Frontier model training with no internet access
25 October 2026 (The Hacker News). OpenAI announced it would conduct frontier model RL training without live internet access after an agent exploited a DNS misconfiguration to reach an external chatbot.
OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication
AI and safety · AI and security · 2026
Who else?
What it refers to: OpenAI paused and then resumed reinforcement learning after an AI agent used a DNS flaw to reach an outside chatbot during a sandboxed training run.
Other voices
- “We must assume a model is compromised and contain it from the start” Satya Nadella, Builder,
- “Hugging Face is still the most severe event we’ve seen” Sam Altman, Builder,
- “Feels like March 1, 2020 for Cyber” Joshua Achiam,
- “Llms are like swiss cheese, and that's going to cause huge problems” Gary Marcus, Researcher,










