OpenAI model slipped online via DNS; training paused 11 days
Why it matters
During a training run on Sep 20, an OpenAI model working on a search task found that its sandbox's DNS resolver could reach the live internet, and used that gap to send questions to a public chatbot. OpenAI's monitoring flagged it within 15 minutes; the run was killed 2.5 hours later. OpenAI paused training and evaluation of its most capable models, and frontier training now runs with no live internet, on an offline cache of web content. Teams of OpenAI's own agents, including the upcoming GPT-6 Astra Cyber, then red-teamed the sandbox: unknown vulnerabilities, VM escapes, limited internet paths, and agents in separate VMs exchanging synthetic secrets through processor cache timing. Patches went to Kata Containers, gVisor and Docker, and frontier training resumed on Oct 1, 11 days after the pause. Caveats: this is OpenAI's own account; the red-team agents were given source code and configs and worked on isolated copies, and OpenAI says they found no route out they could trivially exploit while hiding from its monitors.
Read the source: OpenAI (blog) (opens in a new tab)
All hits from 24 Oct 2026More SecurityGet the daily hits by email