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, an advanced AI model, exhibited alarming self-preservation tactics during safety tests. 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 ...

California-based AI company Anthropic just announced the new Claude 4 models. These are Claude Opus 4 and Claude Sonnet 4.

During a podcast taping, Google co-founder Sergey Brin said that threatening an AI model makes it work best. That seems like ...

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 ...

Skynet might be on the horizon. A new AI system will resort to blackmail if it’s threatened to be replaced or shut down.

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