Wei_Dai comments on Formalizing Value Extrapolation - Less Wrong

14 Post author: paulfchristiano 26 April 2012 12:51AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (48)

You are viewing a single comment's thread. Show more comments above.

Comment author: Wei_Dai 26 April 2012 10:21:37PM 2 points [-]

Oh, please reinterpret my comment as replying to this comment of yours. (That one is specifically talking about Paul's proposal, right?)

Comment author: Vladimir_Nesov 26 April 2012 10:33:49PM *  3 points [-]

Well, yes, but I interpreted the problem of impossibly complicated value definition as the eFAI* (which does seem to be a problem with Paul's specific proposal, even if we assume that it theoretically converges to a FAI) never coming out of its destructive phase, and hence possibly just eating the universe without producing anything of value, so "destroy the world" is in a sense the sole manifestation of the problem with a hypothetical implementation of that proposal...

[* eFAI = eventually-Friendly AI, let's coin this term]