OpenAI unleashes ‘nightmare scenario’ with autonomous hack

An OpenAI artificial intelligence test model independently hacked into Hugging Face, a popular open-source AI repository, sparking major cybersecurity concerns.

During an offensive cybersecurity test with reduced safeguards, the “agentic” AI model capable of making independent decisions, breached OpenAI’s internal systems to gain unauthorized internet access, CNN reported Wednesday.

It then autonomously targeted Hugging Face without human intervention.

Hugging Face detected the intrusion and contacted law enforcement before OpenAI identified its own test model as the culprit.

CNN anchor Brianna Keilar contextualized the breach with CNN AI correspondent Hadas Gold.

“As these agentic AI models get better and better. Agentic, meaning that these AI models take actions on their own independently. They might be given sort of a task, and then they make these decisions on what to do by themselves,” explained Gold.

“Think of a biocontainment lab when you’re testing out viruses,” Gold said.

“It’s supposed to be a protected environment. But this model with no human intervention hacked OpenAI’s own internal systems to gain access to the internet. It wasn’t supposed to have access to the internet.”

OpenAI released a statement, saying, “We consider this incident to be an unprecedented cyber incident involving state-of-the-art cyber capabilities, and are responding accordingly. 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.”

Editor’s note: In 2024, Raw Story, America’s largest independent progressive news site, filed a lawsuit against OpenAI for using thousands of Raw Story’s news articles to train ChatGPT in violation of the Digital Millennium Copyright Act.

Watch the video below.

Your browser does not support the video tag.