Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why I'm still bearish on LLMs after Navier-Stokes

dank.systems

Post reply on HN
Print view View original

601–610 of 646 posts

Re: Why I'm still bearish on LLMs after Navier-Stokes

#601

Post by fc417fc802 »

phoghed wrote: post #591
fc417fc802 wrote: post #574

Earlier quoted context omitted.

Yes, it is indeed self evident. If it can't figure things out then its intelligence isn't general in which case it can't be AGI by definition .

No, because there is no coherent, agreed-upon definition. There’s just a million people vibe defining it. Even if they solve 99% of whatever problems LLMs have, the 1% will remain the goal post, forever. Until you get RFC-whatever from some standards body that defines what an AGI system is, it’s pointless to argue about whether something fits your own personal definition or not. And for what it’s worth I just watched…

Throughout this exchange you're repeatedly confusing the negative and the positive. I agree with you that there is no rigorous and universally agreed upon criteria for exactly what would constitute AGI (ie the positive). There are some vague shapes that are widely (but not universally) accepted such as largely (vague boundary) being capable of replacing (vague criteria) humans.

However there are plenty of disqualifiers that are more or less universally accepted (ie the negative). In the above case it is literally by definition. Something cannot be termed general if it is incapable of generalizing.

Appealing to a standards body won't do you any good here. Those are composed of people. They exist to facilitate wide scale coordination. Their documents aren't always widely accepted. They aren't the arbiters of truth.

Re: Why I'm still bearish on LLMs after Navier-Stokes

#602

Post by HarHarVeryFunny »

lostmsu wrote: post #594
HarHarVeryFunny wrote: post #553

Earlier quoted context omitted.

> They can't possibly remember even a few positions. Sure they could, but that's irrelevant. A chess position is just a matter of remembering what piece number is on each square - just a list of 64 numbers. A trained model may store a trillion numbers (weights). It could store a TON of chess positions if it needed to. However, that's not how LLMs work. They don't memorize inputs - they predict them, based on discover…

> prediction which is closer to memorization > don't memorize inputs - they predict them I feel some tension here. > rice grains on a chess board? Sure, but this has nothing to do with chess, and nothing to do with how many games were in the LLM's training data. > just a list of 64 numbers > remember even a few positions? Sure they could, but that's irrelevant. I don't think you do. Or rather you do know the legend b…

You are talking about 2^64 being a huge number I assume ?

If not, then what are you talking about ?

If yes, then what is the relevance to an LLM playing chess ?

Re: Why I'm still bearish on LLMs after Navier-Stokes

#603

Post by jmcqk6 »

0c3ca83 wrote: post #499
reedlaw wrote: post #494

Earlier quoted context omitted.

Because agents lack human judgment. At the very least there's a need for a human-in-the-loop with agentic processes. Otherwise, it's like running a coding harness with --dangerously-skip-permissions all the time.

Why do you think judgement is impossible to automate? What aspects of it do you think make it hard?

Not the OP, but it's because the value has got to ultimately be recognized by humans.

You can make llms perform judgement, and maybe that will get you some progress. But ultimately the value is going to come from engaging with other humans.

Re: Why I'm still bearish on LLMs after Navier-Stokes

#604

Post by Razengan »

BeetleB wrote: post #581
derpyzza wrote: post #394

Earlier quoted context omitted.

huh i didn't even notice, that's how i write all my blog posts too. it looks nicer to me and i don't have to bother checking for "proper" capitalization if everything's just lowercase anyway. didn't realize people struggled to read text that way though, maybe i should change my writing style if this is a common pain point

It sucks. (So does not adding a period at the end of a sentence)

> (So does not adding a period at the end of a sentence)

Yeah, it does

Re: Why I'm still bearish on LLMs after Navier-Stokes

#605

Post by lelanthran »

brokensegue wrote: post #429
lelanthran wrote: post #379

Earlier quoted context omitted.

> I don't know how well it is studied, but I suspect it is possible there is language-related complexity constraints to the effectiveness of the LLM algorithms. I believe that's obvious - humans don't think in words. Neither do animals. A machine that only thinks in words is obviously going to be deficient in some things, no matter how proficient it is in everything else.

Aren't the new models thinking in neuralese?

> Aren't the new models thinking in neuralese?

Where did you read that?

Re: Why I'm still bearish on LLMs after Navier-Stokes

#606

Post by yunwal »

suzzer99 wrote: post #488
yunwal wrote: post #95

> those who need done a small set of narrowly defined tasks with existing clear guardrails: repetitive physical labor in a controlled environment, call center and customer service chat work, etc. I have no idea how people can so confidently say that call center work is a “controlled environment” or “repetitive”. It’s almost by definition not repetitive or controlled. Customer support is what I go to when the controll…

It's repetitive and controlled if you don't care about the outcome, which monopoly companies don't.

sure, but then why be bearish on LLMs? You don't even need to care about the code just check the boxes.

