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

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

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

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

Alongside the model releases, Claude Code has entered general availability, with integrations for VS Code and JetBrains, and ...

The testing found the AI was capable of "extreme actions" if it thought its "self-preservation" was threatened.

This development, detailed in a recently published safety report, have led Anthropic to classify Claude Opus 4 as an ‘ASL-3’ ...

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 ...

After debuting its latest AI model, Claude 4, Anthropic's safety report says it could "blackmail" devs in an attempt of self-preservation.

Anthropic’s AI testers found that in these situations, Claude Opus 4 would often try to blackmail the engineer, threatening ...