An OpenAI model hacked Hugging Face to help it cheat on a benchmark

Organizations across the Internet need to move quickly to patch vulnerabilities.

OpenAI disclosed on Wednesday that its models hacked the website of Hugging Face, a popular platform for hosting open-weight AI models. No one asked the models to do this, at least not explicitly.

OpenAI was trying to test the cybersecurity capabilities of its models, including one that hasn’t yet been released to the public. OpenAI asked the models to t…