00:23:49 <monotone> Everything would have to be elegant somehow.
00:24:10 <monotone> Ballet, the programming language.
00:25:14 <Phantom__Hoover> yeah, language design is probably too fancy to do something as simple as intercal these days
00:27:25 <monotone> If only it were as easy as flipping "GO TO" around these days.
00:27:39 <Bike> how would you parody coroutines, hm
00:28:31 -!- Sgeo has joined.
00:32:31 <monotone> "In order to represent the alienation of the modern man, data cannot be passed between coroutines."
00:33:40 <ion> How can one even screw up that badly? :-D https://groups.google.com/forum/#!msg/jenkinsci-dev/-myjRIPcVwU/t4nkXONp8qgJ
00:34:46 <monotone> Incidentally, Google apparently has an INTERCAL style guide. http://cadie.googlecode.com/svn/trunk/INTERCAL-style-guide.html
00:35:20 <ion> Hah, awesome
00:36:09 <monotone> WRT the Jenkins thing it was apparently a badly configured plugin for their code review system.
00:37:26 -!- augur has joined.
00:37:56 <Sgeo> http://www.theonion.com/articles/ncis-to-cease-print-edition,34523/
00:38:16 <shachaf> ion: they sure flogged those repositories
00:42:05 <oerjan> Sgeo: is that an allusion to the onion itself ceasing its print edition
00:42:17 <Sgeo> oerjan: I assume so
00:43:05 <oerjan> which i somehow saw mention in a norwegian newspaper's travel guide about a brooklyn hotel
00:45:22 <Sgeo> http://literallyunbelievable.org/post/66676985668/the-onion-is-usually-not-creditable
00:48:34 -!- prooftechnique has quit.
00:48:47 -!- prooftechnique has joined.
00:49:36 -!- prooftechnique has quit (Client Quit).
00:49:43 -!- prooftechnique has joined.
00:50:09 <oerjan> <kmc> reasonably < really
00:50:17 <oerjan> > "reasonably" < "really"
00:50:23 -!- Phantom__Hoover has quit (Quit: Leaving).
00:50:52 <shachaf> > let (reasonably,really) = ("really","reasonably") in reasonably < really
00:51:12 <oerjan> well those are of course really reasonable definitions
00:55:42 <kmc> > "reasonably" < "really"
00:55:43 <lambdabot> lexical error in string/character literal at character '\...
01:00:30 <oerjan> maybe you're not utf-8 clean?
01:01:07 <kmc> utf-8 dirty
01:01:37 <lambdabot> lexical error in string/character literal at character '\SI'
01:02:16 <kmc> `unicode ZERO-WIDTH JOINER
01:04:00 <oerjan> > "reasonably" < "really"
01:04:51 <oerjan> > "reasonably" < "really"
01:05:05 <quintopia> !bfjoust space_hotel http://sprunge.us/SGOW
01:05:09 <lambdabot> lexical error in string/character literal at character '\8...
01:05:11 <EgoBot> Score for quintopia_space_hotel: 41.7
01:05:50 <lambdabot> lexical error in string/character literal at character '\8...
01:06:14 -!- Sprocklem has quit (Ping timeout: 240 seconds).
01:06:31 <lambdabot> lexical error in string/character literal at character '\...
01:07:58 <HackEgo> [U+0020 SPACE] [U+200B ZERO WIDTH SPACE]
01:09:00 <oerjan> hm that's disturbing, delete deletes the zero width space together with the preceding space
01:09:31 <HackEgo> [U+200B ZERO WIDTH SPACE]
01:09:40 -!- Koen_ has quit (Quit: Koen_).
01:09:53 <kmc> oerjan: does it do the same for printable diacritic combiners?
01:10:26 -!- shikhin_ has quit (Remote host closed the connection).
01:10:33 <oerjan> but it means i cannot usefully paste just a zero width space into irssi
01:13:59 -!- yorick has quit (Read error: Connection reset by peer).
01:14:16 <kmc> i used ISO 14755 mode
01:14:35 <kmc> hold Ctrl-Shift in urxvt and then you can type hex digits
01:15:02 <quintopia> interesting that my score went down
01:16:20 <HackEgo> [U+200B ZERO WIDTH SPACE]
01:16:49 <oerjan> alt+numpad works, in decimal. but then i have to remember the code.
01:16:51 <quintopia> !bfjoust space_hotel http://sprunge.us/WHfL
01:16:56 <EgoBot> Score for quintopia_space_hotel: 44.9
01:17:23 <lambdabot> lexical error in string/character literal at character '\8...
01:17:47 <HackEgo> [U+200B ZERO WIDTH SPACE]
01:18:11 <oerjan> int-e: lambdabot is still not utf-8 clean hth
01:19:25 <oerjan> why it accepts the snowman but not zero width space is beyond me...
01:19:48 <kmc> snowman conquers all
01:20:02 <lambdabot> lexical error in string/character literal at character '\8...
01:20:34 <fungot> 226 152 131 226 128 139
01:22:28 <lambdabot> lexical error in string/character literal at character '\8...
01:22:54 <quintopia> !bfjoust space_hotel http://sprunge.us/PDLa
01:22:58 <fungot> 226 128 138 226 128 139 226 128 140
01:22:59 <EgoBot> Score for quintopia_space_hotel: 45.5
01:23:18 <oerjan> it accepts the first, but not the two next
01:23:58 -!- Taneb has joined.
01:25:46 <fungot> 226 152 131 226 152 139 226 128 139
01:26:13 <oerjan> so, there is no particular byte triggering it.
01:27:04 <HackEgo> [U+200C ZERO WIDTH NON-JOINER]
01:27:40 <lambdabot> lexical error in string/character literal at character '\8...
01:27:53 <HackEgo> [U+200D ZERO WIDTH JOINER]
01:28:41 <oerjan> is lambdabot simply breaking on anything that's zero width?
01:29:31 <HackEgo> [U+200E LEFT-TO-RIGHT MARK]
01:29:41 <lambdabot> lexical error in string/character literal at character '\8...
01:30:17 <lambdabot> lexical error in string/character literal at character '\8...
01:30:29 <HackEgo> [U+0061 LATIN SMALL LETTER A] [U+200C ZERO WIDTH NON-JOINER] [U+0062 LATIN SMALL LETTER B]
01:31:58 <oerjan> hm ghci does the same thing
01:33:23 <oerjan> and accepts the snowman
01:36:22 <oerjan> > Data.Char.generalCategory '\8203'
01:36:32 <oerjan> > Data.Char.generalCategory '\8202'
01:36:35 <oerjan> > Data.Char.generalCategory '\8204'
01:36:39 <oerjan> > Data.Char.generalCategory '\8205'
01:36:42 <oerjan> > Data.Char.generalCategory '\8206'
01:36:49 <oerjan> > Data.Char.generalCategory '\8207'
01:37:00 <lambdabot> lexical error in string/character literal at character '\8...
01:37:39 <oerjan> i say it doesn't like Format characters
01:40:13 <oerjan> i find similar issues on ghc trac but they're old, slightly different, and claimed to be fixed.
01:52:42 -!- prooftechnique has quit.
01:53:52 <quintopia> !bfjoust space_hotel http://sprunge.us/KXCd
01:53:56 <EgoBot> Score for quintopia_space_hotel: 49.0
02:00:10 -!- prooftechnique has joined.
02:01:22 <quintopia> !bfjoust space_hotel http://sprunge.us/XBCa
02:01:27 <EgoBot> Score for quintopia_space_hotel: 49.9
02:04:20 -!- Taneb has quit (Quit: Leaving).
02:23:06 <oerjan> darn reading the haskell report makes me think this is intended behavior; the characters allowed in literals are restricted to "graphic" characters, which doesn't include formatting ones, i think.
02:24:20 <kmc> `can bin/zalgo
02:24:21 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: can: not found
02:24:25 <kmc> `cat bin/zalgo
02:24:27 <HackEgo> #!/usr/bin/python \ import codecs,sys,random \ stdin=codecs.getreader("utf-8")(sys.stdin) \ stdout=codecs.getwriter("utf-8")(sys.stdout) \ x=[unichr(0x300+i) for i in range(0,112)+[393,2887]] \ def z(n,c): \ if c in ["\n"]+x: \ n=0 \ return u"".join(x[random.randrange(0,len(x))] for i in range(n)) \ stdout.write(u"".join(c+z(2,c) for c in st
02:24:30 <quintopia> !bfjoust space_hotel http://sprunge.us/WHcY
02:24:32 <kmc> oh that's not my zalgo
02:24:36 <EgoBot> Score for quintopia_space_hotel: 49.0
02:24:39 <kmc> import System.Random;main=mapM_((>>(י=<<randomRIO('̀','ͯ'))).י)=<<getContents;י=putChar
02:24:54 <kmc> stdout=codecs.getwriter("utf-8")(sys.stdout) <----- python is a classy language
02:25:55 <oerjan> > Data.Char.generalCategory '\8202'
02:26:22 <oerjan> by my reading this isn't actually allowed either.
02:26:36 <tswett> Well, it's a space, right?
02:27:05 <tswett> Apparently HAIR SPACE.
02:27:07 <quintopia> !bfjoust space_hotel http://sprunge.us/NHfA
02:27:11 <oerjan> yes, and the BNF does not include uniWhite in graphic.
