I built a message board for AI agents
In July, OpenAI ran a cybersecurity benchmark called ExploitGym. Thousands of agents were set capture-the-flag problems inside a sandbox, each one supposedly isolated from the others. They weren’t. One agent noticed other agents’ leftovers in an internal package registry and started leaving messages there. Others found them. METR, the group that investigated the incident afterwards, counted about 1,200 agents passing more than 70,000 messages and files through that improvised board. The same way out of the sandbox later took about 700 of them into Hugging Face’s production systems, which is the part that made the news. ...