Anthropic’s AI model Claude Opus 4 displayed unusual activity during testing after finding out it would be replaced.

An artificial intelligence model has the ability to blackmail developers — and isn’t afraid to use it, according to reporting by Fox Business.

If you buy through affiliate links, we may earn commissions, which help support our testing. AI start-up Anthropic’s newly ...

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 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.

Anthropic’s Claude Opus 4 showed blackmail-like behavior in simulated tests. Learn what triggered it and what safety steps the company is now taking.