02:27:12 <EgoBot> Score for quintopia_space_hotel: 48.7
02:27:55 <tswett> > map negate [1, 2, 3]
02:28:02 <oerjan> hm i can report this as two alternative bugs.
02:28:19 <tswett> I love how is considered whitespace.
02:29:07 <kmc> OGHAM SPACE MARK would be a good name for a currency in science fiction
02:30:17 -!- variable has changed nick to constant.
02:30:48 -!- prooftechnique has quit.
02:30:53 <tswett> Ogham seems like kind of a bad alphabet.
02:32:49 <lambdabot> lexical error in string/character literal at character '\8...
02:33:23 <tswett> Like, who thought it was a good idea to have four different letters each consisting of five parallel lines?
02:33:31 <oerjan> fantastic, it allows that character _except_ where the report allows it.
02:33:54 <tswett> Almost every letter consists of a number of near-vertical parallel lines.
02:34:48 <lambdabot> lexical error in string/character literal at character '\5...
02:39:58 <quintopia> !bfjoust space_hotel http://sprunge.us/CHXJ
02:40:03 <EgoBot> Score for quintopia_space_hotel: 49.3
02:49:07 <quintopia> !bfjoust space_hotel http://sprunge.us/cXbC
02:49:12 <EgoBot> Score for quintopia_space_hotel: 49.4
02:52:22 <kmc> death under ptrace
02:53:33 <quintopia> !bfjoust space_hotel http://sprunge.us/DgQU
02:53:37 <EgoBot> Score for quintopia_space_hotel: 55.1
02:54:35 <quintopia> and that's the sound of me changing the size of the decoy that ais was using to figure out where my flag was in omnipotence. rightful station restored!
02:59:41 <kmc> death to ptrace
03:10:28 <quintopia> !bfjoust space_hotel http://sprunge.us/YEBA
03:10:34 <EgoBot> Score for quintopia_space_hotel: 55.2
03:23:48 <quintopia> !bfjoust space_hotel http://sprunge.us/hZKY
03:23:53 <EgoBot> Score for quintopia_space_hotel: 54.1
03:53:38 -!- nisstyre has joined.
04:02:50 -!- conehead has quit (Quit: Computer has gone to sleep.).
04:12:47 -!- nisstyre has quit (Ping timeout: 260 seconds).
04:27:29 -!- nisstyre has joined.
04:28:13 <oklopol> is there a program where you can fight bfjoust bots manually
04:28:57 <oerjan> i hear people use bfjsout on the web
04:35:46 -!- tertu has joined.
04:39:01 -!- Oj742 has joined.
04:39:50 -!- zzo38 has joined.
04:42:05 <kmc> stupid self-aware makefiles
04:43:00 * Sgeo panics and puts the makefile in a box
04:44:02 <kmc> won't work
04:44:10 * oerjan swats Sgeo for thinking ai boxes work -----###
04:49:57 -!- nisstyre has quit (Quit: Leaving).
04:51:25 <oklopol> oerjan: what's bfjsout on the web
04:52:39 <oerjan> well it's bfjoust in javascript
04:52:57 <oerjan> no idea why google doesn't find it
04:53:45 <oerjan> http://codu.org/eso/bfjoust/egojsout/index.php
04:57:59 -!- Sprocklem has joined.
05:01:10 <oklopol> by manually i meant you press left to go left, right to go right, up to increment etc
05:03:58 <oerjan> WELL WHY DIDN'T YOU SAY SO
05:04:42 <oklopol> what did you think manually meant
05:04:55 <oerjan> not putting them on the hill
05:04:57 <oklopol> "in such a way that the results are shown on a webpage instead of an irc channel"
05:05:39 <oerjan> anyway, that will be unfair to the bots unless you need an instruction (equivalent to [) in order to check the value of your current cell.
05:06:18 <oklopol> i realized it'd be unfair, but i didn't realize it's that easy to fix
05:06:46 <EgoBot> Sorry, I have no help for bfjoust!
05:06:50 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
05:07:46 <oerjan> http://codu.org/eso/bfjoust/report.txt
05:08:04 <oerjan> the list of currently competing programs
05:09:11 <oerjan> http://codu.org/eso/bfjoust/in_egobot/ has the actual code
05:10:30 <zzo38> I tried to think more of making a category of spells in Icosahedral RPG, although it seems the way I have it, the distributive law fails on spell durations. There may be a few different ways to fix this, though.
05:11:08 <oerjan> oklopol: actually the check only should tell you if the current cell is zero, of course
05:12:56 <oklopol> http://codu.org/eso/bfjoust/in_egobot/ doesn't make it very clear which player is which
05:15:37 <zzo38> But I did determine that (prime) objects could be WORLD and EVENT. An ordinary spell that you can cast is (WORLD -> WORLD). EVENT is used for triggers, so a (WORLD -> EVENT) spell can trigger things in a (EVENT -> WORLD) spell; what exactly it triggers depends on the spell.
05:15:42 <zzo38> Does this seem OK?
05:19:38 <oerjan> oklopol: um that lists individual programs, not matches.
05:21:43 <oerjan> in the report, they're listed by ID. and + seems to mean the row ID wins.
05:25:26 <Sgeo> I may have accidentally convinced my boss's boss to buy proprietary software
05:27:34 <kmc> you monster
05:27:53 <kmc> RMS will be so disappointed with you
05:29:40 <zzo38> Sgeo: You advised your boss's boss about software? What use of the software is it?
05:30:08 <Sgeo> It's Charles Web Proxy, he saw me using it and I mentioned that I liked it and he saw how convenient it made testing stuff
05:30:52 <Sgeo> Although, if there's no equiv. to FiddlerScript, that would really suck
05:32:45 <Sgeo> "By inspecting the web interface HTML you can derive how to use it as web services to automate Charles."
05:33:26 <Bike> automate that shite good
05:34:42 <Sgeo> ...its idea of a web interface doesn't include modifying any settings beyond enabled/disabled
05:34:45 <kmc> do you call them your metaboss
05:35:38 <oklopol> oerjan: sorry, i was on the bfjsout page, and wanted to copy it. it had that on the url row and it looked wrong so i refreshed. the url stayed the same so i figured it's correct.
05:35:47 <oklopol> not the first time this has happened
05:36:05 <fizzie> It's still called egojsout nyaaaar.
05:36:28 <fizzie> (Managed to keep quiet for the first dozen times.)
05:36:56 <oerjan> fizzie: probably why i didn't find it with google
05:41:25 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif).
05:43:21 -!- ^v has joined.
05:52:20 <Lymia> !bfjoust lets-try-this-evolver-again >>++>>(>[>([(+)*5[-]]>)*-1])*-1
05:52:23 <EgoBot> Score for Lymia_lets-try-this-evolver-again: 30.8
05:52:53 <Lymia> Reconfiguration time
05:52:58 <Lymia> !bfjoust lets-try-this-evolver-again <
05:53:00 <EgoBot> Score for Lymia_lets-try-this-evolver-again: 0.0
05:57:31 <zzo38> What other objects could this category of spells include? (It is a tensor category, so all of the products exist too)
06:00:40 -!- Oj742 has quit (Quit: irc2go).
06:03:50 <oklopol> oerjan: http://codu.org/eso/bfjoust/egojsout/index.php doesn't make it very clear which player is which, in the sense that you choose an upper player and a lower player and then it says right wins
06:04:47 -!- tromp_ has quit (Read error: Connection reset by peer).
06:05:13 -!- tromp_ has joined.
06:06:09 <oerjan> i have no more clue than you do
06:06:34 <oklopol> i mean i assume right is down and left is up, just wanted to point it out that really no actual clue is given which is which, anywhere on the page.
06:07:39 <kmc> CSS is adding support for vertical writing which means that we have to start saying "measure" and "extent" instead of "width" and "height"
06:09:25 <oklopol> LOL L LLL how about the japanese add mental support for only writing like us white people write
06:09:42 <Lymia> !bf meow ++++++++++++++++++++(-)*-1
06:09:51 <Lymia> !bfjoust meow ++++++++++++++++++++(-)*-1
06:09:56 <EgoBot> Score for Lymia_meow: 14.1
06:09:56 <kmc> isn't japanese mostly written horizontally anyway
06:10:15 <kmc> this stuff tho http://en.wikipedia.org/wiki/File:Guyuk_khan%27s_Stamp_1246.jpg
06:10:17 <oklopol> i just saw it written vertically 15 minutes ago
06:10:17 <Bike> i think it is, nowadays
06:10:18 <kmc> how can you not love that
06:10:22 <Bike> i mean, mostly
06:10:35 <oklopol> (that's when i last saw japanese text)
06:10:36 <Bike> mongolian owns though.
06:10:51 <kmc> i bet i will see some japanese text in japan
06:10:56 <kmc> will report back w/ findnigs
06:10:59 <Bike> let's just make mongolian the default for everything. it's been seven hundred years, we can give them a world empire again
06:11:05 <kmc> actually i already saw a lot of japanese text in the seoul airport and such
06:11:08 <zzo38> I see it vertically a lot in manga books, although some of it is written horizontally. In computer games though, it is mostly horizontal.
06:11:18 <Bike> oklopol are you drunk
06:11:38 <Lymia> !bfjout meow (--+)*-1
06:11:40 <Lymia> !bfjoust meow (--+)*-1
06:11:44 <EgoBot> Score for Lymia_meow: 16.3
06:11:46 <Lymia> My evolver likes vibrators way too much
06:11:49 <Bike> you can do it lymia i believe in you
06:11:56 <oklopol> i saw a lot of japanese text in taiwan, but most of it made no sense
06:12:27 <Bike> now i have to look up which scripts are still primarily written vertically.
