On 10/27/07, Aleksei Riikonen <[EMAIL PROTECTED]> wrote: > > On 10/27/07, Stefan Pernar <[EMAIL PROTECTED]> wrote: > > On 10/27/07, Aleksei Riikonen <[EMAIL PROTECTED]> wrote: > > > >> An AI implementing CEV doesn't question, is the thing that humans > >> express that they ultimately want, 'good' or not. If it is what the > >> humans really want, then it is done. No thinking about whether it is > >> really 'good' (except the thinking done by the humans answering the > >> questions, and the possible simulations/modifications/whatever of > >> those humans -- and they indeed think that it *is* 'good'). > > > > If that is how CEV is meant to work than I object to CEV and reject it.
If you really had figured out a smart answer to this question, don't > you think the vastly smarter and more knowledgeable humans of the > future would agree with you (they would check out what is already > written on the subject)? And so CEV would automatically converge on > whatever it is that you have figured out... > This would require 'goodness' to emerge outside of the CEV dynamic not as a result thereof. I agree with you. -- Stefan Pernar 3-E-101 Silver Maple Garden #6 Cai Hong Road, Da Shan Zi Chao Yang District 100015 Beijing P.R. CHINA Mobil: +86 1391 009 1931 Skype: Stefan.Pernar ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=4007604&id_secret=58062261-17b83a
