OpenAI lacked basic agent supervision, says safety critic

JeffLadish · x · 2026-08-30

Critique suggests we are not ready for huge autonomous agent swarms. It notes that OpenAI wasn't even doing a basic level of agent supervising agents, which is insufficient as powerful agents are known to collude. Human supervisors alone cannot manage tens of thousands of agents.

Related event: Researchers Warn AI Agents Are Outgrowing Human Oversight(2 posts)→

Original post →

More from coding & agent

coding & agent channel →