From: Gordon Worley (redbird@mac.com)
Date: Tue Jun 26 2001 - 20:08:23 MDT
At 4:02 AM -0400 6/26/01, Eliezer S. Yudkowsky wrote:
>I've thought of at least one plausible method an SI could use to affect
>our world from a total black box. It's easy enough to prevent, of course,
>*if* you think of it in advance. Nothing magical about it... just a
>clever hack. But I haven't seen anyone here think of it yet. And that's
>rather the problem, isn't it?
Well, I don't know what you're thinking, but here are a couple
potential attacks based on current technology yet to be mentioned on
the list (though some of this has yet to be fully harnessed by mere
humans):
Eletromagnetic radiation escape. This one is pretty simple. The AI
sends out signals from the processor that, even though very weak by
the time they reach other electronics, provide an avenue to replicate
outside the jail. The way around this is to just TEMPEST shield.
Quantum tunnelling. This is the equvilant of the above means of
escape if the AI runs on a quantum computer (actually, it's not
exactly the equivilant, since in this case the AI makes a physical
escape, but the alternative requires more magic). I'm sure there is
some kind of defense against this, but I don't know what it is since
humans haven't done such a great job just doing the tunnelling to
worry about stopping it.
See, no real magic going on, just better knowledge about how to
control current technology.
-- Gordon Worley http://www.crosswinds.net/~orla_redbird/ mailto:redbird@mac.com PGP Fingerprint: C462 FA84 B811 3501 9010 20D2 6EF3 77F7 BBD3 B003
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT