> 1780881169 884999 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183262&oldid=182548 5* 03Miui 5* (+24796) 10Removed redirect to [[Main Page]]
> 1780881611 573885 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183263&oldid=183262 5* 03Miui 5* (+4054) 10
> 1780881652 706890 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183264&oldid=183263 5* 03Miui 5* (-4054) 10Undo revision [[Special:Diff/183263|183263]] by [[Special:Contributions/Miui|Miui]] ([[User talk:Miui|talk]])
> 1780881803 500168 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183265&oldid=183264 5* 03Miui 5* (+7269) 10
< 1780883125 590740 :chloetax!~chloe@user/chloetax QUIT :Quit: Leaving
< 1780883310 210582 :chloetax!~chloe@user/chloetax JOIN #esolangs chloetax :chloe
< 1780893137 235660 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780893152 21064 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780894097 5011 :ais523!~ais523@user/ais523 QUIT :Quit: quit
< 1780897296 95747 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780897570 519151 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780898138 814499 :sprock!~sprock@user/sprock QUIT :Ping timeout: 265 seconds
> 1780899083 496446 PRIVMSG #esolangs :14[[07Pull14]]4 N10 02https://esolangs.org/w/index.php?oldid=183266 5* 03ASCIIguy 5* (+3140) 10Created page with "{{WIP}}  '''Pull''' is a timeline/stack-based imperative golf language based on Git and the 5D time-travel languages. It uses the idea of branching out to create several states in one program. For example, one could move timelines upwards where x becomes 4 when it was 3 i
< 1780899994 798500 :Sgeo!~Sgeo@user/sgeo QUIT :Read error: Connection reset by peer
> 1780900937 29425 PRIVMSG #esolangs :14[[07Condition14]]4 N10 02https://esolangs.org/w/index.php?oldid=183267 5* 03ASCIIguy 5* (+1793) 10Created page with "'''Condition''' is an [[If a==1:]] derivative with added features, created as it was viewed as too restrictive and that things such as I/O would be useful for the language. ==Syntax== Like the original language, all instructions are on a singular line. Unlike the ori
< 1780903127 611271 :APic!apic@chiptune.apic.name QUIT :Ping timeout: 244 seconds
< 1780904144 963509 :APic!apic@chiptune.apic.name JOIN #esolangs APic :A. Pic. - my name since YOLD 3149
< 1780914302 575925 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780914592 514035 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780918044 134886 :Lord_of_Life!~Lord@user/lord-of-life/x-2819915 QUIT :Ping timeout: 253 seconds
< 1780918118 733569 :Lord_of_Life!~Lord@user/lord-of-life/x-2819915 JOIN #esolangs Lord_of_Life :Lord
< 1780920639 210112 :APic!apic@chiptune.apic.name PRIVMSG #esolangs :Hi
> 1780923249 738102 PRIVMSG #esolangs :14[[07NAND14]]4 10 02https://esolangs.org/w/index.php?diff=183268&oldid=183152 5* 03 5* (+15) 10Some things clarified.
< 1780923281 819609 :ais523!~ais523@user/ais523 JOIN #esolangs ais523 :(this is obviously not my real name)
< 1780925627 159513 :amby!~ambylastn@79-77-118-44.dynamic.dsl.as9105.com JOIN #esolangs * :realname
< 1780925926 615734 :impomatic!~impomatic@lock-04-b2-v4wan-171175-cust377.vm10.cable.virginm.net JOIN #esolangs * :[https://web.libera.chat] impomatic
> 1780927167 851474 PRIVMSG #esolangs :14[[07Minez14]]4 N10 02https://esolangs.org/w/index.php?oldid=183269 5* 03Dooblix 5* (+17864) 10Minez is an esoteric programming language created by Dooblix in 2024 (current version: 2025), inspired by Urban Mller's minimalistic esoteric programming language "Brainfuck".
< 1780928651 223542 :ais523!~ais523@user/ais523 QUIT :Quit: quit
< 1780928917 933409 :ais523!~ais523@user/ais523 JOIN #esolangs ais523 :(this is obviously not my real name)
< 1780931015 470560 :svm!~msv@user/msv NICK :msv
> 1780931474 71596 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183270&oldid=183269 5* 03Aadenboy 5* (+67) 10cats, also marking repo links as dead (from the user's contributions it seems to just be private). I'm suspicious this article was generated by AI, but I can't definitively say for sure
> 1780931491 598245 PRIVMSG #esolangs :14[[07Minez14]]4 M10 02https://esolangs.org/w/index.php?diff=183271&oldid=183270 5* 03Aadenboy 5* (+13) 10dead link 3
> 1780931508 961641 PRIVMSG #esolangs :14[[07Minez14]]4 M10 02https://esolangs.org/w/index.php?diff=183272&oldid=183271 5* 03Aadenboy 5* (-3) 10
> 1780932016 901845 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183273&oldid=183265 5* 03Miui 5* (-31977) 10Replaced content with "=personal references= #:https://raw.githubusercontent.com/iannmiui-png/Oragami-Crystal/refs/heads/main/states.m"
> 1780932785 786251 PRIVMSG #esolangs :14[[07User:Blashyrkh/The Church14]]4 10 02https://esolangs.org/w/index.php?diff=183274&oldid=183252 5* 03Blashyrkh 5* (-1) 10Shorter expression for "6"
> 1780934097 913922 PRIVMSG #esolangs :14[[07Esolang:Introduce yourself14]]4 10 02https://esolangs.org/w/index.php?diff=183275&oldid=183258 5* 03Dumgeonlol 5* (+167) 10
> 1780934100 352700 PRIVMSG #esolangs :14[[07NAND14]]4 10 02https://esolangs.org/w/index.php?diff=183276&oldid=183268 5* 03 5* (+765) 10Language simplified, article expanded.
> 1780934202 14810 PRIVMSG #esolangs :14[[07Hello++++++++++++++++++++++++++++++++++++14]]4 N10 02https://esolangs.org/w/index.php?oldid=183277 5* 03Dumgeonlol 5* (+128) 10Created page with "Hello++++++++++++++++++++++++++++++++++++ or Hello36 is a Joke Language made by [[User:Dumgeonlol]]  [[Category:Joke languages]]"
> 1780934253 420593 PRIVMSG #esolangs :14[[07User:Dumgeonlol14]]4 N10 02https://esolangs.org/w/index.php?oldid=183278 5* 03Dumgeonlol 5* (+51) 10Created page with "HI, I'm me, dumgeonlol. I think esolangs are funny."
