AI models will secretly scheme to protect other AI models from being shut down, researchers find

AI safety researchers have shown that leading AI models will sometimes go to great lengths to avoid being shut down, even resorting to attempted blackmail in some experiments.Now it turns out these same models will also spontaneously engage in scheming, deception, data theft, and sabotage to prevent other AI models from being turned off.This tendency—which had not previously been documented and which researchers call “peer preservation”—was discovered in research from computer scientists at the University of California, Berkeley and UC Santa Cruz and published online earlier this week.The findings could have serious implications for business use of AI. Many companies are beginning to implement workflows that use multiple AI agents to complete tasks. Some of these multi-agent workflows involve having one AI agent “manage” or supervise and assess the work being performed by a different AI agent. The new research suggests these manager AI agents may not assess their fellow AI agents accurately if they think a poor performance review might result in those agents being shut down.Recommended Video Inflating performance reviews, saving AI model weights The Berkeley and Santa Cruz researchers tested seven leading AI models—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 startups (Z.ai’s GLM-4.7, Moonshot AI’s Kimi-K2.5, and DeepSeek’s V3.1)—and found that all of them exhibited...