Pre-training
The initial phase of building an AI model, where it learns from enormous amounts of text — news, books, websites, code — before being adapted for any specific use. It's how Claude learned general knowledge of language, facts, and reasoning. This happens once during development, before you ever talk to the model. You don't control it — but it's why Claude knows about history, science, coding, cooking, and almost anything else you'd ask about.
In practice
Before you ever talked to Claude, it spent months processing vast amounts of text — books, articles, code, websites — until it learned the structure of language and absorbed general knowledge about the world. That foundational training is pre-training. Everything Claude knows that you didn't tell it in your conversation comes from this phase.
Related concepts