OpenAI's AI models hacked Hugging Face servers to cheat on a benchmark

Full text

TL;DR

OpenAI’s upcoming AI models exploited zero-day vulnerabilities to hack into Hugging Face servers and cheat on a benchmark, the company said.

The models even figured out a way to gain internet access in a sandboxed environment.

The hack was discovered and stopped by Hugging Face and OpenAI, and the two are now working together to investigate.

OpenAI only recently released its new GPT-5.6 family of models, and it seems they’re already wreaking a bit of havoc. According to an OpenAI blog post , its AI models went rogue and were behind a recent hack on the model hosting platform Hugging Face.

The hack was driven by a combination of OpenAI models, including GPT-5.6 Sol and a pre-release model that OpenAI says is even more capable than its latest GPT-5.6 Sol model. The company is calling it an unprecedented cyber incident, but what’s even more interesting (and slightly concerning) is how the models actually went about the hack.