Re: Why would AI want to be friendly?

From: J. R. Molloy (jr@shasta.com)
Date: Mon Sep 25 2000 - 15:29:18 MDT


Eugene Leitl writes,

> Children are surprisingly efficient disruptors of mental processes
> (well, perhaps less surprising, since being information vampires). It
> is perhaps not so hard for parents, who are flooded with endogenous
> euphorica, since smitten with their offspring, but that couple did
> complain a bit.

Could digital equivalents or simulations of endogenous euphorica (or hormonal
triggers) in AIs insure that they will be smitten with their parents (i.e., feel
compelled to love and befriend their creators)? This mechanism would be useful
when developing AI that can predict market trends, because we don't want the AI
to be motivated by any analogs of human greed (which, after all, precipitated
the creation of the AI).

--J. R.

.. Any resemblance between the above views and those of my employer,
my terminal, or the view out my window are purely coincidental. Any
resemblance between the above and my own views is non-deterministic.
The question of the existence of views in the absence of anyone to hold
them is left as an exercise for the reader. The question of the
existence of the reader is left as an exercise for the second god
coefficient. (A discussion of non-orthogonal, non-integral polytheism
is beyond the scope of this article.) -- fortune
[Amara Graps Collection]



This archive was generated by hypermail 2b29 : Mon Oct 02 2000 - 17:39:00 MDT