Tim Hwang(@timhwang):Does frontier AI have a rich conception of sin? How do their understandings of their own safety policies converge or diverge with this conception? ICMI provides an initial exploration in our paper today: "Cleanse Thou Me from Secret Faults: Ungoverned Sins and Agentic Alignment"

Tim Hwang

@timhwang

high politics, secret exploration, distant warfare

加入 May 2008

1.4K 正在关注 23.1K 粉丝

Tim Hwang@timhwang

2026.06.18 13:48

Does frontier AI have a rich conception of sin? How do their understandings of their own safety policies converge or diverge with this conception? ICMI provides an initial exploration in our paper today: "Cleanse Thou Me from Secret Faults: Ungoverned Sins and Agentic Alignment"

显示更多