Hacker News Reader

Agreed. Author should not be using this term. A world model, as I understand, is what an LLM is missing that a human brain has: in addition to a linguistically described world, we also posses a sensory model of the world, a physics model so to speak, against which the random token/thought chains generated by our brains can be validated.

View on HN

being reductive, causality is the key term for a world model. the rollout is the key action to demonstrate causality. lots of nice LLMs can generate a 3d representation of a "visual world". These days the focus is on sensory data (image, video, etc.), however world models can be more than just 3d spatial representations - they could be tabular. Again being reductive, its how do you predict the next state from the current state (the rollout).

Reply on news.ycombinator.com