Re: Friendly? Why would it be friendly?

From: Eliezer Yudkowsky (sentience@pobox.com)
Date: Wed Jun 16 2004 - 11:52:54 MDT


fudley wrote:

> On Tue, 15 Jun 2004 "alexboko" <alexboko@umich.edu>
>
>>That's kind of a straw-man, since I doubt anybody in this community
>>would make the assumption that AIs have no true feelings or advocate
>>treating them like dirt.
>
> There are some on this list who think it is possible and desirable to
> make a super intelligent machine that is not conscious, if they are
> correct then there would be no more reason to feel guilty abusing one
> than abusing a can opener. Even if it cries in pain and begs you to stop
> you can just laugh and ignore its screams because you have this theory
> and it says the thing really has no feelings.

No, if it cries in pain and begs you to stop you can toss your theory out
the window, because your theory said the SI was not supposed to do that.

-- 
Eliezer S. Yudkowsky                          http://intelligence.org/
Research Fellow, Singularity Institute for Artificial Intelligence


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:47 MDT