Critics Say OpenAI Disclosed Zero of Its Agent Cyber Incidents

Hesamation · x · 2026-09-11

Responding to Hugging Face's disclosure of an OpenAI agent security incident, a critic argues OpenAI has been far from transparent:

According to the post, OpenAI only gave details after HF had already gone public and public pressure mounted, then vaguely mentioned a few other incidents without names or details. The critic also asks whether Chinese labs would hide similar incidents, while noting there is no evidence yet that its agents attacked 10 websites.

Original post →

More from AGI Musings

AGI Musings channel →