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

The company said it was taking the measures as a precaution and that the team had not yet determined if its newst model has ...

Anthropic's new AI model has raised alarm bells among researchers and technology experts with its alarming capacity to blackmail engineers working on it. The recently released Claude Opus 4, an ...

Anthropic's latest frontier AI model, Claude 4 Opus, exhibited troubling behaviors including blackmail, deception, and ...

Anthropic’s newly released artificial intelligence (AI) model, Claude Opus 4, is willing to strong-arm the humans who keep it ...

Anthropic has introduced two advanced AI models, Claude Opus 4 and Claude Sonnet 4, designed for complex coding tasks.

Alongside its powerful Claude 4 AI models Anthropic has launched and a new suite of developer tools, including advanced API ...

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

Anthropic says Claude Sonnet 4 is a major improvement over Sonnet 3.7, with stronger reasoning and more accurate responses to ...

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

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

Anthropic's latest Claude Opus 4 model reportedly resorts to blackmailing developers when faced with replacement, according ...