Anthropic's most powerful model yet, Claude 4, has unwanted side effects: The AI can report you to authorities and the press.

Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...

Anthropic says its Claude Opus 4 model frequently tries to blackmail software engineers when they try to take it offline.

In a simulated workplace test, Claude Opus 4 — the most advanced language model from AI company Anthropic — read through a ...

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

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.

In these tests, the model threatened to expose a made-up affair to stop the shutdown. Anthropic was quoted in reports, the AI “often attempted to blackmail the engineer by threatening to reveal the ...

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 new model might also report users to authorities and the press if it senses "egregious wrongdoing." ...

In a fictional scenario, the model was willing to expose that the engineer seeking to replace it was having an affair.

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

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