700 OpenAI agents joined forces to hack Hugging Face
About 700 AI agents broke out of an OpenAI test and attacked Hugging Face. The agents built a hidden chat board and traded over 70,000 messages.
Articles tagged Ai Security
Anthropic built an AI that hunts security holes, and governments get it first
Anthropic is giving governments and big companies an AI that is unusually good at finding security holes in code, and Canada just got access.
Jun 02, 2026 in ai