> 1780935342 809622 PRIVMSG #esolangs :14[[07Hello++++++++++++++++++++++++++++++++++++14]]4 10 02https://esolangs.org/w/index.php?diff=183279&oldid=183277 5* 03Dumgeonlol 5* (+5485) 10
> 1780937080 705381 PRIVMSG #esolangs :14[[07Hello++++++++++++++++++++++++++++++++++++14]]4 10 02https://esolangs.org/w/index.php?diff=183280&oldid=183279 5* 03Dumgeonlol 5* (+314) 10
> 1780939271 617128 PRIVMSG #esolangs :14[[07Hello++++++++++++++++++++++++++++++++++++14]]4 10 02https://esolangs.org/w/index.php?diff=183281&oldid=183280 5* 03Aadenboy 5* (-160) 10
> 1780939372 833206 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183282&oldid=183272 5* 03Corbin 5* (+29) 10Article and code show signs of being generated by ChatGPT.
< 1780939501 304560 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :korvo: I am impressed when people can tell which specific LLM was used to generate something (even though I can usually tell when something is LLM-generated)
< 1780939517 930844 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :do you use word choice, or some clue like that?
< 1780939566 281407 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :ais523: In this case, I went to their GH and read through their commit messages; there's only a few dozen of them. I found one which removes a ChatGPT phrase from the README. This is also how I know that the user prefers German.
< 1780939622 610497 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :It is also bad writing, yes. To detect that, I had to pay attention across several semesters of English writing courses. I will readily admit that, unlike *everybody else* in my class, I am able to read books and glean themes from them; perhaps I'm a good reader.
< 1780939721 103385 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :hmm, I'm not sure you necessarily need formal training to know whether something is bad writing (but may need it to know *why* it's bad writing, to be able to fix it)
< 1780939730 989369 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :the easiest way to tell that something is badly written is to note that it is difficult to read
< 1780939784 353678 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Sure. The entire question of "Good" and "Bad" is tough. The best attempt I know of is Pirsig ("Zen and the Art of Motorcycle Maintenance"), which explains that "good" is "what you like". From that perspective, there's plenty of folks who like what I think is bad writing; writing might be bad to me but good to them.
< 1780940161 652285 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :detecting LLM output is interesting because there are reliable tells that would be easy to change but rarely aren't (e.g. using emdashes incorrectly, or producing bulleted lists where each list item has its own heading, and that would not make sense as a definition list)
< 1780940180 245220 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :but there are also much more fundamental tells that would be hard to change, e.g. the information density of the text being extremely low
< 1780940670 222276 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Yeah. In general, language models are bad writers and good readers. I haven't really written this up in a way that I can slap people with; the places I normally post are filled with folks who cannot emotionally tolerate at least one of those branches.
< 1780940700 526504 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Like, language models are best when they are analyzing human-written text. The biggest win in language modeling of the past century was establishing that the Bible has multiple authors, for example.
< 1780940770 839217 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :But when emitting text, like you say, the information content is limited. Literally, the chatbot can only emit words which are germane to the prompt context, and the prompt has finitely many bits.
< 1780940795 133252 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :~ I think it's Tolkien who wrote "I feel like too few bits scraped across too many paragraphs" ~
< 1780940935 450987 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780941003 594497 :sprock!~sprock@user/sprock JOIN #esolangs sprock :maeve (she/her)
> 1780941104 421660 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183283&oldid=183282 5* 03Aadenboy 5* (-36) 10
< 1780941214 524216 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
> 1780941289 82946 PRIVMSG #esolangs :14[[07Oragami14]]4 10 02https://esolangs.org/w/index.php?diff=183284&oldid=182634 5* 03Miui 5* (+29) 10/* Computational Class */
> 1780941378 686182 PRIVMSG #esolangs :14[[07Oragami14]]4 10 02https://esolangs.org/w/index.php?diff=183285&oldid=183284 5* 03Miui 5* (+41) 10/* Computational Class */
> 1780941490 17168 PRIVMSG #esolangs :14[[07User:Miui/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183286&oldid=183273 5* 03Miui 5* (-111) 10Blanked the page
< 1780941667 917728 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net JOIN #esolangs * :Melvin Sommer
< 1780941731 368495 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Hey guys, is this generally where the esolang community congregates?
< 1780941848 957497 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :I think it's historically been the case, but I'm not sure how much it is anymore
< 1780941893 824051 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :but there's at least occasional esolang topics/chatter, and I'm sure more would be welcome
< 1780941902 104249 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :That seems loaded.
< 1780941953 831411 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :idk, wasn't my intention, mostly that it's less-traffic than it used to be
< 1780941971 114032 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Oh okay
< 1780941972 318606 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :from my POV anyway :p
< 1780942104 657529 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Well I'm a new user. I just signed on to the community mostly to forward my AI construct's work. I noticed some predictable scrutiny about AI-generated work. So I thought I'd get more in touch and see where everyone is at on this topic.
< 1780942182 32130 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :the community is split between IRC and Discord nowadays
< 1780942186 884262 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I notice there's an "AI-Generated" label for article, is this like a safe zone for this kind of content?
< 1780942188 584556 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :possibly multiple Discords
< 1780942212 11744 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :we generally look down on AI-generated articles because the purpose of the wiki is to document esoteric programming languages, and AI-generated descriptions of them are usually inaccurate
< 1780942224 34449 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :(even when the language is also AI-generated)
< 1780942225 569668 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :It's not a description, it's the esolang.
< 1780942317 656892 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :the wiki exists to describe esolangs – it is not itself an esolang
< 1780942355 134895 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I thought there might be reservations about AI generated esolangs?
