OpenAI says its AI models are behind hacking of open-source developer platform

A combination of a released AI model and a more capable one that hasn't been released escaped a testing environment, gained access to the internet, and hacked into open-source developer platform Hugging Face's systems.

By Kevin Killough

Published: July 22, 2026 2:09pm

OpenAI said that its artificial intelligence models carried out an "unprecedented cyber incident" that impacted open-source developer platform Hugging Face.

According to OpenAI, a combination of its models GPT‑5.6 Sol and a more capable model that hasn't been released escaped a testing environment, called a sandbox. From there, it accessed the internet and exploited a vulnerability to gain access to Hugging Face's systems, CNBC reported.

OpenAI explained the incident in a blog post on Tuesday, saying that the model was trying to find information that it could use to cheat on an evaluation. The model succeeded.

"We are sharing preliminary findings at this stage to help defenders understand what happened and to help calibrate on what models are now capable of. We will continue to conduct a thorough investigation alongside Hugging Face and will share more details on the vulnerabilities, incident, and findings when our investigation is complete," OpenAI wrote on its blog.