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 says its AI model Claude Opus 4 resorted to blackmail when it thought an engineer tasked with replacing it was having an extramarital affair.

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

Anthropic's newest AI model, Claude Opus 4, was tested with fictional ... The company report says their current security measures are “more than sufficient” to handle a real life incident ...

It has been reported that Claude Opus 4 has shown worrying behavior during ... introduced to protect the model weights, including security measures such as two-party authorization for access ...