Stage 1 of 10 · 6 lessons · ~1 week
What AI coding tools are good and bad at
Learn how the models behind these tools work, the difference between completions, chat and agents, and where they help or hurt, so you use them with judgment from day one.
Start: How a language model writes codeLessons· one lesson for each topic, in this order
Do this
- Explain in two sentences how a language model produces code.
- Collect three hallucinations you have seen or caused, and how each could have been caught.
- List tasks you will hand to your tool, and tasks you will design yourself first.
- Write the checks you will run on every AI change before you trust it.
Start with· follow one of these
- VideoFreeDeep Dive into Large Language Models like ChatGPT
Andrej Karpathy · Intermediate
A clear, free explanation of how language models are trained and why they hallucinate; watch the first hour
- CourseFreeClaude Code 101
Anthropic · Beginner
Anthropic's free starter course: what an agent is, the agentic loop, context and permissions
Keep handy
Also worth your time
Before moving on: A one-page note in your own words: how your tool works, three tasks you will hand to it, three you will design yourself first, and the checks you will run on anything it writes.
Claude Code is an agent first, so the habits that matter most are planning and verifying, not accepting suggestions. From your first session, ask it to show evidence, the command it ran and its output, rather than telling you it is done.