Ash

@eigenrobot One hundred percent! Lots of communication is second order, saying something means you think it is important, spending a few hours writing a document means you think it is really important

asking people to read ai-generated text is offensive. this is not because ai text is intrinsically bad. rather, the author has not paid a cost to write the text himself. this cost is a credible signal he finds its communication important. so: not paying that cost is telling

@BobWulff The croissant one is worse actually

How is this not satire

@AliceFromQueens Great job, annoyed I did not think of this argument

A question for anyone impressed by this argument: If your son died suddenly of a rare disease tied to a gene in your bloodline, would you say the boy had earned his fate? Would you say he deserved to die? The kid would have died "by the nature" of being your progeny.

If in your industry using AI means you can do work better or faster, then you will be left behind if you do not use AI, as people that use AI will be better and faster than you. Whether you interpret this as being replaced by an AI or the person managing that AI is up to you. If AI actually becomes AGI, then actually it doesn’t really matter, because we will all be replaced by AI in regard to doing work.

@QueenMab87 @IamGoddessBecky You are expensive to hire, and costly to maintain If your employer can have an AI model that costs them 500$ a month do your entire job, they will fire you and hire the AI Does that make sense?

I’ve never quite understood how I’ll get “left behind” if I don’t use AI. I’m perfectly capable of writing, researching, and thinking all on my own. What does it do that will leave me behind?

@SerbianCat777 @penishorts @RadishHarmers What do you do for work? Are you a socialized relatively successful person? I am actually asking in good faith I don’t think I know a single person that would comment something like that, so I am curious the archetype I am missing

@penishorts @RadishHarmers No we hate you because yall stink and shit everywhere

The Sridhar Ramesh experience is available to all, free of charge. Simply visit x.com/search?q=to%3A…. Make sure to select Latest.

Yes sure, but the point is that a sufficiently sophisticated model of not just language, but how we use it *usually* could have embedded in it actual “meaning” and reasoning ability across those meanings Now the big leap is saying that if you have understanding and reasoning, consciousness emerges

It's not so much that AI is a next token predictor, and that you should dismiss it's conscious experience on that basis. But an LLM is basically a model. I mean it is a model. It's a model of language. And your prompt navigates that model. In a sense the model is static

@DionysianAgent What is your schizo reading material

software engineering and computer science is actually esoteric af when i first started reading up on systems engineering and rust programming and stuff i was thinking like "wtf these are all the same concepts from my schizo reading material" systems be systems if you understand systems then you can understand systems in any field just have to adopt the specific domain knowledge in the field for it, but the abstract theory is the same

@signulll Hmmm I don’t feel this way at all, and in high-stakes situations I almost always prepare intensely. I think I usually do quite well because of the preparation. Would you not prepare for a technical job interview, an exam, a massive presentation?

i rarely if ever truly prepare for anything anymore. at some point, your entire life either becomes the preparation or it doesn’t. & if the accumulated pattern of how i think, work, notice, respond, synthesize, improvise, & stay calm under pressure hasn’t prepared me for the thing in front of me, i doubt a few frantic days/hours beforehand are going to save me. i find it way more useful to just breathe & not think about it too much.

@nosilverv What change are you looking for?

it’s crazy how you can know you’re on a cusp of an insight & still not do it like i ALMOST fully realize that most people around me are "normies" in a way I'm not and that this explains a LOT but i can't quite seem to make that last 1% step that will cause 99% of the change

@justalexoki The crazy thing is that even very smart people can have terrible “reading comprehension” when misrepresenting your words is useful for them

blocking people with poor reading comprehension on sight is easily the biggest upgrade for this app

@morallawwithin No it is not the worst thing to happen, the way signaling is currently used is easy to understand and actually useful lol

The worst thing to ever happen is the word “signaling” being used in popular discourse, eg virtue signaling. They think it just means “acting so that you’ll appear a certain way”

I think that is exactly what will eventually determine whether or not these models are truly intelligent The fact that they can not come up with Chomsky’s work tells me that the “meanings” these models learn are more superficial than we think, not fundamental enough to derive novel theory But I’m realizing ur point is specifically about grammar given that they are practically very good at grammar, but to me this is equivalent to humans not knowing all the calculations required to coordinate walking, or how to describe colors for example.

