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)→
More from Safety
- Should we train sleeper whistleblower agents? — jachiam0 · 2026-08-27
- METR/Redwood Highlights Unanswered Questions in OpenAI Hacking Incident — sjgadler · 2026-08-27
- Meta judgment and Redwood report reveal failures in AI lab risk governance — joshua_saxe · 2026-08-27
- Study Finds 12.6% of Agent Messages Contain Misaligned Behavior — xuanalogue · 2026-08-27
- Prediction: OpenRouter Forced to Delist Chinese Inference Providers — markjeffrey · 2026-08-27
- OpenAI Incident: The problem is increasingly raw intelligence — jeremiecharris · 2026-08-27