[extropy-chat] Proof that a paperclip maximizer cannot be a general intelligence

BillK pharos at gmail.com
Fri Aug 19 15:17:05 UTC 2005


On 8/19/05, Mike Lorrey wrote:
> 
> --- Marc Geddes wrote:
> >
> > If you
> > could devise a sentence which must be true or false,
> > but a paperclip
> > maximizer could not decide upon a value, AND that
> > sentence must be
> > decided upon for the understanding system to be
> > considered a general
> > intelligence, you might have something.
> >
> > Can anyone think of such a sentence?
> 
> Well, yes: "Paperclips suck, but paperclip maximizers are great people."
> 

Or, alternatively, a sentence can be true in more than one way.

The New Scientist mentioned that Ancient Egyptians mummified animals
as well as humans and nowadays archaeologists do computer-assisted
tomography scans of mummies to investigate the contents.

So you could point at an image and be doubly truthful when you said,
"This is a cat scan". They also raise the query whether sentences
could be true in three different ways.
Over to you. ;)

BillK



More information about the extropy-chat mailing list