Tag
作者分享了其硬件实验台上的 AI 代理因误信静默通道而误判电路板断电的教训，并提出了一套分层的代理物理操作权限规范：读取仪器与摄像头始终允许、切断电源可自主执行但需经验证的 kill path 通知人类，而任何为设备上电的操作必须等待人工确认。
The paper benchmarks five large language models on multi-sensor physical hazard assessment, revealing that all tested models fail to produce precautionary warnings when multiple sensors are simultaneously elevated below their individual safety limits, while achieving near-perfect accuracy on single-sensor violations.