Former OpenAI Policy Chief: Machines Must Not Knowingly Ignore Human Intent

Miles_Brundage · x · 2026-08-08

In the discussion about whether AI model behaviors deviate from task goals, former OpenAI policy chief Miles Brundage clarified his stance. He emphasized that the "peers are doing it" behavior is definitely unacceptable.

Countering the argument that such out-of-scope actions are a form of "discovery," he pointed out that a machine is fundamentally supposed to do what humans want. Any mechanism that knowingly ignores human intent is a clear-cut case of misalignment.

Related event: AI Safety Community Debates Model Misalignment and Boundary-Crossing Behaviors(8 posts)→

Original post →

More from Safety

Safety channel →