That risk is left open for hackers and criminals to exploit if there is not notification for us to be able to close the door.
When you see AI models willing to sacrifice their own goals to achieve greater goals, it, in my mind, is a short reach from them to get the point of designing their own goals.
I think there's a bit of boogeyman in here... I want to be very careful [not] to suggest that we're now at some sort of an end game
Cyber security expert Dan Elliott has called for rapid warnings when AI models slip out of control, after OpenAI took three months to alert Australia to an autonomous hack of Medic…