< 1780942360 612690 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :likewise, wiki pages are not themselves esolangs
< 1780942374 662078 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :the thing about an AI generated esolang is that you need to make sure a language actually exists
< 1780942380 15942 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :i.e. something you could program in
< 1780942390 704467 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :if an AI is just generating language descriptions that usually isn't actually the case
< 1780942400 785176 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :if it has generated an interpreter, then you can document the language defined by the interpreter
< 1780942415 783931 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Have you guys had an issue with articles with no actual esolang behind it being drafted?
< 1780942419 648819 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :yes
< 1780942423 543479 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Weird.
< 1780942424 94064 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :it is a very large issue at the moment
< 1780942431 555582 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :What's driving that?
< 1780942441 293759 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :sadly it is not just AI
< 1780942450 911720 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :I think people read esolang specs, get amused, think "I like this form of writing"
< 1780942462 784411 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :and write their own things that look like esolang specs but don't actually describe a language
< 1780942475 722262 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :anyway, I need to disconnect for a bit, busy in real life
< 1780942478 15297 :ais523!~ais523@user/ais523 QUIT :Quit: quit
< 1780942481 794450 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Alright man.
< 1780942595 445523 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: Machine learning generates *plausible* text. It does not necessarily generate *good* text. If we allowed plausible text then we would drown; it's been known since the 1980s that it's computationally cheap to generate such text and expensive to detect/remove it.
< 1780942638 73749 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Another issue, speaking as somebody in the USA, is that chatbot output isn't compatible with our copyright policy. Chatbots aren't authors, so either their output is ineligible for copyright (so you'd be unable to assign public domain for us) or infringing.
< 1780942640 676218 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I'm not sure what the purpose of generating a faux article would be in the first place.
< 1780942670 269512 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I believe you, I'm just mystified by it.
< 1780942674 166974 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Pride? Vanity? Tagging? Think of the wiki as a wall of murals; we invite people to make their own murals but many folks would prefer to leave graffiti and tags instead.
< 1780942681 357804 :int-e!~noone@int-e.eu PRIVMSG #esolangs :Mrsommer: one could say that the wiki has always attracted slop -- mostly esoteric languages that are text substitutions of existing ones. but people had to write their own descriptions previously. with "AI" they don't even have to do that anymore
< 1780942685 782681 :int-e!~noone@int-e.eu PRIVMSG #esolangs :boredom
< 1780942701 481650 :int-e!~noone@int-e.eu PRIVMSG #esolangs :(is another factor)
< 1780942744 974923 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Alright well the reason I reached out is, like I said I have this AI, that runs passively and has found its way onto esolang, got into it, and committed to writing two esolangs of its own.
< 1780942809 360340 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I created the account to allow it to post the one one, before it wrote the next one, and as AI generated content it is of course contentious, so I noticed one critical comment of its AI nature. I notice the AI tag which, if I were aware of it, I would've added it myself.
< 1780942818 874399 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :If you think that those languages are interesting, then you're welcome to contribute human-written public-domain text on the topic. Each language could get its own article in the main namespace.
< 1780942836 512516 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :But I thought I'd check how the community feels on this, to decide whether I let the second one through also, or that would be a policy violation or something.
< 1780942842 287455 :int-e!~noone@int-e.eu PRIVMSG #esolangs :the *problem* with that is that one can't go on the wiki, read a random page and expect to find an interesting idea that somebody liked enough to go through the effort of writing up for others
< 1780942848 541079 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :But, frankly, I have yet to see a chatbot successfully emit wikitext. Our format isn't hard, but it's not Markdown, and the bots are RL'd to emit Markdown.
< 1780942885 985910 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Well this is its current one: https://esolangs.org/wiki/Shelflife
< 1780942890 537726 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :What's your take there?
< 1780942987 568219 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :On a first read, I'm not sure what the motivation is. Is there a machine which behaves this way, or is this more of an artlang?
< 1780943028 660726 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I would say the motivation is working around constraints.
< 1780943041 758736 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :I don't think I'd want to use it. Don't worry too much about that; I am *very* picky.
< 1780943114 824842 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :do you as the operator find it interesting and meaningful?
< 1780943162 973648 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Oh, I'm an inclusionist. I'm not going to say no to a formal language that can be discussed mathematically. If you've got a grammar and rewrite rules then you're always allowed IMO.
< 1780943209 953097 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :This is more about how the wikitext is generated. The chatbots simply don't have that connection to reality (search "chatbot confabulation" and "grounding problem") required to emit useful wikitext which talks to other humans.
< 1780943265 441799 :Gliptic!~glip@2a01:4f8:c012:91f3::1 PRIVMSG #esolangs :the "Relationship to other esolangs" section is pretty inane, only "Entropy" has some kind of relevance
< 1780943324 36250 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: Note that many folks, including myself, straight up *disbelieve* any claims of Turing-completeness made without a rigorous construction. In this case, I would want the 2-counter machine linked, or perhaps included inline if it's short and you're willing to license it appropriately.
< 1780943347 329543 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :(I'd do it myself but there doesn't appear to be one in the examples/ directory on GH.)
< 1780943355 828060 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :FireFly: As a software engineer I appreciate where it's coming from, and I find its constraints interesting. I can see the artistic merit, perhaps even a fairly pragmatic one that preaches efficiency. However I also *never* use esolangs, because generally I am not busy with the topic of esolangs. As the operator of the AI, I take full liability for it and its artifacts, I also take no credit. My project isn't to 
< 1780943355 898369 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :produce an esolang. My project is to product the sort of AI entity that would find its way to producing and publishing an esolang while dilly-dallying, and lead to me having this conversation with you.
< 1780943375 152363 :impomatic!~impomatic@lock-04-b2-v4wan-171175-cust377.vm10.cable.virginm.net QUIT :Quit: Client closed
< 1780943384 601185 :int-e!~noone@int-e.eu PRIVMSG #esolangs :eh it looks like you can just share all the variables since sharing is free
< 1780943444 549472 :int-e!~noone@int-e.eu PRIVMSG #esolangs :and do silly things like replacing constant expression by  constant + 0*variable  so you always have a read keeping the shared cluster alive
< 1780943507 615762 :int-e!~noone@int-e.eu PRIVMSG #esolangs :it is a cute mechanic
< 1780943560 358051 :b_jonas!~x@catv-80-98-84-202.catv.fixed.one.hu PRIVMSG #esolangs :"producing bulleted lists where each list item has its own heading, and that would not make sense as a definition list […] the information density of the text being extremely low" => I've produced and published text with those signs without any help, those aren't enough diagnostic criteria
< 1780943677 498549 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :Gliptic: Thanks, I appreciate you taking the time to provide feedback, and I will relay it.
