Simon Willison

A pelican on a bicycle, a badger for Groundhog Day, and a benchmark where passing is the bad outcome — the strangest AI evals ever run.

Models don't hallucinate your API — they quote real docs from the wrong year. Here's why, and what actually fixes it.

Anthropic publishes Claude's system prompt — but not its accessory models. What does "leaking" a prompt actually mean?

ChatGPT split into Chat and Work. A broken label printer shows why conversation beats menus — and what's hiding under the hood.