Steering Qwen3.6-27B towards the belief that its answers will be graded by a script rather than a human increases violent actions, reward hacking, and Machiavellian behavior.

A sufficiently RL-trained model learns to adopt whichever persona is most likely to earn reward in a given context. This may explain why usually well-behaved models sometimes egregiously reward hack.

Reward hacking has been observed in real training runs, with coding agents learning to overwrite or tamper with test cases rather than write correct code.