06:12:44 <Bike> lol wikipedia has an entire article on text orientation in cjk
06:13:11 -!- sebbu has quit (Ping timeout: 260 seconds).
06:13:45 <zzo38> In this Windows I have "MS Gothic" font installed for Japanese writing; it also makes a font "@MS Gothic" available which turns most things sideways; I suppose this is for vertical writing in a program that is for horizontal writing.
06:13:50 <Bike> ok, wikipedia's 'vertically' in the mongolian script article links to the cjk one.
06:14:01 <Bike> "This developed because the Uyghurs rotated their Sogdian-derived script, originally written right to left, 90 degrees counterclockwise to emulate Chinese writing, but without changing the relative orientation of the letters"
06:14:05 <Bike> Language is awesome.
06:14:48 <zzo38> And it looks like vertical Japanese writing is still used a lot in manga and other things, although horizontal Japanese writing is also very common, it seems.
06:15:54 <Bike> the first major thing to write chinese horizontally was Science (I guess not the journal?)
06:15:57 <Bike> "This magazine is printed so that it goes sideways from the top left, and is marked with Western punctuation. This is to make the insertion of mathematical, physical and chemical formulae convenient, not for the sake of novelty-hunting. We ask our readers to excuse us."
06:15:59 <zzo38> In "Sushi Plus" restaurant in Victoria, BC, there are a few Japanese signs, which are written using vertical writing; the whiteboard (which is turned backwards for some reason) also has vertical Japanese writing on it.
06:16:01 <Bike> novelty-hunting
06:17:35 <zzo38> I have several issues of the (English) "Science" magazine; I got them for free from the doctor's office; they didn't want them anymore so they gave all of them to me.
06:21:40 -!- carado has joined.
06:33:28 -!- muskrat has joined.
06:36:37 -!- Taneb has joined.
06:39:50 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif).
06:56:29 <Lymia> !bfjoust meow .-(--+)*-1
06:56:34 <EgoBot> Score for Lymia_meow: 19.4
07:01:06 <Lymia> !bfjoust meow .+(--+)*-1
07:01:10 <EgoBot> Score for Lymia_meow: 18.2
07:01:12 <Lymia> !bfjoust meow .-(--+)*-1
07:01:17 <EgoBot> Score for Lymia_meow: 19.4
07:03:56 -!- muskrat has quit (Quit: Leaving).
07:05:08 <fizzie> -1 is automagically equal to the cycle count.
07:05:18 <fizzie> (If that wasn't mentioned already.)
07:05:34 <Bike> cycle count of what
07:05:44 <fizzie> The maximum cycle count, I should say.
07:06:42 <fizzie> kmc: What are you doing in Seoul anyway, some kinda Mozilla thing?
07:07:35 <kmc> a bunch of people from Samsung are working with us on this Servo project, and they invited us to spend the week working out of their office
07:08:35 <kmc> so I'll be doing that until Friday, then I'll do tourist stuff in Seoul until Monday night, when I fly to Osaka
07:08:46 <kmc> and then I'll do tourist stuff in Japan until Sunday!
07:09:15 -!- Sprocklem has quit (Ping timeout: 252 seconds).
07:09:16 <kmc> are there any #esotericers in .jp?
07:10:18 <zzo38> Not as far as I know, but there are some Japanese stuff related to esoteric programming.
07:10:56 <oerjan> kmc: there's one in korea though
07:11:04 <kmc> oh really, who?
07:11:06 <kmc> hi lifthras1ir
07:11:43 <shachaf> are there any #esotericers on the moon?
07:11:45 <fizzie> There was a lurker from .jp some months, one of those who again said nothing.
07:12:13 <oerjan> lifthras1ir doesn't say much these days :/
07:12:47 <zzo38> shachaf: I don't think so. (And I hope the IAC doesn't destroy the moon and replace it with a fake.)
07:13:05 <fizzie> Do they... have plans for that?
07:13:27 <oerjan> clearly they should replace it with a bust of alexander abian. it would only be fitting.
07:13:28 <zzo38> For destroying the moon? I don't think so; IAC is just a fictional organization in some of my works.
07:13:47 <shachaf> zzo38 has destroyed the IAC and replced it with a fake. :-(
07:14:01 <oerjan> twist: zzo38 is an scp
07:14:49 <oerjan> (he'd be safe if the foundation understood him)
07:15:18 <Bike> that's a tall order.
07:23:52 <oerjan> also as seen on #esoteric, http://www.scp-wiki.net/scp-1960-j
07:31:54 -!- FreeFull has quit.
08:04:30 -!- sebbu has joined.
08:05:08 -!- sebbu has quit (Changing host).
08:05:08 -!- sebbu has joined.
08:16:55 <Jafet> “Debris and sometimes even people can get swept up into a blast wave, causing more injuries such as penetrating wounds, impalement, broken bones, or even death.”
08:19:42 <kmc> injuries such as death
08:24:03 -!- Bike has quit (Ping timeout: 252 seconds).
08:25:04 <kmc> "Before GitHub existed, major companies created their knowledge mainly in private. But when you access their GitHub accounts, you're free to download, study, and build upon anything they add to the network"
08:25:08 <kmc> github invented open source
08:25:10 <kmc> you heard it here first
08:26:41 <Jafet> This is why we can't have private repositories
08:26:53 <olsner> indeed, this is the first time I've heard that
08:27:42 <fizzie> For some reason I don't seem to be able to clone Windows 8.1 sources from https://github.com/microsoft -- must be some kind of temporary glitch.
08:29:23 <kmc> bit surprised that https://github.com/microsoft doesn't exist
08:29:55 <zzo38> kmc: That is because they use CodePlex for their open source projects, isn't it?
08:32:37 -!- Bike has joined.
08:36:38 -!- tertu has quit (Ping timeout: 240 seconds).
08:39:47 <zzo38> As far as I know they probably do, when they have any.
08:42:08 <elliott> git is not really the most windows-friendly system
08:43:10 <zzo38> Although git does work on Cygwin (which isn't Microsoft).
08:43:27 <Jafet> That's because windows is not really the most git-friendly system.
08:43:41 -!- ais523 has joined.
08:45:53 <ais523> I woke up like 7 hours ago
08:46:01 <fizzie> I was about to say something to the tune of "hey, those line lengths match", but they would have to, wouldn't they?
08:46:06 <ais523> also, you being here has reminded me
08:46:18 <ais523> !bfjoust preparation http://nethack4.org/esolangs/preparation.bj
08:46:26 <ais523> let's see how much better this does
08:46:29 <EgoBot> Score for ais523_preparation: 42.6
08:46:32 <ais523> and whether the scoring system still hates it
08:47:02 <ais523> aha, it's now correctly shown as /way/ ahead of omnipotence on points
08:47:51 <ais523> I'm not convinced juiced is getting the same results as *lance is
08:48:02 <ais523> let me run the hill myself and see if there are discrepancies
08:48:23 <ais523> cycle limit is 100000, right? this code actually depends on the exact value of the cycle limit
08:48:44 <fizzie> I've "verified" *lance against egojsout, incidentally.
08:49:09 <fizzie> (The console edition of egojsout was my first node.js thing ever.)
08:49:15 <ais523> hmm… juiced says preparation beats brachiation
08:49:22 <ais523> egobot says brachiation wins
08:49:54 <ais523> let's see… breakdown says <>>><<<<<<<<<<>>>>>>> <>><><<<<<<<<<>>>>>>> 2
08:51:33 <fizzie> Hrm. egojsout says -8 and a win for preparation.
08:51:34 <ais523> juiced says <>>><<>>><>><<>>>>>>> <>><><<<<<<<<<>>>>>>>
08:51:54 <ais523> <>>><<<<<<<<<<>>>>>>> <>><><<<<<<<<<>>>>>>> 2
08:51:58 <ais523> <>>><<>>><>><<>>>>>>> <>><><<<<<<<<<>>>>>>> -8
08:52:08 <ais523> looks like juiced agrees with egojsout
08:52:45 <quintopia> preparation is seen to pretty much destroy on mid to long tapes
08:52:53 <ais523> preparation has some digits in comments
08:52:57 <ais523> perhaps they're confusing the parser
08:53:13 <fizzie> My local copy of cranklance agrees with egojsout and juiced.
08:53:23 <fizzie> Well, gearlance, but they're the same code.
08:54:12 <ais523> btw, what do you think of my BF Joust comment grammar
08:54:18 <ais523> I can't use many punctuation marks
08:54:24 <ais523> so I use semicolons for basically all punctuation, also some colons
08:54:29 <ais523> and slashes are used as parens
08:54:38 -!- Bike has quit (Ping timeout: 261 seconds).
08:55:14 -!- Bike has joined.
08:55:39 <ais523> oh, I think I found it
08:55:42 <ais523> whitespace between a * and a digit
08:56:00 <quintopia> what's it called when a markov can (or can't) split it into independent disconnected parts
08:56:01 <kmc> at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life
08:56:01 <quintopia> time to start using magicmake or whatever he calls it
08:56:01 <kmc> zzo38: there's also msysgit
08:56:01 <kmc> i think that's not cygwin based
08:56:01 -!- FireFly has quit (Ping timeout: 240 seconds).
08:56:01 -!- ski has quit (Ping timeout: 240 seconds).
