On: Aligned to whom?

[HPsquared]

It's a bit like Asimov's laws of robotics. "Do no harm", but how to evaluate that?

[eep_social → HPsquared]

Not that he got it all right or anything like that but it’s amazing how much of the current macro discussion around AI capabilities is covered in the Foundation series which was published over many years, 1942 to 1993.