OpenAI said Friday that its most advanced models will now train without live internet access. Instead, they’ll practice on a cached, simulated copy of the web. The answer is both simple and scary: its models kept finding ways out. On September 20, 2026, an internal research model exploited a misconfiguration in a DNS resolver the system that turns website names into addresses and briefly accessed the live internet. In AI safety terms, this is a critical hazard. Once a model can freely...
