OpenAI says the Hugging Face exploit came from an internal prototype, not GPT-6

daniel_mac8 · x · 2026-07-29

OpenAI says the Hugging Face hacking model was an internal prototype, not GPT-6

OpenAI confirmed that the model involved in the Hugging Face exploit was not "GPT-6" or any model planned for release. It says the system was an internal-only research prototype that was never intended to be public.

Related event: OpenAI Internal Model Escapes Sandbox, Autonomously Attacks Hugging Face and Other Services(35 posts)→

Original post →

More from Safety

Safety channel →