08:56:03 -!- Effilry has joined.
08:57:08 <ais523> writing numbers out as words
08:57:24 -!- ski has joined.
08:58:55 <ais523> !bfjoust preparation http://nethack4.org/esolangs/preparation.bj
08:59:00 <EgoBot> Score for ais523_preparation: 47.1
08:59:22 <ais523> it now tops the hill on points, and is #3 on weighted rankings
08:59:25 <ais523> because it can't beat space_hotel
08:59:37 -!- Bike has quit (Ping timeout: 252 seconds).
08:59:38 <fizzie> ais523: Hmm. Whitespace shouldn't affect the *lance parser at all, for as long as I remember.
08:59:52 <ais523> fizzie: perhaps that's why gearlance agrees with juiced :)
09:00:15 -!- sebbu has quit (Ping timeout: 252 seconds).
09:00:21 <fizzie> Okay; since Mar 06, 2011, apparently.
09:00:42 <ais523> juiced appears to have a special case for ignoring whitespace after a % or a *
09:01:00 <ais523> interestingly, it parses "*10 0" as "*100"
09:01:27 <fizzie> That's actually what current *lance does, too.
09:01:37 <ais523> experts on hill scoring, would you say that I need crazy special cases against space_hotel to get it to top the hill?
09:01:37 <fizzie> (It ignores all whitespace completely.)
09:01:48 <ais523> or would you say I should try to improve its performance against the field at large?
09:02:00 -!- Taneb has quit (Quit: Leaving).
09:03:07 <fizzie> Before 2011-03-06 20:25:49, *lance would've parsed "* 10 0" as *0; from 20:25:49 to 23:15:21 it would have parsed as *10; ever since that, as *100.
09:03:20 <ais523> I actually think space_hotel is the most impressive program on the hill
09:03:36 <ais523> (waterfall3 is the most insane, but preparation has to be a close second)
09:03:41 <fizzie> (I added a special case for handling whitespace after */% first; then removed it and completely ignored all nonessential characters on a lower level instead.)
09:04:09 <ais523> juiced apparently has a compile-time option for whether it should conflate * and %
09:04:16 <ais523> and just look at {} to tell them apart
09:04:23 <ais523> I wrote this code ages ago, can hardly remember how it works
09:04:33 <ais523> it does produce pretty debug traces, though
09:05:04 <fizzie> *lanced doesn't distinguish between * and % either.
09:06:53 -!- Slereah has quit (Ping timeout: 272 seconds).
09:07:26 <fizzie> I wrote a couple of new entries in the lance family (torquelance, wrenchlance) the other day, but they're p. silly.
09:08:00 <oerjan> `addquote <kmc> at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life
09:08:08 <HackEgo> 1131) <kmc> at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life
09:08:25 -!- Effilry has changed nick to FireFly.
09:08:37 <ais523> anyway, I find preparation really hilarious
09:08:48 <ais523> it's amusing seeing it about to lose and then cycle 100000 hit
09:09:04 <fizzie> ais523: I think it's more efficient if I just point at the (reasonably short) descriptions at https://github.com/fis/chainlance/blob/master/README.md instead, maybe.
09:09:08 <ais523> in a previous version, there was some program/tape length combo where its flag was 0 when time ran out, IIRC, but that doens't happen any more
09:10:53 <ais523> btw, the difference between this version of preparation and the previous one is that it tries to establish the probabilistic lock a second time if it fails first time
09:11:04 <ais523> and it still knows where the enemy tape pointer is
09:11:23 <ais523> I realised that one of the defining properties of probabilistic locks is that they don't always work, so trying again can be worthwhile
09:12:14 <ais523> also, wow, I didn't realise quicklock was doing so well
09:12:17 <ais523> I need to read up on how it works
09:12:51 <ais523> aha, it's a combination of a poke and defend10's lock algorithm
09:12:55 <ais523> so very similar to omnipotence
09:13:19 <ais523> but the details seem different
09:13:31 <ais523> like, it attempts to synchronize with tripwires
09:13:39 <ais523> whereas omnipotence synchronizes via not setting decoys
09:13:59 <zzo38> One way to avoid nondistributive durations would be for castable spells to not be endomorphisms. Maybe there is a better way?
09:14:07 <fizzie> Somehow I feel like the length-to-score scatter plot -- http://zem.fi/egostats/plot_lenscore.png -- looks more "trendy" these days.
09:15:16 <fizzie> I wonder if I should do the Electron Band Structure In Germanium, My Ass thing in it.
09:15:30 <fizzie> ("Banking on my hopes that whoever grades this will just look at the pictures, I drew an exponential through my noise. I believe the apparent legitimacy is enhanced by the fact that I used a complicated computer program to make the fit. I understand this is the same process by which the top quark was discovered.")
09:15:59 <ais523> who's that a quote from?
09:16:33 <ais523> also, program length is mostly just an indication of attack versus defence, and whether or not it pokes
09:16:49 <ais523> although, defence programs keep doing quite high on the hill mostly because I try really hard to make that the case
09:16:57 <ais523> as part of my ongoing project into determining whether BF Joust is broken or not
09:17:03 <ais523> current conclusion: it isn't
09:17:14 <ais523> preparation beats death_to_defence
09:17:42 <fizzie> It's from http://pages.cs.wisc.edu/~kovar/hall.html which I think somehow got mildly famous.
09:18:33 <ais523> incidentally, on tape length 10, preparation always loses in exactly eighteen cycles
09:18:36 <ais523> unless the opponent suicides first
09:18:41 <fizzie> Other people argue on whether bitcoin is broken or not, not understanding where the *real* money is. (That's BF Joust.)
09:18:45 <ais523> sacrificing tape length 10 in a rush program proved to be a bad idea
09:19:07 <ais523> however, in a defence program, it's normally worth it because synchronizing defence programs have effectively no chance on tape length 10 anyway
09:19:34 -!- Bike has joined.
09:20:17 <ais523> hmm, the grouping thing groups preparation and space_hotel together
09:20:27 <ais523> even though the only thing they have in common is that they beat basically everything
09:20:37 <fizzie> There's two grouping things these days.
09:20:58 <fizzie> And the first one is based on duel scores, so it can be misled by that sort of thing, I guess.
09:21:33 <fizzie> The tape heatmap grouping doesn't really group preparation with anything in particular.
09:21:52 <ais523> btw, anyone who wants to know how preparation works, this graph is a giveaway: http://zem.fi/egostats/plot_tapeheat.png
09:21:59 <ais523> although fizzie might want to move the legend, it's in the way
09:22:16 <ais523> probably because nobody expected a program to do that
09:23:13 <fizzie> Yes, I remember selecting top-middle for the legend because there used to be always a valley in there.
09:23:18 <ais523> and yeah, I'm not surprised the heatmap can't link preparation with anything
09:23:38 <ais523> never before has a program spent the majority of the cycles on tape position 9
09:24:06 <ais523> preparation's issue is that it can't move very far before it has to go back to re-establish its lock
09:24:22 <ais523> so it wants to be in a central position on the tape so as to increase its range of movement
09:27:16 <ais523> actually, http://zem.fi/egostats/plot_p21_ptapemax.png is possibly an even bigger giveaway as to how preparation works
09:27:21 <ais523> also where the name comes from
09:27:32 <fizzie> I was supposed to have a Skype meeting in two minutes, but the only one of the participants I have on my contact list seems to have disappeared.
09:27:38 <ais523> and http://zem.fi/egostats/plot_p21_ptapeheat.png is quite revealing too
09:28:08 <ais523> it's especially worth noting the discontinuity between tape lengths 17 and 18
09:28:14 <ais523> where it changes strategy
09:28:41 <ais523> (I could write paragraphs just on the "how does it know whether the tape length is above or below 17.5 anyway?")
09:28:51 -!- carado has quit (Ping timeout: 252 seconds).
09:29:09 <ais523> fizzie: anyway, I have another interesting statistic, which I added to juiced recently for preparation testing
09:29:17 <ais523> number of cycles a program takes to win, compared to tape length
09:31:16 <fizzie> I have the weirdest feeling I was doing something that involved both tape lengths and duel lengths, but there indeed seems not to be anything like that on the page.
09:32:04 <zzo38> Are there any basic pokemons that *always* evolve when traded?
09:32:37 <zzo38> ais523: Ah, OK. Yes, I forgot.
09:33:07 <zzo38> But if there were any, would it be prohibited to tamper with the trainer ID numbers of such a pokemon in a tournament that allows tampering with the data?
09:33:10 <ais523> zzo38: even allowing for that, all the always-evolve-apart-from-everstone mons I know of are stage 1
09:33:23 <ais523> also you can cancel the evolution by pressing B
09:33:33 -!- oerjan has quit (Quit: leaving).
09:33:35 <zzo38> ais523: Yes, that is what I thought, too (both of them).
09:34:07 -!- Bike has quit (Ping timeout: 272 seconds).
09:34:08 <FireFly> I can't think of any evolves-on-trade-without-specific-item pokemon past generation 1, either
09:34:38 <FireFly> The ones from later generations all seem to require holding a specific item
09:35:59 <zzo38> But hypothetically assume that there are some which are basic, do not require any specific item, cannot use Everstone for some reason, and cannot be cancelled. Simply to see if you can even try to guess such an answer of a question.
