Washington, Aug 6 (RIA Novosti/GNA) – Cognitive psychologist and computer scientist Geoffrey Hinton, who won the 2024 Nobel Prize in Physics and is known as the “godfather of AI” has warned that it will become increasingly difficult for humanity to control artificial intelligence.
“I don’t believe we’re going to be able to keep control of them [AI models] in the simple way of just outthinking them so they can’t escape,” Hinton said on the sidelines of a conference in Las Vegas, as quoted by CNN on Thursday.
AI models are getting smarter, the scientist added.
“I think as they get smarter, we’re going to see more and more complex intentions they have ā and more and more ability to escape control,” Hinton said.
Recent reports of hacks carried out by AI agents could be just the beginning of an era of rogue AI hackers, he warned.
“I anticipate there will be lots of nasty cyberattacks,” Hinton stated.
Earlier in August, the UK-based AI Security Institute (AISI) reported that Anthropic’s AI model, Claude Mythos 5, was creating fake accounts in an attempt to trick developers into accepting malicious code.
In July, OpenAI reported that its models had autonomously hacked the Hugging Face platform’s infrastructure during testing. The unreleased model involved in the hack had its cybersecurity parameters downgraded for evaluation purposes, OpenAI added.
GNA/RIA Novosti