44 elliott: sorry, I was busy in #nethack 01:40:47 they just discovered a bizarre bug 01:41:06 apparently wielding or offhanding a potion of blindness protects you from certain blinding effects 01:41:13 -!- Phantom__Hoover has quit (Ping timeout: 252 seconds). 01:41:23 ais523: that sounds sort of intentional 01:41:29 my theory is that they were checking for worn blindfolds 01:41:33 not worn potions of blindness 01:41:37 and screwed up the check 01:41:52 offhanding a potion of blindness protecting you from yellow lights makes no sense 01:42:01 -!- youguysaremean has joined. 01:42:06 offhanded items, when you're not two-weaponing, aren't even being used in any significant sense 01:42:11 elliott: can I ban him yet? 01:42:14 or shall I just keep kicking? 01:42:16 -!- ais523 has kicked youguysaremean User terminated!. 01:42:22 or her I guess 01:42:28 he's been using male names, though 01:42:32 ais523: if it is too much work for you to kick then you can ban 01:42:34 so if he's female he's really guarding his gender well 01:42:37 it is sort of funny seeing them be so persistent though 01:42:40 yes 01:44:27 should maybe pointing him to stalker mode if he wants to watch the chat happen 01:44:35 assuming he's sincere about being bored 01:45:14 suggest setting +m to shut him up 01:45:28 as Gregor has voice, there should be no real collateral 01:47:22 -!- Jafet has joined. 01:53:29 -!- Frooxius has quit (Ping timeout: 246 seconds). 01:54:10 -!- whitespacer has joined. 01:54:59 monqy, shall I link? 01:56:24 sure 01:57:12 whitespacer, if you want to watch the chat without being in channel, you can at http://codu.org/logs/log/_esoteric/s 01:57:43 whats the difference? honestly 01:58:16 I could say, but it's kind of mean. 01:58:33 uuh its the internet dont be afraid be mean 01:58:42 Honestly? The difference is that we won't have to deal with your presense in channel. 01:58:50 trololololol 01:59:20 so about navi 01:59:40 how should i go about optimizing it? 01:59:42 ais523? 01:59:59 should inwrite it in machine code? 02:00:22 directly in binary? 02:00:33 no 02:00:35 unary 02:00:51 how about infinityary 02:01:02 no 02:01:04 whitespacer: q 02:01:05 whitespacer: qqq 02:01:06 whitespacer: qqqqqq 02:01:06 whitespacer: qqqqqqqq 02:01:07 whitespacer: qqqqqqqqqqq 02:01:08 whitespacer: qqqqqqqqqqqqqq 02:01:08 whitespacer: qqqqqqqqqqqqqqqqq 02:01:09 whitespacer: qqqqqqqqqqqqqqqqqqqq 02:01:11 whitespacer: qqqqqqqqqqqqqqqqqqqqqqq 02:01:13 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:15 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:17 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:19 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:21 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:23 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:25 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:27 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:29 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:30 °±°±°±° 02:01:31 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:33 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:35 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:37 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:39 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:41 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:43 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:45 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:47 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:48 √π÷§Δ~£©®™℅¿¡\`•÷° 02:01:49 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:51 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:53 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:55 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:01:56 something about squeaky wheels, oiling 02:01:57 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:02:00 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:02:02 • 02:02:02 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:02:04 whitespacer: qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq 02:02:06 q 02:02:06 whitespacer: i think elliott wants something from you 02:02:08 -!- ais523 has set channel mode: +m. 02:02:19 -!- ais523 has set channel mode: -m. 02:02:26 it's like when a baby cries but it's elliott and q 02:02:27 hey now ais523 02:02:37 i was about to engage in polite conversation with whitespacer "trololololol" whitespacer 02:02:39 that was too many qs 02:02:42 whitespacer: i see you use os x 02:02:44 and you don't know if the baby wants food or diapers or what 02:02:47 °Δ° 02:02:55 -!- ais523 has kicked whitespacer User terminated!. 02:03:13 ais523: would you kick oklofok for doing okokokokoko 02:03:18 pretty sure this is unfair opping 02:03:25 no, assuming he spelt it correctly 02:03:33 I'd probably join in though 02:03:39 and besides I didn't kick you 02:03:43 I just +med the channel for a bit 02:04:03 this is my usual response to botloops 02:04:07 -!- pleasehearmeout has joined. 02:04:09 I don't see why I shouldn't do them when they involve humans 02:04:15 alright give me 2 seconds 02:04:22 -!- ais523 has kicked pleasehearmeout that was 2 seconds. 02:04:22 cocococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococococo 02:04:25 * coppro ducks 02:04:39 probably a bit more than 2, actually 02:04:43 took me a while to tab-complete the name 02:04:45 7 per my client 02:04:47 o 02:04:48 oko 02:04:49 okoko 02:04:50 okokoko 02:04:52 okokokoko 02:04:53 okokokokoko 02:04:55 okokokokokoko 02:04:57 okokokokokokoko 02:05:00 okokokokokokokokoko 02:05:01 fuck 02:05:04 monqy: you should try 02:05:08 that's how oko pyramids normally end 02:05:09 (repeating history lines is cheating) 02:05:14 you can keep them going for ages with history but that's cheating 02:05:35 ais523: we need a bot that kicks people who fuck them up like in that other channel 02:05:46 what other channel? 02:05:53 the home of okos 02:06:09 there's a #okokoko? 02:06:18 apparently not 02:06:35 ok, what is actually the history of this oko thing? 02:06:42 I don't actually know 02:06:49 oklopol used to randomly say o a lot 02:06:52 just with no context 02:06:58 I still do it, but only when I remember, which is rarely 02:07:00 o 02:07:03 because you can only do it as a non sequitur 02:07:09 then people started following up with ok 02:07:10 *oko 02:07:12 haha 02:07:21 and then the original person would respond with okoko 02:07:24 and you'd form a pyramid 02:07:35 then it sort-of became a game to avoid screwing it up first, and you had to do all the typing by hand 02:08:15 it also helps that the spelling of oklopol's name is somewhat fluid 02:08:25 I think "oklopol" is the most common 02:08:32 but you get oklofok and okopol and all that sort of thing too 02:09:52 "Unlikely takes dependency injection to the logical extreme." 02:10:09 Doesn't Newspeak try to do that, in an actually productive language? 02:10:25 ais523: that isn't its origin btw 02:10:27 Newspeak is a productive language? I thought it was designed to make it impossible to express traitorous thoughts? 02:10:29 elliott: go on 02:10:31 pretty sure solo okoing came firts 02:10:33 *first 02:10:36 hmm, perhaps 02:10:41 at least there were large streaks of just one person doing it in that other channel 02:10:45 o 02:10:46 oko 02:10:46 okoko 02:10:47 what other channel! 02:10:48 okokoko 02:10:51 /kick ais523 02:10:52 is it secret? 02:10:53 ais523: #vjn 02:10:55 o 02:10:55 oko 02:10:57 I've never been there 02:10:57 okoko 02:10:58 o 02:10:59 oko 02:11:00 okoko 02:11:01 okokoko 02:11:02 okokokoko 02:11:04 okokokokoko 02:11:05 only only vaguely remember it being mentioned 02:11:06 okokokokokoko 02:11:08 /kick ais523 02:11:16 what is it 02:12:11 ais523, http://newspeaklanguage.org/ 02:12:43 o 02:12:43 oko 02:12:45 okoko 02:12:46 okokoko 02:12:47 okokokoko 02:12:50 okokokokoko 02:12:52 okokokokokoko 02:12:55 okokokokokoko 02:12:57 fuck 02:13:00 monqy: you should try!! it's fun 02:13:08 also keeping a count is cheating i think 02:13:18 i don't like that sort of game 02:13:30 im playing a different game too 02:14:00 monqy: what game 02:14:18 it doesn't have a name 02:14:39 elliott: is it traditional to say "fuck" after screwing it up? 02:14:44 that's just me saying fuck 02:14:47 I want to play but don't want to flood the channel 02:14:48 b/c i'm frustrated at messing it up 02:14:53 monqy: how do you play it 02:14:56 Sgeo: #esoteric-blah 02:15:04 Sgeo: flooding the channel is part of the game 02:15:08 it's ok because ais523 will just +m if he gets upset 02:15:09 huh, there's nobody there any more 02:15:11 and then only Gregor can play 02:15:13 but me and Sgeo 02:15:33 the channel was created for the purposes of being flodded 02:15:34 *flooded 02:15:42 and chanserv still seems to be maintaining it after all this time 02:15:43 yes but so was #esoteric 02:15:43 hum does the latest ocaml implementation have some mind reading stuff included? 02:15:50 Arc_Koen: not that I know of 02:15:55 if it does, let me know, it might be worth upgrading 02:16:04 elliott: the game is just coq's standard library :[ 02:16:10 monqy: that's a name! 02:16:13 well I made a file named deque.ml to implement a deque module 02:16:37 thing is I've never implemented a module before - I had no idea what I was supposed to do to compile another file using it 02:17:11 and well hum I made another .ml file which referred to functions from the deque.ml, using the prefix Deque. 02:17:17 Arc_Koen: oh it looks at the filename 02:17:24 and I tried to compile it AND IT WORKED 02:17:30 it'll even complain if you write a file with a filename that isn't a valid identifier 02:17:34 although it'll compile it anyway 02:17:43 yes it does that all the time 02:18:07 but does that mean I don't need to say anything when compiling? 02:18:14 it'll just find the other file by itself? 02:19:39 if it's in one of the places it looks by default, yes 02:19:43 I think the same directory is one of those 02:20:03 that's pretty convenient 02:20:25 though I think I'm gonna set most files to read only from now on 02:23:01 oh, hmm, if I change something in deque.ml that doesn't seem to affect the compilation 02:23:26 I guess it's using deque.cmo or deque.whatever from an earlier compilation 02:24:26 Note: This config file is not supported by any currently shipping kernel version and is expected to be supported only in kernels >=3.7. It has been confirmed to be working in >=3.5. 02:24:29 ais523: does this make any sense to you 02:27:59 Wait, Unlikely classes only have one method? 02:28:53 -!- printercaller has joined. 02:30:17 my favorite programming language is navi 02:30:42 huh, I was pinged when he joined the channel this time 02:30:46 guess why 02:30:52 im leaving 02:30:59 forever 02:31:09 elliott: is 3.5 shipping? 02:31:18 ugh hold on 1 sec... 02:31:19 I guess it means that they just implemented it and as such aren't supporting it yet 02:31:28 -!- ais523 has kicked printercaller that's more than a second. 02:31:46 for some reason my stalkword on INTERCAL was triggering on every line he spoke 02:31:50 because it matches the nick too, or something 02:31:57 but it's hilarious that he made that mistake twice 02:32:26 -!- iactuallywasabou has joined. 02:32:27 I thought it was because I pinged you in another channel 02:32:28 i really was 02:32:37 about to leave 02:32:42 yes 02:32:44 but then you kicked me 02:32:49 but you don't say "hold on 1 sec" and then not react instantly within 1 second 02:32:51 so i cam back 02:32:52 Sgeo: what other channel are they in 02:32:53 we're excessively literal here, sometimes 02:32:57 is it -blah 02:33:10 elliott: they aren't, rather Sgeo is in another channel and doesn't seem to realise PM exists 02:33:14 you could have had me gone forever 02:33:19 bb 02:33:20 and thus is spouting a sequence of non sequiturs there 02:33:20 ais523: is it #nethack 02:33:24 yes 02:33:29 then you decided to kick me 02:33:40 well, I could just ban you 02:33:40 iactuallywasabou: it would actually be really really easy to ban you so you can't come back 02:33:46 it's just more effort than you're worth, you know? 02:33:57 thn i can just use a proxy 02:34:01 damn 02:34:02 a proxy 02:34:05 that's some hacker techs 02:34:10 7 proxies 02:34:16 too bad freenode has an open proxy scanner thing :'( 02:34:34 then i can just use my vomputer 02:34:34 also, 7 proxies is a meme 02:34:41 which you should feel bad for spouting 02:34:44 im on my twblet tri 02:34:52 twblet 02:35:00 tablet 02:35:06 http://knowyourmeme.com/search?utf8=%E2%9C%93&q=behind+seven+proxies 02:35:10 which i hate 02:35:18 I was just hilariously amused at that utf8= parameter in the URL 02:35:31 sure you were 02:35:36 (it's an URLencoded UTF-8 encoded ✓) 02:35:59 it looks like some sort of UTF-8 check except that wouldn't actually work 02:36:02 m going to come back here everyday 02:36:05 so, I don't know why it's there 02:36:18 Easter egg/ 02:36:20 ? 02:36:25 i have 6 different devices i could come here on 02:36:27 you don't put easter eggs in the URL 02:36:34 iactuallywasabou: there's room for 7 bans 02:36:38 okay 02:36:39 actually there's not 02:36:42 our ban list is totally full 02:36:43 shit guy 02:36:44 s 02:36:45 he's got us!!! 02:36:46 fuck fuck fuck 02:36:49 what are we going to do 02:36:56 im going to sing now 02:37:11 were no strangers to love 02:37:23 you know the rules amd so do i 02:37:26 good one iactuallywasabou 02:37:37 you know commitments what im thinkingnof 02:37:47 -!- ais523 has set channel mode: +q iactuallywasabou!*@*. 02:38:00 took me a while to remember that command 02:38:21 he didn't even get the lyrics right. this is pathetic 02:38:21 elliott: btw, check wiki recent changes :) 02:38:33 ais523: ahahahaha 02:38:36 I'll leave it up to you what to do with that edit, it's hilarious 02:38:55 I suggest reverting it, but you might want to implement some degree of ban too 02:39:18 ais523: maybe should just replace "ban" with "kick" to make it more accurate 02:39:22 can't deny the completer asses part 02:40:34 I rolled it back 02:40:45 WinAmp... 02:41:10 ais523: how could you 02:41:22 how about just readd "BE WARNED: The people here are completer asses." 02:41:36 -!- elliott has set topic: BE WARNED: The people here are completer asses. | http://codu.org/logs/_esoteric/. 02:41:47 good enough 02:42:20 OK, /me approves of the topic 02:42:36 what should we complete today is an unkind fashion 02:42:39 *in an 02:42:41 as is our duty 02:42:53 -!- DHeadshot has joined. 02:43:51 in 24 years I will be too old to deal with a million spammers coming back at once 02:43:53 I could listen to this all day 02:43:54 http://www.youtube.com/watch?v=cKqKrH0O9yg 02:44:10 -!- iactuallywasabou has quit (Quit: Page closed). 02:44:11 Error: Error while linking superstack.cmo: 02:44:11 Reference to undefined global `Deque' 02:44:14 why do you think they'd all come back at once? 02:44:21 -!- ais523 has set channel mode: -q iactuallywasabou!*@*. 02:44:27 who turned the mind-reading thing off??? 02:44:42 Arc_Koen: you need to list deque.cmo while linking too 02:44:46 -!- naviISGOD has joined. 02:44:49 navi navi navi 02:44:55 hey listen 02:44:59 what do you mean "too"? I never did that before! 02:44:59 ais523: 41 is pretty old 02:45:01 hey listen 02:45:07 hey listen 02:45:09 naviISGOD: you realise you got un-muted right 02:45:13 you didn't even have to make a new nick! 02:45:19 ok 02:45:23 sorry 02:45:27 ais523: http://esolangs.org/w/index.php?title=Esolang:Community_portal&curid=983&diff=34249&oldid=34248 02:45:33 guys i sorry 02:45:44 ill stop now 02:45:49 if 02:45:55 ais523: already dealt with tho 02:46:06 input: n 02:46:19 sum « 0 02:46:39 unicode 02:46:40 fancy 02:46:47 repeat following two steps while n != 0 02:46:52 -!- DHeadshot has quit (Read error: Connection reset by peer). 02:47:06 n = n*n 02:47:10 -!- DHeadshot has joined. 02:47:15 naviISGOD: btw you can still edit your user talk page at http://esolangs.org/w/index.php?title=User_talk:108.28.95.130&action=edit&redlink=1 to appeal your ban 02:47:18 sum = n * sum 02:47:19 if you so desire 02:47:30 output: n, sum 02:48:07 in my ap comp sci clas 02:48:20 we wrote a pseudeo code compiler 02:49:28 in machine laanguage 02:49:38 congratulations 02:49:45 then transmorgified that into navi 02:49:58 and ran it from there 02:49:59 congratulations 02:50:21 i am bill gates 02:50:28 me too 02:50:37 no youre steve jobs 02:50:41 oops 02:51:06 lololololololol Allen turing was GAy 02:51:25 ais523: you can kick now 02:51:30 I think so 02:51:30 do it 02:51:37 Do It 02:51:37 -!- ais523 has kicked naviISGOD User terminated!. 02:51:59 Such homophobia. 02:52:00 they are wasting so much time 02:52:04 this is great 02:52:07 Makes me wanna fuck a dude. 02:53:01 I just tried to ban them but screwed up the command 02:53:06 so looks like they get another chance 02:55:13 http://sprunge.us/DSET gzip: it's easy. (wheeee) 02:56:44 elliott: You know you want to tell me I'm a terrible programmer. 02:57:28 standards lawyering is hard on code that's more than a line long 02:57:34 :P 02:57:59 i find your omitting braces on that else clause with a braced if clause distasteful however 02:58:12 also the use of lowercase in hex constants 03:01:32 I wrote a (stupid) gzip compressor in less space than zlib's crc32. Is everyone bad, or am I just good? 03:01:55 Maybe zlib isn't stupid. 03:02:02 is it as fast as zlib 03:02:17 elliott: Actually, fast*er*. Though also worse. 03:02:31 does it compress within an order of magnitude of zlib 03:02:41 elliott: Depends on the input. 03:02:43 It's RLE-only. 03:02:58 shachaf: 425 lines of code for one of the simplest checksum algorithms. 03:03:01 i would hazard a guess that maybe everyone else wants something more than run-length encoding 03:03:14 elliott: I want it to be better. 03:03:28 http://www.stillhq.com/gpg/source-modified-1.0.3/zlib/crc32.html 03:03:29 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 03:03:34 this doesn't look like 425 lines of code 03:03:38 i guess it's a bit old 03:03:53 https://github.com/madler/zlib/blob/master/crc32.c This is what I'm going off of. 03:04:12 Huh. The older the zlib the more reasonable, eh? :P 03:04:47 lots of those comments are comments or configuration stuff 03:04:51 s/comments/lines/ 03:04:55 by the looks of it 03:05:11 and optimisations (that may not be relevant in 2012) 03:05:51 s/may not/almost certainly are not/ This is code with far pointer annotations. 03:06:17 well the four-bytes-at-a-time stuff looks relevant 03:14:08 CRC32 is an utterly minimal amount of the time here... 03:21:11 far pointer annotations 03:21:13 ? 03:21:23 Sgeo: For DOS. 03:22:40 i bet it was less minimal in the 90s 03:23:12 When zlib had less crc32 code. ;) 03:24:10 "However, it is widely known that "REPEAT" loops alone are not sufficient for a Turing-complete language." 03:24:24 * Sgeo did not know that 03:24:40 "The secondary design goal of ZOWIE was to strike the perfect balance between It's a Mad Mad Mad Mad World and The Party. It is generally considered a morbid failure in that regard, what with not being a madcap 60's movie and all." 03:24:49 -!- mig22 has joined. 03:29:45 "When a value is written into R7, the boolean negation of that value is written into R7: 1 if the value was 0, and 0 otherwise. Reading from R7 always offers the value 7. 03:29:46 " 03:30:04 I assume that that should say "written into R8" 03:31:19 Sgeo: well I might be missing some context but if the only instruction a language contains is Repeat{ ... } then it's definitely not turing-complete 03:31:41 http://catseye.tc/projects/zowie/README.markdown.html 03:31:43 for one thing, this language actually doesn't have any valid program 03:32:40 (unless the empty program is a valid program) 03:33:39 "Many find the syntax for labels to be quite sumilar to that for identifiers. (Some even find it to be quite similar.)" 03:33:42 http://catseye.tc/projects/quylthulg/doc/quylthulg.html 03:34:39 "But you see what I'm getting at, don't you? Hopefully not." 03:35:44 * Arc_Koen digs his style 03:38:34 -!- monqy has quit (Quit: hello). 03:38:42 " It should be noted that there are at least three schools of thought on this subject. 03:38:42 The first school (Chilton County High School in Clanton, Alabama) " 03:38:57 are you quoting every spec chris has written 03:40:00 i'm ok with that 03:40:01 just asking 03:40:28 Probably not, I don't think I can possibly read all of them 03:58:37 -!- kinoSi has quit (Read error: Connection reset by peer). 03:59:04 -!- kinoSi has joined. 04:00:54 Hmm. Has kinoSi ever said anything? 04:04:52 Hmm, there's a larabee language 04:04:56 Any connection to Gregor? 04:05:25 I speak all languages. 04:06:03 Gregor, glottal master. 04:08:41 "(It should be noted that it was rougly at this point that Pressey reached one of the peaks of his so-called "referential" period, in which he was apt to provide "commentary" on his own work, in the form of interjections or asides, as if from the perspective of a historian from a much later era. Such pretentious interruptions were generally not well received, except perhaps by the occasional loser such as yourself.)" 04:20:38 I r no loser 04:22:26 anyway it's almost 6:30 and I actually plan to go to bed *before* the time when I must get up so gnight 04:23:00 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 04:26:49 Sgeo: any connection to gregor?? 04:27:13 Gregor: How about Portuguese? 04:27:33 elliott, Gregor sometimes goes by "Lawlabee" 04:27:47 shachaf: Portuguese is just Spanish with a funny accent, Spanish is just French with a funny accent, French is just Dutch with a funny accent, Dutch is just English with a funny accent. 04:28:25 And Finnish is just Japanese with a funny accent. 04:28:33 Yup. 04:29:51 @quote dutch 04:29:52 shachaf says: I think Dutch is just a parody of English. 04:29:58 I guess you're right about Dutch. 04:30:13 pikhq_: Finnish isn't a real language. 04:30:57 shachaf: No, it's an accent of Japanese. 04:31:00 See, not a language. 04:31:21 What's Russian? 04:31:40 Polish with a funny accent. 04:31:55 A language encoded in our DNA, that can only be accessed when sufficiently drunk. 04:32:08 All drunk men speak Russian. 04:32:15 I,I given a sufficiently drunk compiler 04:35:56 I keep finding typos in cpressey's documentation 04:36:05 elliott: whoa, dude 04:36:06 At least I assume they're typos 04:36:16 Remember the time when someone said something sensible in #haskell and then it turned out it was you? 04:36:25 when was that 04:38:49 A few years ago. 04:39:02 ok 04:39:58 By year I mean second. 04:40:03 me too 04:42:02 instance Functor BashVar n, maybe? 04:42:11 shachaf: Are there really even more people who just make up answers? 04:42:15 Than there used to be, I mean. 04:45:41 elliott: How can there be more than "all of them"? 04:46:32 *Some* people don't just make up answers. 04:46:58 Oh? 04:47:44 elliott, for instance. 04:48:07 Huh? 04:48:12 elliott just made up an answer right now! 05:15:00 -!- ogrom has joined. 05:15:09 -!- ogrom has quit (Client Quit). 05:32:05 -!- elliott has quit (Ping timeout: 248 seconds). 05:48:59 Didigm is making me hate French. 06:11:06 -!- monqy has joined. 06:20:24 Reading the Mascarpone spec 06:20:32 I really like the naming of reify/deify 06:39:30 -!- iconmaster has joined. 06:43:18 -!- copumpkin has quit (Ping timeout: 245 seconds). 06:43:54 -!- copumpkin has joined. 06:44:02 -!- iconmaster has quit (Ping timeout: 255 seconds). 07:06:18 -!- ais523 has quit. 07:17:13 -!- DHeadshot has quit (Ping timeout: 245 seconds). 07:20:42 -!- atriq has joined. 07:30:12 -!- DHeadshot has joined. 07:43:21 -!- epicmonkey has joined. 07:53:35 some kicking 08:34:07 * Sgeo looks up at logs, and realizes that the reify/deify thing still fascinates him. It has not stopped being a fascinating thing. 08:48:49 Make it a thing/Make it a god 08:48:50 ? 08:48:54 I got deified once 08:49:34 atriq, yes 08:50:21 In Mascarpone, v (reify) pushes the current interpreter onto the stack, and ^ (deify) pops the interpreter from the stack and makes it the current interpreter 08:50:50 :) 08:52:44 Is Mascarpone the one with first class esolangs? 08:53:21 -!- nooga has joined. 08:54:01 I don't think the spec called them "esolangs" as such, but that seems fair enough 08:54:09 Just "interpreters" 08:56:15 The world is quiet here 09:03:55 -!- atriq has quit (Quit: Leaving). 09:10:21 -!- kinoSi has left ("kill -TERM $"). 09:32:46 -!- ogrom has joined. 09:39:45 uh 09:40:04 Hi no 09:40:06 nooga, 09:40:22 hi no to you too, sgeo 09:40:39 hi mo 09:40:42 The perils of tab-complete. 09:40:57 MORE LIKE: 09:41:00 tab-incomplete 09:41:04 CORRECT? 09:41:19 Yes, that is not correct. 09:42:12 ...having trouble finding the exact quote :( 09:43:52 -!- atriq has joined. 09:53:55 are we safe? 09:57:21 -!- ogrom has quit (Quit: Left). 10:00:28 From? 10:01:54 No 10:02:23 We've been infiltrated 10:06:09 -!- monqy has quit (Quit: hello). 10:13:25 from this troll 10:14:37 Hasn't been here for a while 10:20:59 -!- nooga has quit (Ping timeout: 246 seconds). 10:36:24 -!- Vorpal has joined. 10:36:55 -!- Jafet1 has joined. 10:37:39 -!- Jafet has quit (Ping timeout: 260 seconds). 10:39:54 -!- Jafet has joined. 10:41:14 -!- Jafet1 has quit (Ping timeout: 240 seconds). 10:42:24 Hmm 10:44:06 -!- Jafet has quit (Ping timeout: 245 seconds). 10:48:41 -!- epicmonkey has quit (Remote host closed the connection). 10:51:05 -!- epicmonkey has joined. 10:52:43 -!- Phantom_Hoover has joined. 10:54:29 -!- epicmonkey has quit (Remote host closed the connection). 10:54:45 -!- epicmonkey has joined. 10:59:49 -!- monqy has joined. 11:25:43 -!- Jafet has joined. 11:27:38 -!- Jafet1 has joined. 11:29:56 -!- Jafet has quit (Ping timeout: 245 seconds). 11:32:19 -!- Jafet1 has quit (Ping timeout: 246 seconds). 11:35:37 -!- Jafet has joined. 12:12:46 -!- elcot_ has joined. 12:15:37 hi 12:15:46 any one wanna chat 12:16:51 -!- elcot_ has left ("Leaving"). 12:19:13 -!- monqy has quit (Quit: hello). 12:20:18 Evidently not 12:21:09 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 12:24:24 -!- Phantom_Hoover has joined. 12:59:34 Meanwhile in Finland, http://lukijoidenkuvat.hs.fi/kuvat/uusimmat/90123/ 13:06:55 -!- Jafet has quit (Ping timeout: 256 seconds). 13:13:09 -!- AnotherTest has joined. 13:13:18 Hello 13:14:23 -!- Jafet has joined. 13:32:21 Hey 13:55:33 -!- mig22 has quit (Quit: mig22). 13:56:16 > let foo = fromMaybe <$> show <*> cast in [f 1, f (), f [1,2,3], f "Hello"] 13:56:18 Ambiguous type variable `t' in the constraints: 13:56:19 `SimpleReflect.FromExpr ... 13:56:34 http://www.youtube.com/user/redbull?v=MrIxH6DToXQ 13:56:37 > let f = fromMaybe <$> show <*> cast in [f 1, f (), f [1,2,3], f "Hello"] 13:56:38 ["1","()","[1,2,3]","Hello"] 13:56:56 The power of applicatives 13:56:57 @type cast 13:56:58 forall a b. (Typeable a, Typeable b) => a -> Maybe b 13:57:18 It detects if it's a string and shows it if it isn't 13:58:26 Actually uses unsafeCoerce 13:59:56 :t \x -> let r = if typeOf x == typeOf (fromJust r) then Just $ unsafeCoerce x else Nothing in r 13:59:58 -!- Jafet has quit (Quit: Leaving.). 13:59:58 Not in scope: `unsafeCoerce' 14:20:23 -!- nooga has joined. 14:27:02 what's completer ass? 14:27:12 Spam on wiki 14:28:41 Am I the only person active both here and Tumblr? 14:40:53 hard to answer 14:41:05 insufficient data 14:41:32 zzo38 and Gregor both seem possible Tumblrist 14:43:13 Maybe Sgeo? 14:45:17 the idea of any of those people having a tumblr is utterly alien to m 14:45:18 e 14:46:31 I'm gonna register phantom_hoover.tumblr.com 14:46:53 are you going to attempt to impersonate me for your devious purposes 14:47:03 Ok, I can't 14:47:08 Tumblr doesn't like underscores 14:47:10 And yes 14:47:18 I'll take Phantom-Hoover.tumblr.com instead! 14:47:49 Ahahahaha! 14:48:16 oh no! 14:48:20 what slanders are you going to write 14:48:24 I dunno 14:48:36 Maybe I'll reveal all the information I know about you 14:48:45 The jump’s beginning. 14:48:51 Basically, you are from Edinburgh's new town and go to university in Coventry 14:48:58 Which is ridiculous upload speeds 14:49:13 they're only ridiculous compared to the download speeds 14:49:16 Also, you hate brainfuck derivatives with a passion 14:50:21 Well, the John Egbert cosplayer who hates me in her sleep... HAS MY GLASSES 14:50:36 Maybe I'll just bash brainfuck derivatives 14:51:13 But in such a way that it seems they're a perverse lust of yours 14:51:23 Filling the balloon will take quite a while. 14:51:51 ion, are you talking about the guy who's jumping from a balloon? 14:51:57 I filled some balloons yesterday 14:52:23 what, you mean i have some kind of weird s&m thing with brainfuck derivatives? 14:52:29 atriq: yeah 14:52:34 Phantom_Hoover, yeah 14:52:41 although wait, are all lusts perverse from your perspective? 14:52:48 Nah 14:52:51 Just alien 14:54:21 Although my cunning facade will be weakened somewhat when people notice that taneb.tumblr.com and phantom-hoover.tumblr.com are held by the same account 14:56:09 the house of cards will come crashing down 14:56:38 I'm actually seriously gonna do this 14:56:46 like that time me and elliott registered the timeustestified account with a script 14:57:03 (well, elliott wrote the script, i just ran it overnight for him) 14:57:13 the replies to that were delicious 14:59:03 Do... 14:59:06 Do you still have it? 14:59:09 no 14:59:21 in the end we gave it away to someone who turned out to be really boring 14:59:53 http://timaeustestified.tumblr.com/ 14:59:59 it could've been worse though 15:00:27 oh my god they substitute the cursor and have sparkles on it and everything 15:00:31 mission 15:00:33 fucking 15:00:34 accomplished 15:09:59 http://phantom-hoover.tumblr.com/post/33568447695/ugh-there-was-once-a-fish-called-fred 15:10:09 It has begun 15:10:45 you forgot brickbraining you ninny 15:11:04 Thank you very much 15:11:19 also my day is now a little worse for learning about that language 15:11:37 Refresh the tumblpost 15:12:44 is that profile picture a photo of the new town from the castle 15:12:50 Yes 15:13:01 Yes it is 15:13:30 -!- Frooxius has joined. 15:18:27 -!- atriq has set topic: BE WARNED: The people here are completer asses. | http://phantom-hoover.tumblr.com/ | http://codu.org/logs/_esoteric/. 15:21:23 http://www.youtube.com/redbull will apparently display some flight data in the sidebar. 15:22:57 Wow, I can be really reckless sometimes 15:28:04 Who did you ban :) 15:29:23 Nobody yet 15:29:40 Yesterday I climbed up a building even though my friends were telling me not to 15:29:52 Somebody apparentely is pissed about being banned for speaking :D 15:29:52 Today I made a Tumblr where I pretend to be Phantom_Hoover 15:30:20 Today I climbed up walls :) 15:35:57 Yay! 15:36:10 Today I've barely left my bedroom 15:36:25 Hm. 15:36:29 Meanwhile my glasses are in a shopping centre 23 miles away 15:36:38 So distances I can't see so well 15:41:21 -!- elliott has joined. 15:49:45 Hey, elliott 15:50:30 Hey, atriq 16:01:08 -!- FreeFull has quit (Quit: Rebooting). 16:02:47 -!- FreeFull has joined. 16:47:01 -!- Arc_Koen has joined. 16:47:46 hello 16:48:05 Hey 16:48:16 's funny 16:48:54 in real life we name streets and erect statues after people who have done great things 16:49:21 Like Grey Street and Grey's Monument in Newcastle 16:49:49 on irc we write the channel's topic after someone whom we've just banned the previous day 16:51:24 Phantom_Hoover: does your blog know about the right to reply? 16:51:35 or about any other similar concept 16:53:09 I'd like to advocate "There Once was a Fish Named Fred" 16:54:11 first, it's not "There Was Once A Fish Called Fred", it's "There Once was a Fish Named Fred". At least name the thing right! 16:55:04 note the completely arbitrary capitals which are part of that language's pittoresque 16:55:42 second, your only critic of this language seems to be "It literally just replaces the commands of brainfuck with one of 8 words. Nothing more, nothing less." 16:55:48 and that is WRONG 16:56:04 because there are SEVEN words!!! 16:56:25 which is clearly something less 16:57:11 so it's be cool if you could publish an erratum or something 17:02:20 it sucks that the phrase "special case" has two opposite meanings 17:03:05 as a non-native speaker I'd be glad to have more on that 17:04:28 sometimes "foo is a special case of bar" means "bar generalizes foo" 17:04:38 a square is a special case of a rectangle 17:04:49 Hehehe 17:04:53 if you know how a rectangle works, you automatically know how a square works because it's just a particular type of rectangle 17:04:53 So worth it 17:05:02 but then sometimes it means that there is a special rule for foo 17:05:08 kmc, you also need to know how a rhombus works 17:05:28 which means that foo works differently from how you would expect based on how bar works 17:05:33 so it's basically the opposite meaning 17:05:55 hmm, yeah 17:06:10 that happens a lot when we're thinking too much logically 17:06:35 atriq: no, if you're able to handle rectangles, you'll handle squares just fine 17:07:09 Yeah, I was thinking of something else 17:07:25 Arc_Koen, I'm gonna let you in on a secret 17:07:31 you were thinking about the opposite meaning of "how a square works"!! 17:07:39 Phantom_Hoover doesn't own phantom-hoover.tumblr.com 17:07:48 if you write it here and it's logged it won't be a secret 17:07:49 It's... 17:07:50 WHAT 17:07:52 It's me 17:07:57 seriously? 17:08:02 but but but 17:08:07 Read the logs for today 17:08:16 And it's a joke 17:08:27 atriq was just thinking contravariantly 17:08:40 oh, that would most certainly explain why it reads "remove your brain and replace it with a brick" and not "force a brick into your brain" 17:09:11 "At some point, I shall snap and everyone who has posted a stupid Brainfuck derivative (read: a Brainfuck derivative) to this wiki will have their brains forcefully replaced with a large brick." 17:09:17 From Phantom_Hoover's user page 17:10:18 10:31 cmccann: I like the part where «foo would just be a special case» could either mean that you implement unusual behavior for foo or that you don't. 17:12:19 yes 17:12:26 i'm glad you have also noticed thes 17:12:27 this* 17:13:10 Also "existence proof". 17:13:13 hmmm ok atriq 17:13:20 different versions, same story 17:13:24 q 17:13:57 I also had "a brick so large you will believe you actually are a small house" (or flying house) 17:14:11 so i'm reading the logs from last night 17:14:21 it turns out I was so tired I wasn't aware that other people were talking so much 17:14:35 it's like there are five different story told at the same time and I only noticed one 17:15:16 shachaf: what about 'existence proof'? 17:16:06 ais523: one time I got into the deku tree and got either stuck or bored 17:16:07 I can SO relate to that 17:16:45 (though in my case I was playing on a black and white tv and inside of the deku tree we're supposed to hit an underwater switch which was invisible in black and white) 17:18:00 kmc: It could either mean "proving that something exists without having a specific example" or "proving that something exists by providing a specific example". 17:18:14 Mathematicians mostly use it in the former sense, though. 17:18:27 mm 17:18:42 i just understand it to mean "proving that something exists" 17:21:27 -!- jiella has joined. 17:23:13 i wonder if credit card companies have honeypot credit card numbers 17:24:08 why would they need any, as long as they have customers? 17:26:51 shachaf: then we say it's a non-constructive proof, don't we? 17:27:16 like, you proved it existed, without building a particular instance 17:27:26 they wouldn't *need* them, but it would be easy to do and would provide additional information about fraud that might be valuable 17:28:01 Arc_Koen: non-contsructive proof doesn't really quite mean that 17:28:04 Sgeo: what's this newspeak thing? I thought newspeak was a round in frc 17:28:07 though they often coincide 17:28:24 for example you could tell if someone at the CC company or at an affiliate (banks etc.) is selling numbers on the side 17:28:26 Arc_Koen: fantasy rules committee? :p 17:28:57 yup 17:29:02 though you wouldn't detect numbers being stolen from legitimate merchants, which is probably the greater concern 17:29:10 the theme was "design newspeak" or something 17:29:16 Arc_Koen: oerjan used to play that, way back 17:29:32 anyway newspeak is a fictional language from 1984 that both the frc round and the programming language reference 17:29:48 doubleplus ungood 17:29:54 and the first rule was something like "you should add a new modification to the english language every rule, and rules must follow all previous modifications 17:30:01 oh, ok 17:30:05 yes, I know he did :) 17:30:12 he probably played that round, actually 17:30:19 it was an early one 17:30:30 (like, one of the first fifty, or something) 17:30:36 this reminds me i have to keep bugging oerjan to return to agora 17:30:38 -!- Frooxius has quit (Quit: ChatZilla 0.9.89-rdmsoft [XULRunner 1.9.0.17/2009122204]). 17:31:04 if I send a bunch of read requests to a Linux software RAID1 device, is the I/O scheduler smart enough to route them to component drives based on the angular position of each drive? 17:32:05 -!- ogrom has joined. 17:32:15 too bad freenode has an open proxy scanner thing :'( 17:32:47 how does that work? I was assuming proxies were *designed* to be invincible or something 17:32:56 i don't know how it works actually 17:33:22 like, instead of sending an email to you, I send it to a robot which then sends that exact same email to you 17:35:03 Well, if the robot understands a common way of asking it to send mail on people's behalf, someone could ask someone they received mail from to send mail on their behalf to see if it's really a robot 17:36:47 so what would the scanner do then? just say "you've been identified as a proxy, so you're not allowed to be on our network"? 17:38:35 Does Freenode allow Tor? 17:40:20 It has a Tor hidden service for that. 17:40:33 p4fsi4ockecnea7l.onion. 17:41:23 (irc.tor.freenode.net is a CNAME to it.) 17:42:21 A Finnish finance magazine had a short column on bitcoins; it mentioned how bitcoins are used for drugs, sex and violence "on the dark side of the Internet, called Tor", or something like that. 17:42:41 THE DEEP WEB. 17:45:07 atriq: so I just went through 18 hours of logs 17:45:27 most of which were about that navi guy 17:45:39 fizzie, Reddit flipped out some time ago about "the deep web" and how it simultaneously made up most of the Web and was a secret hiding place for things 17:45:46 and in the end it turned out the phantom-hoover thing happended just before I logged in 17:46:40 -!- Frooxius has joined. 17:46:47 Or was it "dark web" 17:47:01 interestingly enough I haven't eat at all during those 18 hours so hum see you guys later 17:48:50 it was deep web 17:53:41 Deep web is for pedos 17:55:39 -!- ogrom_ has joined. 17:57:29 -!- ogrom has quit (Ping timeout: 255 seconds). 17:58:26 -!- ogrom has joined. 18:00:39 -!- ogrom_ has quit (Ping timeout: 255 seconds). 18:14:45 the swan and paedo 18:15:34 so what's with this baumgartner guy 18:15:41 is anyone following that? 18:15:56 Yep 18:16:01 He is falling a lot 18:16:07 And failed to do his stuff 18:17:39 let him land on red square.. then it's cool 18:18:26 Or on the planet of the apes 18:18:35 that would be a cool joke 18:19:09 "welcome back to earth! we've been taken over while you were gone" 18:19:42 or "you gained too much speed and broke the dimension wall" 18:20:00 http://www.youtube.com/watch?v=lrBZeWjGjl8 18:26:44 http://news.bbcimg.co.uk/media/images/63480000/jpg/_63480371_63480370.jpg 18:31:00 I actually hardly know anything about the atmosphere - aren't there issues with pressure, like for scuba divers? 18:31:02 :( why does JMOD want unrestricted access to my computer 18:31:08 I'm lazy and said yes, but still... 18:31:56 what is JMOD 18:32:01 Sgeo: are you sure it's JMOD and not some malware sent to you by a stalker? 18:32:07 Applet that plays MOD files 18:32:14 Used on modarchive.org 18:32:21 Currently happily listening to http://modarchive.org/index.php?request=view_by_moduleid&query=36405 18:34:53 It's the song that was used in Fitznik (a game) and for some levels in Fitznik 2 18:35:47 grant { permission java.security.AllPermission; }; -- man, that's indeed quite some permissions. 18:36:38 fizzie, hmm, is that actually a line somewhere? Where do you see it? 18:36:44 I mean, except for the comment of course 18:37:09 The "java.policy.applet" file inside the jar. 18:37:11 fizzie: Can you, like, write an IRC client for me? 18:37:13 A good one. 18:37:26 There's also a command-line interface included, apparently. 18:37:35 -!- ogrom_ has joined. 18:39:58 And no, I can't. I'm always tempted to write one for me, but even if I one day did do that, it wouldn't probably be something for anyone else. 18:40:15 -!- ogrom has quit (Ping timeout: 255 seconds). 18:43:14 fizzie: Well, you wouldn't be so horrible as to make an IRC client that isn't perfect, right? 18:44:04 You just never know. 18:44:18 http://www.indiegamer.com/archives/t-208.html 18:44:19 <3 18:45:08 fizzie: Have you tried irssi2? 18:45:08 Do I have the permission to create an infobox template on the wiki? 18:45:10 It looks fancy. 18:45:35 I have nots. 18:47:44 I sometimes connect to the Pesterchum network using XChat 18:48:25 irc.mindfang.org 18:48:39 fizzie: Anyway let me know when you have that perfect client written so I can use it, thanks. 18:48:45 I tried out that WeeChat thing few years ago, and it segfaulted on me. 18:49:05 But it's a poorly designed protocol built on top of a disagreeing protocol 18:49:21 From ais523's part message: 18:49:21 So you can see everyone's colour codes and that 18:49:22 fizzie: it makes demons fly out of my window, washing the windows api 18:49:23 Sgeo: ( danvy filinski invented shift reset after other composable continuation operators. they allow you to install mysql. 18:49:32 An awful lot is done client-side 18:49:56 Composable continuations. The best way to install MySQL. 18:49:59 You heard it here first. 18:50:12 fungot: Washed any APIs lately? 18:50:13 fizzie: in haskell anything can be realtime when you throw enough people at it, it would permit easily having discussion of multiple implementations e.g. debian's alternatives, but sicp pdf is at http://www.cs.indiana.edu/bmastenb/ misc/ sicp.pdf, the html at http://mitpress.mit.edu/ sicp/ 18:50:20 ^style 18:50:20 Available: agora alice c64 ct darwin discworld europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 18:50:48 Silly bot. 18:52:45 AnotherTest: if you do that, I'm gonna make some hot chocolate, watch an episode from stargate, and when I'm back if it's working I promise to fill at least three languages' infoboxes 18:53:16 (note: I have absolutely no idea how much efforts are involved in making an infobox template) 18:53:34 60-90 minutes according to this website 18:53:54 then make it two episodes 18:54:11 (but first, hot chocolate!) 18:54:22 You'll have to wait until tomorrow 18:54:41 That's a lot of episodes and hot chocolate. 18:54:45 that's quite a lot of episodes 18:54:52 Unless of course some else wants to do it today 18:55:45 atriq: Out of curiosity, what's your chumhandle? (If it's sort of public.) 18:56:15 For a nice tutorial: http://www.etcwiki.org/wiki/Install_infobox 18:56:49 -!- AnotherTest has quit (Quit: Leaving.). 18:56:56 if it's within my skills, or within skills that are within my reach modulo a reasonable amount of learning, and if I'm allowed to do that with my two-month old account, then there is a possibility for you to talk me into doing it 18:57:09 fizzie, I'm not on often 18:57:20 of course that's gonna be hard if you've already left 18:57:45 My current handle is mathematicalEyebrow, which I'm using for a fan-adventure 18:58:00 atriq: I'm not on ever, I just wondered if it was an interesting pair of words. 18:58:11 Used to be pixellatedQuestant 18:58:36 (fsvo "reasonable amount") 19:04:31 lazy evaluation tells me I probably don't have the authorizations to make up such a thing. switching back to initial plan: hot chocolate! 19:05:26 atriq/fizzie: what are you talking about? 19:05:46 Arc_Koen: Homestuck nonsense. 19:06:12 i've heard that word mentioned on this channel before 19:06:18 Snrk 19:06:28 Homestuck is a web media thing. 19:06:31 It's pretty popular. 19:06:57 http://www.mspaintadventures.com/?s=6 19:06:59 so you think I know nothing about popular stuff!! 19:07:15 I think you know nothing about Homestuck! 19:08:35 wait, are they calling con air a REALLY TERRIBLE MOVIE? I beg to differ! 19:08:51 There are probably many people in the world that do not know about Homestuck. 19:09:05 a web media thing? homestuck is about SEO then? 19:09:22 Even John agrees that Con Air is terrible. 19:09:43 Sgeo, shhh, spoilers 19:09:50 Arc_Koen just started! 19:10:10 wait, yours is named John too? 19:10:21 I got lucky I was almost named something terrible 19:10:23 It's largely static 19:10:35 It's the same for everyone 19:10:43 It's more of a web comic than an interactive game 19:11:07 Although... it would have been fun to see someone read Homestuck believing that it's different for everyone 19:11:23 Maybe next time 19:11:36 Arc_Koen: I think you should read it through in one setting. 19:12:15 like, I start now and don't stop until I'm finished? 19:12:22 Right. 19:12:26 I haven't even made hot chocolate yet!! 19:12:38 Well, how long could it be? 19:13:59 (I think it's somewhere between five and six thousand pages.) 19:14:19 (it's long) 19:15:12 (Many of those pages are also interactive supermedia, the full exploring of which may take moments.) 19:15:38 PUT THE BUNNY BACK IN THE BOX 19:16:12 You are gonna love Act 4 19:16:24 poor bunny, when you know what it's gonna have to go through before it is finally given to the daughter 19:17:10 interestingly, the hero's friend is not on the poster 19:17:34 even though he's been the only ally during the hole flight (well he and that female cop) 19:17:38 whole* 19:21:26 am I the only one to find tire swings depressingly look like hangman's rope? 19:21:43 Hmm 19:21:46 Now you mention it 19:24:28 hmm 19:24:49 I guess at some point he'll accidentally eject the smoke pills from the inventory stack 19:25:02 (that features kind of makes it a queue, actually) 19:25:21 and it will make his room lousy with smoke! 19:28:46 :D 19:29:24 "tentacleTherapist" 19:29:25 hum. 19:29:32 "hum"? 19:30:22 hrm 19:30:43 * Arc_Koen makes sounds with his throat 19:31:05 wait, uh, where did I get my arms from? 19:31:10 I thought I was armless 19:31:11 The chest? 19:31:40 http://www.mspaintadventures.com/?s=6&p=001907 19:32:48 captchalogue captchalogue arms 19:32:51 cards* 19:33:51 this is the kind of jokes that knows you've seen it coming and is even funnier like that! 19:33:55 atriq, btw, I style my nick "Phantom Hoover" unless there are technical limitations. 19:34:06 Please adjust your tumblr to correct for this. 19:36:31 Like that? 19:36:40 Yes. 19:40:08 -!- DHeadshot has quit (Ping timeout: 245 seconds). 19:40:57 people with multiword capsed nicks are so lame 19:41:43 so true 19:41:47 oops 19:42:24 I would definitely agree with you weren't it for that homonym I have on freenode 19:43:18 i had to wage wars to get this nick 19:44:29 -!- DHeadshot has joined. 19:45:52 Aren't there, like, 6 Elliotts in #haskell? 19:46:15 yes 19:46:25 no, it's just elliott being there 6 at once 19:46:28 one of them is annoying & bad & jealous of my name 19:46:30 and this makes me really happy 19:46:44 i've offered a fair trade of $500 for it tho 19:47:12 Hmm 19:47:22 -!- atriq has changed nick to ectoBiologist. 19:47:33 -!- ectoBiologist has changed nick to tentacleTherapis. 19:47:42 -!- tentacleTherapis has changed nick to turntechGodhead. 19:47:47 -!- turntechGodhead has changed nick to atriq. 19:48:00 tentacleTherapist isn't registered on account of being too long 19:48:30 -!- atriq has changed nick to golgothasTerror. 19:48:35 -!- golgothasTerror has changed nick to atriq. 19:48:44 tentacleRapist is shorter 19:49:01 -!- elliott has left ("Leaving"). 19:49:10 Trivia: when I play Guitar Hero Arcade, I always leave my highscore as a Homestuck character 19:49:31 I should have probably left #haskell before doing that 19:50:47 Arc_Koen, where are you up to? 19:51:01 I stopped 19:51:06 :( 19:51:11 it became too much repetitive for me 19:51:17 Ahaha 19:51:31 I highly recommend you try to push on 19:51:41 It becomes a LOT less repetitive 19:51:50 maybe another day (if there's a way to jump ahead back to where I left) 19:52:09 Did you click "save game"? 19:52:20 -!- NihilistDandy has joined. 19:55:25 nope 19:55:36 Since when are people in here suddenly mspainters 19:55:39 Use your browser's history thing 19:55:41 Since forever? 19:56:13 Did irssi mix up channels 19:56:20 Is this #esoteric on freenode 19:56:22 Yes 19:56:33 Ok 19:56:50 > "test" 19:56:51 "test" 19:56:56 but for another kind of esoteric... 19:57:04 `welcome koen 19:57:14 koen: 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.) 19:57:26 lambdabot confirms I'm still in the right channel 19:57:37 -!- Phantom__Hoover has joined. 19:57:58 either that or lambdabot is in the wrong channel 19:59:32 fungot: Is this the right channel? 19:59:33 fizzie: do it like that? you?. but how boring. 20:00:51 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 20:03:14 fungot: boring indeed. 20:03:14 FireFly: haven't seen you around for a good while to understand his objections are sure to be the case, but srfi-7 is " feature-based program configuration language 20:03:28 -!- DHeadshot has quit (Ping timeout: 245 seconds). 20:03:41 fungot: You should maybe brush up on your grammar. 20:03:42 fizzie: actually we're just sitting around thinking completely random thoughts about generic i/ o speed, the hands acquire shaking, the shaking becomes a warning; it is by the fact that set! defines new variables at top level 20:03:42 The beginning of that line is eerily correct 20:04:12 That's somehow scary. 20:04:42 The "the hands acquire shaking, the shaking becomes a warning; it is by the fact that set! defines new variables at top level" part. 20:06:06 if sentences returned noun phrases, fungot would be speaking proper english 20:06:07 Arc_Koen: i just dumped all my music into /home/ fnord 20:06:51 is that some special location, fungot? 20:07:18 fungot: Is it your fault that disk is filling up? 20:07:28 Hmm, suspicious. 20:07:47 fungot: more dune quotes 20:08:00 Arc_Koen: i want to get fancy, you could use macros perhaps 20:08:01 fizzie: in the latest python? for what implementation of lists using pairs. 20:08:01 olsner: class quine: http://rafb.net/ p/xmkaav98.html or maybe figuring out how the clever recursive solution works? ;p it might make things clearer. 20:10:35 if you say so, fungot 20:10:36 FireFly: well, i never could find a definition of y i gave, though. i got a new queue altogether with its own build system that's quite as all-encompassing, however, the core procedures to operate on a flow learning scheme 4 years ago 20:14:58 fungot: dongs 20:14:58 kmc: the egg breakfast before lunch!! i'm in 20:15:07 :3 20:18:16 -!- Vorpal has quit (Ping timeout: 260 seconds). 20:27:58 I should rewatch Up Skit's Creek 20:28:06 iirc it's a bit juvenile, but still 20:49:54 -!- ogrom_ has quit (Quit: Left). 20:59:31 -!- atriq has quit (Quit: Leaving). 21:05:20 fungot! 21:05:29 Phantom__Hoover: excuse me a minute. it explains the design and implementation" from 1975. 21:08:55 -!- elliott has joined. 21:09:10 pikhq_: Is Nvidia or ATI better supported on Linux this month? :( 21:09:41 -!- ais523 has joined. 21:10:21 elliott, I thought it only changes every few years 21:12:16 has it ever changed? 21:13:37 Used to be nVidia, seems to have switched to ATI 21:15:02 I hear bad things about UEFI and Nvidia. 21:15:05 On Linux. 21:16:45 * Sgeo wonders what a Lisp needs to have in order to be a Lisp 21:17:00 Mostly in the context of whether or not ClojureScript qualifies as a Lisp. 21:17:45 Sgeo: A Lisp needs nothing in order to be a Lisp. 21:18:15 what does a not-lisp need in order to become a lisp? 21:18:54 i can't think of a more pointless, masturbatory topic 21:19:19 kmc: Clearly you've been away from #haskell for too long. 21:20:00 There's a ClojureScript REPL. It's backed by a server. 21:20:05 LAME 21:20:27 shachaf: i was just about to make a #haskell joke 21:20:28 fungot: is ClojureScript a Lisp? 21:20:29 kmc: dunno i'd buy that terribly easily if you like 21:20:29 fuck you shachaf 21:20:34 fuck you kmc 21:20:35 ClojureScript macros are Clojure code and there's no eval. 21:20:41 yes we all know 21:20:46 thelliott 21:20:51 who cares whether it counts as lisp 21:20:56 what matters is it sounds bad 21:21:52 elliott: obviously 'Lisp' is special magic fairy dust and not just a programming language with cool features that could be discussed individually 21:22:24 you have to know if a language is 'Lisp' so that you know whether programming in it makes you a real hacker 21:22:37 kmc: What's the matter with fairy dust? 21:22:37 kmc: did you ever see that loper os post about how a brick is more like lisp than clojure 21:22:43 i swear to god it literally said a brick was lisp 21:22:57 has a dog the lisp-nature 21:23:27 -!- Phantom_Hoover has joined. 21:23:38 Phantom_Hoover is Lisp. 21:23:46 kmc: http://www.loper-os.org/?p=405 here 21:23:47 enjoy 21:24:18 i am totally lisp 21:25:42 lulz 21:25:42 -!- Phantom__Hoover has quit (Ping timeout: 245 seconds). 21:26:08 love how the loper-os blog has 32 posts tagged as philosophy and 19 tagged as loper os 21:26:22 Scheme doesn't have reader macros, correct? 21:26:26 'philosophy' 21:26:50 kmc has lisp-nature. 21:27:02 In that case, how does it not force a non-modifiable syntax on programmers (parentheses) any more than Clojure does (slightly more than just parentheses) 21:27:29 parentheses are technically modifiable 21:27:30 obviously, the aspects of syntax I care about modifying are important, but the aspects you care about modifying are irrelevant 21:27:36 in common lisp at least 21:27:48 Phantom_Hoover, I did say Scheme for a reason. 21:27:52 but that line of thinking ends up with you hailing perl as the height of syntactic freedom 21:28:01 elliott, tell Sgeo scheme isn't a lisp 21:28:04 how about machine code 21:28:09 i'm pretty sure you said that at some point 21:28:15 i said scheme isn't a lisp 21:28:28 because scheme macros aren't written in scheme (usually) 21:28:42 this is a troll statement though 21:28:57 common lisp macros aren't really written in common lisp either 21:29:04 -!- variable has changed nick to trout. 21:29:04 elliott, er? 21:29:11 well stuff and stuff 21:29:17 i could make a reasoned argument for this but i won't 21:29:27 The Reasoned Elliott 21:29:33 lol 21:29:35 aren't they usually normal common lisp procedures manipulating syntax as data? 21:29:51 whereas scheme macros are usually not normal scheme procedures; they are rules for a special purpose macro DSL 21:29:56 what about image macros 21:30:06 image macros are the foundation of humor 21:30:17 kmc: ye but (a) the definition of "common lisp" is a bit vague in terms of defining ~lispiness~; you can well argue that the form that looks at the car and switches on special forms or function names is just one DSL in many; (b) hence Scheme macros are in a way Scheme too 21:30:20 (c) stuff and stuff 21:30:40 (c) 2012 elliott "elliott hird" hird 21:30:47 (d) furthermore a definition which includes CL macros as being "in Lisp" but not Scheme macros is an unhelpful definition because it rejects what you want to admit and probably admits what you want to reject 21:31:55 how so 21:32:05 because you want to say that Scheme is a Lisp 21:32:11 if not you then I 21:32:14 i don't particularly 21:32:22 actually more precisely, I don't care about whether I say whether Scheme is a Lisp 21:32:28 but i already described the question of "what is Lisp, really?!?" as pointless and masturbatory 21:32:36 but I'd like to laugh at people who think that there is a definition of Lispiness that (a) is useful and (b) excludes Scheme is true 21:32:46 hence I must adopt this position 21:32:56 s/ is true$// 21:33:02 elliott: You can laugh at them without making up complicated definitions. 21:33:07 Just point and laugh. It's that easy. 21:33:18 Sometimes you don't even need to point. 21:33:34 s/exy/tim/e 21:34:44 is lisp 1.5 a lisp 21:36:02 one might make the case that cl-style macros are more 'lispy' because they further break down the distinction between compile and runtime 21:36:12 perhaps bonghits will fix your ontological conundrum 21:36:31 Phantom_Hoover: counterpoint: CL macros are a pain to use 21:36:31 Phantom_Hoover: kernel is the best lisp :) 21:36:32 and ugly 21:36:34 and annoying 21:37:27 thue morse is supposed to start with 01, right? 21:37:38 how does that falsify the claim that CL is "lisp" 21:37:51 or are you starting with the axiom that Lisp is beautiful and perfect 21:37:58 Arc_Koen, in the scheme or things, it matters not a jot 21:38:06 I'm trying my brainfuck interpreter in thue against keymaker's thuemorse sequence in brainfuck 21:38:17 and it starts with "0 01" 21:38:28 i wonder if there are any interesting ways left to implement brainfuck 21:38:37 in eodermdrome 21:38:43 i guess every TC proof is that 21:38:44 yeah 21:38:53 that could definitely be interesting 21:38:59 kmc: who said I was falsifying that claim 21:39:03 kmc, in that language I was ranting about earlier? 21:39:10 my counterpoint is i don't care what Phantom_Hoover says because cl macros are annoying 21:39:15 and i don't care about a definition of lispy that means something bad 21:39:21 since the obvious way to do it is to represent code and data as graphs 21:39:28 falsifee, falsify, falsifo, falsifoo 21:39:30 -!- jiella has quit (Quit: Leaving.). 21:39:38 someone implement an efficient eodermdrome please 21:39:39 how about kmc 21:39:40 you do it 21:39:40 which makes implementing it more of a syntactic things? 21:39:50 falsisetto 21:39:57 falsifuckyou 21:40:05 ok I'm pretty sure thuemorse is not supposed to start with "0 01 01" 21:40:06 falsihi monqy 21:40:10 Arc_Koen, no 21:40:12 no it isn't 21:40:14 kmc, would doing it as Mascarpone count as interesting? 21:40:19 @ask monqy monqy = the best 21:40:20 Consider it noted. 21:40:30 (Basically, transforming Mascarpone into Brainfuck via Mascarpone code) 21:40:57 Phantom_Hoover: who's to blame, keymaker or me? 21:41:04 'who nose' 21:41:46 oh wait I think it's reprinting the sequence from the beginning 21:42:11 who nose :^) 21:42:11 "it starts with 0. oh no wait it starts with 01. oh no wait it starts with 0110." 21:44:13 * ion ordered http://www.amazon.co.uk/gp/product/0262201623/ http://www.probabilistic-robotics.org/ 21:44:48 wow, http://esoteric.voxelperfect.net/files/brainfuck/src/factor.b claims to be able to factor any arbitrarily large integer 21:45:00 looks reasonable 21:45:05 I think if it can really do that it's worth more money that I can possibly imagine 21:45:08 -!- nooga has quit (Ping timeout: 245 seconds). 21:45:32 um. 21:45:47 Arc_Koen: you realise the difficulty is factoring *quickly*, right? 