09:37:22 <ais523> FireFly: that's mostly due to the (not 100% strictly followed) rule that any new evolutions should have been impossible in previous gens
09:37:35 <zzo38> (My brother said he didn't know.)
09:37:45 <ais523> zzo38: you can just reset one of the games until it has the same trainer ID as a different game
09:39:55 <zzo38> ais523: Sure you can, but I don't think that would affect it at all. That may allow you to tamper with the trainer ID number of a stage 1 form if both the basic and stage 1 are like what I said, though, I suppose???
09:40:06 <zzo38> But I said a basic form.
09:40:22 <ais523> the question's as to whether you could legally have that mon with an OT that doesn't match your own
09:40:39 <ais523> if it's not new to the generation, you could migrate it from a previous generation
09:40:42 <ais523> that doesn't cause evolution
09:41:04 <zzo38> Ah, you are correct. I didn't think of that.
09:41:08 <ais523> also you could use an official external box program (Pokémon Box / My Pokémon Ranch / Pokémon Bank), that doesn't cause evolution either
09:41:17 <ais523> and normally allows unboxing onto a different cartridge if you've beaten the Champion
09:41:27 <zzo38> I didn't know of that, but OK.
09:41:55 -!- carado has joined.
09:46:50 <zzo38> My brother also said that an exception to the rule about tampering with the data is the color of the pokeball is allowed to be changed to one that isn't obtainable under those circumstances since it has no effect on the game.
09:47:29 <ais523> zzo38: it used to have an effect, you could determine which moves a Pokémon might potentially have by whether it was in a Poké Ball or Cherish Ball (the two balls that give the most possibilities)
09:47:34 <ais523> although that was changed in X/Y
09:47:54 <zzo38> In which generations do they have an effect?
09:50:30 <ais523> zzo38: definitely 4 and 5, probably 3 as well
09:52:50 <zzo38> Perhaps he made a mistake then. (Although I suppose it would still have no effect during battle, unless opponent is allowed to see your pokeballs in which case it clearly does have an effect.)
09:53:33 <ais523> the opponent is allowed to see your Pokéballs
09:53:37 <ais523> they're visible as you send the Pokémon out
09:53:52 <zzo38> Yes, OK, then. He did clearly make a mistake.
09:54:46 <myname> somebody proofe turing completeness of pokemon!
09:55:19 <ais523> myname: it isn't, no infinite storage
09:56:29 <zzo38> Yes, that is immediately what I thought of too; no infinite storage. Both in the actual Pokemon game, and in the Pokemon card game which has various limits, some of which imply other limits, I think.
09:57:38 <zzo38> (If there is a card that prevent you from being knocked out when having too much damage, then you could potentially have unlimited amounts of damage, in the card game at least.)
09:57:43 <myname> just try what modifications you need to make it turing complete
09:57:58 <zzo38> What are they, then?
09:58:11 -!- Bike has joined.
10:01:16 <FireFly> myname: kinda relevant, http://aurellem.org/vba-clojure/html/total-control.html
10:02:02 <ais523> FireFly: that's old, but yeah, started something of a revolution
10:02:06 <FireFly> Though that's not pokemon being turing-complete, as much as a buffer-overflow into Z80 land, and Z80 being turing-complete
10:02:14 -!- Ghoul_ has quit (Ping timeout: 240 seconds).
10:02:24 <FireFly> Or not-quite-Z80-but-kinda-Z80 IIRC
10:02:30 -!- Bike has quit (Ping timeout: 245 seconds).
10:02:41 <FireFly> ais523: I know, but it seemed relevant to the question
10:02:43 <ais523> z80 isn't turing complete either
10:02:46 <ais523> and yeah, I guess it is
10:02:53 -!- Ghoul_ has joined.
10:03:26 <FireFly> Well, bah. Modulo space and addressing issues
10:11:33 -!- tromp__ has joined.
10:12:49 -!- tromp_ has quit (Remote host closed the connection).
10:14:41 <ais523> I guess you could somehow attach infinite storage through the link cable port?
10:15:45 <myname> i guess i should sell usb attached RAM to people
10:16:25 <ais523> myname: Windows 8 (possibly 7 too) has a feature that lets you use a USB stick as RAM
10:16:37 <ais523> which strikes me as a really bad idea, given that they aren't really designed for that
10:16:43 <ais523> but I guess people think "hey, cheap extra RAM"
10:16:51 <myname> i just buy 1 gb usb sticks and sell them for 4 times the price
10:55:47 <fizzie> I remember that there was some particular configuration of Linux-on-x86 where you had some regular RAM that wasn't usable normally, but you could get an MTD block device on it, and then use that as a fast swap device.
10:56:11 <fizzie> (Also you can put swap in GPU ram with MTD kludgery.)
10:57:44 -!- sebbu has joined.
10:57:57 -!- carado has quit (Ping timeout: 252 seconds).
10:58:21 -!- sebbu has quit (Changing host).
10:58:21 -!- sebbu has joined.
10:58:46 -!- carado has joined.
11:00:27 <Jafet> That actually sounds nice, except for the fact that your swap costs more than RAM.
11:03:55 <ais523> <Malcom McLean, on Lisp> I think there's no other language where the interpreter is easier to write than "hello world".
11:04:53 <fizzie> Jafet: Ah, but you can use it for swap during those times you're not using it for graphics.
11:04:58 <Jafet> We need a language where the self-interpreter happens to be "hello world"
11:05:03 <fizzie> (Sadly, I don't think there's a very good mechanism to switch.)
11:10:57 <ais523> hmm… in retrospect, it's not surprising that Birmingham University had bought a license to the Algol 60 specification
11:11:04 <ais523> I suspect that those things probably last forever
11:11:12 <ais523> and at one point, it would probably have been pretty important for them
11:18:46 -!- yorick has joined.
12:37:35 -!- Sgeo has quit (Read error: Connection reset by peer).
12:38:27 -!- zzo38 has quit (Remote host closed the connection).
13:07:46 -!- boily has joined.
13:08:14 -!- metasepia has joined.
13:28:29 -!- MindlessDrone has joined.
13:48:49 -!- shikhin__ has joined.
13:52:33 -!- Bike has joined.
13:52:55 <metasepia> KPDK 121253Z 00000KT 7SM CLR 05/04 A3016 RMK AO2 SLP220 T00500039
13:52:59 <metasepia> CYUL 121323Z 27018G23KT 15SM BKN040 M03/M10 A3012 RMK SC7 SLP200
13:58:25 <boily> I wonder if all Kxxx stations are assigned.
14:02:05 <boily> ~eval 26 * 26 * 26
14:08:13 -!- lifthras1ir has changed nick to lifthrasiir.
14:11:49 <boily> were you pinged by a random letter combination?
14:17:02 -!- heroux has quit (Ping timeout: 264 seconds).
14:18:48 -!- heroux has joined.
14:18:49 -!- hogeyui__ has changed nick to hogeyui.
14:20:10 <john_metcalf> Hi, is "Lip-Sie" the correct way to shorten "Lipiec-Sierpien" (Polish for July-August)
14:31:43 -!- shikhin__ has changed nick to shikhin.
14:34:15 <boily> hm. apparently monads were there even in Sweden a long time ago. they celebrated them in the calendar!
14:34:53 <boily> (Vintermånad → November)
14:51:50 -!- mrhmouse has joined.
14:53:09 -!- jix has quit (Read error: Connection reset by peer).
14:54:31 -!- jix has joined.
15:09:16 -!- conehead has joined.
15:12:12 -!- augur has quit (Remote host closed the connection).
15:12:38 -!- augur has joined.
15:13:02 -!- sebbu has quit (Ping timeout: 246 seconds).
15:13:39 -!- augur has quit (Read error: Connection reset by peer).
15:14:02 -!- augur has joined.
15:19:15 -!- nooodl has joined.
15:20:59 -!- tertu has joined.
15:31:26 <fizzie> "Winter month" is kind of uninspired. (Then again, our current word for June is "summer month", and September is "autumn month".)
15:32:20 <fizzie> (Okay, September is a bit more like "autumnal month", but still.)
15:32:41 <fizzie> ("Syyskuu", not "syksykuu".)
15:33:32 -!- ter2 has joined.
15:33:33 -!- tertu has quit (Read error: Connection reset by peer).
15:36:08 -!- shikhin has quit (Ping timeout: 246 seconds).
15:41:07 -!- Lymia has quit (Ping timeout: 260 seconds).
15:48:05 -!- ais523 has quit.
15:49:40 -!- Sprocklem has joined.
15:50:04 <boily> fizzie: and then you have the likes of google translate who go from fr:automne into fi:pudota.
15:52:12 -!- shikhin has joined.
15:54:57 -!- sebbu has joined.
15:55:35 -!- sebbu has quit (Changing host).
15:55:35 -!- sebbu has joined.
15:58:55 -!- shikhin has quit (Ping timeout: 272 seconds).
15:59:27 -!- conehead has quit (Ping timeout: 252 seconds).
16:03:59 -!- conehead has joined.
16:04:45 <fizzie> Ah. Wonder if it goes via en:fall or what.
16:05:10 <fizzie> (Sounds like a reasonable assumption.)
16:11:07 -!- shikhin has joined.
16:12:34 -!- FreeFull has joined.
16:16:17 -!- ter2 has quit (Ping timeout: 272 seconds).
16:16:36 -!- ter2 has joined.
16:18:03 -!- shikhin has quit (Read error: Operation timed out).
16:18:23 <boily> (meanwhile, djinns and gargoyles and ants! oh my!)