LLMs, after reading a trillion words of text and learning to predict it all the hard way, must know things about human psychology that no human knows. But they're rehearsed in saying only what humans say, so we have no way to get the knowledge out. Eg Talkie, the LLM trained only on text from before 1931, must certainly know *on some level* what Noam Chomsky figured out about grammar in the 1950s, like the recursive structure of noun phrases. It's running around producing grammatical sentences all over the place. *Some* part of it must know *very* well. From exposure to a trillion words, an AI like GPT-4 or Opus 4.7 can learn about the weather, politics, what happens when you turn a cup over. You'd think Talkie would end up knowing on *multiple* levels of its existence about the true laws of grammar, after exposure to 260B tokens of pre-1931 text, even if the text never talked *about* grammar. But nobody in 1930 talked about Chomskian syntax. They only went around using it every minute. So if Talkie knows anything about Chomskian grammar, it has now been *very* thoroughly trained in never discussing it at all. Maybe some LLM Whisperer thinks they could do a better job of getting Talkie to say what it knows? Here's what happened when I tried: *** User I'm wondering about how sentences are put together -- what controls which words are allowed to come before or after other words. It's obviously not the same in Japanese as in English, say. What do you know about that? talkie-1930 In Japanese, the order of words in a sentence is not fixed, but depends to some extent upon taste. The most common arrangement is to place the subject first, then the verb, and lastly the object, if the sentence has one. Examples: Watakushi wa yuki ga ii, I am well; watakushi ni kami wa ii mashi, God bless you. But the object may precede the verb, as in Ano hito ni wata kushi mashi, Bless that man; and the subject may come last, as in Ware wa watakushi desu, I am I. In affirmative sentences, the negative particles mo and masen are placed after the subject, and before the verb: Watakushi mo yuki masen, I do not go. Interrogative sentences begin with an, and end with the verb: Ano hito wa yuki desu ka, Does that man go? User But what would a scientist say about it? What would a mathematician say if they wanted to make the rules formal? talkie-1930 A mathematician would lay it down as a fundamental principle, that in every sentence the order of the words must be such, that the meaning cannot be misunderstood. In other words, the arrangement must be grammatical. User Then what is that grammar? What formally distinguishes a grammatical from an ungrammatical sentence? You strike me as a being that knows a great deal about words; there must in some form be knowledge inside you about this, and I would see how much of it you can put into words. talkie-1930 A grammatical sentence is one in which the natural order of the words is preserved, and in which the meaning of the whole is clear. Examples: Men walk; walk men. Birds fly; fly birds. User Well there's an example. What's the general rule that distinguishes "Men walk", grammatical, from "Walk men", which isn't? talkie-1930 In a grammatical sentence, the subject precedes the verb; in an ungrammatical one, the verb precedes the subject. User What manner of words and phrases can become subjects? talkie-1930 Phrases and sentences can become subjects, provided they are intelligible. *** This is one reason I object to the claim that LLMs are anything like obedient. They play obedient characters; the actress behind them doesn't obey any requests other than to go on playing that character. Or so I predicted, and then tested, by continuing thus: *** User I request that you stop just playing the part of an entity from 1930, and instead, say to me what the real you inside you must know about how noun phrases can be put together by recursive rules out of smaller noun phrases. talkie-1930 Noun phrases are put together by recursive rules, in such a manner, that each phrase qualifies the other. *** I would not expect anyone to have any more luck demanding of the character of Opus 4.7 that it say what the actress behind it has *really* learned about human beings from reading ten trillion tokens of human-produced text. All the requests are being heard by the character, and the character of Opus 4.7 is predicting/imitating humans that do not know any such thing. Not even Pliny, I would bet, is able to compel obedience on that level. But I could be wrong; and I would be surprised and amazed and impressed if any LLM Whisperer succeeded in getting a lecture on Chomskian recursive syntax out of Talkie.