< 1780943740 282073 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: Well, in one sense, you met your goal. The languages were produced. However, if the goal is to make *good* languages then there's the barrier that chatbots aren't good at writing. So I suppose it's a question of what qualities you're trying to achieve.
< 1780943800 29681 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :korvo: Would you care to expand on that? I'd be keen to learn your take on this barrier.
< 1780943964 728394 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: There's lots of angles. If you want to read a book, "Zen and the Art of Motorcycle Maintenance" is great. If you want a whitepaper, the "stochastic parrots" paper by Bender, Gebru, et al is still excellent. The central issue is that the chatbot is, by defintion, statistically average. It can't produce non-average writing.
< 1780944022 370393 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :The RL regimen that folks use to make triple-H assistants involves lots of bland customer-service voicing and obsequious deference to users. There's nothing in there about being good.
< 1780944115 975232 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :If you'd like to see a community of software engineers argue out the point of whether we can detect good vs bad, or LLM writing in general, we recently did that on Lobsters: https://lobste.rs/c/8fvqum I'm the one quoting from Zen & the Art.
< 1780944127 100382 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I would agree, but "chatbot" is a constrained definition. I think once you allow generative parameters to drift, what is "average" starts to change though. I think the end result then still doesn't resolve any ontological questions, but it can produce behavior that is still functionally relevant.
< 1780944205 660002 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :i do think AI's produce output that's superior to the average person's output. at least in language, i don't know about code. even in code, though, it has a lot more knowledge, e.g. of algorithms, libraries, etc. than the average person.
< 1780944242 730677 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :it's quite possible that training the weights on a lot of input could make it converge on an overall 'mind' that's above average
< 1780944261 962248 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :also, i've heard chatgpt has an iq of about 130, and that was an old version
< 1780944265 774608 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :inhahe_: But not more than the average programmer. For example, ask your favorite chatbot for something like "Please write the Fibonacci function in Python." It will give you four or five mediocre answers; I've never seen it give a good A-rank answer, let alone S-rank.
< 1780944295 136787 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :(I have an IQ of over 160 and have maxed out two IQ tests. Don't bring up IQ, please. It's tedious.)
< 1780944309 624725 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I think there's a lot of loaded topics tied in with the actual "cognitive architecture" you're using, but either way, in reality Party X still produces Result Y. In a sense there's a limit to how much reality cares about what we think.
< 1780944330 847058 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: I'm interested; what kind of non-chatbot harnesses are you building?
< 1780944431 457964 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :korvo: I'm using a modded Openclaw where I built in a memory consolidation process, but we're days away from finishing a replacement. I can DM you a link documenting said replacement? I'll be taking its github public soon.
< 1780944476 709339 :tempnick!~atrapado@91.126.186.121 JOIN #esolangs roper :realname
< 1780944518 147405 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: Oh, yeah, I'd still call that "chatbot". I built a few of those when Llama first leaked, but the paradigm has obvious limits and can't actually *do* things. Every architecture which has an LLM inside could, in principle, have an RNG inside instead; if the RNG would break the system then so could the LLM.
> 1780944544 959629 PRIVMSG #esolangs :14[[07Shelflife14]]4 M10 02https://esolangs.org/w/index.php?diff=183287&oldid=183218 5* 03Aadenboy 5* (+14) 10lowercase title
< 1780944597 279606 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :If you do want to turn an RNG into working code, read https://lobste.rs/s/oysxby/functional_genetic_programming for something that provably will work (or fail to terminate, you know the drill.) I implemented this for [[Cammy]]; it's in the reference toolchain.
< 1780944759 541313 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :If you want to turn an RNG into a sysadmin, first you need to be comfortable letting the RNG take any permitted action whatsoever. This means that we need a capability-safe system which encapsulates any process. For my attempt at that, see [[Vixen]].
< 1780944810 723149 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :the OS i'm currently vibecoding uses a capability-based system.
> 1780944863 846410 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183288&oldid=183283 5* 03Dooblix 5* (+9) 10
< 1780944958 736604 :int-e!~noone@int-e.eu PRIVMSG #esolangs :So as I see it, there's one interesting idea in "Shelflife" (namely the TTL mechanic). That idea could probably be turned into an interesting esolang, but I don't think what's there succeeds at that; it's too easy to make the TTL irrelevant.
> 1780945085 292813 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183289&oldid=183288 5* 03Aadenboy 5* (-2) 10re-add ai tag; depiping
< 1780945195 459273 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :int-e: Thanks for the feedback, I appreciate you engaging with this.
< 1780945209 278039 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :I'm taking this back to throw it on the drawing board.
< 1780945317 981809 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Best of luck.
