[extropy-chat] Eugen Leitl on AI design

[Eliezer Yudkowsky]

Eugen Leitl wrote:

> On Wed, Jun 02, 2004 at 09:40:07AM -0400, Eliezer Yudkowsky wrote:
> 
>>>Many orders of magnitude more performance is a poor man's substitute for
>>>cleverness, by doing a rather thorough sampling of a lucky search space.
>>
>>Right.  But it automatically kills you.  Worse, you have to be clever to 
> 
> Quite possible. Which is why I'm saying trying to build a human grade 
> AI is probably not a very good idea.

Nnnooo... what follows is that sampling a lucky search space using brute 
force is a poor idea.  Incidentally, if you think this is a poor idea, can 
I ask you once again why you are giving the world your kindly advice on how 
to do it?  (Maybe you're deliberately handing out flawed advice?)

>>realize this.  This represents an urgent problem for the human species, but 
>>at least I am not personally walking directly into the whirling razor 
>>blades, now that I know better.
> 
> You're still trying to build an AI, though.

Only white hat AI is strong enough to defend humanity from black hat AI, so 
yes.

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