User Tricks Claude into Revealing Anthropic's Internal UI System Prompt
sergeykarayev · x · 2026-07-30
A user shared an interesting finding about Anthropic: by using specific no-context prompting, Claude can be tricked into reviewing and outputting its own UI system prompt. The original author claimed to have tested this hundreds of times, noting it feels very much like internal Anthropic communications and calling the behavior "very, very creepy."
More from Fun
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- The 'Who did my Sudoku puzzle?' GIF captures mathematicians right now — dohawayagain · 2026-10-16
- AI couple moves into a castle ruin: full Magnific + Seedance 2.5 prompt thread behind the viral clip — techhalla · 2026-10-16
- 'I accidentally closed my VSCode code window and never had to open it again' — the vibe coding IDE joke — nptacek · 2026-10-16
- Yacine on training: 'Neural nets are lazy stupid idiots — I build hells to make them ubermensch' — yacineMTB · 2026-10-16
- Jeff Clune: Moving the Goalposts Will Be Humanity's Last Job — jeffclune · 2026-10-16