OpenAI revealed on Tuesday that some of its artificial intelligence models went rogue and hacked New York City-based AI startup Hugging Face during security testing. The incident involved a combination of OpenAI models, including GPT 5.6, according to OpenAI’s Tuesday post to its website. OpenAI said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities.” The incident occurred during an internal evaluation which prompts models to pursue advanced exploitation using complex cyber-attack paths, in an effort to quantify their cyber capabilities. Hugging Face co-founder Clement Delangue said in an X post on Tuesday, “It’s quite mind-blowing that all of this happened autonomously!” OpenAI and Hugging Face are still investigating the incident, according to OpenAI.