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

451–460 of 646 posts

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

#451

Post by themgt »

datsci_est_2015 wrote: post #401
sailfast wrote: post #380

Earlier quoted context omitted.

What happens when you ask it to play chess against you if the chess game has an API? Are you measuring chess or multi-tasking skill? Also what harness? If you’re using a general harness of course it’s going to try and give you commentary. I say this not because I’m an LLM shill but because false equivalence is all over the place in the space and maybe it’s a fine heuristic for you but probably not a real outcome when…

Why does a 6 year old not need any of these guardrails? Frontier model’s failure modes are a direct refutation of claims that we’ve reached (or will soon reach) the artificial general intelligence. We may have reached an artificial general intelligence, but there may be more complexity to this than even AI thought leaders are talking / influencing about. Maybe not all AGIs have a path to digital singularity. Maybe ou…

Why does a 6 year old not need any of these guardrails?

Why does a bird not need jet engines or regular professional maintenance?

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

#452

Post by anthonyrstevens »

zahlman wrote: post #296
echelon wrote: post #78

Earlier quoted context omitted.

The AI can write a chess bot program that will beat you. You're thinking about this the wrong way. The system is built and delivered as it is because that's how the providers make the most money. If they cared to have it perform well in chess games, you'd see a different shape and behavior. We shouldn't ask the multibillion dollar automated software generation system to play games with us any more than we should ask…

> The system is built and delivered as it is because that's how the providers make the most money. If they cared to have it perform well in chess games, you'd see a different shape and behavior. This argument is fundamentally incompatible with all the breathless rhetoric about "AGI" coming from the providers' general direction.

>> the breathless rhetoric about "AGI" coming from the providers' general direction

So many commenters here see it as their ... duty? to argue against the most optimistic/unhinged (take your pick) arguments from "the other side" and then treat everybody who disagrees as a shill or an idiot.

Why is "being good at chess" a proxy for whatever AGI strawmen you want to argue against?

Maybe step back from your black-and-white ledge and think about discussing what's actually under discussion? For example, why or why not would an LLM be good at chess? Will they be good at chess? What technical limitations might preclude that?

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

#453

Post by zug_zug »

keeda wrote: post #182
zug_zug wrote: post #141

Earlier quoted context omitted.

> The "value" of most knowledge workers -- based on what enterprises currently pay for them -- is $50 - 70 trillion annually. What do you mean? The sum of ALL US salaries is $13.4 Trillion per year. According to google $65T is the sum of ALL salaries Globally (not just knowledge workers). It's not reasonable to assume AI is a drop-in-replacement for any job yet (perhaps bottom tier customer support from oversees?). >…

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.

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

#454

Post by well_ackshually »

MattCruikshank wrote: post #386
carodgers wrote: post #17

This April 2026 paper is a fun and related read. https://arxiv.org/html/2509.24239v4 Researchers asked frontier models to play chess. Have a look at the MAR rates in Table 3. When not explicitly told which moves were legal, no model identified legal moves at a rate better than 80%. Many asked for more illegal moves than legal moves. And even when explicitly told which moves were legal, the models continued to ask for…

What happens when you ask those same frontier models to write a chess-playing program? I feel like, this is a huge stumbling block that many people have. They'll give a model their data, and ask it questions. I vastly prefer letting the model understand the schema, and then writing functions or programs to answer those questions. I feel like I get way, way better answers. I can have it write unit tests for those func…

>What happens when you ask those same frontier models to write a chess-playing program?

they shit out a carbon copy of https://github.com/official-stockfish/stockfish that they have in their training data. Still doesn't make Fable good at playing chess.

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

#455

Post by lionkor »

glitchc wrote: post #443
lionkor wrote: post #427

Earlier quoted context omitted.

With that approach, the benchmark falls apart. Of course it can write a chess engine, because it learned on lots of stolen source code of chess engines. This has nothing to do with the LLM's ability to reason. Writing a well understood engine for a super popular problem does not count as reasoning about the problem.

> Writing a well understood engine for a super popular problem does not count as reasoning about the problem. Doesn't writing the engine imply understanding about the problem domain? Tool use is a widely accepted measure of intelligence.

In most humans, yes, because we are terrible at memorizing millions of codebases. For LLMs, we need to apply our understanding of them before making statements like that. An LLM can "memorize", and has "memorized"/been trained on tens of thousands of chess engines. Writing a chess engine, or even deriving a chess engine from the rules alone, does not constitute a deep understanding of, and more importantly, the ability to apply, the rules, at all.

When humans do this, they inadvertently learn something, too, but when an LLM reproduces or derives and implementation of a chess engine, it in no way implies that the LLM can follow the rules in its own "train of thought" and consistently apply the rules in its "head".