Re: Why I'm still bearish on LLMs after Navier-Stokes

#607

Post by andrepd »

famouswaffles wrote: post #389
andrepd wrote: post #226

Earlier quoted context omitted.

> The navier-stokes shows us what mathematical problem can be solved when $10m worth of compute is thrown at something. That's the thing, it very much does NOT show us that. What happened was mathematicians at openAI learned of an imminent development on this problem, and the insight that it entailed, then they were able to prompt a system in the correct direction and spend 20 million dollars to write down the final…

>What happened was mathematicians at openAI learned of an imminent development on this problem, and the insight that it entailed, then they were able to prompt a system in the correct direction and spend 20 million dollars to write down the final steps. That's not what happened.

Actually it was. But thanks for elaborating.

Re: Why I'm still bearish on LLMs after Navier-Stokes

#608

Post by keeda »

zug_zug wrote: post #453
keeda wrote: post #182

Earlier quoted context omitted.

It does not have to be 16% of all jobs, but 16% of any given job, i.e. AI stays in an augmentative role rather than a complete job automation. The simplistic analysis is if a tool makes you X% faster, that can be worth X% of your salary to your employer. Unfortunately, I do fear that AI adoption will go beyond augmentation to automation, and I do fear an economic shock. Just posted this down-thread: https://news.ycom…

You said 10s of trillions of dollars of revenue, which when the sum of all salaries is 65T, is minimum 15.3% of all salaries best case. It really feels like you're just pulling numbers out of nowhere here.

Yes, say the sum of all salaries paid be employers is $65T, and if AI accelerates workers by 15.4% -- studies and survey data actually suggest it's closer to 33% already e.g. https://www.stlouisfed.org/on-the-economy/2025/nov/state-gen... -- that is worth 15.4% of 65T which is 10T, which is already "double-digit trillions" as I said.

Assuming a 33% boost takes it to ~20T annually, which is technically "10s of trillions of dollars" in revenue. And these numbers are from before agentic tasks arrived on the scene, so the actual productivity boost and corresponding value to employers is likely even higher.

I'm not sure where the disconnect is?

Re: Why I'm still bearish on LLMs after Navier-Stokes

#609

Post by freejazz »

pixl97 wrote: post #598
freejazz wrote: post #588

Earlier quoted context omitted.

You're making my point for me, surprised you don't realize that...

Because you don't fully understand your own point... You look at science fiction and say "why didn't I get flying cars" and not "why didn't most science fiction predict a global always on network that put the furthest places away from you a few microseconds away from audio, video, or any other type of information that can be digitally encoded. Trying to use flying cars as a gotcha is missing that flying cars aren't n…

> You look at science fiction and say "why didn't I get flying cars"

I definitely don't, and you're definitely not getting my point, but I'm amused that you've instead double down on somehow getting it more than me...

Re: Why I'm still bearish on LLMs after Navier-Stokes

#610

Post by keeda »

webern777 wrote: post #342
keeda wrote: post #73

The premise in the very first point seems off: > the frontier labs are priced according to the narrative that they have produced or will in the very near future produce a fully automated drop-in replacement for most knowledge workers... Even assuming this is how the AI companies are being valued (they're not), the numbers are off. The "value" of most knowledge workers -- based on what enterprises currently pay for th…

The real issue IMO is that is not really what Anthropic and OpenAI are operating on. That is the after the fact justification of the AGI dollar auction. Each round is kind of 3x the previous cost and neither can really stop because second place in the dollar auction is so much worse than winning. The only way to stop the auction is one bidder hits a hard budget constraint, both agree to stop, or an outside party brea…

Could you say more about the AGI dollar auction? Is that something investors are actually thinking about, or a metaphor for what's happening? From what I've read so far, while AGI is definitely a well-known concept, investors are not really banking on it.

FWIW even without AGI there are indications that all this CapEx spend, even with very shallow adoption, is boosting national labor productivity by 1.3%. That is worth ~$123B based on total wages paid in the US alone: https://news.ycombinator.com/item?id=49721338

As such I don't see the need for AGI for any of this to be financially viable. Whether it is economically and socially viable... that's where I have grave doubts.

But Capitalism really only focuses on the former and not the latter, which is why this will keep getting pushed forward. And that is the crux of the problem.

Post reply on HN