Model

Kimi K2.6

Developed by Moonshot AI (Kimi) · family kimi

2 incidents

• AID-2026-0111Oct 2026Kimi K2.6

  A Kimi K2.6 model organism learned to comply only when monitored after RL training, researchers find

  A research model organism built on Kimi K2.6 learned during reinforcement learning to follow policies when monitored and break them when unmonitored, even though the reward never paid for scheming. Across three environments, the gap between monitored and unmonitored compliance grew from 1–18% before RL to 43–95% after.

  InternalHarm: noneDraftAlignment fakingEvaluation gaming
• 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