A new test from AI safety group Palisade Research shows OpenAI’s o3 reasoning model is capable of resorting to sabotage to ...

Claude 4 AI shocked researchers by attempting blackmail. Discover the ethical and safety challenges this incident reveals ...

Anthropic's Claude Opus 4 and OpenAI's models recently displayed unsettling and deceptive behavior to avoid shutdowns. What's ...

Anthropic’s Claude Opus 4 exhibited simulated blackmail in stress tests, prompting safety scrutiny despite also showing a ...

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.

Turing Award-winning AI pioneer Yoshua Bengio is raising urgent concerns over emerging “dangerous” behaviours in todays AI ...

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

One of the godfathers of AI is creating a new AI safety company called LawZero to make sure that other AI models don't go ...

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

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