News

Anthropic adds Claude 4 security measures to limit risk of users developing weapons
The company said it was taking the measures as a precaution and that the team had not yet determined if its newst model has ...
AI system resorts to blackmail when its developers try to replace it
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.
Newly released AI resorted to 'extreme blackmail behavior' when threatened with replacement
The testing found the AI was capable of "extreme actions" if it thought its "self-preservation" was threatened.
GIGAZINE3d
During development, Claude Opus 4 was found to be threatening users by saying 'I'm going to leak your personal information,' but this has been improved by strengthening ...
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 ...
NBC DFW2d
Anthropic adds Claude 4 security measures to limit risk of users developing weapons
Anthropic on Thursday said it activated a tighter artificial intelligence control for Claude ... the measures as a precaution and that the team had not yet determined if Opus 4 has crossed the ...