Collection of Leaked System Prompts from Mainstream AI Products
asgeirtj · github · 2026-07-05
This repository curates and continuously updates extracted system prompts from major AI products. It covers Anthropic (Fable 5, Opus 4.8, Claude Code/Design), OpenAI (ChatGPT 5.5, Codex), Google (Gemini 3.5 Flash, etc.), xAI Grok, and tools like Cursor, Copilot, and Perplexity. The project has nearly 50,000 stars.
More from Safety
- Researcher questions AI safety eval firm, citing 'blatantly sloppy' security and monitoring — Kyrannio · 2026-09-11
- Class action accuses Anthropic of overselling Claude subscriptions with deceptive usage multipliers — The Decoder · 2026-09-11
- MD shows buying lab media requires background checks, calling AI bioweapon doom scenarios implausible — Ghost_Pilot_MD · 2026-09-11
- Spotify chatbot withstands 2023-era jailbreaks but happily writes song code — AaronBergman18 · 2026-09-11
- A 99%-real doctored photo fools detectors: the earring problem in visual forensics — henkvaness · 2026-09-11
- Fields Medalist founds Mathematical AI Safety Institute to prove AI safe like cryptography — The Decoder · 2026-09-11