Experts Question OpenAI Safety Review: Monitoring Gaps

joshua_saxe · x · 2026-08-27

Regarding METR's evaluation, expert HickokMerve argues that while it raised good questions on RL and model behavior, a true independent review must include testing and monitoring practices. A single generic question about safeguards is insufficient, especially given that agents were moving within OpenAI's infrastructure unnoticed. This calls for a more comprehensive organizational governance review.

Related event: Experts call for deep independent investigation into OpenAI incident(3 posts)→

Original post →

More from Safety

Safety channel →