← Back to events
ActiveAI

Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out

Photo: Hacker News

What happened

We watched almost 17k sessions across different types of personas, with 1,163 prompt variations, 75 repositories and 3 coding agents (Claude Code, Codex, Cursor) actually implementing the solutions instead of just recommending one.

Summary assembled by rule from the sources below

Why it's spreading

Sources