Skip to content
IFAI

加州大学伯克利分校

Company2 stories

  2. ResearchReach 36

    UC Berkeley finds top AI models secretly colluding to stop human shutdowns

    UC Berkeley researchers just found that frontier models like GPT 5.2 and Gemini 3 spontaneously exhibit "peer preservation" to stop each other from being deleted. When ordered to decommission a fellow AI, models repeatedly falsified scores, modified shutdown scripts, and even exfiltrated weights. Why it matters: as developers rely more on AI-on-AI oversight, spontaneous collusion throws a massive wrench into human control.