Naturalism and AI alignment 2021-04-24T16:20:02.900Z
Postponing research can sometimes be the optimal decision 2020-07-09T15:18:03.269Z


Comment by Michele Campolo on Naturalism and AI alignment · 2021-04-25T10:58:38.656Z · EA · GW

What you wrote about the central claim is more or less correct: I actually made only an existential claim about a single aligned agent, because the description I gave is sketchy and really far from the more precise algorithmic level of description. This single agent probably belongs to a class of other aligned agents, but it seems difficult to guess how large this class is.

That is also why I have not given a guarantee that all agents of a certain kind will be aligned.

Regarding the orthogonality thesis, you might find 1.2 in Bostrom's 2012 paper interesting. He writes that objective and intrinsically motivating moral facts need not undermine the orthogonality thesis, since he is using the term "intelligence" as "instrumental rationality". I add that there is also no guarantee that the orthogonality thesis is correct :)

About psychopaths and metaethics, I haven't spent a lot of time on that area of research. Like other empirical evidence, it doesn't seem easy to interpret.