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

71–80 of 642 posts

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

#71

Post by peab »

minraws wrote: post #64
sigmoid10 wrote: post #40

Earlier quoted context omitted.

The actual current frontier plays somewhere around GM level. https://chessbench-ai.github.io/#leaderboard It's also worth noting that the very latest models (GPT-6 and Fable 5.1) actually play worse than their immediate predecessors, so it is likely that the labs are not benchmaxxing for this yet. If they did, I'm sure they could come up with something superior to humans. But there is probably very little demand for…

I know HN readers and posters just read numbers and can't be bothered to read, but please read the methodology before making any claims. > About their ELO ratings from their own website: > A field-relative rating calculated within ChessBench. It compares performance among the tested models and is not a direct equivalent of a human chess rating. I am around 1600 elo in over the board I can mop up Astra Fable etc even…

What levels are they actually at in your experience?

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

#72

Post by skydhash »

bigstrat2003 wrote: post #61
famouswaffles wrote: post #48

Earlier quoted context omitted.

Frontier labs don't care about chess. If OpenAI cared, GPT-7 could be a grandmaster+ level chess player. In fact there's a google paper on grandmaster level chess without search with a 270M transformer. Outside that, there was gpt-3.5-turbo instruct which was incidentally a 1800 lichess elo player that didn't make any illegal moves even after a few thousand moves. Frontier labs care deeply about automating knowledge…

> Frontier labs don't care about chess. If OpenAI cared, GPT-7 could be a grandmaster+ level chess player. If the models were actually intelligent, the way that the boosters claim, they wouldn't need to be tuned to play chess in order to be good at it. That's kind of the point of intelligence, that it is generically applicable to whichever task one wishes.

Pretty much this. Feed it a book or two on chess, and you should have a decent (or good) player. That's the generic intelligence people have. The aims is not to be supremely talented at something, but being able to read a manual and figure how to use/play something. Mastery can be gained overtime.

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

#73

Post by keeda »

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 them -- is $50 - 70 trillion annually. It's reasonable to assume that if AI drop-in-replaced all those knowledge workers, AI companies could credibly charge somewhere in that order of magnitude, because that's what the market is already bearing.

So if their hypothetical revenues are double-digit trillions and valuations are some multiple of that, the entire AI industry would be valued at double-digit trillions at the least.

Yet cumulatively the industry (the frontier labs + the SWAG estimate of the AI parts of all the other players) are valued at, say, ~6 - 7 trillion? Which seems like a fair approximation of how much knowledge work they can currently automate.

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

#74

Post by shric »

MichaelNolan wrote: post #69
csande17 wrote: post #58

Earlier quoted context omitted.

Even if you take that website at face value, the ELO scores shown are relative to the other AI models tested , and not comparable to the ELO scores of humans who play against other humans.

I wonder why they didn’t throw a real chess engine in there for a baseline. There are engines where you can set the elo in the settings, so it should possible to see these LLMs relative to a human 1500 rather than just relative to each other.

> so it should possible to see these LLMs relative to a human 1500 rather than just relative to each other

As a 1500 elo human I can tell you that a 1500 elo chess engine doesn't play like anything like a 1500 elo human.

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

#75

Post by skydhash »

danielmarkbruce wrote: post #36
jaykru wrote: post #7

Earlier quoted context omitted.

yes, huge for pure math and activities that look like it.

Doesn't really even need to look like it. If you can verify rewards, RLVR will optimize really really well. If you can't... it's a struggle. There are probably fewer fields where you can verify rewards than one might hope.

> There are probably fewer fields where you can verify rewards than one might hope.

2 tasks I've done today that I believe robots are nowhere near being able to do: Cleaning my wardrobe and draining bad fuel out of my generator. As in generic use cases.

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

#76

Post by someguynamedq »

> current frontier models need laborious oversight and guardrails on even the simplest task

As models advance, we shift the goalpost for what "simplest task" means. Before, "simplest task " meant "write a coherent English sentence." Now, "simplest task" means autonomously fix, review, and merge a bugfix.

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

#77

Post by minraws »

peab wrote: post #71
minraws wrote: post #64

Earlier quoted context omitted.

I know HN readers and posters just read numbers and can't be bothered to read, but please read the methodology before making any claims. > About their ELO ratings from their own website: > A field-relative rating calculated within ChessBench. It compares performance among the tested models and is not a direct equivalent of a human chess rating. I am around 1600 elo in over the board I can mop up Astra Fable etc even…

What levels are they actually at in your experience?

Sub 1300 that's my rating in the singular official tournament I participated at.

But given how easily I can crush them and how often they want to make illegal moves (btw above bench seems to use a harness that pokea the model until it gives valid moves).

I would rate them around 500-800 big range but at that level it's all about if the model can recall an opening or not. If it plays good first 4-8 moves the person on the end will fumble for certain and they win.

I can play good/best moves till 14-15 moves if I remember the lines and find someone who falls for it.

If you could give them the lines as prompts like the best 20-30 openings then they will be around 700-800.

700 is around the rating for a human who doesn't know the tricks but can do bare minimum calculations and understands the rules thoroughly.

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

#78

Post by echelon »

minraws wrote: post #64
sigmoid10 wrote: post #40

Earlier quoted context omitted.

The actual current frontier plays somewhere around GM level. https://chessbench-ai.github.io/#leaderboard It's also worth noting that the very latest models (GPT-6 and Fable 5.1) actually play worse than their immediate predecessors, so it is likely that the labs are not benchmaxxing for this yet. If they did, I'm sure they could come up with something superior to humans. But there is probably very little demand for…

I know HN readers and posters just read numbers and can't be bothered to read, but please read the methodology before making any claims. > About their ELO ratings from their own website: > A field-relative rating calculated within ChessBench. It compares performance among the tested models and is not a direct equivalent of a human chess rating. I am around 1600 elo in over the board I can mop up Astra Fable etc even…

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 a Boeing's flight guidance system to do so.

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

#79

Post by Forgeties79 »

minraws wrote: post #77
peab wrote: post #71

Earlier quoted context omitted.

What levels are they actually at in your experience?

Sub 1300 that's my rating in the singular official tournament I participated at. But given how easily I can crush them and how often they want to make illegal moves (btw above bench seems to use a harness that pokea the model until it gives valid moves). I would rate them around 500-800 big range but at that level it's all about if the model can recall an opening or not. If it plays good first 4-8 moves the person on…

As someone who used to compete for years and plays currently as a hobbyist, you’re absolutely correct. LLM’s are terrible at chess and if anyone wants to sober up their view on AI, try it yourself.

Anyone who casually plays on a regular basis can beat them more often than they lose. As you said if you just know the core openings (and end games, both of which you can get a handle on with modest effort) you will generally win.

Edit: reminder we had computers beating the best players in the world literally decades ago. LLM’s are remarkable tools but the current promises and expectations are ridiculous

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

#80

Post by alain94040 »

Not convinced by those points.

In particular, I found this very misleading or irrelevant:

a typical CPU project anecdotally has about three times as many specification and validation engineers as design engineers and a 5:1 ratio is not unheard of

The reason silicon design has such verification to design ratio is because the cost of one bug is many, many orders of magnitude higher than software. Both in dollar cost and in schedule cost (it takes months to fab a chip, and if you messed up and need to spin a fix, it costs tens of millions of dollars, not counting any design engineering cost).

I don't think you can extrapolate these very industry-specific facts to judging LLMs.

Post reply on HN