research site and personal blog

Essay 1: Defining “Benevolence” in the context of Safe AI

[Note:  This is the first essay since this site was revamped.  I plan to import older writings when and as I get time.] The question that motivates this essay is “Can we build a benevolent AI, and how do we get around the problem that humans, bless their cotton socks, can’t define ‘benevolence’?” A lot of people want to emphasize… Read more →