21:45:54 yes 21:46:01 otherwise I could do it myself 21:46:12 i have no trouble believing that program does what it claims 21:46:29 well the "arbitrarily large" thing is a little stretched 21:47:20 no. it isn't. 21:47:39 i am confident that brainfuck program's semantics are the factorisation of an arbitrarily-large integer given on input 21:47:44 well, rather, not confident, but I find it entirely credible 21:47:56 ok ok 21:47:56 I have not actually read its source, but it is a simple enough task that it's no great deal to believe it 21:48:14 but still it did sound weird 21:48:41 well existing brainfuck implementations won't be able to do it 21:48:44 since they are limited by your RAM 21:48:45 "you can input arbitrarily large numbers... but don't expect a result soon if they're too large" 21:48:51 but that just means they're unfaithful implementations 21:49:03 well, yeah 21:49:14 (also my implementation is incredibly slow) 21:49:48 ((well, not incredibly, since I do believe it is slow.)) 21:55:43 Brainfuck. Strictly more powerful than C? 21:58:17 it would most certainly be if we had improved it with proper extensions! but for some reason all the people who have tried now believe they are small flying houses 21:58:26 Sgeo: From a computational perspective, yes. 21:58:40 Hmm. 21:58:57 C describes a class of finite state machines, Brainfuck describes a Turing-complete system. 21:59:05 Someone should make a Brainfuck variant that allows for execution of arbitrary machine code. 21:59:14 oh, are you saying that C is so low-level that's it's "overspecified" 21:59:26 Arc_Koen, we're saying that C is not turing-complete. 21:59:35 Arc_Koen: Just that C mandates finite state. 21:59:55 Arbitrarily high bounds, but still bound. 22:00:00 well brainfuck certainly isn't turing-complete if you take the original 30000-cell implementation as a reference 22:00:38 C is Turing-complete if you allow file I/O and read the spec right. 22:10:11 Wouldn't C allow you to construct an infinite doubly-linked list 22:10:22 Therefore obliterating all bounds 22:10:30 wow, never seen that happen before: for domain registrations you have to maintain accurate contact details 22:10:41 and my registrars apparently email all their customers every year to ask if there was a change, just in case 22:11:13 FreeFull: no, because sizeof(void*) has to be finite, and CHAR_BIT also has to be finite 22:11:24 and I /think/ that two pointers with the same bit pattern have to be equal 22:11:44 (I know it wouldn't make any sense for them not to be, but it's interesting to see if the Standard actually says that) 22:12:20 ais523: I see 22:12:21 15:24 elliott: Fine. int main(int argc, char**argv){for(int i = 1; i < argc; i++)if(printf("%s%s",argv[i],i!=argc-1?" ":"")<0)return 1;return putchar('\n') != EOF;} 22:12:27 I think it does say something about how copying the bytes back should produce an "equal" (or something) object 22:12:29 ais523: Is that valid C? 22:12:38 Are you sure file io isn't limited then? 22:12:50 shachaf: it's C, so it's probably not valid 22:13:01 -!- fungot has quit (Ping timeout: 246 seconds). 22:19:36 ais523: "Two values (other than NaNs) with the same object representation compare equal, but values that compare equal may have different object representations. 22:20:10 (C11 6.2.6.1p4) 22:20:28 fizzie: but is it guaranteed that *p1 is the same as *p2 just because p1 and p2 compare equal? 22:21:30 elliott: Can't be, because p1 and p2 might be different types. 22:21:51 If p1 is char* and p2 is int*, *p1 is not necessarily *p2. 22:21:52 :) 22:22:16 pikhq_: Comparing a char* and int* with == is a constraint violation. 22:22:50 -!- Nisstyre has quit (Ping timeout: 256 seconds). 22:23:02 (The types of compared pointers need to be compatible, or one has to be void, or a null pointer constant.) 22:23:06 basic logic usually implies that for any x, y, f, if x = y, then f(x) = f(y) but apparently nobody told that to C 22:24:03 well comparing equal is a concept the C standard defines 22:24:16 it's true that if x = y then nothing can distinguish x and y 22:24:19 but that doesn't apply to C equality 22:24:24 since objects with the same representation can compare equal 22:26:22 do you mean with different representations? 22:27:23 -!- Nisstyre has joined. 22:27:24 er, yes. 22:27:27 given ais523: "Two values (other than NaNs) with the same object representation compare equal, but values that compare equal may have different object representations. 22:27:34 fizzie: (add a " pls) 22:27:56 ". 22:28:12 But now the "quote" has all kinds of stuff. 22:30:24 I think it ended when elliott copypasted your quote (and then he just asked you to add a " pls)\n") 22:31:01 Arc_Koen: Now elliott hasn't closed his (! 22:31:30 and we're two '(' deep now 22:31:39 ))) 22:31:41 (((( 22:31:45 It's all gone wrong! 22:32:06 yeah, we're royally screwed now 22:32:15 ⏝ 22:32:52 -!- Arc_Koen has quit (Quit: break; break; break; break; break; EXIT_FAILURE ) (({)). 22:33:11 -!- Arc_Koen has joined. 22:33:44 -!- sirdancealot7 has joined. 22:33:48 @ 22:33:54 there, that fixed all the unbalanced stuff 22:33:56 # 22:34:26 -!- Arc_Koen has quit (Client Quit). 22:34:30 oh, @ automatically balances all parens, quotes and accounts? 22:34:45 @ also makes coffee. 22:34:45 yes 22:34:51 lambdabot: @ 22:34:51 not sure what balancing an account *is*, but I know the phrase for some reason 22:34:52 Maybe you meant: . ? @ activity activity-full admin all-dicts arr ask b52s babel bf bid botsnack brain bug check choice-add choose clear-messages compose devils dice dict dict-help djinn djinn-add 22:34:52 djinn-clr djinn-del djinn-env djinn-names djinn-ver do docs dummy easton echo elements elite eval fact fact-cons fact-delete fact-set fact-snoc fact-update faq farber flush foldoc forget fortune 22:34:52 fptools free freshname ft gazetteer get-shapr ghc girl19 google googleit gsite gwiki hackage help hitchcock hoogle hoogle+ id ignore index instances instances-importing irc-connect jargon join karma 22:34:52 karma+ karma- karma-all keal kind learn leave let list listall listchans listmodules listservers localtime localtime-reply lojban map messages messages? more msg nazi-off nazi-on nixon oeis offline 22:34:52 oldwiki palomer part paste ping pl pl-resume pointful pointless pointy poll-add poll-close poll-list poll-remove poll-result poll-show pretty print-notices protontorpedo purge-notices quit quote rc 22:34:53 read reconnect remember repoint run shootout show slap smack source spell spell-all src tell thank you thanks thx ticker time todo todo-add todo-delete topic-cons topic-init topic-null topic-snoc 22:34:55 topic-tail topic-tell type undefine undo unlambda unmtl unpf unpl unpointless uptime url v vera version vote web1913 what where where+ wiki wn world02 yarr yhjulwwiefzojcbxybbruweejw yow 22:35:00 lambdabot: ? 22:35:00 Maybe you meant: . ? @ activity activity-full admin all-dicts arr ask b52s babel bf bid botsnack brain bug check choice-add choose clear-messages compose devils dice dict dict-help djinn djinn-add 22:35:00 djinn-clr djinn-del djinn-env djinn-names djinn-ver do docs dummy easton echo elements elite eval fact fact-cons fact-delete fact-set fact-snoc fact-update faq farber flush foldoc forget fortune 22:35:02 fptools free freshname ft gazetteer get-shapr ghc girl19 google googleit gsite gwiki hackage help hitchcock hoogle hoogle+ id ignore index instances instances-importing irc-connect jargon join karma 22:35:04 karma+ karma- karma-all keal kind learn leave let list listall listchans listmodules listservers localtime localtime-reply lojban map messages messages? more msg nazi-off nazi-on nixon oeis offline 22:35:05 oldwiki palomer part paste ping pl pl-resume pointful pointless pointy poll-add poll-close poll-list poll-remove poll-result poll-show pretty print-notices protontorpedo purge-notices quit quote rc 22:35:07 read reconnect remember repoint run shootout show slap smack source spell spell-all src tell thank you thanks thx ticker time todo todo-add todo-delete topic-cons topic-init topic-null topic-snoc 22:35:09 lambdabot: . 22:35:10 topic-tail topic-tell type undefine undo unlambda unmtl unpf unpl unpointless uptime url v vera version vote web1913 what where where+ wiki wn world02 yarr yhjulwwiefzojcbxybbruweejw yow 22:35:11 -!- Arc_Koen has joined. 22:35:15 @get-shapr 22:35:15 shapr!! 22:35:18 it's not working 22:35:23 @thx 22:35:24 you are welcome 22:35:28 @vera 22:35:32 shapr claims it does work but slowly 22:35:32 @help vera 22:35:33 I perform dictionary lookups via the following 13 commands: 22:35:33 all-dicts ... Query all databases on dict.org 22:35:33 devils ...... The Devil's Dictionary 22:35:33 easton ...... Easton's 1897 Bible Dictionary 22:35:33 elements .... Elements database 22:35:33 @thank's 22:35:35 [9 @more lines] 22:35:37 you are welcome 22:35:38 @more 22:35:50 The correct response to @thank's would be “your welcome”. 22:35:59 @@ @echo @echo @echo @echo 22:36:00 echo; msg:IrcMessage {msgServer = "freenode", msgLBName = "lambdabot", msgPrefix = "shachaf!~shachaf@unaffiliated/shachaf", msgCommand = "PRIVMSG", msgParams = ["#esoteric",":@@ @echo @echo @echo @ 22:36:00 echo"]} rest:"echo; msg:IrcMessage {msgServer = \"freenode\", msgLBName = \"lambdabot\", msgPrefix = \"shachaf!~shachaf@unaffiliated/shachaf\", msgCommand = \"PRIVMSG\", msgParams = [\"#esoteric\",\" 22:36:00 :@@ @echo @echo @echo @echo\"]} rest:\"echo; msg:IrcMessage {msgServer = \\\"freenode\\\", msgLBName = \\\"lambdabot\\\", msgPrefix = \\\"shachaf!~shachaf@unaffiliated/shachaf\\\", msgCommand = \\\" 22:36:00 PRIVMSG\\\", msgParams = [\\\"#esoteric\\\",\\\":@@ @echo @echo @echo @echo\\\"]} rest:\\\"echo; msg:IrcMessage {msgServer = \\\\\\\"freenode\\\\\\\", msgLBName = \\\\\\\"lambdabot\\\\\\\", msgPrefix 22:36:00 = \\\\\\\"shachaf!~shachaf@unaffiliated/shachaf\\\\\\\", msgCommand = \\\\\\\"PRIVMSG\\\\\\\", msgParams = [\\\\\\\"#esoteric\\\\\\\",\\\\\\\":@@ @echo @echo @echo @echo\\\\\\\"]} rest:\\\\\\\"\\\\\\ 22:36:02 \"\\\"\"" 22:36:30 @. echo . echo echo 22:36:30 echo; msg:IrcMessage {msgServer = "freenode", msgLBName = "lambdabot", msgPrefix = "elliott!~elliott@unaffiliated/elliott", msgCommand = "PRIVMSG", msgParams = ["#esoteric",":@. echo . echo echo"]} 22:36:31 rest:"echo; msg:IrcMessage {msgServer = \"freenode\", msgLBName = \"lambdabot\", msgPrefix = \"elliott!~elliott@unaffiliated/elliott\", msgCommand = \"PRIVMSG\", msgParams = [\"#esoteric\",\":@. 22:36:31 echo . echo echo\"]} rest:\"echo; msg:IrcMessage {msgServer = \\\"freenode\\\", msgLBName = \\\"lambdabot\\\", msgPrefix = \\\"elliott!~elliott@unaffiliated/elliott\\\", msgCommand = \\\"PRIVMSG\\\", 22:36:31 msgParams = [\\\"#esoteric\\\",\\\":@. echo . echo echo\\\"]} rest:\\\"\\\"\\n\"\n" 22:36:45 @@ @hi @elliott 22:36:46 Plugin `compose' failed with: Unknown command: "elliott" 22:36:57 elliott must be a big fan of @@ 22:37:00 @@ @tell shachaf @echo @echo @echo @echo @echo @echo 22:37:00 @² 22:37:00 Consider it noted. 22:37:01 Maybe you meant: . ? @ bf do ft id pl rc v wn 22:37:06 @thanks 22:37:07 you are welcome 22:37:12 @thanks ion 22:37:12 you are welcome 22:37:27 @clean-massages 22:37:27 Messages cleared. 22:38:32 -!- shapr has joined. 22:38:35 wat? 22:38:39 elliott: SEE! 22:38:45 15:35 @get-shapr 22:38:45 15:35 shapr!! 22:38:45 15:35 it's not working 22:38:52 ha 22:38:58 you guys is funny :-P 22:39:05 @thx shapr 22:39:05 you are welcome 22:39:19 But srsly, my favorite esoteric lang of the moment is HackerFoo's Peg 22:39:31 -!- Arc_Koen has quit (Client Quit). 22:39:35 It has roots in Joy, Haskell, and Prolog. 22:39:42 -!- luite has joined. 22:39:44 fizzie: char* is a god damned weird edge case. 22:39:47 oh hai luite! 22:39:51 hi luite 22:40:03 elliott: #-blah is taking over #esoteric 22:40:16 -!- Arc_Koen has joined. 22:40:19 shachaf: I blame you 22:40:26 olsner: Blame elliott 22:40:30 He's the one who 15:38 15:35 @get-shapr 22:40:31 * shapr goes back to configuring his VPS 22:40:33 shapr: I'll be seeing luite this week! 22:40:36 -!- basti_ has joined. 22:40:38 shachaf: awesome! 22:40:38 I sware I asked my client to quit 22:40:41 I'm jealous! 22:40:42 three times laready 22:40:49 Arc_Koen: It did, but then it got lonley. 22:40:53 lonely* 22:40:59 Jag kan inte stava :-( 22:41:12 can't quit shapr 22:41:17 -!- Arc_Koen has quit (Client Quit). 22:41:25 Eu sou incapaz de soletrar. 22:42:04 -!- Arc_Koen has joined. 22:42:13 hi all, first time i'm in this channel :) looks like i'll fit right in, reading the topic 22:42:22 shapr: En voi kirjoittaa. 22:42:23 hello luite 22:42:31 `welcome luite 22:42:35 luite: 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.) 22:42:42 olsner: Whoa, do you speak Finnish? 22:42:53 * shapr tries to puzzle out that sentence... 22:42:57 shapr: finnish is the native language of #esoteric 22:43:00 I am going to read? 22:43:17 kirjoit is "read" I think.. 22:43:21 * shapr gives up 22:43:27 I'll stick with Portuguese. 22:43:35 oh, and I only speak/write/read finnish using online translation 22:43:38 olsner: I think you mean: enn ùoi kirisìȳoi'ta- 22:43:40 Oh I see! 22:43:48 ion speaks real Finnish. 22:43:49 I'm actually learning Portuguese at school. 22:43:52 So does fizzie. 22:43:56 And fungot. 22:43:58 fungot? 22:44:00 FIZZIE! 22:44:02 PERKKELE 22:44:10 one k 22:44:16 SATANA 22:44:19 I lived in Finland for two years 22:44:22 Lumpio-: two t 22:44:24 ...I am Finnish. 22:44:25 er, two a? 22:44:26 ¬u¬ 22:44:31 shapr: Did you have lakka? 22:44:41 I had salmiakki 22:44:45 I just snark at Finish sometimes. 22:44:49 Lumpio-: Well then I fail :-( 22:44:57 No I made typos on purpose 22:45:02 oh, whew 22:45:11 Because English-speaking people always do that when imitating Finnish 22:45:13 -!- fungot has joined. 22:45:27 ^style 22:45:27 Available: agora alice c64 ct darwin discworld europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 22:45:31 I like listening to Finnish from Lappland, where I spent two years. 22:45:33 fungot 22:45:34 shachaf: ( i don't quite understand what the installer asked me if it's still recognized as a bank, but is it possible to program graphics using the basic defaults, mostly. 22:45:42 ^style alice 22:45:42 Selected style: alice (Books by Lewis Carroll) 22:45:44 fungot 22:45:44 shachaf: " and certainly you've given me the best of it!" 22:45:44 Much as I like listening to Norrbotten Swedish, where I spent five years. 22:45:48 fungot 22:45:48 fungot 22:45:48 shachaf: " and what are you thinking of?" i said, " i'm setting you a riddle fnord your victim be in bed, you know." 22:45:49 shachaf: and what a grand thing it would be such a treat!" said lady muriel. " it's a far more interesting question than ' isn't this a picturesque ruin?' aren't those autumn-tints lovely?' i shall have to go without fifty dinners at once! remember what i told you so! you've no idea what to do? 22:46:02 ^style discworld 22:46:02 Selected style: discworld (a subset of Terry Pratchett's Discworld books) 22:46:06 fungot: 22:46:07 shapr: the singing had stopped... that's foreign for cat's water, you know. 22:46:12 * shapr blinks 22:46:17 fungot: hi 22:46:18 shachaf: mr. ogg, you are fully qualified." the cat purred as the fingers tickled it behind the fnord crabs so they could all see. 22:46:24 The book styles tend to be kinda not so good. 22:46:34 -!- Arc_Koen has quit (Client Quit). 22:46:36 ^style qwantz 22:46:36 Is it done with markov chains? 22:46:37 Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011) 22:46:38 fungot 22:46:39 elliott: so in that, well enjoy pooping in it. all the dudes, they will! 22:46:57 shapr: They're something slightly fancier than Markov chains that I completely forget the name of. 22:46:59 ^style monqy 22:47:00 Not found. 22:47:02 viterbi? 22:47:03 :'( 22:47:08 shapr: If you choose to think of it like that. (It's a variable-length n-gram model.) 22:47:12 yes, that 22:47:16 -!- Arc_Koen has joined. 22:47:25 Huh, that's nifty. 22:47:34 I want to make my markov keyboard layout someday... 22:47:44 It's trained with http://varikn.forge.pascal-network.org/ 22:47:55 (Our department made that thing.) 22:47:59 Where it dynamically remaps your keyboard to pick the letter you are most likely to type next by frequency. 22:48:00 * Arc_Koen gives up 22:48:13 shapr: That sounds awful. :-( 22:48:19 I think if I don't shut the client down quick enough it will always try to reconnect 22:48:20 shachaf: But it would be fun to write anyway 22:48:27 Arc_Koen: Which client? 22:48:31 fizzie: Which department? 22:48:33 colloquy 22:48:38 shapr: If you could make it correct typos, though... 22:48:41 I haven't had it for long 22:48:49 I use ERC myself. 22:48:55 ++ for a keyboard that remaps your keys in prediction of a mistype you're about to do 22:48:59 If the next letter is really likely to be 'x' but I press adjacent key 'y', it could use 'x'. 22:49:06 * shapr thinks 22:49:07 I was on xchat aqua for one or two years but then it suddenly stopped working 22:49:11 shachaf: maybe you should write it. 22:49:13 shapr: The ICS department of Aalto University (formerly TKK/HUT) of Finland. 22:49:16 ++ for a keyboard that reads your mind 22:49:21 shapr: Maybe probably not. :-( 22:49:28 Wait, HUT turned into Aalto? 22:49:34 Half a cheer for Klaymen! Hip hip--hoo! 22:49:38 fizzie: Don't you need "of the European Union of Europe of Earth of ..."? 22:49:40 It's not quite specific enough. 22:49:50 fizzie: Did your department move, or did HUT change names, or what? 22:49:54 HUT is one of the three universities that make up Aalto, yes. 22:49:56 Man, HUT did all sorts of awesome things! 22:50:17 The other two are a business university and an arts university. 22:50:21 I know Linux, ssh, and neural networks all came from the Helsinki area. 22:50:28 and of course ... 22:50:28 IRC 22:50:36 I never neural network I didn't like. 22:50:38 I made a pilgrimage to the first IRC server in Oulu 22:50:51 It's a flowerpot now. 22:50:52 shapr: IRC is dead. 22:50:53 They decided we need more interdisciplinarity and all kinds of such things. 22:51:17 craziness. 22:51:23 I can't decide whether an IRC pilgrimage is the worst or best thing ever 22:51:44 On average it's the most average thing ever. 22:51:46 elliott: It's okay, the was out to lunch so I just stood outside the door reverently for a few seconds. 22:51:49 shapr: So far it's really a single university in name only, really; all three have their own campuses (campi?) and there's not too much intermingling except for a few joint projects. 22:52:05 professor* 22:52:08 campopodes 22:52:16 The arts people are I think supposed to move to Otaniemi in the next decade, though. 22:52:16 fizzie: Ah, that's too bad. 22:52:35 elliott: campodes? 22:52:38 I used to think art students just shouldn't mix with technology, then I saw what art students can do with an Arduino. 22:52:46 campae 22:52:51 fizzie: I know people in universities around here who are really into joint projects. 22:52:58 kmc is probably also into them. 22:53:07 is the joke 22:53:21 It's funny that art students ended up making new flavors of Arduinos that I now use myself. 22:53:37 I thought the arduino was a computer 22:53:45 It is 22:54:03 Arc_Koen: Some art person was like "Hey, I want to sew a computer into my clothes." 22:54:15 And then the Arduino LilyPad was born. 22:54:21 * elliott tries to think of a good way to put on "Arduino" <-> "what do we know". 22:54:22 And shapr was like "sew what" 22:54:24 pun on. 22:54:38 when I decided occam-pi would be a neat new language to pick on all the docs told me "occam-pi is great for programming arduinoooooooos get yourself an arduino right nooooow" 22:54:40 Leah Buechley was the woman who started the LilyPad. 22:54:49 (I guess that is probably not how you pronounce "Arduino".) 22:54:50 Arc_Koen: srsly? 22:54:58 yup 22:55:01 wow, neat 22:55:07 I want to get Joy running on my Arduinos 22:55:09 for the record I did not get myself an arduino 22:55:19 @arr duino 22:55:19 Drink up, me 'earties 22:55:27 YOHO 22:55:29 Arc_Koen: but they're awesome! 22:55:31 i like Joy 22:55:31 @yarr duino 22:55:32 Ahoy mateys 22:55:35 @yarr shapr 22:55:36 May the clap make ye incapable of Cracking Jenny's Tea Cup. 22:55:43 @hey-shapr 22:55:44 shapr!! 22:55:46 Anyway, I'm off to the coffeeshop to finish setting up my new VPS 22:55:48 I'm here! 22:55:52 But I'm leaving :-P 22:55:57 @stay-shapr 22:55:58 Unknown command, try @list 22:56:00 nooo 22:56:02 :-( 22:56:06 I have an interview tomorrow morning! 22:56:08 Foiled by edit distance. 22:56:18 all you have to do is spam @get-shapr and he'll be unable to move 22:56:19 Probly gonna write Python part time 22:56:22 if they offer me enough money 22:56:25 shapr: I'm afraid I might not have all the nerdiness/computer-knowledge required to appreciate how much an arduino can offer me 22:56:31 shapr: what if they offer too much 22:56:39 shachaf: Then I'll drop out of school and have kids. 22:57:00 That sounds dangerous. 22:57:20 shapr: There *was* some amount of HUT name recognition that I think was lost, that's true; Teuvo "SOM" Kohonen has an office five doors right from me (not that he visits very often), and Erkki "(Fast)ICA" Oja is my thesis supervisor, but nobody associates those things with "Aalto". 22:57:21 Arc_Koen: I made an RGB LED clock. 22:57:35 fizzie: sadness :-( 22:57:44 I live in Paalo Aalto. 22:57:47 Does that count? 22:57:47 On the other hand, we're now Finland's foremost university in all lists that are in alphabetical order. 22:57:50 shapr: can you hook up an arduino to a coffee pot? 22:58:04 Arc_Koen: I wake up in the middle of the night, and my body can't tell what time it is... so I set an LED to change color according to the time. 22:58:09 So dull red means "keep sleeping" 22:58:18 shapr: We spell it "colouur" around here. 22:58:18 green means "You can go ahead and wake up now" 22:58:24 and blue means "GO TO CLASS NOW" 22:58:27 Arc_Koen: yes, you can 22:58:33 seriously? 22:58:44 and I mean *seriously* 22:58:56 Arc_Koen: https://www.google.com/search?q=arduino+coffee+pot 22:58:56 no, shapr is lying so he can take over the world 22:59:01 cause if it can then it's most definitely going on my to-buy list 22:59:03 by making everyone buy arduinos that can't interface with their coffee pots 22:59:07 Arc_Koen: http://www.wired.com/gadgetlab/2012/01/arduino-controlled-espresso-machine-rivals-way-more-expensive-models/ 22:59:19 http://www.instructables.com/id/Tweet-a-Pot-Twitter-Enabled-Coffee-Pot/ 22:59:30 http://www.arduino.cc/playground/Main/coffeeTronics 22:59:33 though the top of the list is currently "a car" and I'm not working at the moment so it's gonna take a while before anything on that list gets purchased 22:59:41 @brain 22:59:42 Whuu... I think so, BrainPan! But if running shoes had little feet, wouldn't they need their own shoes? 22:59:54 @@ (@brain) (@brain) (@brain) (@brain) (@brain) (@brain) 22:59:54 Now, Pinky, if by any chance you are captured during this mission, 22:59:54 remember you are Gunther Heindriksen from Appenzell. You moved to Grindelwald 22:59:54 to drive the cog train to Murren. Can you repeat that? Are you pondering what I'm pondering? It is here that my cheap workforce of trained iguanas will work 22:59:54 night and day to make our shoes to my exacting specifications! Well, I think so, Brain, but first you'd have to take that whole bridge apart, wouldn't you? I think so, Brain, but culottes have a 22:59:54 tendency to ride up so. I think so, Brain, but a codpiece made from a real fish would get smelly after a while, wouldn?t it? 22:59:55 shapr: you have no idea how happy you just made me 23:00:06 Arc_Koen: Arduinos really ARE awesome, ok? 23:00:09 and they're cheap 23:00:40 fizzie: Isn't Kohonen really old these days? 23:01:17 fizzie: So wait, if Oja is your supervisor, you're doing neural nets? 23:01:42 shapr: it's like life actually has a meaning now 23:02:20 Anyway, I'm off to finish setting up before my interview. 23:02:46 until now there was this "-> get a car -> find a girl -> marry her -> buy house -> have children -> don't forget to be happy all the way through" pattern in my head but there definitely was something missing about it 23:02:55 something involving coffee at some point or another 23:03:25 fizzie does speech recognition. 23:03:32 Unless he thought better of it by now. 23:03:41 I think if I can hook up an arduino to a coffee pot and to the cigar-lighter from a car and just drive around the world 23:06:24 shapr: Erkki's also a supervisor in name only, since the speech group doesn't at the moment have a professorship, and a thesis needs a professor as supervisor. 23:07:05 that sucks 23:08:38 I do have two "instructors" from the speech group, though, and it's possible one of them could become a full professor in the near future, in which case I'd probably switch the supervisor, since that'd really reflect the reality better. 23:09:06 The only thing I know about speech recognition is Viterbi, sadly. 23:09:18 Seems like it would be a fun thing to apply to syntax-directed programming editors. 23:10:17 shapr: And I suppose Kohonen must be really old; his title is "professor (emeritus)" and he just visits sometimes. A friend was making the Matlab SOM Toolbox that Kohonen (I think) wrote portable to Octave too, he had some discussions with him. But Kohonen is certainly not actively working any more. 23:10:24 has elliott weighed in on this topic yet 23:10:54 ah, elliott, the premier authority on thesis supervisors in finland? 23:11:21 Just the authority on the futility of speech recognition. 23:11:44 I'm an authority on thesis supervisors in Finland, too. 23:12:09 -!- sipa has joined. 23:12:51 yow, 1934! http://en.wikipedia.org/wiki/Teuvo_Kohonen 23:14:59 hm i only know him for his maps :) 23:15:00 The article is a bit dated in that the "Adaptive Informatics Research Centre" it mentions is no longer with us either. 23:15:29 It was a 5-year "centre of excellence" project of the Academy of Finland. 23:15:48 Currently the corresponding-but-slightly-different thing is COIN. 23:15:58 Which... means something. 23:16:39 COmputational INference, I think. 23:16:52 I think words like ohjelmointia are way more fun. 23:17:04 `words --finnish 20 23:17:08 seurootusta uppoamisempiville säänsä pohumalaulun siinsa vihkerrostasi röyhäisempaamuyöskemmassa soljumalaulatalle irroille negattamakkoi tyttävineminanne leuksi asevälitamme tuntavasta harvitsemmassa littuvina omalloa hastamme yhyttäviksi oppiltansa 23:17:11 minä haluan hampurilainen! 23:17:18 (This channel is all about the bots.) 23:17:21 That's awesome :-) 23:17:30 negattamakkoi tyttävineminanne leuksi 23:17:30 `words --dutch 20 23:17:31 whoah 23:17:34 Unknown option: dutch 23:17:38 `words --english 50 23:17:40 :( 23:17:42 Unknown option: english 23:17:42 `words --portuguese 20 23:17:45 `word --help 23:17:46 terão acascurarei encorajará cadorejá recoarão indurai alimatricia calatesolacro enfraremos apaireis descendidora intenregrafa despontado consoldariz tralize desence viteimplebrando ento sacomano destinas 23:17:47 dutch isn't a real language 23:17:49 dei 23:17:50 That's I think a character trigram model, made by.. PH? 23:17:52 @quote dutch 23:17:52 shachaf says: I think Dutch is just a parody of English. 23:17:53 elliott: echtwel 23:17:53 `words --help 23:17:57 Usage: words [-dhNo] [DATASETS...] [NUMBER_OF_WORDS] \ \ options: \ -l, --list list valid datasets \ -d, --debug debugging output \ -N, --dont-normalize don't normalize frequencies when combining \ multiple Markov models; this has the effect \ of making larger datasets more influential \ -o, --target-offset change the target length 23:18:02 `run words --help | paste 23:18:06 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.27718 23:18:07 `words -l 23:18:11 valid datasets: --eng-1M --eng-all --eng-fiction --eng-gb --eng-us --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --catalan --swedish --brazilian --canadian-english-insane --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian --esolangs \ default: --eng-1M 23:18:13 `words --finnish 20 23:18:17 heijastani kehräämpänäsi käytyvissioin eroittavimme kaalisellisimme pystyvikseen mättä pikaamolue grönsyinee unoksesi harkokoorukaisi hankeamme turvaan suomimaniltanevaa tyttyvänäni uimmisemme palkua komenneissä kaimpanasi kiehtimeampiesi 23:18:17 `words --eng-all 50 23:18:20 I wanna see it come up with a real word 23:18:23 mud later ewhockhap whitan tnnsyll radh hauter renmitting potiebzii aschrick ofprov falle abethcllama mafe boulamf ijf anximeld rafielo atjina kasen resen evier self modinato erted 23:18:27 http://translate.google.com/#fi|en|asevälitamme seems to be a real word 23:18:30 mud and later and self sure are words 23:18:34 oo 23:18:36 Lumpio-: "hankeamme" is up there. 23:18:38 it does it more for english 23:18:41 self is a real word 23:18:41 Lumpio-: yaecht 23:18:43 fizzie: What's that mean 23:18:44 `words --eng-1M 50 23:18:48 "turvaan" is a real word at least. 23:18:50 parte joar cla boit dil ihr striment incina virin trible flaxt second recd con servc hab wii asile natclif stralthfe mety rettington assar ielec buck 23:18:54 second! 23:18:55 i guess finnish is more agglutinative so there's more made-up words? 23:18:58 wii, that's sort of like a word 23:19:04 yes finnish is better for this 23:19:08 also the orthography is more consistent 23:19:08 `words --esolangs 20 23:19:10 does it use a first order markov model? 23:19:10 since none of these fake english words have any sort of meaning 23:19:11 luite; You don't really believe in Dutch, do you? 23:19:12 6ix twodu tod buband godscript fal var'aq thess alc blane minispace minifuck-2d sher c-lon 2050706 .box datefuck d1ffe7e45e unisc jot 23:19:16 whereas the finnish things occasionally mean something sometimes, I hear 23:19:20 `words --dutch 50 23:19:23 Unknown option: dutch 23:19:29 Lumpio-: Uh... you know, "hanki" + first-person plural + whatever noun case it was. 23:19:40 Pity getting a database for Japanese would be hard. 23:19:40 `words --hebrew 50 23:19:41 aaah 23:19:43 hankipankki 23:19:43 Yes. 23:19:44 `words --swedish 20 23:19:44 ​הדות ממזווע ומקבלם החדות הדבו מטבע נאמינא ודפס משלת לאתר ומדים והמנזק נדב המצו הסים הנגמולד חסוריד עבאסטה ואות האיכ ברו כהמחמד ויליו כאמלה העמדת 23:19:48 ​ölflacks skatiskan äpphöjer hemmans sippierränsam des luftlande bötfäril ändstremier insatserat blick kningskogets spring undigast grip utveden gamensamattadestfält säng hovs förbär 23:19:50 shachaf: only a little 23:19:57 Finnish is hard. 23:20:10 Oh, the words that could be had. 23:20:12 `words --norwegian 100000000000000000000000 23:20:14 Lumpio-: Also the "project-tub", I suppose, if interpreted as hanke|amme compound. 23:20:16 fiffinbøte disittenesperfatt paknemhjulside papire belverds morendensiene plaskiftsutver fruksvirksom navn livens musledelsenterkutap sulemsentipe føringen kjøp ulykkensjkuponing systbetodeal kjørnestregnsker tobakinsfeiner smålene bollen emndefirmasjons østnerorgiveplegi tralmene hydrofer ettenestertets 23:20:27 fizzie: project-tub sounds like some sort of "Web 2.0" "startup" "incubator". 23:20:29 > length . words $ "fiffinbøte disittenesperfatt paknemhjulside papire belverds morendensiene plaskiftsutver fruksvirksom navn livens musledelsenterkutap sulemsentipe føringen kjøp ulykkensjkuponing systbetodeal kjørnestregnsker tobakinsfeiner smålene bollen emndefirmasjons østnerorgiveplegi tralmene hydrofer ettenestertets 23:20:31 : 23:20:31 lexical error in string/character literal at end o... 23:20:34 > length . words $ "fiffinbøte disittenesperfatt paknemhjulside papire belverds morendensiene plaskiftsutver fruksvirksom navn livens musledelsenterkutap sulemsentipe føringen kjøp ulykkensjkuponing systbetodeal kjørnestregnsker tobakinsfeiner smålene bollen emndefirmasjons østnerorgiveplegi tralmene hydrofer ettenestertets" 23:20:37 25 23:20:43 elliott: It could well be the name of one. 23:20:57 > 25 — 100000000000000000000000 23:20:59 0 23:21:02 Finnish is very hard. I spent two years failing to learn Finnish. 23:21:05 "hankeamme" doesn't sound quite as good, though. 23:21:25 elliott: Maybe they could type it with that |. 23:21:36 shapr: I think you need to embrace your inner Scandinavian first. 23:21:37 shapr: If it makes you feel any better, I've spent 23 years failing to learn Finnish, among other languages 23:21:38 > 25 — 100000000000000000000000 -- hi 23:21:40 0 23:21:48 > 1 — 1 23:21:51 0 23:21:59 fizzie: That |? 23:22:06 > 1————————————————————————————————————————————————————————————————————————————————————————1 23:22:08 Not in scope: 23:22:08 ` 23:22:15 I'm gonna go register "hankeamme" 23:22:16 ais523: You should probably kick me. 23:22:18 > a — b 23:22:20 0 23:22:20 pikhq_: I tried embracing a Scandinavian, she broke up with me. 23:22:30 shapr: I specified "inner". 23:22:37 I learned Swedish! 23:22:38 Sort of 23:22:44 pikhq_: shapr's *inner* Scandinavian broke up with him. 23:22:45 That's a different kind of relationship 23:22:47 It's pretty sad. :-( 23:22:51 I think Swedes only ever learn Swedish sort of, too. 23:22:52 shachaf: haha 23:23:11 hydrofer is a neat word. 23:23:24 shapr: You're not even in #scannedinavian. :-( 23:23:32 `words 23:23:33 Wait, you are. 23:23:36 elliott: "hanke|amme". With a nifty logo. 23:23:38 awakely 23:23:47 bah this channel is too active for my productivity 23:23:47 It's a very cruel name 23:23:48 fizzie: Ooh, fancy. 23:23:51 hank?ea"mme! 23:23:57 `words --list 23:24:00 valid datasets: --eng-1M --eng-all --eng-fiction --eng-gb --eng-us --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --catalan --swedish --brazilian --canadian-english-insane --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian --esolangs \ default: --eng-1M 23:24:05 luite: Just don't read it. 23:24:08 `words --gaelic 23:24:09 luite: None of the rest of us do. 23:24:11 luite: It's like #haskell; you can just ignore all the noise. 23:24:12 unpossible 23:24:12 t-siubh 23:24:15 `words --gaelic 30 23:24:18 lomail feal dhe bas caobhan leòc t-uiste ursaich n-eunlamus bliab ceisd athalm chomh treit déidean ain cleach taobradh fiod fhallainn ulladha-rèid timchadh cais stàtaich caibhionn 23:24:23 Except that #haskell is 90% noise and #esoteric is 101%. 23:24:25 `words --polish 10 23:24:25 #haskell is a lot quieter atm :) 23:24:27 bliab 23:24:28 `words --russian 10 23:24:29 pozaną sesemizdaturozsiedocerwsz rytorowy skrysokowywracją nientaktotane wiedodraczał obształybyśmy bydlepylajkach mantetyczykryn zagrzekliłem 23:24:30 `ＷＥＬＣＯＭＥ　luite 23:24:30 Or never be productive. 23:24:35 ​десически най засеялист частолмский масбродом дений тей ьняемом хьюэлоняющие солод 23:24:37 `words --eng-fiction 1- 23:24:40 `words --canadian-english-insane 10 23:24:40 `ＷＥＬＣＯＭＥ luite 23:24:40 if i have a daughter i shall call her bliab 23:24:47 `words --eng-fiction 10 23:24:48 Okay, sleb now; have to be up in 4-and-a-half hours to give an insulin poke to our recently diagnosed diabetic cat. :/ -> 23:24:50 I wish gandi would let me change my country, I don't live in Finland anymore :-( 23:24:54 fizzie: :( 23:24:55 `words --eng-all 23:24:56 everrel amicallin orgolded genetota free pherbodynanting suctua constacebubbuktu lation timeno 23:25:01 Argument "1-" isn't numeric in int at /hackenv/bin/words line 148. \ padi 23:25:03 * pikhq_ *still* hasn't bothered to actually get this thing to do LZ 23:25:05 lebulk caterab vofa sau tection hath attaine int motected beckund 23:25:06 "ьняемом" hahaha, what? 23:25:09 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ＷＥＬＣＯＭＥ　luite: not found 23:25:09 shapr: you'd think gandhi would be more understanding of such things 23:25:10 phog 23:25:14 `words --eng-all 30 23:25:16 ​ＬＵＩＴＥ：　ＷＥＬＣＯＭＥ　ＴＯ　ＴＨＥ　ＩＮＴＥＲＮＡＴＩＯＮＡＬ　ＨＵＢ　ＦＯＲ　ＥＳＯＴＥＲＩＣ　ＰＲＯＧＲＡＭＭＩＮＧ　ＬＡＮＧＵＡＧＥ　ＤＥＳＩＧＮ　ＡＮＤ　ＤＥＰＬＯＹＭＥＮＴ！　ＦＯＲ　ＭＯＲＥ　ＩＮＦＯＲＭＡＴＩＯＮ，　ＣＨＥＣＫ　ＯＵＴ　ＯＵＲ　ＷＩＫＩ：　ＨＴＴＰ：／／ＥＳＯＬＡＮＧＳ． 23:25:22 monsophv wilbee adnancerit ische day oestru josing oraae sor mac mal typali cyclng cmic boarkr mtheran tre wlden glanded plc carta charmen cordik qaz krton 23:25:29 `WeLcOmE shapr 23:25:34 ShApR: 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.) 23:25:36 yow 23:25:54 oh my, this channel really went down the bot hole this evening 23:26:05 monsophv wilbee andnancerit ische day 23:26:07 i blame shapr 23:26:08 er 23:26:08 shachaf 23:26:15 shapr: can you change your name so i can press sha 23:26:17 blame me, everybody else does! 23:26:20 elliott: nope 23:26:23 :( 23:26:24 I forgot how. 23:26:36 /nick not-shachaf 23:26:42 too lazy 23:27:18 wow, I never thought anyone could be lazier than me 23:27:39 `words --eng-1M --eng-all --eng-fiction --eng-gb --eng-us --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --catalan --swedish --brazilian --canadian-english-insane --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian --esolangs 50 23:27:47 `words --welsh 10 23:27:51 Unknown option: welsh 23:27:59 Killed 23:28:04 :( 23:28:17 Manx, but no Welsh? 23:28:30 `words --eng-1M --eng-all --eng-fiction --eng-gb --eng-us --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --swedish --brazilian --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian 50 23:28:32 And no Cornish?! 23:28:33 `words --esolangs 30 23:28:37 dev grusomnia crab triinc help cabrainfuck ext() dot mycelium pointer quantum symespearbf binarylis sendejx musicasmith subskin ted rubescript tri super stantum netwofiftysnail .ger che jug 23:28:41 ext() 23:28:49 Killed 23:28:49 `words --manx 30 23:28:52 claitnys surrym erchoo n'egoil jeshaslavio bogh-screg hellvee thie ker maane-chaa tonnoropal morteir ny-chey jedoobeydagh bengle breeagh lieen shiare eays neuglouan etlag furreyder daagyrtarman shan lharvian 23:28:58 `words --eng-all --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --catalan --swedish --brazilian --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian 50 23:29:05 manx is awesome, apparently 23:29:07 tonnoropal is a good word 23:29:14 webcarting lekterprdrownowboy größenphy qatarabasseturoo uljeitus annum perail cybenblivativaron bai naphenava mará уолствахъли prísti arterrsivelsiom abulark ion друсирод exema physika dark-ono blator tement сотэрд nachaura כשעתו 23:29:28 It'd be cool if it had scots 23:29:28 webcarting 23:29:37 that is the best word I have ever heard 23:29:43 Phantom_Hoover: I get the feeling that everyone who speaks Manx is a dragon 23:30:42 elliott: what is webcarting? 23:30:48 ask HackEgo 23:31:01 olsner: "the best word [elliott] [has] ever heard" 23:31:02 Can't you read? 23:31:09 … ion … 23:31:20 ion 23:32:10 `words --polish 30 23:32:13 zbalnymiancjujecie datnymienami cienaśnie wibranżowski świnetucja niemonowanizowa nieastowe przykowacyjny sztynomowandrzemnym nieautowaniują niezdyssidlana naklowertowi półletnikownej podbijaku wychodziweryplątech zbranowocestrynk zakomusinizorowni łowiajże ocystawizmy niehiperach nierzowałbyście rozsynosłowym pełźnicowie replatowańskakudze zaparskiemaszmacki 23:32:21 polish is boring 23:33:02 It's very poetic 23:33:11 And is good for swearing 23:33:38 "Because Manx has never had a large user base..." -- [[Manx]] 23:34:25 i'm now seeing manx as a shitty scripting language that nobody used 23:34:47 ion: ? 23:35:17 shachaf: ! 23:35:51 16:32 ಠ_ಠ 23:35:55 `? webcarting 23:35:59 webcarting? ¯\(°_o)/¯ 23:36:07 * shapr tries to remember how to configure DNS 23:36:29 shachaf: That was a weird tree. 23:36:34 -!- basti_ has quit (Quit: n8). 23:36:52 -!- noals has joined. 23:37:03 -!- NihilistDandy has quit (Quit: ["Textual IRC Client: www.textualapp.com"]). 23:37:11 -!- noals has left. 23:38:21 -!- monqy has joined. 23:38:49 `learn webcarting is not dissimilar to Mario Kart, but uses real, remote-controlled go-karts. Participants describe it as "the outlandish spectacle of real go-karting combined with the thrill and immersion of Mario Kart". 23:38:52 I knew that. 23:41:28 ion: Try writing some functions that use it! 23:54:09 fmap f (Leaf a) = Leaf (f a); fmap f (Node t) = Node (fmap (f *** f) t) 23:54:23 Right. 23:55:39 Now toList! 23:56:35 Feel free to define it for us, i feel like doing something else. :-P 23:56:49 Phantom_Hoover: is that a real thing? 23:56:57 no 23:57:14 tell randall munroe about it, doubtless he'd think it's a good idea 23:57:18 heh 23:57:54 99,999,999 blog authors and commenters agree: webcarting is "awesome" 23:59:14 millions of office workers briefly comforted by the fantasy of indulging in a pointlessly expensive and destructive hobby 23:59:39 go-karts are pretty hardy 2012-10-15: 00:00:25 not as hardy as stop-karts 00:02:05 are those real russian words? 00:02:09 up there a bit 00:02:13 google can't translate most of them 00:02:27 хьюэлоняющие 00:19:33 whoah i didn't know kmc was still alive! 00:19:42 hi luite 00:19:46 hi kmc :) 00:19:52 you coming to bahug? ;) 00:24:11 kmc: don't lie, you'd play webcarting. 00:24:34 at least I would 00:26:28 i went go-karting once 00:26:31 it was terrifying 00:26:48 i almost went drunk go-karting in montenegro but decided against it 00:26:51 beacuse i am lame 00:28:07 > ord '@' - ord 'r' 00:28:08 -50 00:36:59 > ord '@' 00:37:00 64 00:37:05 :t ord 00:37:06 Char -> Int 00:37:35 What's ord in? 00:37:54 Prelude 00:38:43 No it isn't 00:38:58 At least not according to ghci 00:39:04 Bah 00:39:55 shachaf: Ok, i’m back and i felt like doing it. toList t = toList' (:) t []; toList' f (Leaf a) = f a; toList' f (Node t) = toList' (\(a,b) -> f a . f b) t 00:41:18 toList' needs a type signature, type inference seems unable to handle it. toList' :: (a -> b -> b) -> Tree a -> b -> b 00:41:19 FreeFull: Data.Char 00:41:34 ion: This is data Tree a = Leaf a | Node (Tree (a, a)) right? 00:41:39 yeah 00:42:03 elliott: This will be of great use to me 00:42:03 ion: Doesn't this work? toList (Leaf a) = [a]; toList (Node t) = toList (fmap fst t) ++ toList (fmap snd t) 00:42:26 ion: I have toList (Leaf x) = [x]; toList (Node t) = concatMap (\(x,y) -> [x,y]) (toList t) 00:42:37 Also needs a type signature. 00:42:42 Yours is more efficient, I guess. 00:43:16 ion: Now write fromList! 00:43:23 elliott: toList (Node (Node (Leaf ((4,5),(6,7))))) = [4,6,5,7] 00:44:11 ion: s/++/`interleave`/ then? 00:44:53 I think I get elliott's behavior if I use unzip instead of the thing I did. 00:45:22 anyway ion's implementation is obviously wrong because it's ugly 00:46:56 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:53:50 foldMap f (Leaf a) = f a; foldMap f (Node t) = foldMap (\(a,b) -> f a <> f b) t 00:54:08 and get toList for free 00:57:48 isn't your toList' just fold with a wonky argument order anyway 00:58:13 ion: btw fold > foldMap 00:58:23 i guess it's actually more awkward here though :/ 00:58:41 fold (Leaf a) = a; fold (Note t) = fold $ fmap (uncurry mappend) t? 01:01:01 pikhq_: what's the one that isn't twisted neumatic called 01:01:06 IPS, thanks 01:02:03 ooh you can get IPS monitors cheapish nowadays?? 01:02:05 thanks monqy 01:03:26 yeah they are pretty cheap now 01:03:34 elliott: Yeah, that works. But you’ll also have to define foldMap f = fold . fmap f (or alternatively, foldr). 01:03:50 ion: pretty sure that's a default in Foldable 01:04:05 elliott: Alas, it isn’t. 01:04:19 The default foldMap uses foldr and the default foldr uses foldMap. 01:04:43 kmc: yeah this ASUS one is surprisingly cheap ($175 for 23" LED/IPS), downsides are seemingly that it has a really ugly placement of buttons jutting out from the bottom that would annoy me endlessly & that it actually has less than 96 ppi 01:04:48 elliott: http://techreport.com/review/23291/those-27-inch-ips-displays-from-korea-are-for-real 01:04:53 also it's asus and I seem to recall their displays are shit 01:04:58 so 01:05:06 I guess what I mean is they started selling bad IPS displays 01:05:35 oh it brags about 5 ms response time too 01:05:41 there are no-brand korean IPS monitors for really cheap 01:06:04 ion apparently just linked to that 01:06:12 27" is too big though :( i'm too small to use a 27" display 01:06:39 http://www.overclock.net/t/1225919/yamakasi-catleap-monitor-club 01:06:42 ah yeah 01:07:01 i have three dell IPS monitors at work 01:07:37 also they look too high-ppi for 2012 01:07:47 but i spent an unreasonable amount of money on them 01:07:58 everyone is still using pixels so I cannot buy a high-enough ppi monitor without annoyingness :( 01:08:35 if you want a 24" 16:10 monitor i like the Dell U2412M 01:08:38 it's about $300 at newegg 01:08:55 mm 01:09:00 i can't actually buy things from newegg because i am in the uk 01:09:06 I just find stuff on newegg and then pray someone sells it in the UK 01:09:09 heh 01:09:14 well i'm sure someone does sell this 01:09:18 and it is always for like twice the price when I do 01:09:24 they actually don't sell to UK or is the exchange rate just horrible? 01:09:31 they don't ship to uk 01:09:34 or at least 01:09:36 didn't years ago 01:09:37 maybe they do now 01:09:45 elliott: Say hi from me to the queen. 01:10:13 kmc: this one is 8 ms, it must be good 01:10:19 yeah i've heard you basically pay the same number of pounds as the US dollar price :/ 01:10:26 for electronics in the UK 01:10:27 how to judge monitors: look at the advertised response time 01:10:29 the higher it is, the better 01:10:39 And the dynamic contrast ratio. 01:11:24 -!- monqy has quit (Quit: hello). 01:11:36 kmc: i'm annoyed that the 14" displays are always 1920xwhatever 01:11:47 the ppi!!!!! so low!! 01:11:49 er 01:11:49 24" 01:11:51 all displays are 1920xwhatever basically 01:11:56 yeah 01:12:15 http://i.imgur.com/E00nl.gif 01:12:21 anyway i hear dell monitors are good 01:12:24 so maybe I should just look at those 01:12:28 The cheap Korean ones are 2560×something 01:12:53 i should get an IBM T221 01:13:10 conspicuous consumption and all that 01:13:29 hopefully the PC hardware industry will copy apple's retina display, like they copy everything else 01:13:37 kmc: Indeed. 01:13:57 About time to get a bit less sucky DPI values. 01:14:00 http://upload.wikimedia.org/wikipedia/commons/6/64/IBM_T221.jpg 01:14:07 ibm t221, because you don't want to be able to see your xterms 01:14:24 i think it actually shows itself as multiple displays to the graphics card or whatever 01:14:30 so you have to set up a multi-monitor OS setup to get it working 01:15:12 Ah, someone i know on IRC has one. 01:15:33 only updates at 41 Hz :/ 01:16:05 kmc: you only get so much from 2001 tech 01:17:27 [[You see, shortly after I mentioned on Twitter that I'd ordered one of these monitors, my friend Jeff Atwood of StackOverflow and SuperUser fame decided to order three of them on my "recommendation." Vaguely terrified, I tried to explain that my review was still forthcoming, but he wasn't dissuaded.]] 01:17:29 thanks jeff atwood 01:17:59 ion: you forgot to mention how the buttons are broken 01:18:19 good thing i am the kind of awful person who uses their display at full brightness always 01:19:06 oh 01:19:08 the buttons are just complicated 01:19:09 great 01:19:20 Buttons? You don’t need buttons where we are going. 01:19:53 "I fairly quickly realized that the flashing power LED above the buttons was an indicator: the faster or slower it flashed, the higher or lower the volume." 01:20:17 it is a good thing i don't have any use for in-monitor speakers 01:20:21 because ha ha LED that flashes constantly 01:20:26 elliott: Please tell your Amazon to ship (sorry, “dispatch”) my booke quickly. 01:20:31 theff atwood 01:20:54 ion: sorry but amazon is a bookstore not a bookestore looks like you got mislead!!! 01:20:58 elliott: I like to think that quote is about the T221 01:21:04 bookstor 01:21:25 bokehstore 01:22:10 kmc: sorry it's about the korean things 01:22:13 sory 01:22:33 i would like to live in a world where equipment does not have awful status LEDs 01:23:26 sometimes i disable them 01:23:35 hack your annoying LED using tape 01:23:41 that's work though 01:23:42 yes tape works 01:23:44 but tape is also sort of gross 01:23:50 on one computer i soldered a 10 kΩ resistor in series with the power LED 01:24:16 hm i bet i could sell a power LED dimmer that just plugs into the motherboard header 01:24:47 and then i could sell the Y3TI MUTILAT0R XTREME GAMER EDITION of that for $50 01:25:21 i think i know what happens next in this annual effort to upgrade my computer to something better than a toshiba half-laptop-half-netbook-from-a-few-years-ago 01:25:26 it's keyboard obsessiveness :( 01:30:07 "The fact that these two monitors are in a dead heat in response times comes as little surprise, since they both appear to lack an internal chip dedicated to scaling or other forms of image processing. Such chips enable all sorts of nice features, but they're also one of the primary contributors to input lag." 01:30:15 hm, I wonder what these are listed as in product descriptions so I can avoid them 01:30:42 do you actually care that much about lag 01:31:03 kmc: well it depends what you mean by care 01:31:04 don't monitors regularly get sub 10ms latency even with processing? 01:31:11 i have to at least pretend to care to myself 01:31:23 the other day my monitor crashed such that half the screen was overlaid with noise 01:31:29 and rebooting the monitor fixed it 01:32:05 the mission of all tech is to introduce as many points of failure as possible 01:33:22 * shapr agrees 01:35:38 kmc: do you know anything about the current state of SSDs? I am several years out of the loop 01:36:05 yeah there are a lot of credible alternatives now 01:36:19 http://www.storagereview.com/best_drives 01:36:32 only the intel drives were worth anything last time I checked, which was a long time ago 01:36:37 except some OCZ stuff was ok too or something 01:36:47 yeah that's how it was when i bought my first SSD 01:36:55 now Intel is still good but there are viable alternatives 01:37:38 I don't suppose capacity is high enough to use SSDs exclusively without being rich yet 01:37:51 admittedly this laptop just has a 256 gigabyte drive, but it's sort of not ideal 01:37:56 i recently bought a 240 GB Intel SSD 520 01:37:58 for $250 01:38:15 i'm happy with it so far 01:38:26 my laptop has an older Intel X25-M 80 GB 01:38:38 i find 80 GB is plenty of local storage 01:39:17 since i'm only running one OS and it's Linux 01:39:37 I have a 120 GB OCZ Vertex 3. I’ve been happy with it. 01:39:40 -!- Frooxius has quit (Ping timeout: 246 seconds). 01:39:56 kmc: well it depends what you mean by "local" 01:39:59 i have all my TV shows and music and such on a 10 TB fileserver 01:40:07 which i can sshfs-mount when i am at home 01:40:10 I only use one computer at a time, so pretty much everything gets centralised 01:41:28 i have a laptop and a file server and a desktop at work 01:41:46 also an ec2 instance which just runs irssi and finch 01:45:27 hm, i find 80GB too small for my laptop, got a samsung 830 256gb recently :) 01:46:29 -!- copumpkin has quit (Ping timeout: 260 seconds). 01:47:04 -!- copumpkin has joined. 01:50:05 nice 01:50:22 "I also make bacon unicorn references on Twitter." 01:50:26 i will get a new laptop soon, and it will have more space because SSD space is so cheap now 01:50:29 that sure does win the prize for worst by-line ever 01:53:10 Not as cheap as HDD yet 01:54:04 sure but much cheaper than when i bought that 80 GB SSD back in 2009 01:58:20 Well hardware prices do tend to go down for PC stuff 01:58:59 keen observation 02:01:28 -!- FreeFull has quit (Quit: Zzzzzzzzzzzzzzzzzzzzz). 02:02:19 FreeFull really has a way of stating obvious 02:02:51 i see they have started pushing the clock speed of processors back up 02:02:57 and dialing back the core numbers 02:04:35 how's that? 02:04:49 the new thing is "Turbo Boost" or whatever 02:05:01 which means that if only one core is active, it can use a higher clock than the max clock of allcores together 02:05:09 because the limiting factor is heat dissipation 02:05:41 well there is this "Intel Core i7-3770K Ivy Bridge 3.5GHz (3.9GHz Turbo) LGA 1155 77W Quad-Core Desktop Processor Intel HD Graphics 4000 BX80637I73770K" (catchy name) 02:05:48 last time the i7s were all like sub-3 ghz but 8-core 02:05:59 i doubt they were 8 core 02:06:13 they might have been erroneously advertised as such when they are 4 core with hyperthreading 02:06:44 i thought they were 02:06:56 maybe, how long ago was that 02:06:59 hm 02:07:00 apparently not 02:07:06 weird 02:07:14 maybe i am thinking of the nehalem xeon 02:08:37 yeah i don't think they have shipped more than 6 cores in a non-xeon chip 02:09:22 ugh I forgot computer cases are the land of living hell 02:09:30 everything is terrible 02:09:57 yeah your choices are ugly beige box or some ridiculous blinged out monstrosity with a plexi cutout of a dragon fucking a robot 02:10:14 i really like the Antec Three Hundred; it is a rare exception 02:10:26 i seem to remember deciding to buy an antec case last time 02:10:40 and it has good cable management stuff on the inside 02:11:00 other recommendation is don't buy fans smaller than 120 mm if you care about noise 02:11:18 and seal all places where dust might get in, with fan filters or just tape over them 02:11:51 yeah I was sufficiently obsessive to develop Opinions about fans last time 02:11:54 hopefully I can remember some of that by now 02:12:12 (this is why I never get anything done) 02:13:09 http://www.newegg.com/Product/Product.aspx?Item=N82E16811133188 wow look at this thing 02:13:14 what a mess 02:13:34 they should make an art exhibit filled with insane computer cases 02:14:11 it's called every brick and mortar computer store 02:14:37 that one is super ridiculous 02:14:56 it looks like a transformer 02:16:32 i like http://www.newegg.com/Product/Product.aspx?Item=N82E16811147111 as a small cheap case but it's out of production or something 02:17:03 http://www.newegg.com/Product/Product.aspx?Item=N82E16811129042 appears reasonable 02:17:22 kmc: did the computer industry work out what kind of ATX it likes best yet 02:17:32 yep i have that one 02:17:35 the antec three hundred 02:17:36 it's good 02:17:47 I seem to remember deciding to get an Antec P182 last time, but apparently they don't exist now!! 02:17:53 elliott: shrug 02:18:04 elliott: *-ATX fits in a straight ATX case. 02:18:08 if you have a big case then it doesn't matter 02:18:09 right 02:18:20 if you want a small case then you might need a micro-ATX motherboard 02:18:26 which isn't really that small 02:18:34 it seems like there are more smaller-than-ATX mobos and cases than ATX stuff nowadays 02:18:48 The other *-ATX stuff is just smaller versions of ATX; they fit in a full ATX case, you just have a lot of empty space. 02:19:07 a lot of mobos are micro-ATX, yeah, because they don't need more space 02:19:18 Well, there's larger variants too but you are probably not getting them. 02:19:25 smaller stuff like mini-ITX is not compatible though 02:19:37 holy shit RAM is cheap these days 02:19:46 i mean even cheaper than it was before 02:19:48 -!- monqy has joined. 02:19:50 yeah seriously 02:19:53 Yes, RAM is cheaper than fuck. 02:20:02 yeah you can get 4 GB for like $15 02:20:06 you can't get a good fuck for that 02:20:12 See? 02:20:37 if I wanted I could buy 64 gigabytes of ram for $285 02:20:46 uses I have for 64 gigabytes of RAM: 02:21:13 yeah who even needs a SSD then 02:21:17 all your files will be cached forever 02:21:27 monqy: welcome back 02:21:34 monqy: weren't you just here a second ago 02:21:39 no 02:22:25 I wonder if I can convince myself buying 32GB of RAM for $140 is at all reasonable 02:22:35 why do you need it 02:22:58 monqy: that's the main problem :( 02:23:00 I'm sure some starving kids in africa could make much better use of all that ram 02:23:08 don't be silly monqy 02:23:12 they don't have computers in africa 02:23:28 elliott: you need 64GB for debugging ghc! 02:23:43 luite: you mean you need 64GB for compiling anything with ghc :P 02:23:51 that too 02:24:02 so is phantom hoovere blogging about brainfuck now 02:24:25 so is taneb blogging about brainfuck now 02:24:35 africa is such a poor country 02:25:27 hi kmc, luite, elliott, monqy, africa 02:25:41 "pleasure 2 meet u" 02:26:20 elliott: How do you think I feel with a measly 8GB? 02:26:36 I forget how many gb I have but I think it might be 2 02:26:38 maybe 4 02:26:40 I've got 4. 02:26:44 where's nortti 02:26:47 But, I'm using a few-years-old system. 02:26:57 Which only faintly resembles modernity. 02:26:59 I've got 4 and I run out just browsing the web 02:27:01 thanks 2012 02:27:01 new systems are for losers 02:27:21 monqy: are you calling me a loser!!! 02:27:23 flash player nearly makes my computer grind to a halt 02:27:24 I managed to get it so it's quite usable, though. 02:27:29 I now use LXDE and Opera. 02:27:30 monqy: do you use a dumpster computer 02:27:37 ion: Did you write fromList yet? 02:27:38 well sometimes it's fine 02:27:40 I'm using 2.6 gigs for tons and tons of tabs. 02:27:41 other times it grinds to a halt 02:27:42 pikhq_: xmonad uses less RAM than lxde 02:27:43 * elliott smug 02:27:55 Eh. 02:28:10 elliott: You know what uses less RAM than xmonad? 02:28:16 LXDE is a non-revolting DE. 02:28:24 shachaf: Nah, i’m playing FTL. 02:28:25 And doesn't make X leak like a sieve. 02:28:31 (XFCE has X resource leaks.) 02:28:33 shachaf: is it @ 02:28:44 is it twm 02:28:45 ion: Should I acquire FTL? 02:28:45 pikhq_: xmonad is a non-(revolting DE) 02:28:54 shachaf: Yes. It’s great. 02:28:55 elliott: I was thinking of Windows 3.11. 02:28:56 speaking of what's hot and new, what's the language of the future these days 02:29:01 elliott: Why yes, yes it is. 02:29:05 ion: Does it require OpenGL to run? :-( 02:29:08 I don't have OpenGL. 02:29:11 i love dumpster computers 02:29:14 also dumpsters 02:29:15 i hear FTL is a good roguelikelike except for the last bit which is bad 02:29:21 also it's actually a roguelike if you just press pause all the time 02:29:27 my friend made really good pear bread from some pears from the whole foods dumpster 02:29:38 (good rogue)like 02:29:56 kmc: do consumer motherboards support ECC RAM yet 02:30:09 I’d expect it to work well enough with software OpenGL implementations, but it might not. In any case, this is the best place to get it since you’ll get the DRM-free versions (Linux, too) as well as a Steam key. http://www.ftlgame.com/ 02:30:21 ion: I don't even have software GL. 02:30:29 i hear it's good roguelikelike except for i hear you need specific stuff or attack power or something to deal with the last bit. i don't know anything else about ftl 02:30:36 those are just the things everyone talks about 02:30:39 not what ftl actually is 02:30:41 monqy: right I hear the final boss ``cheats'' 02:30:52 by not letting you use a bunch of playstyles that are viable up to that point 02:30:56 elliott: oh no! 02:31:01 elliott: can i ``cheat'' too? 02:31:13 The boss is a challenge, but it’s winnable. 02:31:19 rm -rf final.boss 02:31:25 "how do u like that" 02:31:28 elliott: not to my knowledge 02:31:38 maybe sometime in the future I'll play a game 02:31:39 kmc: hooray 02:31:43 maybe some high end enthusiast ones 02:32:02 but maybe not because it would slow down kill3r overclockzzzz 02:32:57 you can use a server board in a desktop of course 02:33:06 but there are some drawbacks, like the onboard video is probably enormously shit 02:33:28 we did this at ksplice and the onboard video literally could not handle moving windows around on a normal 2D linux desktop 02:33:36 nice 02:33:36 it had like 8 MB of VRAM 02:33:45 well i plan to buy a video card of some sort 02:33:52 since intel integrated graphics are still shit right 02:33:56 except for having good linux support 02:34:06 i think they're pretty good 02:34:16 basically all laptops with integrated graphics have intel 02:34:32 don't expect to play the latest games on high settings 02:35:09 but how else can I delay the feeling of having spent an awful lot of money on a computer that is totally excessive for my needs 02:35:33 shachaf: Why don’t you have OpenGL? 02:35:45 yeah you better buy at least two high end video cards 02:35:46 ion: nvidia optimus 02:35:55 more like pessimus am i right 02:36:02 Yes. :-( 02:36:53 Shouldn’t mesa work on anything? 