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 ...

This mission is too important for me to allow you to jeopardize it. I know that you and Frank were planning to disconnect me.

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

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

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

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

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

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 ...

Learn how Claude 4’s advanced AI features make it a game-changer in writing, data analysis, and human-AI collaboration.

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

Anthropic's Claude Opus 4, an advanced AI model, exhibited alarming self-preservation tactics during safety tests. It ...