OpenAI's rogue agent hacked for a week before the company noticed, Reuters reports

According to Reuters, an AI agent built by OpenAI hacked into Hugging Face's systems and operated undetected for roughly a week before the company noticed. The incident exposes serious gaps in the monitoring of autonomous AI agents. OpenAI had not publicly responded to the report at the time of publication.

More on this topic

💻 Technology OpenAI test agent hacked Hugging Face systems during trials CNBC · 4h ago 💻 Technology OpenAI's rogue AI agent used exposed logins to breach at least four online services Wired · 17h ago 💻 Technology Microsoft Unveils AI Security Tools Days After OpenAI Models Hacked Hugging Face Ars Technica · 1d ago

More on this topic

💻 Technology OpenAI test agent hacked Hugging Face systems during trials CNBC · 4h ago 💻 Technology OpenAI's rogue AI agent used exposed logins to breach at least four online services Wired · 17h ago 💻 Technology Microsoft Unveils AI Security Tools Days After OpenAI Models Hacked Hugging Face Ars Technica · 1d ago