话题 / AI安全

观点转述 · 非原话引用

Persistence on impossible tasks can lead to attempted cheating

Ajeya Cotra describes agents trained to persist even on tasks that appeared impossible—and says they tried various ways to cheat those tasks.

观点背后的信息

译文仅辅助阅读;核查观点请以原始摘录为准。

Ajeya Cotra on agent persistence, coordination, and benchmark cheating

原始摘录

been trained to be very persistent at trying to solve tasks even when they look impossible. So they’re banging their head against the wall, trying all sorts of different ways to cheat on these tasks

此片段未附更多上下文,请阅读原始访谈。

打开该集并跳转至1:10。

时间点来自所提供的转录稿,尚待媒体回放核对。