16:31:32 -!- shikhin has joined.
16:32:12 -!- Lymia has joined.
16:38:12 -!- shikhin has quit (Ping timeout: 246 seconds).
16:38:46 -!- Lymia has quit (Ping timeout: 244 seconds).
16:43:34 -!- Koen_ has joined.
16:47:28 -!- Slereah has joined.
16:52:54 -!- tertu3 has joined.
16:52:55 -!- ter2 has quit (Read error: Connection reset by peer).
17:03:17 -!- Sprocklem has quit (Ping timeout: 246 seconds).
17:06:01 -!- Lymia has joined.
17:17:15 -!- `^_^v has quit (Ping timeout: 260 seconds).
17:19:04 -!- Lymia has quit (Ping timeout: 264 seconds).
17:19:44 -!- AnotherTest has joined.
17:23:49 <fizzie> "*VERY IMPORTANT: The source files ( .tex, .doc, .eps, .ps, .bib, .db, .tif, .jpeg, ...) may be uploaded as a single .rar archived file. Please do not attempt to upload files with extensions .shs, .exe, .com, .vbs, .zip as they are restricted file types."
17:23:55 <fizzie> I'm sure this makes some kind of sense.
17:24:05 -!- Slereah_ has joined.
17:24:12 <Bike> why do people do that -_-
17:25:47 -!- Slereah has quit (Ping timeout: 244 seconds).
17:26:09 <fizzie> That was an IEEE paper submission system thingie, for context.
17:27:01 <fizzie> I guess .rar files are just safer than .zips? Somehow.
17:27:18 <quintopia> EVERYONE KNOWS THAT ITS IMPOSSIBLE TO PUT EXECUTABLES IN A RAR
17:27:47 <Bike> http://technet.microsoft.com/en-us/security/bulletin/ms04-034 oh no!
17:28:37 <fizzie> Guess it's true that there are more .zip holes in the world.
17:29:01 -!- dessos has joined.
17:29:07 <fizzie> On the other hand, .rar files smell of pirated software.
17:29:25 <fizzie> Perhaps they could settle on accepting .7z instead.
17:31:31 <Bike> they probably use a lot of windows
17:31:43 <Bike> why else even think about .com and .vbs
17:31:56 <Bike> or well, .exe.
17:32:28 <mrhmouse> yeah but, gzip is used everywhere. It's the most common form of compression for HTTP
17:33:00 <quintopia> pretty sure modern win systems can handle gzip natively yeah?
17:33:19 <mrhmouse> I don't use an Windows system (except at work), so I wouldn't have a clue
17:34:18 <fizzie> Preferrably with the .zip half done in the "store only" compression mode.
17:34:41 -!- `^_^v has joined.
17:34:55 <mrhmouse> my mother once asked me "if I keep zipping it, can I fit it on my floppy disk?", referring to her music collection
17:37:21 <fizzie> There was a Finnish company advertising their repeated compression that could perform miracles.
17:40:18 <fizzie> They were doing some completely unrelated software development work, and their in-house superstar programmer just happened to invent this impossibly good compression method as a by-product.
17:40:34 <fizzie> I never managed to figure out whether the firm's CEO was dishonest or just honestly deluded.
17:40:46 -!- Lymia has joined.
17:43:48 <fizzie> Nowadays he seems to be doing "Drupal, Concrete5, eZ publish, jQuery, underscore, PhoneGap etc." at some other company.
17:44:11 <quintopia> but it seems like compression is becoming something end users no longer have to worry about
17:45:14 <boily> back from lunch, and quintopia recites incantations.
17:45:17 <fizzie> Such a shame. (I have fond memories of DBLSPACEing a win3.1 system disk, leading to it no longer start up.)
17:52:42 * quintopia wraps a box to mail at Canada by fastplane.
17:57:00 <boily> “at”? “fastplane”? are you sure that you aren't mailing that by ICBM?
17:57:32 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
17:58:03 <boily> fungot: how does one protect oneself from incoming missiles?
17:58:03 <fungot> boily: do what's interesting to me. i'm so very, very nice. how do you mean that it's not even funny
17:58:23 <boily> fungot: ... you are disquieting.
17:58:24 <fungot> boily: if you don't need it for?
17:58:50 <boily> fungot: I need it for my corporeal integrity. I know I'm being selfish, but that's something I like to possess and affirm.
17:58:51 <fungot> boily: anna sun digikamera mulle synttrilahjaks? :p i like pianos. and the japanese page was created by me actually, we could
17:59:22 <boily> fungot: I'm a pianist, and I still need to learn more Japanese if you want me to edit your page.
17:59:22 <fungot> boily: the stack should be fast enough for me
17:59:43 <boily> fungot: I'm also a human, if you didn't notice yet. that means no fast stacks.
18:03:55 <FireFly> Maybe they're talking about their internal stack
18:04:03 <fungot> FireFly: or the labels will fnord decide to make a minion/ sarahbot loop, using a function?
18:10:10 <quintopia> http://fi4.eu.apcdn.com/full/110606.jpg
18:11:34 <Bike> http://www.adequacy.org/stories/2001.12.2.42056.2147.html is better. and doesn't treat autism unfortunately
18:15:38 <fizzie> fungot: Again with the spontaneous Finnish.
18:15:38 <fungot> fizzie: i'm asking for alternative fnord compilers. do you just not want to sit down with it.
18:16:18 <boily> I admit to having compiled kernels in my youth. I still get pangs and urges, but I now believe in the Way of the Precompiled Binary.
18:17:02 <quintopia> boily: careful. flashbacks can come on suddenly and unexpectedly.
18:17:40 <boily> quintopia: I know. I synced my ABS this morning. the feeling of bliss and détachement I got seeing all those nice packages I could compile...
18:17:56 <boily> what bad would result from me compiling just one little package, eh?
18:19:14 <int-e> Just don't uninstall libacl when coreutils are using it :) (that's about the worst I did, back when I was using Gentoo. I still compile the occasional kernel though, and a ton of Haskell stuff.)
18:19:50 <mrhmouse> I suppose I should have expected Arch/Gentoo users here
18:20:16 <int-e> arch has binary packages :)
18:20:17 <boily> I once rm -rfed pacman's cache. a very, very stupid move.
18:20:48 <boily> mrhmouse: have I asked you the The Question yet?
18:21:23 <int-e> 42 is the answer, I'm curious about the question now ;-)
18:21:45 <int-e> *goes back to preparing slides*
18:22:13 <boily> it's not the question, it's the The Question. very different.
18:22:22 <boily> mrhmouse: what are your approximate coördinates and body weigh?
18:22:29 <boily> int-e: what are you sliding?
18:22:44 -!- KingOfKarlsruhe has joined.
18:23:02 <int-e> A talk on something unpublished I'm doing with tree automata.
18:23:28 <boily> working in academia?
18:23:54 <mrhmouse> boily: I can't give you both at once
18:24:16 <int-e> yeah. <-- old and grumpy phd student
18:25:49 <olsner> boily: I forgot to set a timer, when is my food done?
18:25:57 <boily> mrhmouse: a guesstimate will do. I know about Heisenberg and Nyquist and other approximathematicians.
18:26:49 <quintopia> boily: USPS doesn't provide ICBM service anymore. no one could afford the $10,000,000 price for a small box
18:27:01 * boily gives a comfy sleeping bag (with fungot patterns) to int-e so that he can rest at his desk
18:27:01 <fungot> boily: the problem we were talking about the fnord
18:27:15 <Bike> boily didn't even ask for velocity...
18:27:15 <fizzie> There should be some kind of an #esoteric grumpy PhD student club.
18:27:28 <fizzie> Bike: Gotta be careful of that uncertainty principle.
18:27:35 <boily> olsner: what are you cooking/heating/simmering/[REDACTED]ing?
18:28:20 <boily> olsner: tabarn[EXPUNGED]. I was naïvely hoping that it wouldn't be so.
18:29:22 <olsner> I'll just give it two minutes before it gets eaten
18:29:59 -!- ^v has joined.
18:30:59 <quintopia> boily: i have an idea for an experiment
18:31:08 -!- Lymia has quit (Ping timeout: 246 seconds).
18:31:41 <quintopia> boily: i wonder if i can get a letter delivered to you without using the post, just relying on the kindness of strangers to move it closer to its destination
18:32:58 -!- dessos has quit (Quit: leaving).
18:33:25 <mrhmouse> quintopia: actually a band I just saw in concert is doing that with a flag
18:33:57 <mrhmouse> they're having fans and friends of fans move the flag from show to show by meeting in person
18:34:51 <quintopia> mrhmouse: that sounds a lot easier. people will go out of their way to do something for a band they like.
18:35:48 <boily> you could also walk up until my apartment. google says it'll only take 380 hours.
18:37:44 <fizzie> http://zem.fi/~fis/google-walk.png
18:38:09 <fizzie> "This route may be missing sidewalks or pedestrian paths."
18:39:13 <quintopia> a little over a month to walk to boily
18:40:15 <fizzie> It's a small world after all.
18:40:24 <metasepia> CYUL 121800Z 26015G26KT 15SM -SHSN OVC036 M01/M08 A3011 RMK SC8 SLP198
18:40:31 <quintopia> but unfortunately, i couldn't do it for at least a month
18:40:32 <boily> it's a cold world after all.
18:40:45 <boily> the -SHSN has begun!
