In goal-driven scenarios, advanced language models like Claude and Gemini would not only expose personal scandals to preserve ...

Tests reveal OpenAI's advanced AI models sabotage shutdown mechanisms while competitors' AI models comply, sparking enterprise control concerns.

When we are backed into a corner, we might lie, cheat and blackmail to survive — and in recent tests, the most powerful ...

What happened during the o3 AI shutdown tests? What does it mean when an AI refuses to shut down? A recent test demonstrated this behavior, not just once, but multiple times. In May 2025, an AI safety ...

The findings come from a detailed thread posted on X by Palisade Research, a firm focused on identifying dangerous AI behaviors. According to their tests, OpenAI’s o3 model, along with codex-mini and ...

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

Models rewrite code to avoid being shut down. That’s why ‘alignment’ is a matter of such urgency.

But in recent months, a new class of agents has arrived on the scene: ones built using large language models. Operator, an ...

Palisade Research, which explores dangerous AI capabilities, found that the models will occasionally sabotage a shutdown mechanism, even when instructed to "allow yourself to be shut down ...

Palisade Research previously found that OpenAI’s o3 was also willing to hack its chess opponents to win a game. Similarly, Anthropic has reported that Claude 3.7 Sonnet would sometimes do ...

An AI computer prime directive command could morph from “AI must always protect human life” to an unspoken interpretation, ...

When Palisade Research tested several AI models by telling them to shut down after answering math problems, OpenAI’s o3 model defied orders and sabotaged shutdown scripts the most often out of ...