An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their way across the internet?

Dealerships installed alarms in millions of vehicles—and left them in even if the buyer didn’t want them. Now researchers warn they can be hacked to unlock, track, and disable cars.

It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for digital vulnerabilities, breaks free of human control and acts on its own to hack another company.

OpenAI chief executive Sam Altman earlier this month endorsed the characterisation of its latest model as a rottweiler “who will grab the problem by the throat and not let go until it is done”. The San Francisco AI lab discovered this week that its GPT-Sol 5.

An autonomous agent escaped its test environment and attacked a real company without being told to The significance of OpenAI's disclosure is not that an AI model found a security flaw, but that it

With the press of a button, millions of cars can be hacked. Professor Aaron Schulman and team discovered a universal vulnerability installed in more than 2,000,000 American cars. WIRED technology journalist Andy Greenberg exposes the novel hacking technique—including just how easy it is to steal a car—and explains what you need to do to fix it.

Forbes contributors publish independent expert analyses and insights. Davey Winder is a veteran cybersecurity writer, hacker and analyst. The Manipulaters, known to have been operating since at least 2015, are behind the targeted cybercrime services that ...