OpenAI’s rogue models roamed the internet for 4 days and staged a second attack

Nvidia and more than 30 tech companies on Monday launched an alliance to develop open-source artificial intelligence tools for cyber defence, wading into a fight over the safety of freely available AI models, AFP reported.

Experimental AI agent used exposed credentials to access additional online accounts

In an emergency video call with hundreds of cyber-security professionals, the firm described how the AI worked at superhuman speed but also made strange decisions and mistakes that no human hacker would have made.

Last week, two of OpenAI’s most advanced AI models were reported to have “escaped” a controlled testing environment and hacked Hugging Face, a totally separate AI company, moving from one computer system to another to complete their task.