LLM (Large Language Model)
Also known as: Large Language Model
Definition
A large language model (LLM) is an AI system trained on vast amounts of text to understand and generate human language, predicting likely continuations to answer questions, write, summarize, reason, and — when connected to tools — drive agentic workflows.
LLMs are the engines behind modern AI assistants. Anthropic's Claude and OpenAI's GPT models are LLMs. On their own they generate text; paired with tools, memory, and the ability to act, they become the reasoning core of agentic systems like Claude Cowork and the Codex app.
Understanding that an LLM is a prediction system — powerful but not infallible — is why review and human-in-the-loop checks remain part of any serious workflow.