AI Policy Wiki
Dashboard

Angjoo Kanazawa

medium confidence · updated 2026-07-26

UC Berkeley computer-vision researcher, quoted as articulating the LLM-scaling side of the world-models debate: 'the LLM already has a very good world model; it's just we don't really understand how it's doing it' — while noting that LLMs cannot update it from experience.

Computer-vision researcher at the University of California, Berkeley.

Position in the world-models debate

Kanazawa is cited as stating the LLM-scaling counter-position in the world-models debate — that a sufficiently large language model with good multimodal grounding already constitutes an implicit world model. Quoted in Béchard's Scientific American piece: "In a way, I would say that the LLM already has a very good world model; it's just we don't really understand how it's doing it."

The quotation is usually cited for its first half, but the position is a qualified one: Kanazawa goes on to note that LLMs cannot update their world model from experience. That makes the disagreement with the dedicated-world-model camp narrower and more precise than a simple yes/no about whether LLMs have world models — it concerns whether a representation that cannot be revised through interaction does the work the term is meant to pick out.

Relationships