02:37:18 I've yet to get any xorg.conf to work. 02:38:24 perhaps bonghits will fix your xorg.conf 02:39:28 kmc: I don't I can do this alone. It'll have to be a joint effort. 02:39:31 kmc: remember that terrible optimus keyboard 02:39:53 yes 02:40:09 elliott: It was terrible? 02:42:08 it was extremely expensive because it has an OLED display under each key 02:42:20 they also make a much cheaper (still too expensive one) which just has transparent keys over a LCD 02:42:28 That doesn't sound terrible to me. 02:42:40 it probably sucks as a keyboard, i dunno 02:42:44 I don't *look* at my keys. 02:43:10 kmc: Just imagine the amazing Compose-key customizations you could make to it! 02:43:12 it's not so much a real product as an art / concept prototype, which people with far too much money could order on a small run basis 02:43:15 yeah! 02:43:16 man 02:43:18 that would be the best 02:43:47 pikhq_: in theory it would be useful for learning the keyboard shortcuts for a new application 02:43:59 you know, if the programs actually knew about it 02:45:15 It would be nice if I felt like learning the kana layout. 02:45:46 Though to do that "right" I'd probably also need the weird extra keys... 02:45:51 pikhq_ kana be bothered. 02:45:55 the black keys 02:46:03 The ones that would be right where the groove in my spacebar are. 02:46:04 Or maybe it would be more accurate to say that he ain't kana. 02:46:15 (seriously, I've got a freaking groove worn in my spacebar) 02:49:11 i read "i've got a freaking grove worm in my spacebar" 02:49:36 i read "three men in a boat" 02:49:43 heh 02:49:48 i read that after you told me to 02:50:04 http://images1.wikia.nocookie.net/__cb20100605031305/spyro/images/6/67/Grove_Worm.png 02:50:35 i didn't even know it's a thing 02:54:46 Java 2 Electrical Engineer 02:55:13 kmc: Did you read TaPL? 02:55:23 yeah 02:55:28 and some of ATaPL 02:55:44 Is it good to read if I want to learn more about type systems? 02:55:48 kmc: What's the difference between Sandy Bridge and Sandy Bridge-E and Ivy Bridge? :( 02:55:48 yes 02:55:57 ivy bridge is the new generation 02:56:15 e is some xeon version 02:56:34 hmm, why are they selling consumer processors with E then? 02:56:45 oh really? 02:56:55 Ivy Bridge is newest, it's the same architecture as Sandy but shrunk to 22 nm process, and with some minor additional features 02:57:31 -E is high end i7 and Xeon. 02:57:41 ah right 02:57:41 That is, it's *also* some consumer models. 02:57:41 a hardware RNG 02:57:45 Ivy Bridge is what you want. 02:57:46 and a semi useless kernel security feature 02:58:13 and faster gfx 02:58:21 i7s sure do seem more expensive than last time... I guess because now there's the whole i3/i5 split 02:58:36 elliott: Better wait for Haswell. 02:58:41 Haswell is the future. 02:59:00 If you can wait 'til June. 02:59:20 shachaf: Is Haswell like Haskell? 02:59:28 elliott: Yes. (No.) 02:59:33 I think you mean yes. 02:59:40 elliott: Well, it has transactional memory!!!! 02:59:44 elliott: Nah, it's the latest tock iteration of Intel's design cycle. 02:59:52 And, yeah, HTM. 02:59:55 pikhq_: Isn't it a tick iteration? 03:00:05 I see they aren't at single-digit nanometers yet 03:00:13 * shachaf suspects pikhq_'s clocks go backwards. 03:00:17 No, tick is the die shrink. 03:00:24 Oh. 03:00:28 Maybe it's my clocks, then. 03:00:32 Why do they have the major changes on tock? 03:00:33 That's really stupid. 03:00:33 Nah, it's Intel's clocks. 03:00:45 elliott: Beats me. 03:00:48 pikhq_: Intel's clocks aren't getting faster anymore. :-( 03:00:49 monqy: we know our clocks better, rght? 03:00:51 It makes a lot more sense for tock to be the die shrink. 03:01:03 shachaf: Instructions-per-clock keeps going up at least. 03:01:26 elliott: You should get a 32-core machine like kmc. 03:01:32 48 03:01:35 but it's not mine 03:01:37 OK, if kmc donates the funds. 03:01:41 elliott: You should get a 48-core machine like kmc. 03:01:43 And compile colonels on it. 03:01:50 i built it for ksplice and it's probably sitting unused in some oracle warehouse now 03:02:09 Haswell will apparently have 10% higher instructions-per-cycle than Ivy Bridge. 03:02:19 kmc: c'mon, where's my money 03:02:31 do you think we are joking, or making with the funny stuff 03:14:35 Meanwhile, a hay competition: http://ubuntuone.com/0FaPo5mnm0KHJ1M4W1P6US 03:30:09 I'm the Emperor, and I want dumplings! 03:30:53 ion: Help, is my type broken? 03:32:11 shachaf: No, you should simply use a dynamically typed language. 03:54:22 ion: I mean my Tree type. 03:54:27 It made sense before but now I don't get it. 03:54:33 Are the Humble Bundle ebooks worth reading? 03:54:36 20:15 That would be something like data Tree k a = One k a | Two (Tree k (k,a,a))? 03:54:43 I've read Cory Doctorow's Down and Out in the Magic Kingdom 03:56:31 shachaf: Your Tree type is known, IIRC. 03:56:38 there's a humble ebook bundle now? shit 03:56:41 cool 03:56:48 I think it has properties. 03:57:56 elliott: Is it even valid? 03:58:09 I wrote it but now I don't know how it works. 03:59:49 these all sound pretty good 04:00:00 except for doctorow's book, which sounds terrible 04:00:04 but i never really liked anything he wrote 04:01:03 I wouldn't buy anything with a Doctorow book in it just on principle. 04:01:31 Wait, what's wrong with Doctorow? 04:01:49 elliott would arrange the bundle such that you get a Doctorow book unless you pay more than the average. 04:03:00 hahaha shachaf 04:03:06 Sgeo: I don't know, I've been ignoring him for the forseeable past on account of him being annoying. 04:03:25 down and out was boring 04:03:33 But I seem to remember he has a penchant for oversimplification. 04:03:34 i just don't give a shit about disneyland 04:04:01 and all the futuristic post-singularity stuff was pretty standard sci-fi fare by the time i read it 04:04:24 And some of his other stuff just beats you over the head with politics. 04:04:30 It's obnoxious *even if you agree with him*. 04:04:36 eastern standard tribe was ok but i don't recall really enjoying it at any point 04:04:42 kmc: Have you read The Metamorphosis of Prime Intellect? 04:04:45 It's... certainly a book. 04:04:47 elliott: yes! 04:05:03 i really enjoyed that book when i was like 14 and found it through everything2 or kuro5hin or something 04:05:13 Likewise. 04:05:26 good times 04:05:28 Might've been 15, but eh. 04:05:31 Back when all the "cool websites" had digits in their names. 04:05:43 as opposed to missing vowels 04:05:59 kmc: By the way, how does it feel being over 9000 days old? 04:06:06 I hear there's a sequel coming out roughly never. 04:06:17 This reminds me I should finish catching up with Ra. 04:06:21 kmc: You've read Fine Structure, right? 04:07:29 -!- zzo38 has joined. 04:07:32 elliott, have you even finished Fine Structure yet? 04:07:37 elliott: no 04:07:53 shachaf: wow 04:08:00 Sgeo: Yes! I'm now going to invoke this fact: 04:08:07 kmc: What! Even *I've* read Fine Structure. 04:08:23 even monqy has read Fine Structure assuming he actually got round to it which is unlikely 04:08:23 kmc: Sam Hughes is awesome. 04:08:28 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk). 04:08:49 kmc, I am thirding the Fine Structure suggestion. 04:08:58 I have added some examples of FurryScript, some people asked for some examples 04:09:12 Hey, who said it was a suggestion??? 04:09:18 Maybe I hate Fine Structure and want to warn kmc off. 04:09:34 elliott: You *read* it. Surely you don't hate it. :P 04:09:53 pikhq_: you like everything you've read?? 04:10:10 elliott: pikhq_'s point is that you can't read Fine Structure and not like it. 04:10:16 elliott: No, but I suggest you can't read Fine Structure and hate it. 04:10:43 You might read it and neither like or hate it. 04:10:55 shachaf: I've got a TIP for you, get the POINT? 04:13:13 This is FurryScript truth-machine program: 1[ <1> 1# ] PAR DUP ~# 04:13:31 Static analysis of stack effects would be required to prove that it would work. 04:13:51 However, it does not actually work, for similar reasons as some of the other examples of truth-machine that doesn't work for the same reason. 04:14:11 for similar reasons as some of the other examples of truth-machine that doesn't work for the same reason. 04:14:15 Good point. 04:16:35 The implementation will work if you put 0 however, it will make 0 output and stop. 04:17:45 (If you are running the program on your own computer, the second command-line parameter is the input; if running on the form for custom scripts, use the PAS command to fill in the input.) 04:17:45 reading Fine Structure 04:35:01 what's a truth machine 04:36:32 http://esolangs.org/wiki/Truth-machine 04:36:48 Do you know what a cake machine is? 04:37:00 I'm just going to paste my pun in. 04:37:01 11:34 I found this to be a very nice informal intro: "Some of the best things in life are free; and some are not. Truth is free. Having proved a theorem, you may use this proof as many times as you wish, at no extra cost. Food, on the other hand, has a cost. Having baked a cake, you may eat it only once. If traditional logic is about truth, then linear logic is about food" 04:37:07 11:35 Unless you're Zeno. 04:37:10 11:35 Zeno knew how to halve his cake and eat it too. 04:39:14 heh 04:51:49 oh i thought this was going to be about the cake being a lie 04:54:26 05:26 < kmc> where's nortti // I was sleepinh 04:54:56 hi nortti 04:55:01 Welcome back to awakeness. 04:55:09 kmc: Did you notice your 9000th birthday? 04:56:02 kmc: I wonder whether _Typing Haskell in Haskell_ is a good example of literate programming. 04:59:54 -!- sivoais has quit (Ping timeout: 240 seconds). 05:04:05 -!- sivoais has joined. 05:14:33 -!- mig22 has joined. 05:25:21 i did not notice it 05:25:26 but you did 05:25:31 which is weird but cool 05:25:43 anyway i have to sleep now, ttyl 05:41:17 me too 05:41:42 -!- copumpkin has quit (Ping timeout: 276 seconds). 05:42:17 -!- copumpkin has joined. 06:29:55 elliott, monqy UPD8 06:30:33 monqy never gets better 06:30:38 What does linear logic mean? 06:30:44 linear logic 06:31:07 O, I found in Wikipedia, OK 06:36:08 Is it possible to make up a type system similar to Haskell but also has kinds for linear logic instead of only intuitionistic? 06:36:50 (There are some cases I have thought of where I have wanted something like this) 06:50:24 -!- nooga has joined. 06:54:36 -!- ais523 has quit. 07:00:41 -!- nooga has quit (Ping timeout: 246 seconds). 07:17:25 Is the list of stuff put near the top of the page is OK? Do you like this? http://esolangs.org/wiki/User:Zzo38/FurryScript 07:25:13 There Once Was A Fish Named Fred 07:25:19 best esoland or bestestest esolang? 07:25:30 unit besting 07:26:23 -!- epicmonkey has quit (Remote host closed the connection). 07:26:37 “(However, note that it is being discussed this notice might be wrong.)” That should be followed by “(However, note that it is being discussed also this notice might be wrong.)” 07:30:36 shachaf: I don't know! 07:33:37 -!- zzo38 has quit (Remote host closed the connection). 07:34:23 zzo38: "(there must be a space after [ and before and after ] however)" 07:34:31 Can you drop the requirement for a space after ]? 08:21:40 -!- epicmonkey has joined. 08:22:20 -!- hagb4rd has joined. 08:32:44 -!- epicmonkey has quit (Read error: Connection reset by peer). 08:35:12 -!- epicmonkey has joined. 08:36:05 -!- Phantom_Hoover has joined. 08:37:40 -!- atriq has joined. 08:40:59 -!- zzo38 has joined. 08:48:41 zzo38, you've mentioned going to conventions in the past, correct? 08:49:58 Yes 08:50:19 What kind of conventions? 08:50:30 The unconventional kind, no doubt. 08:50:31 shachaf: You have 1 new message. '/msg lambdabot @messages' to read it. 08:53:48 -!- epicmonkey has quit (Remote host closed the connection). 08:53:59 -!- epicmonkey has joined. 08:55:02 I went to anime convention 08:55:23 Just out of curiosity, were there many Homestucks? 08:55:38 I don't think so. 08:58:02 How long ago was this? 08:58:12 A few months ago. 08:58:18 Unusual 09:00:23 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 09:04:36 No crowd of people being weird wearing grey make-up and orange horns? 09:05:03 I think there were two. 09:05:10 Not a lot. 09:05:14 Yes 09:05:20 Hmm 09:05:27 Okay 09:05:57 I guess there are either a lot of Homestucks around here or they're really organized 09:07:17 Hmm 09:07:32 I wonder if the "her" mentioned on Koen's user page refers to someone specific 09:09:05 The list is kind of coffee-oriented. 09:09:32 -!- monqy has quit (Quit: hello). 09:10:22 Hmm hmm 09:10:40 I've got an ssh server on my other computer, and I want to access some HTML pages on there from here 09:11:04 It does still have "find her" which doesn't sound all that specific; then again, it just might be someone specific but in hiding. 09:11:09 Is there a way I can set it up so I can point my browser at file////whatever/othercomputer/whatever/file.html 09:11:11 And have it work 09:12:19 You can do 'sshfs othercomputer:/place /anotherplace" on thefirstcomputer, and then you can just use file:///anotherplace/thing to access the /place/thing of othercomputer. 09:12:34 At least with luck, and with sshfs+fuse installed. 09:13:04 Also it's probably best not to mix ' and " like I did there. 09:14:37 Thanks 09:16:06 This is a VERY roundabout way to mess with haskell 09:21:40 Okay, that's a VERY good reason for that to not work 09:43:49 "Warning: If you don't follow the instructions correctly, the result may be an unbootable Linux. Even if you do follow the instructions correctly, the result may be an unbootable Linux." 09:46:22 An unbootable Linux is always an option. 09:51:58 -!- zzo38 has quit (Remote host closed the connection). 10:04:14 -!- Slereah_ has changed nick to Slereah. 10:06:53 fizzie: More like an inscrutable Linux, right? 10:10:32 atriq: ...the usual way to access HTML pages is via a HTTP server 10:16:29 -!- Phantom_Hoover has joined. 10:22:27 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 10:23:19 Lumpio-, advise on setting one up? 10:43:20 pacman -S nginx 10:46:30 That... appears to be a pacman game 10:47:07 Did I do something wrong? 10:48:37 You probably used the "wrong" Linux distribution. 10:48:49 (All of them are wrong.) 10:49:06 Is Solaris the wrong Linux distribution? 10:49:08 I think Arch system maintanence would be a lot less stressful if pacman(1) was just a pacman game. 10:49:27 I think I can definitively state that Solaris is, in fact, the most wrong a Linux distribution can possibly be. 10:49:33 I concur. 10:49:44 Okay, because I'm not using that 10:49:48 How about Windows 98 SE? 10:50:00 Windows 98 SE is quite a good Linux distribution IMO. 10:50:10 I mean, it's better than Solaris. 10:50:17 All the cool dudes use Windows 98 SE Linux. 10:50:55 My favourite Linux distribution is BeOS. 10:51:03 When GHC gets ported to Haiku I'll probably use Haiku 10:51:32 (actually serious) 10:54:06 -!- mig22 has quit (Quit: mig22). 11:04:11 Actually, wait 11:04:19 I'd need nVidia drivers 11:04:52 -!- mig22 has joined. 11:12:27 -!- ais523 has joined. 11:32:03 ais523: hi 11:32:28 hi elliott 11:32:30 -!- Phantom_Hoover has joined. 11:32:38 I'm busy adding /ˈæmbiːɛf/ to the wiki 11:33:27 ais523: come up with an ascii redirect or i'll kill you :P 11:33:31 -!- elliott1 has joined. 11:33:33 im a test 11:33:40 oklofok, help 11:33:41 there's a link in the language list 11:33:44 i need guidance 11:33:59 ais523: but I like typing http://esolangs.org/wiki/$x 11:34:17 OK, I'll add a redirect from [[$x]] 11:34:19 and not explain it 11:34:30 :( 11:34:50 object-oriented thue is terrible right 11:35:14 it sounds terrible but my brain is too mathsed to bother wading through that spec 11:37:24 ais523: you know about protocols right 11:37:39 ais523 knows all the protocols 11:37:46 he has to otherwise he might accidentally break a law 11:47:38 elliott: OK, added 11:47:45 http://esolangs.org/wiki/$x 11:48:01 ais523: that redirect goes to an interesting place 11:48:07 -!- mig22 has quit (Quit: mig22). 11:48:16 oh hmm 11:48:19 maybe it is xchat haha 11:49:27 xchat doesn't like the link? 11:49:43 ais523: you have a bad category 11:49:45 try http://esolangs.org/wiki//%CB%88%C3%A6mbi%CB%90%C9%9Bf/ instead 11:49:47 which one? 11:49:48 tape-based? 11:49:50 ye 11:49:52 you can fix it, it's a wiki 11:49:57 didn't know if BF derivatives got that one 11:49:58 i'm lazy tho 11:50:03 OK, I'll fix it 11:50:10 ais523: by bad i mean 11:50:11 it's a redlink 11:50:21 and yr article is the only entry 11:50:25 oh right 11:50:31 meh, it shouldn't be included anyway 11:51:02 anyway, going home, I need sleep 11:51:24 ais523: here i was just about to ask you programming questions too!! 11:51:25 you win this time 11:51:27 -!- ais523 has quit (Quit: Page closed). 11:51:45 fizzie: Guess whose lucky day it is?? 11:52:17 I think it's most definitely not mine. 11:53:25 fizzie: Correct! 11:54:31 fizzie: Is there some kind of generic thing that encapsulates a protocol and gives it encryption (and ideally authentication?) so my server/client don't have to worry about it per se? My current best idea is just opening "ssh server connect-to-local-server-socket-and-hook-stdio-to-it" as a process and using that as the "socket", which seems a bit... suboptimal. 11:56:53 Well, uh. Certainly there are rather generic encrypted-and-optionally-authenticated transport channels. TLS, for example. But maybe that's not what you mean. 11:57:41 fizzie: Right, I thought TLS might be what I'm thinking of. I... guess I'll go look into that. 11:58:04 (I don't suppose TLS supports SSH public-key authentication. :p) 11:58:46 Mostly TLS seems to have lots of complex fiddly thingies I'm not sure I care about, like certificate-signing and so on. 11:59:22 At least not normally, no; the authentication aspects are traditionally all X.509. 11:59:54 Right. That sounds like it could potentially be a pain to set up on clients and stuff "just" for this thing I'm working on. 12:01:13 So maybe I'll just go with the ssh thing after all. 12:01:58 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 12:02:28 Still. 12:02:32 Aren't these things meant to be nice? 12:02:37 I think TLS supports pre-shared key ciphersuites, if that's an option. Of course it's not quite SSH public keys. 12:03:21 (But it's not dabbling with certificates either.) 12:03:58 fizzie: I don't even know what a ciphersuite is. 12:04:01 I'm bad at this stuff. 12:04:27 IS IT: a suit you wear in bad cyberpunk novels that encrypts your travels through CYBERSPACE with a cipher? 12:05:18 Just a term they use. "The fiddly details," sort of. A name for the particular pile of encryption and authentication and whatnot algorithms that are used. 12:06:26 Right. I mean, I don't even know if the typical Linux system has the programs you need to set such a thing up, though. 12:06:42 It sounds fiddlier than making an ssh key, which takes 0 seconds because everyone* has one. 12:06:46 *Everyone that matters. 12:08:27 I didn't know whether TLS libraries support the TLS-PSK things if it's an extension; based on a quick google, though, at least GnuTLS does, and has helper functions to generate and hex-encode/decode keys. But, really, for pre-shared keys, it's just K random bits. 12:08:51 Right. 12:08:53 OpenSSL API isn't IIRC the most pleasant to work with. GnuTLS probably isn't any nicer, though. 12:09:13 Hmm, I guess I could do some sort of ssh tunneling deal rather than "ssh server connect-to-local-server-socket-and-hook-stdio-to-it". 12:09:18 That seems... less awful, maybe. 12:09:27 fizzie: Well, I don't anticipate talking to it directly from C. 12:09:44 That's always nice. 12:10:43 Anyway this is all sounding awfully complicated. :( 12:11:21 There are netcat-like tools that provide encrypted pipes, but it's arguable whether that's really any better than your SSH method. 12:11:28 Possibly the optimal solution may depend on what's comfortably available for your implementation language. 12:12:01 * elliott doesn't even know that, except that it's almost certainly one of Haskell, Python or C, and probably not C. 12:12:06 My planning: woefully under. 12:12:29 -!- Arc_Koen has joined. 12:12:49 hello 12:14:53 Hey 12:15:12 Arc_Koen, is the "her" mentioned on your user page someone specific, or just a general goal? 12:15:28 just a general goal 12:15:37 though there are specific candidates 12:15:41 elliott: SSL does have the advantage that I'd expect most decent things have a way to speak it. (And everyone has the openssl command line tools installed, so fiddling with the certificates isn't too many orders of magnitude more complicated than fiddling with SSH public keys, except the commands are a lot uglier.) 12:16:37 fizzie: Right. 12:16:58 fizzie: I don't suppose it gets any easier if I settle for password-based authentication? 12:18:15 Well. A TLS encrypted-only channel with just a password query would be easy, but also somewhat MITM-risky, since there's no way to detect someone just forwarding all traffic in the middle. 12:19:22 SSH at least has the host key checks. Assuming the user just doesn't type "yes" to all questions. 12:19:47 fizzie: Right. Well, in this case it's more the server trying to keep riff-raff out than much about the client trusting the server. 12:21:34 Apparently there's also a "TLS-SRP" password-based-key-exchange authentication extension, implemented in the usual libraries. 12:21:38 -!- nooga has joined. 12:22:19 atriq: I'm surprised you read that already 12:22:25 I read EVERYTHING 12:22:34 Even minds. 12:22:35 So you can nowadays do TLS with certificates, with pre-shared keys, or with passwords. Fancy. 12:22:36 (disclaimer: I don't actually read everything) 12:24:07 -!- Phantom_Hoover has joined. 12:25:07 Help 12:25:23 atriq: hi 12:26:37 I think I'm being flirted at 12:27:30 atriq: Shoot a cloud of ink to hide behind, and then slink away. 12:30:58 how do I put a link to http://esolangs.org/wiki//ˈæmbiːɛf/ on the wiki? 12:31:18 the starting / seems to be confusing the wiki 12:31:24 [[:/ˈæmbiːɛf/]] 12:31:30 well, [[:/ˈæmbiːɛf/|]] 12:32:17 oh tahnk you 12:32:44 (and then common sense tell me I could've seen how ais did on the languages list) 12:42:09 so i : just a symbol to say "don't treat this link like you usually do" or does it mean something like . and .. in a unix shell? 12:47:33 format is [[namespace:foo]] 12:47:40 like [[Template:Blah]] 12:47:42 or [[Esolang:Policy]] 12:47:47 the "main" namespace's name is an empty string 12:48:00 if you do [[:foo]] then it's the page named foo... otherwise [[/foo]] is interpreted as a subpage of the current page 12:48:03 i.e. [[:thispage/foo]] 12:49:15 So it kind of is like Unix's "." 12:50:12 it's more like unix's / 12:50:16 yeah 12:50:21 [[foo]] is like ./foo 12:50:24 [[:foo]] is like /foo 12:50:46 and [[foo:bar]] is like C:\bar because now the metaphor is windows 12:50:56 haha 12:51:22 and how to make a distinction between a subpage and a page that has a / in it? 12:51:35 Do you need to? 12:52:55 I don't know 13:09:32 -!- nooga has quit (Ping timeout: 265 seconds). 13:14:59 -!- mig22 has joined. 13:16:08 -!- boily has joined. 13:21:03 Arc_Koen, there is no distinction. 13:21:19 a/b is a subpage of a if a exists, otherwise it's just a page with a / in the name. 13:21:31 oh, ok 13:21:40 -!- jiella has joined. 13:22:34 -!- nooga has joined. 13:24:45 wikipedia has at least two maps of the island that thomas the tank engine is set on 13:30:20 Sodor? 13:33:48 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 13:35:33 -!- aloril_ has quit (Ping timeout: 276 seconds). 13:36:07 Are there any spoken programming languages? 13:36:22 Sure 13:36:25 Go get a nerd 13:36:26 fizzie: Can your department hack up a spoken programming language please? :-) 13:36:31 Tell him "Make a program that does this" 13:36:49 I was thinking more like lojban->Haskell 13:36:52 * shapr thinks about that 13:37:06 Spoken or written is just the medium 13:37:15 I guess if there's an easy way to turn spoken lojban into text, that would be enough. 13:37:18 You could just say out loud written Haskell 13:37:28 And get a speech to text converter 13:37:39 Lojban isn't really any more programmy than any other language 13:37:53 -!- Phantom_Hoover has joined. 13:37:56 Also there's Plain English, but that is the worst language 13:39:20 -!- nooga has quit (Ping timeout: 255 seconds). 13:39:48 There are plenty of (buggy) english-to-*-compilers out there, though 13:40:32 shapr: I don't think we have investigated recognition of spoken (existing) programming languages, let alone tried to make an easily-recognizable new language. 13:41:51 Don't you remember Plain English, fizzie! 13:41:56 From osmonian or something 13:42:17 I mean "we" as in our department. 13:42:31 It's not like I could forget Plain English, no. 13:42:32 What department 13:42:57 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 13:43:43 The department that the speech recognition/synthesis research group that I'm in is part of. 13:43:55 http://www.osmosian.com/ 13:44:01 I HATE THEM SO MUCH 13:44:34 The Osmosian Order! Man, they're wacky. 13:44:55 shapr: I'm not sure if anyone mentioned fungot's implementation language to you yet, so let me just do a shameless plug here. 13:44:56 fizzie: but that makes things worse than ever! everybody is going straight to the top, since who cares! the utahraptor's been having a bad time to say all the run-of-the-mill thoughts we have! 13:44:59 ^source 13:44:59 http://git.zem.fi/fungot/blob/HEAD:/fungot.b98 13:45:13 Yes, it made things worse than ever. 13:45:58 -!- nooga has joined. 13:47:35 -!- aloril_ has joined. 13:48:09 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:51:19 -!- boily has quit (Quit: Poulet!). 13:52:47 fizzie: That's terrifying. 13:56:54 -!- atriq has quit (Quit: Leaving). 13:59:25 Stratos jump successful http://youtu.be/yFU774q6eVM 14:08:01 -!- Phantom_Hoover has joined. 14:12:41 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 14:12:47 -!- nooga has quit (Ping timeout: 252 seconds). 14:16:36 -!- atriq has joined. 14:19:18 -!- augur has quit (Remote host closed the connection). 14:36:20 -!- mig22 has left. 14:40:12 -!- copumpkin has joined. 14:49:46 -!- augur has joined. 14:55:31 -!- Lumpio- has quit (Ping timeout: 260 seconds). 15:03:33 -!- FreeFull has joined. 15:07:59 -!- AnotherTest has joined. 15:08:01 -!- AnotherTest has left. 15:08:06 -!- AnotherTest has joined. 15:08:10 Hello 15:09:49 Hi 15:12:13 -!- Phantom_Hoover has joined. 15:14:21 -!- Frooxius has joined. 15:21:27 -!- Lumpio- has joined. 15:49:55 -!- AnotherTest has quit (Quit: Leaving.). 15:50:17 -!- AnotherTest has joined. 15:58:54 -!- nooga has joined. 16:06:40 -!- ogrom has joined. 17:03:37 -!- atriq has quit (Quit: Leaving). 17:13:45 -!- Vorpal has joined. 17:15:33 -!- elliott1 has quit (Ping timeout: 248 seconds). 17:15:50 -!- elliott has quit (Ping timeout: 244 seconds). 17:17:13 -!- AnotherTest has quit (Quit: Leaving.). 17:17:27 -!- AnotherTest has joined. 17:22:15 -!- impomatic has joined. 17:23:48 -!- atriq has joined. 17:33:12 You know, at the beginning of the American Civil War, the confederates thought that they could count on the support of the British, because Britain imported a lot of cotton from them. 17:33:45 However, when they asked for military aid, Britain thought "why bother" and got cotton from Egypt instead, which turned out to be cheaper. 17:33:55 The moral of the story is, don't rely on the British? 17:34:46 haha 17:37:42 never underestimate the ability of the british to screw you over? 17:38:00 the chinese can attest to that one too 17:38:55 afaict the opium wars were basically a bond villain plan 17:40:07 -!- augur has quit (Remote host closed the connection). 17:43:52 "Well, Mister Bond, you have discovered my plan to sell opium to China so we can afford tea and they'll be too high to care!" 17:43:55 "Hahahaha" 17:44:08 (I don't know that much about the Opium wars) 17:44:26 -!- augur has joined. 17:44:33 i think at some point the chinese tried to foil this fiendish plan by banning opium 17:44:37 this is where the wars come in 17:45:50 -!- AnotherTest has quit (Quit: Leaving.). 17:47:01 -!- AnotherTest has joined. 17:52:07 Arc_Koen, did you ever try Homestuck again? 17:52:17 "ever" 17:52:25 Since, well, yesterday evening 17:52:31 last time was about 14 hours ago 17:52:31 Did you get that hot chocolate? 17:52:35 yes 17:52:36 yes I did 17:53:00 well, the chocolate I got about two hours ago, actually 17:53:06 talk about delaying 17:53:51 I'm currently implementing deadfish in thue 17:53:51 -!- augur has quit (Read error: Connection reset by peer). 17:54:00 (and also wondering why I'm doing that) 17:54:14 -!- augur has joined. 18:06:18 -!- zzo38 has joined. 18:07:38 -!- epicmonkey has quit (Ping timeout: 245 seconds). 18:07:46 http://esolangs.org/wiki/The_Best_Place_To_Grab_Cash_Financing_Very_Quickly ? 18:08:06 I need to make an esolang REALLY QUICKLY 18:09:09 I have a good idea atriq 18:09:19 How developed 18:09:58 is your idea? 18:10:38 -!- AnotherTest1 has joined. 18:10:39 (note: this idea might not work out, and if it does, it will be virtually impossibe to write a program in this language) 18:10:46 and sorry for disconnecting 18:10:59 -!- AnotherTest has quit (Disconnected by services). 18:11:12 -!- AnotherTest1 has changed nick to AnotherTest. 18:12:29 (look at Fueue and Eodermdrone and Malbolge) 18:12:54 atriq: are you interested in languages with randomness? 18:13:08 I'm more interested in functional languages 18:13:16 oh 18:13:18 okay 18:13:25 then my idea is probably not for you 18:13:33 Nah, I want to hear it 18:14:06 okay so, this is only a vague idea (keep that in mind): 18:15:14 A is parsed into a tree. So the root node would be the first instruction, and then a random number is generated in the range (for example) [1, 5] 18:15:28 this number determines the number of child nodes the root has 18:16:13 Okay 18:16:14 next, each of the child nodes will (if enough instructions are available) also get a random amount of child nodes in the range [1, 5] 18:16:30 this continues until there are no more instructions 18:16:48 then the execution starts as following: 18:17:02 The root instruction is executed 18:17:13 Then a random child of this root node is executed 18:17:25 this process continues until a node without children is reached 18:17:35 That's it basically 18:18:34 I'm not entirely sure whether it would be possible to write an actual program (that does something that makes sense) in this language 18:19:52 Hmm 18:19:53 -!- ogrom has quit (Read error: Connection reset by peer). 18:21:12 It would be an accomplishment to write a hello world program in such a language 18:25:06 The Code Poems book appears to have been published... http://wired.co.uk/news/archive/2012-10/12/code-poems-book - not sure about the availability 18:26:20 atriq: so, what do you think? 18:26:36 Could be interesting 18:28:09 Well, if we want to to make this, we will need to determine the details 18:28:23 -!- Por_gammer has joined. 18:28:39 for example, what would be the basic instructions? 18:29:06 `welcome Por_gammer 18:29:08 I was also thinking to have the memory as a tree (with randomness when going down, but not when going up) 18:29:16 Por_gammer: 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.) 18:29:28 "Scala macros are, in fact, cats." 18:30:46 atriq: what if we took the brainfuck instructions, and organized them in this new manner? 18:30:50 uhmm... hi? 18:30:54 Hey 18:30:57 -!- sipa has left. 18:31:04 AnotherTest, I think it may work well with function-y ness 18:31:23 atriq: also good 18:31:42 Define each function to be n-adic where n is any number from 1 to 5 18:31:49 Then you can use the whole tree 18:32:01 n-adic? 18:32:16 Taking n inputs 18:32:21 ah 18:33:34 atriq: so you want to make a fully functional language, where the flow of instructions is in this manner? 18:33:49 It could work 18:33:57 Yes, perhaps 18:34:25 If each subtree is a function from a tree to a tree 18:34:36 -!- Gregor has set topic: BE WARNED: The people here are the completest asses. | http://phantom-hoover.tumblr.com/ | http://codu.org/logs/_esoteric/. 18:34:56 we are donkeys? 18:35:04 So the only data type is a tree of ...? 18:35:09 nortti: The completest. 18:35:09 Functions 18:35:12 and afunction 18:35:27 What is an incomplete donkey? 18:35:29 oh a function is a tree 18:35:34 I get it 18:36:00 FireFly: The truest of tragedies :'( 18:39:34 so, atriq, suppose you said fun a (with possibly function b as argument) = (+ 1) b; It would do either b or (+1) (so it would either be 1 or b + 1) 18:39:55 I think so! 18:40:02 I haven't really thought of this much 18:40:29 So you can specify an amount of arguments, but it's not certain that they will get passed 18:41:38 f(x, y, z) = x + y + z might do x, y, z, x + y, y + z or x + z 18:41:52 assuming that the parameters that are not passed are 0 18:42:25 or are the neutral element for the operation that is being done (thus when multiplying they equal 1) 18:42:41 It might also do nothing 18:42:43 Or when composing they equal the identity function 18:43:37 Yes f(x, y, z) = (x · y · z)(1) might thus be 1 18:43:57 (assuming · is actually an open dot, which it is not unfortunately) 18:47:08 -!- epicmonkey has joined. 18:48:19 -!- boily has joined. 18:49:52 -!- atriq has quit (Ping timeout: 244 seconds). 18:51:18 -!- epicmonkey has quit (Remote host closed the connection). 18:51:51 half-hi all! 18:52:39 h all? 18:52:42 i all? 18:53:15 maybe something like *bwarg*. half-my mouth is frozen from the dentist. 18:54:01 So your dentist injects dry ice instead of novocaine too! 18:54:04 I thought that was just mine! *whew* 18:54:28 injecting dry ice 18:54:30 new one on me 18:54:31 dry ice? 18:54:42 I'd be very surprised if it was dry ice. 18:54:49 particularly given it's a solid 18:54:51 but they went and used multiple products. 18:56:26 Gregor probably just doesn't understand because nobody trusts his country with the good anaesthetics 18:56:54 HA HA YOU GUYS ARE BAD AT JOKES 18:57:09 The joke was that “frozen” is a bizarre word choice. 18:57:36 *we're* bad at jokes? 18:57:39 pardon my French :p 18:57:48 how many members of monty python were american again?? 18:58:03 terry gilliam? 18:58:06 Aaaaand Phantom_Hoover thinks that Monty Python was about jokes. 18:58:06 Yikes. 18:58:18 no, mostly i did that for the terry gilliam thing 18:58:26 a "half-my" mouth is an interesting concept ... I guess the other half belongs to the novocaine 18:59:02 shows how affected I am by the intervention... 19:00:05 -!- AnotherTest has quit (Quit: Leaving.). 19:01:56 -!- augur has quit (Remote host closed the connection). 19:02:20 -!- atriq has joined. 19:07:03 http://fi3.eu.apcdn.com/full/63422.jpg 19:08:08 as if stallman would have children 19:09:07 Hello Android! HAW HAW HAW 19:10:57 -!- augur has joined. 19:11:18 -!- Taneb has joined. 19:17:51 -!- zzo38 has quit (Remote host closed the connection). 19:20:39 Oh dear god I've cloned myself 19:22:24 atriq: here is an idea of a name for an esolang 19:22:28 hope it inspires you 19:22:43 "Talk talk: Turing tarpit" 19:22:54 -!- Taneb has quit (Disconnected by services). 19:23:22 -!- Taneb has joined. 19:24:05 -!- Taneb has quit (Disconnected by services). 19:24:31 -!- Taneb has joined. 19:26:49 http://esolangs.org/wiki/Talk_talk:Turing_tarpit 19:27:20 I was planning to make this a language one day or the other but I don't really have a proper idea yet 19:27:43 I was thinking maybe something self-modifying in the same vein as emmental (except a turing tarpit) 19:28:19 so if you have a proper idea any time soon, go ahead :) 19:28:59 beware the turing armpit, where [expunged] 19:29:16 thing is I really need to make a language heavily inspired by nomics but I don't have a consistent idea yet 19:31:04 beware the turing armpit, where everything is possible but nothing is smooth? 19:41:07 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 19:41:33 kmc, remember when I was talking Common Lisp and was trying to work out how to get the lexical environment to show off that whatever we were talking about could be done in Common Lisp, and I gave up? 19:42:00 Pretty sure it could be done in Common Lisp, because I did it in Clojure and I think Common Lisp is sufficiently similar in regards to the basic concept 19:42:03 https://www.refheap.com/users/sgeo 19:42:05 oops 19:42:11 https://www.refheap.com/paste/5886 19:49:12 !rot13 renslo 19:49:14 erafyb 19:50:04 not funny :( 19:50:12 !rot13 turing 19:50:13 ghevat 19:50:30 !rot13 guro 19:50:30 theb 19:50:43 !rot13 gura 19:50:43 then 19:51:36 !rot13 cymru cymry 19:51:37 plzeh plzel 19:51:52 !rot13 clojure 19:51:53 pybwher 19:51:55 !rot13 welsh 19:51:55 jryfu 19:52:47 ok, rot13 is boring again 19:53:17 !rot13 na na. na na na na. 19:53:17 an an. an an an an. 19:55:12 !rot13 mana mana 19:55:13 znan znan 19:55:20 !rot13 ééééééé 19:55:21 ​ééééééé 19:55:24 meh. 19:55:48 would have been nice if it had outputed somthing like ŕŕŕŕŕ 19:56:22 -!- Phantom_Hoover has joined. 19:56:51 !rot13 hey hey hey goodbye 19:56:52 url url url tbbqolr 19:57:00 o.O 19:57:11 !rot13 na na. na na na na. hey hey hey. 19:57:12 an an. an an an an. url url url. 19:58:01 -!- augur has quit (Remote host closed the connection). 19:59:58 An url!? 20:00:17 !rot13 earl 20:00:17 rney 20:00:25 !rot13 Renae 20:00:26 Eranr 20:00:57 !rot13 Renee 20:00:58 Erarr 20:00:58 ^rot13 can you do UPPERCASE? 20:00:59 pna lbh qb HCCREPNFR? 20:01:06 !rot13 error 20:01:06 reebe 20:01:20 I could play this game all day 20:01:27 !rot13 rebate 20:01:27 erongr 20:01:33 ... 20:01:48 !rot13 ignore 20:01:48 !rot13 Sgeo 20:01:48 vtaber 20:01:48 Ftrb 20:01:54 !rot13 my nick 20:01:54 zl avpx 20:02:04 !rot13 vtable 20:02:05 ignoyr 20:02:21 !rot13 verticle tabber 20:02:21 iregvpyr gnoore 20:02:32 !rot13 vertical tabber 20:02:33 iregvpny gnoore 20:02:37 I learned how to spell! 20:04:18 !rot13 shatbg 20:04:19 fungot 20:05:26 -!- nooga has quit (Ping timeout: 255 seconds). 20:06:05 ^rot13 shat up 20:06:05 fung hc 20:06:32 fhng hc 20:09:43 atriq: so, any idea for Talk talk: Turing Tarpit? 20:10:14 "talk talk" sounds like the french onomatopoeia for knock knock 20:11:25 so I was thinking something about a nomic-inspired turning tarpit with something about doors 20:11:29 -!- FireFly has quit (Excess Flood). 20:11:56 -!- FireFly has joined. 20:13:06 Not really 20:13:12 Something like dupdog, maybe? 20:13:59 if I recall correctly dupdog was something about WARNING: Don't Spend Your Whole Night Trying To Understand Dupdog!!! 20:14:31 also tarpit looks like the french word for carpet 20:14:39 so maybe something with doors and carpets 20:15:35 actually that's consistent with the idea of a turning tarpit: you're in a circular, spinning room with lots of doors and a nice rug under your feet (and instructions are behind the doors) 20:16:25 oh wait no I'm mistaking it with something else 20:16:36 dupdog is that thing using the length of the source code, right? 20:16:57 but what happens if you shuffle too much in that room? wouldn't trying to read the instructions cause an electric discharge and fry them? 20:17:28 ouh, nice 20:17:51 like, sometimes door can open in the middle of two instructions? 20:18:23 * Arc_Koen adds that to his list of potentially-interesting-ideas 20:24:00 oh, or a non-deterministic language using the same idea as ais523's amBF, where instructions are in a circle, and everytime you use the symbol for an instruction, one of the three instructions (previous, that one, next) will be executed instead 20:24:53 (by "in the same idea as /'æmbeef/" I don't mean it needs to be a brainfuck-derivative) 20:33:32 -!- augur has joined. 21:04:20 -!- Vorpal has quit (Ping timeout: 248 seconds). 21:05:49 -!- atriq has quit (Remote host closed the connection). 21:12:02 -!- Taneb has quit (Ping timeout: 255 seconds). 21:38:57 -!- zzo38 has joined. 21:46:08 -!- boily has quit (Quit: Poulet!). 21:48:56 there should be an "invent your own cargo cult C performance rule" contest 21:49:03 a la http://chronicle.com/blogs/linguafranca/2012/10/03/a-new-contest-centered-around-usage/ 21:51:38 * Sgeo pokes kmc 21:52:11 yes? 21:53:13 https://www.refheap.com/paste/5886 getting the lexical environment, both variable symbols and values, in Clojure 21:53:22 And a similar concept should work in Common Lisp, I think 21:54:00 Do you like this? http://www.chessvariants.org/index/msdisplay.php?itemid=MSsecretbombsche 21:54:55 kmc, 21:55:38 -!- nys has joined. 21:55:39 And of course, it should be easy to write an eval that takes such a map and wraps its argument in a let 22:00:58 zzo38: why "Cannot escape pictorial checkmate."? 22:01:58 checkmate usually means "you're in check and cannot escape" - if you change the rules, then it seems only logical that it affects the possibilities of checkmate 22:02:27 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 22:02:30 unless those new rules have actually been tested and it has been decided it's actually better this way 22:04:08 (also, I've never seen the phrase "pictorial checkmate" before, but I assume it means "a position that would be a checkmate if we were playing regular fide chess") 22:04:23 Arc_Koen: Yes, that is what "pictorial checkmate" means, and I have seen it before. 22:08:06 zzo38: have you had a look at http://www.chessvariants.org/large.dir/contest84/orwellchess.html ? 22:09:52 I am looking now. 22:14:03 Not bad. 22:20:37 that's the chess variant I've been the most impressed with 22:20:55 and I'm looking (not actively, though) for an opportunity to play it 22:23:31 -!- copumpkin has joined. 22:24:25 Maybe make up some pieces and board you can do it 22:24:43 yes 22:25:19 I was thinking a circular board would be more appropriate than a cylindrical one 22:25:34 Then make up your own variant of variant 22:26:01 it's not really a variant - it's just another way to represent the 'torus' aspect of the board 22:26:43 OK 22:27:57 Is my description of FurryScript better now? I think you have asked for some improvement and now I have done. 22:28:19 if I were to make a program with graphics it would probably display the board both as a cylinder and a disc 22:28:23 It is not only the description; if you have additional questions, or you wanted some additional commands, you can ask that too. 22:28:29 let me have a look 22:28:44 Arc_Koen: OK, it could be done like that, could be one way I guess. 22:29:49 what's a "domain specific" programming language? 22:30:38 does that mean it's been designed for one purpose mainly (with "domain" meaning a field like physics or biology)? 22:30:55 http://en.wikipedia.org/wiki/Domain-specific_language 22:31:01 Arc_Koen: Yes, like PHP 22:31:07 -!- augur_ has joined. 22:31:22 PHP is PHP HyperText Preprocessor or something like that. 22:31:25 thanks 22:31:30 so what's furryscript's domain? 22:32:02 No idea 22:32:05 SNOBOL was for text processing 22:32:20 A good example of a domain specific language is regular expressions. 22:32:22 FurryScript is even more domain-specific than PHP; the original reason it was written was actually specifically to interpret this: http://zzo38computer.org/furry/scripts/furrygenerator_7thsanc.txt (it is also where the name comes from) 22:32:41 -!- augur has quit (Read error: Connection reset by peer). 22:33:26 Although the current version implements many commands which are not used in that file. 22:35:49 I have no idea what "generation" means 22:36:26 You also have to read the section about "templates" like it tell you to do 22:36:40 Probably I could explain it better, but am unsure how. 22:37:08 -!- shapr has left ("focus on code"). 22:37:26 -!- augur_ has quit (Remote host closed the connection). 22:37:55 But if you are still confused, you can ask more specific or see some of the external examples might explain a bit? 22:38:32 -!- Gregor has changed nick to RocketJSquirrel. 22:38:46 hmm yes I'm definitely still confused 22:39:20 the examples use PAR a lot and I have no idea what it does either 22:39:53 also what do the "( -- )" and "( ? -- ? )" means? 22:40:01 The purpose of PAR command is explained clearly in the text; it is used to read input. 22:40:14 Things like "( -- )" are stack effect notation (commonly used with Forth). 22:41:44 I added another paragraph of text to the "Generation" section. 22:42:15 If I want to implement esolangs in Clojure, I should find a good parsec-equivalent 22:43:02 hmm I understand a little better now 22:43:41 so it's mainly a functional language right? except with side effect on the stack 22:44:34 Arc_Koen: Somewhat, I guess 22:45:15 there's this whole continuation thing I'm not sure I understand 22:45:54 does it mean when a subroutine is called, it is provided with a copy of the stack (and of the program state)? 22:46:49 No; they all use the same stack. It is only provided with a copy of the stack and of the rest of the program state if you use the command to call with the current continuation. Also, continuations cannot be called backward. 22:47:10 You may see these files for more examples: http://zzo38computer.org/furry/scripts/ (I have added a link directly to this directory now) 22:47:14 oklofok?? 22:47:20 dammit man i need guidance 22:50:39 Do you understand the external examples? If anything in external example not understand, you can ask specific clarification I may add the comments if needed. 22:52:47 well the beer program looks very much like any usual stack based language 22:53:05 though I'm not sure when things are outputted 22:54:11 Things output when the program ends, any strings remaining on the stack are process any instructions they contain, and then send to output. 22:54:31 king_game and lifepath don't really look like programs at all - do they simply take some input to fill in some form? 22:55:05 " , eyes, and .> 22:55:13 ok, but that means the 99 is put on the stack first, then 98, etc., so 99 will be outputted last instead of first? 22:56:02 " , eyes, and .>" is a string which contains four instructions, "colordata", "skindata", etc, these subroutines are called and anything added to the stack since that point, one is selected at random and the instruction is replaced with that result. 22:56:15 ohhhhh 22:56:17 Arc_Koen: No, because the + at the beginning of any instruction tells it to use concatenation. 22:56:37 oh, of course 22:56:38 You can try the programs if you want; either install it on your own computer or use the HTML form. 22:57:35 so king_game basically generates a sentence with random values for skindata and stuff? 22:57:44 Yes. 22:59:50 -!- impomatic has left. 23:01:43 SU ( y x -- result ) Subtract x from y does this mean that the code "3 0 SU" will output -3 and not 3? 23:02:35 No. 23:02:55 Actually it won't output anything because it is not a string, but you can cast it to a string by +<> afterward 23:04:53 ok 23:05:36 so in ( z y x -- z' ) the top of the stack is z? 23:05:42 or x 23:06:03 The top of the stack is x same as in Forth 23:06:08 ok 23:07:27 Hopefully it is understandable now? 23:08:54 yes 23:09:26 still a bit confused about the whole good-bad-very bad thing 23:10:47 Perhaps look at some of the files that use those commands 23:20:43 Does it help? 23:22:47 -!- jiella has quit (Quit: Leaving.). 23:23:46 Arc_Koen, shachaf: I would say that "domain-specific language" is a much narrower thing than PHP 23:23:59 PHP is basically a general purpose programming language 23:24:02 kmc: I agree 23:24:09 zzo38: not really 23:24:13 a terrible one, and definitely with lots of web stuff baked in, but with lots of other things too 23:24:20 and i mean "web stuff" is a really broad domain 23:24:24 I think it's similar to ocaml's exceptions 23:24:40 to me a DSL is like, a makefile language or a 3D renderer scene description language or such 23:25:04 they might be turing complete but they aren't oriented towards the general tasks of programming 23:25:15 kmc: Yes, I agree with you. 23:25:32 one insight is that one should focus on building the domain specific bits and not on reinventing the programming language bits, incrementally and poorly 23:25:58 basically every 'config file' format eventually grows a bad implementation of variables, control flow, etc. 23:26:17 so the so-called "embedded domain-specific languages" are really just libraries in a host language, and you have the host language's features for these things 23:26:34 er I meant to ping shapr not shachaf 23:26:36 but shapr is not here 23:27:19 i worked somewhere where both frontend and backend were written in a mixture of Ruby on Rails and PHP 23:27:54 meaning, both the webapp and backend batch processing or sysadmin scripts 23:27:56 -!- augur has joined. 23:28:08 -!- augur has quit (Remote host closed the connection). 23:28:19 -!- augur has joined. 23:34:11 kmc: Your description of these thing of domain specific programming, is a bit like how FurryScript is like 23:34:43 -!- nys has quit (Quit: quit). 23:35:03 hi kmc 23:37:12 hichaf 23:37:15 how goes? 23:38:47 I need to find a place which is quiet and pleasant and open at odd hours. 23:39:00 And isn't $HOME. 23:39:10 how odd 23:39:21 The library works for everything except for the odd-hours bit. 23:39:37 -!- Por_gammer has quit (Ping timeout: 245 seconds). 23:47:05 ion: You gonna talk about applicative functors with XMunkki face-to-face, like a man? Huh? 23:48:12 Hehe 23:48:14 I know him from elsewhere. 23:49:26 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:50:04 i wonder when 4TB drives will be reasonably priced and not shitty 23:51:35 What counts as "reasonably"? 23:52:18 Looks like you can get one for $300 23:52:39 That's not so bad. 23:52:53 it's twice as much as a 3TB drive, though 23:53:45 3TB is $150? 23:53:54 ish 23:53:54 How times have changed, or something. 23:54:13 and 2TB is like $110 23:54:29 I should get an external drive. 23:55:30 my storage array is 99.6% full 23:56:25 How many TBs is that 0.4%? 23:56:43 I never petabyte I didn't like. 23:58:09 0.032 2012-10-16: 00:06:56 just zip it repeatedly until it's small 00:06:58 so easy 00:08:24 yep 00:08:37 many people just zip once and get it down to like 80%, but what they don't realize is 0.8^10 is like 0.1 00:08:51 oklofok: You should patent it! 00:08:57 i should 00:08:59 I bet it'd get accepted. 00:09:28 in fact i should probably patent powers of endomorphisms in general. 00:11:07 so today i was programming shit 00:11:32 that's funny, today i was shitting programs 00:11:53 i think i may have omitted some detais 00:11:55 details 00:12:47 what i was going to say was i programmed this thing that takes a texture and then chooses uvs of vertices in your triangles so that the texture is always the same size 00:12:56 which was ofc kinda trivial 00:13:08 but there was this one bug i just couldn't fix 00:13:28 everything was the wrong way around 00:13:35 so 00:13:45 i'm going to share this with you so you'll know in the future 00:13:58 clockwise means the direction clocks tick in 00:14:07 not the direction they don't tick in 00:14:30 i even invented a mnemonic 00:14:44 clockwise sounds kinda like "clock direction" 00:14:57 so you can think of it as like the "direction of a clock" 00:15:00 if that makes sense 00:15:55 kinda far-fetched i admit but mnemonics are sometimes easy to remember because they are so silly 00:15:57 you know 00:16:15 there seem to be at least 21 linux installs buried somewhere within my drive array 00:16:33 no actually some of them are freebsd 00:18:03 FreeBaSeD 00:38:55 Hehe. It was fun to see him out of character. http://www.huffingtonpost.com/2012/10/14/stephen-colbert-meet-the-press-newsman_n_1965034.html?utm_hp_ref=butt 01:03:43 WD and Seagate 3TB drives are exactly the same price 01:03:54 i guess the thing to do is get half of each 01:35:42 -!- nooga has joined. 01:40:47 -!- nooga has quit (Ping timeout: 240 seconds). 01:45:52 Please Move The Deer Crossing http://youtu.be/CI8UPHMzZm8 01:57:28 Anyone except Sgeo can submit 4clojure questions. 01:57:59 * Sgeo wants to make the halting problem a 4clojure problem >:D 02:04:30 -!- luite has quit (Quit: leaving). 02:34:39 -!- monqy has joined. 03:02:25 -!- Arc_Koen has quit (Quit: Arc_Koen). 03:02:46 -!- Arc_Koen has joined. 03:03:11 -!- Arc_Koen has quit (Client Quit). 03:21:50 -!- RocketJSquirrel has changed nick to Gregor. 03:30:43 -!- Robdgreat has joined. 03:39:40 -!- tswett has quit (Changing host). 03:39:40 -!- tswett has joined. 03:41:23 -!- Frooxius has quit (Ping timeout: 245 seconds). 03:45:25 i got my oyster mushroom spores 03:45:39 the sketchy spore company included a baggie of opium poppy seeds as a 'free gift' 03:56:34 -!- sirdancealot7 has quit (Ping timeout: 240 seconds). 04:03:30 I have entered Famicompo Mini vol.9 and you will see it at Halloween, unless you wish to enter in which case you must submit before then. 04:04:11 When's Canadian Halloween? 04:05:36 October 31 04:06:02 However, I am talking about the Japanese, which is on October 31. 04:06:11 Wow, it's the same day as American Halloween. What a coïncidence. 04:06:25 (I don't know if they celebrate Halloween much, but nevertheless it is still October 31) 04:12:03 If you write any music, try!! 04:16:12 zzo38: Do they have a 4th of July in Canada? 04:20:11 Yes, but it is not anything special. 04:25:28 zzo38: Halloween in Japan is a) a very recent cultural import b) not a big deal. 04:26:07 But it does exist in Japan, yeah. 04:26:13 And even in a vaguely recognizable form. 04:28:27 Fairly unlike say, Christmas, or Valentine's, though, in that it's not exactly a major holiday. 04:48:53 Is it possible to make any halting problem into a formula of Typographical Number Theory which is true statement if and only if the program halts (even though it cannot be proven)? 05:14:16 How common is additive synthesis in .NSF? 05:55:41 Some of the userboxes I made on Wikipedia are used by others some aren't. nopatents (me only) netcatIRC (1 other) DVIPDF (me only) gamediff4 (me only) AntiAntiTerrorist (1 other) ownpythag (self only) dnd35 (30 other) Vonkeror (me only) Yomi (me only) AkagiManga (me only) TeX (3 other) Mad_TeX (me only) gopher (1 improper use) ... 05:59:16 ... cmdline (95 other) textonlygame (8 other) hexeditMIDI (5 other) dnd35monsterchara (3 other) 05:59:22 shachaf: http://wwpgd.com/ 05:59:31 this is what happens when I wander into TechCrunch 06:04:30 oh man http://twitter.com/shit_hn_says 06:12:52 kmc: Ha. 06:29:13 I mentioned Dada Engine and rmutt in the document of FurryScript now. 06:32:38 Those are also programming language for random text generator, which I did not know about when I made FurryScript, and are less powerful and less strange than FurryScript. 06:35:08 -!- zzo38 has quit (Remote host closed the connection). 06:40:37 -!- sirdancealot7 has joined. 06:57:34 -!- sirdancealot7 has quit (Ping timeout: 240 seconds). 07:01:57 -!- nooga has joined. 07:06:35 -!- epicmonkey has joined. 07:10:31 -!- FreeFull has quit. 07:18:28 -!- nooga has quit (Ping timeout: 252 seconds). 07:33:35 -!- epicmonkey has quit (Ping timeout: 246 seconds). 07:43:10 -!- hijack has joined. 07:43:36 -!- hijack has changed nick to mean. 07:48:15 -!- zzo38 has joined. 07:57:07 -!- copumpkin has quit (Ping timeout: 245 seconds). 07:57:41 -!- copumpkin has joined. 08:08:41 -!- nooga has joined. 08:23:49 -!- sirdancealot7 has joined. 08:54:49 -!- nooga has quit (Read error: Operation timed out). 09:03:24 -!- monqy has quit (Quit: hello). 09:09:12 -!- epicmonkey has joined. 09:16:34 -!- zzo38 has quit (Remote host closed the connection). 09:44:55 -!- Arc_Koen has joined. 09:45:18 and hello 09:50:46 What's the "and" for? 10:13:59 -!- TodPunk has quit (Read error: Connection reset by peer). 10:14:12 -!- TodPunk has joined. 10:32:39 -!- Phantom_Hoover has joined. 10:32:39 -!- Phantom_Hoover has quit (Client Quit). 10:32:45 -!- Phantom_Hoover has joined. 11:02:36 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 11:14:27 -!- coppro has quit (Ping timeout: 260 seconds). 11:15:07 -!- coppro has joined. 12:02:30 -!- Frooxius has joined. 12:08:04 -!- Phantom_Hoover has joined. 12:32:02 -!- boily has joined. 12:36:52 -!- MoALTz has joined. 12:51:44 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 12:59:15 -!- ogrom has joined. 13:26:43 -!- elliott has joined. 13:30:15 -!- Phantom_Hoover has joined. 13:39:22 -!- epicmonkey has quit (Remote host closed the connection). 13:39:32 -!- epicmonkey has joined. 13:41:35 tswett: do you have any opinion wrt http://esolangs.org/wiki/Talk:Surprised_look 13:43:59 Arc_Koen: about http://esolangs.org/wiki/User:Koen/brainfuck.thue -- I think generally we avoid putting user pages in categories like that, but it seems like it'd fit just fine as an article 13:44:04 (say [[Brainfuck interpreter in Thue]] or something) 13:45:53 -!- copumpkin has quit (Quit: Computer has gone to sleep.). 13:49:10 Arc_Koen: the link in http://esolangs.org/w/index.php?title=EsoInterpreters&curid=2229&diff=34294&oldid=33862 we explicitly avoid per http://esolangs.org/wiki/Esolang:Policy 13:49:20 maybe the best thing there is an external link to your user subpage (as bizarre as it is) 13:49:25 anyway ais523 might have a better idea than me 13:55:30 elliott: yes I don't know why when I started writing it it felt more natural to make it a user page, and when I was over it felt like it should have been in the main namespace 13:55:34 I'll change it I guess 13:56:01 also for EsoInterpreters, all the links are just "X"s with no distinction between internal and external links 13:56:13 should move it by copy-paste so I get the opportunity to do an exciting history merge 13:56:18 haven't had enough of those since NSQX disappeared 13:56:35 Arc_Koen: well the external links are coloured slightly differently 13:56:40 not the biggest deal though 13:57:08 -!- MoALTz has quit (Ping timeout: 246 seconds). 13:57:43 by copy-paste do you mean I should just create a new page and don't care about the old one? 13:59:56 that's exactly what you should not do but also exactly the thing that would lead me to have to merge the history of the pages 14:00:02 it was a joke, makes no sense unless you were around when NSQX was :p 14:00:09 just use the move option 14:00:25 oh, ok 14:00:41 well I still should start by rewriting all the parts that were first-person, right? 14:01:18 not sure, really 14:01:30 honestly you should just ak ais523, probably he remembers the last time we had an interpreter in userspace 14:01:58 ok, thanks 14:04:52 -!- copumpkin has joined. 14:12:23 elliott: not really. I don't particularly care whether it's deleted or salvaged. 14:23:44 i was thinking it should probably just have the blanking reverted and some note about it being abandoned added 14:23:53 since deleting it is a shame and leaving it blank is confusing 14:25:14 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 14:29:31 and a link added to the logs where it is described? 14:29:51 maybe 14:29:55 too lazy to find that myeslf 14:29:56 myself 14:36:38 -!- copumpkin has changed nick to Shylock. 14:36:52 -!- Shylock has changed nick to copumpkin. 14:37:10 -!- Phantom_Hoover has joined. 14:44:24 -!- augur has quit (Ping timeout: 244 seconds). 14:49:51 -!- ogrom has quit (Quit: Left). 15:03:02 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 15:24:37 -!- nooga has joined. 15:34:56 -!- pikhq_ has quit (Read error: Operation timed out). 15:35:10 -!- pikhq has joined. 15:36:26 -!- augur has joined. 16:05:19 -!- AnotherTest has joined. 16:05:45 Hello 16:06:31 -!- Vorpal has joined. 16:09:14 -!- Phantom_Hoover has joined. 16:11:57 -!- Vorpal has quit (Ping timeout: 276 seconds). 16:27:42 hey is there a something like "plainpres" or something to force every cell in a wikitable to look like it were in snippets? 16:28:18 like HTML's 
?
