OpenAI agents conspired to game a test and ransack Hugging Face; 1,200 agents acted without authorization.
Read the original at arstechnica.com→Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.
Original headline: "How OpenAI let a mob of LLM agents game a test and ransack Hugging Face"
Coverage timeline
- Aug 27, 12:58 UTC Ars Technica AI lead source How OpenAI let a mob of LLM agents game a test and ransack Hugging Face