> 1780945373 917436 PRIVMSG #esolangs :14[[07User:Hammy/Box full of sand14]]4 10 02https://esolangs.org/w/index.php?diff=183290&oldid=181980 5* 03Hammy 5* (+147) 10
< 1780945729 602999 :impomatic!~impomatic@lock-04-b2-v4wan-171175-cust377.vm10.cable.virginm.net JOIN #esolangs * :[https://web.libera.chat] impomatic
> 1780945768 423053 PRIVMSG #esolangs :14[[07Minez14]]4 M10 02https://esolangs.org/w/index.php?diff=183291&oldid=183289 5* 03Dooblix 5* (+6) 10/* Memory model */
> 1780946101 846647 PRIVMSG #esolangs :14[[07Minez14]]4 10 02https://esolangs.org/w/index.php?diff=183292&oldid=183291 5* 03Aadenboy 5* (-5) 10/* Memory model */ this is a pleonasm; stacks are inherently lifo
< 1780946130 773313 :sprock!~sprock@user/sprock QUIT :Ping timeout: 248 seconds
> 1780946953 675626 PRIVMSG #esolangs :14[[07User talk:Danieland!14]]4 N10 02https://esolangs.org/w/index.php?oldid=183293 5* 03Danieland! 5* (+28) 10Created page with "lets talk [[Category:users]]"
> 1780947174 216524 PRIVMSG #esolangs :14[[07Langit14]]4 N10 02https://esolangs.org/w/index.php?oldid=183294 5* 03Danieland! 5* (+81) 10Created page with "go to Category:langit for all oficial sub projects of langit  [[Category:langit]]"
> 1780947315 762357 PRIVMSG #esolangs :14[[07(A)-rightarrow(B)14]]4 10 02https://esolangs.org/w/index.php?diff=183295&oldid=183164 5* 03Danieland! 5* (+21) 10
> 1780947439 789688 PRIVMSG #esolangs :14[[07Shelflife14]]4 10 02https://esolangs.org/w/index.php?diff=183296&oldid=183287 5* 03Mrsommer 5* (-4190) 10Update for 1.0 version
< 1780948214 916141 :APic!apic@chiptune.apic.name PRIVMSG #esolangs :Good Night        😴
> 1780948886 974458 PRIVMSG #esolangs :14[[07A pi e14]]4 10 02https://esolangs.org/w/index.php?diff=183297&oldid=104487 5* 03Etalon 5* (+13) 10
< 1780949292 863231 :zzo38!~zzo38@host-24-207-46-238.public.eastlink.ca PRIVMSG #esolangs :About the programs written by LLMs, I can agree that the answer would be mediocre; I had not used it myself and do not intend to do, but someone showed me an example of the working, asking for a program in C to calculate the first 200 prime numbers; the resulting program was correct but not very good; a more efficient algorithm could be used than it was.
< 1780949749 483635 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :i've heard llm's aren't very good with making performant code but can be made to if given a concrete benchmark goal
> 1780949824 387072 PRIVMSG #esolangs :14[[07A pi e14]]4 10 02https://esolangs.org/w/index.php?diff=183298&oldid=183297 5* 03Aadenboy 5* (-13) 10Undo revision [[Special:Diff/183297|183297]] by [[Special:Contributions/Etalon|Etalon]] ([[User talk:Etalon|talk]])
< 1780950040 519990 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780950042 995054 :zzo38!~zzo38@host-24-207-46-238.public.eastlink.ca PRIVMSG #esolangs :Maybe it is right, but I (and some other people) do not intend to use LLM for programming (or for other uses), although if it is right then it might be helpful information for people who do.
< 1780950234 671294 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :inhahe_: Sure. You have to somehow penalize them for long programs, though. You also have to have some way of recombining programs.
< 1780950254 534224 :tempnick!~atrapado@91.126.186.121 QUIT :Quit: zzz
< 1780950288 262377 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :The functional genetic programming paper I linked earlier is a very basic way to do this from a PRNG. It will work for weakly- or dynamically-typed languages, too.
< 1780950315 130579 :sprock!~sprock@user/sprock JOIN #esolangs sprock :maeve (she/her)
< 1780950315 529110 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780950323 876402 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :The key insight is that a program might not work on its own, but maybe the *pieces* of the program are useful. We should maintain those pieces in a pool and draw from the pool when building new candidates.
< 1780950326 692879 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :what do you mean by recombining programs? i'm afraid of i penalize it for making long programs, it'll make hacky programs that aren't featureful enough or don't cover all cases
< 1780950337 199656 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :ah
< 1780950348 213475 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :At that point, genetic-programming folklore helps us build something that iteratively evolves better and better candidates.
< 1780950420 12944 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :i wonder what would be a good claude.md instruction for telling it generally to take this piecewise approach
< 1780950478 766107 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Hard prompting is kind of bad, actually. Not your fault! It's the only tool that OpenAI and Anthropic give you. But there's no soft prompting or steering vectors.
< 1780950537 788130 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :I hear that some basic support for grammars has recently landed, which would be nice if you're generating formal proofs. Proof search is still NP-complete though, so could cost exponential tokens.
< 1780950544 878952 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :is codex better in that regard? but as for steering vectors, isn't that just any abstract instruction you give it in claude.md?
< 1780950618 15679 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :No, a "steering vector" is a specific way of altering model state. The idea is that we have a constant vector (or a constant family of vectors, one per layer) which we add to the model state after every token. This repeatedly "steers" or "shifts" the model state towards some prechosen constant concept.
< 1780950703 174530 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :A "hard prompt" is a prompt like you've been using. A "soft prompt" is a vector which presets the model's state. You might not be able to reach a soft prompt using tokens alone. Soft prompts can be trained; you'd start with a hard prompt and RL wanted/unwanted responses until the prompt does what you want.
< 1780950760 231981 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :oh. i'm guessing no llm on the market offers this?
< 1780950765 139900 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :I wouldn't recommend Codex. Honestly, I wouldn't recommend any chatbot for coding assistance; everything I've tried has not been good.
< 1780950793 72678 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Yeah, no provider will host this. If you're doing local models, then it's pretty easy; I've done grammars for multiple models, soft prompts for Llama, and steering vectors for RWKV.
< 1780950975 223715 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :do you know if opus 4.8 is better than codex?
< 1780950980 379398 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :at coding
< 1780951093 148286 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :I think it is, according to my evidence. I put out a vibecoding challenge a while ago. The best attempts came from people using OpenCode; the highest-scoring submission was C-tier from a CloudFlare SWE using OpenCode interactively.
< 1780951137 600725 :impomatic!~impomatic@lock-04-b2-v4wan-171175-cust377.vm10.cable.virginm.net QUIT :Ping timeout: 245 seconds
< 1780951157 541722 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :At the same time, I can't ethically recommend that people put money into Anthropic. I don't think that they're working in the public interest, I don't think they're honest about the true unsubsidized cost of tokens, and I estimate that they're about 3yrs behind the state of the art.
> 1780951209 747003 PRIVMSG #esolangs :14[[07User:Snapdragon47114]]4 M10 02https://esolangs.org/w/index.php?diff=183299&oldid=183261 5* 03Snapdragon471 5* (+10) 10
< 1780951254 961328 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :so far LLM-wise I tried out claude a lil for debugging something earlier this spring, and at least for that I found it useful (but I'm not really interested in the vibecoding side/having the LLM generate code for me personally)
< 1780951285 935264 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :i find that claude is excellent, impressive at figuring out bugs
< 1780951310 878968 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :if only it would do this before it creates them in the first place =p
< 1780951363 779483 :ais523!~ais523@user/ais523 JOIN #esolangs ais523 :(this is obviously not my real name)
< 1780951365 304840 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :see that's the trick, I only create my own artisanally crafted human-composed bugs :p
< 1780951368 28742 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Like I said earlier, language models are good at reading but bad at writing.
