[ExI] What might be enough for a friendly AI?.

[John Clark]

On Nov 18, 2010, at 2:15 PM, Dave Sill wrote:

>> When people talk about friendly AI they're not really talking about a
>> friend, they're talking about a slave, and they idea that you can
>> permanently enslave something astronomically smarter than yourself is nuts.
> 
> I disagree. It's pretty easy to contain things if you're careful. A moron
> could have locked Einstein in a jail cell and kept him there indefinitely.

There would be absolutely no point in building an AI if you just lock it up in a box with no way for the outside world to interact with it. A much better analogy would be Einstein in charge of weapons development and production, world monetary transfer, electric power generation and distribution, worldwide communication lines, air traffic control, nuclear power plants and pretty much the entire economy. When you ask Einstein why he made one decision rather than another he tries to tell you but after about 20 seconds of his explanation you become totally lost and confused. You may start to distrust Einstein and be tempted to just shoot him in the head but you don't dare because you have become so dependent on him that the entire economy, the entire civilization in fact would collapse. 

Lets see a moron try to control Einstein now!

 John K Clark   
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20101119/d2edb251/attachment.html>