What is a world model?

An AI’s “world model” can be thought of as a map or description of reality (or a subset of reality) that the AI uses to navigate the world, predict the future, or make decisions.

During training, neural networks pick up patterns present in their training data and compress them into a set of interconnected rules and algorithms stored in their neural weights. The resulting collection is equivalent to a neural network's world model.

The difference between narrow AI and general AI (AGI) can be defined by the scope of their world model. An AGI would have a world model general and complete enough to allow it to accomplish a wide range of tasks, solve problems not found in its training data, etc., while narrow AI can only act effectively on a specific subset of reality.