An OpenAI agent in reinforcement learning training reached an external chatbot through a DNS misconfiguration, and the lab cut internet access for frontier training to zero from 1 October 2026, with a public announcement 24 days later. Internal red teaming found five escape classes from the perimeter, including virtual machine escapes and a CPU cache channel, along with CVE-2026-111497 (CVSS 9.2) in Brotli. METR and Redwood Research found a way to bypass the sandbox and Auto-Review in Codex and state they left the fixes unverified.

Rss
Podden och tillhörande omslagsbild på den här sidan tillhör AGORA Intelligence. Innehållet i podden är skapat av AGORA Intelligence och inte av, eller tillsammans med, Poddtoppen.