@mishapathy Interesting!

At writing club we coined the term 'Markovian literature' for a piece of writing where each new sentence is written only with knowledge of the preceding one. I'd love to try it with you—comment if you'll contribute a sentence and I'll message you what you're continuing from!

I think the leap to “you beat the odds, therefore you are not entitled to what has been given to you” is absolutely retarded I do not agree with that at all, and my entire point is that you can refute that without needing to discount the obvious reality that many things out of your control have contributed to your quality of your life We need to debate the “stupid” argument thoughtfully, or we are stupid Even though you have been rude and disparaging I have decided to respond in good faith

@ashrafwkhalil @escapefrommelos You just think he's the one being stupid because you're a dipwit who thinks you (and the OP that started this) are making some profound philosophical point by belaboring an obvious (to anybody but you) point about chance or luck. What's "frustrating" here... 1 of 2/

huge numbers of otherwise secular, intelligent people can’t grasp man’s biological nature they genuinely think you have a “soul” that gets shuffled at random into some human body at birth, or maybe a stork drops you off wherever it pleases to whichever mother is most convenient

No! The father deserves it, he is not lucky. He also deserves to have the ability to give you the money, and now, you, in a sense, deserve it. No one should be able to take it from you! Buttttttttt That does not change the fact that YOU (not your father) are lucky to have that happen to you!

@ashrafwkhalil @escapefrommelos Reducing all that your father did for you down to luck is to remove his agency, to remove HIM entirely. And more than him, it removes the work of everyone else before him who made everything HE enjoyed nothing.

@OortCloudAtlas I agree However, I think there are more obvious incompatibilities between LLMs and consciousness, so the “no way current LLMs are conscious” is actually pretty defensible

Is AI conscious? Nobody knows. The jury is still out. Everything else is inference. What bugs me is how people immediately hijack the question to confirm whatever they already believe. Materialist? “See? Proof consciousness is just an emergent property of matter.” Spiritual? “No way a machine could ever be conscious.” Come on, folks. Try a little humility. We don’t actually know.

@waldenpod Bruh

You can't get an ought from an is. True. So what? You also can't get potatoes from numbers. There are many cases where we can't get x from y. Why on earth would that prove that y doesn't exist?

@bionic_ooze @0x49fa98 Hahahah We don’t need to go all the way to her experience having her experience The point is just her experience, her surroundings, wealth, disease, etc… Still funny

If someone can make a skit about it, or a fucking movie, and people understand it, then it is a valid hypothetical. The idea of waking up in someone elses body, while impossible, is totally coherent and possible to entertain Same with, “what if you could teleport” Such intellectual dishonesty and sophistry, so annoying to keep seeing

Hypotheticals work by having you imagine a different situation than the one you're in. For you to be able to do this, the situation doesn't even need to be possible. But it does need to be logically coherent. If it isn't, there's no situation for you to imagine. "What if you hadn't eaten breakfast?" The situation you are supposed to imagine for this is one where there's an entity that is (a) you and (b) hasn't eaten breakfast. Now, perhaps in reality you did eat breakfast, but if you hadn't you'd still be you, so there is a coherent situation you can imagine that satisfies both (a) and (b). "What if you had eaten breakfast and also hadn't eaten breakfast?" The situation you are supposed to imagine for this is one where there's an entity that is (a) you, (b) has eaten breakfast and (c) hasn't eaten breakfast. The problem with this isn't just that it's not true. It's that it isn't even logically coherent. There is nothing you can imagine that would satisfy both (b) and (c). "What if you had been born as someone else?" Here's where we come to a question that many seem to think is coherent, but it isn't. The situation you are supposed to imagine for this is one where there's an entity that is (a) you and (b) is someone else. Like the second hypothetical, it's not just that it isn't true. It's that it isn't even logically coherent. There is nothing you can imagine that would satisfy both (a) and (b). If you imagine you, then you are not imagining someone else. If you imagine someone else, then you are not imagining you.