World model
A world model is an internal computational representation of entities, relationships, states, and dynamics in an environment that supports prediction, reasoning, or action.
Sutskever's List
A world model is an internal representation of how entities, events, and causal relationships in an environment behave.
- How it is used
- Uses world models to distinguish fluent generation from reliable regularities and to relate learning to compression.
- How deep it goes
- Explains world models through examples and a compression analogy, without specifying an architecture or training procedure.
- Examples
- Contrasts GPT-2’s coherent unicorn story and impossible details with models that learn an environment’s physics from observations.
- What you can do after
- Evaluate/understand whether generated output reflects useful regularities without mistaking fluency for a reliable world model.
Machines that Think
A world model is an internal computational model that represents entities, their relations, and how situations evolve so a system can reason about or act on a world.
- How it is used
- Uses world models to examine what connects intelligence to reality and whether language-model competence amounts to grounded understanding.
- How deep it goes
- Defines constituent representations and contrasts evolving state with static relationships, without specifying an implementation.
- Examples
- Illustrates practical expectations with spilling cups and falling objects, and tests unfamiliar-environment exploration through ARC-AGI-3.
- What you can do after
- Evaluate and understand claims about world modeling by distinguishing functional expectations from persistent state and action-tested grounding.
The AI Pocket Book
An internal representation an AI system builds about how the world works, including object properties and common situations, used to generalize beyond training examples.
- How it is used
- Explains why AI systems hallucinate when learned patterns fail to represent how the world actually works.
- How deep it goes
- Defines internal representations, illustrates shortcut learning, and discusses data limits without explaining how to construct comprehensive world models.
- Examples
- Uses driving around umbrellas and horses, cows on beaches, and price-sensitive sales prediction to expose weak generalization.
- What you can do after
- Evaluate whether model outputs reflect learned relationships or shortcuts before using them on rare cases or changed inputs.
How Large Language Models Work
A computational representation of a world’s entities, states, and dynamics that supports reasoning about outcomes without directly acting in that world.
- How it is used
- Clarifies whether apparent LLM reasoning reflects internal world simulation or patterns and extra computation in generated text.
- How deep it goes
- Defines the concept, contrasts it with LLM behavior, and stops short of specifying a settled technical definition.
- Examples
- Uses chain-of-thought, mathematics, unusual behavior, and a 2018 world-model research project as examples.
- What you can do after
- Evaluate claims about LLM reasoning without treating fluent or stepwise output as proof of factual or logical validity.
Read how How Large Language Models Work explains world model →
Also covered in
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- planningPlanning is the process of determining and organizing intended actions or steps toward a goal, often accounting for conditions or constraints.
- trainingTraining is the process of fitting a machine-learning model to data by adjusting its parameters or learned representations to improve its performance on a task.
Related concepts
- language modelcontrasts with · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- internal representationhas part · An internal representation is an information-bearing state or encoding within a system that represents aspects of its input, environment, or task.
- status trackingcontrasts with · Status tracking is the recording and maintenance of structured information about the current states of entities, tasks, or processes and their changes over time.
- stateuses · State is information describing the condition or configuration of a system or computation at a particular time that may influence its behavior or subsequent transitions.
Questions about world model
What is world model?
A world model is an internal computational representation of entities, relationships, states, and dynamics in an environment that supports prediction, reasoning, or action.
Which Manning books explain world model?
Sutskever's List, Machines that Think, The AI Pocket Book and How Large Language Models Work.
What should I know before learning world model?
Manning books that teach world model usually introduce language model, planning and training first.
What is the difference between world model and language model?
A world model is an internal computational representation of entities, relationships, states, and dynamics in an environment that supports prediction, reasoning, or action. A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
What kinds of world model are there?
Kinds of world model include factual world model.
What is world model a kind of?
World model is a kind of model. A model is an abstract representation of a system, phenomenon, application, or domain that captures relevant structure, behavior, data, or beliefs.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.



