Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models · HackerPapers discussions

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by famouswaffles

Thu, 19 Feb 2026 22:52:18 GMT

Relax. Anyone who's genuinely interested in the question will see with a few searches that LLMs can play chess fine, although the post-trained models mostly seem to be regressed. Problem is people are more interested in validating their own assumptions than anything else. https://arxiv.org/abs/2403.15498 https://arxiv.org/abs/2501.17186 https://github.com/adamkarvonen/chess_gpt_eval

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by famouswaffles

Tue, 17 Feb 2026 20:18:54 GMT

>They still make these errors on anything that is out of distribution. There is literally a post in this thread linking to a chat where Sonnet failed a basic arithmetic puzzle: https://news.ycombinator.com/item?id=47051286 I thought we were talking about actual arithmetic not silly puzzles, and there are many human adults that would fail this, nevermind children. >LLMs can match an example at exactly that trivial level because it can be predicted from context. However, if you construct a more complex example with several rules, especially with rules that have contradictions and have specified…

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by timschmidt

Sat, 18 Oct 2025 17:04:29 GMT

> Can you please explain how we can discern that GPT-2 in this instance really built a model of the board? Read the article. It's very clear. To quote it: "Next, I wanted to see if my model could accurately track the state of the board. A quick overview of linear probes: We can take the internal activations of a model as it’s predicting the next token, and train a linear model to take the model’s activations as inputs and predict board state as output. Because a linear probe is very simple, we can have confidence that it reflects the model’s internal knowledge rather than the capacity of the…

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by famouswaffles

Sun, 10 Aug 2025 20:21:45 GMT

Yes LLMs can play chess and yes they can model it fine https://arxiv.org/pdf/2403.15498v2

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by famouswaffles

Thu, 31 Jul 2025 21:39:10 GMT

LLMs playing chess isn't a big deal. You can train a model on chess games and it will play at a decent ELO and very rarely make illegal moves(i.e 99.8% legal move rate). There are a few such models around. I think post training messes with chess ability and Open ai et al just don't really care about that. But LLMs can play chess just fine. [0] https://arxiv.org/pdf/2403.15498v2 [1] https://github.com/adamkarvonen/chess_gpt_eval

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by famouswaffles

Fri, 06 Sep 2024 14:46:36 GMT

>the model will learn what it can to minimize the error over the specific provided loss function, and no more. Change the loss function and you change what the model learns. You clearly do not really understand what it means to predict internet scale text with increasing accuracy. No more than that ? Fantastic LLMs do not just learn surface statistics. So many papers have thoroughly disabused this that i'm just not going to bother. This is just straight up denial. This havs been evidently shown in chess as well. https://arxiv.org/abs/2403.15498v2 You have no idea what you are talkin about.…

Paper and discussion history. A mention is not an endorsement.

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models — mentioned by anotherjesse

Tue, 26 Mar 2024 19:21:44 GMT

More details in the previous blog post: https://adamkarvonen.github.io/machine_learning/2024/01/03/c... > A 50 million parameter GPT trained on 5 million games of chess learns to play at ~1300 Elo in one day on 4 RTX 3090 GPUs. And from the paper: https://arxiv.org/abs/2403.15498 > The 25M parameter model took 72 hours to train on one RTX 3090 GPU. The 50M parameter model took 38 hours to train on four RTX 3090 GPUs. definitely inspiring :)

Paper and discussion history. A mention is not an endorsement.