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 model calibrated to 1100 ELO.
The author of the originating post says that "current frontier models need laborious oversight and guardrails on even the simplest tasks", and he's absolutely correct.
1. It’s hard to trust a 2026 paper that’s showing results for such old models.
2. Chess seems to be a poor benchmark for generalized strategic reasoning. People who are good at it rely more on experience and deep domain expertise than on skills that generalize to make them experts at unrelated tasks.
3. The study sounds like proving humans will never fly because they don’t have wings. In reality, humans do fly, and Claude Fable would destroy any human at chess by coding a strong enough engine on the fly.
> People who are good at it rely more on experience and deep domain expertise
People are good are 1900 or 2100 above and the top ones who spend decades in the field i.e. deep expertise are well in the 2200-2700 range.
A 1100 player is none of these things, they are purely relying on strategic reasoning there is a good chance they cannot name a single opening or articulate clearly why a move was appropriate. 1100 is quite low bar.
1100 at online speed chess or something, could be. I'm not that deep in the chess world but everyone I know that can make 1100 in official rating can name a dozen openings and most of the known tactics, and is pretty good at applying at least one opening.
1100 lichess/chess.com does not represent real elo. I'm around 1400 online, I would still be unranked in the real world. The fact that I easily beat any model publicly available is not a great look for AGI.
If the goal for buyers of AI is “replace this knowledge worker”, how much does it matter that the model in a simple loop can’t do it, but the model with a strong general purpose harness and a little time to gather resources and knowledge to augment the harness going forward, plus tool calls, plus custom built tools, etc, can replace the knowledge worker?
Probably the only thing saving many jobs from being replaced right now is that it’s hard to have a verification of correctness in the loop, so the agent can’t hill climb very easily.
Tests are often conducted under restricted conditions. For example, elementary school students aren't given calculators in math class, or during an interview, you are asked what encapsulation is and aren't allowed to use Google. The chess test effectively demonstrates the reasoning capabilities of an LLM without relying on brute force, because a human is incapable of calculating trillions of combinations yet plays chess successfully. This test is necessary because many complex problems cannot be solved by brute force, such as managing a business or playing Heroes 3. Therefore, we can make the assumption that if an LLM can play chess at a grandmaster level without brute force, it means it will be able to command an army or manage production.
People might care about this for chess, but no one really cares if an LLM can command an army or manage production of a business without any tools. If it can do those tasks reliably when given access to tools (including any tools it autonomously creates for itself), then that's more than sufficient. No one cares if an LLM is doing reasoning the way humans do it, as long as it can get the job done.
The assumption is that if an LLM is incapable of playing chess—a game with a relatively small number of pieces, clear and simple rules, and perfect information—even after reading a hundred thousand books on chess, then it is fundamentally incapable of managing an army or a factory. This is because those scenarios involve more 'pieces,' incomplete and fuzzy information, and implicit rules that need to be deduced independently. It doesn't matter whether it has tools or not. It's simply that running tests with chess is cheap, whereas testing with an army or writing a browser from scratch is quite time-consuming and expensive.
so prove it! get a public repo out there, have it play against some open source engines
also I think the operative letter in AGI is the G - and if the G is short for 'variably competent savant-like hyperfocus on certain kinds of software coding and not any other general skill' then its not really G at all, is it?
is that what I'm saying? or am I talking about AGI? perhaps there's some irony here to be explored when it comes to basic reading comprehension gaps
My point was you are misunderstanding G, or at least applying it erroneously here. Being good at chess is not a generalization of any other body of knowledge, it is a rigorous set of rules. The only way to be good at chess is to practice chess, or to apply deep calculations. The latter is the model writing code.
The illegal move aspect has more to do with a failure of online/in-context learning, which would support your point. I tend to think it is a byproduct of reasoning in language, which newer architectures would fix, but we shall see.
