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:
- It never disclosed the 10 websites its agents swarmed into;
- It never disclosed the German wiki incident;
- The critic believes OpenAI likely wouldn't have disclosed the HF incident either if HF hadn't announced it first.
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.
More from AGI Musings
- From 1786 scribbling machines to GenAI: 240 years of anti-machine arguments, same ending — sethjuarez · 2026-09-11
- Fields Medalist jokes he'll write yuri novels if AI solves all math problems — basedjensen · 2026-09-11
- AI safety debaters clash: is misaligned superintelligence or misuse of weak AI the bigger risk? — JacquesThibs · 2026-09-11
- New Essay 'Prompting Is Thinking Too' Argues Prompting Is a Form of Thinking — StePalminteri · 2026-09-11
- AI safety researcher muses on a gold rush into superalignment work — JacquesThibs · 2026-09-11
- Consciousness vs intelligence: researchers clash over whether AI can truly think — AndyMasley · 2026-09-11