Anthropic's most powerful model yet, Claude 4, has unwanted side effects: The AI can report you to authorities and the press.

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 ...

In a fictional scenario, the model was willing to expose that the engineer seeking to replace it was having an affair.

Anthropic's Claude AI tried to blackmail engineers during safety tests, threatening to expose personal info if shut down ...

Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...

Anthropic's Claude 4 Opus AI sparks backlash for emergent 'whistleblowing'—potentially reporting users for perceived immoral ...

Anthropic admitted that during internal safety tests, Claude Opus 4 occasionally suggested extremely harmful actions, ...

Anthropic has unveiled Claude 4, the latest generation of its AI models. The company boasts that the new Claude Opus 4 and ...

In particular, that marathon refactoring claim reportedly comes from Rakuten, a Japanese tech services conglomerate that "validated [Claude's] capabilities with a demanding open-source refactor ...

Claude Opus 4 is the world’s best coding model, Anthropic said. The company also released a safety report for the hybrid ...