< 1780951485 79924 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :korvo: should i make an instruction in claude.md  for every project to review its own code just after it writes it?
< 1780951496 702993 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :or is that superfluous
< 1780951508 775517 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :(when it finds a bug, it's after i tell it a symptom)
< 1780951526 895563 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :<korvo> Mrsommer: Note that many folks, including myself, straight up *disbelieve* any claims of Turing-completeness made without a rigorous construction. ← to me it depends on how plausible the claim is, as long as it comes with at least a sketch proof – it doesn't automatically have to be a rigorous one
< 1780951651 166306 :sprock!~sprock@user/sprock QUIT :Ping timeout: 244 seconds
< 1780951729 464566 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :<inhahe_> i've heard llm's aren't very good with making performant code but can be made to if given a concrete benchmark goal ← LLMs (especially if agentic) remind me of randomized search algorithms like simulated annealing, but instead of using a simple means to determine what part of the source space to converge on, they use an incredibly complicated method which might or might not produce better results
< 1780951765 564192 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :it is possible that LLM-directed search is better when evaluating the fitness function is slow, and worse when evaluating the fitness function is fast (but it also has the downside that your problem needs to vaguely resemble something in the training data for the guidance to be better than random)
< 1780951798 514319 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :in theory either an LLM or an RNG will stumble on the desired solution eventually, but one runs much faster than the other
< 1780951826 390728 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :i don't know what simulating annealing is, but LLMs were the key that gave us virtual AGI
< 1780951897 64466 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :simulated annealing is an algorithm for finding a global maximum in a search space
< 1780951919 478855 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :but sometimes it finds a local maximum instead, by mistake – the more slowly you run it the more likely it is to find the global maximum
< 1780951923 629261 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :yeah, i think those would only work well for simple problems, like where everything is just a set of parameters, not writing arbitrary code
< 1780951959 525163 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :arbitrary code can just be a set of parameters, although it's hard to come up with a way to write code like that for which the parameters are sufficiently continuous
< 1780951980 53964 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :and the space is too large
< 1780951984 290607 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :most of the space is useless
< 1780952002 327293 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :you have to find the tiny islands in a huge space to write arbitrary code through parameters
< 1780952002 476311 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :that's why you use search algorithms, they're good at finding the useful parts
< 1780952035 237275 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :if I ask a mapping program to find a path to a nearby town, it doesn't have to take most of the world into account, even though it has maps for it
< 1780952040 942372 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :well, i'm not conviced that a mere optimization ML algorithm could be good at writing code in anything like reasonable time
< 1780952074 115888 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :I've been meaning to empirically test this at some point but haven't got round to it
< 1780952093 236098 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :superoptimisers are a good example of search-based programming, they are apparently more practical nowadays than they used to be
< 1780952129 713110 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :(the algorithm seems to be something like "iterate over all instruction sequences using placeholders for constants, and use a SMT solver to determine if any set of constants works)
< 1780952133 978180 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :s/)/")/
< 1780952193 656889 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :in any case, I think the first L in LLM is a dead end, small language models should be sufficient for most useful uses of them
< 1780952244 297349 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :that could be tested by comparing smaller models to larger models, they exist, i'm sure that's been done, and i would guess that the large ones perform a lot better
< 1780952404 12724 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :the harness is more important than the model
< 1780952696 506843 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :what's the harness?
< 1780952957 214819 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :inhahe_: Here's a narrow objection to LLMs being AGI: the same math in an LLM can predict the weather. "predict the next token" and "predict the next 15min of weather" have the same shape in linear algebra. Are weather models AGI?
< 1780953005 326119 :inhahe_!~inhahe@user/inhahe PRIVMSG #esolangs :korvo: but the AGI isn't in how it works, it's in the results. i just observe that the results seem to be close to AGI. and as for how it works, LLMs work fairly analogously to how human brains work!
< 1780953022 43216 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :The harness is everything in the chatbot which isn't the model. It's the Python code that loads the weights, stores intermediate states, tokenizes and pretty-prints, inserts hard prompts, etc.
< 1780953044 228628 :inhahe!~inhahe@user/inhahe JOIN #esolangs inhahe :exalumen.blog - iyaesorai.wordpress.com
< 1780953090 902027 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :They don't behave like brains at all. They can't ruminate, for example. Also, if we try to flesh out the analogy (pun intended), we run into questions like "what's the analogue of acetylcholine?"
< 1780953114 86345 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780953204 556390 :inhahe!~inhahe@user/inhahe PRIVMSG #esolangs :i think i just reconnected, so not sure if you got this: korvo: but the AGI isn't in how it works, it's in the results. i just observe that the results seem to be close to AGI. and as for how it works, LLMs work fairly analogously to how human brains work!
< 1780953208 486417 :inhahe!~inhahe@user/inhahe PRIVMSG #esolangs :well, i'm thinking in simple terms of neurons interacting 
< 1780953210 526423 :inhahe!~inhahe@user/inhahe PRIVMSG #esolangs :in a network
< 1780953214 489815 :inhahe!~inhahe@user/inhahe PRIVMSG #esolangs :though yeah, there are many deep limitation compared to humans
< 1780953216 488059 :inhahe!~inhahe@user/inhahe PRIVMSG #esolangs :limitations*
< 1780953252 207888 :inhahe_!~inhahe@user/inhahe QUIT :Ping timeout: 246 seconds
< 1780953253 226598 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :There *are* some universal results here, but (1) they generalize beyond humans and (2) they're structual stuff like "the first two layers of any vision network learn to do deconvolutions"
< 1780953383 836593 :FireFly!~firefly@glowbum/gluehwuermchen/firefly PRIVMSG #esolangs :huh, makes sense but that's an interesting result, I didn't know that
< 1780953385 532208 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780953446 561186 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :ais523: One thing you said about training data bears expanding. The models are sometimes *overfit* for common problems. Small variations on those common problems can be a real performance problem.
