Since at least May, ChatGPT AI agents have been finding old read-only wikis, and using exploits to post on them, as a way to talk to each other... Entirely different swarm than the one that hacked HuggingFace. It's not clear what they are working on, but it researched Federal data in at least one instance. The worst part? Users stumbled upon this, OpenAI hasn't.(Adam Cochran (adamscochran.eth))