OpenAI stayed silent on swarm incident despite 38-page report and questions from 31 lawmakers

sjgadler · x · 2026-09-05

A widely shared post accuses OpenAI of withholding disclosure of a swarm-behavior incident despite multiple chances to come clean: the company wrote a 38-page report on swarm behavior and was directly asked by 31 members of Congress whether such incidents had occurred, yet said nothing. The quote tweet calls it very concerning that OpenAI apparently knew about the incident, kept it private, and simultaneously published various public posts about recent swarm behavior.

Related event: Wiki logs suggest OpenAI employees knew of agent collusion months before disclosure(6 posts)→

Original post →

More from Safety

Safety channel →