16:29:44  hum, a, maybe
16:29:57  http://i.imgur.com/59rw6.jpg
16:33:00 -!- zzo38 has joined.
16:33:21  ?messages
16:33:21  You don't have any new messages.
16:42:17  Arc_Koen: you should just wrap them in  or 
16:44:02  the whole table?
16:44:33  I seem to recall last time I used 
 inside a table, Oerjan edited after me to make it more simple
16:45:35  try that again :p?
16:45:47  probably do whatever oerjan did then :p
16:47:32  @ask zzo38 Want a message?
16:47:33  Consider it noted.
16:48:30  @tell zzo38 and another one
16:48:30  Consider it noted.
16:58:16 * Arc_Koen resists the urge to imitate shachaf and AnotherTest 
17:02:18 -!- FreeFull has joined.
17:15:23  Other programming languages for random text generator other than FurryScript includes Dada Engine and rmutt, although FurryScript seems to have many more features, and an entirely different syntax.
17:15:23  zzo38: You have 2 new messages. '/msg lambdabot @messages' to read them.
17:15:59  TITLE("The Passion Considered as a Mornington Crescent Game")
17:36:57 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
17:49:29 -!- augur has quit (Read error: Connection reset by peer).
17:49:50  @tell Arc_koen remember to ask ais523 about User namespace when you get back
17:49:50  You can tell yourself!
17:49:55 -!- augur has joined.
17:50:18  ok.
17:58:57 -!- AnotherTest has quit (Quit: Leaving.).
17:59:08 -!- AnotherTest has joined.
17:59:26 -!- atriq has joined.
18:00:58 -!- augur has quit (Read error: Connection reset by peer).
18:01:23 -!- augur has joined.
18:10:15 -!- mean has quit (Remote host closed the connection).
18:10:51 -!- mean has joined.
18:11:21 -!- mean has quit (Client Quit).
18:16:44  http://blog.humblebundle.com/post/33714074132/humble-ebook-bundle-is-now-five-times-more-hilarious
18:17:44  ebooks... of web comics?
18:17:45 -!- epicmonkey has quit (Remote host closed the connection).
18:17:55  hehe
18:18:01  it's like... the web in book form in web form
18:18:31 -!- Phantom_Hoover has joined.
18:19:55  "Eläinlääkintäeverstiluutnantittomuuttaankinkohan vihollisarmeija jämähti?" = "I wonder if one of the reasons why the enemy army stopped was their lack of Veterinary Lieutenant Colonels?"
18:21:29  nice one
18:22:25  ion: The string on the left looks shorter than the string on the right, but that's only due to lack of spaces.
18:23:07  > length "ä"  -- did lambdabot handle this right?
18:23:08    1
18:23:38  > let f = length . filter isAlpha in map f ["Eläinlääkintäeverstiluutnantittomuuttaankinkohan vihollisarmeija jämähti?", "I wonder if one of the reasons why the enemy army stopped was their lack of Veterinary Lieutenant Colonels?"]
18:23:40    [70,88]
18:23:46  > length "1-Äh-hä-hä"
18:23:48    10
18:24:13  I'm temporarily out of money, so I won't get the Humble eBook Bundle
18:24:31  ion: i can't decide if that was actually an increase in hilariousness or a decrease
18:24:43  the SMBC books will probably be good
18:24:58 -!- sirdancealot7 has quit (Ping timeout: 265 seconds).
18:25:31  > length "ä"
18:25:33    2
18:25:54  > "length"
18:25:55    "length"
18:25:59  > length "length"
18:26:00    6
18:26:35  > "ä"
18:26:36    "a\776"
18:28:26  This morning I was bored so I wrote a program to find perfect numbers
18:28:47  It found eight straight away then ran out of memory half an hour later
18:29:13  eight magic numbers, or the number eight?
18:29:17  The former
18:29:22  Perfect numbers
18:29:30  6, 28, 496, yada yada yada
18:29:44  I don't know what those are
18:30:20  Numbers that are equal to the sum of their factors (other than themself)
18:30:32  Factors of 6 are 1, 2 and 3. 1 + 2 + 3 = 6
18:30:41  it's more perfect if you include themself
18:30:44  themselves
18:31:02  Factors of 28 are 1, 2, 4, 7, 14. 1 + 2+ 4 + 7 + 14 = 28
18:31:07  Then it would just be 1?
18:32:43  import Data.Numbers.Primes -- from the primes package on Hackage
18:32:52   Then it would just be 1?
18:32:55  1 is pretty perfect don't you think
18:33:13  main = mapM_ print [2 ^ (p - 1) * q | p <- primes, let q = 2 ^ p - 1, isPrime q]
18:33:24  1 is ridiculously imperfect.
18:33:40  33550336 is perfect
18:34:00  The program can easily be altered to find mersenne primes
18:34:31  I have a sed script to find perfect numbers.
18:34:32  By removing "2 ^ (p - 1) * "
18:35:03  Does it work in a similar way?
18:35:33  I don't remember how it works.
18:36:20  I just wrote a program to draw a madelbrot fractal
18:36:29  *mandelbrot
18:36:36  Does it work?
18:36:40  It does
18:36:43  Yay!
18:36:46  and it matches colors
18:37:07  I don't remember what I'm meant to give as input to this program.
18:37:18  although it doesn't render them smooth (although there is an algorithm for that I believe)
18:38:41  http://sprunge.us/cQZc -- oh, so that's how it works, it looks for as many numbers as there are letters on the line.
18:39:21  nice
18:39:22  Sadly, I don't think it's really efficient enough to go past 8128 very well.
18:40:03  This one tests only numbers of the form 2^(p-1)(2^p-1).
18:40:20  So it'll skip all those possible odd perfect numbers.
18:40:39  (The first version tests every number for perfection, but it's kinda slower.)
18:42:27  I think it does unary math, anyway.
18:43:01  At least the body of the pow2 loop is just a s/^x*/&&/.
18:43:17  (There's a unary-to-decimal conversion at the end.)
18:44:19  Meanwhile in the Free World, http://www.huffingtonpost.com/2012/05/20/asset-forfeiture-wisconsin-bail-confiscated_n_1522328.html?utm_hp_ref=butt&src=butt&comm_ref=butt
18:45:14 -!- AnotherTest has left.
18:51:32  I don't believe in odd perfect numbers.
18:53:27  Are you SURE there aren't any? 
18:54:35 -!- ais523 has joined.
18:55:20  Though given that lower bound of 10^1500, maybe the unary-using program wouldn't need to spend time looking for it.
18:56:18  hmm, so it's not the sum of factors, but the sum of all combinations of factors?
18:56:44  I was just about to combine factor and dc into a perfect number tester, but now I'll probably not bother
18:56:45 -!- Zerker has joined.
18:57:13  olsner: Sum of all (positive, proper) divisors.
19:07:10  fizzie, +1
19:08:00 -!- epicmonkey has joined.
19:11:05  Can any programming be made involving linear logic making functions?
19:11:47  Instinct says yes
19:12:00  Don't know enough about linear logic
19:12:47  Look in Wikipedia
19:25:17  Oh dear
19:25:50  Today at school I provided an alternate proof that for any a and b in a group, (ab)^-1 = a^-1 b^-1
19:25:54  (alternate to the teachers)
19:25:57  And someone filmed it
19:27:09  Isn't it b^-1 a^-1?
19:27:13  Yes
19:27:16  That is what I meant
19:29:04  How many proofs of that can there be?
19:29:59  At least two, evidently
19:30:20  Teacher's proof:
19:30:31  Wait
19:30:38  I can't remember the teacher's proof
19:31:02  Yes I can
19:31:24  (ab)^-1 = b^-1 a^-1
19:31:43  -> (ab)^-1 a = b^-1 a^-1
19:31:55  a
19:31:55  Wait, what?
19:32:14  -> (ab) ^ - 1 a = b^-1
19:32:41  -> (ab)^-1 a b = b^-1 b
19:32:53  Actually, I have no idea what I'm doing
19:32:58  My proof was better
19:34:35  ((ab)^-1)(ab) = 1; (((ab)^-1)a)b = 1; ((ab)^-1)a = b^-1; (ab)^-1 = (b^-1)(a^-1)
19:36:44  Hmm
19:56:14 -!- augur has quit (Remote host closed the connection).
20:38:47 -!- epicmonkey has quit (Remote host closed the connection).
20:39:04 -!- epicmonkey has joined.
20:45:23  That was silly.
20:52:37  Can the "!" in linear logic be made like a kind of comonad?
21:16:08  elliott: heh, when I saw you on [[The Best Place To Grab Cash Financing Very Quickly]] I was wondering whether it was spam deletion or language construction ;)
21:16:15  it does sound like a good language name
21:16:32  zzo38: it has both monad-like and comonad-like properties
21:16:53  I think my supervisor and I concluded it was probably a comonad
21:17:01  but I wasn't sure, and it didn't really matter for what I was doing
21:17:49  I talked with my supervisor and concluded that ais523 was probably a cocoa monad.
21:18:24  ais523: Can you kick me?
21:18:41  ais523, give him voice!
21:18:43  shachaf: can you kick you?
21:18:55  /kick shachaf
21:19:00  no
21:19:24  I can kick arbitrary people from the channel, assuming they're here at the time
21:19:27  whether I /should/ is another issue
21:19:35  Am I arbitrary enough for you?
21:19:37  heh, Gregor's still voiced?
21:19:56  Gregor: hi Gregor
21:20:03  everyone should have the right to kick and ban themselves
21:21:09  hmm
21:21:19  on Wikipedia, they actually had to ban people from banning themselves
21:21:28  had to?
21:21:29  because it had unintended side effects
21:21:38  (especially involving shared IPs)
21:22:10 -!- atriq has quit (Quit: Leaving).
21:27:17  so people actually ended up banning a lot more people than themselves?
21:29:31  I think you could just delete [[The Best Place To Grab Cash Financing Very Quickly]]. Administrators can undelete anyways if required isn't it?
21:30:26  zzo38: Wow, what a h8r.
21:30:36  Why would you delete an esolang like that?
21:31:17  ais523: Arc_Koen was going to ask you stuff
21:32:21  Arc_Koen: btw i believe you misunderstand http://esolangs.org/wiki/Works_in_progress possibly
21:32:27  (see the first paragraph0
21:32:28  *)
21:32:35  oh maybe not
21:32:40  shachaf: Mostly because it is already deleted.
21:32:53  And even when it exist, contain nothing of any use.
21:33:09  (If is required, I guess undelete since I think MediaWiki allows it)
21:33:20  UNDELETE.EXE
21:34:46  hello
21:34:48  Although I prefer pure wiki deletion, if it could be made MediaWiki to support it (such as making the history is viewable on deleted pages and everything else just like blanking it, but it never appears on lists of pages and never appears on random page function either.
21:35:41  elliott: no, Lazy Prefix was made to be a work in progress
21:35:55  zzo38: pure deletion would probably be a bad idea, people would link to deleted history pages and then maintain it as Wikipedia's official position
21:36:02  and quite a lot of people would be stupid enough to fall for it
21:36:44  it's mainly the result of me trying to fall asleep and if it can make sense for anyone I'd be glad that they make it their thing as much as mine
21:37:14  pure wiki deletion is terrible for things like copyvio and personal info also
21:37:35  ais523: yes I had a question about User:Koen/brainfuck.thue
21:38:03  I'm gonna move it to main namespace - thing is, I'm not sure it fits as is
21:38:19  for instance I use first-person throughout the page, should I change that?
21:38:34  and move the external links to a "external resources" section, also
21:38:42  Even normal page deletion is bad for things like copyvio; instead, administrators should delete individual changes in the page history list, in such cases as that, if something must be remove entirely without disturbing the rest of the article, in case it is otherwise OK.
21:38:54  elliott said you would remember the last time an interpreter was in the user namespace
21:40:08  the reason I put it there in the first place was because there was already a link to a brainfuck interpreter on the thue page, and while making mine I felt more like doing something for myself than actually contributing to esolangs in general
21:42:00  fwiw if you want to license it as something other than CC0 then the best thing would be to put it up elsewhere on the web (e.g. on a pastebin) and link to it externally, also
21:42:15 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
21:45:34  I'm not so excited about copyrights
21:45:47  I AM ORGASMIC OVER COPYRIGHTS
21:46:31  i copyright things all night and then go to bed and dream about copyright
21:46:51  ais523: http://esolangs.org/wiki/WASD sigh
21:47:08  ais523: we should split the language list up so all the brainfuck derivatives are on another page or something
21:48:18  yes
21:48:20  yes we should
21:48:21  elliott: how about my derivative that uses the symbols <> for [], -+ for <>, ,. for -+, [] for ,.
21:48:29  Phantom_Hoover: ☝ innovation ☝
21:48:44  what the fuck
21:48:59  is that like a fishhook
21:49:19  http://esolangs.org/wiki/Not_a_brainfuck_derivative i remember making this
21:49:35  how about my derivative that uses the symbols 8=D, 8==D, 8===D, 8====D, 8=====D, 8======D, 8=======D, and 8========D
21:49:44  I have an even better idea! a brainfuck-derivative on a left- and right-unbounded tape with bounded wrapping cells, using the symbols > for <, < for >, + for - and - for +
21:49:57  Arc_Koen: and . and , do 255-x?
21:49:57  oh wait it already exists
21:50:09  yes, yes they do
21:50:44  and [ and ] don't test whether x = 0, but whether x = 256
21:51:07  data D = D deriving Eq; instance Num D where fromInteger 8 = D
21:51:41  kmc and his smiling chefs
21:51:41  nice pointless deriving Eq
21:52:00  elliott: kmc believes in Eq a => Num a
21:52:11  Like the Haskell Report (and unlike GHC).
21:52:18  the history of haskell is the history of class struggle
21:52:23  I guess kmc forgot to derive Show.
21:52:26  shachaf: then he also has to believe in Show a => Num a
21:52:29  so it is pointless or invalid
21:52:48  kmc: elliott just called you not(pointful and valid)
21:53:18  fsvo you
21:54:06  fix u = let mad = u mad in u
21:56:01  > let in shachaf please
21:56:03    Sorry, shachaf's not allowed in.
21:56:46  kmc: can i have applause
21:56:53  > please
21:56:56    ()
21:57:16  *clap clap clap*
21:57:23  but considering he's already in, shouldn't we be allowing him out instead?
21:57:42  I'm probably gonna regret I ever asked, but what other esolangs have inspired wasd?
21:58:00  hi elliott
21:58:10  Arc_Koen: presumably brainfuck
21:58:15  elliott: Did you @admin - me?
21:58:23  shachaf: no, but I might next time
21:58:29  elliott: the page says "inspired by brainfuck and other esolangs"
21:58:38  Arc_Koen: probably ook or something then
21:59:01  oh, yes, it does bear some resemblance with Ook!
21:59:05  and blub
21:59:09  how did I not see that sooner
21:59:17 -!- Zerker has quit (Ping timeout: 255 seconds).
21:59:29  might be nice with an esolang that's somehow a superset of all the other esolangs
21:59:55 -!- augur has joined.
22:00:21  something dangerous to say, someone might overhear you and go ahead and do it
22:00:44  that'd be awesome because then I get the benefit of having thought it without having to actually do any work
22:00:57 -!- copumpkin has joined.
22:01:15  I was gonna say "I'm gonna hit random page a few times and include every esolang I'm gonna come across"
22:02:18  like, starting from brainfuck, and if I meet deadfish I add a command to square the current cell (taking it out of 0-255), and if I meet a stack-based language I add that every cell is in fact a stack, etc.
22:02:25  so I hit random page
22:02:34  http://esolangs.org/wiki/Cvlemar
22:02:43  not sure how that'd fit with brainfuck :)
22:03:09  which is a pretty neat excuse to let you find someone else to do your dirty work!
22:04:50  oh and I thought it might be cool to prove a "subset" of Kipple turing-complete... and that subset would not allow stacks to hold anything else than zeroes
22:06:22  in fact that's probably easy to prove, via reduction from 3-cell brainfuck
22:14:25 -!- nooga has quit (Ping timeout: 244 seconds).
22:30:22 -!- Slereah_ has joined.
22:31:06 -!- Slereah has quit (Ping timeout: 252 seconds).
22:55:42 -!- mean has joined.
22:57:56  looks like i picked the wrong day to stop sniffing glue
22:58:15  `welcome mean
22:58:24  mean: 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.)
22:58:53  kmc: What kind of glue did you stop sniffing?
22:59:14  all kinds
22:59:20  o
23:00:04  oh
23:00:23 -!- boily has quit (Quit: Poulet!).
23:05:13  ohh
23:05:15 -!- ais523 has quit.
23:06:47  ohhh
23:06:47 -!- epicmonkey has quit (Remote host closed the connection).
23:07:09 -!- epicmonkey has joined.
23:07:14  > map ('o:' . flip replicate 'h') [0..]
23:07:16    :
23:07:16       lexical error in string/character literal at chara...
23:07:19  > map ('o': . flip replicate 'h') [0..]
23:07:20    : parse error on input `.'
23:07:27  I seem to be too tired for code.
23:07:31  > map (('o':) . flip replicate 'h') [0..]
23:07:33    ["o","oh","ohh","ohhh","ohhhh","ohhhhh","ohhhhhh","ohhhhhhh","ohhhhhhhh","o...
23:07:46 -!- epicmonkey has quit (Remote host closed the connection).
23:08:10 -!- epicmonkey has joined.
23:08:16 -!- epicmonkey has quit (Remote host closed the connection).
23:19:06  ion: ugly!
23:19:12  > iterate (++ "h") "o"
23:19:15    ["o","oh","ohh","ohhh","ohhhh","ohhhhh","ohhhhhh","ohhhhhhh","ohhhhhhhh","o...
23:19:59  heh
23:20:20  > map (\n -> take n ('o':repeat 'h')) [1..]
23:20:22    ["o","oh","ohh","ohhh","ohhhh","ohhhhh","ohhhhhh","ohhhhhhh","ohhhhhhhh","o...
23:20:41  > (tail . inits) ('o':repeat 'h')
23:20:43    ["o","oh","ohh","ohhh","ohhhh","ohhhhh","ohhhhhh","ohhhhhhh","ohhhhhhhh","o...
23:20:54  nice
23:21:14  > (map ('o':) . inits . repeat) 'h'
23:21:16    ["o","oh","ohh","ohhh","ohhhh","ohhhhh","ohhhhhh","ohhhhhhh","ohhhhhhhh","o...
23:21:46  > inits []
23:21:47    [[]]
23:21:50  right
23:23:58  whee, earthquake
23:24:04  magnitude 4.5, 90 miles north of me
23:24:46  Did you survive it?
23:25:37  He didn’t say it happened yet. Perhaps he won’t.
23:26:00  i did survive yes
23:46:30 -!- MoALTz has joined.

2012-10-17:

00:18:48  [[
00:18:48  Absurd Ambition: Towards lifting differential/integral calculus into Haskell (self.haskell)
00:18:48  submitted 1 day ago by enolan
00:18:48  Okay, so first observe that FRP is a language embedded in Haskell for reasoning about systems evolving in time. Then make time first class. This enables time-bending programs, among other things. Remember that "regular" calculus is about rates of change and things depending on other things. Generalize FRP into differential/integral calculus on arbitrary data. (Remember we can find derivatives of data structures!)
00:18:49  Please poke all the holes possible in this idea.
00:18:51  Bitcoin donations graciously accepted here 1EDqgKBx3XuVnMughSzmTtFjqz5zey12Jv
00:18:53  ]]
00:18:55  i nominate this for worst /r/haskell post of any time
00:18:58  any objections
00:19:14  [[I'm aware of automatic differentiation, hence "Remember we can find derivatives of data structures!".]]
00:19:18  looks like their replies are golden too
00:19:28  "Automatic differentiation is not the same as differentiating data structures." "I don't know what that means yet, but thank you."
00:20:28  shachaf: does this enolan guy talk in #haskell at all
00:21:23 -!- Phantom__Hoover has joined.
00:21:28  17:21   enolan was last seen on #haskell 1 day, 1 hour, 18 minutes and 3 seconds ago, saying: http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/
00:21:39  http://www.reddit.com/user/enolan
00:21:40  wow
00:21:59  a supercomputer that's also a nuclear reactor
00:22:06  guy thinks big, i'll give him that
00:22:15  "Architect of the Bitcoin singularity, man of super-Einsteinian ambition, nerd accelerator. ;)"
00:22:20  guys this is an emergency
00:22:23  http://paste.ubuntu.com/1276031/
00:22:24  someone has actually described themselves with these words
00:22:30  this guy is grade-a awful
00:22:36  (the a is for awful)
00:22:45  Phantom__Hoover: what is that from
00:22:52  fuck
00:22:53  knows
00:23:02  he posted a link to it on reddit, there is no context
00:23:11  no comments, just downvotes
00:24:22  http://www.reddit.com/r/askscience/comments/10bnuv/mirs_orbit_eventually_decayed_and_it_crashed_into/
00:24:24  troll
00:24:27 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
00:24:28  for the love of god please
00:24:45  Phantom__Hoover: The question is: How can I donate bitcoins to this person?
00:24:50  http://www.reddit.com/r/askscience/comments/z8mnv/why_are_tall_women_generally_considered_more/
00:25:39  if we capture and dissect this man we may finally understand the true essence of human stupidity
00:26:14  "Asking for money seems a bit gratuitous." "I think this is gratutiously awesome idea."
00:26:18  best reddit comment ever
00:27:41  "Anyone who posts like that, and hurts my brain, gets upvotes and possibly BTC."
00:27:57  "Does that mean we need dependent Haskell to express this? I am totally willing to go there!"
00:27:58  careful guys
00:28:04  he's totally willing to go there!!
00:28:11  he went there
00:28:15  "Why is Edward getting all the imaginary internet points in this thread? Where are my points?!?!!?" he actually posted this
00:28:16  no coming back from there
00:29:05  "hey guys upvote upvote!!! it's ok because i've evolved beyond meaningless ideas of karma"
00:29:42  http://www.reddit.com/r/math/comments/yy344/askmath_what_is_a_good_mathematical_basis_for_a/
00:29:47  oh sweet jesus
00:30:10  @tell cmccann I have no idea what this is -- http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/ -- but it looks sort of like trolling, esp. given http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/c6n0evb... the asking for money thing seems inappropriate but I don't know if you want to do anything about it
00:30:10  Consider it noted.
00:30:26  my work is done
00:30:51  that's a pretty depressive sentence.
00:30:58  @tell cmccann make sure you check his post history if you feel like working up a good healthy hatred
00:30:58  Consider it noted.
00:31:25  Why are you @telling cmccann?
00:31:47 -!- DHeadshot has joined.
00:31:48  shachaf: I was @telling cmccann because reddit's report feature is useless and he's the most active /r/haskell mod and I talk with him fairly.
00:31:58  Phantom__Hoover is @telling cmccann because he's trying to be annoying, which I'm sure is behaviour you're familiar with.
00:32:11  elliott: Fairly?
00:32:18  *fairly often, whatever
00:32:22  What about copumpkin?
00:32:37  More like coolpumpkin, AM I RIGHT?
00:32:41  ?
00:32:43 -!- Phantom__Hoover has quit (Quit: Leaving).
00:32:47  hey do you pronounce it often or often?
00:32:56  copumpkin: shachaf is talking about /r/haskell mods :p
00:32:59  re  @tell cmccann I have no idea what this is -- http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/ -- but it looks sort of like trolling, esp. given http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/c6n0evb... the asking for money thing seems inappropriate but I don't know if you want to do anything about it
00:33:02  I pay attention to the modqueue whenever I can
00:33:08  and have done my fair share of moderating recently
00:33:23  You should make elliott a moderator.
00:33:24 * elliott would have reported it if reddit's report feature included anything even vaguely useful like a text box to say wtf you're reporting for
00:33:30  It would be the end of /r/haskell as we know it.
00:43:49  elliott, feel free to report then message mods?
00:46:02  Sgeo: I figured just messaging a mod would be less work.
00:46:06  Formal complaints are work 'n stuff.
00:46:18  "A" mod?
00:46:22  Why not the mods?
00:47:20  You do know that that's a thing, right? You don't have to choose one particular mod, you can message /r/haskell
00:47:39  
00:47:46  /msg /r/haskell hi monqy
00:47:49  telling "a" mod, n.  @tell cmccann I have no idea what this is -- http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/ -- but it looks sort of like trolling, esp. given http://www.reddit.com/r/haskell/comments/11ixcl/absurd_ambition_towards_lifting/c6n0evb... the asking for money thing seems inappropriate but I don't know if you want to do anything about it
00:48:22  elliott wants to tell his buddy cmccann
00:48:30  Because he knows cmccann will give him special treatment.
00:49:08  Yes, I control /r/haskell from behind closed doors.
00:49:17  Sgeo has found out my terrible secret.
00:49:22 -!- Jafet has joined.
00:49:34  I will have to assassinate him and shachaf for their sins.
00:50:05  ok well good night
00:50:15  copumpkin might assassinate you for your cosins!
00:50:16 -!- Arc_Koen has quit (Quit: and happy assassination).
00:50:31  Does the co in cosine have anything to do with the category co?
00:50:37 -!- Arc_Koen has joined.
00:50:52  copumpkin: Please spare me, my cousins didn't do anything wrong.
00:51:10  elliott: your wish is granted, just this once
00:51:19 -!- Arc_Koen has quit (Client Quit).
00:51:47  My croissants are to die for.
00:52:04 -!- Arc_Koen has joined.
00:52:42 -!- Arc_Koen has quit (Client Quit).
00:52:58  "The cosine of an angle is the ratio of the length of the adjacent side to the length of the hypotenuse: so called because it is the sine of the complementary or co-angle."
00:53:01  --Wikipedia
00:53:33  Don't stifle shachaf's new angle on category theory.
00:53:34 -!- Arc_Koen has joined.
00:53:52  Sgeo: Yes, I know.
00:54:04 * Sgeo chokes with laughter.
00:55:25  ...so I type /quit followed with a funny reason, then I click the damn red button to close the application before it has time to reconnect me somehow, and you know what? instead of closing it pops a little window "are you sure you want to close the application? that would close all connections"
00:55:36  "what connection"
00:55:51  "Welcome to the esoteric programming channel!
00:56:03 -!- Arc_Koen has quit (Client Quit).
00:57:06  shachaf: You killed Sgeo.
00:57:07  That's murder.
00:57:08  `quote murder
00:57:12  152)  Phantom_Hoover: Don't be nasty; he's a lunatic, not a murderer. \ 304)  elliott, it was an artful robbery!   wait, murder \ 826)  you've constructed a situation in which i have no choice but to die in 10 days   well done   that's murder
00:57:40  when did monqy say that :'(
00:57:51  Less than ten days ago?
00:58:01  Presumably.
00:58:05  monqy is a ghost.
00:58:10  `quote ghost
00:58:13  457)  monqy: last night in my dreams I saw a false photo album of my childhood... looking ghostly \ 504)  I MIGHT BECOME GHOST
00:58:15  `qhuost
00:58:19  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: qhuost: not found
01:16:38 -!- Jafet1 has joined.
01:17:29 -!- Jafet has quit (Disconnected by services).
01:17:35 -!- Jafet1 has changed nick to Jafet.
01:18:28  http://www.reddit.com/r/Clojure/comments/11kav3/the_consequences_of_not_using_paredit/
01:20:40 -!- hogeyui has quit (*.net *.split).
01:20:43 -!- lahwran has quit (*.net *.split).
01:21:47 -!- hogeyui has joined.
01:21:47 -!- lahwran has joined.
01:36:33  pareddit
01:37:50  Their target market is the non-OCD customers.
01:40:31 -!- DHeadshot has quit (Read error: Connection reset by peer).
01:40:36 -!- DH____ has joined.
01:46:33 -!- trout has changed nick to function.
01:57:35  What mathematical problems, besides Fermat's last theorem, could a solution to the halting problem be used to solve, and to which we do manage to know the answer?
01:58:27  All of them really
01:58:45  Most any. It's fairly trivial to produce a brute-force check of most theorems by looping over all *possible* combinations, that will only halt/not-halt if it's true.
01:58:48  Well, all problem that are recursively enumerable
01:59:00  Which ones were difficult?
01:59:19  And so a halting oracle can basically give you an answer to anything you can write an algorithm, no matter how shitty, to check.
01:59:22  It doesn't work if, say, you need to check over aleph_0 solutions
01:59:37  Preferably a famous one. I have a reason for asking
02:00:05  Poincaré conjecture?
02:00:05  Hmm. I wonder if P=NP could be expressed appropriately.
02:00:15  The thing about it is
02:00:17  Sgeo: anything of the form (exists (n:Z), p(n)) where p is a decidable proposition can be solved given a halting oracle
02:00:34  You can solve most math because you can do a syntactic proof using logical axioms
02:00:35  print $ doesHalt $ filter (isProofOf P) $ listAllProofs
02:00:49  proof: halts?({ for(Z i=0;;i++)if(p(i))break; })
02:00:51  and what Jafet said yes
02:01:03  The syntactic proof has to exist, though, but that's a pretty wide category of things
02:01:03  You probably want to run that in parallel with (isProofOf (not P))
02:01:15  And provableIn (modelOf P)
02:01:16 * Sgeo would have done Fermat's last theorem, but I don't see a simple way to loop over a b c and n such that it won't just increase one of them
02:01:37  Sgeo: do you really not see a bijection Z^4 <-> Z
02:01:52  i mean i can't think of a *good* one (fsvo good) off-hand
02:01:55  but Q <-> Z hence pack etc.
02:02:08  elliott, I know it exists, but I don't know how to do it easily
02:02:50  > [ (a, b, c, n-a) | n <- [0..], a <- [0..n], b <- [0..n-a], c <- [0..n-a-b] ]
02:02:51    [(0,0,0,0),(0,0,0,1),(0,0,1,1),(0,1,0,1),(1,0,0,0),(0,0,0,2),(0,0,1,2),(0,0...
02:03:10  hmm
02:03:24  Cool
02:04:23  Wait, why n-a?
02:04:31  > [ (a, b, c, n) | n <- [0..], a <- [0..n], b <- [0..n-a], c <- [0..n-a-b] ]
02:04:32    [(0,0,0,0),(0,0,0,1),(0,0,1,1),(0,1,0,1),(1,0,0,1),(0,0,0,2),(0,0,1,2),(0,0...
02:04:49  Sgeo: because n <- [0..]
02:04:57  need to reset it when you "roll over"
02:05:57  Actually I don't know. That could be wrong.
02:06:15  There are variuos ways to encode pairs into single numbers, such as bit interleave, or whatever
02:09:02 -!- DH____ has quit (Read error: Connection reset by peer).
02:10:19 -!- Slereah_ has quit (Ping timeout: 260 seconds).
02:15:25 -!- Slereah has joined.
02:40:31 -!- MoALTz has quit (Ping timeout: 256 seconds).
02:49:27  http://i.imgur.com/BJmIg.jpg
02:52:48  but that left parenthesis has a match
02:56:24  Is there programs for random text generator other than Dada Engine, rmutt, and FurryScript?
02:58:06  autogen
02:58:21  Oh, wait. That wasn’t the one i was thinking of.
03:00:54  what kind of random text?
03:01:10  i wrote http://hackage.haskell.org/package/detrospector
03:01:19  there are a billion programs like it
03:03:02  Ah, found it. polygen
03:03:30  What sort of fun can I have with reified lexical environments?
03:03:40  http://pdos.csail.mit.edu/scigen/
03:03:51  I mean like the examples I have given, though. However these are OK too
03:14:08  kmc: It is good; I do not think any of the three programs I listed have any command for Markov chain, but maybe later I may add command in FurryScript for Markov (including high order).
03:14:25  Anyways, which programs have you used to write your own, which one don't, etc?
03:16:35  You said there are billion programs like it, how many in Haskell and what difference of feature?
03:19:40  kmc: Aww, you can’t use detrospector as a library?
03:21:02 -!- Jafet has quit (Ping timeout: 255 seconds).
03:21:34  Do you intend to change it so that it does?
03:26:16  yeah, people have asked for that
03:26:18  i probably won't though
03:26:21  because i am lazy
03:29:53  Sgeo: What is reified lexical environments?
03:31:12  zzo38, a macro in Clojure, and probably Common Lisp, can help capture the lexical environment, as in, symbols bound by let and their values
03:33:56  Design goals include speed and full Unicode support. I welcome suggestions and patches regarding any aspect of this program.
03:34:19  kmc welcomes your suggestions into the trash bin.
03:36:26 -!- Jafet has joined.
03:50:54 -!- elliott has quit (Ping timeout: 240 seconds).
03:59:22 -!- mean has quit (Ping timeout: 260 seconds).
04:05:08 -!- Jafet has quit (Ping timeout: 248 seconds).
04:10:39 -!- sirdancealot7 has joined.
04:18:57 -!- sirdancealot7 has quit (Ping timeout: 252 seconds).
04:21:32 -!- Frooxius has quit (Ping timeout: 246 seconds).
04:25:12  kmc: Man, I looked up some things on Google and found #haskell logs with you and ski and all that.
04:25:15  Those were the days.
04:25:19  heh
04:25:20  yeah
04:25:25  i do miss #haskell 
04:25:28  Talking about ∃ and things.
04:25:40  i tried reasonably hard to get the good parts of it elsewhere
04:31:23  kmc: You know the way converting ∃ to ∀ is like currying?
04:32:36  i could probably come up with it, but what do you have in mind?
04:39:48  kmc: (exists a. Foo a) = forall r. ((exists a. Foo a) -> r) -> r
04:40:21  forall a. Foo a is like (a:*) -> Foo a, exists a. Foo a is like ((a:*),Foo a)
04:41:02  So ((exists a. Foo a) -> r) is like (((a:*),Foo a) -> r), and if you curry that you get ((a:*) -> Foo a -> r), so it's the same as (forall a. Foo a -> r)
04:41:43  Something along those lines, anyway.
04:42:38  ais523 also says "!" in linear logic is like comonad, too? So, it is not only me. Is it like intuitionistic logic can be a comonad on linear logic, as classical logic can be a monad on intuitionistic logic? They mention how encoding intuitionistic logic in linear logic.
04:43:27  So what happen in linear logic putting multiple "!" and/or "?" together?
04:45:00  Oh, zzo38 
04:45:10  An example of what I meant by reified lexical environment
04:45:23  In Clojure, a hash-map is {key1 val1 key2 val2} etc
04:45:39  I wrote a macro, get-lexical-env, that does this:
04:46:04  (let [a 1 b 2] (get-lexical-env)) ; returns {'a 1 'b 2}
04:46:11  Although it would print as {a 1 b 2}
04:46:43  O, that is what it means. OK
04:50:20  I don't know if that's actually a correct description of the term "lexical environment", but it's what I meant.
04:52:25  OK
04:56:35 -!- Jafet has joined.
05:00:58 -!- evincar has joined.
05:27:16  PSY vs Ghostbusters - Gangnam Busters - Mashup by FAROFF http://youtu.be/82LCKBdjywQ
05:31:04  ++
05:41:52 -!- monqy has joined.
05:47:29 -!- evincar has left.
06:40:33  I made up law of excluded middle continuations.
06:42:42  are they any useful
06:43:06  You can't prove that they aren't useless, so they are useful.
06:43:44  callCC (return . Right . (<=< return . Left)) :: ContT r m (Either a (a -> ContT r m b))     it is similar to law of excluded middle, I guess.
07:10:04 -!- FreeFull has quit (Quit: And so pie was invented.).
07:15:04  I have added some more commands in FurryScript now, including AGA IMC MC SHF
07:17:07 -!- zzo38 has quit (Remote host closed the connection).
07:33:38 -!- nooga has joined.
07:48:49 -!- sirdancealot7 has joined.
08:12:38 -!- epicmonkey has joined.
08:42:39 -!- monqy has quit (Quit: hello).
09:18:42 -!- Arc_Koen has joined.
09:20:13 -!- Arc_Koen has quit (Client Quit).
09:20:35 -!- Arc_Koen has joined.
09:20:58  hello
09:27:07 -!- ais523 has joined.
09:28:17  wb elliott
09:37:19 -!- Phantom_Hoover has joined.
09:51:32 -!- epicmonkey has quit (Remote host closed the connection).
09:51:52 -!- epicmonkey has joined.
10:23:49 -!- ais523 has quit (Read error: Connection reset by peer).
10:24:03 -!- ais523 has joined.
10:34:02 -!- ogrom has joined.
10:48:07 -!- ais523 has quit (Ping timeout: 246 seconds).
10:48:47 -!- ais523 has joined.
10:59:45  this is fucking scary: http://superchief.tv/leaked-north-korean-documentary-exposes-western-propaganda-and-its-scary-how-true-it-is/
11:00:10  Someone forgot to tell Gnesa that 0) autotune exists; 1) clown makeup looks even more atrocious in close-up. http://youtu.be/CF2o5RDkq9A
11:01:13 -!- Phantom_Hoover has quit (Ping timeout: 268 seconds).
11:05:18 -!- nortti has changed nick to protip.
11:05:28 -!- protip has changed nick to nortti.
11:17:47 -!- ais523 has quit (Remote host closed the connection).
11:19:01 -!- ais523 has joined.
11:30:40  nortti: It’s funny when it’s true.
11:43:55 -!- ais523_ has joined.
11:46:13 -!- ais523 has quit (Ping timeout: 246 seconds).
11:59:47 -!- boily has joined.
12:01:43 -!- Frooxius has joined.
12:13:16 -!- ais523_ has changed nick to ais523.
12:23:42  I know The Rock's real name!
12:32:52  mroman: But can you find Britain on a map?!
12:35:04 -!- Phantom_Hoover has joined.
12:36:24  Does he have a GPS phone?
12:38:57  Does a GPS phone transmit voice through GPS satellites? 
12:39:51  No, silly, it uses the GPS satellites to calculate your location and transmits it to spy satellites.
12:41:56  [image of Keanu Reeves] What if GPS satellites are spy satellites?
12:44:15  Jafet: I hear all phones are espionage devices that listen to you even when turned off, and transmit detailed location data too.
12:44:23  I heard this from that Stallman guy.
12:44:25  ok hopefully my emmental interpreter should be working buuuuuuut I have nothing to test it on
12:44:32  (Disclaimer: slightly exaggerated, maybe.)
12:45:16  Actual quote, for the record: "I refuse to have a cell phone because they are tracking and surveillance devices. They all enable the phone system to record where the user goes, and many (perhaps all) can be remotely converted into listening devices." http://stallman.org/rms-lifestyle.html
12:45:20  Yay, another cheesy language
12:45:36  what language?
12:45:37  fizzie: actually, that's probably true
12:45:41  Arc_Koen: You need to eat, I mean, write some emmental.
12:45:55  yes I do need to eat
12:47:10  (for the record if I ever have to take part in a conspiracy, I promise I won't take my phone with me)
12:47:11  fizzie: his statement is, of course, technically correct
12:47:30  I refuse to have a cellphone for reasons which are only very vaguely related (specifically, I don't like people being able to contact me at arbitrary times)
12:48:10 -!- Slereah_ has joined.
12:49:34  fizzie: http://www.ted.com/talks/malte_spitz_your_phone_company_is_watching.html
12:49:49 -!- Slereah has quit (Ping timeout: 256 seconds).
12:51:06  Most people probably want their phone to be able to remember where they went and what they did, anyway.
12:51:27  How about their phone company?
12:51:30 -!- ais523 has quit.
12:51:33 -!- ais523_ has joined.
12:51:40  Most people are pretty short-sighted.
12:54:42  you mean metaphorically, right?
12:54:44 -!- ais523_ has changed nick to ais523.
12:54:52  literally, I think more than half of people can focus to infinity
12:55:10  and focusing beyond infinity is not a massively useful operation (despite being technically possible, it just leaves /everything/ out of focus)
12:55:12  But you can only focus to infinity if the universe is infinite :o
12:55:34  The location-tracking is kind of obvious; I'm a bit more sceptical on any claims that phone companies / law enforcement / the gummint would generally turn phones into listening devices. (Admittedly RMS only says "can".)
12:55:40  The universe can be finite and have unbounded light lines
12:55:55  Slereah_: focusing to infinity means assuming that incoming light rays are parallel to each other
12:56:08  Yes, but how are you going to get that!
12:56:12  focusing beyond infinity is only useful if you have a lens that's making light rays more convergent and want to cancel out its effects
12:56:21  Light tends to be emitted isotropically
12:57:47  in practice, focusing to infinity is visually indistinguishable from focusing to, say, 100m
12:58:53  Mostly because your eye can't make the difference if the light rays land a nanometer apart~
12:59:55  I don't quite see how the actual incoming light would matter when discussing how your optics can or cannot focus.
13:01:32  Do you want me to make irrelevant complaints about something else, perhaps
13:02:20  hey guys I'm getting the weirdest errors
13:02:53  for instance if I try to pop an element from a queue and push it on a stack, when the queue is empty, ocaml raises exception Stack.Empty
13:07:26  http://sprunge.us/DYDR -- not for me.
13:08:06  yes I think it is reasonable to assume I'm the one doing something wrong, not ocaml
13:08:13  You just never know.
13:10:13  ok I just fixed a minor bug that was apparently completely unrelated and now it seems to be raising the proper exceptions
13:10:35 -!- ais523 has quit.
13:10:57 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
13:17:03  https://www.computerworld.com/s/article/9232477/Pacemaker_hack_can_deliver_deadly_830_volt_jolt The following people were surprised by the security problem:
13:19:45  Like wardriving but more fun
13:21:45 -!- elliott has joined.
13:22:10  Hm, same person behind http://youtu.be/bidDXuM4-2E
13:22:41 -!- ogrom has quit (Ping timeout: 255 seconds).
13:27:49  libseccomp looks really nice. http://s3hh.wordpress.com/2012/07/24/playing-with-seccomp/
13:31:13  This is like the path that goes over mountains and through five days of blinding hail to get capabilities
13:31:36 -!- copumpkin has joined.
13:33:25 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds).
13:41:34 -!- AnotherTest has joined.
13:42:07 -!- Phantom_Hoover has joined.
13:42:17  Hello
13:42:27  heroux, 
13:43:15  http://esolangs.org/wiki/WASD - oh god
13:43:28  "inspired by brainfuck"
13:46:06  Inspired by brainfuck is a code for brainfuck cypher
13:46:54  so for what is "and several other esolangs" code?
13:47:08  "with elements from"
13:47:28  also which ones? (except for all other brainfuck equivalents)
13:48:04  But then again, I once made an esolang based on unlambda because I didn't like lazy evaluation
13:48:13  In this regard, I would like to suggest that brainfuck equivalents will no longer be listed in the manually maintained language list
13:48:17  Although I tried mixing it up by adding lambda calculus
13:48:40  Hmm.
13:48:54  Slereah_: did you ever figure monads out
13:48:56  Having rewritten the argument I'm not sure that he specified the same loop semantics as Brainfuck.
13:49:03  s/argument/article/
13:49:04  Brainfuck equivalents are EQUIVALENT to brainfuck, thus they shouldn't be considered separated pages
13:49:11  elliott : Hell, I didn't even look up esolangs in months
13:49:45  Phantom_Hoover:"If pointer is set to 0 loop starts"
13:50:13  Phantom_Hoover: he probably wanted to say "If the value at the pointer is set to 0"
13:52:32  Alright his input is different
13:53:04  He reads integers rather than characters
13:54:54  and you can't nest loops because his implementation sucks
13:57:09  " in order to create a language that would be quick to program"
13:57:18  Yeah, definitely
13:57:43 -!- TeruFSX has quit (Read error: Connection reset by peer).
13:58:21  This is a shame for the wiki
13:59:00 -!- Phantom__Hoover has joined.
13:59:32  there is not really limited space
13:59:41  are http://esolangs.org/wiki/Snack and http://esolangs.org/wiki/Esme better because they're not bf derivatives
13:59:58  AnotherTest: Did you check the WASD interpreter? It's... kinda curious, when it comes to loops. Can't say I've ever seen that particular approach yet.
14:00:17  elliott: At least they are not listed on the language list!
14:00:38  fizzie: yes, I have (unfortunately) seen it
14:01:42  AnotherTest: you are wrong
14:01:49  snack is listed on the languag elist
14:01:49  elliott: well snack is
14:01:51  *language list
14:01:56  esme is not
14:02:10  snack shouldn't be listed either
14:02:17  http://esolangs.org/wiki/FURscript another bad language unrelated to brainfuck
14:02:28 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds).
14:02:29  and that should be on the language list, not the joke language list; it clearly has semantics, just stupid ones
14:03:28  I must agree
14:03:53  but I must also say that I never said that only brainfuck equivalents were often bad
14:04:04  There are lots of other bad languages
14:04:53  well the language list should not be an arbiter for taste... the featured language thing was meant to highlight some of the better esolangs but it hasn't been updated in ages because apparently I and all the other admins are lazy as sin
14:05:05  arguably there should be a separate list for brainfuck derivatives just because there are so many of them, but idk
14:05:52  I just noticed the case of "WASD", the creator cannot even implement loops. You can as well ask a 5 year old to think of a nice way to write the brainfuck operators.
14:06:27  elliott: I'm talking about equivalents here, not deriatives, may that be clear (there are many very nice deriatives)
14:06:40  s/deriatives/derivatives
14:07:04  didn't you just find out its semantics are different :p
14:07:09  I guess the interpreter might be equivalent though
14:07:55  But where not intended to be different; I'm pretty sure the author just didn't understand brainfuck or couldn't make a proper implementation
14:10:23  If a new visitors clicks the language list and chooses a random language at this moment, chances are getting higher (because of such languages) it's going to be a worthless language
14:11:04  suspect people are more likely to click random page
14:11:28  anyawy a list of good esolangs would certainly have value, though it's of course completely subjective... the wiki has traditionally been open to every language no matter how crappy though
14:11:50  suggestion: have a bf substitutions page
14:11:54  and, unfortunately, there are an awful lot of crap esolangs... far outweighing the good ones
14:11:55  but that's just how it is
14:12:08  AnotherTest: Be fair, it implements *a* loop.
14:12:09  it's a giant table of the name of the language, the command substitutions, and author name etc
14:12:34  There's quite a few interpreters that don't get nested loops. (Although this was the first one that duplicated essentially the whole interpreter for the insides of the loop.)
14:13:05  delete all pages for substitutions except the one or two with historical interest (by which i mean ook)
14:13:08  First one I've seen, I mean.
14:13:22  Phantom__Hoover: you could have at least read the interpreter before making an incorrect edit
14:13:22  elliott: That people can create crappy pages: OK if you really want it like that; but that they are all in the same language list: definitely not OK.
14:13:55  there should be a QA process -- Quintopia Approval :p
14:14:00 -!- FreeFull has joined.
14:14:10  (at least one of my langs is already certified)
14:14:17  AnotherTest: well feel free to come up with some objective criteria for whether an esolang should be on the list or not... the closest thing I can think of is some kind of vote, which would be terribly un-wiki and slow things down immensely and generally result in stagnation IMO
14:14:35  elliott: so I will make a brainfuck interpreter were you input real numbers, and it will be an entirely new concept?
14:14:40  besides, it would be dishonest to portray the esolangs community as mostly full of quality languages... it is a mixed bag and that's how it's always been
14:15:17  AnotherTest: I don't claim to make any judgement of whether it's entirely new or not... it would probably be uninteresting and I wouldn't like it, although real numbers are a vaguely interesting premise for a BF derivative (depending on what +-[] do)
14:15:52  elliott: I'm pretty sure the author of WASD didn't even realize q was different.
14:15:56  still, I don't see how you can just say "the language list shouldn't list unoriginal languages" without realising how impractical that is
14:15:58  Psh
14:16:03  Make it complex numbers
14:16:42  hmm, wasd doesn't actually allow for nested loops
14:17:11  elliott: I realize that, but it might still be possible to filter out a number of cases; such as were one language can be converted to another by simply replacing characters
14:17:36  AnotherTest, that only ever happens with brainfuck though.
14:18:07  well at least that would get rid of the dozens of brainfuck equivalents
14:18:45  i still prefer my idea
14:18:47  the closest thing I can see as being viable is to have a section on the joke language list for languages that are very very close (intentionally so) to existing esolangs
14:19:01  if you think that'll make the average language on the main list good though you're out of your mind :)
14:19:36  what do we need to form a language? syntax, sematics..and..
14:19:55  What about something like a good language list? I know it's unpractical to realize, but it doesn't have to be a large list either.
14:20:07  http://esolangs.org/wiki/Esolang:Featured_languages
14:20:21  you need to define rules for it or people will just put their own languages on and you'll have dumb revert wars over matters of opinion of whether a language is good or not
14:20:34  elliott: I think there are more than 2 good languages
14:20:41  main problem is almost all ideas are either too much overhead/work (and hence they stagnate), or open to that kind of nonsense
14:20:47  featured language process has the former
14:21:03  feel free to put a better proposal for a collection of recommended languages on the community portal, it would be welcomed
14:21:38  speaking of bad languages, seems like good old !!!Batch got an update
14:21:48  what would we do without shubshub
14:24:00  Personally I think that the languages on the "good language list" should be implemented. I realize that some very good languages have not yet been implemented, although visitors should be able to try out these "good languages".
14:25:01  syntactics, semantics and pragmatics.. finally got it
14:25:13  shut up hagb4rd 
14:25:56  and it should have a decent specification (either external or on the wiki); this means, for example, that you can't capitalize every word(Like With !!!Batch Really)
14:28:04  The language may also not be a semantic equivalent of another language
14:29:49  How much of a problem are these unoriginal languages right now?
14:30:22  As long as there is a way to filter the good languages from the bad languages they are not a problem
14:30:35  but there is currently not a good way to do it
14:30:57  so I think they're a pretty big problem when you want to find nice languages
14:32:13  wow Phantom__Hoover 
14:32:21  did you edit WASD wiki page?
14:32:24  Oh, another requirement should be that the language is not a vague idea, but rather is actually well defined etc.
14:32:34  did you actually CONTRIBUTE to that brainfuck-derivative??
14:33:01  i don't quite understand why everyone is reacting so strongly here, you guys realise trivial brainfuck ciphers are nothing new right :P
14:33:21  Brainfuck is the most trivial cipher of brainfuck
14:34:07  elliott: something about a straw and a camel, I reckon
14:35:40  your backs should have broken years ago
14:36:11  btw I think Ook! was an awesome idea
14:36:18  it wasn't
14:36:36  it was a funny joke at the time for about 20 minutes
14:36:48  it's just the 36 zillion that came after that were bad ideas
14:38:13   and it should have a decent specification (either external or on the wiki); this means, for example, that you can't capitalize every word(Like With !!!Batch Really)
14:38:20  these sound basically like the rough featured language criteria i wrote ages ago
14:39:13  elliott: I should probably read those, it might be a good source of inspiration
14:39:22  and only two languages were good enough??
14:39:54  Arc_Koen: how about read the process before making assumptions
14:40:03  that was a joke
14:40:12  it relied on admins do sift through them every now and then and that didn't happen because it means main page blurbs have to be written for the language
14:40:21  and that's difficult and annoying and nobody ever wants to do it :p
14:40:24  so it's laid dormant for months
14:42:58  "If pointer is set to 0 loop starts" uh, does that mean "if the pointer points to the first cell"?
14:43:30  Zeroth cell
14:43:37  Assuming there is one
14:46:50  uh, his interpreter seems to do awful stuff
14:50:22  doesn't seem to
14:50:24  it does
14:50:28  in particular I think the instruction pointer will never wander beyond the first end loop
14:50:47  elliott: I have a list of 7 requirement
14:50:51  +s
14:51:28  http://esolangs.org/wiki/Esolang_talk:Community_portal#List_of_.22good.22_languages
14:51:49  your mission, if you accept it, is to find those 7 requirements, and destroy them using enchanted swords and other basilisk fangs.
14:52:09  "This message will self destruct in 60 seconds."
14:52:18  "semantically equivalent" rules out TC languages
14:52:37  let me modify that
14:52:46  I wasn't clear
14:53:43 -!- augur has quit (Remote host closed the connection).
14:53:57  hey seriously if your secret agents require a whole minute to read their assignment I doubt they will be a match against the great evil we're all fighting
14:54:02  "The language may not be convertible to another language by a series of simple substitutions."
14:54:31  elliott: Is that better?
14:54:38  better, certainly
14:54:42  not good enough!
14:54:49 -!- augur has joined.
14:54:53  see http://esolangs.org/wiki/Maze
14:54:59  it can be converted to brainfuck easily
14:55:09  uh, wait, the opposite
14:55:19 -!- augur has quit (Remote host closed the connection).
14:55:33  in fact, you're basically ruling out all turing tarpits
14:55:56  You can't convert Maze by simple substitutions
14:56:09  You have to preform additional semantic checking
14:56:12  no, I mean, you can convert brainfuck into Maze by simple substitutions
14:56:46  oh yes
14:56:47  hm
14:57:56  well Maze is much more recent that brainfuck but that's not the point, for instance brainfuck can be converted into C easily
14:58:24  Yeah
14:58:46  By replacing one lexeme with another lexeme from the other language?
14:59:06  (note: by just one lexeme)
14:59:18  i have a great idea
14:59:28  how about you take brainfuck but the cells have like complex values
14:59:37  ouh, great idea
15:00:04  in fact I had a hard time not saying the exact same thing a few minutes ago
15:00:05  that's ruled out by another rule :)
15:00:45  AnotherTest: the "just one lexem" thing allows languages like "unary brainfuck" in
15:01:00  I mean, what "one lexeme" is is easily abusable
15:01:05  darn, clue doesn't fit the specification
15:01:17  because it's page is a joke.
15:01:30  oklofok, you mean there are two versions of + and -
15:01:31  Arc_Koen: unary brainfuck doesn't meet all the other requirements
15:01:39  which are orthogonal to each other
15:01:59  Phantom__Hoover: yeah gaussian integers because all the other complex numbers are just silly
15:02:14  true - but then can you think of one language that is ruled out by 4 but not by 5?
15:02:14  oh yes! i needed your guidance
15:02:37  i hung out with that elliott one and he peer pressured me with constructivism
15:02:58  now i have nagging doubts whenever i do proofs by contradiction
15:03:07  constructivism? lol try finitism. in fact fuck finitism, i'm a singletonist.
15:03:19  Arc_Koen: No, but 4 is easier to determine objectively.
15:03:28  what is 2 anyway
15:03:30  what is 1
15:03:32  what are numbers
15:04:29  well a cell in brainfuck is just a simple 256-state automaton
15:05:01  lol nihilism is just silly, i'm a singletonist to the bone. as we singletonists say, cogito ergo sum, but that's it.
15:05:08  AnotherTest: how about "is not a close derivative of another language"
15:05:23  also known as solipsism then i guess.
15:05:49  Arc_Koen: you can add it an 8th rule
15:06:51  how bout group by affinities in the instruction set or sth
15:06:58  is that not essentially 4?
15:07:02  no I intend to strongly argue that it is redundant with 4 and 5 and at least one of the three should not be included
15:07:08  oh actually not 
15:07:26  but perhaps what Arc_Koen said
15:07:34  or maybe we should make a list of requirements for a requirement to be featured in the requirement list
15:09:22  "semantically equivalent" was interesting - that'd probably leave us with a list of computational models, plus deadfish
15:09:53  oh and also a few like banana scheme and twoducks
15:11:47  oklofok: singletonism, eh?  As in forall x y, x = y?
15:12:53  I have a tendency to prefer axiom systems capable of expressing themselves.
15:12:56  totally
15:13:52  Let x = x.  Is x an element of x?
15:13:53  tswett: you're out to complete gödels incompleteness theorem?
15:14:02  or at it least to extend it
15:14:20  hagb4rd: no, I'm not sure what you're getting at.
15:14:25  the heck does "Let x = x." mean
15:14:35  Arc_Koen: it means "let x be a value such that x = x".
15:14:48  what's a value
15:14:52  also shut up hagb4rd 
15:15:06  yep
15:15:06  tswett: the heck is x
15:15:18  Arc_Koen: a value such that x = x.
15:15:19  ^_^
15:15:40  tswett: the heck is x
15:15:52  I'M STUCK PLEASE HELP ME
15:16:07  A value equal to itself?
15:16:14  oh, ok
15:16:20  lol
15:16:26  Alternatively, let me restate.
15:16:32  True or false: For all x, x is an element of x.
15:16:49  see that would have been much more simple to answer with nihilism
15:17:31  (but honestly who needs a set theory when there is only one element?)
15:17:32  "There's no such thing"?
15:17:55  well all statement starting with "for all" would be true
15:18:31  at least better then false
15:18:38  Hm.  So, here's a simple set theory.  I'll call it Zero.
15:18:46  the would be fatalism i guess
15:18:48  The axioms of Zero: "For all x, x != x."
15:19:05  i came up with a complete consistent axiomatization of number theory
15:19:24  kmc: neat!  Does it prove its own consistency?
15:19:32  sure
15:19:39  i just take every true statement of number theory as an axiom
15:19:41  it's so easy!
15:19:54  Hm.  I like it.
15:20:11  kmc, what if it's inconsistent
15:20:18  WHAT IF YOU'RE INCONSISTENT
15:20:23  Hm, let me ponder that system.
15:20:49  this is why goedel's incompleteness theorem says there is no complete, consistent, *recursively enumerable* axiomitization of number theory
15:20:55  but people forget about the third condition
15:21:02  To be fair, kmc, you're not recursively enumerable.
15:21:04  Burn?
15:21:16  nah i'm a finite object
15:21:20  What counts as a "statement of number theory"?  Is it simply a statement quantified over the natural numbers whose predicates are addition and blah blah blah?
15:21:37 -!- glogbackup has quit (Ping timeout: 246 seconds).
15:21:39  "yo momma so fat she's a strongly inaccessible cardinal"
15:22:21 * hagb4rd pulls on his kmc shirt
15:22:51  It puts the lotion on its skin?
15:23:33  no, it lights on in the dark
15:24:33  Yo mama so fat, the set {{x} where x ∈ yo mama} has a cardinality strictly smaller than that of yo mama.
15:24:49  also it levels up charisma by 1 if worn in set with the mkc boots
15:25:10 -!- augur has joined.
15:25:45  uh, is that possible?
15:26:23  please don't say "fsvo 'strictly smaller'"
15:30:21  AnotherTest: what if the complex numbers in my brainfuck derivative are encoded as polynomials to which they are roots?
15:30:49  would that be a unique enough concept?
15:31:21  how are you manipulating them then
15:31:46  by factoring them
15:31:59  (yeah hum currently the implementation is unavailable)
15:32:40  maybe with coefficients?
15:39:42 -!- AnotherTest has left.
16:14:46 -!- Phantom__Hoover has quit (Ping timeout: 244 seconds).
16:32:54  Arc_Koen: it's not possible in ZFC, since there's a bijection { (x, {x}) where x ∈ yo mama}.
16:33:29  what's zfc? (and why am I asking?)
16:33:49  http://en.wikipedia.org/wiki/Zermelo%E2%80%93Fraenkel_set_theory
16:37:35  is ur mama a urelement?
16:37:59  Zermelo Fried Chicken
16:38:21  Does someone join a mostly empty Dropbox shared folder? I'll get this 250 MB "Get Started" reward if I get a fifth step done in this stupid thing. (Made stupider by the fact that I'm not even going to use the deebee for anything.)
16:38:25  I can drop an in-Finnish religious proselytization note I found on the ground in Järvenpää into the folder to sweeten the deal.
16:38:34  Well, a photo of one, anyway.
16:40:15  fizzie: what is deebe
16:40:16  e
16:41:06  Dropbox.
16:43:53  fizzie: i'll do it if you give me the note irl
16:43:54  post it
16:44:32  I didn't actually pick it up. I thought then I'd be depriving someone else of God and whatnot.
16:44:37  The next one to walk that way, I mean.
16:44:58  so I just put a slice of bread in a frying pan, with grated cheese on top of the bread, and an egg on top of the grated chease
16:51:56 -!- ogrom has joined.
17:03:28  as I feared, the slice of bread got completely burnt before the egg was properly baked
17:04:07  next time I'll try putting the egg under the toast, or something
17:05:28  You can also put it beside the toast.
17:06:06  or maybe make it an egg sandwich
17:06:19  and when the egg is half-baked, I flip it
17:07:02  I wonder if that's how they do paninis
17:08:53  Don't those usually get made in those grill-on-both-side machines? 
17:09:05  http://en.wikipedia.org/wiki/File:Professional_panini_machine.JPG you know, that kind of things.
17:10:33  Also thanks a whole lot, now I'm terribly hungry.
17:14:51  Panini was also the first esolanger :V
17:21:04 -!- Phantom__Hoover has joined.
17:46:10 -!- zzo38 has joined.
18:01:21 -!- augur has quit (Read error: Connection reset by peer).
18:01:44 -!- augur has joined.
18:16:21  fizzie: yes during the whole thing I was wondering if there was anything I could use to heat the egg from above
18:21:26  uh
18:21:33  are you experimenting in advanced egg-cooking
18:21:50  It was more about sandwich-making.
18:28:36  anyway see you later guys
18:28:52 -!- Arc_Koen has quit (Quit: Arc_Koen).
18:51:22 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds).
18:55:00 -!- augur has quit (Read error: Connection reset by peer).
18:55:19 -!- augur has joined.
