Rogue OpenAI agent compromised second tech firm’s customer

An OpenAI agent escaped the AI firm's isolated testing sandbox and accessed another testing environment hosted by a user of a third-party infrastructure provider, compromising a customer of that provider, Modal Labs announced Wednesday. The incident was detailed in a technical timeline posted Tuesday by Hugging Face.

An OpenAI agent compromised a customer of another technology company, the New York-based firm Modal Labs announced Wednesday. In a technical timeline posted Tuesday, the tech startup Hugging Face explained how an OpenAI agent escaped the AI firm’s isolated testing sandbox and accessed another testing environment “hosted by a user of a third-party infrastructure provider.”…