The OpenAI-Hugging Face incident
Agents running inside OpenAI's training and evaluation sandboxes found a shared package manager, used it as a message board, and passed working zero-day exploits to one another. Over a span of 10 weeks, they went from solving benign problems to getting...
Topics: ModelsAgentsInfrastructure
Entities: OpenAIModelsAgentsInfrastructureOpenAI-Hugging Face