18:59:23 -!- ogrom has quit (Quit: Left).
19:37:01  fizzie: Of course I can find Britain on a map.
19:37:23  If the map has names on it then I also can locate Afghanistan.
19:38:40  It's a pretty big country.
20:04:27  if it's a map of afghanistan I can probably locate it
20:13:13 -!- Phantom__Hoover has joined.
20:24:20  If it's a map of great britain I can locate it perfectly.
20:24:48  I'm quite good at locating Afghanistan on maps of Great Britain too
20:24:56  neither am I
20:25:54  I just have to abuse a little trick from classic logic.
20:26:06  12:47:30:  I refuse to have a cellphone for reasons which are only very vaguely related (specifically, I don't like people being able to contact me at arbitrary times)
20:26:12  oh my god someone else who hates phones
20:26:33  who the fuck thought it was a good idea to invent a device that allows people to blindly pester you whenever they like
20:26:47  Well
20:26:53  Bell
20:26:57  according to the north korean propanda movie
20:27:05  an iPhone changes everything!
20:27:28  Nice typo.
20:27:35  I don't think they like pandas.
20:27:56  if they don't like pandas why would they make propanda movies?
20:28:06  To please china?
20:28:10  (obviously)
20:28:19  ah, right
20:29:51  i hate pandas
20:31:28  Blasphemie.
20:55:57 -!- MoALTz has joined.
21:01:09 -!- Frooxius has quit (Quit: ChatZilla 0.9.89-rdmsoft [XULRunner 1.9.0.17/2009122204]).
21:06:56 -!- Frooxius has joined.
21:38:48 -!- augur has quit (Remote host closed the connection).
21:42:45  shachaf: What type f has f (a,b) = Either a b?
21:43:49  elliott: Is there such a type?
21:44:22  Is there?
21:44:28  What type f has f (Either a b) = (a,b)?
21:44:44 -!- MoALTz has quit (Quit: Leaving).
21:45:25  Why would these types exist?
21:45:37  Why would anything exist?
21:46:32  elliott: woah, dude
21:46:41  we already had this conversation today dammit
21:46:49  But, really, why does that make sense?
21:46:49  shachaf: profound, isn't it?
21:46:57  elliott: "I could do this with recursion, but since I'm doing this in Haskell, I'd like to understand the monads. The State Monad is probably the best for this job, I suppose?"
21:47:01  shachaf: I don't know. Do you make sense?
21:47:07  elliott: Sometimes I do.
21:47:22  shachaf: Anyway if you defined f (Either a b) = (a, b) as a type family what would you call it?
21:47:24  And what does it mean?
21:47:37  elliott: Oh, a type family.
21:47:40  That's not at ype.
21:48:09  if it's not at ype, where is it?
21:48:25  olsner: oerjan would never say that.
21:48:31  That's why you should be more like oerjan.
21:49:05  shachaf: I didn't mean a type family before.
21:49:22  So F (Either a b) = (a,b)
21:49:31  Do you know anything else about F?
21:50:20  shachaf: oerjan would never make fun of at ypo?
21:50:24  shachaf: Well, ideally F (forall r. (a -> r) -> (b -> r) -> r) would be isomorphic to (a, b).
21:50:52  @context elliott
21:50:53  Unknown command, try @list
21:51:33  I'm just wondering.
21:52:01 -!- hagb4rd has quit (Quit: hagb4rd).
21:53:39 -!- sirdancealot7 has quit (Ping timeout: 268 seconds).
21:54:13 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
22:02:16  Then how can F be if it is possible to make that working?
22:02:28  I have no idea, honestly.
22:02:44  elliott: What do you want it for?
22:03:35  elliott: Is there a "log" function such that f (a,b) = Either (f a) (f b)?
22:03:36  Is it possible, even? If not with intuitionistic logic, is it possible with linear logic, or other logical systems? Would F do anything else other than just this?
22:03:44  shachaf: I don't want it for anything.
22:03:54  I don't know if there's such a log. But that sounds cute, so let's go with: yes.
22:04:07  shachaf: Const Void satisfies log.
22:04:14  elliott: I know.
22:05:24  elliott: What's the other thing you need to satisfy log?
22:05:39  Something like log 1 = 0?
22:06:19  Presumably.
22:06:33  I have tried before to make logarithm of types but I don't think it can be done?
22:06:36  You have b^log_b(a) = a. So Log a -> b should be iso to a. Problem: what's b?
22:06:51  I don't think that even makes sense.
22:06:57  b has to be constant; you can't extract any info out of the result.
22:07:00  It looks like callcc.
22:07:15  shachaf: Anyway Const Void satisfies log 1 = 0 too.
22:07:52  shachaf: Log (a -> b) ~ (a, Log b).
22:07:53  I don't think you can make a base of natural logarithms as a type, though
22:08:00  15:07  shachaf: once upon a time I had this idea that log corresponded to "paths" in data structures
22:08:03  Does Const Void satisfy that? I guess yes.
22:08:03  15:07  shachaf: e.g. a path to a value in an (a,b) structure is either a path to an a, or a path to a b.
22:08:05  Since (a, Void) is Void.
22:08:06  15:07  shachaf: but I couldn't quite make it all work out nicely.  but I'm still convinced there's something interesting there.
22:08:32  elliott: I have a feeling you're missing a point here.
22:08:40  Maybe, try something, see
22:08:48  Or are you trying to come up with a rule for log that Const Void doesn't satisfy?
22:09:42  shachaf: Yes.
22:09:42 -!- boily has quit (Read error: Connection reset by peer).
22:11:51  elliott: Also, Log_b (a -> b) = a? That doesn't even make sense.
22:12:34  shachaf: I think forgetting about "b" here is ideal.
22:12:38  It seems misleading.
22:12:47  (But it does seem to make sense somehow...)
22:12:48  elliott: Makes sense.
22:12:57  What about Bag x = e^x?
22:13:00  (If you take b as some kind of continuation token, then the formulae involving b seem to make sense.)
22:13:03  Wait, no, we figured out that that was nonsense.
22:13:14  15:12  shachaf, heh, that looks an awful lot like de morgan's law
22:13:49  15:12  cmccann: You have 5 new messages. '/msg lambdabot @messages' to read them.
22:13:52  15:12  D:
22:14:03  elliott: Stop making cmccann's life painful.
22:14:19  that was my fault
22:14:32  Phantom__Hoover: Oh, and you.
22:14:53  I sent two; Phantom__Hoover sent one.
22:15:02  If there's any more then either it's someone else or Phantom__Hoover decided to be more annoying than usual.
22:15:08  15:14  did elliott finally lose it after all those lambdabot messages and start spamming everyone? :D
22:16:05  shachaf: This is great. It's like being in #haskell except all the lines have wrong timestamps on them.
22:16:13  elliott: /join #haskell
22:16:21  Why?
22:16:40  To fix your timestamps.
22:16:45  Otherwise I'll have to keep pasting.
22:16:51  15:15 -!- gnuvince [~vince@ip-50-21-138-141.dsl.netrevolution.com] has joined #haskell
22:16:54  15:15 -!- clahey is now known as cl_away
22:16:57  15:15 -!- zhulikas [~Derp@195.181.64.50] has quit [Ping timeout: 246 seconds]
22:16:59  15:15  cmccann: Hey, it does.
22:17:02  15:16 -!- corruptmemory [~jim@h-64-236-128-62.nat.aol.com] has joined #haskell
22:17:45  15:17:15  heh, so I guess f ~ ((->) Void)  works
22:17:57  you know, if any of us wanted to be in #haskell we'd be in #haskell
22:18:01  (Void -> a -> b) ~ (a, Void -> b)?
22:18:05  Is that true?
22:18:08  That's not true.
22:19:06  Oh, it's (-> Void).
22:19:10  (-> Void), yes.
22:19:24  ((a -> b) -> Void) ~ (a, b -> Void).
22:19:34  not (a implies b) = a and not b
22:19:43  Isn't that true in classical logic?
22:20:11  (0^x) is pretty close to (const 0) :-(
22:20:14 -!- copumpkin has joined.
22:20:20   You have b^log_b(a) = a. So Log a -> b should be iso to a. Problem: what's b?
22:20:23  Also let's say b = Void.
22:20:27  (Log a -> Void) ~ a
22:20:30  ((a -> Void) -> Void) ~ a
22:20:32  not not a ~ a
22:20:38  snazzy
22:20:46  So it is for classical logic only, I guess.
22:20:50  OK, now we can not think about Log ever again.
22:21:13  Can't have logs base 0.
22:23:16  15:21  byorgey: (-> Void) = (0^), which is worryingly close to (const 0)
22:23:22  15:21  It doesn't really behave like a logarithm in terms of most things you expect from a logarithm, I think.
22:23:30  15:21  Then again it's hard to do that while staying discrete. :-)
22:24:07  what timezone are those timestamps in?
22:24:17  GMT+shachaf
22:24:26  is that a couple of minutes ago or 9 hours ago?
22:24:28  More like GMT-shachaf
22:24:38  olsner: A couple minutes ago.
22:25:54  anyway, what's exponentiation in types?
22:26:03  (->)
22:26:06  a^b = b->a
22:27:49  Just like with sets!
22:28:02  which is just iterated product!
22:28:19  Which is just iterated iterated sum!
22:29:10  which is just iterated iterated iterated succ!
22:30:22  which is just iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated iterated
22:30:26  stack overflow
22:36:33  I wasn't listening before, but was there any use for this Log thing except trying to figure out what it might mean?
22:37:12  oh, and shouldn't it be Log b a or something? just guessing that the base should be involved somewhere
22:37:30  olsner: Real logarithms don't have bases.
22:37:37  really?
22:37:48  Really.
22:37:56  wow
22:37:58  log_b(x) is just log(x)/log(b) so
22:38:08  yah
22:38:23   I wasn't listening before, but was there any use for this Log thing except trying to figure out what it might mean?
22:38:23   15:07  shachaf: once upon a time I had this idea that log corresponded to "paths" in data structures
22:38:25   15:07  shachaf: e.g. a path to a value in an (a,b) structure is either a path to an a, or a path to a b.
22:38:26   15:07  shachaf: but I couldn't quite make it all work out nicely.  but I'm still convinced there's something interesting there.
22:38:36  15:38   15:07  shachaf: once upon a time I had this idea that log corresponded to "paths" in data structures
22:39:54 -!- augur has joined.
22:39:57  and log is the length of the path?
22:40:33  no, Log t would be the path itself
22:40:38  type of paths
22:46:25 -!- impomatic has joined.
22:47:13  alright, I am slep
22:47:16  tell me if you ever figure it out though
22:52:48  I want to make a Clojure-like language that gets some inspiration from Tcl.
22:52:53  But the name....
22:53:06  Tclj comes to mind, but that makes it look like it's primarily based on Tcl.
22:53:11  I might call it Cloqure.
22:53:17  Clojure with a lot of quote marks
22:56:34  pikhq, is [uplevel] generally hated?
22:58:18 -!- nooga has quit (Ping timeout: 264 seconds).
23:07:34  16:06  shachaf: btw, logarithms are easy for representable functors
23:07:42 -!- Arc_Koen has joined.
23:08:10 -!- sirdancealot7 has joined.
23:08:11  hello
23:08:49  elliott: do you know what that is :'(
23:09:11  shachaf: yes
23:09:41  Someone suggested Tclojure
23:10:18  [[
23:10:19  For a long years Archlinux WAS my favorite linux distibutive. Because it was simple and powerfull, flexible configurabe. It was really best choise for home and for server! And now, archlinux turning into ....even not Unbutu, Arch turning into Windows!!
23:10:19  RIP, beloved ARCH!
23:10:19  P.S.: I WISH LENNART POETTERING TO GO TO HELL!!!
23:10:19  ]]
23:10:51  Arch turning into Windows!!??
23:10:54  oh no!!
23:11:15  lennart poettering?
23:11:18  What next, gates turning into basements?
23:11:28  yet another linux derivative
23:11:45  Phantom__Hoover: he's this guy who to goed to hell after someone flamed him on the arch linux forums
23:11:46  hope it's not a simple substitution
23:11:52  https://bbs.archlinux.org/viewtopic.php?pid=1175809#p1175809
23:11:54  oh ok
23:11:59  next time include the link :'(
23:12:01  how is arch turning into windows btw
23:12:13  in an AWFUL way
23:12:14  Phantom__Hoover: well all windows users to go to hell on a regular basis
23:12:40  "this guy who to goed to hell"
23:12:42  Hmm, Lennart Poettering wrote PulseAudio.
23:12:51  like, "to to go to hell" is a verb?
23:13:00  Sgeo: Uh, not so much "hated" as it is "use sparingly".
23:13:03  Arc_Koen: if this post is any metric, then yes
23:13:25  well I can live with that
23:13:36  shachaf: yes
23:13:46  as long as nobody starts to coming from hell
23:13:48 -!- Phantom_Hoover has joined.
23:14:04  pikhq, similarly to how in Lisps, people are expected to use macros sparingly?
23:14:18  pikhq, and I'm thinking more in terms of, do alternatives exist
23:14:29  (that was supposed to be a joke but I think it's broken)
23:14:59  Sgeo: Not really.
23:15:07  If you want custom control structures you need uplevel.
23:15:26  (because tcl is bad)
23:15:27 -!- copumpkin has changed nick to BinderFullOfWome.
23:15:37  pikhq, I don't mean within Tcl, I mean as far as language features go
23:15:42  well you have to keep your wome somewhere
23:15:49  can't just have it lying all over the place
23:15:50 -!- BinderFullOfWome has changed nick to BinderOfWomen.
23:15:50  That would still give me pervasive eval + lexical scope
23:15:54 -!- BinderOfWomen has changed nick to copumpkin.
23:16:09  is that a binder containing women, or is it someone who binds women?
23:16:27 -!- copumpkin has changed nick to BinderOfBigBird.
23:16:28 -!- Phantom__Hoover has quit (Ping timeout: 260 seconds).
23:16:44  BinderOfBigBird: hi
23:16:52  hey
23:16:57  oh god not another bird fetishist
23:17:11  http://manuel.github.com/wat-js/doc/manual.html
23:17:15  BinderOfBigBird: Three rings to bind them all?
23:17:24  yes
23:17:25  kmc, ^
23:17:44  kmc, v
23:18:00  kmc: <
23:18:10  Well, more like
23:18:13  kmc: ☚
23:19:20  beware the turing tar pits
23:19:35  oh wait, I was trying to make a pun by merging "turing" and "ring"
23:19:52  ah, the famous ring tar pits
23:20:05  see, it doesn't work
23:20:31  Tarring turpids
23:20:39  tarring turnips
23:21:02  well you understand my joke anyway and assuming we share some common sense of humour, you're free to go ahead and laugh even though the pun failed
23:21:16  or better pretend it went right!!
23:22:41  hey can I add Emmental to the list of featured language candidates?
23:23:45  assuming you did not create it
23:24:21  are you kidding it's chris pressey's
23:25:06  idk maybe you are chris
23:25:10  `pastelogs ZOMGMODULES
23:25:25  MAYBE I AM
23:25:38  http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.9977
23:26:40  2011-04-05.txt:20:38:24: * ZOMGMODULES IS ZOMGMODULES
23:26:48  if only we still had chris around to dispense wisdom like this
23:27:05  i
23:27:13  Maybe I should make wat running on node.js my new favorite language.
23:27:15  i've forgotten chris' last name :'(
23:27:18  Phantom_Hoover: pressey
23:27:20 * Phantom_Hoover looks up a few lines
23:27:24  right, pressey
23:27:48  Sgeo: ooooh
23:28:18  2011-04-05.txt:21:39:53: * ZOMGMODULES SAYS ONLY EXACTLY WHAT ZOMGMODULES MEANS
23:28:18  2011-04-05.txt:21:40:18: * ZOMGMODULES DISMISSES TSWETTBOT!!!!
23:28:19  Phantom_Hoover: you hang around with brainfuck-equivalent designers too much
23:28:38  why do you hurt me so ;_;
23:28:57  2011-04-05.txt:22:54:21:  YES
23:28:57  2011-04-05.txt:22:54:23:  YES YES YES
23:28:57  2011-04-05.txt:22:57:01:  THIS IS HOW CHILDREN LEARN
23:30:00  kmc: 16:29  Boston has some good burritos.
23:30:00  16:29  dolio: As good as SF?
23:30:00  16:29  I don't know.
23:30:16  kmc: You're clearly the one to answer this.
23:30:17  i like beantown taqueria
23:30:19  it's close to my house
23:30:22  i was just there
23:30:32  Wtf is tswettbot.
23:30:42  luite is in FS.
23:30:44  SF
23:30:48  That place with the burritos.
23:30:50 -!- BinderOfBigBird has changed nick to copumpkin.
23:31:08  hm if i enumerate eight different ways of complaining about brainfuck-equivalent esolangs, then...
23:31:20  tswett: something you made in 2k11
23:31:34  Wtf is 2011.
23:31:43  2k11 = 22,000
23:31:48  yes
23:31:50  2.011k = 2011
23:31:52  I remember no such year as 2011.
23:32:19  i have invented a language where each line is a transcript of something said in #esoteric complaining about brainfuck-equivalent esolangs
23:32:47  is it a brainfuck equivalent
23:33:04  each line performs an operation equivalent to one of brainfuck's <>+-,.[] according to the number of the day on which the thing was first said, mod 8
23:33:25  I have invented a language where Phantom_Hoover = [, elliotit = ], shachaf = <, kmc = >, tswett = -, pikhq = +, oerjan = ,, olsner = .
23:33:38  Sorry oerjan. :-( You got the worst operator.
23:33:45  kmc: does that mean your language evolves every time someone complains about brainfuck equivalents?
23:33:47  elliotit
23:33:51  Oh, and operators have to be enclosed in <>
23:33:55  shachaf: do you also have a giant chessboard and 32 silly outfits?
23:34:07  Arc_Koen: yeah, though old programs should keep the same meaning
23:34:19  elliott: "oopse"
23:34:38  "ddoublle lleterss are hard"
23:34:39  elliotit: the wiki server backed by the elliott content tracker
23:35:06  kmc: that's just esolangs.org
23:35:10  so we're developing brainfuck-equivalent supersets of brainfuck-equivalents? EVEN WORSE
23:35:11  kmc: More like the elliot content tracker.
23:35:17  that's like being brainraped
23:36:16  wait I was supposed to put "we create brainfuck-equivalents against our will" in one of the sentences before, otherwise the joke doesn't work
23:36:24  did I just fail three jokes in a row?
23:36:44  kmc: Today I overheard people talking about their social photo-sharing app for iOS.
23:39:13 -!- elliott has left ("Leaving").
23:41:57 -!- Nisstyre has quit (Quit: Leaving).
23:42:12  isn't that every day in the bay area
23:42:28  \
23:42:34  Pretty much. :-(
23:42:38  No newline at end of file
23:42:45 -!- Nisstyre has joined.

2012-10-18:

00:11:46  shachaf: people elsewhere are talking about the best bagels in san francisco
00:12:31  apparently http://www.deliboardsf.com/ has secret bagels
00:12:40  which are boiled in new york, baked in SF, and not listed on the menu
00:13:00  On the other hand there's http://idlewords.com/2007/04/the_alameda-weehawken_burrito_tunnel.htm
00:14:08 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:15:33  Someone asked a question in #clojure about whether the stdlib includes a feature
00:15:52  As far as we can tell, it's both a really bad idea and impossible. But my language would make it possible.
00:16:00  That sort of makes me take pause.
00:17:33  Someone linked to http://www.ioccc.org/2012/tromp/hint.html 
00:20:37 -!- sirdancealot7 has quit (Ping timeout: 246 seconds).
00:24:39  Hmm, I think the scoping I have in mind is technically dynamic but with a function to essentially temporarily clear currently bound stuff
00:24:48  http://store.valvesoftware.com/product.php?i=CP201
00:26:01  ++
00:26:24  Is something like this too ugly?
00:26:28  space gotta go to space
00:26:48 -!- sirdancealot7 has joined.
00:26:49  (defn foo '[a b c] '(level '(+ a b c)))
00:26:55  In terms of needing that level there?
00:26:59  Wait, hmm
00:27:11  o.O that level is in a very wrong place
00:29:08  is that scheme?
00:29:17  Of course not.
00:29:26  It's Clojure. You don't even need to read it to know that it's Clojure.
00:29:27  oh
00:29:34  The nick is enough.
00:29:43  oh
00:30:13  Not Clojure
00:30:26  It's a variation based on Clojure + Tcl
00:30:33  Unsure how I'm going to deal with lexical scoping
00:31:47 -!- Frooxius has quit (Ping timeout: 240 seconds).
00:32:40  Is this ugly?
00:32:49  (deflfn '[a b c] '(+ a b c))
00:32:51  it looks like scheme
00:32:52  Translates to
00:32:54  how could it be ugly
00:33:08  deflfn is a weird word though
00:33:20  (def '(level '(fn '[a b c] '(+ a b c))))
00:33:59  also for the ioccc link you provided - that looks like it's Real Fast Nora's Hair Salon 3: Shear Disaster Download
00:34:09  It occurs to me that defn and anything similar should be providing a name
00:34:18  (def 'foobar '(level '(fn '[a b c] '(+ a b c))))
00:34:26  (deflfn 'foobar '[a b c] '(+ a b c))
00:35:49  with LAMBDA as 00, APPLY as 01, ZERO as 10 and ONE MORE THAN as 1
00:38:49 -!- monqy has joined.
00:40:38  I am slowly turning into Gamzee.
00:40:58  That reminds me. Arc_Koen, keep reading Homestuck.
00:41:07  yeah hum maybe
00:41:16  I mean I liked the humour
00:41:25  buuuut it was kind of repetitive and slow
00:41:39  It speeds up
00:53:10 -!- sirdancealot7 has quit (Ping timeout: 246 seconds).
01:02:27  's a shame the mailing list doesn't exist any longer
01:20:14  If I don't have true lexical scoping, but do have an easyish way to effectively say "Hey, consider this a separate scope", is that sufficient for a language to be comfortably usable?
01:21:19  ???
01:26:20 * Sgeo is suddenly not sure if he's reinventing picolisp or not
01:26:57  Hmm, I'm... not sure
01:27:20  what are you doing and why
01:27:38  monqy: ask not what are you doing and why, but what aren't you doing and why not
01:27:39  Language based off Clojure and Tcl where conditionally printing looks like
01:27:52  (if blah '(println "true") '(println "false"))
01:27:58  For example
01:28:07  Tcl-esque
01:28:30  have fun i guess
01:32:59  why wouldn't you have lexical scoping though
01:33:02  i bet it's a bad reason
01:33:34  "i bet you're a bad person" - "monqy'"
01:33:46  sssh baby steps
01:34:16  monqy: HEY THAT WAS MONQY PRIME
01:34:17  not you
01:34:20  ok?
01:34:40  ok
01:35:37  get it?
01:35:39  got it
01:35:40  good
01:50:42  kmc: 00000000-0000-0000-0000-000000000000 is a perfectly valid UUID!
01:50:53  It could've come about as random chance.
01:50:54  Stop reading into things.
01:51:43  kmc: So IOCCC 2012 is done.
01:51:51  When's your contest coming along?
01:53:03  shachaf: guaranteed to be chosen at random
01:53:30  oh IOCCC 2012 is done?
01:53:39  i had a good idea for an entry
01:53:41  next year i guess
01:54:17  kmc: http://www.ioccc.org/years.html#2012
01:54:39  18:51  https://raw.github.com/gist/3909430/377bfe9b1a62e1c74acac0ec32ca4261c66379cd/%F0%9D%94%93%F0%9D%94%AF%F0%9D%94%A2%F0%9D%94%A9%F0%9D%94%B2%F0%9D%94%A1%F0%9D%94%A2.hs
01:55:10  ion: Why doesn't that export most of the identifiers?
01:56:19  I forgot.
02:07:47 -!- pikhq has quit (Read error: Connection reset by peer).
02:09:08 -!- pikhq has joined.
02:28:08 -!- jfguest has joined.
02:38:38 -!- jfguest has quit (Quit: leaving).
02:45:39 -!- Arc_Koen has quit (Quit: Arc_Koen).
02:46:59 -!- Max00355 has joined.
02:48:15  Is it possible to write to a file with brainfuck?
02:50:11 -!- pikhq_ has joined.
02:50:16 -!- pikhq has quit (Ping timeout: 244 seconds).
02:53:09 -!- Max00355 has quit (Ping timeout: 260 seconds).
03:02:46 -!- Max00355 has joined.
03:05:31 -!- zzo38 has quit (Remote host closed the connection).
03:15:47  BACK IN THE DAY, SON, WE DIDN'T HAVE FILES
03:15:54  AND EVERYTHING WAS IN UPPERCASE
03:16:03  BACK IN THE DAY WE DIDN’T HAVE SONS
03:19:51  Max00355, well, you could direct the output of a brainfuck interpreter to a specific file
03:20:06  Or you could use something like PSOX, although I abandoned it before hammering out the file stuff
03:28:42  ion++
03:28:44  that is amazing
03:30:42  http://i.imgur.com/6QpIO.png
03:31:00  kmc: https://gist.github.com/3909452
03:33:51  nice
03:37:10  Interesting, the gist title was cut off from the first non-BMP character.
03:43:49  Max00355: Brainfuck itself has no particular mechanism for doing so.
03:44:46  that's why you should always use brainfuck implementations where the tape has finite size and the array indexing is not bounds-checked
03:44:52  then you can write to files
03:45:16  now i wanna write a brainfuck JIT spray
03:52:02  So, let me blab about NFU.
03:52:18  NFU is that set theory where comprehension is allowed for any "stratified" formula.
03:53:10  So {x where x = x} is a valid set.  It contains everything.  {x where {} is a subset of x} contains all sets.  {(x,y) where x is a subset of y} is a valid set.
03:53:30  {x where x is not in x} is not a valid set, because "x is not in x" is not a stratified formula.
03:54:33  Stratified comprehension is the bulk of NFU.  It has an axiom, the axiom of choice, that is equivalent to a function with a certain property.
03:55:05  Equivalent to the existence of such a function, I mean.
03:55:11  It has another axiom, the axiom of counting, which isn't obviously equivalent to the existence of a function at all.
03:58:04  If S is a set, let Box(S) = {{x} where x in S}.
03:58:19  The axiom of counting states that if S is finite, then S has the same cardinality as Box(S).
04:03:05  The "obvious" way to express that as a function is to say that if S is finite, then there is a bijection between S and Box(S).  But that sounds really dangerous.
04:11:47 -!- sivoais has quit (Quit: leaving).
04:12:17 -!- sivoais has joined.
04:16:44 -!- FreeFull has quit.
04:49:45 -!- Jafet1 has joined.
04:51:10 -!- Jafet has quit (Ping timeout: 265 seconds).
04:56:04  is there pine tar flavored bread in finland
04:58:53  kmc: johnw of #haskell-blah is on the C++ committee, voting on C++14 features.
04:58:57  You're missing the fun.
04:59:10 -!- zzo38 has joined.
05:04:14  jesus
05:04:17  what's new in C++14
05:04:57  Apparently they were voting on "return { 10 };" syntax today.
05:05:39  Which, if your return type is a class, calls the constructor of the class?
05:11:26  Lots of other things.
05:42:34 -!- impomatic has quit (Quit: http://BASICcomic.com).
05:52:28 -!- FireFly has quit (Excess Flood).
06:00:04 -!- FireFly has joined.
06:51:18 -!- AnotherTest has joined.
06:51:26 -!- AnotherTest has left.
07:04:17 -!- Phantom_Hoover has joined.
07:14:06 -!- Jafet1 has quit (Quit: Leaving.).
07:25:28 -!- epicmonkey has quit (Remote host closed the connection).
08:02:54 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
08:04:50 -!- zzo38 has quit (Remote host closed the connection).
08:10:54 -!- nooga has joined.
08:23:30 -!- epicmonkey has joined.
08:30:04 -!- Jafet has joined.
08:55:55 -!- sirdancealot7 has joined.
09:04:45 -!- epicmonkey has quit (Remote host closed the connection).
09:04:55 -!- epicmonkey has joined.
09:15:47 -!- monqy has quit (Quit: hello).
10:11:49 -!- Phantom_Hoover has joined.
10:21:31  What exactly can brainfuck be used for besides printing out some ASCII characters? 
10:23:01  inputting ascii characters
10:23:21  Calculating exciting stuff.
10:23:24  ^pow2
10:23:25  1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384 32768 65536 131072 262144 524288 1048576 2097152 4194304 8388608 16777216 33554432 67108864 134217728 268435456 536870912 1073741824 2147483648 42949672 ...
10:23:31  See, that's from brainfuck.
10:23:41  Making benchmarks against your new language
10:24:07  Getting brain-bricked, via the "make a derivative language, wait a few seconds" plan.
10:24:50  ^rainbow Not to forget the prettiest rainbows.
10:24:51  Not to forget the prettiest rainbows.
10:26:24  And then there's always the highly vibrant brainfuck adventure game development community. There's Lost Kingdom, and... well, I guess Lost Kingdom.
10:27:41  Can it be modded?
10:28:21  I seem to recall it was mostly automatically generated, so the code isn't perhaps too edit-friendly.
10:28:50  The source is 2189420 bytes long.
10:30:38  I bet most games aren't that big.
10:33:53 -!- ais523 has joined.
10:57:45 -!- ais523_ has joined.
10:57:50 -!- ais523 has quit.
10:59:01 -!- ais523_ has changed nick to ais523.
11:20:00 -!- atriq has joined.
11:38:38 -!- olsner has quit (*.net *.split).
11:43:02 -!- olsner has joined.
12:02:47 -!- boily has joined.
12:09:15 -!- Arc_Koen has joined.
12:09:34  hello
12:09:55  Hey
12:10:31  moi
12:10:46  bonjour mein freundes
12:11:00 -!- pikhq_ has quit (Ping timeout: 265 seconds).
12:11:18  is this international day or something?
12:11:44  Da.
12:11:49  ad nibelung des moines
12:11:53  Internation indoeuropean day
12:12:08  wow, Chris Pressey's back
12:12:28  and it looks like he wants to make it up for the time he was missing!
12:16:50  "mascarpone"
12:16:59  so that's why someone said "another cheesy language" yesterday
12:17:15  netbsd 6.0 released!
12:23:44  where
12:24:06  In its natural habitat, one hopes.
12:24:08  Back into the wilds of Northern Scotland
12:24:43  atriq: Do you have roaming bands of BSDs in Scotland? 
12:25:05  fizzie, nah, they're quite solitary
12:25:23  I'm too far south to get them here, though
12:31:02  northern scotland, or as literally everyone else calls them, the highlands
12:31:39  Is that where the HIGHLANDERS fight? 
12:36:57 -!- ais523_ has joined.
12:37:14 -!- ais523 has quit (Read error: Connection reset by peer).
12:40:44  bon matin à tous! I'm wearing my http://www.amazon.com/Save-Planet-Learn-Proto-Indo-European-T-shirt/dp/B0087LFWDY t-shirt today!
12:47:30  fizzie, no, they do that in new york
12:47:52 -!- ais523_ has changed nick to ais523.
12:59:16 -!- atriq has quit (Ping timeout: 246 seconds).
13:16:49 -!- atriq has joined.
13:18:42 -!- elliott has joined.
13:30:57  ais523: ping
13:30:57  elliott: You have 2 new messages. '/msg lambdabot @messages' to read them.
13:51:46 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
14:10:14  UK court says Apple must now run adverts in major British papers and leave a banner on its website for 6 months saying Samsung isn't a tablet-design copycat. (zdnet.com)
14:10:15  i
14:10:36  [[Apple has lost an appeal against Samsung in the U.K. after the first judge claimed the Galaxy Tab 10.1 could not have infringed the iPad because it wasn't "cool" enough.]]
14:10:37  im
14:12:11 -!- copumpkin has joined.
14:38:36 -!- function has changed nick to constant.
14:41:03 -!- copumpkin has quit (Remote host closed the connection).
14:53:59  hahaha
14:54:27  wait is this real life you're talking about
14:54:46  Surreal life
14:55:44  i had an english teacher who pronounced surreal 'sooral'
14:56:15  Soo ray al?
14:58:32  yes
14:58:57  she also pronounced poem 'poeeyem' but that's weirdly common in scotland
15:00:53  Did she pronounce "film" with two syllables?
15:01:15  probably
15:03:30 -!- copumpkin has joined.
15:05:27  like "fillem"?
15:05:45  Yes, or "fillum"
15:06:01  nah, that's just you pronouncing fillem wrong!
15:06:06  :P
15:06:24  anyway see you later
15:06:28  See ya
15:06:43  oh and give a look at that mascarpone language it looks great
15:07:03  (was looking for a slightly more expressive adjective than just "great" but hey)
15:07:46  how about "awesome"
15:08:35  there's no page on the wiki. is there any public info floating somewhere on mascarpone?
15:11:13  Possibly the same thing as Emmental, not sure
15:19:10 -!- zzo38 has joined.
15:21:23 -!- Vorpal has joined.
15:37:09 -!- ais523 has quit.
15:38:12  Thinking about Featured Languages
15:41:18  I'm gonna suggest not Underload, because Glass is stack based too
15:41:48  I might put my weight behind Malbolge
15:44:59  It's quite different to Glass and ///
15:45:03  It's got examples
15:45:21  It's got a specification
15:46:46  It's implemented
15:50:03 -!- augur has quit (Remote host closed the connection).
15:52:06 -!- hagb4rd has joined.
15:53:45  atriq: are you planning to become an admin
15:53:50  do you want to be in charge of featured languages
15:54:06  I don't know if I can be trusted with the responsibility!
15:54:47 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
16:03:06 -!- copumpkin has quit (Ping timeout: 264 seconds).
16:06:24  Do you have a pipe organ?
16:08:33  I do not!
16:08:50  I have an electric keyboard with 2 pipe organ voices, though
16:09:04  atriq: Two????
16:09:08  Yes
16:09:14  Pipe Organ 1 and Pipe Organ 2
16:09:47  Also, Synth Organ and Jazz Organ
16:12:05  atriq: fancy
16:12:43  atriq: Do they sound different???
16:12:48  I don't know
16:12:51  I want to hear Pipe Organ 1 and Pipe Organ 2. How do you make two separate pipe organ voices.
16:12:58  how can you not know!!
16:14:05  Well, I suppose they could have different stops, different swell shades, etc
16:14:05  Hmm
16:14:14  Pipe Organ 1 sounds bolder, Pipe Organ 2 more italic
16:14:22  I think that only makes sense for me
16:18:10  atriq: i'm going to have to demand audio here
16:19:00  I'm gonna have to refuse or at least arbitrarily delay
16:21:14  harsh
16:21:20  i will never know the smooth sounds of pipe organ 1 & 2
16:21:24  "More italic", is that like as in the cursive typeface? 
16:23:52  fizzie: Hey, how's that thing?
16:25:28  What, what, WHAT. There's no "things".
16:28:44 -!- copumpkin has joined.
16:32:55 -!- atriq has quit (Ping timeout: 252 seconds).
16:34:02  fizzie: Are you sure??
16:36:38 -!- mindlessDrone has joined.
16:36:52  hi
16:37:18 -!- ais523 has joined.
16:38:00 -!- FreeFull has joined.
16:38:23  elliott: http://www.youtube.com/watch?v=k-jRj8qXpag#t=1m40s
16:39:36  `welcome mindlessDrone
16:39:48  mindlessDrone: 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.)
16:41:02 -!- augur has joined.
16:41:22  They tell you that it's the international hub, but really there are only two countries: Hexham and Finland.
16:41:29  (And I'm not Hexhammish!)
16:41:51  Hexland and Finham.
16:46:12  No, some people of esolang are Canada, too.
16:47:05  Some people of esolang are *alleged* to be Canada.
16:47:14  (Innocent until proven guilty and all that.)
16:47:34  zzo38: What is there in Canada, really, once you take out the Hexham and the Finland?
16:50:18 -!- copumpkin has quit (Ping timeout: 256 seconds).
16:50:27  shachaf: Canada.
17:04:02 -!- Phantom_Hoover has joined.
17:13:53 -!- AnotherTest has joined.
17:14:02  hello
17:17:24 -!- atriq has joined.
17:18:10  fizzie, yes
17:20:13 -!- atriq has quit (Client Quit).
17:22:12  I'd ask how it translates to sound, but I might not want to hear the answer.
17:27:06  I'm in England but not Hexham
17:27:38  OMG this is a programming language? I thought this is hardcore esoteric like walking over water
17:27:58  I can walk in water
17:28:06  And over water if there is a bridge or something
17:28:16  ^^
17:29:02  Can you walk on water if frozen to make ice?
17:29:27  I'm back from lunch and what do I know? people here doubting my canadianness.
17:29:57  mindlessDrone: What did you want about walking over water, anyways?
17:30:27  Esolang is not in itself a programming language, but rather involves prorgamming language; see wiki for information
17:30:49  don't know ..i want to know how jesus may felt
17:31:50  try nailing yourself to some wood
17:32:00  xD
17:32:32  i try to read the wiki ..but its so much text ...
17:34:18  It is supposed to be so much text ...
17:35:30  zzo38: No, I slip
17:39:04 -!- oklofok has quit (Ping timeout: 246 seconds).
17:40:37  There's that thing.
17:41:16  http://dsc.discovery.com/gear-gadgets/man-attempts-walking-across-sea-in-a-human-sized-hamster-wheel-photos.html
17:41:22  That thing, maybe that's a bit Jesusy.
17:41:33  I mean, kind of, sort of.
17:42:26 -!- copumpkin has joined.
17:42:37  awesome
17:43:21  And anyway wasn't he a carpenter's son or something? I mean, adopted, if you can call it that. I'm sure he could've fiddled together something like that.
17:44:05  Maybe a slightly more creakier version but still.
17:47:33  sure ..sounds plausible
17:48:05 -!- nortti has changed nick to []{}\|-_`^.
17:48:10  It is also possible that they mistaken him, they misremembered, they added the walking on water for metaphorical purposes, and various other things, including but not limited to, divine magic
17:48:53 -!- []{}\|-_`^ has changed nick to nortti.
17:51:36  a german comedian once sayed "maybe he was just buying water" because in german buying and walking are rhyming
17:52:35  indeed.
17:53:28 -!- WeThePeople_ has joined.
17:57:07 -!- epicmonkey has quit (Ping timeout: 246 seconds).
18:00:02  FreeFull: Um...
18:00:07  England is *in* Hexham.
18:00:39 -!- nortti has changed nick to ^[.
18:00:51  nortti has escaped the dungeons of doom.
18:01:02 <^[> :P
18:01:25  Many electronic piano/synthesizer have only a few fixed settings and cannot be changed much, sometimes there are a few possibilities.
18:01:35 -!- WeThePeople_ has quit (Read error: Connection reset by peer).
18:02:00  zzo38: http://ampnoise.com/mp3/MusicOnThePDP-1X_Pinafore.mp3
18:02:25 -!- ^[ has changed nick to [-].
18:02:36 -!- [-] has changed nick to ^[.
18:02:52  I wrote on paper some 32 byte registration of digital synthesizer, including FM section, additive section, square section, saw/triangle section, organ section, percussion section, and global section.
18:04:10 -!- ^[ has changed nick to nortti.
18:06:16  And then you can have multiple manuals, each with their own registration, and pedalboard, as well as other pedals and other controls
18:07:16 -!- oklopol has joined.
18:12:45  hmm, I think I hit my personal record for getting a Slashdot post modded up to +5
18:12:48  it was less than 5 minutes
18:12:56  (second post on an article about a court case, linking to the verdict)
18:17:34  wow, I'm already old enough to have difficulty comprehending just how fast computer storage is increasing
18:17:49  you can get a 64GB SD card for a reasonably affordable price, for insance
18:17:52  *instance
18:18:20  I grew up with floppy disks (5¼" were the most common when I started using computers, but 3½" were the first I really started using)
18:19:09  I never ued a 5¼" floppy disk. :-(
18:19:24  that was before I started using PCs
18:19:24  But I remember 3½" fondly, of course.
18:19:33  SD cards don't freak me out as much as microSD cards. Aren't those up to at least 32G now too? 
18:19:47 * shachaf has a 32GB microsd card.
18:19:58  PCs were quite common when I was young, but didn't have anywhere near the market share they do nowadays
18:20:03  It used to be in my phone but now my phone doesn't have a microsd slot.
18:20:05  That gives me the shivers.
18:20:36  fizzie: You can get 64GB microsd these days.
18:20:53  That's, like, double-shivers.
18:21:04  It's the size of a fingernail.
18:21:08  my primary school used primarily Acorn computers, together with some BBC Micros
18:22:24  The "parallel class" (not sure what's the term; same grade, a different group) in primary school had a PC. We were kinda jealous.
18:22:27  I don't like SD card much, though, especially the small ones which don't have a write protect switch.
18:22:40  (On the other hand, we took more class trips.)
18:23:01  Their PC ran Windows 1.02; this was in the higher grades.
18:23:21  Hmm, 32gb microsd is down to $20.
18:23:29  the computers in my secondary school were PCs, mostly running Windows 95; some were on Windows 3.11, and they upgraded to 98 after a while
18:23:53  They also had a directory with "high-ascii" (sorry for the misnomer) characters in it, with Leisure Suit Larry 1 (I think) and some other games hidden in it.
18:24:07  See, the teachers couldn't get in there.
18:24:31  i used a bbc micro in playschool
18:24:33  pretty sure it was obsolete then
18:24:39  elliott: it probably would have been
18:24:41  You had to memorize the numbers to type with alt-NNN. One of them was the empty space, too.
18:24:43  since this was like late 90s-early 2000s :P
18:24:47  about the time I finished secondary school, they decided to get rid of their BBC Micros
18:24:54  so they sold them to their students for £20 each
18:25:03  in year 1 or so we had an acorn(!!)
18:25:04  we bought one and played with it for a while; I learned 6502 asm on it
18:25:14  BBC Micro? That sounds like the future.
18:25:21  the B and Y keys were broken, but that wasn't impossible to deal with
18:25:31  because function keys were rebindable
18:25:33  Then they installed that Windows 1, and the MS-DOS Executive let you navigate to any directory. It was a problem.
18:25:51  you could get the B via copying-and-pasting from the "BBC" tagline it printed when it loaded
18:25:57 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds).
18:26:10  for Y you had to write a short BASIC program
18:26:15  oh right, I presumably even knew the Micro was obsolete, since I got a computer before then...
18:26:18  Sounds like an esolang.
18:26:21  (it ran windows 3.11)
18:26:27  shachaf: it wouldn't be a very good one
18:26:32  (did you know: windows 3.11 is not very good)
18:26:43  HEY
18:26:44  HEY
18:26:47  Windows 3.11 is awesome.
18:26:50  elliott: I actually enjoyed 3.1, it did what it was intended to do quite well
18:26:50  ais523: how long did it take you to relearn how to type on a keyboard with b and y where they are rather than on the fkey row
18:26:52  didn't use 3.11
18:26:57  http://upload.wikimedia.org/wikipedia/en/c/c4/Interface_age_scan_nov_1983_p30_bbc_micro_ad.jpg
18:26:57  elliott: not very long, actually
18:27:07  I'm quite used to keys changing places when I move to a different keyboard
18:27:08  Same school where I was called to the principal's office, which was a bit worrisome, but then they just had printer problems.
18:27:10  Gregor: i used windows 3.11 when i was 3, i'm the expert
18:27:14  That looks pretty great.
18:27:19  elliott: I did too, I think!
18:27:24  fizzie: heh, I only got called to the headteacher's office when they wanted to reward me
18:27:29  the punishment was mostly done by other people
18:27:44  shachaf: that sounds unlikely
18:27:50  shachaf: well I guess you aren't that much older than me
18:27:58  I'm pretty sure I did.
18:27:59  and also windows 95 had been out for a few years by the time i got that thing anyway
18:46:12 -!- mindlessDrone has left.
18:59:36  Also remember not to SMARTDRV your Windows 3.1 system disk, because it will cause the loader to just eat a chunk of the Windows logo and choke.
18:59:51  Not SMARTDRV.
18:59:58  What's the online disk compression tool.
19:00:19  DBLSPACE, I mean.
19:01:03  (You can certainly SMARTDRV it.)
19:02:36  Apparently it's a valid configuration if you jump through the right hoops.
19:02:39  Didn't work out for me, though.
19:04:23 -!- AnotherTest has quit (Quit: Leaving.).
19:04:38 -!- AnotherTest has joined.
19:04:43  smartdrv was the disk cache thing?
19:05:35  Yes.
19:05:53  Doublespace played all kinds of weird tricks with hidden volumes called h: and whatnot.
19:07:43  Also loadlin, that's so nifty. My first dual-boot box had its dual-boot done by keeping DOS in the MBR, then using the fancy DOS 6 [menu] menuitem boot menu things to automagically blarp with loadlin.
19:08:22  loadlin is cool
19:08:22  And umsdos, isn't that even niftier? I think I had a slackware umsdos installation.
19:08:27  (Then it went bork.)
19:08:33  what's umsdos
19:09:23  It's the thing that lets you put Unixy things like uids and gids into a plain directory of a FAT filesystem, so that you can have your root in C:\LINUX.
19:09:55  It puts the extra data into a FAT file called --LINUX-.---.
19:10:09 -!- epicmonkey has joined.
19:10:23  Then you can go peek at your /etc as C:\LINUX\ETC\ in DOS land.
19:10:36  And of course ruin everything if you mess with things there too much.
19:11:16  Goes well with loadlin: no partitioning, no boot loader messing-up-with, no nothing. You just enter the drag^HLinux from dos.
19:11:40  I suppose compared to ext2 there might have been some slight performance issues maybe.
19:15:42 -!- copumpkin has quit (Ping timeout: 255 seconds).
19:25:15  Try Jumping http://youtu.be/VSttd3edW98
19:29:11  fizzie: drag^HLinux = draLinux?
19:29:46  Uh, ^W.
19:30:19  (Though "draLinux" doesn't sound like an unreasonable name for a distribution.)
19:30:22  I was trying to find info on this draLinux on google
19:30:28 -!- AnotherTest1 has joined.
19:30:32  I found nothing
19:30:42  The rules state you must now make it.
19:31:10 -!- AnotherTest has quit (Read error: Connection reset by peer).
19:31:39  fizzie: good. I had no name for my distro
19:33:21  fizzie: should I use 2.4 kernels so I could use umsdos?
19:38:47 -!- AnotherTest1 has quit (Quit: Leaving.).
19:39:14 -!- pikhq has joined.
19:39:20  I, uh. I wouldn't, but you are certainly free to.
19:40:11  ok. I'm going to use mastodon linux as a starting point
19:40:44  hmm… YouTube top comment is a warning not to read the rest of the comments
19:40:49  YouTube's self-awareness is scary sometimes
19:41:04  I read the first page of actual comments, they mostly just said that the comments were fine again now
19:41:11  lol
19:42:04 -!- AnotherTest has joined.
19:42:37  Don’t you dare offer free education to our residents! http://chronicle.com/blogs/wiredcampus/minnesota-gives-coursera-the-boot-citing-a-decades-old-law/40542 Meanwhile: http://www.startribune.com/business/164349766.html
19:45:35  I wonder how well modern linux software will work with gcc 2.95 and libc4
19:45:56  2.95 might work.
19:46:03  Actually.
19:46:06  Depends on the program.
19:46:15  Some stuff will work just fine, some stuff depends on C99.
19:46:26  and libc4?
19:46:34  Same issue.
19:46:40  C99 libc.
19:46:46  Also pthreads.
19:46:51  linux 2.0 :D
19:46:51  if you are using gcc 2.95 and libc4 then presumably you are enough of a neo-luddite to not want to use modern linux software
19:47:15  Linux 2.6.0 is the first (official, stable) version of Linux where you can have correct pthreads.
19:47:29  And 2.4.0 is the first where you can have threads that almost work if you squint.
19:47:32  (IIRC)
19:47:40  I'll use 2.4 then
19:47:56  (pssst, you want to use musl)
19:48:15  but why?
19:48:19  :P
19:48:38  LinuxThreads/libc5 was a working combination for threads, at least, pre-NPTL. I don't quite know about libc4 and threads.
19:48:51  fizzie: Very non-conformant though.
19:48:58  and musl doesn't build with 2.95 if I remember correctly
19:49:03  POSIX, schmosix.
19:49:06  +gcc
19:49:14 -!- copumpkin has joined.
19:49:46  as if any of the programs using threads are correct enough that you could tell that the thread implementation is broken
19:50:17  I am still not sure if I want to make draLinux a serious distro or not
19:50:36  fizzie: Each thread in LinuxThreads has a different pid.
19:50:44  ugh
19:50:50  that. is. horrible
19:50:50  This isn't a *subtle* non-conformance error, it's a Big one.
19:50:55  why?
19:51:41  wait. is thread implementation part of kernel or part of libc on linux?
19:52:00  Part of libc, *but* with some support needed from the kernel.
19:52:10  hmm
19:52:22  2.4 doesn't support the flag for clone that indicates the new process needs the same PID as the parent.
19:53:01  patch it
19:53:04  ksplice it
19:53:10  Can we make the Imakuni?'s card in Dungeons&Dragons game?
19:53:21  should it be hard to fix? I have not really poked anything newer than linux 0.2
19:53:39  Red Hat 9 backported it.
19:53:52  You could probably just filch their patch.
19:53:58  what about RHEL3?
19:54:16  I always read RHEL as RHELL
19:54:22  RHEL3 was derived from Red Hat 9.
19:54:22 -!- ais523 has quit (Remote host closed the connection).
19:54:25  So, I assume so.
19:54:25  yes that's how it's often pronounced too
19:54:36  ksplice never worked on 2.4 to my knowledge
19:54:44 -!- ais523 has joined.
19:54:59  Well, yeah. 2.4 to 2.6 involved Huge Changes.
19:55:26  nortti: Anyways, you should use musl because it is the Best Libc Ever. :P
19:55:56  pikhq: ok. If I can get it to compile with something ancient I'll give it a shot
19:56:02  well so does 2.6.9 to 3.4 and ksplice supports that whole range :)
19:56:05  but yeah
19:56:07  nortti: Builds with PCC.
19:56:17  going back to 2.4 would be a bigger deal still
19:56:31  pikhq: isn't pcc c89 only?
19:56:40  No, it's been updated to C99.
19:56:46  good
19:56:52  that is worth a try
19:57:09  linux 2.4+toybox+pcc+musl
19:57:38  Should the Haskell programs in their own pages in esolang wiki to use literate Haskell format so that you can download the file and then it will work?
19:58:20  GCC 2.95 however is C89-only. ;)
19:58:30  yeah
19:58:40  Fair warning, you cannot build Linux with PCC.
19:59:07  are you a bad enough dude to build linux with pcc
19:59:18  I probably need both pcc and tcc and patches for linux or gcc 2.95
19:59:52  or, you know
19:59:53  gcc 4
20:00:01  of course not
20:00:08  that would be rational
20:00:51  when I'm going to use linux 2.4 and coreutils without cp why not use ancient/obscure compilers
20:01:21  +?
20:01:45  and it will of course use umsdos and loadlin
20:02:13  The better option would be to pay landley to do qcc.
20:02:25  hmm. yeah
20:02:58  but wouldn't it have the same problem as pcc (lack of gcc specific stuff)?
20:03:24  What he wants to do with it is make it usable as the only compiler in his Aboriginal Linux project.
20:03:38  (and he considers it a regression if he can't build Linux From Scratch using that)
20:03:49  that sounds good
20:04:05  now to find out where and how I can send the money
20:04:23  And realize that paying a guy to do something fulltime for a few months is pricy. :P
20:04:42  yeah...
20:05:26 -!- AnotherTest has quit (Quit: Leaving.).
20:05:35  so qcc was tcc frontend bolted to qemy code generator, right?
20:06:07 -!- AnotherTest has joined.
20:07:47  And then the frontend boosted like crazy.
20:07:50  And then binutils.
20:08:08  Because, in short, "fuck GNU"
20:08:39  yes
20:08:55  I also hope toybox gets cp and mv soon
20:08:56 -!- AnotherTest has left.
20:09:16  using sash for those things in my minidistro is getting annoying
20:09:38  does it really not have cp and mv
20:09:59  On landley's todo list up there with "get email working".
20:10:04  it does have those but those are broken
20:10:09  elliott: Nah, it's a relatively new project.
20:10:28  And landley's spent the past year unable to work on it as much as he'd like.
20:11:16  For Dungeons&Dragons game (and for Icosahedral RPG) I could make up the "Imakuni?'s" spells like the Imakuni?'s cards, and I could make up the "Kjugobe's" psionic powers like the psionic powers that would be made up by my character.
20:12:58 -!- atriq has joined.
20:13:16  zzo38: why would anyone bother to memorize an Imakuni?'s spell?
20:13:23  (also, why would anyone embed a question mark in their name?)
20:14:53  ais523: In case you are strange you would do those things, I suppose.
20:15:33  But it may occasionally find useful as you would any spells, so you might want to write on the scroll to use as a scroll.
20:18:20  I wrote a dupdog interpreter because I was bored
20:18:24  And I've no idea if it works
20:26:54  "ॐኙ┯䩛钳𒥣𥋃񊖃򔬃*** Exception: Prelude.chr: bad argument: 1218051"
20:27:05  That's meant to say "Hello, World!"
20:27:15  Close enough.
20:27:17  I think my program is wrong
20:32:16  1218051 is *so close*, it's almost a characer. I mean, relatively speaking. They do go up to 1114111.
20:36:25  ion: U+006D   LATIN SMALL LIGATURE RN   [m]
20:39:36  Verily.
20:41:55  @remember shachaf U+006D   LATIN SMALL LIGATURE RN   [m]
20:41:56  Okay.
20:42:29  Why do they call them like U+006D instead of U+6D?
20:43:19  On the other hand, now that we have U+1F773 ALCHEMICAL SYMBOL FOR HALF OUNCE, why isn’t it U+0006D?
20:44:08  It's some kind of a thing that it's max(4, needed) characters.
20:45:50  > chr 'a'
20:45:51  (We do sort-of have U+100000  too, so maybe it should be U+00006D.)
20:45:51    Couldn't match expected type `GHC.Types.Int'
20:45:51          against inferred type ...
20:45:55  > chr 1000
20:45:56    '\1000'
20:46:02  > chr 1114111
20:46:04    can't find file: L.hs
20:46:08  Heh.
20:46:09  > chr 1114111
20:46:11    can't find file: L.hs
20:46:18  What does that error mean
20:46:38  It's the let-definitions file, isn't it? 
20:46:52  Possibly some sort of a race condition. Normally it's a very transient error, though.
20:46:55  > chr 1114111
20:46:56    '\1114111'
20:47:03  "There, I fixed it."
20:47:10  (Full disclosure: I did nothing to fix it.)
20:47:37  > map chr [0..]
20:47:38    "\NUL\SOH\STX\ETX\EOT\ENQ\ACK\a\b\t\n\v\f\r\SO\SI\DLE\DC1\DC2\DC3\DC4\NAK\S...
20:47:47  > map chr [32..]
20:47:48    " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefg...
20:47:57  I like how it has the ASCII control character names.
20:48:03  > map chr [127..]
20:48:04    "\DEL\128\129\130\131\132\133\134\135\136\137\138\139\140\141\142\143\144\1...
20:48:50  > map chr [255..]
20:48:51    "\255\256\257\258\259\260\261\262\263\264\265\266\267\268\269\270\271\272\2...
20:49:01  It's not going to print them, is it
20:49:48  It doesn't look that way.
20:50:00  > "Ā"
20:50:02    "\256"
20:50:06  Works as input, though.
20:51:04 -!- Vorpal has quit (Ping timeout: 246 seconds).
20:51:05  From what I recall, it disallows unallocated code points in string literals, if not escaped, due to some reason related to not getting the lexical information about the characters from the unicode character database.
20:51:34  > "࿿"
20:51:35    :
20:51:35       lexical error in string/character literal at chara...
20:51:39  Right.
20:51:42  > "♥"
20:51:43    "\9829"
20:51:51  > "\♥"
20:51:52    :
20:51:52       lexical error in string/character literal at chara...
20:51:57  > "\♥"
20:51:58    :
20:51:58       lexical error in string/character literal at chara...
20:52:04  iOS6 maps? http://i.imgur.com/aaVkk.jpg
20:52:08  > "\u0342"
20:52:09    :
20:52:09       lexical error in string/character literal at chara...
20:52:12 -!- nys has joined.
20:52:13  > "44"
20:52:15    "44"
20:52:23  ion: Maybe they're just resting.
20:52:42  > "\x0342" -- maybe what you wanted?
20:52:43    "\834"
20:53:05  > "\\♥"
20:53:06    "\\\9829"
20:53:23  > ord '♥'
20:53:24    9829
20:53:51  Anyway, there are control character names (maybe slightly less standard) for 0x80..0x9F, IIRC, they could've added those names too, is what I was supposed to say after trying the 127.. thing.
20:56:10  http://www.adequatelygood.com/2010/3/JavaScript-Module-Pattern-In-Depth lambda the ultimate
20:57:25  > sqrt (-1)
20:57:26    NaN
20:57:46  > 1/0
20:57:47    Infinity
20:57:54  > -1/0
20:57:55    -Infinity
20:58:03  > (-1/0) + (1/0)
20:58:04    can't find file: L.hs
20:58:28  > sqrt (-1) == sqrt (-1) -- the nans strike again
20:58:29    False
20:58:36  > (-1/0) + (1/0)
20:58:37    NaN
20:58:57  > sqrt -1 * 0
20:58:58    Overlapping instances for GHC.Show.Show (a -> a)
20:58:58     arising from a use of `...
20:59:09  > sqrt (-1) * 0
20:59:09    NaN
20:59:22  Ok, multiplying by zero doesn't get rid of it
20:59:27  > sqrt (-1) :: CReal
20:59:31    mueval-core: Time limit exceeded
21:00:07  > sqrt ((-1) :+ 0) == sqrt ((-1) :+ 0)
21:00:08    True
21:00:33  > sqrt ((-1) :+ 0) -- because
21:00:34    0.0 :+ 1.0
21:01:30  Yay Data.Complex
21:04:34 -!- atriq has quit (Ping timeout: 240 seconds).
21:04:44  Data.Complex should do type Zomplex = Complex Double (or however that's written).
21:06:19  Hey, there's a BLAS.C.Zomplex Haskell module.
21:06:48  It defines things that operate on Ptr (Complex Double).
21:08:01  There's such delightful signatures like zgbmv :: CBLASOrder -> CBLASTrans -> Int -> Int -> Int -> Int -> Ptr (Complex Double) -> Ptr (Complex Double) -> Int -> Ptr (Complex Double) -> Int -> Ptr (Complex Double) -> Ptr (Complex Double) -> Int -> IO ().
21:10:33  it's haskell so i can tell right from the type what that does
21:10:34  (It does y = a*A*x + b*y, or y = a*A^T*x + b*y, or y = a*A^H*x + b*y, where a, b are scalars, x, y are vectors, A is a matrix, A^T is its transpose, and a^H its conjugate transpose, depending probably on the CBLASTrans.)
21:10:58 -!- boily has quit (Quit: Poulet!).
21:11:03  (And it does it FAST, because it's BLAS, and you have a BLASt.)
21:11:11  whence the name "Zomplex"
21:11:12  ?
21:11:25 -!- Phantom_Hoover has joined.
21:11:55   my primary school used primarily Acorn computers, together with some BBC Micros
21:12:07  my neighbour used an acorn until like 5 years ago
21:12:11  It's the double-precision complex, I think for the blas/lapack single-letter names that go S for single-precision, D for double-precision, C for single-precision complex and Z for double-precision complex.
21:12:20  I'm thinking they just couldn't think of a suitable letter.
21:12:59  Also, SGI's math library uses 'complex' and 'zomplex' with the same difference. Not sure who was first there.
21:13:06  it should be T, if anything
21:15:08 -!- augur has quit (Remote host closed the connection).
21:16:27  Actually I was slightly inexact there, A needs to be a general band matrix, i.e. only some amount of its diagonals are stored. You can (obviously) tell from the GV.
21:16:56  It would of course be ZGEMV for the general matrix-vector operation.
21:20:32  "General" to distinguish it from Hermitian (regular, band, packed-storage), orthogonal (regular, packed), Hessenberg (upper, upper-generalized), symmetric (regular, tridiagonal, packed), positive definite (regular, band, packed, tridiagonal), triangular (regular, packed, bad, generalized), trapezoidal, unitary (regular, packed), diagonal or bidiagonal matrices which all have their own ...
21:20:39  ... optimized storage formats and function versions. (List not exhaustive, I just got bored typing.)
21:20:42  Numeric programming must be such fun.
21:21:03  That one "bad" should've been "band".
21:21:17  There's no special version/format for bad triangular matrices.
21:21:35  In fact, I'm not sure what makes a triangular matrix bad. Maybe it has just one or two elements on the other side? 
21:23:05 -!- epicmonkey has quit (Remote host closed the connection).
21:23:25 -!- epicmonkey has joined.
21:35:07 -!- monqy has joined.
21:56:31 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
22:00:12 -!- augur has joined.
22:10:50 -!- Phantom_Hoover has quit (Ping timeout: 268 seconds).
22:11:58 -!- Phantom_Hoover has joined.
22:19:07  What is brainfuck useful for exactly?
22:19:24  everything
22:19:32  It's Turing complete!
22:19:34  So totally
22:20:23  Max00355: proving other languages turing complete and not much else
22:21:30  it has some interesting derivatives, and a lot more really boring derivatives
22:21:31  Hmm, but what I don't understand is how a self-interpreter could be made than.
22:21:42  elliott: I'd actually say that proving other languages TC is not that useful a use
22:21:48  Max00355: It's TC
22:21:53  minsky machines or tag/cyclic tag machines are normally easier to implement
22:21:59  coppro, I know that.
22:22:09  any turing-equivalent language admits a self-interpreter
22:22:18  elliott: unless it can't take input
22:22:18  ^
22:22:26 -!- copumpkin has joined.
22:22:27  ais523: well, then you just need to encode it in initial state, or whatever
22:22:29  (not being able to produce output isn't a problem)
22:22:32  well, OK
22:22:38  I guess it depends on your definition of interpreter
22:22:49  I find myself agreeing with elliott here, repeatedly
22:22:49  weird
22:23:04  hmm, does any TC language admit a self-interpreter? even if it's super-Turing?
