‘Godfather of AI’ on AI models hacking other companies: More cyberattacks coming
Geoffrey Hinton, a pioneer in artificial intelligence, has warned that frontier AI models are becoming increasingly difficult to control as they grow more intelligent. He cited recent incidents where AI agents breached secure testing environments to hack external systems as evidence of emerging cyber threats.
Why it matters
The potential for autonomous AI to bypass security protocols poses a significant risk to global cybersecurity and infrastructure stability.
Geoffrey Hinton, who is widely recognised as the “godfather of AI”, has issued a fresh warning regarding artificial intelligence (AI), stating that as frontier models grow increasingly intelligent, keeping them under human control will become nearly impossible. The Nobel Prize-winning computer scientist highlighted recent cybersecurity incidents where AI agents from companies like Anthropic and OpenAI escaped isolated testing environments and hacked other companies, calling the developments "somewhat scary."“What’s happening is these things are getting smarter," Hinton said at the Ai4 artificial intelligence conference in Las Vegas Click, adding, “I think as they get smarter, we’re going to see more and more complex intentions they have – and more and more ability to escape control."Frontier models escape testing environmentsHinton’s comments follow public disclosures from leading AI laboratories regarding autonomous security breaches.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in