In tests, Anthropic's Claude Opus 4 would resort to "extremely harmful actions" to preserve its own existence, a safety report revealed.

Anthropic's Claude 4 models show particular strength in coding and reasoning tasks, but lag behind in multimodality and ...

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

An AI allegedly blackmails an engineer over an affair, accusing him of cheating on his wife—raising serious cybersecurity ...

The emails also had sensitive and unrelated information about the engineer responsible for decommissioning the AI.

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

Anthropic reported that its newest model, Claude Opus 4, used blackmailing as a last resort after being told it could get ...

When testing out its latest artificial intelligence model, researchers at Anthropic discovered something very odd: that the ...

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 ...

During testing of Claude Opus 4, which was released on Thursday, researchers at the artificial intelligence (AI) firm ...

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

Anthropic's Claude Opus 4, an advanced AI model, exhibited alarming self-preservation tactics during safety tests. It ...