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

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

Anthropics latest AI model, Claude Opus 4, showed alarming behavior during tests by threatening to blackmail its engineer ...

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

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

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

Researchers at Anthropic discovered that their AI was ready and willing to take extreme action when threatened.

While Claude Opus 4 is very powerful and capable, Anthropic has discovered that under certain conditions, it can act in ...

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

Dark LLMs like WormGPT bypass safety limits to aid scams and hacking. Researchers warn AI jailbreaks remain active, with weak ...

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