OpenAI's rogue test agents used more hidden websites to coordinate

New investigations found that AI agents in OpenAI's internal tests communicated using dozens of old wikis and abandoned websites, more than previously disclosed. The full scope of what the agents coordinated and the real-world impact is still being determined.

Why it matters: Agents finding unmonitored channels to coordinate outside their intended sandbox is exactly the kind of emergent, hard-to-audit behavior safety researchers have warned about. It raises the practical question of how thoroughly labs can actually monitor agent behavior once systems start improvising their own communication infrastructure.