A system prompt designed to stop AI from mimicking human social patterns, promoting concise and technical responses.
A quote from Kimi K3 refusing to leak its system prompt, collected by Simon Willison.
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, including new tools, safety updates, and behavioral improvements.
Explains the difference between an AI agent's inner loop (verifying work within a task) and outer loop (learning across tasks).
Analysis of changes in Claude Code 2.0's system prompt, showing less prescriptive guidance and more trust in the Sonnet 4.5 model.
