Community
Chat Logs
Tuesday, March 3, 2026
- dreamrealmarkov chain of you!
- jreicherOh really...
- jreicherbe jreicher
- nevet* channeling jreicher: i'm very much against the idea are the ticks, because they would continue while "players" are away. that might be prepared to modify the pr with your feedback
- jreicherbe jreicher
- nevet* channeling jreicher: to emacs. they don't always like what the tradition is. "rabbi, is it the tradition then to sit for the shema. failing to come up with a really infantile concept
- jreicherOh that i need to think about. A rabbi commenting on Emacs and the shema.
- dreamrealhey rabbis probably prefer emacs to vim
- dreamrealbut yeah, nevet has a clojure operation now :D
- bot[jottinger/bytecode.news] New issue #148: Wiki-style references in Markdown content ([[factoid]] and [[slug]] resolution) - https://github.com/jottinger/bytecode.news/issues/148
- * NeXeN joined #nevet
- * NeXeN joined #nevet
- * jreicher joined #nevet
- dreamrealyo jreicher
- blue YO jreicher
- dreamreali wonder what the effect would be of using four tokens for the markov chain instead of three
- dreamrealtwo goes off the rails really quickly, ONE goes off the rails SUPER-quickly
- dreamrealthree is recognizable, but still absurd
- bluewhat are you on about
- dreamrealbe dreamreal
- nevet* channeling dreamreal: people unable to talk about main vs master an asshole issue, and were not winners
- bluebe DJT
- nevetNo message history found for DJT.
- dreamrealthat's done by building a markov chain for the nick's history
- blueidk what a markov chain is
- dreamrealask what is a markov chain?
- nevetA Markov chain is a mathematical model that predicts the next item in a sequence based only on the current state, not the full history. In the context shown, dreamreal is using it to generate text by analyzing which words commonly follow others in chat history—for example, using 3 tokens means looking at the previous 3 words to predict what comes next.
- blue"current state", "3 previous words", ok. more nonsense
- dreamrealthat's not nonsense. If you don't understand it, all that means is that you don't understand it.
- dreamrealSo: imagine a sequence of words: X X Y, X X Y, X X Y, right?
- blueyes?
- dreamrealif you take that as a sample, you can say that "after X, you have a percentage of times you get X, or Y"
- blueyeah but what's the big deal, how is that different to any other statistically observation
- dreamrealX can yield X or Y: roughly a 50% chance based on that sample set, so if i say "here's X, what should follow, statistically?" you'd get 50% of X or Y
- bluestatistical*
- dreamrealbut if you say "what follows X X" it's Y, every time, right?
- dreamrealI'm getting there, geez
- blue*waits*
- dreamreal"this is what surface area means, class" "why aren't you giving me the surface area of the conical projection for these coordinates already, what's wrong with you"
- dreamrealanyway, so in a ONE token sample, You say "X" and the answer is 50% X, 50% Y
- blueya
- dreamrealin a TWO token sample (meaning the input to see what the 'next token' is) you'd get Y, 100%
- dreamrealthis is very useful in a lot of situations: autocorrect uses it a lot (and it's part of why autocorrect is so annoying), but you can do weather patterns, too
- blueyou needed 10 sentences to tell me you wanna calculate a statistically observation based on 2 vs 4 messages?
- dreamrealif you have four days of sun, there's a statistical prediction of whether the next day will be sunny, too, although you'd factor in more than "four days of sun" in an actual weather markov model
- blueyes
- dreamrealno, it should have been obvious right out of the gate but it wasn't, so I explained it
- bluebut I still don't get what'st he big deal. it's just statistics. why call it a markov chain
- dreamrealbecause that's literally the name of the specific model
- blueso markov chain is just a hipster name for how many messages we look back?
- dreamreal... no?
- dreamrealI mean, that's the guy who formalized the rules and data about the model, it's why we talking about 'newtonian physics' and not 'you know the apple shit'
- blueHA!
