Foundations
How to prompt and give context to AI, from first principles
Learn how to prompt from a place of first-principles understanding. A clear mental model of what's happening inside these tools, why they fail, and what to do about it. The single underlying idea is sophisticated approximation — every failure mode flows from it.
- A clear, transferable mental model of what LLMs actually do
- The ability to predict why a given prompt will fail or succeed
- A practiced habit of calibrated scepticism applied to AI output
- Specific countermeasures for each failure mode