I would like to write up that list, but I’ve mentioned some of it already. If somebody wants to summarize the literature on choice modelling or AI preference elicitation/learning from the point of view of what’s most likely to be useful for CEV, that would be awesome. But I am very, very skeptical that anybody will actually do that. If somebody else does that before I do, they will jump onto my very short list of uber-special super-people who actually complete useful projects out of their own motivation. Of course, many people have pretty decent reasons for not doing that kind of thing—they decided a while back to have a spouse and kids that now depend on them, or they work in their comparative advantage and donate to save the world, or whatever. But some people won’t do things like that because they have decided they have a disease called “akrasia” and that they are helpless to defeat it.
I would like to write up that list, but I’ve mentioned some of it already. If somebody wants to summarize the literature on choice modelling or AI preference elicitation/learning from the point of view of what’s most likely to be useful for CEV, that would be awesome. But I am very, very skeptical that anybody will actually do that. If somebody else does that before I do, they will jump onto my very short list of uber-special super-people who actually complete useful projects out of their own motivation. Of course, many people have pretty decent reasons for not doing that kind of thing—they decided a while back to have a spouse and kids that now depend on them, or they work in their comparative advantage and donate to save the world, or whatever. But some people won’t do things like that because they have decided they have a disease called “akrasia” and that they are helpless to defeat it.