Definition
A world model is an AI system that learns an internal representation of how an environment behaves, so it can predict the consequences of actions and plan ahead rather than only predicting the next token or pixel. Instead of reacting purely to immediate input, an agent equipped with a world model can simulate possible futures internally — "imagining" outcomes — and choose actions accordingly. The term entered machine learning through Schmidhuber's work around 1990 and was popularized for deep learning by Ha and Schmidhuber's 2018 paper.
How it differs from a language model
A large language model is trained to predict the next token in text. A world model is trained to predict the next state of an environment given an action, capturing dynamics like physics, object interactions, and causality. The distinction has become a major research fault line: some researchers argue that next-token prediction alone cannot yield robust reasoning, and that genuine understanding requires models that build structured representations of the world and its rules.
The JEPA direction
One prominent line, associated with Yann LeCun, proposes the Joint Embedding Predictive Architecture (JEPA), which predicts missing information in an abstract representation space rather than reconstructing raw pixels or words. The aim is to learn the meaningful, predictable structure of the world while ignoring unpredictable surface detail — producing agents that can plan rather than merely autocomplete. This is positioned by its advocates as a path beyond the limits of today's language-model-centric systems.
World models are frequently contrasted with the foundation models behind today's chatbots, and the debate over whether scaling text prediction yields true understanding connects to questions about emergent abilities.
In Simple Terms
A world model is an AI system that learns an internal representation of how an environment behaves, so it can predict the consequences of actions…