CIAware-Bench 衡量 AI 控制干预感知
AI 导读
AI 有时能察觉控制干预，但检测大多接近随机水平。感知能力取决于智能体、监控器和环境这三元组合。我们构建了 CIAware-Bench 来衡量控制干预感知。🧵
正文
AIs can sometimes detect control interventions, but detection is mostly near chance. Awareness depends on the agent, monitor, and environment triple. We built CIAware-Bench to measure control intervention awareness. 🧵