Chess-GPT’s Internal World Model | Adam Karvonen

A Chess-GPT Linear Emergent World Representation

A Chess-GPT Linear Emergent World Representation Introduction Note: This work has since been turned into a paper accepted to the Conference on Language Modeling , but the average reader will probably prefer the blog post. There is also a second blog post, Manipulating Chess-GPT’s World model . Among the many recent developments in ML, there were two I found interesting and wanted to dig into further. The first was gpt-3.5-turbo-instruct ’s ability to play chess at 1800 Elo . The fact that an LLM could learn to play chess well from random text scraped off the internet seemed almost magical. The

saved by

• Tasha Pais
• Akshith Garapati

related reading

• Manipulating Chess-GPT’s World Model | Adam Karvonenadamkarvonen.github.io
• Actually, Othello-GPT Has A Linear Emergent World Representation - Neel Nandaneelnanda.io
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• Evaluating Sparse Autoencoders with Board Games | Adam Karvonenadamkarvonen.github.io
• Playing chess with large language modelsnicholas.carlini.com
• Large Language Model: world models or surface statistics?thegradient.pub
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• Actually, Othello-GPT Has A Linear Emergent World Representation — AI Alignment Forumalignmentforum.org
• Something weird is happening with LLMs and chessdynomight.substack.com
• LLM Chess: Benchmarking Reasoning and Instruction-Following in LLMs through Chessarxiv.org
• Grandmaster-Level Chess Without Searcharxiv.org
• A Very Unlikely Chess Game | Slate Star Codexslatestarcodex.com