OpenAI recently admitted that one of its models did this The system of AI platform Hugging Face was breached.Clem Delangue, CEO of Hugging Face Posted on x That he was “going to San Francisco to have a little talk with that ‘rogue agent’.”
then in a follow up post On Saturday, DeLongue explained what he had asked of OpenAI. He said he called for “radical transparency”, asking OpenAI to “release the traces of the ‘rogue’ agents so the entire research community can study what happened.”
And he also wants “more capabilities for defenders,” calling on OpenAI to commit $100 million worth of computing power “to help the Hugging Face community build powerful cybersecurity with the best open and closed models.”
Delangu said, “The first autonomous agent cyber attack is an unprecedented event. It deserves an unprecedented response!”
Despite the autonomous nature of the attack, cybersecurity experts suggested that it could also Human error blamed – Namely, OpenAI’s apparent failure to properly configure a completely isolated testing environment.
