News

AI model threatened to blackmail engineer over affair when told it was being replaced: safety report
Anthropic’s Claude Opus 4 model attempted to blackmail its developers at a shocking 84% rate or higher in a series of tests that presented the AI with a concocted scenario, TechCrunch reported ...
Interesting Engineering11h
Anthropic's most powerful AI tried blackmailing engineers to avoid shutdown
Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...