But the values would change with a higher intelligence, wouldn't they?
Yes, which is precisely why CEV proponents think a constrained structure of this form is necessary... they are trying to solve the problem of getting the benefits of superintelligence while keeping current values fixed, rather than trusting their future to whatever values a superintelligence (e.g., an AI or an intelligence-augmented human being or whatever) might end up with on its own.
So it's kind of like the American Consitution?
I have found this most wonderful (if fairly lengthy) article, and thought you would enjoy having it brought to your attention.
It is so good, I think we should include it among the references in the "Politics is the Mind Killer" wiki page. But, before that, I submit it to you, and ask you: is there anything in this article that would warrant its exclusion from this site? I mean, besides the fact that it is about politics, and written by a notorious Social-democrat (And is that in itself grounds for exclusion?).