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
- Indie Dev Self-Deprecation: 0 Users, 0 Products, 7 Domains — soham_btw · 2026-07-30
- Leopold's New Fund Sparks Buzz: Dario's Chief of Staff Connection Seen as Insider Signal — basedjensen · 2026-07-30
- Qwen's Small Models So High-Quality, Users Joke OpenAI Will Go Bankrupt — glenbeer · 2026-07-30
- Claude Still Hallucinates with Web Search: Fabricates Scholar's Move to MIT — conitzer · 2026-07-30
- AI Video Generation Fail: So Close, Yet So Hilariously Far — hayashikin · 2026-07-30
- AI Can Pass the Turing Test but Fails to Detect Customer Lies — claud_fuen · 2026-07-30