Does he think all the properties of superintelligent systems that will be relevant for the success of alignment strategies already exist in current systems? That they will exist in systems within the next 4 years? (If not, aren’t there extremely important limitations to our ability to empirically test the strategies and figure out if they are likely to work?)
Does he think all the properties of superintelligent systems that will be relevant for the success of alignment strategies already exist in current systems? That they will exist in systems within the next 4 years? (If not, aren’t there extremely important limitations to our ability to empirically test the strategies and figure out if they are likely to work?)