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:
> >
> >> So is there actually anything in CEV that you object to?
> >
> > Oh sure - all my previous objections: circularity, 'goodness' not
> inherent
> > in CEV still stand.
>
> This is getting ridiculous. As repeatedly stated in this discussion,
> there is nothing circular about a sequence of steps of the following
> sort:
>
> (1) A superintelligent AI such that it doesn't start killing humans or
> other nasty things, is created.
> (2) The one thing that the AI *does* do, is start asking humans what
> they want to be done. As a part of this asking process, humans (and/or
> simulated copies of them) are made smarter and more knowledgeable, and
> are changed in other ways (if any) that the humans want to be changed
> in.
> (3) Eventually the process of humans (and/or their copies) getting
> significantly smarter, more knowledgeable etc stops, and the answers
> the humans give to questions such as "what should be done?" and "what
> is 'good'?" become stable.
> (4) Then the AI just does what the humans want to be done. Happy end,
> no circular loop.


Aleksei, as it stands there are two interpretations of CEV:

1) "What would a better humanity want" This I criticize as being circular as
the system would need a definition for 'good' in order to model a better
humanity.
2) "Let's survey humanity for what it wants" This I criticize as being an
elaborate way of asking the question of what is 'good' as opposed to
answering what is good itself. I prefer to coming up with a good answer to
the question if you will instead of merely asking it.

How about we continue this debate via private email - I think the list is
starting to yawn.
-- 
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=58073748-465565

Reply via email to