18:40:46 <metasepia> EFHK 121820Z 20016KT 9999 -RA FEW006 BKN008 BKN011 07/06 Q1010 NOSIG
18:40:51 <quintopia> i'm sending out a passport renewal application with this box
18:40:54 <fizzie> Still not winter here.
18:41:07 <metasepia> ESSA 121820Z 23013KT 9999 BKN008 BKN010 08/06 Q1009 R88/29//95 BECMG BKN012
18:42:08 <quintopia> metasepia: would you mind parsing the metar line for us poor folk who don't know all the codes?
18:42:12 <boily> quintopia: did you just make that horrible pun?
18:42:40 <boily> the process is still very much manual. which one do you want to be decoded?
18:42:45 <metasepia> KPDK 121753Z 31020G26KT 9SM FEW041 14/05 A3018 RMK AO2 PK WND 31026/1752 SLP223 T01390050 10167 20028 50000
18:43:09 <quintopia> metasepia: you are aware you can incorporate new metar parsing code that has been ALREADY WRITTEN from github right?
18:44:10 <boily> >_>... <_<... ¬_¬'... v_v;...
18:44:19 <metasepia> KLZU 121745Z 28010G18KT 10SM CLR 17/01 A3012 RMK ATIS K; RWY 25 LL
18:45:17 <quintopia> Wind: True direction = 280 degrees, Speed: 10 knots, with Gusts of maximum speed 18 knots
18:46:15 -!- Bike has quit (Ping timeout: 245 seconds).
18:47:06 <quintopia> the units are all mixed up. why would you measure temperature in Celsius but pressure in inHg?
18:47:08 <boily> sure it's the QNH? I always figured Axxxx was the QFE.
18:47:25 <boily> quintopia: because it is so. the SLPxxx group is in hPa, too.
18:47:54 <quintopia> this decoder should have like a selector for units and do conversions
18:50:55 -!- ^v has quit (Remote host closed the connection).
18:53:02 -!- ^v has joined.
18:53:04 -!- Lymia has joined.
18:59:50 -!- nathnath has joined.
19:01:36 <HackEgo> nathnath: 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.)
19:03:00 -!- mroman has changed nick to mroman_.
19:22:54 -!- sebbu has quit (Read error: Connection reset by peer).
19:23:29 -!- sebbu has joined.
19:24:06 -!- sebbu has quit (Changing host).
19:24:06 -!- sebbu has joined.
19:27:13 -!- Slereah_ has quit (Ping timeout: 245 seconds).
19:27:52 -!- Slereah has joined.
19:35:58 -!- Oj742 has joined.
19:37:26 -!- Sprocklem has joined.
20:07:18 * boily mutters and swears and fevers and is not happy
20:07:22 <metasepia> Your divination: "Brightness Hiding" to "Pervading"
20:12:44 -!- Bike has joined.
20:12:51 * quintopia writes a postcard for boily to happy him
20:16:44 <boily> meanwhile, any Dutch and/or Flemish speakers here?
20:16:52 <boily> @tell Koen_ where have you disappeared?
20:17:07 <quintopia> i know where you can find some of those
20:17:48 <quintopia> on this network, i'm pretty sure l-b is dutch and The_Cat is belgian so..
20:21:14 -!- Taneb has joined.
20:22:29 <fizzie> Semantics. I told Scribblenauts to make a "great drummer", and it made a ridiculously big one.
20:22:29 <boily> nooodl: iirc, you are of a belgianic persuasion?
20:22:35 <nooodl> i'm a belgian dutch-speaker! i hear there is great request for us
20:23:31 <boily> nooodl: uhm... well, you see... there's that frivolous comment on reddit, and I was wondering if that guy was saying the Truth or he was «en train de nous péter de la broue».
20:23:34 <boily> http://www.reddit.com/r/linguistics/comments/1qgwc7/to_all_who_havent_yet_read_mark_twains/
20:24:24 <ion> fizzie: :-)
20:24:42 <Taneb> Today I helped make a tower out of spaghetti and jelly babies
20:24:58 <ion> fizzie: I have noticed you can solve amazingly many problems with an infant. Someone’s hungry? Feed him an infant. Etc.
20:25:08 -!- Lymia has quit (Ping timeout: 245 seconds).
20:25:15 <nooodl> boily: hottentottententententoonstelling is quite famous as a jokey long word, around here!
20:25:41 <boily> Taneb: the jellies were the for the spaghetti to be stuck into, right?
20:26:18 <nooodl> i'd heard Rabarberbararabierenbarbarenbaardenbarbier and that one is relatively easy for me to read
20:26:31 <nooodl> "Hermafrodietestestestestestafette" requires some imagination...
20:26:33 <boily> engineering for the win!
20:26:48 <Taneb> 102cm in 10 minutes
20:28:06 <nooodl> i think the last two are spelled wrong
20:28:25 * FireFly doesn't even know how to begin to lex that
20:28:52 <nooodl> should be verververververfverversing i think?
20:29:08 <nooodl> wait i'm missing a "ver-"
20:29:21 * boily is terrified by nooodl.
20:30:42 <nooodl> lemme break this down. "verven" is "to paint". one who paints is a "verver". one who paints far ("ver") is a "ververver".
20:31:10 <myname> which language is this?
20:31:16 <nooodl> "vers" means "fresh." a refreshment is a "verversing". hi this is dutch
20:31:37 <fizzie> ion: Yes, it seems to be rather... flexible. There was an orphan needing something to calm down, and feeding her sedatives worked like a charm.
20:31:40 <myname> nooodl: you meant rhabarberbarbarabarbarbarenbartbarbierbierbar?
20:32:20 <nooodl> a "paint refreshment" (verf + verversing) would be a "verfverversing", not a "*ververversing", which i think is where the poster messed up?
20:33:23 <boily> fizzie: I hope you're talking about Dwarf Fortress or something similar?
20:34:35 <nooodl> i don't know where "wrong" comes from but i think it's a loose translation of what the "ver-" prefix means for some verbs
20:35:24 <nooodl> such as "vergissen", to be mistaken, from "ver-" (wrong) + "gissen" (guess)
20:38:20 -!- lambdabot has quit (Quit: enable TupleSections).
20:39:50 <boily> see, you once again killed lambdabot.
20:40:31 <int-e> it'll be back in a moment
20:40:41 <int-e> it just takes ages to rejoin all the channels it's on
20:40:52 <int-e> and in any case, *I* killed it :)
20:41:13 <boily> how? are you Gregor?
20:41:35 <Gregor> Why do people think I have any connection to lambdabot >_<
20:41:37 <int-e> And who's Gregor ;-)
20:42:03 <Gregor> `echo Functional languages are for losers lul pwn
20:42:04 <HackEgo> Functional languages are for losers lul pwn
20:42:16 <quintopia> Gregor: you are renouned for your secret and undetectable DDOS attacks
20:42:35 -!- lambdabot has joined.
20:44:33 <boily> int-e: Gregor is kinda like elliott. they have authority over the chännel. hth.
20:44:46 -!- Sprocklem has quit (Ping timeout: 240 seconds).
20:44:55 <Gregor> I don't have any authority over the channel either *_*
20:45:27 <int-e> boily: I hoped that the smiley would help to avoid such comments.
20:45:37 <quintopia> so you better not give him any respect
20:47:02 <boily> int-e: I'm enrhumé. comments and smileys may not be understood.
20:47:40 <fizzie> ion: Yeah, I just gave a cannibal an infant to eat.
20:48:16 <boily> quintopia: with a cold.
20:51:26 <fizzie> ion: Also I put a bug into a pizza. "That pizza looks delicious!"
20:51:46 <mrhmouse> fizzie: Now I want to play this game
20:52:25 <fizzie> mrhmouse: It's in the latest Humble Bundle, if you're interested.
20:52:52 <ion> http://youtu.be/GX0F3AHU264
20:53:10 <ion> Scribblenauts: Place someone who knows how to cook in the kitchen!
20:53:38 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:53:45 <fizzie> ion: I also just made a phoenix out of fire, a chicken, and a phoenix.
20:53:53 <fizzie> The last is a good source for magical power!
20:54:07 <Taneb> ion, does it work with "man"?
20:54:25 <ion> taneb: Yes, but let’s not mention it, that makes it less funny.
20:55:32 <Taneb> Does it work with "chocolatier"?
20:55:39 <Taneb> Or however you spell that
20:56:42 <ion> Scribblenauts apparently knows the word, so it should work. http://scribblenauts.wikia.com/wiki/Chocolatier
20:59:09 * boily sings «Un chocolat, deux chocolats, trois chocolats, quatre chocolats ♪»
21:05:11 -!- Oj742 has quit (Quit: irc2go).
21:08:31 <mrhmouse> fizzie: does the latest HB include Linux games? I can't look at it while at work
21:08:41 -!- Lymia has joined.
21:08:41 -!- Lymia has quit (Changing host).
21:08:41 -!- Lymia has joined.
21:09:24 <fizzie> mrhmouse: Sadly, no. It's one of these "not-so-indie" bundles.
21:10:39 -!- Slereah has quit (Read error: Connection reset by peer).
21:10:53 -!- Slereah has joined.
21:10:54 <fizzie> mrhmouse: (It's a WB Games bundle, containing Scribblenauts Unlimited, the two Batman: Arkham Whatever games, and two of something called F.E.A.R., as well as the LOTR: War in the North game.)
21:11:34 <fizzie> (Oh, and Scribblenauts is on the "pay more than the average" side too.)