Let's say you want to evaluate my algebra skills. You make me solve some algebra challenges. If I then whip out a computer and write a calculator, or take some sticks and stones and take a couple hours to build an abacus, and then solve the algebraic challenges, this would not constitute a good solution, and would defeat the entire point of the test. If, instead, I do the algebra in my head or on paper, it might seem like there's no difference, but you can derive all sorts of information from that.

For example, you could time it, check for recurring errors I make, for interesting mistakes like mistaking 7 and 1 for one another due to bad hand-writing, etc.

If that was the goal, then me writing a calculator or crafting an abacus defeats the point of the test. Yes, me writing a calculator shows that I'm intelligent, and I understand the algebraic rules, but if the test is about applying the rules, I have not passed.

In the very same way, an LLM writing a chess engine to solve a chess benchmark that is all about LLM's reasoning capability is complete bogus and defeats the entire point.

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

#456

Post by contubernio »

stinkbeetle wrote: post #207
carodgers wrote: post #17

This April 2026 paper is a fun and related read. https://arxiv.org/html/2509.24239v4 Researchers asked frontier models to play chess. Have a look at the MAR rates in Table 3. When not explicitly told which moves were legal, no model identified legal moves at a rate better than 80%. Many asked for more illegal moves than legal moves. And even when explicitly told which moves were legal, the models continued to ask for…

> Researchers asked frontier models to play chess. Have a look at the MAR rates in Table 3. When not explicitly told which moves were legal, no model identified legal moves at a rate better than 80%. Many asked for more illegal moves than legal moves. And even when explicitly told which moves were legal, the models continued to ask for illegal moves. With illegal asks discarded, none of the bots could beat a chess mo…

They should just make them read an old chess book like Lasker that gives low level heuristics

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

#457

Post by lostmsu »

HarHarVeryFunny wrote: post #395
lostmsu wrote: post #138

Earlier quoted context omitted.

The fact that LLMs can play chess at any level is a strong indication we are in AGI.

It would be more impressive if they could play chess (or do anything they haven't been custom RLVR trained for) by reasoning, rather than just "have a go at it" prediction which is closer to memorization. HOW you do it makes a big difference in how you should assess the capability of the thing doing it. Stockfish will trounce any LLM, and any human, at chess, so should we say that Stockfish is smarter than both?

They can't possibly remember even a few positions. Don't you know the legend about rice grains on a chess board?

The claim here is not about intelligence, it is about generality. There's no doubt for me the LLMs are intelligent.

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

#458

Post by well_ackshually »

glitchc wrote: post #443
lionkor wrote: post #427

Earlier quoted context omitted.

With that approach, the benchmark falls apart. Of course it can write a chess engine, because it learned on lots of stolen source code of chess engines. This has nothing to do with the LLM's ability to reason. Writing a well understood engine for a super popular problem does not count as reasoning about the problem.

> Writing a well understood engine for a super popular problem does not count as reasoning about the problem. Doesn't writing the engine imply understanding about the problem domain? Tool use is a widely accepted measure of intelligence.

>Tool use is a widely accepted measure of intelligence.

Stop anthropomorphizing the parrot. The parrot has had stockfish's source code blasted at high pressure into its head along with dozens of millions of other pieces of code whose sole role is to have efficient algorithms to more or less brute force through the best result. Brute forcing (no matter how smart it is) isn't understanding the problem domain.

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

#459

Post by looki »

derpyzza wrote: post #394
yshklarov wrote: post #209

Great article, but the lack of sentence capitalization makes it unnecessarily difficult to read. Apologies if this comment is off-topic, but it really is quite egregious, and since the article was submitted by the author I presume they are open to the feedback.

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

I'm sort of wondering why you think we capitalize the beginning of sentences if not to help the reader.

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

#460

Post by cbolton »

empath75 wrote: post #435
cbolton wrote: post #417

Earlier quoted context omitted.

It's a great test of cognitive abilities. There are many claims that current LLMs surpass humans in cognitive abilities so it's noteworthy that they underperform on that test. Letting the model execute a chess program (that it wrote) would make sense if you're measuring its economic potential, but for cognition that would be cheating just like if you let a human run a chess program. The fact that the human would have…

> It's a great test of cognitive abilities. It isn't. Stockfish running on your laptop can beat every human being on earth easily at chess. It's not intelligent _at all_ in any sense that matters.

Well it's not a perfect test so you need a bit of care in how you use it. If you have no idea what the subject is doing, then you don't know if you're measuring cognitive ability or something else (like cheating ability, or algorithmic sophistication or whatever). But failing the test is a pretty clear sign of certain cognitive abilities being poor.
Post reply on HN