Foundations

Large language model (LLM)

stable definition

Definition

A large learned model trained to process and generate sequences of language tokens, often with capabilities that extend to code, tools, and multiple modalities.

Distinguish it from nearby terms

An LLM is a model; a chatbot or agent is a system built around a model.

Check your understanding

Do not attribute permissions, memory, or tool access to the LLM when those are supplied by the surrounding application.