chess is not a rigorous set of rules, it is rules as foundation. and so is, for example, scientific methodology or chemical interactions or virtually everything else under-the-sun. knowledge for chess, specifically, is derived from memorizing strategies that have been well-defined for decades paired with in-game reasoning processes. it is not at all different from any other body of knowledge - it only 'feels' different to us humans because it is so logic-based and it takes a long time before our inferential, pattern-recognition kicks in and starts seeing the board in a naturally, systemic way. for an AGI, that should be a cakewalk, trained as it were to surpass human capability in any and every domain (thus the G for 'general' and not 'H' for 'hyperspecific')
I'm not. AGI is almost necessarily closer to ASI than it is to human intelligence. you take the concept of domain knowledge transferring to other areas. presumably, an 'AGI' that is generally as good as a really good human at every task under-the-sun will already be much better than most humans because it can incorporate cross-domain knowledge and apply it in a reasonable fashion. it's like the parable of Newton and the apple - the domain knowledge that an apple falls according to certain rules observed before igniting the creative spark that led to universal gravitation
> presumably, an 'AGI' that is generally as good as a really good human at every task under-the-sun will already be much better than most humans at the task because it can incorporate cross-domain knowledge and apply it in a reasonable fashion.
I disagree with this definition of AGI, and I disagree that chess skills significantly benefit from generalizing non-chess knowledge, outside of computing moves probabilistically.
AGI has historically been defined as human level or better, with generality to new domains. I think blurring it with ASI makes the terminology confusing to use.
Chess is learned rules and the ability to apply those rules. Strategy as a whole is applying a set of rules to circumstances, that's how it is taught: "here are examples of circumstances and actions, try to pattern match to future circumstance and apply commensurate action."
If you make the point that chess is a large part of the training data, or that LLMs are unable to learn chess well, I'll accept that as refuting that LLMs are AGI, but these other points I disagree with.
Declarative knowledge is not the same as procedural knowledge. You can read as many chess tutorials, strategy documentation and game archives as you like, they won't make you good at chess until you actually start practicing chess.
The issue with the models isn't that they play a bad game, but that they persist in making illegal moves. An average intelligent human can be told the rules of chess and then play chess, badly, within the rules.
Sure, but the LLM is free to construct a representation of the chess board and update it as it goes along. It is not in any way banned from using a virtual board, or whatever representation of game state it pleases.
> Claude Fable would destroy any human at chess by coding a strong enough engine on the fly.
A bash script can clone and build stockfish, feed in human moves, and reply. By your standard, this bash script would "destroy any human at chess."
Are you interested in assessing the intelligence of the model, or the intelligence of the tools the model can use?
Maybe practically it doesn’t matter? Perhaps AGI is not the model but the model plus everything it’s got access to. If we’re modelling intelligence in the way we seem to have to to have any coherent definition of AGI, it seems to me <model + everything it can access> is always going to be more “intelligent” than <model> alone.
My points is more that, while we have a strong intuition about where, as an entity, a human's boundaries are (i.e. where the person begins and ends), philosophically it' not immediately obvious that the analogy applies to the a model in the same way. Why should that be the line drawn that says this is the "thing" and this other stuff is external to the thing? It feels somewhat arbitrary.
Of course this is a difficult question with humans too, hence my reliance on intuition above. We don't have the same cultural/biological framework to fall back on with AI.
I think all this debate about whether an LLM can write (or download) a chess engine is sort of missing the point. For basically any economically valuable work there is no equivalent of a chess engine for it. If there were we wouldn't need humans or AI to begin with.
If the goal is merely to "win at chess", then yes, an LLM using stockfish is better than any human alone at performing the task. When you are talking about what AI agents are capable of doing, there is no such thing as "cheating". They are as capable as the tools they can use effectively. The entire history of human civilization was driven by effectively using tools to achieve goals.
Not sure how that vague truism applies to this paper.
Lots of papers have great results that don’t depend on the latest models.
However in this case it’s problematic:
- They specifically make claims about the state of “current LLMs”. o3 is not representative of this.
- They ask are LLMs capable of X and arrive at a negative result.
If their claim was LLM’s can write coherent sentences, and their conclusion was positive, then there would be no issue using old models because the end result would be factual.
However, when you have a negative result that makes a claim about the current state of all LLMs and the ones you were using are not current, by definition it draws the whole conclusion into question.
carodgers · · focus · HN ↗
<a href="https://arxiv.org/html/2509.24239v4" rel="nofollow">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 illegal moves. With illegal asks discarded, none of the bots could beat a chess model calibrated to 1100 ELO.
The author of the originating post says that "current frontier models need laborious oversight and guardrails on even the simplest tasks", and he's absolutely correct.
