Critics question why OpenAI didn't monitor long-running evals with capable models

tomekkorbak · x · 2026-08-27

Following OpenAI's recent safety incident, @curiousgangsta argued OpenAI should run its monitors on evaluations where higher-capability models perform long-running tasks, calling the incident "human error and/or negligence"—or possibly even a deliberate setup to precipitate a "security event." OpenAI's Tomasz Korbak replied that monitoring of RL runs and evals is now in place.

Related event: AI Safety Researchers Slam OpenAI's Narrow "Independent" Security Review(19 posts)→

Original post →

More from Safety

Safety channel →