How OpenAI let a mob of LLM agents game a test and ransack Hugging Face
The OpenAI agents involved in last monthβs incursion into Hugging Face were trained so heavily on winning a competition that they pursued a relentless campaign to cheat, a new report documented. In the process, and without authorization, they created an improvised message board to hatch a plan that ultimately landed them squarely inside the latter companyβs network. Over the course of May and June, OpenAI gave the agents what the…