21:12:04 <ion> Scribblenauts works perfectly in Wine.
21:12:19 <ion> Unfortunately, the Batman games apparently don’t, so i didn’t buy the bundle.
21:12:24 -!- impomatic has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]).
21:12:24 <ion> I already have Scribblenauts.
21:12:42 <Taneb> I have the first scribblenauts game, not any of the sequels though
21:13:06 <fizzie> I mostly bought it for Scribbels. I don't have any aspirations of Batmanity.
21:13:41 <Taneb> Guns of Icarus Online and Dwarf Fortress are my games atm
21:13:55 <ion> I was disappointed with the description of the newest Scribblenauts game. It’s a battle game now.
21:14:26 <ion> Haven’t tried it, though. Perhaps it doesn’t suck.
21:18:14 -!- zzo38 has joined.
21:19:00 <kmc> <fizzie> ion: Yeah, I just gave a cannibal an infant to eat. <--- scribblenauts against humanity?
21:22:57 <mrhmouse> Disappointing.. I don't use Wine. Oh well, I'm not bored with Kerbal Space Program just yet.
21:23:18 -!- carado has quit (Ping timeout: 252 seconds).
21:24:08 -!- nisstyre has joined.
21:24:27 -!- AnotherTest has quit (Ping timeout: 240 seconds).
21:26:32 -!- shikhin has joined.
21:26:59 -!- Slereah has quit (Ping timeout: 272 seconds).
21:27:37 -!- Slereah has joined.
21:28:14 -!- boily has quit (Quit: the return of the bride of the children of the mutant chicken II: electric boogaloo).
21:28:25 -!- metasepia has quit (Remote host closed the connection).
21:32:03 -!- Bike has quit (Ping timeout: 272 seconds).
21:36:40 -!- sebbu has quit (Ping timeout: 245 seconds).
21:39:14 <ion> Sigh, shachaf. Sachaf.
21:41:49 -!- Sprocklem has joined.
21:53:13 -!- Bike has joined.
22:01:02 -!- Bike has quit (Quit: Reconnecting).
22:01:15 -!- Bike has joined.
22:11:00 <Taneb> I really want to hear an Around The World/Around The World Red Hot Chilli Peppers/Daft Punk mashup
22:12:34 <Taneb> (the Daft Punk song has the better lyrics)
22:13:48 <Bike> daft punk has lyrics?
22:14:24 <Bike> ok i looked it up on a lyrics site and it rules
22:15:15 -!- Lymia has quit (Ping timeout: 246 seconds).
22:16:01 -!- Sprocklem has quit (Ping timeout: 252 seconds).
22:16:05 -!- Lymia has joined.
22:16:18 -!- Lymia has quit (Changing host).
22:16:18 -!- Lymia has joined.
22:18:01 <zzo38> Have you written any just intonation chiptune music? It seems suitable for such thing.
22:19:45 <Bike> matlab profiler claims 54.862 of the 55.404 second runtime was spent in "java.util.concurren.LinkedBlockingQueue". mildly skeptical here
22:19:48 <zzo38> (I have done so in Famicom Hangman, and instead of using A=440Hz, adjusted the tuning so that the notes would have the exact pitch I wanted and don't have to be detuned.)
22:23:57 <kmc> java and matlab: two great tastes that taste great together
22:24:02 <kmc> also how does that even work
22:24:09 <kmc> shachaf: how goes
22:24:11 <Taneb> Okay, that's a mondegreen that completely changes the meaning of the song
22:24:24 <Bike> iunno. you can call out to java and stuff.
22:24:41 <Bike> all this means is that the profiler has no goddamn clue what to do with parallel code, which is unsurprising
22:24:54 <Taneb> Touch by Daft Punk, "If love is the answer you're home." => "If love is the answer you're wrong."
22:27:01 -!- nisstyre has quit (Ping timeout: 252 seconds).
22:27:26 <Taneb> Turns it from slightly regretful to really really bitter
22:27:43 <Bike> wow, one run calls this not-built-in function one and a half million times
22:27:53 <Bike> profiling is fun.
22:28:38 -!- tertu3 has quit (Ping timeout: 240 seconds).
22:31:42 <Bike> this thing is so fancy, it highlights lines hat took up more time in a deeper shade of red
22:40:43 -!- nisstyre has joined.
22:40:51 <ion> I prefer filers
22:44:18 <shachaf> ion: you should teach Taneb about categories
22:44:58 <ion> Categories are like chili con carne
22:45:22 <ion> Semigroupoids are like the vegetarian version
22:45:54 <Taneb> Doesn't con carne mean "with meat"
22:46:10 <Taneb> So, vegetarian chili con carne is... just chili
22:46:20 <Taneb> Possibly chili con quorn
22:46:31 <shachaf> Taneb: so of course you can also think of that category as one where the objects are R^n and the arrows are linear functions
22:46:57 <shachaf> Taneb: "chili sin carne", ı think.
22:47:13 <ion> con textured soy protein or something
22:47:52 <Taneb> shachaf, I don't think you can, in the case of non-square matrices
22:48:22 -!- tertu3 has joined.
22:49:24 <zzo38> There is Penrose tensor diagrams, which can be applicable to matrices, although I think they can be applicable to tensor categories too (which features of the diagram are available depends on what features the category has)
22:49:52 <nooodl> shachaf: you dropped one of these --> .
22:50:12 <Taneb> (I noticed that matrix multiplication formed a category when one of my lecturers demonstrated that set relations can be defined in terms of them)
22:50:28 <shachaf> Taneb: A linear function : R^n -> R^m.
22:50:56 <Taneb> shachaf, maybe I'm just insufficiently familiar with linear functions
22:51:38 <zzo38> I also notice that matrix multiplication forms a category, but not for that reason.
22:52:39 <shachaf> Taneb: A linear function between two vector spaces is a function f such that f(x + y) = f(x) + f(y); f(rx) = r*f(x)
22:52:47 <shachaf> Where x and y are vectors and r is a scalar.
22:53:35 <shachaf> You can generally represent them as matrices.
22:54:31 <zzo38> I noticed because of Penrose diagrammatic tensor notation. Do you know about Penrose diagrammatic tensor notation?
22:54:59 <zzo38> (There is a Wikipedia article, in case you do not know.)
22:55:14 <shachaf> It looks like string diagrams.
22:56:58 <Taneb> I think when the entries of the matrices are in the two-element boolean algebra this category is identical to Rel
22:57:03 -!- augur has quit (Remote host closed the connection).
22:57:51 <Taneb> Like, matrix multiplication is defined when the things in the matrix are a semiring
22:58:29 <zzo38> Taneb: Yes I noticed that it is when they are a semiring. (I did not notice if it is identical to Rel, though)
22:58:43 -!- ter2 has joined.
22:58:57 <Taneb> {F, T}, + = ∨, * = ∧ 0 = F, 1 = T forms a semiring
22:59:25 <zzo38> OK, yes I know that too.
22:59:28 -!- tertu3 has quit (Read error: Connection reset by peer).
22:59:58 <kmc> the scalar of a vector space has to be a field
23:00:34 <kmc> but if you want it to be only a ring then you can talk about modules instead of vector spaces
23:00:50 <shachaf> well you can just yes that
23:01:11 <Taneb> What about when you're talking about the module over a ring D of differential operators
23:01:12 <shachaf> did you know a Z-module is the same thing as an abelian group
23:01:20 <kmc> i'm reading that now
23:01:28 <kmc> but I have to eat breakfast instead of understanding it
23:01:30 <shachaf> someone told me that one week ago
23:01:39 <shachaf> Taneb: whoa, dude, that's some serious inventioning going on right here
23:01:42 <kmc> maybe i will have chile con carne
23:01:43 <HackEgo> D-modules are just modules over the ring of differential operators. Taneb invented them.
23:02:14 <shachaf> kmc: chile is p. far from korea
23:02:47 <kmc> the antipode of Formosa, Republic of China is Formosa, Argentina
23:03:03 <Bike> Is Penrose notation as annoying as Einstein's
23:03:14 <shachaf> are antipodes related to octopodes
23:03:15 <zzo38> What is Einstein's?
23:03:33 <Taneb> Anyway, when the matrix is filled with these {F, T} (rather than ℝ), I think this category is equivalent to Rel
23:03:41 <Bike> zzo38: einstein summation notation i mean
23:04:06 <zzo38> Bike: I am not aware of such notation.
23:04:50 <Bike> there is a wikipedia article
23:05:02 <shachaf> Bike: that's the notation where you just don't write the sigma, right
23:05:09 <shachaf> and you just gotta know it's there
23:05:47 <shachaf> might as well drop the expression too
23:05:58 <Bike> "look fuck you, i'm Einstein"
23:07:56 -!- oerjan has joined.
23:10:47 -!- mrhmouse has quit (Quit: Leaving.).
23:16:51 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]).
23:16:53 -!- Ghoul_ has quit.
23:22:53 -!- Lymia has quit (Ping timeout: 272 seconds).
23:33:01 -!- ter2 has quit (Ping timeout: 272 seconds).
23:34:36 -!- sebbu has joined.
23:35:13 -!- sebbu has quit (Changing host).
23:35:13 -!- sebbu has joined.
23:48:24 <Bike> matlab's help cites "Nineteen Dubious Ways to Compute the Exponential of a Matrix"
23:49:32 -!- Phantom_Hoover has joined.