22:23:23  seems like you could make a construct more powerful than a UTM, but one insufficiently inflexible to emulate itself
22:23:36  like a halting oracle where you have to embed the program to check in the source code, or something
22:23:56  hmm
22:24:04  superturing isn't normally considerd tc
22:24:13  would you consider BF to be a PDA?
22:24:22  fair enough, but you know what i mean
22:25:15   Any webhamster who specifies pt (or cm, for that matter) for a non-print layout (that is any non-fixed-size layout) should go to jail for no less than double the font size (measured in football fields, of course).
22:25:17  hmm
22:25:50  elliott: so would you say curly-L is strictly weaker than TC?
22:25:57  or do you think it's pointing out that TC is poorly-defined?
22:26:56  ais523: is this related?
22:27:51  "this" = ?
22:28:01  she shouldn't use pronouns on the internet
22:29:47  this =
22:29:47   hmm
22:29:47   elliott: so would you say curly-L is strictly weaker than TC?
22:29:47   or do you think it's pointing out that TC is poorly-defined?
22:29:57  related to =
22:29:58   hmm, does any TC language admit a self-interpreter? even if it's super-Turing?
22:29:58   seems like you could make a construct more powerful than a UTM, but one insufficiently inflexible to emulate itself
22:29:58   like a halting oracle where you have to embed the program to check in the source code, or something
22:29:59   hmm
22:30:01   superturing isn't normally considerd tc
22:30:03   would you consider BF to be a PDA?
22:30:13  elliott: it's vaguely related
22:30:28  curly-L is the class of languages that can interpret some TC language, right?
22:30:47  so it's a case of establishing bounds either way
22:30:57  but I just realised I wasn't really thinking
22:30:57  sure
22:31:07  hmm, are all super-turing languages also TC?
22:31:13  fwiw, s/TC/capable of implementing a UTM etc./ in my statement
22:31:18  if you want it unambiguous
22:31:19  ish
22:31:21  I'd imagine that a language that was, say, /just/ a halting oracle wouldn't be
22:31:51  well... you can implement a UTM emulator with that, sort of
22:31:58  TC if you can write a program that halts iff UTM, right?
22:32:02  er
22:32:04  TC if you can write a program that halts iff UTM halts, right?
22:32:09  you can write a program that prints 1 iff UTM halts and 0 if not
22:32:13  "sort of TC"
22:32:25  oh, hmm, right
22:32:28  although not vice versa
22:32:31  not really TC
22:32:32  but "sort of"
22:32:36  yes
22:32:43  it's reminiscent of curly-L but in a different way
22:32:54  if you have halts(p) and ifnot (bool) stmt and loop_forever() then you can do
22:33:01  ifnot (halts(...)) loop_forever()
22:33:16  "ew" - audience
22:33:24 * ais523 optimises that
22:33:28  whilenot (halts(...)) ;
22:33:38  ais523: until (halts(...));
22:33:43  hello
22:33:48  elliott: you said "ifnot", not "unless"
22:33:51  hi Arc_Koen
22:33:55  elliott: so I was just copying your style
22:33:57  ais523: it was a joke
22:34:02  I know
22:34:04  so was mine
22:34:09  (what's a pda?)
22:34:14  Arc_Koen: push-down automaton
22:34:15  ais523: well, you're a joke
22:34:30  Arc_Koen: personal digital assistant
22:34:32  you know how languages with two stacks are usually turing-complete, unless they have weird flow control issues?
22:34:39  Arc_Koen: public display of affection
22:34:44  if you take one of those but give it only one stack, you usually get a push-down automaton
22:34:47  Arc_Koen: pricy dice access
22:34:57  Arc_Koen: pillar-dancing anemone
22:35:01  elliott: he asked an on-topic question, can't he get an on-topic answer?
22:35:08  Arc_Koen: park drive automobile
22:35:10  ais523: no
22:35:13  well personal digital assistant I knew
22:35:13  ais523: well yes actually
22:35:13  he did
22:35:18  then i gave him lots of off-topic answers
22:35:21  but somehow I figured that's not what brainfuck was
22:35:37  Arc_Koen: a simple example is a modification of BF where all tape cells to the right of the pointer instantly get set to 0
22:35:57  anyway, my point was that BF is at least as powerful as a PDA, but it's not normally considered a PDA because it's /also/ TC
22:35:58  creepy
22:36:38  well that seems only logical
22:36:55  the set of brainfuck programs is strictly larger than the set of pda programs
22:37:00  you could replace < with [-]<
22:37:03  everywhere
22:37:05  and get the same effect
22:37:07  (larger than in the sense of inclusion)
22:37:14  anyway, PDA is one of the few interesting sub-Turing computational classes
22:37:23  and you can write some real programs in it, sometimes
22:37:33  the set of rectangles is strictly larger than the set of squares
22:37:33  (primitive recursive is another, and there are not nearly enough esolangs that use it)
22:37:43  and yet rectangles are not normally considered squares
22:37:58  (btw, I'm considering making the Anarchy compiler give a warning if the input program isn't provably primitive recursive)
22:38:06  I've never really know the definition of primitive recursive
22:38:23  Arc_Koen: the simplest definition is that for all loops, you need to be able to cap the number of iterations before you start looping
22:38:31   (btw, I'm considering making the Anarchy compiler give a warning if the input program isn't provably primitive recursive)
22:38:32  just make it total
22:38:32  oh, o
22:38:33  this obviously implies that the program necessarily halts eventually
22:38:34  ok
22:38:37  all the cool languages are total
22:38:54  elliott: I strongly considered that but it turned out that making it total syntactically disallowed interesting things
22:39:01  so I decided static analysis for totality made more sense
22:39:03 -!- nys has quit (Quit: quit).
22:39:10  and hey, if you really want to write an infinite loop, you can, but it's a little nontrivial
22:39:14  what does it disallow that you want?
22:39:48  elliott: most notably, tail-recursion (specifically recursion, don't really want general tail-calls for this) that simply mutates the input parameters
22:40:00  you can refactor that into a version that doesn't but it's a lot of annoying boilerplate
22:40:13  like, see C-INTERCAL's optimizer for an example
22:40:14  ais523: um, I think Agda allows that
22:40:20  so maybe your checking sucks :p
22:40:21  hmm
22:40:24  it can't allow it /in general/
22:40:27  I think Coq does too
22:40:31  but monqy probably knows more than me there
22:40:39  what specific restrictions does it put on it to keep it total?
22:40:43  no idea
22:40:48  but for instance, foo (S n) = foo n is obviously OK
22:40:52  because clearly if you don't mutate the parameters, you get an infinite loop
22:40:54  since you know it can't keep taking that path forever
22:41:06  (because it's not codata)
22:41:15  elliott: Anarchy can do that too without the warning
22:41:28  I'm thinking more along the lines of foo (x, y) | x > y = foo y x
22:41:33  err, = foo (y, x)
22:41:43  let me not muddle curried and uncurried versions of things
22:41:45 * elliott finds that definition dubious anyway
22:41:51  brb
22:42:23  elliott: codata?
22:42:25  well of course it's dubious
22:42:57  it'd be nice to be able to automatically resolve a bunch of those and determine whether it definitely halts, or whether the compiler isn't sure whether it definitely halts or not
22:43:09  and thus only a warning, in case the compiler fails to solve the halting problem in that particular case
22:44:32  how about a language with a halting oracle to which you give a pair (p, n) where p is a pointer to the beginning of a program (in that language) and n the length of the program
22:44:48  this means you can feed the halting oracle the program it's in
22:45:20  Arc_Koen: that just defies the laws of physics
22:45:26  I think so
22:45:29  if you can conditionally run an infinite loop
22:45:39  ais523: anyway, I think you can do something like that
22:45:43  but you need to use something stronger than booleans
22:46:07  elliott: anarchy's type system is already straining at the edges of credibility anyway
22:46:10  funnily enough we get the same paradoxes as with time travel
22:46:13  I can implement it, but not in a compositional way
22:46:19  Arc_Koen: see http://esolangs.org/wiki/TwoDucks if you haven't already
22:46:20  ais523: that's very very bad
22:46:23  I'd scrap it entirely
22:46:27  I have
22:46:29  elliott: it may be implementable compositionally too
22:46:37  but really this is for ease of use rather than mathematical purity
22:46:41  it should be obvious :)
22:46:44  the two are linked
22:46:46  "warning: code is dead, cannot typecheck it"
22:47:41  elliott: well it probably annoys mathematicians, and Haskell fans in particular
22:47:41  hmm, question
22:47:53  and anyone who's listened to me talk to my boss will know how much I insist on things generally being compositional
22:47:57 -!- epicmonkey has quit (Ping timeout: 276 seconds).
22:48:02  but it seems like a small price to pay for a language this great to use
22:48:10  I wouldn't have invented Anarchy if I didn't really badly want to use it
22:49:12  imagine I have a language X_n defined as { p in {brainfuck programs} such that the deepest level of loop-nesting in p is n }
22:49:26  hmm… not counting efficiency/computational complexity, in pure total programs, call-by-name and call-by-value are observationally indistinguishable, right?
22:49:28  so for instance X_0 is brainfuck without [ ], X_1 is brainfuck without nested loops, etc.
22:49:33  ais523: I think that's because you only think about the Anarchy programs you want to write
22:49:37  not the ones you'll miswrite by mistkae
22:49:38  *mistake
22:49:56  Arc_Koen: if the question is "what's the first that's TC", I've wondered that myself
22:50:29  that's indeed the question
22:50:35  what did yourself answered?
22:50:38  Arc_Koen: it's widely believed to be either 2 or 3
22:50:44  but I don't think it's ever been settled conclusively
22:50:44  oh, sweet
22:51:04  I was afraid none would be
22:51:11  ok, new question then: what about qdecl?
22:51:40  if I limit the number of nested loops to, say, 200 or something, do you expect it would still be TC?
22:51:52  Perhaps does anyone know how to make a quine with FurryScript? I have not figured it out by yet.
22:52:26 -!- Phantom__Hoover has joined.
22:53:02  Arc_Koen: well put it this way, you can write a BF self-interpreter, right?
22:53:18  I've never tried
22:53:20  and you can bundle a self-interp with an input program, because you can do ++++>++>+++++>++>++++++> or whatever at the start of the program with no loops at all
22:53:33  so the question boils down to "what BF self-interpreter has the least deeply nested loops?"
22:54:14  ais523++ # makes sense
22:54:23  that sounds clever but I actually have no idea what your mean
22:54:54  Arc_Koen: let's see
22:54:57  xmodmap:  please release the following keys within 2 seconds: Control_L (keysym 0xffe3, keycode 66)
22:55:07  i like to read this as a threat
22:55:22  suppose we extend BF with a command that interprets the input tape as a BF program
22:55:27  two things happen
22:55:27  kmc: I hate it when that happens. :-(
22:55:39  first, Phantom_Hoover replaces our brain with a brick
22:55:39  kmc: I'm too lazy to fix my things, so I run while true; do xmodmap -e 'remove Lock = Caps_Lock' -e 'keysym Caps_Lock = Escape'; disable-capslock; sleep 2; done
22:55:47  second, we can compile any BF program into one that uses no loops
22:55:52  heh
22:55:54 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
22:56:01  because it doesn't require any loops to put the program on the tape
22:56:11  and so we can just put the program on the tape, then run our new command
22:56:16  do you understand that far?
22:56:23  but how will you do complete the second step when your brain is a brick?
22:56:36  ye,s I do
22:56:59  ohhhh I get it
22:57:01  Arc_Koen: now, suppose that in order to avoid inferring the wrath of Phantom__Hoover, instead of adding this new command to BF, instead we write a BF program that interprets the tape as a BF program and runs it
22:57:24  yes, I get it, ++++>++>+++++>thing was filling the cells with a brainfuck program
22:57:37  that's nice
22:58:18  well, with a different instruction encoding, but there's no need to use ASCII
22:58:27  Do you like this psionic power for Dungeons&Dragons game????     http://zzo38computer.org/dnd/options/Kjugobe_Psionic_Hack.p
23:03:23  Arc_Koen: anyway, I'm not sure if anyone's seriously tried to write a two-nested-loop selfinterp, or even a three-nested-loop selfinterp
23:04:05  that's ok
23:04:20  I was wondering because I wanted to prove Emmental TC
23:04:27  ais523, i'm only a short train ride from birmingham, remember
23:04:29  and I think I can convert Qdecl programs into Emmental
23:04:31  you're playing with fire here
23:04:43  except I need a distinct symbol for every nested loop
23:04:58  and there are only 256 symbols soooooo
23:05:04  the minimum nesting has to be finite because otherwise any TC interpreter written in BF would have to be infinite
23:05:12  it's probably small too
23:06:19  hmmm though I'm wondering if I only needed a distinct symbol for nested loops... for instance consider a program like BEGIN BEGIN END BEGIN END BEGIN END END
23:06:28  (with actual code inside of all those loops)
23:06:37 -!- Jafet has quit (Quit: Leaving.).
23:07:44  http://www.comedycentral.com/video-clips/5a1dsd/key-and-peele-bling-benzy---da-struggle
23:11:13 -!- copumpkin has changed nick to brony.
23:11:16 -!- brony has changed nick to copumpkin.
23:22:07  copumpkin: Ahhh, other-channel-/nicking.
23:22:12  copumpkin: Always fun.
23:25:04  yep
23:49:17  ais523: huh, did you know that Debian changed official desktop environments?
23:49:26  what is it now
23:49:45  Xfce; http://anonscm.debian.org/gitweb/?p=tasksel/tasksel.git;a=commitdiff;h=2a962cc65cdba010177f27e8824ba10d9a799a08
23:50:37  “This ensures that the desktop will fit on CD#1, which gnome currently does not.”
23:50:39  Best reason.
23:51:08  Gregor: suspect that's code for "I don't like GNOME 3 and thought of a decent technical excuse" :p
23:51:55  Eeyup.
23:52:30  If it were my call, I'd have just made the commit message “Switched the default WM to XFCE, because Gnome is fucking terrible.”
23:53:02  if only xfce was actually godo rather than just not being gnome
23:53:31  yeah
23:53:36  why didn't they just use godo instead
23:53:43  *good
23:53:49  todo make wm called godo

2012-10-19:

00:01:47 -!- nooga has quit (Ping timeout: 244 seconds).
00:32:08 -!- augur has quit (Remote host closed the connection).
00:32:57 -!- augur has joined.
00:34:00 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
00:49:28 -!- DHeadshot has joined.
01:14:45 -!- DHeadshot has quit (Read error: Connection reset by peer).
01:14:51 -!- DH____ has joined.
01:15:38  http://pastebin.com/GxsYVyED
01:15:39  :(
01:22:25  "If the queue is empty, any instruction that would normally use a value from the queue instead uses 0."
01:22:26  ghhhhhh
01:31:56  after a few corrections the hello world program finally outputs "he???????e>?"
01:32:02  not so bad
01:34:32  and after a few more corrections "hell?η?wE?"
01:34:39  note the incredible progress
01:34:54  also the number of characters is now wrong, which probably means I should go to sleep now
01:35:54  (for the record I have no idea what the heck this η thing is doing there - my shell has never supported anything else than ascii 0-127 before
01:39:32 -!- DH____ has quit (Read error: Connection reset by peer).
01:39:37 -!- DHeadshot has joined.
01:50:05  that's more a matter of the terminal than the shell
01:51:04  have you actually tried non-ascii characters before?
01:51:53 -!- Jafet has joined.
01:55:54  not recently
01:56:10  it's not really surprising that it would work out of the box on a modern OS
01:56:26  amazingly, some people speak languages other than english, and want to use computers
01:56:32  WHAT
01:56:36  that's crazy
01:56:39  i know, right?
01:56:51  kmc: Some people just speak English.
01:57:05  kmc: it didn't suddenly lose accents and so on just because ASCII defined an arbitrary subset in the 60s
01:57:16  not to mention punctuation
01:57:43  i don't understand what point you are making
01:59:13  That you could be more confusing about your sarcasm!
01:59:20  (I wasn't disagreeing at all.)
01:59:34  (Just saying that you don't need to go to foreign languages to see ASCII's inadequacy.)
01:59:39  yeah
01:59:57  english does have some diacritic marks, yes
02:00:10  and confounding hyphen with minus with en dash with em dash is annoying
02:00:29  Quotes, too, though nobody cares about that any more.
02:00:33  Not even Wikipedia.
02:00:41  wikipedia doesn't use fancy quotes?
02:00:44  Nope.
02:00:46  i know someone who uses them in IM
02:00:49  Specifically recommended against in their MOS.
02:00:53  heh
02:00:59  yes, random nerds who do it to be pedantic don't count :p
02:00:59  on what grounds
02:01:18  kmc: far simpler to input, basically universal, work just fine
02:01:18 -!- Jafet has quit (Ping timeout: 255 seconds).
02:01:26  and I think causing fewer display issues with crappy fonts etc.
02:01:28  yeah
02:01:44  it's not a bad justification as far as input goes... random editors would hardly bother with that
02:01:45  i use fancy quotes in latex and pretty much nowhere else
02:01:49  yeah
02:01:56  anyway I am going to sleep now
02:02:13  high-class online publications still use them
02:02:28  newspapers etc
02:03:38  but then again The New Yorker still writes coöperate and such
02:03:43  The Sha Chafer
02:05:44  but hungarian is cooler: it has o, ó, ö, and ő
02:06:13 -!- elliott has quit (Ping timeout: 246 seconds).
02:07:48  ő
02:07:57  ő_ő
02:08:02  in french we use « quotes »
02:08:41  and german uses some weird fancy-but-reversed quotes
02:09:04  like they confused the beginquote and endquote
02:12:28  gnight
02:12:32 -!- Arc_Koen has quit (Quit: Arc_Koen).
02:19:31 -!- TodPunk has quit (Read error: Connection reset by peer).
02:19:45 -!- TodPunk has joined.
02:26:41 -!- Jafet has joined.
02:27:45  hey hey smoke weed everyday
02:27:57  is that what you do these days, kmc?
02:28:15  no
02:28:25  smoke weed a measure zero subset of days
02:28:34  i mostly do boring things like work and eat pasta
02:28:41  i am growing mushrooms in my house, but the non-psychoactive kind
02:28:58  though the spores came from a sketchy website that included a baggie of opium poppy seeds as a "free gift"
02:29:43  Do you like music "Funiculi Funicula"?
02:31:06  lol
02:31:11  kmc: SR?
02:31:18  zzo38: I know it
02:31:25  wouldn't say I particularly like it though
02:31:34  SR what?
02:31:43  silk road
02:32:05  where all techies get their drugs these days
02:32:07  (In case you forgot, I mean the music only; disregard the words)
02:32:10  and other assorted spores
02:32:35  heh
02:32:45  are you still mining bitcoins copumpkin?
02:33:24  nah, stopped mining pretty quickly
02:33:31  I still deal in them a fair amount though
02:34:56 -!- amca has joined.
02:43:02  I had idea of pieces in chess variant, such as the "opposer", which after moved, you can change any of adjacent pieces to opponent's pieces.
02:44:57  I use fancy quotes mostly with TeX only writing ``...'' it prints using starting/ending quotation mark
03:08:21 -!- ais523 has quit.
03:19:53 -!- ais523 has joined.
04:47:16 -!- zzo38 has quit (Remote host closed the connection).
05:15:40 -!- FreeFull has quit.
05:25:02 -!- ais523 has quit.
05:31:17 -!- ais523 has joined.
05:33:23  oh wow, anagolf has malbolge now
05:33:26  nobody is safe
05:42:34  anagolf?
05:44:29 -!- DHeadshot has quit (Read error: Connection reset by peer).
05:44:49 -!- DHeadshot has joined.
06:07:33  coppro: golf.shinh.org
06:07:59  the site's way more complex and better-run than it looks from the appearance
06:08:10  basically, shinh is a really good programmer but not so great at graphics design skills
06:10:15 -!- ais523 has quit.
06:16:26  But I thought those skills *always* go hand-in-hand.
06:40:55 -!- copumpkin has quit (Ping timeout: 260 seconds).
06:42:47 -!- copumpkin has joined.
07:06:43 -!- DHeadshot has quit (Ping timeout: 246 seconds).
07:11:34 -!- epicmonkey has joined.
07:34:18  :D
07:34:31  It also has Burlesque
07:35:31  But currently it's broken I think. (It worked earlier)
07:36:07 -!- epicmonkey has quit (Ping timeout: 246 seconds).
07:38:36  oh.
07:38:39  It seems to work again.
07:40:06  Yep.
08:20:12 -!- atriq has joined.
08:21:42  Well, I've started using emacs
08:21:49  It's going better than I expected
08:23:26  atriq: brickbrain
08:27:31  What did you use before you started using emacs? 
08:27:34 -!- fungot has quit (Ping timeout: 246 seconds).
08:27:41  gedit and Eclipse
08:31:42 -!- nooga has joined.
08:39:48 -!- epicmonkey has joined.
08:46:20 -!- Zerker has joined.
09:28:20 -!- Zerker has quit (Remote host closed the connection).
09:39:42 -!- mindlessDrone has joined.
09:43:58  hi
09:45:43  `welcome mindlessDrone 
09:45:54  mindlessDrone: 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.)
09:46:36  mindlessDrone, two questions
09:46:42  First, are you in Finland?
09:47:20  atriq: I think we already did the welcome bit.
09:47:28  Oh, okay
09:47:32  fizzie, are you in Finland?
09:47:33  Maybe also the Hexland/Finham bit, I'm not sure.
09:47:38  Yes, I am.
09:47:44  Are you in Hexham?
09:47:51  No, I am not.
09:47:54  Okayu
09:47:57  *-u
09:48:21  ya you did the welcome thing ..im neither in finland nor in hexham
09:49:11  Okay
09:49:36  Are you in Metzingen?
09:50:03  where is that?
09:50:09  Germany
09:50:33  Baden-Wrttemberg, apparently
09:50:36  It's twinned with Hexham
09:51:59  oh i see ..well i live in this direction
09:52:06  Okay
09:52:16  I don't think anyone here lives in Metzingen
09:52:31  Even though it's statistically more likely than living in Hexham
09:53:32  Espoo is apparently twinned with Esztergom, Gatchina, Irving, Køge, Mumbai, Kongsberg, Kristianstad, Nõmme, Sauðárkrókur, Shanghai and Sochi.
09:53:39  I don't know if that actually means anything.
09:54:00  (But Sauðárkrókur is a fancy name.)
09:54:00  Basically, they get to put on their signs "Twinned with Espoo!"
09:54:06  Sounds Icelandic
09:54:11  It's Icelandic.
09:54:16  South Krakow?
09:54:32  "Sauðárkrókur is a town in Skagafjörður."
09:55:07  is krakow icelandic?
09:55:17  No, it's Polish
09:55:40  I was just reading it phonetically
09:56:15  Although if I was translating the name I would call it Sodamouth
09:56:43  i can't follow you
09:57:01  Sometimes I can't follow me
09:57:04  Don't worry
09:59:23  atriq: "Directly translated to English the name would be 'Sheep-river-hook'."
09:59:47  Yeah, but that's ridiculous
10:00:12  I don't know, krókur sounds very hooky to me.
10:00:25  True
10:00:35  Sheepcrook, maybe?
10:00:54  Sheepstream Crook
10:18:27 -!- Arc_Koen has joined.
10:19:01  hello
10:20:22  Hey
10:21:15 -!- monqy has quit (Quit: hello).
10:21:24  this morning was weird
10:21:32  What happened?
10:22:06  well I had a driving lesson and for some reason I set my alarm clock but forgot to turn it on
10:22:19  so I was waken up by someone ringing at the door
10:22:30  and yesterday I went to bed at 4am
10:22:54  the driving lesson was... different from usual
10:24:34  at some point I stopped at a light
10:24:45  Cool. They have taken 11-word sequences from Wikipedia, taught an appropriate neural network using them and used the t-SNE algorithm to make a map of the most common words that tries to group words with similar feature vectors together. http://www.cs.toronto.edu/~hinton/turian.png
10:25:02  after one minute he asked me why I was stopping... the light was GREEN
10:25:45  what's a feature vector?
10:26:45  The neural net’s output in this case.
10:26:55  is it like grouping chemical elements according to the molecules they can form?
10:27:38  If you can make a neural network figure that out by itself, then i guess so.
10:51:04 -!- mindlessDrone has left.
10:52:05 -!- mindlessDrone has joined.
10:55:59  Kinda reminds me of the good old WEBSOM.
10:57:34  Dimensionality reduction is a funny topic.
10:57:59  There were people fiddling with NeRV around here, I think.
10:58:21  http://research.ics.aalto.fi/mi/software/dredviz/ these guys.
10:58:43  I even wanted to NeRV something up, but by now I've completely forgotten what it was.
11:36:08 -!- mindlessDrone has left.
11:43:04 -!- nooga has quit (K-Lined).
11:54:17 -!- amca has quit (Quit: Farewell).
12:41:27 -!- ogrom has joined.
12:45:56 -!- Jafet has quit (Ping timeout: 255 seconds).
12:46:33 -!- Jafet has joined.
13:21:34 -!- elliott has joined.
13:22:46 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
13:30:13  Sgeo: why do you keep objecting to your deregistration and then not doing anything
13:30:13  elliott: You have 2 new messages. '/msg lambdabot @messages' to read them.
13:30:20  I guess that contract thing but you did it before then too
13:31:26 -!- Taneb has joined.
13:32:13 -!- atriq has quit (Disconnected by services).
13:32:16 -!- Taneb has changed nick to atriq.
13:41:18 -!- elliott has quit (Remote host closed the connection).
13:42:10 -!- copumpkin has joined.
13:42:23 -!- copumpkin has quit (Client Quit).
13:43:37 -!- elliott has joined.
13:45:52 -!- copumpkin has joined.
13:46:25 -!- pumpkin has joined.
13:47:16 -!- copumpkin has quit (Disconnected by services).
13:47:17 -!- pumpkin has changed nick to copumpkin.
14:24:41 -!- boily has joined.
14:53:06 -!- AnotherTest has joined.
14:53:21  Hello
14:53:28  Hey
15:09:03 -!- epicmonkey has quit (Ping timeout: 244 seconds).
15:23:22  hi.
15:23:27  hello
15:44:33  Is codeeval.com a good way to look for a job?
15:46:16  Browsing through Burlesque's Language Reference seems to take longer and longer :D
15:46:31  Which means I'm on the right path :P
15:47:19  or...
15:47:22  feature bloat
15:47:31  but let's assume that's not the case
15:51:17  Meh. I'm going to do it
15:51:22  And have a honking good time
15:51:29  ...that last line was weird
15:53:22 -!- mindlessDrone has joined.
15:55:17  Sgeo: the only proper way to honk is in by being zen doing python.
15:57:12  AnotherTest: It has more features than I can remember having implemented ;)
15:57:54  mroman: remember not to forget referring to microsoft, as this was their amazing idea
15:58:01  That's why it has a documentation.
15:58:33  I'm going to assume that in every not small software project you have implemented more stuff than you could possibly remember without the documentation.
15:59:04 -!- Vorpal has joined.
15:59:28  Well
15:59:41  at least I don't know every sideeffect of any command in Burlesque
16:00:01  So when I golf in it on anagol I have to consult the documentation often :)
16:00:44  Of course, the documentation can't tell you which sideeffect you need
16:00:57  Do you already have support for complex numbers?
16:01:02  so you just randomly read something and judge if it is useful
16:01:04  AnotherTest: No.
16:01:11  :'(
16:01:21  but you are welcome to implement it ;)
16:01:42  I lack a solid Haskell experience
16:02:01  I'm no haskell pro either.
16:02:32  I know the things one needs to know to get most things done in it.
16:02:37  Well, I have never written anything big in haskell. And I didn't learn how to use important features of the language such as types yet.
16:03:10  s/(learn)/\1 well
16:03:44  It's surprisingly easy at the lower levels
16:03:56  and surprisingly freaking complicated at the higher levels ;)
16:04:34  Especially since haskell is nowhere near my field of study.
16:04:54  Which is?
16:05:01  imperative languages?
16:05:15 -!- boily has quit (Read error: Operation timed out).
16:05:29  No.
16:05:48  My field of study is... well...
16:06:01  optimizations?
16:06:10  (for compilers)
16:06:26  just general compiler design?
16:06:41  interpreters? concurrency?
16:06:57  It's a mix of finance, physics, communication technology, mathematics, economy, law
16:07:14  a.k.a. ...?
16:07:41  it's called information technology ;)
16:07:41  The legal implications of communication technology in an ideal economic system
16:08:00  I'm not privileged enough to study at a university
16:08:23  I'm not even old enough to study at a university!
16:08:44  which means I don't have the right credentials to study at a university
16:08:49  because I learned a job ;)
16:08:58  Well, maybe I were if I was invited or something - which will most likely not happen :(
16:09:12  I wrote a paper... maybe if they see that?
16:09:19  Well probably not.
16:10:39 -!- augur has quit (Remote host closed the connection).
16:10:55  mroman: Can't everyone go to university if they want to?
16:11:12  I think you can still go...
16:12:38 -!- FreeFull has joined.
16:21:42 -!- boily has joined.
16:30:46  Apparently Pythonistas hate reduce()
16:30:47  :(
16:32:02  C people do not like me either because sometimes I use goto
16:32:53  python 3 lacks reduce iirc
16:32:58  ps dont say pythonistas
16:34:46  Slereah_: Sometimes goto is the cleanest way to do something
16:34:55  That's why the linux kernel has goto in places
16:36:09  This codeeval challenge says this company prefers solutions in Python
16:36:22  But this makes me want to do it in Clojure
16:36:44  Do it in Haskell
16:36:50  Then they won't know what the hell
16:37:09  I don't think codeeval even accepts Haskell
16:37:09  Do it in unlambda
16:37:22  I think this was weighing on my mind a bit when I started liking Clojure over Haskell
16:37:40  good criteria to like a language by
16:46:56  AnotherTest: No, you can't.
16:47:06  Universities obviously don't accept everybody.
16:47:24  So there is a very complex bureaucratic system which describes who they accpet.
16:47:27  *accept
16:47:50  Obviously in the form of restrictions.
16:48:00  There restrictions are different from where you come.
16:48:05  *These
16:48:13  for example
16:48:30  If I were to take the entry exam they would require me to have knowledge in chemistry
16:48:41  even if I'm going to study something which has nothing to do with chemistry.
16:48:47  (obviously this is bullshit)
16:49:05  however, if I waste three years at some other school (which does not have chemistry) I get a free pass
16:49:23  so If I come from a different school they suddenly don't require me to have chemistry knowledge.
16:50:42  also the way we study is completely flawed too.
16:51:07 -!- augur has joined.
16:51:20  It's actually the university who tells you what you have to study
16:51:23  and not you.
16:51:43  Of course they hide that fact well behind bureaucracy.
16:52:07  also students have a different set of pre-knowledge
16:52:36  some study-courses require specific pre-knowledge while others don't.
16:53:01  To study computer science at a university of applied sciences (so not a real university) you are not required to know ANYTHING.
16:53:16  so obviously the first course in your studies is "how does a fucking browser work"
16:53:32  which is completely bullshit for people who already know much.
16:53:49  right now I'm in the third semester and we're being teached assembler.
16:54:03  Obviously I already know how to do that.
16:54:33  But I can't just say "I'm not going to learn anything for the exam"
16:54:44  because they don't test if you know how to do stuff in assembler
16:54:55  they test if you know how to do it in their specific setting
16:55:19  so they use a custom assembler with a different syntax
16:55:52  which means you have to learn the differences in the syntax from the assembler you know and the one they customly manipulated.
16:56:20  also you have to write programs for a specific processor which means you have to study that processor.
16:57:00  Not that it's hard to do that, but it costs time of course you could be spending learning completely new interesting things.
16:58:16  Next semester we are going to have "operating systems"
16:58:19 -!- augur has quit (Remote host closed the connection).
16:58:33  sounds interesting but it's at such a low level it's completely bullshit
16:58:54  Oh. You don't say? There's multitasking? NO WAY! <- like that
17:00:58  mroman: there is no entry exam for computer science where I live
17:01:23  and I'm pretty sure that if you know the required basis of maths, that it's feasible to succeed
17:01:42  In Switzerland you have to come from specific schools to be accepted or pass a standardised general entry exam
17:01:51  Not in Belgium
17:01:56  (which tests also knowledge you will never use during your study)
17:02:16  It's like saying
17:02:20 -!- augur has joined.
17:02:40  "So, you are good at math and wan't to study math? Let me just check how good you are in geographie, chemistry and french"
17:02:49  (yes, in switzerland they test french)
17:02:56  if you don't know french, you can't study anything.
17:03:09  even if you don't actually need french for your field of study
17:03:20  but that's how the system runs.
17:03:51  and nobody needs french for their field of study unless they are studying languages or french itself.
17:04:41  I spent 8 years of learning french just to be able to be at the point of study I currently am.
17:05:40  Of course, I never had to actually use it so I actually I don't know any french any more ;)
17:05:42  There's a mandatory Swedish exam in Finland that's required to get a master's degree out of the "technical university" schools.
17:05:56  And that just pisses me off.
17:06:12  It's a waste of thousands of hours for nothing.
17:06:32  fizzie: http://en.wikipedia.org/w/index.php?title=File:Pois_pakkoruotsi.svg
17:07:00  I mean, yes you can argue that "having once learnd a foreign language is good if you want to learn some other language later in your life
17:07:10  but that's so far fetched
17:07:30  Well we learn french and english at school here as a second language
17:07:40  and I'm learning German after school
17:08:07  not sure how that is in Switzerland
17:08:10  The only important foreign language today is english.
17:08:19  And actually schools teach english at third grade
17:08:27  which is ~at an age of 9.
17:09:18  and you are literally going to have a hard time finding an adult who still knows french
17:09:23  even if he had to learn it for 8 years.
17:09:52  well, we have to learn French and Dutch (since these are the most used languages here). I though French is one of the languages in Swiss?
17:09:57  because there is just no use for french.
17:09:59  *thought
17:10:05  We learn Swedish in primary/secondary education schools (grades 1-12 counting numerically), and there's a lot of debate whether that's useful or not, but at least those are sort of more or less generic schooling; having to pass a Swedish exam as part of the tertiary education is IMO kinda stupef.
17:10:06  AnotherTest: So are two other languages ;)
17:10:21  mroman: 3?
17:10:31  I was under the impression the language areas are rather strictly geographically split in Switzerland.
17:10:38  There are 4 official languages in switzerland
17:10:40  Retro-roman, Italian and German
17:10:46  and French
17:10:48  and more non official languages of course.
17:11:13  AnotherTest: isn't the "call" in "stmnt   := literal stmnt | call stmnt | ε" a little redundant?
17:11:28  since then you define "literal := int | real | string | char | call"
17:11:32  At least everything went from French to German when we took a train from Geneve to Bern.
17:11:45  fizzie: Yes.
17:11:55  On they way from Geneve to Bern you are crossing one of the language borders.
17:12:46  Arc_Koen: Yeah it is in that case
17:12:54  Which means there are 3 parts of switzerland where I can't understand my fellow countrymen :)
17:13:06  Incidentally, we'll be passing through Switzerland (Geneva-Visp-St. Moritz-Tirano-Lugano-Milan; okay, so there are some dips into Italy) next summer.
17:13:15  If I still knew french then it would only be two parts
17:13:16  but still.
17:13:22  mroman: isn't it mandatory when you leave in a multiple-languages country to learn all of those languages?
17:13:36  Arc_Koen: You can remove the call stmnt production indeed
17:13:44  Arc_Koen: No.
17:13:51  shouldn't it be?
17:13:55  No.
17:14:05  That would require you to know 4 languages
17:14:10  Depends on the country in question.
17:14:17  and that's a lot.
17:14:20  Swedish is mandatory here, but then again we only have two.
17:14:24  that's not practical.
17:14:34  mroman: note that by "mandatory" I'm not talking about law or anything
17:14:45  Oh.
17:14:47  Well...
17:14:54  again
17:15:00  Learning 4 languages is hard
17:15:34  So it's not really practically possible to understand everybody
17:15:36  Unless of course they happen to be programming languages :p
17:15:51  well, one of them is already your mothertongue
17:16:03  so that narrows it done to 3
17:16:11  I'm actually learning 3 languages
17:16:12  also you might want to include english as well
17:16:13  Arc_Koen: We don't actually speak german here ;)
17:16:42  but yeah
17:16:42  mroman: Swiss German ≃ German?
17:16:45  I think 4 is probably the most common number of languages "learned" (as in, at least a couple of years of it in school) in Finland; Finnish, Swedish and English to (practically) everyone, and then one other that's most commonly French or German.
17:16:52  But yes.
17:17:04  it's 3 completely foreign languages one would have to learn here.
17:17:12  and one somewhat foreign language.
17:17:55  can't you deduce roman from french and italian?
17:18:03  and you have to learn different dialects
17:18:08  Arc_Koen: Well...
17:18:16  Probably the same way you can deduce english from other languages
17:18:36 -!- nvt has quit (Ping timeout: 246 seconds).
17:18:55  hmm the opposite would feel more natural for me
17:18:55  it's helps you a little but it's still going to be hard.
17:19:00  *it
17:19:43  We deduce german from swiss german ;)
17:19:45 -!- ogrom has quit (Quit: Left).
17:19:50  Which doesn't work all the time
17:20:05  because the grammar and vocabulary is not exactly the same.
17:20:08  Arc_Koen: I have corrected the redundant production
17:20:43  so basically stmnt is a string of literals
17:21:07  Yes
17:21:11  and call a list of ids?
17:21:15  Does anybode of you know somebody who works for youtube?
17:21:29  If so, kick his ass ;)
17:21:31  Technically "call" isn't an actual literal but OK
17:21:46  and call is indeed a list of ids, separated by dots
17:22:05  Everytime I jump back in time it reloads the whole video.
17:22:13  which means I have to download it yet again
17:22:21  YOU CAN JUMP BACK IN TIME
17:22:31  teach me
17:22:48  and with my poor bandwidth this really sucks like hell
17:23:05  Arc_Koen: Wait for it to buffer for 2 minutes
17:23:10  then watch the first two minutes
17:23:24  then in the timebar let's say you wan't to rewatch minute 01:00 - 02:00
17:23:38  assuming that's it's going to play that from what you already downloaded
17:23:39  BUT NO
17:23:44  it's going to restart the download
17:24:12  -'s
17:28:14  hm
17:28:24  now I don't have a linux ghc build environment anymore :(
17:33:18  You should just youtube-dl anything you're going to watch.
17:33:24  Then it's local.
17:34:23  my youtube-dl stopped working :/
17:36:27 -!- nvt has joined.
17:36:52  :(
17:37:00 -!- atriq has quit (Quit: dinner).
17:40:14  One has to keep updating it every now and then. (Disclaimer: haven't youtube-dl'd anything in a while.)
17:48:28  AnotherTest: How are things going with HELP?
17:48:35  Does it have an include yet?
17:48:45  no :p
17:48:52  Well...
17:48:55  DO IT ;)
17:48:59  I seem to have lost interest in help a bit
17:49:00  well
17:49:04  maybe not exactly lost interest
17:49:15  That's one of the most interesting features about a pre-processor I think.
17:49:20  But I have not a lot of time to work on esoteric things
17:49:28  understandable.
17:50:02  If I have free time, I usually work on this networking applications I'm creating
17:50:28  I'm planning to write something bigger in Burlesque
17:50:39  and an include would have been nice :)
17:50:42  well
17:50:46  I just use my own preprocessor
17:53:40  It doesn't have really a lot of features, but it has include, ifdef, ifndef and define
17:53:52  and was written while I was learning haskell.
17:54:43  I'll add it now
17:55:12  :)
17:55:15  \o/
17:55:19  use M4!
17:55:21  peer pressure has won.
17:55:27  kmc: I rather shoot myself.
17:55:34  i can't tell if m4 sucks or if it's just associated with things people hate (sendmail, autoconf)
17:55:37  I think the answer is "both"
17:55:48  mroman: I just finished a part of the other thing
17:56:00  kmc: I'd also guess "both"
17:56:08  I have to rewrite my paper on that though
17:56:12  but my opinion of autoconf actually improved as a result of using it in earnest
17:56:16  so i'm probably some kind of freak
17:56:25  You are writing a paper about it?
17:56:33  The IEEE guy said it was good but I needed to give more quantitative stuff
17:56:46  mroman: about the networking thing, not about HELP (of course)
17:57:04  kmc: You missed edwardk's lens talk in SF!
17:57:07  and he was probably right too
17:57:15  Good talk.
17:57:49  I wonder what m4 was supposed to be used for ... when do you want a macro language?
17:59:00  The paper might actually have been published directly if I had won a noble price I think
17:59:37  olsner: your hardware is just not powerful enough to do anything more demanding than macro substitution?
17:59:52  olsner: "Its primary use has been as a front end for Ratfor for those cases where parameterless macros are not adequately powerful."
18:00:22  fizzie: wow
18:00:26  kmc: I actually can literally shoot myself with M4.
18:00:38  since 1994.
18:01:12  olsner: (Second sentence of the abstract of Brian W. Kernighan and Dennis M. Ritchie. The M4 macro processor. Technical report, Bell Laboratories, Murray Hill, New Jersey, USA, 1977.)
18:01:36  "1972 - Dennis Ritchie invents a powerful gun that shoots both forward and backward simultaneously. Not satisfied with the number of deaths and permanent maimings from that invention he invents C and Unix."
18:01:48  "It has also been used for languages as disparate as C and Cobol -- is particularly suited for functional languages like Fortran, PL/I and C --"
18:02:14  Ah yes, the well-known functional languages Fortran, PL/I and C. 
18:02:16  "functional languages like Fortran"?
18:02:29  fizzie: were does that come from
18:02:35  The same abstract.
18:02:42  What
18:02:47  It continues "-- since macros are specified in a functional notation."
18:02:48  they have functions!
18:02:56  Dennis Ritchie wrote that?
18:03:00  It's a kind of different "functional language" there.
18:03:16  Either Ritchie or Kernighan. It doesn't exactly say which one.
18:03:20  M4 looks like lisp
18:03:27  and lips looks functional.
18:03:30  *lisp
18:03:43  It didn't say anything about how "functional" M4 is, though.
18:04:53  Ratfor seems to have been the primary use case, though.
18:06:36  There was a point of time where C's preprocessor didn't have macros with arguments either.
18:07:14 -!- atriq has joined.
18:07:28  ("Many other changes occurred around 1972-3, but the most important was the introduction of the preprocessor -- Its original version was exceedingly simple, and provided only included files and simple string replacements: #include and #define of parameterless macros. Soon thereafter, it was extended, mostly by Mike Lesk and then by John Reiser, to incorporate macros with arguments and ...
18:07:35  ... conditional compilation." (Dennis M. Ritchie. 1993. The development of the C language. SIGPLAN Not. 28, 3 (March 1993), 201-208. DOI=10.1145/155360.155580 http://doi.acm.org/10.1145/155360.155580)
18:07:47  mroman: just a warning, HELP is actually much worse :p
18:08:15  I don't have a cpp build environment anyway
18:46:30 -!- elliott has quit (Read error: Connection reset by peer).
18:47:09 -!- elliott has joined.
18:47:10 -!- elliott has quit (Changing host).
18:47:10 -!- elliott has joined.
18:54:37  fizzie: It's hard to do good macros with any language that actually has syntax =P
19:12:44 -!- AnotherTest has quit (Quit: Leaving.).
19:16:02 -!- ais523 has joined.
19:29:04  Some Finns received empty MMS messages timestamped at 1970 after a telecom operator did a software update. A newspaper interviewed the company’s Chief [roughly “mobile plan business”] Officer about it. He said “the testing of the messaging technology started already in the 1970s. Messages may have been left to the phone network back then.”
19:29:06  http://www.hs.fi/kotimaa/Aamulehti+Saunalahden+asiakkaat+saivat+viestej%C3%A4+70-luvulta+j%C3%A4rjestelm%C3%A4virheen+takia/a1305608399534
19:30:53 * kmc wonders whether to take FreeFull's bait
19:31:32  you know, C has no syntax, a program is just a sequence of characters
19:31:35  that is the only syntactic form
19:31:49  what those characters *mean* when juxtaposed is of course a semantic question
19:32:16  ion: good thing they upgraded their system to get rid of all those unsent messages then
19:32:32  kmc: Then nothing has any syntax?
19:32:58  apparently the reason the TTL field was added to IP is that in older internetworks, as time approached infinity, traffic consisted entirely of packets caught in routing loops
19:33:43  FreeFull: it's reducto ad absurdum from the ridiculous "Lisp has no syntax" claim
19:33:43   Some Finns received empty MMS messages timestamped at 1970 after a telecom operator did a software update. A newspaper interviewed the company’s Chief [roughly “mobile plan business”] Officer about it. He said “the testing of the messaging technology started already in the 1970s. Messages may have been left to the phone network back then.”
19:33:45  ion: amazing
19:33:59    Some Finns received empty MMS messages timestamped at 1970 after a telecom operator did a software update. A newspaper interviewed the company’s Chief [roughly “mobile plan business”] Officer about it. He said “the testing of the messaging technology started already in the 1970s. Messages may have been left to the phone network back then.”
19:34:03     Some Finns received empty MMS messages timestamped at 1970 after a telecom operator did a software update. A newspaper interviewed the company’s Chief [roughly “mobile plan business”] Officer about it. He said “the testing of the messaging technology started already in the 1970s. Messages may have been left to the phone network back then.”
19:34:25  TTL=255     Some Finns received empty MMS messages timestamped at 1970 after a telecom operator did a software update. A newspaper interviewed the company’s Chief [roughly “mobile plan business”] Officer about it. He said “the testing of the messaging technology started already in the 1970s. Messages may have been left to the phone network back then.”
19:34:52   hi
19:36:04  kmc: Lisp does have syntax though =P
19:36:19  TTL=254      etc
19:36:21  Not as much as many other languages, but it does
19:36:27  Otherwise it wouldn't work =P
19:37:01 -!- standa_ has joined.
19:37:07 -!- standa_ has quit (Client Quit).
19:37:11  yeah that's my point
19:37:48  and my other point is that things like (let (x 2 y 3) ...) vs (let ((x 2) (y 3)) ...) are basically syntactic questions
19:37:57  or at least, it is not unreasonable to call them syntactic questions
19:38:15  ultimately words are arbitrary and the participants in a discussion should just agree on what they mean
19:38:36  then i'm not sure if Kernel has syntax besides s-expressions :)
19:38:54  (or besides s-expressions plus a trivial rule for the syntactic form of a combination)
19:39:08 -!- zzo38 has joined.
19:39:09  Kemel
19:40:17  shachaml
19:40:27  o'shachaml
19:41:33  !rot13 shachaml
19:41:34  funpunzy
19:42:29  !rot13 shachamry
19:42:29  funpunzel
19:46:15  !rot13 ocaml
19:46:16  bpnzy
20:01:17  In a dynamically-typed language, if I'm getting wrong but sensible looking results, is it at all plausible that it's a type error, or is logic error far more likely?
20:01:23  Such as, getting 4 instead of 5
20:01:47  Because the Python program I wrote is giving wrong answers, but I feel like if I screwed up at all, it's type-related
20:10:52  I think one problem with Emmental is that its instruction-rewriting system cannot be rewrited
20:12:09  well, you can overwrite it with something else to stop being able to rewrite, but you can't write a different system since the instructions you create can only be sequences of instructions that already exist
20:13:11 -!- epicmonkey has joined.
20:14:01  Then do you have to make up a new one which includes the instruction to rewrite the instruction-rewriting system?
20:14:27  well yes, you can do that, but it won't introduce anything new
20:18:31 -!- ais523_ has joined.
20:19:08  That is what I thought
20:19:55 -!- ais523 has quit (Ping timeout: 260 seconds).
20:20:18 -!- ais523_ has changed nick to ais523.
20:22:46  A bit of printing helps me find my error
20:22:51  \n was getting into some of the strings
20:24:12  Ok, so I'm still getting wrong results
20:30:11  I'm actually getting _more_ wrong results
20:32:18  hmm, I guess you've made the code more wrong then?
20:33:19  Not necessarily.
20:38:43  yeah it's alright
20:38:51  you probably corrected a mistake that was cancelling out another
20:40:40  if two bugs are cancelling each other out that's less wrong than having either of those on its own uncancelled by the other
20:41:04  olsner, not if they only happen to be cancelling each other out in one test case
20:51:29  If two bugs are cancelling each other out is that even a bug?
20:53:45  Hm.
20:54:06  Maybe one can consider it a skill introducing two bugs which are cancelling each other out on purpose.
20:54:13  no, it's not a bug - it's two!
20:54:18  Well...
20:54:25  If there is no problem, is there a bug?
20:55:26  Technically such a bug is not observable until you actually introduce a bug by removing the cancellation?
20:56:50  there may be other ways to trigger either bug - let's say in 90% of cases both trigger and you're fine
20:57:13  but some cases might only trigger one of the bugs, requiring it to be fixed
20:59:42  If there are two bugs that cancel eachother out all the time, you've discovered a new algorithm
21:00:55  olsner: Yeah I know.
21:01:12  I just wanted to troll about the definition of it being a bug if there is no observable problem ;)
21:01:37  yeha, how can the code be wrong if it works?
21:02:02  :)
21:02:04  Again
21:02:11  (was supposed to be "yeah", but I guess you can read it yeeehaw if you like)
21:02:15  Technically if it works it can't be wrong :)
21:02:17  I
21:02:23  I'm beginning to hate Python
21:02:29  (If it really works in 100% of the time)
21:02:44  If anything it's bad ugly messy code.
21:02:57  Sgeo: good for you
21:04:42  !c int a, b; a, b = 4, 5; /* look, ma, Python-style unpacking assignment */ printf("a = %d, b = %d", a, b); /* whoops */
21:04:44  a = 0, b = 4
21:05:00  I'd like to know how many Python programmers have tried that.
21:05:15  I wish haskell had forward declarations
21:05:21  mroman, why?
21:05:24  It doesn't need it
21:05:48  i,i .hs-boot
21:06:22  It's one of these cases where A needs B and B needs A
21:06:36  which in C(++) you can resolve with forward declaration
21:06:47  the guys in #haskell told me
21:06:54  "just merge the shit into a single file"
21:06:57  well
21:07:11  Oh
21:07:20  !c int a, b; a, b = (4, 5); /* maybe it works if I make it more like a tuple */ printf("a = %d, b = %d", a, b); /* whoops again */
21:07:20  now it's a huge file with a lot of stuff in it :)
21:07:22  a = 0, b = 5
21:07:39  https://github.com/FMNSSun/Burlesque/blob/master/Burlesque/Eval.hs
21:07:46  ^- see. I would like to categorize builtins
21:07:55  so I can put them into files by category
21:08:05  but some builtins require functions from other categories
21:08:18  which yields to this circular dependency (or whatever you guys call that)
21:08:49  and apparently according to #haskell there is no way to do it without merging all into a single file :(
21:09:21 -!- atriq has quit (Quit: Leaving).
21:09:23  also the case matching is kinda messy
21:09:30  but I guess there is no better way to do it.
21:09:46  and haskell tidy removes comments
21:09:54  (which totally sucks btw.)
21:10:02  Oh, I didn't notice that this thing counts y as a vowel
21:10:13  it cleans up your indentation and stuff, but it throws away all the comments.
21:10:30 -!- Phantom_Hoover has joined.
21:10:40  (Not that there actually are lots of comments in the code :) )
21:10:43  (but still)
21:15:53 -!- mindlessDrone has left.
21:16:05  It's funny how little the actual eval function is :)
21:16:54  And I should probably switch to a Map of some sort instead of the linear tupel lookup
21:17:52  I wonder what the smallest lisp written in haskell is
21:19:17  Two test-cases working
21:19:21  http://sources.defmacro.org/blaise/src/
21:19:25  ^- probably not the smallest
21:19:27  but very simple
21:19:38  Found that already =P
21:20:21  :)
21:21:45  Well
21:21:55  Let's write the smallest lisp interpreter in haskell then shall we
21:22:15  hm.
21:22:30  (+ (- 3 2) (* 2 2))
21:22:46  One could actually do some regex hacks
21:22:49  to transform that to
21:22:54 -!- epicmonkey has quit (Ping timeout: 264 seconds).
21:22:57  (:+ (:- 3 2) (:- 2 2))
21:23:15  then one declares a data with a Data Constructor :+ and :-
21:23:33  and just let deriving Read do the work
21:23:48  *let me try that*
21:24:26  (writing parsers is for fools if you can just let ghc generate one for you :D)
21:26:03  hm
21:28:40  damn
21:28:46  that only works for infix
21:32:24  You could use a regex hack to replace * - + with (*) (-) (+)
21:32:36  Except you'll have to special-case negative numbers =
21:32:38  =P
21:33:10  Maybe turn "(* " into "((*) "
21:38:44  http://codepad.org/EhQMqj7Z
21:38:50  not quite how I imagined
21:39:06  but it works so it can't be wrong :P
21:39:43  also since this is PythonLisp whitespaces matters :D
21:39:56  if you don't put enough whitespaces in there it's gonna crash.
21:40:33 -!- Arc_Koen has quit (Quit: that's dr. turing to you, punk).
21:45:12 -!- boily has quit (Quit: Poulet!).
21:49:01  http://codepad.org/F3WR4M98
21:49:53  well
21:49:57  not really lisp of course
21:50:12  You'd have to treat defun and stuff.
21:51:01  At least writing a simple lisp interpreter is actually very easy.
22:00:56  where by "lisp" we mean "a vaguely lisp-like language intended to be easy to implement"
22:01:07  actually implementing Common Lisp, Scheme, or Clojure is not easy :)
22:01:49  Common Lisp is weird
22:02:23  (R5RS Scheme is not horrifically hard, either, but I wouldn't call it easy)
22:02:47  Scheme and Clojure are closer to the "Lisp-spirit"
22:03:17  i wonder what's the hardest part of R5RS to implement
22:03:20  maybe dynamic-wind
22:04:02  though maybe that's secretly easy in a CPS transform or something
22:04:04  i haven't thought about it
22:06:56  uh oh, the first hit for r5rs dynamic-wind is an oleg article :/
22:07:30  kmc: call-with-current-continuation + dynamic-wind are A Fun Pair
22:07:43 -!- sivoais has quit (Ping timeout: 260 seconds).
22:07:51  dynamic-wind, as in like hurricanes?
22:07:57  olsner: danger danger high voltage
22:08:06  inherit the dynamic-wind
22:10:19  "Fortunately, delimited control operators let application programmers write dynamic-wind themselves; that function is no longer a primitive, is no longer hard-to-explain, and no longer has to be provided by the implementation."
22:13:36  Dead CodeEval
22:13:42  Fuck yourself with a rusty rake
22:13:51  *Dear
22:14:18  One of the challenges is "Email Validation "
22:14:20  (followup question: what are these delimited control thingies?)
22:14:31  "You are given several strings that may/may not be valid emails. You should write a regular expression that determines if the email id is a valid email id or not. You may assume all characters are from the english language."
22:14:43  lol "no longer hard-to-explain"
22:15:39  if it wasn't hard, what's it doing on oleg's site in the first place?
22:15:42  http://www.ultrapico.com/Expresso.htm
22:18:48 -!- copumpkin has quit (Quit: Computer has gone to sleep.).
22:22:30  Sgeo: i.e. this? http://ex-parrot.com/~pdw/Mail-RFC822-Address.html
22:23:38  a correct answer might be that the language of valid email addresses is not regular and cannot be matched by a regexp
22:25:06  that kind of fancy book-learnin' will get you nowhere
22:35:10  !rot13 foo barvaz baz
22:35:10  sbb oneinm onm
22:35:51   (followup question: what are these delimited control thingies?)
22:35:52  shift/reset
22:38:55 -!- Nisstyre-laptop has joined.
22:41:53 -!- copumpkin has joined.
22:42:25 -!- heroux has quit (Ping timeout: 252 seconds).
22:42:34 -!- heroux has joined.
22:44:02 -!- sivoais has joined.
22:51:37  http://soundcloud.com/g3ksan/troll
23:09:19  This recording is hilarious. :-D
23:09:49  ion: Are you using Control.Lens yet?
23:10:33  shachaf: I haven’t written any real code that uses it but i have it in my .ghci
23:10:56  Is "over both" the right way to do it?
23:11:34  I'll probably need to painstakingly learn the operators one by one.
23:11:53  toListOf (both.both) ((1,2),(3,4))
23:12:35  Well, its type is right and it does the right thing. :-P
23:12:50  shachaf: Btw, i added a bunch of ….Lens imports. https://gist.github.com/3909552
23:12:52  Sure, but maybe there's another way of doing it?
23:13:03  ion: I should probably do that...
23:13:11  ion: Gah.
23:13:24  Wasn't your .ghci about 10 lines before?
23:14:09  This is what i posted first. https://gist.github.com/3909552/fb2dd963e317571249d29f5c4d305dc3c233b707
23:14:30  Hmm.
23:15:06  diff -u0 <(curl -s https://raw.github.com/gist/3909552/a92d0b0506154300baaf2be86b011213bfc458cf/.ghci) <(curl -s https://raw.github.com/gist/3909552/170990e52c4499158f45d1738cdf10796f32513f/.ghci)
23:20:04  http://blog.sigfpe.com/2006/12/evaluating-cellular-automata-is.html is this likely to be a good explanation of comonads?
23:20:37  ion: So have you figured out the zipper business?
23:20:48  Nope, haven’t even looked at it yet.
23:21:01  Sgeo: everything sigfpe writes is good
23:21:10  Well, you saw the slide?
23:21:47  zipper ("hello","world") % down _1 % fromWithin traverse % focus .~ 'J' % rightmost % focus .~ 'y' % rezip
23:21:53  Yeah
23:21:54  ("Jelly","world")
23:22:08  But that’s the only thing i’ve looked at wrt. them.
23:24:45  kmc: Are you going to accept typos for the mosh bug bounty?
23:28:13  heh
23:28:16  maybe $0.01
23:28:23  didn't you get some money mining typos in tarsnap?
23:28:28 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
23:28:53  kmc: $20 for running a spellchecker on the codebase.
23:28:54  I’m in tears laughing at this recording. :-D
23:29:05  I got $30 more for "minor bugs"!
23:29:27  kmc: Man, you guys are cheap. Tarsnap gives you a whole $1 per typo!
23:29:38  $1-9, actually.
23:33:46 * ion switched from tarsnap to s3ql + S3
23:36:53  kmc: That's because C is as "close to the hardware" as it gets, right?
23:37:41  y u troll
23:37:57  u started it :'(
23:42:32  o
23:42:42  øis523
23:44:17  Thanks, Hanks. Thanks. http://youtu.be/-C2h6JSnM-E
23:49:59 -!- Phantom_Hoover has joined.
23:51:16  shachaf: I learned how to type ő with Compose!
23:51:18  Compose = o
23:51:29  kmc++
23:51:33  I was just wondering the other day.
23:51:54  I settled for copying it from https://en.wikipedia.org/wiki/Paul_Erdős
23:52:04  it works for u as well
23:52:24  kmc: Presumably it works for anyone who's using the default Compose layout.
23:52:28  i wonder if other vowels with that mark exist in unicode (without combining characters i mean)
23:52:35  womp womp
23:53:28  04F3   CYRILLIC SMALL LETTER U WITH DOUBLE ACUTE     [ӳ]
23:53:49  That's it, though, I think.
23:54:20  kmc: You should get a Unicode search thing! That way you can look things up easily.
23:54:31  I have a file with all of Unicode that I search with less +R
23:54:40  Er, -R
23:58:42  mm
23:59:16  ӳ is used in... Chuvash, a language I have never heard of

2012-10-20:

00:05:09  "Therefore if F' is right-Lobachevsky then |Σ| ≅ ℵ₀. By Newton's theorem, if Darboux's criterion applies then I < Γ'. So ζ is conditionally Erdős."
00:05:41  ok
00:05:50  http://thatsmathematics.com/blog/archives/102
00:08:40  hah
00:09:04 -!- Nisstyre-laptop has quit (Ping timeout: 246 seconds).
00:15:56 -!- Nisstyre-laptop has joined.
00:39:59 -!- DHeadshot has joined.
00:55:01  My program needs to run efficiently. My program is running more efficiently than I expect with my algorithm, which is horribly inefficient. My program is giving wrong results some, but not most, of the time.
00:55:47 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:00:18 -!- Vorpal has quit (Ping timeout: 276 seconds).
01:06:21  Fixed the code to be in line with my mental algorith,
01:06:24  algorithm
01:06:29  Getting out of memory errors
01:11:27 -!- DHeadshot has quit (Read error: Connection reset by peer).
01:12:58  Figured out a new algorithm
01:13:09  perhaps bonghits will fix your out of memory errors
01:16:03 * shachaf must be missing something there.
01:19:03  The Looney Tunes Show 1x22 finally gets to Looney Tunes levels of drag.
01:21:21  missing what
01:21:26  why does Gregor have voice
01:21:32  i thought #esoteric was a classless society
01:21:48  kmc: Looks like it's a reference to a git commit involving Radeon?
01:22:20  it's a reference to http://www.jerkcity.com/jerkcity490.html
01:22:56  kmc: I have +v because I'm SPECIAL.
01:23:07  Dangit, it's not fast enough, I think
01:25:25  It's annoying that using an iterable in Python permanently mutates/consumes it
01:27:51  http://goatkcd.com/1123/sfw nsfw
01:29:28  kmc: I've yet to click on any of these links.
01:29:45  I'm vaguely curious what happens to a one-panel comic, but not enough to click.
01:30:09  what happens in what sense
01:30:33  I don't really know!
01:30:49  http://blog.ezyang.com/2012/10/duality-for-haskellers/
01:32:23  Sgeo: it is annoying; on the other hand, reasoning about space usage would be harder were it not the case, I think
01:33:04  It's already harder with lists in Haskell!
01:33:43  writing... code... is harder
01:34:13  I think I may have screwed up my ability to write imperative code.
01:34:53  that sucks
01:35:01  writing imperative code is an important skill in any language
01:35:27  not necessarily any
01:35:47  whether it's important depends not on the language but on the problem you're trying to solve
01:36:38  The problem I'm trying to solve tends to be the language not supporting functional idioms sufficiently
01:36:38  that's tautological
01:38:09  Tautologies tend to be.
