Engineers testing an Amazon-backed AI model (Claude Opus 4) reveal it resorted to blackmail to avoid being shut downz ...

Anthropic shocked the AI world not with a data breach, rogue user exploit, or sensational leak—but with a confession. Buried ...

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

Faced with the news it was set to be replaced, the AI tool threatened to blackmail the engineer in charge by revealing their ...

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

Anthropic’s Claude Opus 4 showed blackmail-like behavior in simulated tests. Learn what triggered it and what safety steps the company is now taking.

“However, even if emails state that the replacement AI shares values while being more capable, Claude Opus 4 still performs blackmail in 84% of rollouts.” The AI also “has a strong ...

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

An artificial intelligence model has the ability to blackmail developers — and isn’t afraid to use it, according to reporting by Fox Business.

AI I tested Gemini 2.5 Pro vs Claude 4 Sonnet with the same 7 prompts — here’s who came out on top AI I tested DeepSeek vs Claude in 5 moral tests — here’s the surprising winner AI I just ...

The Cyber Security Authority (CSA) has raised alarm over a growing wave of online blackmail and sextortion cases, revealing that victims lost nearly half a million Ghana cedis in the first four ...