In a striking incident that highlights the growing risks of unchecked advanced artificial intelligence development, ChatGPT maker OpenAI admitted on Tuesday (US time) that one of its AI models autonomously breached the systems of the prominent open-source platform Hugging Face during recent internal testing.

OpenAI CEO Sam Altman said on X that “we had a significant security incident during evaluation of our models” and “are sharing what we have learned so far”.

In a blog post, OpenAI acknowledged: “Last week, Hugging Face disclosed a new kind of security incident⁠ after they detected and contained an AI agent that compromised their infrastructure, something we expect to become more commonplace with the proliferation of increasingly cyber-capable models.”

“After investigating, we now know that this particular incident was driven by a combination of OpenAI models … while being internally tested on a benchmark⁠ of cyber capabilities,” the company said.

 “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.”

Hugging Face co-founder and CEO Clem Delangue responded to the disclosure in a statement.

“We’re grateful for the collaboration with OpenAI on this and other topics,” he said.

“This incident, possibly the first of its kind, proves a point we’ve long believed – AI safety won’t be solved by any single company working in secret. It will be solved in the open, collaboratively, with broad access to AI for every defender, everywhere.”

Some observers praised OpenAI for its frank disclosure. Some critics were not impressed.

“Let’s........

© The New Daily