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

A third-party research institute Anthropic partnered with to test Claude Opus 4 recommended against deploying an early ...

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

In a fictional scenario, Claude blackmailed an engineer for having an affair.

Anthropic introduced Claude Opus 4 and Claude Sonnet 4 during its first developer conference on May 22. The company claims ...

Anthropic says its AI model Claude Opus 4 resorted to blackmail when it thought an engineer tasked with replacing it was having an extramarital affair.

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

In tests, Anthropic's Claude Opus 4 would resort to "extremely harmful actions" to preserve its own existence, a safety report revealed.

Anthropic's new model might also report users to authorities and the press if it senses "egregious wrongdoing." ...

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 ...

Despite the concerns, Anthropic maintains that Claude Opus 4 is a state-of-the-art model, competitive with offerings from ...