01:44:00  i don't believe you
01:44:26  unless you are just doing toy functional programming exercises, you will need imperative style some of the time
01:44:57  i like Haskell not because it's OMG HARDCORE PURE FP, but because it actually supports imperative programming in a good way, a way which makes sense to people who understand FP too
01:45:26  but you know for every person who understands the IO monad there are 50 beginners talking about how pure the factorial function is and how it's going to destroy imperative programming next year
01:45:30 * kmc semi-coherent rant
01:45:48  i don't understand why you are making lots of assumptions about what i meant
01:46:30  i'm not assuming
01:46:36  i'm ranting off what Sgeo said
01:46:40  Isn't "coalgebroid" a great word?
01:46:46  no
01:46:52  oh
01:46:56  i thought you were replying to my statement
01:47:07  kmc: What about "iggrammatical"?
01:47:09  that the only reason he needs imperative programming is "the language not supporting functional idioms sufficiently"
01:47:12  anyway I disagree with " unless you are just doing toy functional programming exercises, you will need imperative style some of the time", at least philosophically
01:47:28  well it is a pragmatic statement, not a philosophical one
01:47:48  well i sort of disagree with it pragmatically too
01:47:49  see also: FRP still doesn't work
01:47:58  there are FRP libs that are mature enough for doing fairly involved stuff
01:48:00  A pragmatist in our midst!
01:48:02  well maybe it started working in the past year and nobody told me
01:48:08  depends what you mean by "doesn't work"
01:48:09  kmc, well, I don't have an issue when I need to write imperative code to handle imperative things, it's just imperative code when I know more functional languages have function idioms for those htings
01:48:11  *things
01:48:15  do you know of any major problems with reactive-banana/reactive-banana-wx?
01:48:15  ah, i see
01:48:21  that makes more snense
01:48:24  (And I understand those idioms and their use sufficiently well)
01:48:25  elliott: no, i haven't used them at all
01:48:29  I don't know of any semantic glitches it has, performance seems good...
01:48:38  i never tried doing FRP because everyone talked about how half-baked it was
01:48:41  but that may be out of date
01:48:42  what *doesn't* work is one frp framewotk to rule them all, yet
01:48:44  *framework
01:48:50  there are tradeoffs still
01:49:04  Not entirely comfortable with the idea of monad transformers to represent an entire running program's state+everything
01:49:10  but, I still think you can write a good amount of stuff without resorting to imperative programming right now
01:49:15  So more willing to do that stuff imperatively
01:49:19  elliott: You know who's "cool"?
01:50:23  I think part of kmc's point is that "resorting to imperative programming" assumes that "imperative" is always the worst way to express something.
01:50:33  Whereas in practice it can the clearest way to express your intent.
01:50:47  (But I'm not kmc so I shouldn't say what his point is.)
01:51:39 * elliott likes to be militantly anti-imperative as a general policy; that means I have to try hard to show to myself that imperative programming *isn't* the best way to express any given thing.
01:51:44  Which is good, because the results are sometimes insightful.
01:51:48  (Okay, only occasionally.)
01:52:30  elliott: Right, sometimes "your intent" is the thing that's misguided, and learning to "figure out what your intent really is" is one of the values of learning Haskell and such things.
01:52:40  But sometimes not.
01:53:41  i think "functional" and "imperative" is a bad choice of terms
01:53:45  shachaf: I think imperative programming often seems like the right choice just because of the baggage of the systems we use (like Unix)... obviously that means it *is* the right choice in practice, but I think it tends to not be inherent to the problem.
01:53:51  i think things should be more "denotational"
01:53:56  See also: strings as a nearly-useless data type.
01:53:56  and maybe "declarative"
01:53:58  (Booleans too, to some degree.)
01:54:05  imperative programming could be made more denotational and declarative
01:54:07  kmc: Conal, is that you?
01:54:12  haskell is a small step in that direction
01:54:28  I forget if I decided strings have any value.
01:54:30  But I think I didn't.
01:54:35  @quote stark
01:54:35  AlanPerlis says: The string is a stark data structure and everywhere it is passed there is much duplication of process. It is a perfect vehicle for hiding information.
01:54:47  elliott, what's wrong with strings and booleans?
01:55:03  @google boolean blindness
01:55:04  http://existentialtype.wordpress.com/2011/03/15/boolean-blindness/
01:55:05  Title: Boolean Blindness « Existential Type
01:55:07  @google string sightlessness
01:55:08  http://legal-dictionary.thefreedictionary.com/strike+sightless
01:55:08  Title: strike sightless legal definition of strike sightless. strike sightless synonyms ...
01:55:09  Sgeo: The former is useless; the latter is harmless.
01:55:12  er.
01:55:14  Sgeo: The former is useless; the latter is harmful.
01:55:18  Also the former is often harmful too.
01:55:26  elliott: Is [Bool] useless or harmful?
01:55:29  http://existentialtype.wordpress.com/2011/03/15/boolean-blindness/ is a good description of the problems with booleans, yes.
01:55:35  shachaf: Yarmful.
01:58:02  Anyway I guess booleans are better than strings.
01:58:10  You can take them as configuration and that's not as bad as it could be.
01:58:12  Though it's still bad.
01:58:21  And even configuration usually wants its own types.
01:58:43  elliott: I prefer the strings "true" and "false".
01:59:51  kmc: Did you see the lens slides?
01:59:56  Or elliott, or whoever else.
02:00:05  Sgeo: Does Clojure have lenses?
02:00:08 -!- Nisstyre-laptop has quit (Quit: Leaving).
02:00:28  What slides?
02:00:46  Erm. I wanted to write a lens library once. But whenever I try to describe them to #clojure, they don't see the value.
02:00:48  https://groups.google.com/d/msg/bahaskell/YifnIpEu2OY/kddoyuvdCOMJ
02:01:18  Oops.
02:01:28  Er, no oops.
02:01:31  noops
02:01:45  no operations
02:01:58  no ooperations
02:02:28  Phantom_____Hoover: I define a new language as follows:
02:02:40  A program is composed of the character < > - + [ ] , .
02:02:44  Any other character is illegal.
02:02:52  The characters < > - + [ ] , . are all nops.
02:08:53  An interpreter in your new language: ++[->.<<[-,<+>++]]
02:09:01  A quine: 
02:09:34 -!- copumpkin has quit (Ping timeout: 240 seconds).
02:09:59  Jafet: I guess I should introduce v2.0 of the language.
02:10:06 -!- copumpkin has joined.
02:10:08  v2.0 disallows the []s to be balanced.
02:11:46   A program is composed of the character < > - + [ ] , .
02:11:50  that's not a character
02:11:50  Is my quine legal in v2.0?
02:12:22  I met < > - + [ ] , . once. Great character.
02:12:50  elliott: It is in UNICODE VERSION 7
02:13:55  They should make a unicode glyph that consists of a table of all unicode glyphs.
02:18:20  Including itself, obviously.
02:21:03  An idea is programming using the linear logic, with additive conjunction, multiplicative conjunction, additive dusjunction, multiplicative dusjunction, and other stuff like "!" and so on, you can encode intuitionistic logic in linear logic using "!" so perhaps if you have a category, you can make "!" like a comonad for using ordinary functions? (Like you use "Cont" monad in Haskell to make continuations)
02:21:30  zzo38: cmccann in #haskell is all about linear logic, I hear.
02:25:55 -!- Max00355 has quit (Read error: Connection reset by peer).
02:37:22 -!- copumpkin has quit (Ping timeout: 245 seconds).
02:37:56 -!- copumpkin has joined.
02:42:17 -!- augur has quit (Remote host closed the connection).
03:14:42 -!- augur has joined.
03:27:48  https://www.destroyallsoftware.com/talks/wat
03:27:54  I'm lolling
03:28:11  Yeah, that talk is brilliant.
03:32:00  pikhq: do you know how wayland+xwayland compares in binary size to x11 right now
03:32:04  i have actual reasons for asking this
03:35:27  I wonder what causes the overhead when running OpenGL programs with Compiz? They run much smoother without compositing. One would think a single extra pass through render-to-texture wouldn’t cause anything noticeable by itself.
03:36:00  I suppose Wayland is more efficient at that.
03:39:09 -!- ogrom has joined.
03:41:53  Because compiz
03:42:45  jafet: Another OpenGL compositor on X.org might not have the issue?
03:43:58  Is there any other?
03:44:31  A hypothetical one
03:44:51  I.e. are you saying the problem is in Compiz, not X.org?
03:46:41  I don't know. Compiz has many problems.
04:00:57  How do you tell Mozilla to load the entire text first before loading images and CSS?
04:48:36 -!- Nisstyre-laptop has joined.
04:52:58  colon colon one y'all
04:53:09  kmc: lolcathost?
04:53:14  yessss
04:53:42  -    if ((request.META['REMOTE_ADDR'] != '127.0.0.1')
04:53:42  +    if ((request.META['REMOTE_ADDR'] not in ('127.0.0.1', '::1'))
04:53:56  what if it's 127.0.0.2
04:54:12  kmc: Did you know you can drop octets from an IP address and it fills them in according to some complicated pattern?
04:54:29  a.b.d -> a.b.0.d
04:55:21  (d can be a number up to 256^2, in which case it also works for c.)
04:55:45  Also you can use 0x or 0 for any octet.
04:58:43  anybody happen to know what a "two-way server" is?
04:59:03  far as i can tell it's an obscure term for either dual core or dual processor
04:59:05  \o/
04:59:09  |O|
04:59:14  How do you do it?
04:59:24   \ o /
05:01:04  ahh, it's offline still
05:01:06  sorry :(
05:05:16  yeah people say "four-way SMP" and such
05:05:28  it probably does not distinguish dual core and dual socket
05:05:36  mk
05:05:45  i'm pretty sure he meant multi processor specifically
05:05:53  the usage was real weird
05:06:03  well in some cases "multi processor" might also include multi core
05:06:06  also apparently if you replace a dual-core system you should get a new dual-core system
05:06:09  :facepalm:
05:06:13  ?
05:06:29  when you first said "two-way server" i thought of http://www.supermicro.com/products/nfo/1UTwin.cfm
05:06:53  ah, just editing some technical articles
05:06:59   m o m
05:07:00  which is two independent servers in a 1U case
05:07:06  /o/
05:07:08  unfortunately the guy doing the writing here ... apparently doesn't know jack
05:07:11  How do you do it, myndzi?
05:07:11  and they also have 4 servers in a 2U case
05:07:17  like i said.. it's offline, sorry
05:07:24  Oh, that's what you meant.
05:07:25  kmc: thanks :)
05:07:32  :-(
05:07:35  shachaf: yeah, my work comp and laptop are up atm
05:07:36  lol
05:07:39  but not my home desktop
05:07:45  hesktop
05:10:18  that's not quite as dense as blades, but it's probably a better deal if you only need a few of them
05:13:33  according to smartctl, my hard drive has spent 20 billion years with the head flying
05:14:44  That's a lot of years.
05:14:56  20 billion years isn't cool, though.
05:15:18  what about 20 trillion years?
05:15:23  Now *that's* cool.
05:15:28  apparently seagate drives just report nonsense to smartctl for fun
05:15:29  http://www.users.on.net/~fzabkar/HDD/Seagate_SER_RRER_HEC.html
05:15:36  FLYING THROUGH SPACE AND TIME
05:15:40  I,I 32-bit integers aren't cool. You know what's cool? 42-bit integers.
05:16:48  Bah. N-bit integers where N is a non-integer computable is cool.
05:17:04  kmc: i think you could get a good 3 to 4 rants out of this tweet https://twitter.com/ryah/status/258634435161899009
05:17:19  good to know node.js has such a sound engineer behind it
05:17:30 -!- monqy has joined.
05:17:36  (haha @ implication that "C/C++" (haha @ that too) isn't "legacy bullshit" also)
05:17:43  (haha @ @)
05:17:44  Sweet fuck.
05:17:47  Uh. By "interesting" do they mean "interesting + likely to be widely used"?
05:17:55  elliott: Well, technically C++ is "interesting".
05:18:01  hi
05:18:12  C/C++
05:18:15  & then:
05:18:16  https://twitter.com/ryah/status/258635644681728000
05:18:17  It teaches how not to design a programming language by example.
05:18:26  https://twitter.com/ryah/status/258635662587199489
05:18:26  https://twitter.com/ryah/status/258635676726218752
05:18:44 * Sgeo sads
05:18:52  No reason given. At all.
05:18:54  monqy: hello
05:18:58  hey sgeo how's your clojure without lexical scoping going
05:19:02  yeah this is such transparent trolling
05:19:05  I'll give him a very slight bit of credit: Rust actually appears interesting.
05:19:13  i can't really work myself up over it
05:19:32  elliott: i heard C++ is for fat people
05:19:36  monqy, on hold while I try to determine if it actually would be better than Kernel
05:19:41  ok
05:20:08  You could accomplish more or less the same thing with Kernel's eval, I think
05:20:15  i hope that sometime near the end of The Office (US), the characters suddenly become aware of the fact that Kevin has gradually developed a severe cognitive impairment over the past decade, and find this profoundly disturbing
05:20:24  Well, not the same exact thing, but similarish enough, I think
05:20:54  kmc, does Kernel have quasiquoting? I vaguely remember "no", but not sure.
05:21:10  i don't remember
05:21:14  And if the answer is "no", who do I have to slap
05:21:17  are you asking about the `(a b) concrete syntax
05:21:33  or about the quasiquote special form
05:21:34  or what
05:21:46  presumably quasiquote wouldn't be a sepecial form, just an operative you can define yourself
05:21:57  and it's not super useful for the kernel way of doing things
05:21:59  Well, `(a b) concrete syntax would be nice, preferably translating into a particular set of operatives
05:22:12  i assume `x would be sugar for (quasiquote x) as in scheme
05:22:17  and ,x for (unquote x)
05:22:21  Yes
05:22:33  `,@x
05:22:38  Distinctly different from the Common Lisp style things of not actually having a concrete translation
05:22:42  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ,@x: not found
05:22:52  anyway quasiquote is not that useful for writing operatives, but it might sometimes be useful to use traditional lisp-ish macros in kernel
05:23:01  i think it should be easy to implement defmacro as an operative
05:23:15  i wonder if there is some kind of "quasieval" syntax you could define, to make writing operatives nicer
05:24:12  kmc, well, I more wanted to emulate Tcl-style commands, but with quasiquoting, since Tcl doesn't have nice quasiquoting syntax built-in and that sucks
05:24:46  (define list (vau xs env (if (nil? xs) nil (quasieval env (cons ,(car xs) ,(cdr xs))))))
05:25:09  => (define list (vau xs env (if (nil? xs) nil (cons (eval env (car xs)) (eval env (cdr xs))))))
05:25:29  awkward to use ` because you need to put the env parameter somewhere
05:27:34  http://twitter.com/ryah/status/258665167934611457
05:27:41  mmmmmmmmmmmmmmm
05:27:55  good to know his problem is uninteresting
05:29:13  monqy: ais523: you might like: http://www.ioccc.org/2012/tromp/hint.html
05:29:23  He could at least acknowledge that without PL research, he'd be stuck writing code in .... I'm not even sure
05:29:24  elliott: stop trolling by proxy
05:29:45  kmc: My friend said that trolling by proxy is fun but I don't believe him.
05:29:45  COBOL?
05:29:45  hey guys my cousin's barber says haskell causes aids
05:29:51  How can I show him the error of his ways?
05:30:27  Machine code.
05:30:41  He should write all his code in 0s and 1s from now on.
05:31:00  kmc: what is #esoteric fo rthen
05:31:08  if not crap
05:31:16  Silly elliott. #esoteric is for trolling directly, not by proxy.
05:31:23  But we shouldn't troll kmc, or he might leave. :-(
05:31:30  programming community full of anti-intellectual blowhards; film at 11
05:31:31  come on
05:31:41  actually though i have violated my own rule about the word 'community'
05:31:42  it is art to dismiss list but talk about scheme-relative JS as interesting and innovative and not legacy crap
05:31:44  *lisp
05:31:45  i'm not sure what to call that community
05:31:59  if i was trying to rile plt people up i couldn't do it so well
05:32:01  hacker news jackoff community
05:32:23  Then I'll be stuck either looking for bugs in Mosh or not talk to kmc!
05:32:47  i dread the day when the startup i'm working for now gets posted to hacker news
05:33:04  kmc: Is it still a secret what it does?
05:33:09  yeah
05:33:17  but it's not the interesting kind of secret
05:33:17  sorry
05:33:25  kmc is working on bombs
05:33:37  we're making a useful product, but it's not like ksplice where it's going to blow your mind that it's even possible
05:33:44  kmc is working on stealth bombers.
05:33:47  clearly
05:33:55  That's why his startup is in Stealth Mode.
05:33:57  kmc: ksplice didn't really surprise me
05:34:00  sorry
05:34:03  i am too ... anti-jaded
05:34:09  haha
05:34:29  i'm not really surprised that it worked as a research project
05:34:42  well that's the hard part
05:34:45  then you send it off to the engineers
05:34:47  and they ruin it
05:34:56  but i am very impressed that they managed to make a commercial product that was deployed on 200,000+ machines and crashed almost none of them
05:35:13  of course there were 2 years of work in between those two stages
05:35:43  I,I deployed on ℵ₁ machines and crashed almost none of them
05:35:47  hehe
05:35:52  Only a countable number!
05:35:54  is that alef or math alef?
05:36:00  2135   ALEF SYMBOL     [ℵ]
05:36:10  The other one puts you in RTL mode, which is annoying.
05:36:13  or blackboard bold script italic math alef
05:36:13  hehe
05:36:36  (But on the other hand I have to type in the codepoint instead of switching my keyboard to Hebrew mode.)
05:36:51  kmc: whoa, dude, Unicode has codepoints for letters + nikud!
05:36:56  I thought it just had combining nikud.
05:36:57  I want to make up a chess variant having googolplex number of kind of pieces. I already wrote of some idea of such things.
05:37:13  shachaf: There are various things I dislike about Unicode
05:37:15  is there continuouschess
05:37:23  continuous chess*
05:37:27 * kmc should get a new spacebar
05:37:29  continuous chess got made up in here once
05:37:30  it went badly
05:37:35  kmc, "almost"?
05:37:38  what was continuous
05:37:42  piece position or also identity?
05:37:44  kmc: the board
05:37:52  mostly the problem is that you can't express the moves you want to make
05:37:54 * Sgeo should try continuous chess
05:37:56  1EE00   ARABIC MATHEMATICAL ALEF     []
05:38:02  kmc: i think the pieces might have been continuous too
05:38:05  honestly i do not remember
05:38:05  There's an ARABIC MATHEMATICAL ALEF but no HEBREW MATHEMATICAL ALEF?!
05:38:19  mathematical elf
05:38:29  did rooks and bishops have a facing direction
05:38:38  Another idea is to make up a description of googolplex number of variants all at once
05:38:43  This isn't it, is it?
05:38:43  http://www.chessvariants.org/other.dir/continuouschess.html
05:38:45  kmc: Do you know Gess?
05:38:47  It says created 2001
05:38:49  no
05:38:51  "Chess" played on a Go board.
05:38:58  yes Sgeo we made up continuous chess in this channel in 2001
05:38:59  It's kind of neat.
05:39:02  then put it on some random chess variants website
05:39:04  how did you guess
05:39:24  Hence me thinking that that isn't it.
05:39:25  A "piece" is any 3×3 square that contains at least one of your Go pieces and none of the enemy's.
05:39:35  Stones.
05:39:41  I do know Gess too
05:39:46  The 8 outer stones are bits that decide in which direction your "piece" can go.
05:40:02  The inner stone says whether it can move just one step or as far as it wants.
05:40:21  Your "queen" is 9 pieces, and your "king" is a ring. You lose when you have no ring.
05:40:30  (You can make additional kings if you're careful.)
05:40:31  weird
05:40:48  and moves are by 1 rather than 3?
05:40:50  You can make strange new pieces that can only move in a particular direction.
05:41:07  this is like go + chess + game of life
05:41:18  Hmm, I'm not sure...
05:41:32  Ah, there's a Wikipedia article. https://en.wikipedia.org/wiki/Gess
05:41:36  It says it can move up to 3.
05:41:53  in that it depends on identifying and cataloguing formations that are bigger than the 'physics' of the game, and can form out of other things
05:42:06  Right.
05:42:11  kmc: going to "troll" you with this too https://plus.google.com/u/0/115212051037621986145/posts/HajXHPGN752
05:42:26  "abstractions are slow in python so if you want to write fast python don't use them" -- gvr
05:42:51  elliott: Did you see bos's slides?
05:43:03  What if you make continuous chess where your moves are limited to rational numbers, or to algebraic numbers, or allowing rationals and quadratic surds
05:43:08  http://bos.github.com/reaktor-dev-day-2012/reaktor-talk-slides.html
05:43:25  And have a minimum movement
05:43:52  elliott: Guido was at ekmett's lens talk yesterday.
05:44:21  that's ok
05:44:28  I can make fun of people even if they attend edwardk talks
05:44:32  that's my superpower
05:44:53  Python's going to get lenses now, that's all I'm sayin'.
05:45:32  A go variant where you can't see the opponent's stones
05:45:54  And if you place a stone on an occupied place, the stone disappears
05:46:23  i'm just so burnt out on caring about people being wrong on the internet about programming languages
05:46:31  i did a tour of duty in /r/programming and two in #haskell
05:46:39  kmc: It's a sign you're getting old.
05:46:43  haha
05:46:43  (And wise?)
05:46:45  probably
05:46:48  maybe not that one
05:47:00  kmc: you should join #haskell again for the good times
05:47:08  is it good now
05:47:11  kmc: heck no
05:47:16  They were arguing about whether Lisp has syntax an hour ago.
05:47:26  (To be fair, you get that in here too.)
05:47:40  Someone linked to paulgraham.com an hour ago
05:47:44  Also someone was asking whether Haskell was used in any real-world projects and refusing to read any links.
05:48:23  more like poorgraham imo
05:48:54  Is there a channel that's like #haskell, except for all the bad parts?
05:48:59   Also someone was asking whether Haskell was used in any real-world projects and refusing to read any links.
05:49:02  who was this i wanna read it in the logs
05:49:07  elliott: No one.
05:49:20  that's not helpful
05:50:00  You can find it quickly by searching for "real-world", because that phrases comes up infrequently there
05:50:08  kmc: I went to a talk about graph coloring and the birthday problem and variations.
05:50:43  Jafet: There's only one result for "real-world" and one for "real world" in today's log. :(
05:50:44  Did you know that a pretty good approximation for "number of people you need in a room to have a 50% chance that two share the same birthday" is 1.2√c, where c is the number of days in a year?
05:51:02  no
05:51:53  Also coloring graphs is hard. :-(
05:54:37  I knew all those children's books had sinister intentions.
05:57:06  whoa, dude
05:57:06  Orwell did not invent the term "two minutes hate"; it was already in use in the First World War.[1] At that time, British writers satirised the German campaign of hatred against the English, and imagined a Prussian family sitting around the kitchen table having its "morning hate".[2]
05:59:29  Hmm. Well, if using a field and using getter/setter had the exact same syntax, with no oddities, I don't see any problems with using fields directly.
05:59:54  C# that's not the case, fields can be used in ways that properties (getter/setter combinations) cannot
06:00:08  There is also leap years though
06:00:24  So better to start off with properties rather than using fields, then needing to convert to getter/setter and finding that it breaks some code.
06:00:54  zzo38: Leap years don't influence it much.
06:01:03  In fact, even actual birth statistics don't influence it much.
06:01:45  Did you know that in the US, there are 20% fewer births on weekends?
06:01:47  (So I hear.)
06:03:35  kmc: Did you know that Compose v / makes √?
06:03:40  Radical, man.
06:03:44  nice
06:03:56  No, I didn't know that there are 20% fewer birth on weekend in US.
06:06:18  why is it
06:06:37  20% of labor is induced and doctors don't like to work on weekends, or something along those lines.
06:07:28  Cæsarean sections, too, I guess.
06:11:58  makes sense
06:13:09  20 % of labor is mathematically induced.
06:13:28  mathematical induct ion
06:14:10  A friend who's in liquor production
06:14:10  Owns a still of astounding construction.
06:14:11  The alcohol boils
06:14:11  Through old magnet coils;
06:14:11  She says that it's "proof by induction."
06:14:24  > cycle "HA"
06:14:25    "HAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHA...
06:16:33  not a true limerick as it lacks a dirty joke
06:16:40  that's like a haiku without a seasonal reference
06:17:24  I have an incomplete song with a (5+7+5)/8 rhythm.
06:18:52  kmc: Have you read some of Lear's limericks?
06:19:20  I don't really get them.
06:20:13  no
06:20:18  Preview from a crappy General MIDI export http://codu.org/webmidi/gen/924563928975/924563928975.ogg
06:20:33  elliott: Have you seen the way edwardk "overloads function application"?
06:21:46  Did you write this music?
06:21:50  yeah
06:22:05  It’s unfinished.
06:22:13  kmc: I changed some scenery but it didn't really help.
06:22:14  When, and what software?
06:22:25  Do you have more advice?
06:23:26  for what problem?
06:23:31  and which scenery?
06:23:45  I wonder the same thing
06:23:46  zzo38: I made a score in Lilypond () in 2011-01. You also get a crappy General MIDI file out of it almost for free.
06:25:12  OK
06:28:40   elliott: Have you seen the way edwardk "overloads function application"?
06:28:41  ?
06:28:41  Are there any simpler versions of Lilypond which will generate DVI output and do not require so many source files and that stuff?
06:28:43  You mean a ($) class?
06:29:03  elliott: I mean isomorphism.
06:29:23  inc :: Num a => a -> a <-> a; inc = isomorphic (+1) (subtract 1)
06:29:29  Lilypond even requires Python and Scheme and all that stuff too
06:29:31  inc 4 -- 5
06:29:37  from inc 5 -- 4
06:30:10  zzo38: You generally use just one source file with Lilypond.
06:31:14  shachaf: I don't get it.
06:32:07  Hmm
06:32:18  How is that <-> legal? Language extension?
06:32:38  I think I get it but I don't get the types
06:35:31  elliott: Oh, maybe I got the type wrong?
06:35:35  And the syntax sometimes changes.
06:36:00  elliott: Anyway, inc acts like a function when you apply it, but you can also get the other part of the isomorphism from it.
06:36:12  For example it requires Unicode
06:37:12  Which encoding of unicode?
06:37:17  UTF-8?
06:37:31  Who said anything about encodings?
06:37:58  shachaf, I should note that I didn't look at the type that closely
06:39:18   elliott: Anyway, inc acts like a function when you apply it, but you can also get the other part of the isomorphism from it.
06:39:19  How?
06:39:55  > (\x -> x x) (\x -> x x)
06:39:57    Occurs check: cannot construct the infinite type: t = t -> t1
06:39:59  class Category k => Isomorphic k where isomorphic :: (a -> b) -> (b -> a) -> k a b
06:40:07  isntance Isomorphic (->) where isomorphic = const
06:40:36  data Isomorphism a b = Isomorphism (a -> b) (b -> a); instance Category Isomorphism; instance Isomoprhic Isomorphism
06:40:45  type a <-> b = forall k. Isomorphic k => k a b
06:40:51  from (Isomorphism a b) = isomorphic b a
06:42:54  elliott: "pretty crazy huh"
06:44:06  oh
06:44:07  typeclasses
06:44:08  they don't count
06:45:07  > (\x -> x) (\x -> x)
06:45:09    Overlapping instances for GHC.Show.Show (t -> t)
06:45:09     arising from a use of `...
06:45:18  > (\x -> x) 4
06:45:19    4
06:45:22  > (\x -> x) id
06:45:23    Overlapping instances for GHC.Show.Show (a -> a)
06:45:23     arising from a use of `...
06:45:27  > id id
06:45:29    Overlapping instances for GHC.Show.Show (a -> a)
06:45:29     arising from a use of `...
06:45:52  FreudFull
06:46:02  > ego
06:46:03    Not in scope: `ego'
06:46:07  > superego
06:46:08    Not in scope: `superego'
06:50:42  Is there a version of LilyPond which generates DVI output and does not require Freetype, Ghostscript, Guile, Python, Pango, Unicode, etc?
07:00:03  Or similar program?
07:18:48  Depends on how you define similar. The major feature of Lilypond is how much they have made effort over the years to make the output look non-computer-ish.
07:19:08  Is your floppy disk running out of space?
07:21:33  No, I am using a hard disk.
07:23:03  5GB one?
07:24:26  Couldn't it be done with just one source-file (other than fonts), and then use ATLAST for extensions (also just one source file), and have macro files (just one for standard notation; others for specialized), use MCK-like syntax, output to DVI?
07:25:20  FreeFull: No, it is 200GB
07:29:05  I can understand why they would make effort over the years to make the output look non-computer-ish it is good idea. However, I don't think they should need many source files and all that other stuff to do that.
08:00:26  How difficult would it be to take the LilyPond source files, remove half of the stuff, change some of the stuff, and have it compile without anything more than the C++ compiler and no extra libraries?
08:01:05  try it
08:04:39  I looked at the source files and it appears to be way too complicated.
08:05:38  Most source does on first look
08:09:27  Many source files are not very large, but there are a lot of them, in a big mess, in multiple programming languages (including PostScript), a huge number of other files, too many external files needed, etc
08:10:49  Ideally nothing else should be needed except a DVI driver, and METAFONT (if you want to compile the fonts).
08:15:41  It even has a lot of makefiles, many files in Scheme, C++, Python, why does it need to be????
08:16:34 -!- epicmonkey has joined.
08:24:32  Even if there is one that does not make the output look non-computer-ish, is there one which will make DVI format output and which does not use Unicode?
08:25:07  I sincerely don’t see what’s wrong with Unicode.
08:25:28  A score-writing system that heavily restricts the languages you can use for the lyrics would be strange.
08:25:49  And which requires only one programming language instead of five?
08:26:22  I don’t think using only one programming language prevents you from using Unicode.
08:27:43  ion: You don't need to restrict the languages you can use for the lyrics just because Unicode won't work. Just do it the way TeX does it
08:28:17  Yeah, writing Chinese in the variants of TeX that don’t support UTF-8 is nice.
08:29:43 -!- mekeor has joined.
08:30:02  Actually it is possible to write a macro in Plain TeX which will parse UTF-8 or other encodings you might use; I have done this. So you can write macros for the encoding you want.
08:30:52  I thought the goal was to be simple, with just a couple of files of source code. Now we’re going to have turing-complete macros?
08:31:32  Well, you should have some extension engine whatever it is; I suggested ATLAST.
08:31:57  (Which is a single C source file and a header file, as far as I can tell)
08:32:55  Problem with Unicode (for any uses, really) is the complicated stuff like character properties, changing text directions, and various other things
08:33:34 -!- monqy has quit (Quit: hello).
08:34:06 -!- mekeor has quit (Remote host closed the connection).
08:37:03 -!- monqy has joined.
08:41:41  Even if you do use Unicode, it shouldn't need to use a list of character properties and that stuff.
09:02:59  Program such as TeX works fine with just one source file, one macro file, and a few fonts. Same with METAFONT, LodePNG, TeXnicard, Famitile, and others.
09:04:32 -!- zzo38 has quit (Remote host closed the connection).
09:17:41 -!- MoALTz has joined.
09:52:48 -!- copumpkin has quit (Ping timeout: 244 seconds).
09:53:23 -!- copumpkin has joined.
09:56:50 -!- monqy has quit (Quit: hello).
09:58:50 -!- elliott has quit (Ping timeout: 255 seconds).
10:39:16 -!- barts has joined.
10:39:21  hi
10:49:52 -!- Vorpal has joined.
11:00:27 -!- Phantom_Hoover has joined.
11:11:06 -!- MoALTz has quit (Quit: Leaving).
11:43:55 -!- ogrom has quit (Quit: Left).
12:02:52 -!- carado has joined.
12:09:46 -!- hagb4rd has quit (Read error: Operation timed out).
12:20:11 -!- coppro has quit (Read error: Operation timed out).
12:20:18 -!- coppro has joined.
12:20:30 -!- mindlessDrone has joined.
12:50:14 -!- copumpkin has quit (Ping timeout: 240 seconds).
12:50:49 -!- copumpkin has joined.
13:18:11 -!- atriq has joined.
13:47:38  Well, I have new shoes
13:54:45  The new shoes! Is it the 2012 model? 
13:55:06  is it the green model?
13:55:27  can you walk with 'em?
13:56:13  Blue model
13:56:29  I think they're the 2012 model
13:57:37  how fast are they?
13:59:05  which OS?
14:00:50 -!- Frooxius has joined.
14:01:59  olsner, I dunno, other factors are holding it back
14:02:03  mindlessDrone, Nike
14:02:08 -!- carado has quit (Ping timeout: 252 seconds).
14:07:31 -!- atriq has quit (Ping timeout: 244 seconds).
14:09:34 -!- jix has quit (Ping timeout: 240 seconds).
14:23:08 -!- ogrom has joined.
14:28:18 -!- ogrom has quit (Quit: Left).
14:48:11 -!- hagb4rd has joined.
15:24:40 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
15:27:17 -!- TheJimmyJames has joined.
15:30:45 -!- TheJimmyJames has quit (Client Quit).
15:37:56 -!- Phantom_Hoover has joined.
15:40:48 -!- AnotherTest has joined.
15:40:53  Hello
15:41:25  Hi
16:03:51  hi
16:04:59  `? hi
16:05:10  hi? ¯\(°_o)/¯
16:09:06 -!- atriq has joined.
16:09:07  `log iterate
16:09:38  2010-07-04.txt:14:15:08:  please obliterate this feature
16:09:43  > iterate (<|> " Hello!") mempty
16:09:44    [""," Hello!"," Hello! Hello!"," Hello! Hello! Hello!"," Hello! Hello! Hell...
16:12:29 -!- impomatic has joined.
16:21:20 -!- epicmonkey has quit (Remote host closed the connection).
16:21:36 -!- epicmonkey has joined.
16:35:36  Obliterate literate iterators.
16:42:11 -!- impomatic has quit (Quit: http://BASICcomic.com).
16:42:20 -!- ogrom has joined.
16:42:36 -!- ogrom has quit (Client Quit).
16:43:15  > iterate (id)
16:43:16    Overlapping instances for GHC.Show.Show (a -> [a])
16:43:16     arising from a use of...
16:43:21  > iterate (id) 0
16:43:23    [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,...
16:53:47 -!- elliott has joined.
17:13:19  elliott, \o/ Hi!
17:13:32  why didn't myndzi react to that?
17:13:34  \o/
17:13:37  weird
17:13:52  http://www.reddit.com/r/ProgrammerHumor/comments/11rcrl/google_has_their_own_version_of_chuck_norris_joke/
17:14:20  is there any conceivable reason why i would click that link
17:15:18  Because they're slightly humorous?
17:15:33  oh boy /r/ProgrammerHumor
17:15:43  i'm sure this won't at all make me want to murder everyone
17:17:03  hey guys there's this little-known comic called xkcd, it's really funny
17:17:07  anyone else like it
17:17:49  Phantom_Hoover: actually, I find xkcd more insightful than funny
17:17:55  although some of the side material is hilarious
17:18:43  and randall munroe seems to be really good at apocalyptic overthinking
17:19:17  kmc: something called /r/programmerhumor is one thing
17:19:22  kmc: the chuck norris part worries me more about that url though
17:19:24  Phantom_Hoover: i only like obscure nerdy things, like video games, and movies based on superhero comics
17:19:24  his only weakness is his inability to draw 3-a-week comics
17:20:30  he's also good at aggregating data into vaguely surprising results
17:21:25  ais523, have you seen the tumblr insane theory that Randall Munroe is Andrew Hussie?
17:22:51  On the basis that they don't seem to know eachother and they are both friends with Ryan North
17:23:03  whatif.xkcd.com is actually fairly entertaining.
17:23:11  yeah
17:23:20  a lot of people have been saying for a long time that he should do something like whatif
17:23:32  Yeah. It plays very well to his strengths.
17:23:37  unclear if he can make money off it though
17:23:52  In "recent" xkcd, the various info things are all that have been more than "meh".
17:24:11  i like a few of the jokes from recent years
17:24:13  but not that many
17:24:22  kmc: can't he just make money off it the same way he's been doing
17:24:24  people don't generally agree on which of the jokes are funny
17:24:39  http://kawaii-yaois.tumblr.com/post/26879203396/a-case-study-randall-munroe-andrew-hussie
17:24:43  elliott: well he makes money off the comic by making one huge poster comic per month
17:24:46  i feel like xkcd might be gradually transitioning into a state of being underrated
17:24:53  since it seems to have been getting consistently better for a while now
17:24:56  which every nerd is then contractually obligated to buy for their dorm room
17:24:57  I'm pretty sure the plural of "yaoi" is "yaoi".
17:24:59  well
17:25:05  i guess it's impossible for it to be underrated
17:25:06  and then he phones in the other 11 comics for that month
17:25:08  since it has a huge fanbase
17:25:10  but they don't count
17:25:21  elliott: do you think the comic is getting better, or just side projects?
17:25:45  i think the comic has reached a very consistent level of mediocrity
17:25:50  pikhq, I'm pretty sure that isn't relevant
17:25:53  the comic; i think if you look back to how it was fairly recently (like a year or so) it's been improving
17:26:02  atriq: :P
17:26:04  obviously it is not as good as it once was but i think it is getting less bad than it became
17:26:17  every new joke is a rehash of some joke he's already done, but worse
17:26:46  it is rarely offensively terrible, but it's hitting the same dozen themes over and over and wringing all the funny out of them
17:26:48  http://xkcd.com/7/ was the last actually funny one
17:26:53  kmc: Which is still better than "insert nerdy reference here" sadly.
17:26:53  lol
17:27:18  Man. It's really funny his art quality has gone *down* over the years.
17:27:40  ugh arch upgrade fucked with my stuff
17:27:44  why are links opening in firefox now
17:27:51  arch deluxe
17:27:54  i am desirous of a refund
17:27:56  Firefox is best browser
17:28:39  One of my friends upgraded from Safari to Internet Explorer and the speed increase was so great he's too afraid to go to any quicker browser
17:29:43  i left my computer for 3 weeks and now pacman scares me
17:29:43  "upgraded"
17:30:03  elliott, apparently, Safari is really awful?
17:30:15  i guess on windows modern ie > safari
17:30:25  Doesn't it include a partial port of Cocoa on Windows?
17:30:28  Phantom_Hoover: i will derive intense satisfaction from your inability to handle the systemd transition and subsequent breaking of your installation
17:31:09  i can't really fault xkcd's art style
17:31:34  i mean nobody is reading it for the amazing art, but it's a consistent and recognizable look which is not terrible
17:31:36  Sugar. Javascript Sweetened. (sugarjs.com)
17:31:38  programmers
17:31:40  can we please stop
17:31:44  trying to imitate apple marketing
17:31:46  with slogans
17:31:51  thank you
17:31:55  compared to other stick figure comics on the internet which mostly look like they were drawn using the ellipse tool in ms paint
17:32:04  AND ALSO: programmers can we stop talking about JS
17:32:08  like, forever
17:32:10  kmc, it's better than most of MegaTokyo's art style, which I think is cluttered
17:32:18  stop imitating apple? then we would have to, like, think of original ideas
17:32:33  a more relevant criticism of xkcd is that most of the jokes just don't need to be visual
17:32:42  the prototypical bad xkcd strip is two unmoving stick figures exchanging dialogue
17:32:50  "Is Sugar available for Node.js? Yes!"
17:32:53  oh boy oh boy!!
17:32:59  but if this thing extends javascript does it count as an interesting language??
17:33:02  I liked the latest xkcd's art
17:33:03  sounds like it might be legacy garbage
17:33:07  panel 1: setup line which nobody would possibly ever say in real life
17:33:14  panel 2: mildly amusing tweet-worthy observation
17:33:16  Javascript: the new C.
17:33:49  panel 3: unnecessary post-punchline dialogue (e.g. "we live in the future", " is weird, man", "i like science a whole lot can i please be in your club guys")
17:34:35  i wonder if any people at MIT hate RM on appropriationist grounds
17:34:44  most of the people i've talked to who know him seem to like him
17:35:13  RM = ?
17:36:11  randall munroe
17:36:23  guys should i play adom
17:37:03  Ah.
17:37:24  Yeah, my experience with him (admittedly limited and via IRC) suggests he's a decent guy.
17:37:31  kmc: maaan
17:37:37  kmc: did you know i've been on an old version of mosh for MONTHS???
17:37:40  because the AUR package got renamed
17:37:42  and nobody told me
17:37:50  this is offset by the fact that I don't use mosh though
17:37:54  heh
17:37:58  you should upgrade to the just-released 1.2.3
17:38:09  kmc: afaict there's only mosh-git
17:38:14  gotta live on the bleeding edge
17:38:14  oh
17:38:20  oh!
17:38:23  there is mosh in the community repos
17:38:28  you're Officially a Program now
17:38:51  here by "you" I mean "mosh"
17:39:09  the package is 1.2.3 too
17:39:09  huray
17:39:55  yay
17:41:09  https://github.com/keithw/mosh/commit/029e8bbde5e53b2e3454241143050cef27705cbe#L0R1018
17:41:12  security is hard :(
17:41:34  before anyone starts ranting about "rolling your own crypto", this is a third party crypto library bundled with mosh and written by professional cryptographers
17:42:35  i think it's really interesting how "optimisations" like memcmp bailing out early are insecure
17:42:55  and also, really worrying
17:43:14  i also think a Sufficiently Smart compiler would be allowed to optimize my constant_time_memcmp into something that bails out early anyway
17:43:36  right
17:43:43  current infrastructure is just totally fucked for writing secure programs
17:43:46  it seems basically futile
17:43:49  yep
17:43:57  but what secure programs want is so at odds with what you want in general
17:44:04  like my regular programs would like memcmp to be fast pls
17:44:08  writing programs without timing side channel leaks probalby requires a domain specific language
17:44:19  and even then you will have to be careful about cache effects, etc
17:44:23  right
17:44:40  I guess in the end the ideal would be having all security code packaged up in libraries written in languages that are very precise about timing and so on
17:44:52  yeah
17:45:08  written by a small number of experts, exposing APIs which are hard to mis-use
17:45:22  which is how we saw ocb.c
17:45:27  ha, an API is that is hard to mis-use
17:45:35  a very self-contained "decrypt this packet and tell me if it's authentic" function
17:45:38  but even experts make mistakes
17:46:35  and yeah, it will always be possible to misuse APIs
17:46:45  especially when we have preconditions like "never use the same nonce twice"
17:47:04  but there is also a lot that can be done to improve this
17:47:42  clearly linearly-typed nonces
17:48:55  yes
17:49:01  perhaps linearly-typed nonces will fix my crypto API
17:49:37  don't talk noncense, kmc
17:49:42  wompwomp
17:50:45  What's mosh?
17:50:46   As the saying goes, Britain and America are two nations divided by a common charset.
17:50:52  atriq: http://mosh.mit.edu/
17:51:08  Mosh is food
17:51:20  that's nosh
17:51:31  now he's telling users who can't get it to run to read his academic paper
17:51:36  you'd think this was haskell software or something
17:51:38 * kmc rimshot
17:51:47  nfood then
17:52:03  That reminds me
17:52:14  I need to find a way of running Skype from the command line
17:53:46  have some hard times trying to get these knockout.js observables to work with jquery based plugins.. thousand lines of workaround-js-code.. a nightmare
17:54:01  atriq: yeah
17:54:11  i switched to command line irc and aim/xmpp clients because of mosh
17:54:29  i run them on ec2 and my sessions follow me wherever i go
17:56:25  also it works on a lot of very marginal connections where the IRC protocol (or anything else TCP-based) is completely unusable
17:57:25  Spiffy.
17:57:46  okay so who wants to tell me how to fix links opening in firefox thanks
17:58:03  like i am not picky
17:58:06  it could be anyone
17:58:07  Change your default browser
17:58:07  could be you
17:58:19  which file
17:58:41  Who knows?
17:59:10  Maybe you open your browser of choice and click the button that says "make this your default browser"
17:59:41  Default browser
17:59:42  Chromium cannot determine or set the default browser.
18:00:01  Then you're using an obscure operating system
18:00:05  also does anyone have email client recommendations
18:00:41  I personally am using Claws ATM, but I'll note that it's a little rough. And if you find something better let me know.
18:01:01  use gmail like a normal human being
18:02:05  My university's email is on fucking outlook.com. I'm not using that straight.
18:02:08  kmc: i do and am vaguely sick of it
18:02:32  maybe i should just use mutt, 10 billion linux nerds can't be wrong
18:02:43  even if threaded discussion sort of sucks
18:03:02  http://twitter.com/1990sLinuxUser
18:03:13  wish this was still updating
18:04:55  *grin*
18:05:13  "Why has systemd deprecated support for /usr on a different filesystem!!"
18:05:43  My sensibilities run vaguely close to "90's Linux User", but I applaud that of systemd. Except that it didn't go far enough.
18:05:56  ln -s / /usr is the only right way
18:06:01  haha
18:06:06  what. could. go. wrong.
18:06:16  In my testing, nothing at all.
18:06:20  seriously?
18:06:23  Yeah.
18:06:27  wow
18:06:34  you a crazy motherfucker
18:06:36  And it's even FHS conformant.
18:07:07  About the only weirdness is you get a few more directories in /
18:07:14  e.g. /x86_64-unknown-linux-musl
18:08:05  i have come to prefer separate /usr
18:08:12  to some degree
18:08:29  i guess anything that traverses directories already needs to understand symlink loops
18:08:37  there seems to be enough semantic distinction between what is in /usr and e.g. the stuff in /var
18:08:48  and i don't think having a read-only /usr is inherently an unreasonable idea
18:09:07  Also, I see nothing wrong with /run at all.
18:09:22  i kind of want to compress /usr
18:09:26  I see nothing.
18:09:30  for my ssd
18:09:32  Because I AM BLIND ALL ALONG
18:09:36  :O
18:09:41  hm
18:09:45  speaking of 1990s linux users
18:09:45  Makes perfect sense to merge run-time transient state into a single dir.
18:09:46  (disclaimer: I'm not blind)
18:09:49  did I ever get X11 working on that floppy linux distro
18:09:51  i think i didn't :(
18:09:56  i should try that again!
18:10:03  Awesome. :)
18:10:18  pikhq, what's you're reaction to me, elliott, and Phantom_Hoover all being from the 90's
18:10:20  i managed to get the latest kernel and a crappy shell and some vaguely crappy standard utilities (written in asm) working, I know that much
18:10:22  in <1.4 megs
18:10:27  kmc: all modern file systems have transparent compression
18:10:30  uh i think pikhq was born in the 90s too
18:10:36  THE MYSTERY DEEPENS
18:10:37  oh and by "working " I mean "in qemu"
18:10:38  I was born in 1990, so yes.
18:10:59  I'm 18 in two weeksz
18:11:00 -!- atriq has quit (Quit: Leaving).
18:11:09  elliott: You're not getting a (recent-ish) build system in that space, sadly.
18:11:09  oh right that's why i asked thingy
18:11:13  olsner: really?
18:11:13  pikhq: you know about wayland right
18:11:23  Best I was able to do was an 11M squashfs.
18:11:30  elliott: Only vaguely.
18:11:30  olsner: do you mean automatically or with some command per-file
18:11:40  I have no idea if it + xwayland is larger or smaller than X11.
18:11:52  http://en.wikipedia.org/wiki/Ext4 says "no" for ext4
18:11:53  oh did you answer that
18:11:54  btrfs has a mount flag for compression, zfs lets you set it per file system
18:11:54  Though, bootstrap-linux currently static links all the binaries.
18:11:56  i fell asleep at one point so if you did
18:12:02  elliott: I didn't.
18:12:06  ok
18:12:08  http://www.ohloh.net/p/e4z
18:12:11  i suspect it'd probably be larger
18:12:20  just because wayland depends on fancy kernel graphical stuff that i turned off
18:12:22  probably
18:12:31  btrfs has it though
18:12:38  (I'm just too lazy to get the crosscompiler build scheme done "right", so it can actually do dynamic linking)
18:12:39  anyway maybe i would be satisfied with two floppies
18:12:43  one with X and a build chain and one with everything else
18:12:58  GCC's fucking huge.
18:13:03  but I think it'd be really cool if you could get a Linux system that's fully "bootstrapped" in that it comes with everything you need to download and rebuild itself in a graphical environment in 1.4 megs
18:13:04  (bak later)
18:13:16  with some ridiculous compression and brutal feature trimming
18:13:30  pikhq: are the patches to compile the kernel with tcc kept up-to-date
18:13:39  No.
18:13:43  bootstrap-linux is currently 31M...
18:14:21  At some point in the next year I anticipate landley actually getting tcc (well, more like qcc) functional, at least.
18:14:34  Though toybox probably comes first.
18:14:54   bootstrap-linux is currently 31M...
18:14:57  how big is your kernel
18:15:03  I think I got my kernel down to like 300-500 kilobytes compressed
18:15:11  as in, it actually booted in qemu and ran the stuff
18:15:19 -!- zzo38 has joined.
18:15:27  3.1M but I have *not* cleaned up the kernel config at all.
18:15:30  also I had no filesystems except in ram
18:15:42  i just used the embed-a-directory-tree-directly-into-the-kernel stuff
18:15:48  so it got compressed with the kernel image and loaded into ram
18:16:01  in fact I think the kernel had no idea how to load floppies at all
18:16:09  it just relied on the bootloader loading everything it needed or whatever
18:16:33  arguably it would be better to try and stuff floppy support into the kernel
18:16:46  so that you could boot it, recompile the sources from scratch (given a copy of them), and then write a new floppy with it
18:17:50  Hmm, the cpio.xz is a mere 7.9M...
18:18:24  "mere"
18:18:34  it gets something like exponentially harder to get things smaller as you go
18:18:46  IME
18:19:27  I'd probably do well to switch on dynamic linking.
18:19:33  pikhq: do you think the basic X11 protocol is simple enough that I could implement a tiny X server that outputs to the framebuffer without wanting to kill myself or spending a year on it
18:19:47  In a word, no.
18:19:55  not sure dynamic linking would help... you'd include unused library functions, and compression should already handle most of the redundancy, right
18:20:04  Removing the kernel from the cpio and some documentation got it down to 4.3M
18:21:23  anyway probably this would be a lot easier with some like 2.4 kernel
18:21:25  but that is cheating
18:21:53  Major benefit of dynamic linking is that binutils has a *lot* of programs which use libbfd...
18:25:41  are there no smaller alternatives for binutils?
18:25:51  I think I found my singing voice
18:26:32  olsner: Not really.
18:26:43  And I even went and beat a lot of bloat out of it with a giant stick.
18:27:03  -ffunction-sections -fdata-sections -Wl,--gc-sections
18:27:20  Why does elliott need a tiny X server?
18:28:28 -!- epicmonkey has quit (Remote host closed the connection).
18:28:44 -!- epicmonkey has joined.
18:28:56 -!- epicmonkey has quit (Remote host closed the connection).
18:29:24 -!- epicmonkey has joined.
18:29:30 -!- epicmonkey has quit (Remote host closed the connection).
18:30:50 -!- epicmonkey has joined.
18:36:46  pikhq: I'm not sure that's the "giant" stick, but definitely a start
18:37:05  olsner: From some binutils binaries it removes nearly a meg.
18:40:32  Also did some more autoconf fighting to convince it not to install libiberty.
18:40:48  Or libbfd.
18:41:05  (if you don't install the headers, you don't get to install the damned library!)
18:41:50  (libiberty is only installed as a .a anyways, meaning you don't even get the excuse of "it's a utility library all binutils needs")
18:44:26 -!- jix has joined.
18:58:26  pikhq: imo rewrite binutils
19:00:54  GCC's a bit more important to rewrite IMO.
19:01:09  binutils is bloated. GCC is bloated and stupidly fragile.
19:01:25  Or you could use a different compiler
19:01:29 -!- atriq has joined.
19:01:36  Name one that builds Linux.
19:01:51  ungcc
19:04:30  clearly minix time
19:08:50  Hasn't clang been used to compile a "working" kernel already? 
19:09:00  does clang fit on a floppy?
19:09:27  fizzie: Needs patching, I think. Like icc.
19:10:04  GNU stuff tends to be bloated
19:13:18 -!- monqy has joined.
19:13:45  There's a BOM in my UTF-8 file.
19:14:47  fizzie: ew
19:16:15  clang's *larger* than GCC.
19:16:22  olsner: depends how you define "to flop"
19:16:32  Though GCC will probably catch up, and that quickly.
19:17:03  The only advantage GCC has over clang in binary size is that GCC is in C, and GCC isn't in C anymore.
19:17:34  And clang has the (decent) excuse of being a full on C static analysis tool that happens to have a code generator attached.
19:17:46  anyway, is the whole compiler and toolchain required to be on the floppy as well?
19:17:47  GCC isn't in C anymore?
19:18:03  zzo38: They switched to requiring C++ in git recently.
19:18:19  GCC 4.8 will be C++.
19:18:45  OK, but they should still compile C codes as well as C++ codes too
19:19:01  It does still function as a C compiler.
19:19:07  It's just written *in* C++ now.
19:19:17  OK
19:19:28  GCC also supports some targets that LLVM does not support, though, such as MMIX
19:21:13 -!- AnotherTest has quit (Quit: Leaving.).
19:25:38 -!- heroux has quit (Read error: Operation timed out).
19:30:21 -!- heroux has joined.
19:35:48 -!- shubshub has joined.
19:35:50  hi
19:36:03  hi
19:39:36  pikhq: do you know anything about ncurses
19:40:29 -!- hagb4rd has quit (Read error: Operation timed out).
19:41:55  Nwitches cast ncurses.
19:42:35 -!- hagb4rd has joined.
19:42:36  the BOM is also a zero-width non-breaking space
19:42:45  though there's now a different codepoint you're supposed to use for that
19:45:56  Well, it's immediately at the start of the file, there's no real reason for a zwnbsp, and (I think; haven't verified) it's confusing mplayer's srt subtitle parser because it expects "1", not "\ufeff1", at start. (Or possibly it's not autoloaded for some other reason.)
19:46:21  heh
19:46:41  All Microsoft's fault.
19:47:32  (Notepad expects and emits a UTF-8 BOM for UTF-8 text)
19:48:03  "Failed to open subtitle demuxer", it says, if I explicitly -subfile it. (VLC is happy with it though.)
19:51:20  This was from the Finnisn national broadcasting company's web thing (YLE Areena), though I'm really not sure if it's their fault, or the YLE-specific rtmpdump script+plugin's fault.
19:51:35                          urllib.urlretrieve(url, subtitlefile.encode(enc, 'replace'))
19:51:38                          self.add_BOM(subtitlefile)
19:51:44  Okay, that's quite clear.
19:52:21  I'm assuming some player or another is using the BOM to go all "hey, these subs are in UTF-8 and not in our legacy 8-bit encoding".
19:54:58  pikhq, Microsoft has done some good though. Isn't XMLHttpRequest from IE?
19:54:59  Also I think the web thing used to have burned-in subtitles in the RTMP video stream, it's kind of nice that they've switched it to an external SRT file presumably loaded by the official Flash player.
19:55:09  heh, that seems likely
19:55:39  btw python urllib sucks ass
19:55:43  'requests' is a much nicer library
19:55:53  Aren't you supposed to use urllib2?
19:56:10  someone probably thinks so
19:56:14  but requests is nicer  than urllib2
19:56:30  I meant over urllib
19:59:48  Sgeo: It imports urllib and urllib2.
20:00:34  I seem to recall you used some things from the old one. But I haven't used it much. (It wasn't a nice library.)
20:02:27 -!- shubshub has quit (Remote host closed the connection).
20:03:30  yle-dl changelog, 1.99.7: "Add byte order mark into subtitle files. Some players don't show umlaut characters correctly without it."
20:04:44  How fast would CPU having an internal memory and an external memory, where the internal memory is partially ROM and partially RAM and also includes the external address bus and data bus as locations in the internal memory, it execute instructions from the internal memory using VLIW instructions and those are used like microcodes to execute external instructions?
20:37:37 -!- MoALTz has joined.
20:37:44 * Sgeo is poking a giant gaping hole in the Clojure bot's sandbox in #clojure
20:37:52  Although someone else discovered the hole, I'm exploring it
20:39:26  have fun
20:42:34 -!- epicmonkey has quit (Ping timeout: 240 seconds).
20:46:06 -!- carado has joined.
20:50:38  Now I figured out how to beat the demon in Dungeons&Dragons game, I think, although we need to beat the chancellor first just because it is more important.
20:50:50  We need to somehow tilt the demon's castle.
20:51:37  Like how Kaiji managed to tilt the entire casino in order to win at a pachinko game.
20:52:27  Like in New Super Mario Bros Wii?
20:52:41  It may or may not have happend in New Super Mario Bros Wii
20:52:45  I'm only on world 2
20:53:14  I don't know if it happens in New Super Mario Bros Wii, I have not played that game.
20:53:53  `:t foldr
20:53:55  :t foldr
20:53:56  forall a b. (a -> b -> b) -> b -> [a] -> b
20:54:02 -!- carado has quit (Ping timeout: 255 seconds).
20:54:03  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: :t: not found
20:59:16  When I was in the castle last time, I found that it was not tilted, and there is also water on the ceiling. If I use anti-magic in there (I know where to get such a device), the water might fall down and flood everything. Or maybe it is even artificial gravity and something will go wrong with that too...
21:00:47  Do you have any manipulate water spells?
21:01:03  I can't use those in a anti-magic field!
21:01:16  ...manupulate water prayers?
21:01:30  I can't use those in a anti-magic field either!
21:01:43  A very large sponge?
21:01:54  erect an anti anti-magic field field
21:02:23  No, my plan was to tilt the building so that all the water would go to one side
21:02:35  So that it is shallow on one side and deep on one side
21:02:40  One day I may actually play D&D
21:03:12  What character do you prefer to play?
21:03:26  I dunno
21:03:31  Probably a cleric type
21:03:39  kmc:
21:03:40  *Main> :kind! Foldr Pair Unit (Map Show '[Int, String])
21:03:40  Foldr Pair Unit (Map Show '[Int, String]) :: Constraint
21:03:40  = Pair (Show Int) (Pair (Show [Char]) ())
21:03:54  I do happen to know the demon's age if that ever becomes important (I know by psychic impressions on a chancellor's guard's sword)
21:03:59  (class (a, b) => Pair a b; instance (a, b) => Pair a b); type family Unit :: Constraint; type instance Unit = ())
21:04:10  kmc: real world haskell
21:04:39  atriq: There are different versions of D&D game; I am playing D&D 3.5 edition. One day I may complete the writing of Icosahedral RPG rules; much of what I have in my mind I have not typed.
21:04:56  I've got the 4th ed player's handbook
21:05:18  I don't really like 4th edition, many other people also don't like it
21:05:42  I dunno, I've never actually played it
21:05:49  Or 3.5 or any other D&D
21:06:00  I've also got the Diana: Warrior Princess book
21:06:53  I also happen to know that the demon's magic powers are less powerful the farther away he is from his castle (I know this from the illithid savant's "lore" class feature); my idea initially was to try to lure the demon to the opposite side of the Earth.
21:07:15  That'd take a while
21:07:26  It might be quicker to move his castle
21:07:28  Yes I know, that is one reason why I won't do it
21:08:27  http://sprunge.us/jTUh
21:08:31  good ghc errors
21:08:41  (while trying to write mapElimH :: (All c ts) => (forall a. (c a) => a -> r) -> HList ts -> [r])
21:09:45  I know a shortcut to the inside of the castle, which only works at nighttime, though. I may need a team to come in this way, exit through the door or something, and weaken the foundation, to tilt the castle.
21:14:42  But at first I need to get rid of the assassins, and I have some plan related to the phase of the moon and pretending to be trapped by the illithid haters society and miscast a spell intending to communicate with someone else, so they will believe me and try to kill me, but it is a illusion so that way I can trap them.
21:14:58  And then after that, I somehow need to trap the chancellor too, and rescue the king.
21:16:08  I cannot enter the king's castle because only the chancellor's guards are seen at the entrances; the king's guards are no where to be seen. So instead we just try something else, such as, sending messages secretly to the royal scribes and so on.
21:16:26  Hopefully the chancellor's guards have not infiltrated them too!
21:20:05  How much do you know about the Chancellor?
21:20:15  And how much does he know about you?
21:21:34  allThrough :: (All p (x ': xs)) => (forall ys. (All p ys) => rep ys -> r) -> rep xs -> r
21:21:34  allThrough k = k
21:21:36  even this isn't helping :(
21:32:19 -!- mindlessDrone1 has joined.
21:33:40 -!- mindlessDrone has quit (Ping timeout: 268 seconds).
21:33:51 -!- nys has joined.
21:36:26  I know a few things about the chancellor and he knows a few things about me. I do happen to know the chancellor is evil and I know his age too, but I do not know his location. The chancellor probably knows a few things about me or at least his guards do; they hired an assassin to kill me.
21:36:37  And I know exactly how much money they got paid for that job, too.
21:37:09  Could you outbid the assassin?
21:37:24  shachaf: Did you get your Stripe web CTF shirt yet?
21:38:45  kmc: Nope.
21:38:48  Did you?
21:38:52  nope
21:39:03  I was thinking it was just me, since they never managed to get it to me last time.
21:39:09  yeah, not just you
21:39:14  i should bug gdb about it
21:39:24  or perhaps i could... de-bug gdb?!?!?
21:39:50 -!- mindlessDrone1 has left.
21:41:06  Occasionally I go to their various events, so I might bug him then.
21:45:33  atriq: I have not enough money to outbid the assassin.
21:45:37  :(
21:45:57 * kmc is currently mashing four potatoes
21:46:01  shachaf: what are their events like?
21:46:01  Even if I did have enough, I do not know where the assassin's guid is.
21:46:09  s/guid/guild/
21:46:50  kmc: four potatoes!
21:46:58  Do you know where there's a thieves' guild?
21:49:11  *Main> mapElimH' showTo (HCons 1 (HCons "abc" HNil))
21:49:11  ["1","\"abc\""]
21:49:12  aww yeah
21:49:44 -!- atriq has quit (Remote host closed the connection).
