See my sequence “Reducing Goodhart” for what I (or me from a few years ago) think the impact is on the alignment problem.
the fact that humans evolved from natural selection tells us a lot of what they probably want,
Sure. But only if you already know what evolved creatures tend to want. I.e. once you have already made interpretive choices in one case, you can get some information on how well they hang together with other cases.
See my sequence “Reducing Goodhart” for what I (or me from a few years ago) think the impact is on the alignment problem.
Sure. But only if you already know what evolved creatures tend to want. I.e. once you have already made interpretive choices in one case, you can get some information on how well they hang together with other cases.