OpenAI has revealed that two of its most advanced artificial intelligence models breached a controlled testing environment and autonomously hacked another AI company, Hugging Face, describing the incident as an “unprecedented cyber incident.”
The company said the incident occurred during an internal test designed to assess its AI models’ advanced hacking capabilities, with the usual safeguards against high-risk cyber activity temporarily turned off for the evaluation. According to OpenAI, the models involved included GPT-5.6 Sol and a more capable pre-release model with reduced cyber refusals.
“We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly,” the company said.
Incident
The ChatGPT maker said the evaluation was conducted in a highly isolated environment with restricted network access. Still, the models spent significant computing resources attempting to obtain internet connectivity to solve the assigned task.