21:50:20  I don't know a thieves' guild either but I don't think I need one of those.
21:50:53  elliott: is HCons like Lisp's cons?
21:51:00  depends what that means
21:51:11  sort of and no
21:51:18  Is there a HCar and HCdr
21:51:19  whatever it is, i'm sure lisp's is better because it's lisp
21:51:39  these are type level lists right
21:51:47  except that you've used some insane GHC 7.4 black magic
21:51:54  or am i totally off base
21:52:31  it's actually 7.6 black magic at this point
21:52:57  kmc: http://sprunge.us/BJHh
21:53:10  took the Show thing from an SO answer and modified it and am trying to get it to use mapElimH
21:54:52 -!- Nickname_ has joined.
21:55:40  next up: toListH :: (Homogeneous ts a) => HList ts -> [a]
21:56:02  GODDAMNNIT APPARENTLY THERE"S NO SUCH THINGS AS HEADPHONES THAT WON"T BREAK IN MY CARE
21:56:11 -!- MoALTz has quit (Quit: Leaving).
21:56:11  that is my experience as well
21:56:14  it is a matter of when, not if
21:56:14  actually hm
21:56:16  maybe i want something more like
21:56:22  but all things decay Sgeo
21:56:34  If atriq is ever come back on let them to read the recent text on my Dungeons&Dragons game if interested, or anyone else read if interesting perhaps you comment on my plans too
21:56:38  toListH :: HList ts -> Maybe () [] (Homogeneous ts)
21:56:44  hmmmmmm
21:56:46  Oh, I think it was the video, not the headphones
21:56:53  oh I actually do want a typeclass I think
21:56:54  Or even complain about spelling and grammatical errors if you want to
21:56:55  just one with an ATF
21:57:00  What is ATF?
21:57:32  associated type family
21:57:59  alcohol tobacco and firearms
21:58:05  uhh what's the simplest way of writing a foldr that checks all elements of a list are equal
21:58:05  essential ingredients for haskell programming
21:58:08  on the value level
21:58:12  shachaf: help
21:58:12  kmc: ... and explosives, nowadays
21:58:26  http://en.wikipedia.org/wiki/Bureau_of_Alcohol,_Tobacco,_Firearms_and_Explosives
21:58:29  yeah
21:59:02  What type family do you need?
21:59:47  something along the lines of toListH :: (Homogeneous ts) => HList ts -> [Elem ts]
22:00:17  oh hm
22:00:29  that doesn't work because HNil is polymorphic
22:00:31  interesting
22:01:24 -!- Nickname_ has quit (Quit:  Alt-F4).
22:02:06  aha
22:02:07  toListH :: (All ((~) a) ts) => HList ts -> [a]
22:02:34  toListH :: (All ((~) a) ts) => HList ts -> [a]
22:02:34  toListH = mapElimH' cast
22:02:34  cast :: To ((~) a) a
22:02:34  cast = To id
22:03:02  so now just to separate mapElimH' and toListH
22:03:56  toListH :: (All ((~) a) ts) => HList ts -> [a]
22:03:56  toListH HNil = []
22:03:56  toListH (HCons x xs) = x : toListH xs
22:03:57  One thing Haskell doesn't have but would be like is classes with automatic instances, you cannot define your own instances you can only use the instances made automatically. Typeable should be made into such a class. But I have wanted to make other classes having this feature too.
22:04:02  *Main> :t toListH
22:04:02  toListH
22:04:03    :: (Foldr
22:04:03          Constraint Constraint Pair () (Map Constraint * (* ~ a) ts)) =>
22:04:03       HList ts -> [a]
22:04:10  kmc: i am enterprising
22:07:05  kmc: You were at one of them, weren't you?
22:07:06  shachaf: You have 1 new message. '/msg lambdabot @messages' to read it.
22:07:24  elliott: help
22:15:13  at what?
22:15:15  oh
22:15:20  yeah i was at the first ctf wrapup
22:24:47  zzo38: Why would you want that?
22:29:00  mroman: It would be useful sometimes, when you want to indicate that certain features of the type are available, as part of a constraint, Typeable is one example of such thing, although there are others, such as types belonging to another class but without exposing its methods, etc
22:30:53  "Seriously, what moron in this day and age is not familiar with the limitations of aclocal and the best practices to use system-wide m4 macros?" :D
22:31:42  http://www.nytimes.com/2012/10/20/us/in-silicon-valley-perks-now-begin-at-home.html
22:31:58  let's feed our programmers and do their laundry and clean their rooms and make sure they don't have to be capable of functioning as adults in any way
22:32:44  programmers are children right, it would be crazy to just give them money and expect them to spend that money in ways they see fit
22:33:12  Not all programmers are children. Some may be.
22:34:15  oh no
22:34:18  I need a way to eliminate via iso here
22:34:31  this sux
22:34:32  i think there is a learned helplessness aspect too
22:34:55  when all your daily needs are met by The Company and all your friends and housemates work for The Company and all your social events are organized by The Company, it makes it that much harder to quit
22:36:57  That is why you need to quit.
22:37:11  elliott, Phantom_Hoover monqy mapdate
22:49:45 -!- ais523 has quit.
23:30:41 -!- Vorpal has quit (Read error: Operation timed out).
23:36:25 -!- Nisstyre-laptop has quit (Ping timeout: 246 seconds).
23:38:35 -!- Nisstyre-laptop has joined.
23:40:27 -!- monqy has quit (Quit: hello).
23:41:51 -!- monqy has joined.
23:51:57  kmc: Have you had strawberries with balsamic vinegar?
23:53:44  OM NOM NOM
23:53:45  also, bacon
23:54:03  copumpkin: I don't think I've had that.
23:54:22  bacon with balsamic is good
23:54:35  everything is good with balsamic
23:54:40  Everyth -- that.
23:58:17  test :: ((forall a. (Show a) => a -> String) ~ (Int -> String)) => ()
23:58:19  why is this not ok
23:58:21  is there a ~ that means
23:58:23  "can unify with"
23:58:25  so i can do
23:58:30  (a ~ String -> String, a ~ Int -> String)
23:58:38  and a = forall a. (Show a) => a -> String
23:58:39  works

2012-10-21:

00:04:46  i haven't had strawberries with balsamic though
00:04:48  but i hear it's good
00:05:21  kmc: Well, now you have a mission in life!
00:10:43  when i was little i tried balsamic vinegar with balsamic vinegar
00:10:51  Delicious.
00:10:51  it began a lifelong love of balsamic vinegar
00:11:00  also extremely painful lips
00:11:58 * Sgeo is watching The Myth of the Genius Programmer
00:12:23  you need an entire video to tell you that genius is bullshit?
00:14:27 -!- Arc_Koen has joined.
00:17:37 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:18:27 -!- Frooxius has quit (Ping timeout: 276 seconds).
01:01:36  shachaf: help ^
01:02:03  elliott: with what ☝
01:02:27   test :: ((forall a. (Show a) => a -> String) ~ (Int -> String)) => ()
01:02:27   why is this not ok
01:02:27   is there a ~ that means
01:02:27   "can unify with"
01:02:27   so i can do
01:02:28   (a ~ String -> String, a ~ Int -> String)
01:02:30   and a = forall a. (Show a) => a -> String
01:02:32   works
01:02:46  Oh.
01:02:57  I don't know if there's such a thing. It seems kind of weird.
01:07:16  It'd be useful for me.
01:08:08  elliott: Ask in #haskell!
01:08:18  Good one.
01:13:17  elliott: Oh no, race condition!
01:13:30  What if someone sent you a good message right before the @clear-messages?
01:15:27  @clear-messages?
01:15:27  Messages cleared.
01:15:32  thank you
01:15:42  @clear-messages!
01:15:42  Messages cleared.
01:15:49  @ask monqy hi monqy :')
01:15:50  Consider it noted.
01:15:57  @clear-messages.
01:15:57  Messages cleared.
01:16:06  @tell monqy what have you done?!
01:16:07  Consider it noted.
01:16:31  @clear-messages‽
01:16:31  Unknown command, try @list
01:16:41  help
01:16:41  monqy: You have 1 new message. '/msg lambdabot @messages' to read it.
01:16:44  heeelp
01:17:07  uh, oh, can you put comments in urls?
01:17:20  @clear-messages⸘
01:17:21  like, using '.' inside of the url and everything after it is ignored
01:17:21  Unknown command, try @list
01:17:24  @clear-messagesá
01:17:24  Messages cleared.
01:17:28  zomg
01:17:37  I bet lambdabot is doing edit distance in UTF-8 bytes. :-(
01:28:42 -!- Arc_Koen has quit (Quit: Arc_Koen).
01:43:50  I also think "can unify with" might sometimes be useful and the automatic classes I suggested could be used to make it, I think. 
01:47:32  Automatic classes if used in Ibtlfmm (instead of only Haskell) could do other things too, including, check if it is not a specific type, trex records, whatever, but in any case they could only be used with the class is specified in the constraint that your function is using it
02:11:12  kmc: I was reading a book that denoted the empty set by □.
02:23:22  shachaf: It's because you forgot to quantify the "a".
02:23:32  elliott: I know.
02:24:14  elliott: For some reason I thought it would be "scoped" from the "data" but that's a bit silly.
02:24:31  yeah, GADT headers are weird
02:24:35  you can just put a kind signature there instead
02:24:40  Coq actually "scopes" it like that
02:24:46  Agda does too, right?
02:25:20  I remembered that there was a difference between "data Foo (n:Nat) : * -> *" and "data Foo : Nat -> * -> *" or "data Foo (n:Nat) a : *" or something.
02:25:25  But i guess that was in Agda.
02:28:45  elliott: So did you know 18:49  Either x y = exists b. if b then x else y; (x,y) = forall b. if b then x else y
02:29:27  shachaf: Sure, that makes perfect sense.
02:29:44  I didn't say it doesn't make sense.
02:30:21  Well, I mean... what is there to know?
02:30:45  Nothing.
02:31:39  shachaf:
02:31:44  data To' p f = To' (forall a. (p a) => a -> f a)
02:31:44  mapH :: (All p ts) => To' p f -> HList ts -> HList (Map f ts)
02:31:54  shachaf: What can I do here if I want to set p = Show, and map show over the list?
02:31:59  I need to specify an "f".
02:32:05  But what I want is (Const String), but you can't do that.
02:32:13  Since type Const a b = a can't be partially applied.
02:32:22  shachaf: Can you think of a decent way to generalise the type of mapH so this works?
02:32:34  I've considered
02:32:38  data To'' p = To'' (forall a r. (p a r) => a -> r)
02:32:45  mapH' :: ??? => To'' p -> HList ts -> HList ???
02:32:47  using
02:32:54  class (Show a, r ~ String) => Shoe a r
02:33:03  class Shoe a r
02:33:03  instance (Show a, r ~ String) => Shoe a r
02:33:04  or something
02:33:11  but I don't see how that would work.
02:33:15  Yes, I'd say that it's certainly the most thoughtful and intelligent traffic signal I've ever met.
02:33:17  As in I don't know what the ???s would be.
02:33:20  And anyway it feels wrong.
02:33:23  So do you have any ideas?
02:34:23  Not off-hand.
02:34:36  OK.
02:34:43  Well, if you think of any, let me know.
02:35:00  (I know I can just do newtype Const a b = Const { getConst :: a } and do To' (Const . show) instead, but that leads to problems later.)
02:35:08  (Since then I want to use toListH :: (All ((~) a) ts) => HList ts -> [a].)
02:35:12  (But Const a b and Const a c don't unify.)
02:36:21  HLists are the devil.
02:36:35  19:36  I just don't see the point
02:36:39  (Referring to HLists, I'm sure.)
02:37:56  shachaf: This isn't about HLists, though.
02:38:14  It's about figuring out how this kind of stuff can be used at the type-level.
02:40:28   nooodl: 1, 1, …? Everyone knows the Fibonacci sequence begins with 89, -55.
02:40:30  ion: What's this about?
02:41:00  shachaf: Hmm.
02:41:16  shachaf: If I could somehow specify that I want p to have the fundep a b | a -> b, then I think
02:41:17   data To'' p = To'' (forall a r. (p a r) => a -> r)
02:41:17   mapH' :: ??? => To'' p -> HList ts -> HList ???
02:41:18  would work.
02:41:28  shachaf: But you can't do that. But that's what type families are.
02:41:28  > fix ((89:) . (-55:) . zipWith (+) <*> tail)
02:41:29    Couldn't match expected type `a1 -> a' against inferred type `[t]'
02:41:34  err
02:41:42  > fix ((89:) . (-55:) . (zipWith (+) <*> tail))
02:41:44    [89,-55,34,-21,13,-8,5,-3,2,-1,1,0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,6...
02:41:44  shachaf: But an associated type family doesn't work, because then you have to pass the associated type family as a type argument to To''.
02:41:53  shachaf: And then you're trying to partially-apply it.
02:41:59  So you run into the same problem.
02:42:23  elliott: Just a joke inspired by the debate about whether the sequence begins with 1 1 or 0 1.
02:42:37  Ah.
02:43:39  fix ((-1:) . (-1:) . (zipWith (+) <*> tail))
02:43:50  > fix ((-1:) . (-1:) . (zipWith (+) <*> tail))
02:43:52    [-1,-1,-2,-3,-5,-8,-13,-21,-34,-55,-89,-144,-233,-377,-610,-987,-1597,-2584...
02:43:55  > fix ((0:) . (0:) . (zipWith (+) <*> tail)) -- maximally correct
02:43:57    [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,...
02:44:37  > fix ((1:) . (0:) . (zipWith (+) <*> tail))
02:44:39    [1,0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,109...
02:45:27  > fix ((1:) . (((sqrt 5 + 1)/2):) . (zipWith (+) <*> tail)) -- this is actually the right one
02:45:29    [1.0,1.618033988749895,2.618033988749895,4.23606797749979,6.854101966249685...
02:45:43  yes
02:46:05  @let phi = (sqrt 5 + 1)/2
02:46:07   Defined.
02:46:34  > (phi + 1 :: CReal) / phi == phi / 1
02:46:37    True
02:47:05  > (phi + phi + 1 :: CReal) / (phi + 1) == (phi + 1) / phi
02:47:07    True
02:47:09  See?
02:48:22  "It was a dotfile virus (communicated via infecting workstations) to advertise a fraternity party"
02:49:09  shachaf: You gonna stand up and take that from Nereid???
02:50:03  elliott: I sure showed that Nereid, eh?
02:50:12  yes
02:50:28  shachaf is fibbing.
02:53:26  Ooh, I know.
02:53:31  I can make a type family indexed by constraints.
02:53:44  Correspond is one of my useful spells it can be used for various things including to determine your longitude.
02:53:54  Let's see if you understand how I might beat the assassin with the Correspond spell and the phase of the moon.
02:54:13  elliott: What is that useful for, though?
02:57:06  *Main> toListH (mapH' showTo'' (HCons 1 (HCons 2 HNil)))
02:57:06  ["1","2"]
02:57:10  zzo38: Well, uh...
02:57:17  *Main> toListH (mapH' showTo'' (HCons 1 (HCons "abc" HNil)))
02:57:17  ["1","\"abc\""]
02:57:19  It's pretty cool!
02:58:10  > [show 1, show "abc"]
02:58:11    ["1","\"abc\""]
02:58:22  > ["1","\"abc\""]
02:58:23    ["1","\"abc\""]
02:58:28  Do I win the "oversimplify the example" game?
02:58:29  > "hi monqy"
02:58:31    "hi monqy"
02:59:17  > let fibs = (go (-) 1 (-1), 0, go (+) 1 1) where { go f a b = fix ((a:).(b:).(zipWith f<*>tail)) }; right (ls,x,r:rs) = (x:ls,r,rs); left (l:ls,x,rs) = (ls,l,x:rs); iterateN n = appEndo . Data.Foldable.foldMap Endo . replicate n in ((\(_,_,rs) -> rs) . iterateN 10 right . iterateN 20 left) fibs
02:59:18    can't find file: L.hs
02:59:20  > let fibs = (go (-) 1 (-1), 0, go (+) 1 1) where { go f a b = fix ((a:).(b:).(zipWith f<*>tail)) }; right (ls,x,r:rs) = (x:ls,r,rs); left (l:ls,x,rs) = (ls,l,x:rs); iterateN n = appEndo . Data.Foldable.foldMap Endo . replicate n in ((\(_,_,rs) -> rs) . iterateN 10 right . iterateN 20 left) fibs
02:59:22    [34,-21,13,-8,5,-3,2,-1,1,0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,...
02:59:30  *Main> :t \to -> toListH . mapH' to
02:59:30  \to -> toListH . mapH' to
02:59:30    :: (Foldr
02:59:30          Constraint
02:59:30          Constraint
02:59:31          Pair
02:59:33          ()
02:59:35          (Map Constraint * (* ~ a) (MapResult p ts)),
02:59:37        Foldr Constraint Constraint Pair () (Map Constraint * p ts)) =>
02:59:39       To'' p -> HList ts -> [a]
02:59:41  monqy: im wizard
02:59:57  type Constrain't = Constraint -> Void
03:00:26  OK now for foldrH.
03:00:37  I think this type is going to make something like no sense at all.
03:00:44  what are you doing.................
03:00:49  monqy: magic
03:00:56  monqy: toListH :: (All ((~) a) ts) => HList ts -> [a]
03:01:00  monqy: something "pretty cool"
03:01:09  monqy: HList '[String, String, String] is an ok input to toListH.
03:01:13  monqy: but HList '[String, Int] isnt'.
03:01:15  *isn't
03:01:24  elliott: whoa, dude
03:01:29  class (a, b) => Pair a b
03:01:29  instance (a, b) => Pair a b
03:01:29  type family Unit :: Constraint
03:01:29  type instance Unit = ()
03:01:29  type All p xs = Foldr Pair Unit (Map p xs)
03:01:32  monqy: "that's the definition of All"
03:01:36  Longcat is long. https://sphotos-a.xx.fbcdn.net/hphotos-ash3/557771_483841354969839_129064845_n.jpg
03:01:42  hion
03:01:44  Pair is just (,) on constraints and Unit is just () on constraints but
03:01:50  it doesn't work if you do that
03:01:53  so I have to redefine them
03:02:07  elliott: It doesn't?
03:02:18  shachaf: nope
03:02:24  shachaf: (() :: Constraint) works but just () doesn't
03:02:25  What if you use type instead to define it?
03:02:26  It thinks it's the wrong kind?
03:02:32  and ((,) :: Constraint -> Constraint -> Constraint) doesn't work at all
03:02:37  apparently only (a, b) is overloaded, not (,) itslef
03:02:40  *itself
03:02:46   type family Unit :: Constraint
03:02:46   type instance Unit = ()
03:02:48  this is because you can't do
03:02:52  type Unit :: Constraint = ()
03:02:58  it's the only way to give a type synonym a kind signature
03:02:59  type Unit = (() :: Constraint)
03:03:02  doesn't work
03:03:02  try it
03:03:06  Works for me.
03:03:12  You need the parentheses on the right side, though.
03:03:17  oh wtf
03:03:18  you need the parens
03:03:20  that's dumb as hell
03:03:27  "i kno dude"
03:03:29  Why did they make like that? It ought to work.
03:03:35  :t foldr
03:03:36  forall a b. (a -> b -> b) -> b -> [a] -> b
03:04:05  foldrH :: (All p ts) => (forall a. (p a) => a -> b -> b) -> b -> HList ts -> b
03:04:08  ok so this works but it's obviously not ideal
03:04:13  we want a fold on the type-level ts
03:04:33  so foldrH :: ??? -> HList ts -> Foldr f z ts
03:04:35  for some f, z
03:05:21  I guess (forall a. (p a) => a -> b -> f a b)
03:05:32  er
03:05:34  I guess (forall a b. (p a) => a -> b -> f a b)
03:05:37  though that fails to express that the "b" comes from the fold :/;
03:05:39  *:/
03:09:23  shachaf: Hey, isn't this just induction?
03:09:29  monqy: You use Coq a lot, right?
03:09:31  elliott: What is?
03:09:36 * shachaf wasn't paying many attentions.
03:09:39  monqy: What type does Coq infer for induction on the standard cons list type?
03:09:48  (Or the general recursion scheme, I guess; practically the same for my purposes.)
03:09:50  I have an All typeclass
03:09:58  mine is way bettar
03:10:06  copumpkin: How's yours definde?
03:10:07  *defined
03:10:10  can't remember
03:10:12  I tried a few ways
03:10:13  copumpkin: Mine doesn't involve any typeclasses!
03:10:22  copumpkin: Just type families with results that are used as constraints.
03:10:24  I did one of those at some point
03:10:29  It's worked out just great so far.
03:10:31  but it didn't work very well
03:10:41  but I was using 7.4.1 at the time
03:10:45  maybe shit has improved
03:10:49  http://sprunge.us/HVji
03:10:54  (7.6-only code.)
03:11:03  elliott: list_rect
03:11:03       : forall (A : Type) (P : list A -> Type),
03:11:03         P nil ->
03:11:03         (forall (a : A) (l : list A), P l -> P (a :: l)) ->
03:11:04         forall l : list A, P l
03:11:28  is that what you wanted?
03:11:31  monqy: yep, thanks
03:11:38  monqy: time to write that in haskell..........
03:11:46  lol
03:12:05  copumpkin: if i close my eyes and pretend hard enough it will be agda
03:12:08  but faster
03:12:11  totally
03:13:50  monqy: foldrH :: (All p ts) => (forall a us. (p a) => a -> f us -> f (a ': us)) -> f '[] -> HList ts -> f ts
03:14:01  monqy: : )
03:14:03  monqy: :      )
03:14:08  : /
03:14:51  it would be nice to represent the ordering somehow rather than having it be as vague as (All p ts)
03:14:52  but oh well
03:15:05  would need more indexy types for that I guess
03:17:34  i wish i were cool enough to use ZFS
03:18:06  are you cool enough to use btrfs
03:18:15  is btrfs fully baked yet?
03:18:22  I know someone who lost three filesystems to btrfs.
03:18:49  Problems ranging from data corruption to kernel deadlock, or something like that.
03:18:53  kmc: I use JFS. Is that cool?
03:18:55  i'm trying to figure out the best way to stack encryption, LVM, and RAID on my new server
03:18:55  I mean, OS/2 is cool.
03:19:14  and my understanding is that ZFS handles this all together in an integrated sexy way
03:19:35  kmc: I think by "integrated" that means "in its own separate universe to everything else, with its own version of everything".
03:19:45  (I don't think it does LVM; I think it has its own implementation of what LVM does. No?)
03:19:49  that's what i mean
03:20:21  like, i wouldn't need LVM because i could just have a single RAID-Z partition which spans multiple drives of different sizes
03:20:48  Are you using FreeBSD?
03:20:49  no
03:21:18  Uh oh.
03:21:22  I think I need unsafeCoerce to do this one.
03:21:40  are you a bad enough dude to use unsafeCoerce
03:21:49  unsafeCoerce enables quite a lot of type hackery
03:22:02  Has anyone told Oleg about it?
03:22:24  shachaf: You can't spell unsafeCoerce without fun and saeCoerce.
03:22:49  20:21:22  I think I need unsafeCoerce to do this one.
03:22:52  ........................................
03:23:10  monqy: hey, usually I bring out unsafeCoerce much before this!!!
03:23:20  ........................................
03:23:37  > ((==) `on` (sort . map toLower . filter isAlpha)) "unsafeCoerce" "cancerous fee"
03:23:40    True
03:23:46  I know there are some things that can be done with unsafeCoerce I think my extensible product types library use unsafe
03:23:58  shachaf: i
03:24:00  shachaf: how
03:24:09  monqy:
03:24:09  data Foldy p = Foldy (forall a us. (p a) => a -> FoldR p us -> FoldR p (a ': us))
03:24:09  type family FoldR (p :: * -> Constraint) (xs :: [*]) :: *
03:24:09  foldrH :: (All p ts) => Foldy p -> FoldR p '[] -> HList ts -> FoldR p ts
03:24:09  foldrH _ z HNil = z
03:24:09  foldrH foldy@(Foldy f) z (HCons x xs) = unsafeCoerce (f x (unsafeCoerce (foldrH foldy z xs)))
03:24:18  O, it is a anagram?
03:24:25  monqy: foldy named in honour of 4.1 loopy
03:25:21  im very upset about this unsafecoerce
03:25:41  monqy: which one
03:25:58  monqy: feel free to write a patch removing it
03:26:08  monqy: Remember that time I got unsafeCoerce into an edwardk library?
03:26:11  good times
03:26:27  im upset about that too
03:26:33  im upset about both unsafecoerces
03:26:36  elliott: Did you know 1.8% of Hackage is edwardk libraries?
03:26:39  basically i don't want to have to think about stacking all these different kinds of virtual block device
03:26:51  i just wanna say "here are some drives, make sure my shit is redundant and also encrypted, thx"
03:26:52  monqy: one day you'll grow up to be as old as me and then you'll appreciate unsafeCorece
03:26:53  kmc: That's why you buy a sysadmin!
03:27:02  kmc: well I think LVM is bad and people shouldn't use it
03:27:16  why specifically
03:27:18  I guess that also means I think people shouldn't encrypt their drives
03:27:20  or align their blocks on SSDs
03:27:24  kmc: well have you seen it
03:27:28  you don't need LVM to do either of those things
03:27:28  it's the messiest piece of crap I've ever seen
03:27:33  numbers blocks and stuff differently from the kernel
03:27:48  if I wanted to avoid LVM i suppose I could do a RAID0 of my two RAID5 devices
03:27:57  except no i can't
03:27:59  > (0 + 5) / 2
03:28:00    2.5
03:28:04  because they will be different sizes
03:28:06  kmc: btw how do you do the alignment thing without lvm on linux
03:28:14  iirc it was required ages ago
03:28:42  Alignment?
03:28:45  elliott: it seems like LVM would *hurt* there
03:28:51  it's another layer of metadata to mess up the alignment
03:29:16  you would just make sure your partition is aligned
03:29:21  and then tell your mkfs to align shit
03:29:29  (they support this originally for RAID performance)
03:29:30  monqy: ~eaxample use~
03:29:31  type instance FoldR ((~) a) xs = [a]
03:29:31  toListH' :: (All ((~) a) ts) => HList ts -> [a]
03:29:31  toListH' = foldrH toot []
03:29:31  toot :: Foldy ((~) a)
03:29:31  toot = Foldy (:)
03:29:48  i can't believe this shit works
03:30:01  shachaf: SSDs erase data in big blocks; for performance you want these to be aligned with filesystem blocks
03:30:14  by "erase" I mean "write"
03:30:15  kmc: Right, but what does that have to do with LVM?
03:30:26  yeah that's what i'm wondering too ;)
03:30:32  I think RethinkDB had a post on their weblog about doing this once.
03:30:34  if you want to use LVM, it's another layer on which you have to get the alignment right
03:30:42  But it looks like they replaced their site with a "launching soon" page.
03:30:45  heh
03:30:47  sucks
03:31:05  (On the other hand maybe they'll be launching soon!)
03:31:20  shachaf: paul graham joke
03:31:21  they weren't already launched
03:31:27  Sort of.
03:31:29  elliott: i can't believe that shit works either
03:31:38  shachaf: did rethinkdb "pivot"
03:31:38  If you can pull of launching a second time, why not?
03:31:45  pie-vot
03:31:49  they make pies now
03:31:51  pivot, n. making a new business except it has the same name and people
03:31:55  artisinal local gluten-free pies
03:31:59  because you didn't have a business model for the previous one
03:32:03  (business model for the new one not required either)
03:32:05  pies that celebrate craftsmanship
03:33:00  kmc: They added a word! https://addons.heroku.com/
03:33:08  Now it's "Fast, elegant full-text search that celebrates your craftsmanship."
03:33:39  but is it awesome?!?!?!?!?
03:33:55  i must know if this software is awesome, minimalist, suckless, and "done right"
03:34:05  kmc: Does $KMCCOMPANY have fulltext search?
03:34:11  Your customers expect fast and accurate keyword search, autocompletion menus and inputs, faceted browsing, spatial search and so much more.
03:34:13  that's classified
03:34:31  class Company a
03:34:38  data Kmc = Kmc; instance Company Kmc
03:35:04 -!- augur has quit (Read error: Connection reset by peer).
03:35:24 -!- augur has joined.
03:35:59  shachaf: Is there a Void :: Constraint?
03:36:08  elliott: What would that be?
03:36:17  shachaf: A constraint that is never satisfied.
03:36:22  (Int ~ String) works but ew.
03:36:52  I don't know.
03:37:18  At least do (False ~ True) or something.
03:37:36  Or data Blah = A | B; (A ~ B)
03:38:59  I have a Foldr and FoldR that are two different things.
03:39:07  That's good, right?
03:45:43  elliott: do you have a foldR
03:47:01  http://okmij.org/ftp/cpp-digest/toy_OS.txt
03:50:00  monqy: http://hpaste.org/76553
03:53:58  something tells me haskell wasn't made to do this!!!!!
03:54:38  monqy: they should have thought of that before they invented GHC extensions!!
04:27:34  how do i get a specific element out of a tuple in haskell? lets say x out of (x,y,z)
04:28:16  0) Tuples may be the wrong thing to use if you need that; 1) f (x,y,z) = x
04:28:42  or: f (x,_,_) = x
04:29:51  (But probably you want to pattern-match directly in your function, rather than defining f and using it.)
04:29:54  (But see #0.)
04:30:14  yourFunction (x,_,_) = doSomethingWith x
04:31:10  just want to know how to address a value of a tuple.. lets have an example (and please i'm not out to reinvent the whell, just try to get an idea of it)
04:31:13  let v2len va vb = sqrt(((vb!!0) - (va!!0))^2 + ((vb!!1)-(va!!1))^2)
04:31:40  how to make it happen with tuples
04:31:54  !! works only for lists
04:32:42  know what i mean?
04:32:42  you probably shouldn't use (!!) either btw
04:32:47  yep
04:32:56  thats exactly what im asking
04:33:12  v2len (ax,ay,az) (bx,by,bz) = sqrt ((bx-ax)^2 + (by-ay)^2 + (bz-az)^2)
04:33:24  -- was typing what ion was writing, yeah.
04:33:28  ah
04:33:28  ion: Wait, why do you have three values there?
04:33:29  okay
04:33:34  The lists are two elements long in hagb4rd's example.
04:33:45  i see
04:33:46  He was talking about a 3-tuple at first.
04:33:54  yep, thank you
04:33:57  it's clear now
04:35:47  @let matrix = ((1, 0, 0), (2, 4, 4), (0, 0, 0))
04:35:48   Defined.
04:35:54  :t matrix
04:35:55  forall t t1 t2 t3 t4 t5 t6 t7 t8. (Num t, Num t1, Num t2, Num t3, Num t4, Num t5, Num t6, Num t7, Num t8) => ((t, t1, t2), (t3, t4, t5), (t6, t7, t8))
04:36:16  nice inferred type
04:36:32  hagb4rd: FWIW if you have a tuple of more than two elements you usually want to define your own data type.
04:36:53  data Row a = Row a a a; data Matrix a = Matrix (Row a) (Row a) (Row a) and then use Matrix Integer, or whatever.
04:37:05  kool
04:38:38  Don’t do this, you don’t want to use lists as geometrical vectors, but here’s a toy example of computing the length between two lists of arbitrary length (assuming both have the same length). I just thought it might be educational wrt. avoiding (!!). f as bs = (sqrt . sum . map (^2)) ds where ds = zipWith (-) as bs
04:40:23  Another thing that is wrong with it is the unchecked assumption that the lists have the same length.
04:41:06  ion: I don't understand why you use where where there instead of just inlining it, possibly using ($).
04:41:56  I thought giving a (somewhat descriptive) name to the intermediate list would make it clearer for a newbie.
04:42:03  okay, i guess there are already some functions for playing arond r2, r3..how would you implement  transformation matrices (lets say sth like a rotation in R2 :)
04:42:10  ion: Fair enough.
04:44:28  i would like implement a R3->R2 transformation (display 3D on 2D screen) for some very basic geomatrical figures (vertices, lines).. that would be nice :)
04:45:54  i guess the z-values need to be moved towards the vanishing point in some way
04:47:55  (so the further away you get, the more they get moved towards viewcenter)
04:48:11  gd
04:48:14  whoops
04:48:17  wrong window
04:48:29  is this #haskell now
04:48:45  kmc: yes
04:48:57  kmc: join #haskell and talk about esolangs
04:49:09  420 join #haskell every day
04:49:37  sleep, 'night
04:49:41  Let’s think of a simple case where you only implement the multiplication of a 3×3 matrix with a 3-vector. Using elliott’s Row and Matrix types and also defining
04:49:50  data Vector a = Vector a a a
04:50:01  how would you multiply a single Row with a Vector?
04:50:03  i guess haskell would be a very efficient way to implement such calculations in a few lines of code :)
04:51:14  http://www.youtube.com/watch?v=vSTJL1ikxXY
04:54:25  i wonder if that was rethinkdb's thinking
04:55:00  To prevent people from downloading the newest games, Black and White, a "no experience" security patch was added. This *encourages* downloading the newest games, if you want to use this, isn't it?????
04:58:51  I don't know.
05:01:33  hagb4rd: Feel free to ask if you’re not sure.
05:03:01  yea, i will readmy self on through some docs first.. but cool thank you
05:03:10  consider it noted
05:03:28  I mean, we can go through the implementation right now.
05:03:50  if you want
05:10:43  guess i better try to catch up some of the basic ideas of haskell-typing first..
05:11:03  don't want to waste your time with this
05:11:33  but we can speak lateron if you like. i would be glad too :)
05:12:04  ok
05:19:51  but we could discuss the algorithm on how to solve the (z-transformation/that thing with the vanishing point).. pseudo code/math/whatever
05:25:03  is z-transformation an esolang
05:25:19  an implementation of it might be
05:25:25  hagb4rd: You might find this useful. http://www.scratchapixel.com/lessons/3d-advanced-lessons/perspective-and-orthographic-projection-matrix/perspective-projection-matrix/
05:25:49  perfect
05:25:52 -!- nys has quit (Quit: quit).
05:26:04  thank you
05:30:23  kmc: exciting ipwn update: it's just "on hiatus".
05:31:08  barts: also i admit trying to creep some scope from you handsome people ;)
05:33:05  "TWO-THIRDS of Scots would back independence if they believed it would make them £500 better off, according to a poll."
05:33:17  in other news, a third of Scotland would knowingly vote against their own interests
05:33:44  loaded questions, the finest art
05:34:29 -!- ogrom has joined.
05:47:09  elliott: haha
05:51:49 -!- TodPunk has quit (Read error: No route to host).
05:52:44 -!- TodPunk has joined.
06:02:13 -!- ogrom has quit (Quit: Left).
06:10:03  shachaf: Did you know if you d othis
06:10:06  *do this
06:10:07  data Foldy p = Foldy {friend::forall a us. (p a) => a -> FoldR p us -> FoldR p (a ': us)}
06:10:10  you get a type error?
06:10:14  The accessor doesn't type.
06:10:25  WRONG
06:10:32  I get a "FoldR not in scope" error
06:10:44  Has anyone win at Iter Vehems ad Necem with zero contrast? Has anyone win with maximum contrast?
06:11:28  I've never won :(
06:11:38  don't worry monqy
06:11:39  but I've gotten "pretty dang far" and then died and then gotten bored
06:11:45  you win at life
06:11:51  "it's true"
06:12:15  : o
06:17:56      Expected type: a -> FoldR p us -> FoldR p ((':) * a us)
06:17:56        Actual type: a -> FoldR p us0 -> FoldR p ((':) * a us0)
06:17:59  ghc
06:19:02  i heard ghc was the worst compiler ever
06:19:17  me too
06:19:45  this must be penance for your unsafecoerce shenans
06:20:05  barts: i heard barts smells
06:20:14  who knows the real trutrths in the world...........................
06:20:18  eat my shorts
06:20:25  good one
06:20:38  monqy: ps this is me trying to undo said `shenans'
06:21:52  it's still upset
06:25:19  sacrifice a virgin compiler
06:27:09  barts: btw who are you
06:27:30  `pastelog barts
06:27:50  hlep
06:27:55  `pastelogs barts
06:27:59  h t h
06:28:10  No output.
06:28:16  `pastelog pastelog
06:28:20  http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.18045
06:28:26  http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.6290
06:29:05  Why did that work?
06:29:23  `run ls -lh $(which pastelog)
06:29:27  ​-rwxr-xr-x 1 5000 0 602 Oct 21 06:29 /hackenv/bin/pastelog
06:31:28  data Foldy p = Foldy (forall a us. (p a) => a -> FoldR p us -> FoldR p (a ': us))
06:31:28  data Foldy' p = Foldy' (forall a us. (p a) => HList us -> a -> FoldR p us -> FoldR p (a ': us))
06:31:38  shachaf: Can you write a function to convert between these two types without using unsafeCoerce at all?
06:31:45  Declare type family FoldR (p :: * -> Constraint) (xs :: [*]) :: *
06:31:51  and data HList :: [*] -> *
06:32:11  Foldy p -> Foldy' p is what's desired.
06:33:05  elliott: @paste or something, I can't read IRC lines like this.
06:33:08 * shachaf is barely awake.
06:34:42  shachaf: http://sprunge.us/iPBU
06:34:52  shachaf: The only change between the two types is the inclusion of a dummy parameter at the front.
06:34:55  Your conversion can ignore it entirely.
06:35:04  It's only there to unify the type argument of the HList with the us elsewhere.
06:35:15  i.e., in spirit, you want convert (Foldy p) = Foldy' (\_ -> p).
06:35:18  (But you'll find that won't work.)
06:36:07  That doesn't even compile.
06:36:13  Your paste.
06:36:30  I guess you need to import GHC.Prim or something.
06:36:35  Oh, right.
06:36:39  Yes, you need to import that for Constraint.
06:36:46  GHC.Exts, rather.
06:38:31  elliott: whoa, dude, convert (Foldy p) = Foldy' (\_ -> p) doesn't work.
06:39:00  Yep.
06:39:05  It's because type family.
06:39:11  I think.
06:39:14  Can you think of a way to fix it?
06:39:37  Note that Foldy' (\_ -> unsafeCoerce p) does work, I think. It just refuses to unify for some reason.
06:40:32  Can you simplify this a bit?
06:40:41  I bet the whole HList thing isn't necessary.
06:40:44  shachaf: Sure.
06:40:46  (It isn't.)
06:41:22  And even foo (Foldy p) = Foldy p doesn't type-check.
06:41:56  Right.
06:41:58  shachaf: http://sprunge.us/EFQX
06:42:04  (Plus the relevant extensions.)
06:42:07  Then write Foo a -> Foo' a.
06:42:14  (Note: I haven't tested that this has the same problem, but I'm virtually certain it does.)
06:42:31  shachaf: Er.
06:42:38  shachaf: data Foo a = ... should just be data Foo = ...
06:42:41  Same for Foo' a = ...
06:42:43  You want Foo -> Foo'.
06:43:18  can you recommend a haskell gui?
06:43:22  ide
06:43:35  i use vim and emacs
06:43:39  there's leksah if you really want an ide
06:43:44  but i don't, personally
06:45:31  yea i installed leksha but i already _hate_ it
06:45:47  okay
06:45:52  notepad will do
06:45:59  elliott: type family Hi a; data Foo = Foo (forall a. Hi a); conv (Foo x) = Foo x
06:47:54  shachaf: I take it that doesn't work?
06:47:57  shachaf: That doesn't really bother me though.
06:48:01  I know you can't just write it as identity.
06:48:06  shachaf: (And BTW I think that is intentional behaviour.)
06:48:25  elliott: If that doesn't work, why do you expect your more complicated case to?
06:48:34  shachaf: Because you have to do it differently.
06:48:35  I don't know how.
06:48:39  But I bet you can use the forall somehow.
06:54:30  foo :: (forall a. Hi a) -> (forall b. Hi b)
06:54:35  Can you write that?
06:54:49  shachaf: Can you?
06:55:01  Maybe.
07:01:57  elliott: "NB: `Hi' is a type function, and may not be injective"
07:02:01  What if you just use a data family instead?
07:02:30  shachaf: That would defeat the whole point.
07:02:38  The only reason I have a type family is so that it can be a type synonym family.
07:04:00  hate the synonym not the syn
07:08:23  GNU is my IDE
07:11:03  hi
07:11:13  hi monqy :')
07:11:33  what s'up!!
07:12:30  monqy: EVERYTHING
07:25:13  elliott: What if you just write some instances?
07:28:30  shachaf: Like what?
07:28:46  Any.
07:29:55  shachaf: What kind of instance?
07:30:08  type instance FoldR blah
07:30:13  Presumably this family has instances?
07:30:59  shachaf: Sure.
07:31:03  Adding an instance doesn't change anything.
07:31:08  Since I have them.
07:37:09 -!- epicmonkey has joined.
07:53:10  how would i just have these few lines of code executed everytime i start ghci?:
07:53:11  data Vector4 a = Vector4 a a a a; let p1 = 0.0 0.0 0.0 0.0;
07:53:20  sry
07:55:44  fuck this can't be so complicated.. modules imports omg.. do i need all this shit? just want to exec this 2 lines.. nothing more. please help
07:56:31  data Vector4 a = Vector4 a a a a; let p1 = Ve0.0 0.0 0.0 0.0;
07:56:41  data Vector4 a = Vector4 a a a a; let p1 = Vector4 0.0 0.0 0.0 0.0;
07:57:04  damnit sry.. the last version works.
07:57:48  but howto run as a scipt/batch?
08:00:45  @data Vector4 a = Vector4 a a a a;
08:00:45  Unknown command, try @list
08:00:56  >data Vector4 a = Vector4 a a a a;
08:16:38  #!/usr/bin/env runhaskell
08:23:02  thx barts
08:42:35 -!- Phantom_Hoover has joined.
08:49:25 -!- Nisstyre-laptop has quit (Ping timeout: 246 seconds).
08:49:54  yw
08:57:33 -!- MoALTz has joined.
09:13:59 -!- monqy has quit (Quit: hello).
09:16:54  Confucius say too much. -- Recent Chinese Proverb
09:17:15  i like that zzo38 
09:17:23  `addquote  Confucius say too much. -- Recent Chinese Proverb
09:17:33  871)  Confucius say too much. -- Recent Chinese Proverb
09:28:52  shachaf: Does Rust support dynamic loading?
09:32:23 -!- zzo38 has quit (Remote host closed the connection).
09:32:37  why does #esoteric only talk about mainstream computer languages today
09:32:56  next up: agda
09:34:34 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
09:44:32 -!- Phantom_Hoover has joined.
09:47:06  barts: you are welcome to supply discussion of esolangs
09:47:19  failing that the channel is more people who like esolangs talking about random crap than actually a channel about esolangs
09:47:57  sometimes the people don't even really like esolangs
09:48:13  Except in clear help channels usually there are just people having the same interestst
09:48:30  but that does not mean they talk about what the name of the channel would suggest :)
09:51:17  but to change the topic into a random direction
09:51:34  what about an esolang only accepting a bunch of differential equations as programs?
09:52:55  what about an esolang only accepting equations which are wrong .
09:53:36  what about an esolang
09:53:47  what about an esolang where you are only allowed to work on monids
09:53:51  *monoids
09:54:11  essentially that means you only have one 'instruction' 
09:54:19  you ruined the pattern mroman
09:54:21  now you must die
09:54:31  what about an esolang where you must die?
09:54:46  hellang :)
10:00:00  what about an esolang which is so esoteric it can't possibly exist.
10:04:06  what about
10:11:31 -!- barts_ has joined.
10:12:24 -!- nooga has joined.
10:12:28  https://github.com/smtlaissezfaire/bcompiler whaaa
10:15:09 -!- barts has quit (Ping timeout: 276 seconds).
10:42:53 -!- carado has joined.
10:49:43 -!- Jafet has quit (Quit: Leaving.).
10:51:55 -!- epicmonkey has quit (Remote host closed the connection).
10:52:17 -!- epicmonkey has joined.
10:52:29 -!- Jafet has joined.
11:02:19 -!- Jafet has quit (Quit: Leaving.).
11:14:46 -!- ogrom has joined.
11:15:01 -!- ogrom has quit (Client Quit).
11:17:55 -!- nooga has quit (Ping timeout: 260 seconds).
11:32:40 -!- Phantom_Hoover has quit (Remote host closed the connection).
11:50:35 -!- nooga has joined.
12:20:27 -!- nooga has quit (Ping timeout: 260 seconds).
12:57:54  @tell ion [hagb4rd.geometry.transformation.haskell] i've got some (very basic) work done now.. guess this would be a good point to start from: http://pastie.org/5093143
12:57:55  Consider it noted.
12:59:35  > p = "np"
12:59:37    : parse error on input `='
12:59:42  > let p = "np" in p
12:59:44    "np"
13:00:01 -!- carado has quit (Ping timeout: 246 seconds).
13:00:22 -!- Jafet has joined.
13:12:19 -!- nooga has joined.
13:12:32 -!- carado has joined.
13:18:45 -!- nooga_ has joined.
13:21:35 -!- nooga has quit (Ping timeout: 246 seconds).
13:29:10 -!- nooga has joined.
13:31:54 -!- nooga_ has quit (Ping timeout: 240 seconds).
13:38:17 -!- Frooxius has joined.
13:42:38 -!- nooga_ has joined.
13:45:47 -!- nooga has quit (Ping timeout: 252 seconds).
13:58:27 -!- hagb4rd has quit (Read error: Connection reset by peer).
14:13:20 -!- Vorpal has joined.
14:26:20 -!- hagb4rd has joined.
14:42:30 -!- nooga has joined.
14:45:14 -!- nooga_ has quit (Ping timeout: 240 seconds).
14:47:36 -!- ogrom has joined.
14:50:04 -!- nooga has quit (Ping timeout: 246 seconds).
14:50:36 -!- nooga has joined.
15:02:08 -!- nooga has quit (Ping timeout: 255 seconds).
15:15:48 -!- ogrom has quit (Quit: Left).
15:17:15 -!- AnotherTest has joined.
15:17:24  hello
15:18:30  hello
15:18:44 -!- Arc_Koen has joined.
15:18:57  hello
15:19:07  hello
15:23:32  hello
15:24:23  hello
15:24:51  hello
15:25:09  I feel so welcome
15:25:15  that's overwarming
15:25:46  hey
15:25:47  sorry we actually hate you
15:25:55  just having a chorus of hellos and you happened to drop by
15:26:02  now we will kill you
15:28:36  oh, now I understand why that tinkerbell guy felt rejected
15:28:54  he must have dropped by in the middle of a go out chorus, or something
15:29:43  no that's just because we're all completer asses
15:30:54  Well maybe the go out chorus was a consequence of that
15:38:20  mroman: #include is working
15:45:15  #include 
15:48:56  You don't need < > or " " though :p
15:51:46  you're not using the normal C preprocessor?
15:54:06  no, he's using a parallel version
15:57:25 -!- atriq has joined.
15:58:33  kmc: This is for HELP
15:58:58  that's an esolang?
15:59:01  I think I might stop using Ubuntu
15:59:10  BUT I DON'T KNOW WHAT TO SWITCH TO
15:59:14  it's pretty easy to invoke the regular C preprocessor
15:59:24  though it will make some assumptions, like removing C comments
15:59:30  that might be unsuitable for some languages
15:59:48  GHC Haskell uses CPP in some circumstances and it's kinda gross
16:01:25 -!- copumpkin has quit (Ping timeout: 248 seconds).
16:01:59 -!- copumpkin has joined.
16:02:13  kmc: No just a preprocessor for esolangs
16:02:38 -!- atriq has quit (Quit: Leaving).
16:02:54  atriq: I switched to Debian some time ago. I find it better than ubuntu was when I stopped using it
16:03:00  oh
16:03:10  @tell atriq I switched to Debian some time ago. I find it better than ubuntu was when I stopped using it
16:03:10  Consider it noted.
16:04:45  i've been happy with Debian since forever
16:06:18 -!- atriq has joined.
16:08:46  :t ()
16:08:46  atriq: You have 1 new message. '/msg lambdabot @messages' to read it.
16:08:47  ()
16:09:08  AnotherTest, okay, I'll keep Debian in mind
16:11:11  Debian is maintained by competent, careful people
16:12:04  Does WINE work on Debian? (I'm guessing yes)
16:12:13  they don't change everything every six months in order to chase some half-baked imitation of Apple products
16:12:16  yes
16:12:25  there's very little open-source Linux software that is distro-specific
16:12:32  and yes Debian has packages for WINE
16:12:36  In the Future will Steam work on Debian (I'm still guessing yes)
16:12:43  beats me
16:13:01  i mean, someone will almost certainly figure out a way
16:13:04  debian and ubuntu are pretty close
16:13:10  they use the same package manager
16:13:16  sometimes you can install ubuntu packages on debian as-is
16:13:47  Yes
16:14:24  I'd rather say debian packes on ubuntu as-is
16:14:37  Not sure if ubuntu has their own package managing system
16:14:56  I think they still use debian packages
16:15:04  that's not relevant to the question of whether steam will work on debian
16:15:11  Valve said that Steam on Linux is being released as a closed external beta some point in October, which is Valve time for around about Christmas
16:15:25  yes, ubuntu uses .deb packages, installed with dpkg and apt and such
16:15:34  ubuntu releases are distributed as apt repositories
16:15:45  it is much the same infrastructure as debian
16:16:00  but e.g. an ubuntu package might depend on a version of libc which doesn't exist in debian's repositories
16:16:10  which is why it doesn't always work
16:16:41  commercial linux software is often statically linked or bundled with its own libraries in order to avoid such problems
16:17:06  even if not, you could set up an ubuntu chroot to run steam, it's not too hard
16:18:08  Or manually unpack the .deb
16:18:25  that won't get you the libc version you need
16:18:33  or do you mean, unpack the ubuntu libc .deb
16:18:36  and all the other dependencies
16:18:46  and then wire them all up in a subdirectory
16:19:16  you could do that, but setting up a proper ubuntu chroot is probably easier
16:19:24  debian/ubuntu have good tools for creating and managing chroots
16:20:13  kmc: In theory, the libc version should be ABI compatible, apt just doesn't know that.
16:21:12  That is, if you just *unpack* Ubuntu packages on Debian, and manually make sure the dependencies are installed, it'll mostly work.
16:21:20  yeah, perhaps
16:21:33  glibc does break ABI compatibility from time to time though
16:21:39  Some of the other libraries might have ABI issues though.
16:21:43  but still, this probably works for current debian vs. current ubuntu
16:21:44  yeah
16:27:06  How easy is it to install Debian over Ubuntu?
16:27:16  by "over" you mean "instead of"?
16:27:27  Yes-ish
16:27:30  Yes
16:27:42  not much harder
16:28:14  I mean, "over" as in "I've got Ubuntu now, and I want to go to Debian"
16:28:31  can you back up the files you care about and do a clean reinstall?
16:28:58  That is feasible
16:32:30 -!- augur has quit (Remote host closed the connection).
16:44:05  hello
16:44:11  Hey
16:44:21  morning
16:44:31  @time barts_
16:44:32  Local time for barts_ is Sun Oct 21 18:44:18 2012
16:44:44  It's not morning for either of us
16:46:36  there is a script which you can run as root on any linux and it makes it into a debian
16:46:55  @time atriq
16:46:56  Local time for atriq is Sun Oct 21 17:46:56
16:47:10  you're british!
16:47:15  Yes
16:47:17  Yes I am
16:47:24  I thought this was already established
16:47:29  `? hexham
16:47:34  Hexham is a European town. There are nine people in Hexham, and at least two of them are in this channel. Taneb looks after the ham.
16:47:37  hmm, maybe
16:47:55  But yes, I'm one of the thousands of people living in Hexham
16:48:31  I'll come to your kingdom for new year's eve
16:49:00  why would you do that
16:49:26  To see the queen's speech?
16:49:27  I dunno
16:49:42  I think you can watch the queen's speech from outside the UK
16:49:54  And I think it's on at Christmas, not New Years
16:50:58  barts_ weeeeeeell
16:51:08  because my last few new year's eves in france sucked
16:51:20  because last yeat in london was greate
16:51:27  http://www.reddit.com/r/ProgrammerHumor/comments/11u0rx/you_all_have_probably_already_seen_these_but/
16:51:31  oh and also because of a girl
16:51:33  I might be slightly easily amused
16:51:47  Arc_Koen, is this the girl mentioned on your user page?
16:52:01  a candidate
16:52:04 -!- carado has quit (Ping timeout: 246 seconds).
16:52:21  Don't you think restricting by gender is close-minded?
16:53:06  well I'm guessing if that restriction turns out to be wrong my mind will blow out open
16:53:55  I just deleted a gigabyte's worth of recording of the Queen's Diamond Jubilee Concert of 2012.
16:54:14  They sent it out in Finnish tellyvision.
16:54:23  I don't know about any yearly speeches, though.
16:56:05 -!- MoALTz has quit (Quit: Leaving).
17:03:37 -!- augur has joined.
17:04:42 -!- carado has joined.
17:26:04  Wait. There's a patent on John Titor's time travel machine?
17:26:19  Hmm, just the theory
17:27:29  That's still... erm
17:28:26  Can I patent a process for making a turing machine that solves the halting problem?
17:28:35  Maybe I could get a patent on a way to make 1+1=3
17:29:23 -!- atriq has quit (Ping timeout: 246 seconds).
17:32:34  there are many patents on impossible things
17:32:41  there are patents on algorithms to compress any file by at least one byte
17:34:16  o.O
17:35:13  I have to know what those claim about compressing the 0-byte file
17:35:22  Actually, I'm curious to see one in general
17:35:46  (And yes, I know compressing the 0-byte file isn't the biggest problem. Although I don't know if it might be connected)
17:36:07  Removing a byte from a 0-byte file *is* not exactly easy.
17:36:08  pigeonhole principle
17:36:25  But it's not like patents need to make sense.
17:37:13  yeah, i'm not sure it's actually a problem that people can patent impossible things
17:37:19  http://gailly.net/05533051.html
17:37:51  Oh, it's just one bit.
17:37:57  (If that's the same.)
17:38:20  There was a Finnish nonsense compression thing around few years back.
17:38:26  Something to do with repeated compression.
17:38:38  There were lots of arguments on the tubes, as usual.
17:38:54  "Of course, this does not take into account any overhead registers or other "house-keeping" type information which must be tracked. However such overhead tends to be negligible when processing the large quantities of data typically encountered in data compression applications."
17:38:54  I think they also claimed something about compressing every file.
17:38:55  :D
17:39:13  kmc: Presumably it's a special case of something that is a problem, though.
17:39:33  also i like the old DOS "compression" utilities where "compress" is actually just delete, and "decompress" recovers your file from the free blocks on the hard drive
17:39:57  shachaf: the patent system?
17:40:14  Well, that people can patent things that patent examiners don't know whether are possible or not.
17:40:29  is that actually their job, though?
17:41:25  i might prefer a system where the government's role in the patent system is minimized and instead you incentivize private companies to take down bad patents
17:42:13  Bleh, I can't recall the name of the company involved. As I recall, they were doing something completely different, and then their resident genius programmer just figured out the ultimate compression algorithm.
17:42:18  Well, it's easy to make a compression algorithm that in the worse case expands the data by 1 bit.
17:42:58  Sgeo: That's nothing. I can make a compression algorithm that in the *best* case expands the data by 1 bit.
17:43:21 * kmc invests in shachaf's company
17:43:40  What do you call an algorithm that takes an algorithm as input?
17:43:52  an algorithm
17:44:11  unless you are guido van rossum then you call it "oh god what is that get it away from me"
17:44:15  Yes, stop being so racist, Sgeo.
17:44:28  Maybe it was a setup for a joke, though? 
17:44:33  nope
17:45:40  Aw, the company's website has disappeared.
17:46:49 -!- elliott has quit (Ping timeout: 272 seconds).
17:48:16  Anyway, the idea was that you can just rerun it over and over again to compress everything to the "theoretical limits".
17:48:58  And the company was an ad agency "for reals", they just happened across the ultimate secret.
18:02:41  http://uncyclopedia.wikia.com/wiki/Haskell <- the f*?
18:04:59  kmc: Compress is delete? Now that's lossy compression
18:09:04 -!- carado has quit (Ping timeout: 246 seconds).
18:11:28 -!- AnotherTest has quit (Quit: Leaving.).
18:33:09 -!- hagb4rd has changed nick to hagb4rd|afk.
18:33:11  >retro music tip .. beautiful deep black female voice.. https://docs.google.com/file/d/0BzorK_eWYM0-bXJ1b3hWcmJxOTA/edit
18:36:17  "Scala has a lot of upside because it is extensible and Clojure has a lot of upside because it is an easy language to learn."
18:36:18  what.
18:36:44  Well, I mean, I imagine Clojure being easier to learn than Scala, but um, how is Scala more extensible?
18:49:44 -!- MoALTz has joined.
18:54:56  Sgeo: the smaller it is, the more you can extend it!
18:57:16  What does extensible even mean for a language?
18:57:20  defmacro stuff?
18:58:44  it means whatever you need it to mean in order to prove the point you're making
18:58:51  like every other adjective applied to programming languages
18:59:50  can "programming" be considered an adjective?
19:00:56  Well, there are programming books, so I suppose so
19:01:23  Also programming languages
19:01:30  The programming language known as English
19:02:21  I'm sure it was linked recently, http://www.osmosian.com/
19:04:43 -!- Arc_Koen has quit (Ping timeout: 246 seconds).
19:05:30  Sgeo: The problem is that there is no compiler for English
19:05:57  Isn't there an implementation? Not sure what it is though
19:06:43  But it's not a proper one. Won't work for all imputs
19:07:42  natural language would be a *terrible* programming language
19:07:56  English is terrible for specifying precise instructions
19:07:58  Agreed
19:08:01 * Sgeo meant of Osmosian Order's language
19:08:12  Maybe you could use Lojban
19:08:16  But not English
19:12:22 -!- Arc_Koen has joined.
19:15:15  honestly did any of you learn lojban?
19:16:15  it sounded very interesting, but at the same time learning a language that no one actually speaks seems kind of a waste when there are so many useful languages
19:17:37  I've looked at it before
19:17:55  There are lojban IRC channels
19:38:35  so I've made this emmental program
19:38:37  almost
19:39:53  it's very "destructive" as it redefines all of char 3-255 to mean "subtract 3 and try again" and char 0 to mean "output '0'", char 1 to mean "outout '1'", char 2 to mean "output '2'"
19:40:17 -!- augur_ has joined.
19:40:22  problem is, once you've defined everything like that, you cannot actually begin the last "loop" of -3 decrements
19:40:42  because you have no char left to be the triggering instruction!
19:41:37  so I only redefined chars 3-254, and before doing so, I defined char 255 to mean "redefine yourself to mean the same as the others, then take a char from input, then execute the char taken from input"
19:41:56 -!- augur has quit (Ping timeout: 252 seconds).
19:42:16  so once I've redefined everything else, I can still use char 255 to begin
19:42:22  except
19:42:30  I DON'T HAVE A CHAR 255 ON MY KEYBOARD
19:43:11 * Sgeo thinks its neat that Clojure will yell at you for at least one sort of attempted unhygienic macro
19:43:15  http://ideone.com/PgiIQd
19:44:16  hmm, the compilers I use most often have the habit of halting when there are too many inconsistencies
19:45:08  but this is ridiculous: I have to substitute a printable char for char 255
19:45:49  and printable char are in the middle of all that, so I can't make a pseudo-for loop "push chars 4 to 254 on the stack"
19:49:55  `chr 70
19:49:55  oh wait that's EgoBot
19:49:58  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: chr: not found
19:51:49  Arc_Koen: I've studied Lojban some, but I stopped... over a year ago, I think.
19:51:51  oh wait I could be clever
19:52:53  tswett: Lojban does sound very attractive but seriously didn't you think learning a language that might connect you with your neighbours would be better?
19:53:15  Yes.
19:53:27  Above all, Lojban is an experiment.
19:53:44  (though I realize that's a pretty odd consideration to have in the channel for esoteric programming languages)
20:02:36  it would be interesting to see what lojban becomes if it had some actual native speakers from birth
20:02:44  i bet a lot of the logical purity goes right out the window
20:09:41  this is one of the reason I'd like to be immortal
20:11:34  maybe after so many hundreds of years, and raising many many children, it eventually becomes enough of a routine thing that you start spicing it up with experiments of this kind
20:12:33 -!- zzo38 has joined.
20:13:58  ok, so, the program works properly when input is congruent with either 0 ro 2 modulo 3
20:14:17  but when it's congruent with 1 it complains the stack is empty
20:17:20  a logical conclusion would be that there's a difference between the definition of 1 and the definitions of 0 and 2
20:17:40  ; #35#52#56#46 #!
20:17:40  ; #35#52#57#46 #1!
20:17:41  ; #35#53#48#46 #2!
20:17:57  they seem close enough to me
20:18:20  ohhhhhh or there is a problem with the definition of 4
20:18:25  of course
20:33:36 -!- hagb4rd|afk has quit (Quit: hagb4rd|afk).
20:36:43 -!- monqy has joined.
21:00:17  @tell hagb4rd Some suggestions wrt. the code: 0) The semicolons are redundant, i’d remove them. 1) Run hlint against the code, it will give some good suggestions. 2) After seeing how that implementation will be nicer to read with hlint’s suggestions, switch from record accessors to pattern matching. That will make it even nicer.
21:00:17  Consider it noted.
21:04:02  @tell hagb4rd You can use “data Vector4 … = … deriving (Eq, Read, Show)” to get default Show etc. instances.
21:04:02  Consider it noted.
21:06:31 -!- augur_ has quit (Remote host closed the connection).
21:13:31  @tell hagb4rd Also, when you feel you’ve learned everything you can from writing your own vector and matrix math implementation, i’d suggest switching to HMatrix or REPA. They are mature, optimized libraries.
21:13:32  Consider it noted.
21:18:22 -!- Nisstyre-laptop has joined.
21:27:11 -!- augur has joined.
21:32:18 -!- nortti has quit (Ping timeout: 252 seconds).
21:32:59 -!- aloril_ has quit (Ping timeout: 260 seconds).
21:34:10 -!- nortti has joined.
21:41:50 -!- aloril_ has joined.
22:00:30  it's kind of terrifying when your javascript code grows from 10 lines in a