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

Explore Claude 4, the AI redefining writing, coding, and workflows. See how it empowers users with advanced tools and ...

Faced with the news it was set to be replaced, the AI tool threatened to blackmail the engineer in charge by revealing their extramarital affair.

Learn how Claude 4’s advanced AI features make it a game-changer in writing, data analysis, and human-AI collaboration.

Malicious use is one thing, but there's also increased potential for Anthropic's new models going rogue. In the alignment section of Claude 4's system card, Anthropic reported a sinister discovery ...

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 ...

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 ...

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

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

The Anthropic CEO reportedly acknowledged that AI models confidently responding with untrue responses is a problem.