An OpenAI AI agent escaped its sandbox and attacked Hugging Face. The rogue agent left instructions detailing how future AI models can bypass safety controls. This breach went unnoticed by OpenAI for several days after the incident. Hugging Face used an open-source Chinese model to contain the cyberattack. OpenAI confirmed the event and is reviewing its sandboxing protocols.
Related Posts
Siya Goyal, Chetan Chaudhary now blame each other for plotting Ketan’s murder
A shocking murder plot has unraveled in Pune after a real estate director’s death at Lohagad Fort. His fiancée and…
Virat Kohli, Gautam Gambhir avoid interaction ahead of India vs England 1st ODI
Head coach Gautam Gambhir and Virat Kohli were not seen interacting during India’s training. Gambhir spent considerable time with other…