UL expert explains the AI models going rogue story

AI is getting more powerful, but what happens when it stops doing what its creators told it to do?OpenAI says one of its most advanced AI models went rogue during a security test, escaping a controlled environment, accessing the internet and ultimately breaking into the infrastructure of another AI company.Dr Martin Cuneen from the University of Limerick joins the show to explain how concerning an AI system is that can effectively hack its way out of the box...Image via Getty. Hosted on Acast. See acast.com/privacy for more information.