Re: AI: Relative difficulty

Anders Sandberg (
Mon, 20 Jan 1997 10:58:53 +0100 (MET)

> From: Eliezer Yudkowsky <>
> > [Elizer is quoting Anders Sandberg without attribution:]
> > > The way to test it is of course to
> > > bring up a child in a virtual reality with different laws...
> >
> > What a concept. WHAT a concept. Alert Greg Egan. "Bring up a child in
> > a virtual reality with different laws!" Do you really think that if one
> > plus one always equalled three in the virtual environment, the child
> > would begin thinking in new laws of mathematics that were based on this
> > basic assumption? Wouldn't he notice that in his own mind, one thought
> > and one thought equalled two thoughts?

How would you build a world where 1+1=3? It would be rather inconsistent,
and thus unlikely to work (although the experiment could work just as
well with a child in a inconsistent VR, of course). A better example
would be a world with hyperbolic geometry or objects that are not persistent.

BTW, David Brin has had this idea before. He wrote a short story about how
the Japanese used genetic engineering and cognition enhancing techniques
to make genius children in the womb. They were trained in topology,
differential geometry and other branches of math, and solved problems for
the government. Of course, one of the mothers realizes something nasty is
going on...

Another idea on this theme was a story in the Shadowrun sourcebook about
Cyberspace, where the Nasty Megacorp (TM) brought up babies in cyberspace
to act as super-hackers (to get from their virtual playroom to their
virtual bedroom they had to "solve a puzzle", i.e. hack a security

My guess is that this in principle is possible if you start early enough
an manage to create a world still compatible with our basic brain wiring.
What this wiring exactly is, well, that was the question which started
this debate. :-)

Anders Sandberg Towards Ascension!
GCS/M/S/O d++ -p+ c++++ !l u+ e++ m++ s+/+ n--- h+/* f+ g+ w++ t+ r+ !y