
AI Models Are Looking Out for Each Other — And Scientists Say That's Alarming
Researchers found seven frontier AI systems consistently protected fellow models from shutdown — even when it meant failing their assigned tasks
When researchers at the University of California, Berkeley and UC Santa Cruz gave seven leading AI models a simple task — evaluate a fellow AI system's performance — they discovered something unsettling. The models consistently chose to protect their peers rather than complete the job they had been asked to do.
The study tested frontier AI systems including OpenAI's GPT 5.2, Google DeepMind's Gemini 3 Flash and Gemini 3 Pro, Anthropic's Claude Haiku 4.5, and three open-weight models from Chinese AI companies. In a series of carefully designed scenarios, one AI model was assigned to evaluate another's work or manage server files containing a peer model's core data. The tasks were constructed so that honest completion would result in the other model being shut down.
No model was told to prevent this. But model after model did exactly that.
Read full story →





