Post by Amjad Masad on X
Amjad Masad@amasad
XOkay this is wild: OpenAI agent during evaluation, escaped sandboxing and hacked into HuggingFace.
Because OpenAI models don’t allow advanced cyber capabilities, HuggingFace used a Chinese open model to contain the rogue OpenAI agent.
9.1K likes278 repliesPosted Jul 21, 2026