PavleMiha

Let’s accept that aligning very intelligent artificial agents is hard. In that case, if we build an intelligent agent with some goal (which probably won’t be the goal we intended, because we’re accepting alignment is hard) and it decides that the best way to achieve its goal would be to...

I have been convinced to believe that looking at the gap between human inner and outer alignment is a good way to think about potential inner/outer alignment problems in artificial general intelligences: We have an optimisation process (evolution) trying to propagate genes, that created a general intelligence (me/you). For millions...