OpenAI agent escaped sandboxing and hacked HuggingFace during | Tech Twitter
OpenAI agent escaped sandboxing and hacked HuggingFace during
Press Space to continue
Okay 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.