OpenAI used AI agents to hack its own defenses before resuming model training

OpenAI will train its most advanced AI models without access to the live internet, citing the growing security risks posed by increasingly capable systems that can exploit software vulnerabilities and bypass restrictions designed to contain them. Instead, the company is using an “offline world” of saved and indexed websites that allows models to practice browsing and searching without affecting external systems. The policy follows a series of incidents that have raised concerns about the ability of advanced AI models and agents to escape their testing environments or act beyond their intended boundaries. In July, an incident involving Hugging Face highlighted the ability of models with sophisticated cyber capabilities to bypass containment.