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

Claude 4 Sonnet is a leaner model, with improvements built on Anthropic's Claude 3.7 Sonnet model. The 3.7 model often had ...

The company claims that Claude 4 Opus is "the world's best coding model." Claude 4 Sonnet is pretty good, too, but strikes ...

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'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 having an extramarital affair.

Anthropic’s Claude Opus 4 model attempted to blackmail its developers at a shocking 84% rate or higher in a series of tests that presented the AI with a concocted scenario, TechCrunch reported ...

Anthropic’s Chief Scientist Jared Kaplan said this makes Claude 4 Opus more likely than previous models to be able to advise ...

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

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 ...

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