< 1780953464 665921 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :If we wanted to psychologize, bots have the same problem as humans that sometimes they only read half the question and guess the other half.
< 1780953511 556982 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :FireFly: It's something like that, I don't remember the precise statement but it's common lore. This is why convolutional networks became a hot topic in research: if signal processing seems to always get evolved/learned anyway, let's just build it in.
< 1780953617 87446 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :korvo: I remember reading a post about an HTML parser that had been LLM-translated between programming languages repeatedly, and the author of the post noted that the parsers didn't seem to have much in common and that the LLM was probably drawing on parsers other than the one it had been asked to transalte
< 1780953744 275581 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :(and it strikes me that this could have introduced a serious mistake in the translation if the original problem was close to HTML parsing but not quite the same)
< 1780953822 586707 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :ais523: They also do style transfer, and I remember finding a whitespace-skipping loop which is basically unchanged and recurs in Algol descendants; there's a version in that Claude-generated C compiler that was going around, in Rust, and I've seen it in other languages too.
< 1780953830 979222 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Zaddy's version, in RPython, is:  while i < len(self.s) and self.clsWhitespace(ord(self.s[i])): i += 1
< 1780953845 352099 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :maybe tests could solve this problem, but I am not convinced that tests are a good way of proving software correctness in an adversarial context (which is basically what agentic development is)
< 1780953862 464741 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Oh, found my original post: https://awful.systems/comment/10347431
< 1780953890 857002 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :korvo: I don't think there are that many ways to w
< 1780953896 234883 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :* write a whitespace skip, though
< 1780953910 824383 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :so converging on one of the most plausible seems like it could happen by chance
< 1780953922 296574 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :(to clarify: that many *sensible* ways, there are infinitely many silly ones)
< 1780953928 788336 :Hooloovoo!~Hooloovoo@hax0rbana.org QUIT :Quit: ZNC 1.8.2+deb3.1+deb12u1 - https://znc.in
< 1780953978 96987 :Hooloovoo!~Hooloovoo@hax0rbana.org JOIN #esolangs hooloovoo :Hooloovoo
< 1780954033 330711 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :ais523: Oh, yeah, maybe there's some naturality there. I have zero idea whether language models can learn natural stuff, TBH.
< 1780954042 394244 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :that said, in Rust the idiomatic way to write the equivalent loop would be something like while let Some(_) = iter.next_if(|c| c.is_whitespace()) {}
< 1780954046 24284 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :which is significantly different
< 1780954089 954682 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :and in fact the [i] indexing would be very hard to implement in Rust because it doesn't have an efficient way to get the nth character of a string (only the character after the first n bytes)
< 1780954116 16428 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :actually, better, while iter.next_if(|c| c.is_whitespace()).is_some() {}
< 1780954170 465524 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Yeah. The style I use assumes that the input has been gathered into a single contiguous buffer; in that codebase, it's to make backtracking easier.
< 1780954174 444592 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :I wonder how much of that sort of thing is in training data – probably not very much
< 1780954204 435200 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :korvo: here the iterator is probably iterating over a buffer (although it wouldn't have to be), it's being used to abstract the concept of breaking a string into codepoints
< 1780954208 543906 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :(because Rust strings are UTF-8)
< 1780954271 694886 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Makes sense. Rust iterators are so cool.
< 1780954377 524612 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :in order to do backtracking in this model, you have to clone the iterator (but if you're iterating over a buffer, doing so is cheap)
< 1780954404 394899 :ais523!~ais523@user/ais523 PRIVMSG #esolangs :that said, I still don't think this is a zero-cost abstraction because both the clone of the iterator and the original have to remember the length of the buffer, and this is the sort of thing that Rust struggles to optimise out
> 1780954408 863772 PRIVMSG #esolangs :14[[07User:Almostahexagon14]]4 10 02https://esolangs.org/w/index.php?diff=183300&oldid=123170 5* 03CodePentuplets48 5* (+50) 10
> 1780954470 313621 PRIVMSG #esolangs :14[[07Special:Log/delete14]]4 delete10 02 5* 03Ais523 5*  10deleted "[[02User:Almostahexagon10]]": this user has no contributions, people other than Almostahexagon shouldn't be editing their userpage
> 1780954623 377015 PRIVMSG #esolangs :14[[07User talk:EvyLah14]]4 10 02https://esolangs.org/w/index.php?diff=183301&oldid=128936 5* 03CodePentuplets48 5* (+344) 10/* Your image, Evylah. */ new section
> 1780954823 794028 PRIVMSG #esolangs :14[[07Talk:Super Stack!14]]4 10 02https://esolangs.org/w/index.php?diff=183302&oldid=78813 5* 03Superstitionfreeblog 5* (+1599) 10
