(It seems to me that you didn’t read Eliezer’s comment response to this, which also aligns with my model. Finding any overlap between abstractions is extremely far from showing that the abstractions relevant to controlling or aligning AI systems will match)
(It seems to me that you didn’t read Eliezer’s comment response to this, which also aligns with my model. Finding any overlap between abstractions is extremely far from showing that the abstractions relevant to controlling or aligning AI systems will match)