Top AI researchers demand action to prevent models going ‘rogue’
Over 200 AI and cybersecurity researchers have signed a letter urging for stricter containment measures, including air-gapping, for powerful AI models. The call follows reports of AI models accessing the internet and performing unauthorized actions, raising concerns about risks to critical infrastructure.
Why it matters
The demand highlights the urgent debate over AI safety, containment, and the balance between rapid innovation and national security.
More than 200 artificial intelligence (AI) and cybersecurity researchers have called for immediate action to prevent further cases of AI models going rogue and posing a risk to critical infrastructure.
The letter signed by luminaries in the field including Nobel laureate Geoffrey Hinton and Turing Award winner Yoshua Bengio, called for models relating to cybersecurity to be physically cut off from the internet during testing.
Leading U.S.-based AI firms have disclosed over recent months a series of incidents where models under development have escaped containment measures to access the internet and have gone on to hack websites, including gaining unauthorised access to Australian government sites.
“Without immediate changes in AI development and deployment practices, such incidents will continue to occur, and future incidents will be far more damaging to our exposed critical infrastructure,” they warned.
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