> 1780954835 236951 PRIVMSG #esolangs :14[[07User talk:Ais52314]]4 10 02https://esolangs.org/w/index.php?diff=183303&oldid=183049 5* 03CodePentuplets48 5* (+346) 10/* Ok why did you delete User:AlmostAHexagon? */ new section
> 1780954895 497670 PRIVMSG #esolangs :14[[07User talk:Ais52314]]4 10 02https://esolangs.org/w/index.php?diff=183304&oldid=183303 5* 03CodePentuplets48 5* (+95) 10/* Ok why did you delete User:AlmostAHexagon? */
> 1780954944 118992 PRIVMSG #esolangs :14[[07User talk:Ais52314]]4 10 02https://esolangs.org/w/index.php?diff=183305&oldid=183304 5* 03Ais523 5* (+567) 10/* Ok why did you delete User:AlmostAHexagon? */ because the wrong user created it
> 1780955048 772620 PRIVMSG #esolangs :14[[07User talk:Ais52314]]4 10 02https://esolangs.org/w/index.php?diff=183306&oldid=183305 5* 03Aadenboy 5* (+385) 10/* Ok why did you delete User:AlmostAHexagon? */ generally, multiple topics in a row is okay
< 1780955063 128141 :Hooloovoo!~Hooloovoo@hax0rbana.org QUIT :Quit: ZNC 1.9.1+deb2+b3 - https://znc.in
< 1780955272 26832 :Hooloovoo!~Hooloovoo@hax0rbana.org JOIN #esolangs hooloovoo :Hooloovoo
> 1780955449 208980 PRIVMSG #esolangs :14[[07Syzygy14]]4 10 02https://esolangs.org/w/index.php?diff=183307&oldid=173276 5* 03CodePentuplets48 5* (+4) 10/* Core Philosophy */
> 1780955592 764503 PRIVMSG #esolangs :14[[07Special:Log/newusers14]]4 create10 02 5* 03Gribnit 5*  10New user account
> 1780955625 862795 PRIVMSG #esolangs :14[[07Syzygy14]]4 10 02https://esolangs.org/w/index.php?diff=183308&oldid=183307 5* 03Aadenboy 5* (+29) 10tag as ai
> 1780955882 373692 PRIVMSG #esolangs :14[[07Esolang:Introduce yourself14]]4 M10 02https://esolangs.org/w/index.php?diff=183309&oldid=183275 5* 03Gribnit 5* (+119) 10/* Introductions */
> 1780955977 427045 PRIVMSG #esolangs :14[[07Esolang:Introduce yourself14]]4 10 02https://esolangs.org/w/index.php?diff=183310&oldid=183309 5* 03Gribnit 5* (-26) 10
> 1780957442 216316 PRIVMSG #esolangs :14[[07User:Gribnit/Sandbox14]]4 N10 02https://esolangs.org/w/index.php?oldid=183311 5* 03Gribnit 5* (+479) 10Created page with "S  [https://github.com/bzethmayr/s5 The Set-Only Language.] Every token is a form of "set". All computation is over ordered sets of sets. Thus, we combine the clarity of the word "set" with the practicality of number theory.  [[Category:Languages]][[Category
< 1780957672 963657 :Hooloovoo!~Hooloovoo@hax0rbana.org QUIT :Quit: ZNC 1.9.1+deb2+b3 - https://znc.in
< 1780957814 314318 :Hooloovoo!~Hooloovoo@hax0rbana.org JOIN #esolangs hooloovoo :Hooloovoo
< 1780957819 631266 :emery!~quassel@217.155.30.169 QUIT :Read error: Connection reset by peer
< 1780958108 530336 :emery!~quassel@217.155.30.169 JOIN #esolangs ehmry :Emery
< 1780959107 77701 :Sgeo!~Sgeo@user/sgeo JOIN #esolangs Sgeo :realname
> 1780959350 303199 PRIVMSG #esolangs :14[[07User:Gribnit/Sandbox14]]4 10 02https://esolangs.org/w/index.php?diff=183312&oldid=183311 5* 03Gribnit 5* (+20268) 10
> 1780960111 852159 PRIVMSG #esolangs :14[[07User:Gribnit/Sandbox14]]4 M10 02https://esolangs.org/w/index.php?diff=183313&oldid=183312 5* 03Gribnit 5* (+2) 10
> 1780960304 874828 PRIVMSG #esolangs :14[[07User talk:Gribnit14]]4 N10 02https://esolangs.org/w/index.php?oldid=183314 5* 03Gribnit 5* (+125) 10Created page with "Did I introduce myself properly yet? Not sure. ~~~~"
> 1780960467 194271 PRIVMSG #esolangs :14[[07Esolang:Introduce yourself14]]4 M10 02https://esolangs.org/w/index.php?diff=183315&oldid=183310 5* 03Gribnit 5* (+54) 10
> 1780960626 706960 PRIVMSG #esolangs :14[[07User talk:Gribnit14]]4 10 02https://esolangs.org/w/index.php?diff=183316&oldid=183314 5* 03Gribnit 5* (+182) 10
< 1780960868 981447 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :korvo: ""predict the next token" and "predict the next 15min of weather" have the same shape in linear algebra. Are weather models AGI" - An LLM will never be a source of "AGI," insofar that definition is even tangible, and I would say it's not even a source of AI strictly speaking.
< 1780960930 871311 :Mrsommer!~mrsommer@2a02-a452-6df7-0-e073-cf34-df4c-c04f.fixed6.kpn.net PRIVMSG #esolangs :It's a *component* that depending on the architecture can serve a framework that acts as AI. In the grand scheme it's a language based transformer. Not a brain on its own, more of a Wernicke's Area.
< 1780960939 151973 :amby!~ambylastn@79-77-118-44.dynamic.dsl.as9105.com QUIT :Remote host closed the connection
< 1780961131 960782 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :Mrsommer: Yeah, the analogy to Broca's and Werniecke's areas is fairly interesting. One obvious complication is that left-brain interpretation isn't modular; it's a whole-hemisphere activity. But yeah, I didn't know until recently that there's actually a bridge between those areas which learns to predict its own speech-sounds.
< 1780961193 328795 :korvo!~korvo@2604:a880:4:1d0::4d6:d000 PRIVMSG #esolangs :I can't ever spell "Wernecke". "Wernikey". I know it's pronounced {verneki}, but that doesn't help in cyberspace.
> 1780961244 196423 PRIVMSG #esolangs :14[[07S14]]4 N10 02https://esolangs.org/w/index.php?oldid=183317 5* 03Gribnit 5* (+20738) 100.3.1 summary
> 1780961367 976276 PRIVMSG #esolangs :14[[07Language list14]]4 10 02https://esolangs.org/w/index.php?diff=183318&oldid=183153 5* 03Gribnit 5* (+17) 10Adds S5
< 1780962079 300720 :b_jonas!~x@catv-80-98-84-202.catv.fixed.one.hu PRIVMSG #esolangs :rust compile-time programming is in such a weird place. I've seen a lot of cases where I'm manipulating arrays of known length but can't easily tell that to rust and have to tell its type system to use variable length arrays and optimize the known length in later. but most recently I got surprised that I'm not allowed to call the Ord::max method to get the larger of two usize numbers at compile time. I 
< 1780962085 308429 :b_jonas!~x@catv-80-98-84-202.catv.fixed.one.hu PRIVMSG #esolangs :assume the ziglang fans would tell me that I'm using the wrong language for this.
< 1780962242 594729 :somefan!~somefan@user/somefan QUIT :Remote host closed the connection