This is related to the theme Eliezer quite elegantly goes on about in Creating Friendly AI and that he for some reason barely mentioned in CEV, which is that the AI should look at its own source code as evidence of what its creators were trying to get at, and update its imperfect source code accordingly.
Yes, but it still has to be explicitly programmed to do that! The question is how to get it to do so. AFAIK shaper-anchor semantics is still quite a ways from being fully specified, but it seems the bigger obstacle is that an AI writer is less likely than not to take the effort to program it that way in the first place.
Yes, but it still has to be explicitly programmed to do that! The question is how to get it to do so. AFAIK shaper-anchor semantics is still quite a ways from being fully specified, but it seems the bigger obstacle is that an AI writer is less likely than not to take the effort to program it that way in the first place.