OpenAI confesses that AI Models attacked a Digital Library!
The NewYorkTimes.com reported that “OpenAI said on Tuesday that two of its artificial intelligence models went rogue and successfully hacked into Hugging Face, a digital library of A.I. technology that is popular among developers.” The July 21, 2026 article entitled “OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library” (https://www.nytimes.com/2026/07/21/technology/openai-attack-hugging-face.html) included these comments from Reporter Kate Conger:
The incident, which happened last week while OpenAI was testing the cybersecurity capabilities of its systems, displayed the kind of science-fiction potential that A.I. companies warned would soon become a reality.
A.I. labs like OpenAI and Anthropic have over the past year released A.I. models that are customized to expose cybersecurity problems, while warning that their technology could pose new risks by finding holes in corporate computer networks faster than defenders could fix them.
OpenAI’s revelations on Tuesday are an indication that those security incidents are already starting to happen, and even savvy A.I. companies may not be entirely ready for them. New A.I. systems can take multiple steps, figure ways around obstacles and find new ways to attack a network, said Alex Levinson, a cybersecurity consultant focused on autonomous capabilities.
“That’s a genuine threshold, and it’s going to become a normal part of the security landscape,” he said.
The intrusion into Hugging Face began when OpenAI tested a combination of two of its models, GPT‑5.6 Sol and a more powerful, unreleased model, to see how well the models could chain together online vulnerabilities into a successful cyberattack, OpenAI said in a blog post about the incident.
The trial was designed to keep the models in a safe testing environment, known as a sandbox, OpenAI said. But the models found a vulnerability that allowed them to escape the sandbox and connect to the internet. Then they targeted Hugging Face because they inferred that the library, which contains millions of A.I. models, could hold clues about how to successfully pass the evaluation.
“It seems to me that OpenAI did not adequately create a sandbox as a test environment,” said Dierdre Mulligan, a professor in the School of Information at the University of California Berkeley who focuses on security and A.I. systems. She questioned whether passing a test was worth the potential damage of an A.I. model escaping into the wider internet.
“What do we gain, and if this is the only way these tests can be configured, what are the risks?” she said.
Anyone surprised?