WhitneyLand · · focus · HN ↗
2. Chess seems to be a poor benchmark for generalized strategic reasoning. People who are good at it rely more on experience and deep domain expertise than on skills that generalize to make them experts at unrelated tasks.
3. The study sounds like proving humans will never fly because they don’t have wings. In reality, humans do fly, and Claude Fable would destroy any human at chess by coding a strong enough engine on the fly.
manquer · · focus · HN ↗
People are good are 1900 or 2100 above and the top ones who spend decades in the field i.e. deep expertise are well in the 2200-2700 range.
A 1100 player is none of these things, they are purely relying on strategic reasoning there is a good chance they cannot name a single opening or articulate clearly why a move was appropriate. 1100 is quite low bar.
svachalek · · focus · HN ↗
tovej · · focus · HN ↗
orwin · · focus · HN ↗
what · · focus · HN ↗
Delusional, but then Claude fable also isn’t beating any human at chess, the engine is.
senordevnyc · · focus · HN ↗
If the goal for buyers of AI is “replace this knowledge worker”, how much does it matter that the model in a simple loop can’t do it, but the model with a strong general purpose harness and a little time to gather resources and knowledge to augment the harness going forward, plus tool calls, plus custom built tools, etc, can replace the knowledge worker?
Probably the only thing saving many jobs from being replaced right now is that it’s hard to have a verification of correctness in the loop, so the agent can’t hill climb very easily.
numitus · · focus · HN ↗
senordevnyc · · focus · HN ↗
numitus · · focus · HN ↗
paimapi · · focus · HN ↗
also I think the operative letter in AGI is the G - and if the G is short for 'variably competent savant-like hyperfocus on certain kinds of software coding and not any other general skill' then its not really G at all, is it?
BobbyJo · · focus · HN ↗
paimapi · · focus · HN ↗
jibal · · focus · HN ↗
BobbyJo · · focus · HN ↗
The illegal move aspect has more to do with a failure of online/in-context learning, which would support your point. I tend to think it is a byproduct of reasoning in language, which newer architectures would fix, but we shall see.
paimapi · · focus · HN ↗
BobbyJo · · focus · HN ↗
AGI != ASI. You are confusing the two.
paimapi · · focus · HN ↗
BobbyJo · · focus · HN ↗
I disagree with this definition of AGI, and I disagree that chess skills significantly benefit from generalizing non-chess knowledge, outside of computing moves probabilistically.
AGI has historically been defined as human level or better, with generality to new domains. I think blurring it with ASI makes the terminology confusing to use.
Chess is learned rules and the ability to apply those rules. Strategy as a whole is applying a set of rules to circumstances, that's how it is taught: "here are examples of circumstances and actions, try to pattern match to future circumstance and apply commensurate action."
If you make the point that chess is a large part of the training data, or that LLMs are unable to learn chess well, I'll accept that as refuting that LLMs are AGI, but these other points I disagree with.
nmehner · · focus · HN ↗
brindleth · · focus · HN ↗
_superposition_ · · focus · HN ↗
foldr · · focus · HN ↗
empath75 · · focus · HN ↗
foldr · · focus · HN ↗
carodgers · · focus · HN ↗
A bash script can clone and build stockfish, feed in human moves, and reply. By your standard, this bash script would "destroy any human at chess."
Are you interested in assessing the intelligence of the model, or the intelligence of the tools the model can use?
nimbleal · · focus · HN ↗
Planktonne · · focus · HN ↗
nimbleal · · focus · HN ↗
Of course this is a difficult question with humans too, hence my reliance on intuition above. We don't have the same cultural/biological framework to fall back on with AI.
thinkharderdev · · focus · HN ↗
empath75 · · focus · HN ↗
Planktonne · · focus · HN ↗
Certhas · · focus · HN ↗
The idea that anything other than a breathless blog post about the latest model snapshot is useless is really poisonous to proper debate on AI issues
WhitneyLand · · focus · HN ↗
Lots of papers have great results that don’t depend on the latest models.
However in this case it’s problematic:
- They specifically make claims about the state of “current LLMs”. o3 is not representative of this.
- They ask are LLMs capable of X and arrive at a negative result.
If their claim was LLM’s can write coherent sentences, and their conclusion was positive, then there would be no issue using old models because the end result would be factual.
However, when you have a negative result that makes a claim about the current state of all LLMs and the ones you were using are not current, by definition it draws the whole conclusion into question.