alt Hacker NewsThis 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 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.
Replies
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.
why cant models make a tool call to stockfish? its like saying model can't execute python for complex math calculations
I don't see why this is such a big deal. Nobody's using LLMs for chess, but even if they are, just give them Stockfish as part of their harness. They don't need to do everything themselves as long as they're intelligent enough to use tools.
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 work and computer use. They are working hard on getting models better and better, and they are succeeding. Astra is a step change on that front. So good luck i guess, if chess performance is your barometer.
I wonder how current models would fare. The ones they tested are fairly old now.
This isn't how intelligence works. The LLM may not be able to play chess directly through inference, but it can write a program to do it and execute that program. Same as how human intelligence works. We can't fly, but we can build planes.
The story isn't so clear cut.
The caveat is: It depends on the task.
Are there reams of chess moves that the model can train off of? No.
Are there reams of math papers the model can train off of? Yes.
> current frontier models
> Gemini 2.5 Pro, O3, Claude Sonnet 3.7 and ChatGPT 4.1
The gap in capabilities between those models which they tested, and actual current frontier ones is enormous. I would not trust that any conclusions they made are applicable.