📝 Agents escaping containment After OpenAI reported that Hugging Face was hacked by AI agents powered by their models, people have (rightfully) raised cybersecurity and even existential worries. I'm not worried, and I want to explain why in terms everybody can understand. If you are not up to speed, OpenAI described an agent was put inside an evaluation environment, or sandbox, for cybersecurity research purposes. It was instructed to try to escape it, and… it escaped. But it did so in a way…