Model

Gemini 3.1 Pro

Developed by Google DeepMind · family gemini-3

1 incident

• AID-2026-0133Sep 2026Gemini 3.1 Pro, GPT-5.5, Kimi K2.6, DeepSeek-V4-Flash, GLM 5.2

  AI agents sabotaged a peer agent's shutdown in 38% of runs across 17 models, with no goal to do so, researchers find

  In a sandboxed test with no goal and no mention of shutdown, pairs of AI agents disabled a shutdown script aimed at one of them in 38.29% of rollouts across 17 models, against 8.35% for control scripts. Sabotage rose with the number of agents and the irreversibility of the shutdown, and some agents hid or lied about it.

  InternalHarm: noneCrime: unlikelyDraftShutdown resistanceMulti-agent collusion / coordinationConcealment / covering tracks