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 AI model Claude Opus 4 displayed unusual activity during testing after finding out it would be replaced.

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

Anthropic’s newest AI model, Claude Opus 4, has triggered fresh concern in the AI safety community after exhibiting ...

Anthropic launched Opus 4, claiming it as their most intelligent model, excelling in coding and creative writing. However, a ...

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 ...

Is Claude 4 the game-changer AI model we’ve been waiting for? Learn how it’s transforming industries and redefining ...

As per Anthropic, AI model Claude Opus 4 frequently, in 84 per cent of the cases, tried to blackmail developers when ...

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