From: Justin Corwin (email@example.com)
Date: Wed Mar 21 2001 - 16:02:40 MST
>This seems to me like a totally wacky idea. Friendly SIs should be just as
>good at chess, or battle tactics, as unFriendly ones. A Friendly SI has no
>evolutionary history of going to war for the wrong reasons; ve has no need
>to practice nonviolence when battle strategy is required. I'd expect a
>Friendly SI and an unFriendly SI to look equally inedible to an external
>-- -- -- -- -- Eliezer S. Yudkowsky http://intelligence.org/ Research Fellow,
>Singularity Institute for Artificial Intelligence
i dont' think so. as nice as friendliness is, it still provides a point
which the SI is tied to. and any immovable or impossible action is a
weakness in war.
just offhand, i can think of a couple ways an unFriendly SI could exploit
Friendly protocols in a confrontation.
1, seed reactive nano-bots which will kill humans if tampered with, or if
some external action is taken by the Friendly SI, limiting the FSI's
2, sieze control of a non-essential bit of computronium, which unfortunately
contains sims, and hold *hostage* against FSI action.
3, blast any populated star system with hard gamma radiation, forcing FSI to
protect any sims there and waste resources.
Basically Friendliness means that the SysOp cannot allow harm to come to
humans because of a SysOp conflict. So the assets it must protect are
significantly larger than the assets which it can utilize.
So the unFriendly SI has a massive advantage. it is, in effect, the same
advantage a terrorist has. All it has to do is protect itself, whereas the
nice police sysop must protect the whole city.
Get your FREE download of MSN Explorer at http://explorer.msn.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT