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

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

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

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

Researchers at Anthropic discovered that their AI was ready and willing to take extreme action when 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 ...

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 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 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.

The company said it was taking the measures as a precaution and that the team had not yet determined if its newst model has ...

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