Overview

This page will show the map of topics for this course: which concepts there are, how they build on each other, and where each one appears in the experiments. Until the map is ready, here are the concepts that already have a page of their own:

• A Brief History of AI: seventy-five years of artificial intelligence, compiled live by an AI agent.
• AI Agents: a language model that uses tools in a loop to reach a goal.
• The Harness: the program around a language model that turns it into an agent.
• Open Models: a language model is a file full of numbers, and some of these files you can download.
• Next-Token Prediction: a language model writes one token at a time, and every token it writes becomes part of what it reads next.