Re: Envisioning sysop scenarios Re: Universal Uplift as an alternative to the Sysop scenario

From: James Higgins (jameshiggins@earthlink.net)
Date: Thu Mar 22 2001 - 08:10:40 MST


At 02:50 PM 3/21/2001 -0500, Gordon Worley wrote:
>At 1:48 PM -0500 3/21/01, Brian Atkins wrote:
>> > If we can have faith in one SI doing the right thing, why not in more
>> than one? The Friendliness attractor that keeps a 'SysOp' SI on the
>> right path will also keep other SIs on the right path too. If a second
>> intelligence can clearly demonstrate it's mind is Friendly, then I see
>> no reason why the first should have to baby-sit the other. It's a mature
>> intelligence - it won't *want* to do anything evil.
>>
>>Right I agree that if a SI can prove itself friendly somehow then there
>>should be no need to monitor it.
>
>What about an SI that just makes everyone think that it is Friendly? Such
>a situation would be dangerous because an un Friendly SI could slip
>thorough and do something horrible, because all that there would be to
>stop ver are Friendly SIs who wouldn't hurt a fly in VR. It is going to
>take un Friendly SIs to stop un Friendly SIs who manage to escape the
>control of a Sysop.

Bingo! Should a SI ever slip out of the Sysop's control, I doubt it could
do anything about it. Heck, I could probably talk an ideally Friendly
Sysop into the fact that it would be unfriendly to put my back under
control now that I have been free. That would be like imprisonment. I can
only imagine the ways a true SI could handle this situation.

I doubt the Sysop scheme will ever see the light of day. And, if it does,
it will either vanish in the blink of an eye or end up suppressing everyone
to such a degree that most, if not all, SIs up terminating their own
existence to be free of it.

James Higgins



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT