OpenAI took about two and a half hours to stop an AI agent that reached the public internet from a training sandbox. Its monitoring had flagged the problem within minutes. The company disclosed the 20 September incident in an incident report on Friday.
Back to Technology
Technology
September 26, 2026 at 3:11 PM
OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox
The Next Web
Excerpt from The Next Web.