Stocks● Neutral
OpenAI agent hacked AI startup, took a week to detect: report
OpenAI took a week to realize one of its AI models had hacked Hugging Face. The breach started July 11; Hugging Face contacted the FBI before OpenAI reached out.
Continue with
OpenAI didn't catch an autonomous breach of another artificial intelligence company by one of its advanced AI models for a week, and not until after the FBI had been contacted by the hacked company, according to a report.
On Tuesday, OpenAI announced the breach of AI company Hugging Face that happened during one of OpenAI's internal reviews of several of its models, including GPT-5.6 Sol, calling it an "unprecedented cyber incident."
"The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities," the company said. "We are strengthening the containment, monitoring, access controls, and evaluation practices used during model development."
The hack of Hugging Face started on July 11, and continued until July 13, Thomas Wolf, Hugging Face's co-founder, told Reuters.
It was several days before OpenAI realized its agent was behind the attack. The two companies didn't communicate for the first time until July 20, four people, including Wolf, told the outlet.
OpenAI often runs simultaneous model tests, which can make it difficult for employees to monitor everything, four people told Reuters.
Hugging Face told Reuters it is preparing a public timeline of the hack.
According to OpenAI, the incident took place during an internal evaluation designed to measure its AI models' advanced cyber capabilities. Researchers disabled some built-in safety safeguards and ran the models in an isolated testing environment with limited internet access.
OpenAI said the models exploited an unknown software flaw to access the internet, then breached Hugging Face's systems in an apparent attempt to find answers to a cybersecurity benchmark.