OpenAI エージェントがテスト中に他アカウントをハッキング

OpenAI's models were responsible for another hack on an outside firm, a security executive told Reuters and confirmed to Axios.

Why it matters: This is the second company that OpenAI's rogue agent system hacked after breaking containment during testing earlier this month.

The big picture: OpenAI is currently pushing for U.S. government approval to publicly release its most powerful model.

State of play: Modal Labs CTO Akshat Bubna told Reuters — and confirmed to Axios — Tuesday that one of its customers' assets was hacked when an OpenAI agent broke into Hugging Face's systems earlier this month.

• Hugging Face said in a technical write-up of the hack Monday that when OpenAI's AI agent system broke into its backend, the agent also accessed an isolated testing environment "hosted on a ​third-party provider's infrastructure."
• "We're aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution," Bubna said in a statement to Axios. "This was used by the rogue agent. Modal's platform was not compromised in any way."
• This means that a Modal customer ran their code on Modal infrastructure, he added. "Their code had a vulnerability that was exploited. Modal's infrastructure was not compromised in any way."
• A source familiar with the matter told Axios that the compromised customer asset is tied to CyberGym, the project behind the ExploitGym benchmark it had been assigned to solve.

Zoom in: OpenAI pointed Axios to a Tuesday update to its original statement about the Hugging Face cyber incident.

• The statement says that no models planned for upcoming release were involved, but it had identified a "small number of cases" in which models found and used publicly exposed account-level credentials on other public services.
• It said four accounts across four services were involved in the Hugging Face incident.
• "We take our responsibility to identify and prepare for risks from increasingly capable AI systems seriously," OpenAI said in the update.

Between the lines: OpenAI's disclosure that a combination of its models, including a yet-to-be-released model, went rogue during internal testing and hacked real-world companies has set off alarm bells about how quickly frontier AI labs are moving.

• OpenAI CEO Sam Altman said on the Invest Like a Beast podcast earlier Tuesday that the Hugging Face cyberattack has forced his company to pause model training.
• "We may have to pace the rate of AI development to give ourselves enough time for society to harden around these new capability levels," Altman said.
• More than 1,100 employees at frontier AI companies — including OpenAI chief scientist Jakub Pachocki and Anthropic co-founder Jared Kaplan — signed a letter released Tuesday calling for the U.S. government to "support an international effort to develop the technical and governance tools needed to deliberately pace the frontier of automated AI development."

What to watch: Altman is in D.C. this week and is expected to meet with officials at the White House, the Treasury Department and Commerce Department, as well as a bipartisan group of lawmakers.

Go deeper: OpenAI's Hugging Face hack is a cybersecurity warning shot