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

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 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...

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 ...

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

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's Claude AI tried to blackmail engineers during safety tests, threatening to expose personal info if shut down ...

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 ...

A third-party research institute Anthropic partnered with to test Claude Opus 4 recommended against deploying an early ...

A universal jailbreak for bypassing AI chatbot safety features has been uncovered and is raising many concerns.