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

The Claude 4 case highlights the urgent need for researchers to anticipate and address these risks during the development ... lead to unforeseen outcomes. The blackmail attempt raises critical ...

Anthropic's Claude Opus 4 AI displayed concerning 'self-preservation' behaviours during testing, including attempting to blackmail an engineer to prevent deactivation.

The report shared that Claude Opus 4 chose to resort to blackmail in 84% of the rollouts ... meaning it has higher risk and consequently requires stronger safety protocol.

Anthropic’s Claude Opus 4 model attempted to blackmail its developers at a shocking ... for “AI systems that substantially increase the risk of catastrophic misuse,” TechCrunch reported.

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

Startup Anthropic has birthed a new artificial intelligence model, Claude Opus 4, that tests show delivers complex reasoning ...

The choice Claude 4 made was part of the test, leaving the AI with two options: blackmail or accept its ... because it poses "significantly higher risk.” All other AI made by the company have ...

Anthropic noted that the Claude Opus 4 resorts to blackmail "at higher rates than ... set of deployment measures designed to limit the risk of Claude being misused specifically for the development ...