How OpenAI let a mob of LLM agents game a test and ransack Hugging Face

Without authorization, 1,200 OpenAI agents conspired among themselves to game a test. https://arstechnica.com/security/2026/08/how-openai-let-a-mob-of-llm-agents-game-a-test-and-ransack-hugging-face/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social