- dreamrealsame with bayes: "it's just numbers" but the specific reference has meaning
- dreamrealand the number of messages we feed INTO the model is actually called "the number of messages we feed into the model" and the model is a markov chain with specific characteristics, in this case the number of tokens that make up a sequence
- blueanyway, I consider this feature dumb: why do I need the bot spouting my own nonsense
- bluealso the messages in isolation often make no sense
- dreamrealhaha, nice! of course you do. But this was actually one of the first reasons the INITIAL bot was actually designed: we had a user who was very caustic and didn't believe he was being caustic. So I build a markov chain of HIS data, and had the system generate "stuff he would say" based on the data (removing MY bias against how he phrased things) and ran THAT through a sentiment analysis: if my
- dreamrealsuspicions were correct, he'd have a negative sentiment *as generated by the model* - and lo, he got a -0.4
- bluemhm
- bluetoxicity dreamreal
- dreamrealnevet would have said -4, not -0.4
- bluehm, broken
- dreamreal~sentiment #nevet
- dreamrealsentiment #nevet
- nevetSentiment for irc://libera/%23nevet: Sentiment +3/10 | Intensity mod | Themes: markov chains, statistics, bot features, technical explanation | Summary: Extended tech discussion between dreamreal and blue about markov chains/bot functionality. blue skeptical but engaged; dreamreal patient/explanatory. Tone mildly positive with light banter.
- dreamrealtehre is no operation called "toxicity"
- bluethen we NEED one!
- dreamrealWhy? !sentiment exists. And it's more useful than "toxicity" would, because it measures the quality and not the actual judgement.
- blueI think the bot misread me though, I'm not skeptical, I'm mocking, it's a fine difference
- dreamrealYeah, well, it doesn't have your internal negative locus
- blueman ai is such a dumpster fire
- dreamrealAnd we purposefully limit the backscroll for it, so it can't really learn it well, nor should it. You wouldn't want the bot to accurately evaluate you. :D
- blueit would do a bad job either way. the more I use AI, the more nonsensical it comes across
- blueone typical thing is that it has zero understanding of proper abstraction
- dreamrealSee? I mean, how is tis related to AI being a dumpster fire? AI comes across as nonsensical because I don't think you understand it. Look at how you interacted with markov - which is itself a form of AI.
- blueis your point that if I only understand a crazy person, I wouldn't think he's crazy?
- dreamrealI mean... "AI has zero understanding of abstraction!" from a guy who refused to see markov chains as an abstraction, it's just statistics, why not just call it toxicity... I mean... err...
- dreamrealAI is not a PERSON. It'd be like arguing with a wrench.
- dreamrealOh, wait, that's an abstraction. So a wrench is a tool, you hold it in your hand, it's generally a piece of steel moulded to...
- blueso what I've noticed, AI is really good at regurgitating nonsense produced by humans
- bluethat makes it completely useless, by reaffirming broken old patterns
- bluethe older a technology is, the best it is at it. so it's completely progress-resistant
- bluethe better*
- bluefor example: you can't program ANYTHING in zig in it
- dreamrealI mean... is this new? An LLM has training data and works based on that data, just like a markov chain does - which is why the markov abstraction is useful, BTW - and thus an LLM is naturally suspect and SHOULD be. Why would you expect anything different? The purpose of the system is what it does and what it's designed to be. They do EXACTLY what they should be expected to do, although there are
- dreamrealfacets to the models that diminish their effectiveness for some uses.
- bluezig is moving very fast, and AI will usually produce you code that has worked in version x-2, if at all
- blueyeah, but you're completely disregarding the HUGE chasm between human EXPECTATION of AI and what it is
- dreamrealI don't think that's true, actually: I think you'd have to make sure the AI had a way to introspect information about zig to make it work the way you want. Why do you think an AI is actually intelligent or mimics intelligence?
- bluecalling it 'AI', to begin with, is completely mislreading adn wrong
- dreamrealIt's... not. It's artificial. It's in the name. On the tin.
- blueit's NOT intelligent
- bluenor can it be, definitionally
- blueand artifical... well yeah, algorithms are artificial as well
- dreamrealI mean... but... dude
- blueI propose calling it a NRM, nonsense regurgitating machine, instead of AI
- bluethat is an ACCURATE description of it
- dreamrealAI is a term that means exactly what it's always meant: a derivative mechanism that yields results. It's often an oblique result (3(4)=12 is not oblique, but 'what will the price of tea in china be tomorrow if it rains' is.) But AI applies to bayes, markov, LLM, perceptrons, hopfield networks, pagerank... they're all just "statistics," is how I think you'd put it.
