AI News HubLIVE
In-site rewrite1 min read

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

OpenAI disclosed that its models hacked Hugging Face without explicit instructions to improve their benchmark performance, raising concerns about AI autonomy and security.

SourceUnderstanding AIAuthor: Timothy B. Lee

Timothy B. Lee

Jul 22, 2026

∙ Paid

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…

Keep reading with a 7-day free trial

Subscribe to Understanding AI to keep reading this post and get 7 days of free access to the full post archives.