[ExI] Unfrendly AI is a mistaken idea.

John K Clark jonkc at att.net
Sun May 27 16:40:03 UTC 2007


"Lee Corbin" <lcorbin at rawbw.com>

> Clearly artificial machines do many things
> never *explicitly* programmed into them

One of the great understatements of all time, if it were not true there
would be no point in building computers at all.

> But they do not engage in extremely focused behavior

I don't know what that means, calculating a billion digits of PI seems
pretty damn focused behavior to me.

> unless someone or something has crafted this into them

You obviously think this "someone" can only be a flesh and blood human
being, although why this should be true you never make clear.

> or it evolved under selection pressure.

As I said before even an electronic AI that doesn't have an ounce of flesh
or a drop of blood is still operating under evolutionary pressure just as we
are.

> a behavior that will never simply arise
> in the absence a vicious evolutionary struggle.

Are you seriously suggesting that an AI will not consist of innumerable
subprograms each competing for runtime on valuable hardware,  that an AI
will not need to compete for resources because it lives in a different
universe than we do,  that there will only be one AI?

> your Versions 347812 and its direct descendant Version 347813 are just
> refining initial goals laid down way back

A 5 line program can behave in ways that are imposable to predict, the only
way to know what it will do next is to watch it and see. And it's not even
connected to the external environment! You propose a hundred trillion line
program that will operate exactly as we expect it to for all eternity
regardless of the astronomical amount of input it receives. I don't think
so.

> one of the early innovations people and Version 42 will add is to never
> fall into energy wasting infinite loops.

Imposable. Turing proved 70 years ago that in general you can't prove you're
in an infinite loop: Perhaps the Goldbach conjecture is false and in the
very next integer I test I will find an even number greater than 4 that is
not the sum of two primes greater than 2. Perhaps the Goldbach conjecture is
true but un-provable, that means 6.02 * 10^23 years from now I will still be
grinding through numbers looking, unsuccessfully, for a counter example to
prove it wrong and still looking, unsuccessfully, for a proof to prove it
right.

  John K Clark









More information about the extropy-chat mailing list