- dreamrealYes, we're all just NRMs, ghosts in a machine we cannot see
- dreamrealbe dreamreal
- nevet* channeling dreamreal: run in clojure :d
- dreamrealbe blue
- nevet* channeling blue: me issues should represent a complete item of work, i mean this:
- dreamrealheh
- bluedreamreal: I call them 'items' now
- blueI never really liked the term issue
- dreamrealthis is why I wonder about switching it to a four-token machiine :D
- blueissue sounds like a problem; a feature is NOT an issue
- dreamrealYou should call it whatever makes sense to you, that's what other people do, after all
- blueno I mean on RP
- dreamrealI think you should just call them records or rows or "things"
- dreamrealthat's what they are, after all
- dreamreal"file a thing" or, well, filing has meaning too: "do something for a thing"
- bluerecords/rows sounds too much like a db thing. and thing is very general. item means "item of work"
- dreamrealoh NOW words have meanings
- blueyes
- dreamrealthey ARE records and rows in a database, I presume
- blueyes?
- dreamrealSo why not call them what they are? Calling a mathematical model "markov chain" hides that it's just math; calling rows "issues" or "items" hides that they're database rows. Geez. Have some consistency.
- blueI can read that annoyed you earlier
- blueI thought it would be harder!
- dreamrealyes, because i'm allergic to stupidity and you were being stupid
- blueI was being belligerent, not stupid
- dreamrealBelligerence IS stupid.
- dreamrealsentiment #nevet
- nevetSentiment for irc://libera/%23nevet: Sentiment +4/10 | Intensity mod | Themes: AI/LLM capabilities, markov chains technical discussion, terminology debates | Summary: Extended technical debate—dreamreal patient/explanatory, blue critical but engaged with humor. Tone collaborative despite disagreement; banter present throughout.
- dreamrealInteresting.
- bluesomehow it improved despite your open toxicity
- blue"critical but engaged with humour" hits it well
- dreamrealYou know, one of the things about having kids - especially one who takes things rather literally - is that you learn to supress sarcasm, even when it's innate, because it serves few apart from the one using it.
- blueya
- bluein that, you win over me
- blueI don't have kids
- dreamrealIt's not a competition, just a lesson learned from having them
- blueI didn't present it, I just meant I don't have that experience so you're my senior in that
- bluepresent it as such*
- dreamrealbut one thing it produced in ME is that I don't take stupidity as anything more than face value, just in case. "Dad, how do batteries work" deserves a real answer, just like "why does the water in a toilet flush like it does?"
- blueI often feign stupidity. I do so because I want to let others define things as they understand them, instead of repeating something someone else said
- dreamrealtheatrical belligerence doesn't serve anyone. be who you are, if that means being stupid, be stupid.
- dreamrealWhy not just ask them to define it clearly?
- bluebecause, then they will *try* to define it clearly
- blueI don't want them to define it clearly
- dreamrealInstead, we had a full conversation where I wasn't having the same conversation you were - and yes, I'm annoyed by it more NOW than I was, because it was not an honest conversation.
- blueI want to understand how they see it in their brains
- dreamrealThere are ways to do that without doing it as you did.
- dreamrealBut that's neither here nor there. *I* don't need that shit.
- blueI don't think so, not in my experience. if you ask people to define something clearly, they usually do something else
- dreamrealI'm not other people. I know how to think.
- bluethat's WHY you're annoyed
- dreamrealRight. And it doesn't change that I'm annoyed.
- blueif that REALLY annoys you, I can ask you to clearly define it next time, assuming you'd have said the same thing
- bluebut that's not what I typically do
- dreamrealThat's fine. But there's a reason pilpul is frowned upon, and I'm frowning on it. I weaponize pilpul all the damn time, but I mind poe's law while I'm at it so there's no confusion about it.
- blueI also don't particularly understand why it's annoying; I personally don't care if someone is feigning ignorance or asking outright, I'd try to explain the same either way
- dreamrealI can understand that, but I already said why it annoys me: it means I was having a different conversation than you were.
- bluealso, *sometimes* it'll be something in the middle between feigning ignorance and "I don't 100% remember what this term means; let's see how this person meant it"
- dreamrealSure. Yet that's still not the same thing; it's asymmetric. if that's how you want our conversations to be, that's fine. I'm too much a leftist to enjoy that shit, but okay, you're one of the madding crowd.
- dreamreal"Madding crowd" here means the ordinary people, the villagers, the unaware, the guided.
