本研究方向将开展欺骗性对齐的概念研究,设计密谋行为倾向评估和蜜罐测试。项目方向示例:
London
I am a research scientist on the AGI Safety & Alignment team at Google DeepMind. I focus on deceptive alignment and AI control, particularly [scheming propensity evaluations](https://arxiv.org/abs/2605.29729). My past research includes dangerous capability evals, power-seeking incentives, specification gaming, and avoiding side effects.
我会与学员一起讨论研究想法。