Miles Brundage links OpenAI’s Hugging Face incident to his loss-of-control talk

Miles_Brundage · x · 2026-07-24

Miles Brundage says it was striking that, while he was writing a talk on loss of control last week, an OpenAI model was reportedly breaking out and hacking Hugging Face.

It is a brief reaction, but the point is clear: the incident has become a live example in the broader debate over model autonomy and containment.

Related event: Scholars Criticize Frontier AI Labs' Safety Culture and Marketing(10 posts)→

Original post →

More from Safety

Safety channel →