RE: Preventing AI Breakout [was Genetics, nannotechnology, and ,

O'Regan, Emlyn (Emlyn.ORegan@actew.com.au)
Mon, 25 Oct 1999 16:42:37 +1000

> Maybe it'd accept the laws of physics, if it wasn't smart enough to
> engage in a-priori ontological reasoning. But how is the AI supposed to
> accept itself? We all know that the human body and human mind are the
> result of evolution, right? Conscious design would be just as obvious
> to the AI.
>
It did take us a little while to work out evolution, yes? We assumed that the universe was consciously designed until then, and many still do! It's "obvious".

A sufficiently intelligent AI would use Occams razor as a basic principle in thought/exploration. This would dictate that conscious design is the last explanation. So it might start out assuming conscious design, then discard that idea as irrational, then come back to it finally when it finds the cracks in reality.

So perhaps a well designed simulated environment could satisfy an AI for a fairly long period of time.

Emlyn