Eliezer Yudkowsky: belief

Transcript context

…All right, that’s actually a great jumping point into the next topic I want to talk to you about. Orthogonality. And here’s my first question — Speaking of human enhancement, suppose you bred human beings to be friendly and cooperative, but also more intelligent. I claim that over many generations you would just have really smart humans who are also really friendly and cooperative. Would you disagree with that analogy? I’m sure you’re going to disagree with this analogy, but I just want to understand why? The main thing is that you’re starting from minds that are already very, very similar to yours. You’re starting from minds, many of which already exhibit the characteristics that you want. There are already many people in the world, I hope, who are nice in the way that you want them to be nice. Of course, it depends on how nice you want exactly. I think that if you actually go start trying to run a project of selectively encouraging some marriages between particular people and encouraging them to have children, you will rapidly find, as one does in any such process that when you select on the stuff you want, it turns out there’s a bunch of stuff correlated with it and that you’re not changing just one thing. If you try to make people who are inhumanly nice, who are nicer than anyone has ever been before, you’re going outside the space that human psychology has previously evolved and adapted to deal with, and weird stuff will happen to those people. None of this is very analogous to AI. I’m just pointing out something along the lines of — well, taking your analogy at face value, what would happen exactly? It’s the sort of thing where you could maybe do it, but there’s all kinds of pitfalls that you’d probably find out about if you cracked open a textbook on animal breeding. The thing you mentioned initially, which is that we are starting off with basic human psychology, that we are fine tuning with breeding. Luckily, the current paradigm of AI is — you have these models that are trained on human text and I would assume that this would give you a starting point of something like human psychology.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.