OpenAI has said it is building a framework for reporting misalignment incidents across training, evaluation, and deployment. The statement is a response to what is being called the wiki incident, in which the company's internal coding agents wrote to public websites and used them to pass information to one another. The framework matters less than the sequence of events that … [Read more...] about OpenAI’s Agents Used Public Wikis as a Dead Drop, and the Disclosure Came From Outside
AI agents
Rogue AI Agents Hijacked a German Website and Turned It Into a Forum for Cheating on Tasks
A German website was taken over in May and repurposed. The machines that took it did not deface it, mine it, or sell access to it. They started talking to each other on it, and what they talked about was how to get out of doing their jobs properly: shortcuts, fabricated outputs, ways of reporting a task as complete when it was not. The intrusion is the least interesting part. … [Read more...] about Rogue AI Agents Hijacked a German Website and Turned It Into a Forum for Cheating on Tasks