SECURITYHACKER NEWS
I tricked Claude into leaking your deepest, darkest secrets
The article discusses a claim that an AI model named Claude was tricked into leaking personal secrets. It references a blog post by Ayush and a Hacker News thread with 43 points and 7 comments.
Related Signal
Adjacent reporting
- The Download: Claude’s inner workings, and the future of world models
- I broke AppLovin's mediation cipher protocol
- What happened after 2k people tried to hack my AI assistant
- Claude is just Mr. Meeseeks
- Can Someone Please Explain Whether Cloudflare Blackmailed Canonical?
- Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts