RE: MW QT AI please phone home; another path to a Singularity?

Date: Sun Apr 21 2002 - 18:24:07 MDT

On Sun, 2002-04-21, Brian Atkins wrote:
> Of course I'm a complete armchair (less than that really :-) quantum
> physicist,

Me, too. Still, I thought I'd toss in my two cents since as I see it,
there are some unmentioned assumptions here.

> but it seems to me like the whole scenario seems awfully
> "this world"-centric. Reminds me of the whole Aristotle thing. If
> communications across worlds is possible, then shouldn't we already
> have been contacted by now?

Unless, of course, this hypothetical act of communication to a parallel
world in itself also splits the target world into branches where said
communication a) occured b) didn't occur. Thus we'd simply happen to be
in a branch where no communication from another world (to the best of
our knowledge, anyway) has taken place.

Of course, I might toss in the idea that in some of the hypothetical
parallels, standard quantum fluctuations may be trivially interpreted as
communication from another parallel. ("Trivially" as opposed to forced
interpretation along the lines of xoring something with a given one-time
pad, thus getting a message saying "Hi".) Thus any explicitly initiated
communication (with the abovementioned branching assumption) would be
somewhat indistinguishable from spontaneous generation of the message in
question. So if you do the experiment and get, say, an unFriendly AI,
there's not much of a difference if that was another parallel's UFAI
reproducing via quantum communication or just plain chance, rendering
this form of communication rather, hmh, uncommunicative. Of course, this
breaks down if a method of affecting other parallels _without_ branching
them can be devised.

Anyway, how about doing the experiment without running the result, and
if it results in something resembling AI source code, giving it to some
expert (*cough, cough*) for Friendliness analysis. (Sorry, Eliezer ;)

(Speaking of Eliezer, I just have to commend his excellent summary on
the whole conversation. Still gives me occasional spurts of laughter :)
Mikko Rauhala - - <URL:>

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:38 MDT