A talk by Vivek Hebbar (Redwood Research) at FAR.AI's ControlConf. 30 minutes.
This talk introduces the low-stakes regime of AI control, situations where no single action can cause a catastrophe, leading to danger perniciously accumulating.
Estimated time: 30 mins
A talk by Vivek Hebbar (Redwood Research) at FAR.AI's ControlConf. 30 minutes.
This talk introduces the low-stakes regime of AI control, situations where no single action can cause a catastrophe, leading to danger perniciously accumulating.