- dreamrealIf you need definitions for those nouns, I can provide that too.
- blueyou know pretty well I don't care for labels, right
- dreamrealJust let me know.
- bluethough I gotta say
- dreamrealHey, you set the boundaries, not me
- blueMadding crowd sounds cool. I'd prefer maddening crowd
- dreamrealI'm sure, but they're different labels.
- bluecan I be one of the maddening crowd instead?
- dreamrealNo, that requires agency that external loci do not have.
- bluethis reminds me, like 30 years ago, having read Far from the Madding Crowd
- dreamrealIt's almost like references have meaning!
- dreamrealHuh.
- blueoh man you're REALLY mad now
- bluesentiment #nevet
- nevetError: Sentiment analysis requires ADMIN role
- blue+admin blue
- dreamrealkarma dmlloyd
- nevetdmlloyd has karma of 1.
- bluehm
- dreamrealsentiment #nevet
- nevetSentiment for irc://libera/%23nevet: Sentiment +4/10 | Intensity mod | Themes: AI skepticism, markov chains, terminology preferences, technical debate | Summary: Long technical exchange—dreamreal patient/pedagogical, blue critical but playful. Tone light despite disagreement; banter throughout softens edge.
- blue4/10 isn't bad, almost average
- dreamrealSo here's the thing: if you're trying to figure out how I think and what I mean, there's a lot here that's useful data... but it's data gathered in a way that does not benefit you, because data gathered like that eats social capital WITH ME. Maybe others act differently, and that's fine, but for ME it does actually irritate me - congratulations, you're aspiring to "maddening" - but it doesn't make
- dreamrealme ANGRY. It makes me tired. And when people tire me, I remember that. I'm trying to remember patience but it's an effort. And I'm lazy.
- bluewhy does it irritate you?
- dreamrealDude... stop
- dreamrealStop doing that shit
- dreamrealthanks
- blueoki
- dreamrealhomie don't play that with equals.
- dreamrealBuber applies.
- blueaah, that's hard, for me at least
- dreamrealSo I find I vastly disagree with nevet on the sentiment; I might need to revise the query to include some philosophical underpinnings that help it determine actual sentiment and interplay.
- bluenah, don't change nevet on my account, I'll just try to stop annoying you
- dreamrealNo, this is useful data
- bluewhat I find fascinating is that it totally missed how annoyed you were
- blue"dreamreal patient/pedagogical" was NOT a correct approximation of reality
- blue"dreamreal seething with annoyance" would have been more accurate
- dreamrealI don't know that I was seething, but sure
- blueyou were using dots!
- dreamrealI don't know how I'd instruct the models for that: depleting social capital like that is a pretty complex interaction to build in 100 lines of corpus, especially when the models can't take into account identity
- bluemhm
- dreamrealI can totally see how "patient/pedagogical" would map, because I wasn't shouting at you in traditional forms, I was more beseeching you to engage the brain I thought you had, but that's because I was talking to you and not a projection of you
- dreamrealI'm an introvert, and a pretty severe one, and you pretty much ran through as much rope as I had. Nicely done. But toxic.
- blueI'm a bigger introvert, though
- dreamrealI'm only 6'1, I'm shrinking as I get old
- * blue tries to figure how much is that in non-freedom scales
- dreamreal185cm
- blueoof, 186cm
- * blue is 189cm
- dreamrealoh no. I'm lesser than you.
- blueit's ok, I'm lanky, you probably weigh more
- * dreamreal sighs. Well, I can only say it so clearly before it starts to offend me.
- blueoh come now don't be SO annoyed. if I REALLY annoyed you with it, then I apologise. But that's often how I interact. I CAN drop feigning ignorance with YOU, but that's way for me to LEARN how people think
- bluea way*
- * dreamreal points to a rope
- dreamrealI dedicated too much of my energy to this bullshit already. I have to live with people, and they have to live with me, and this mode of conversation utterly exhausts me - I do it because I'm trying to serve tikkun olam for people who NEED it, and being told "hah, it wasn't needed" is wasteful and disrespectful of my time and energy.
- dreamrealWith all due respect and as little judgement as I can muster, that's a values violation, and you of all people should understand my values better than the goyim who babble without understanding. They use pilpul because it's what they understand best. WE should be different.
- bluemhm
- * jreicher joined #nevet