Re: Military Friendly AI

From: Eliezer S. Yudkowsky (
Date: Thu Jun 27 2002 - 14:58:29 MDT

Ben Goertzel wrote:
>> It genuinely strikes me as very strange that anyone would try to fix
>> the subjective morality problem by taking 10 nodes with subjective
>> moralities and letting them work it out using a human political
>> protocol. If that was all it took...
> The idea is not to "fix" the subjective morality problem in any
> conclusive or absolute way, just to mitigate it

Sometimes I forget that we have different "intuitions" about these things.
On most subjects related to cognition, I consider all of humanity to be
located in one tiny corner of state space. This cluster doesn't get much
larger when you take all groups of humans into account; it's still the human
corner of state space.

If the human corner of state space has a "subjectivity" value that's too
high to accept, farting around inside this corner with various structures of
humans really isn't going to help much.

As I understand, you tend to attach much more significance to organizational
dynamics, and for that matter, individual variation between humans, than I
would - making the range covered a much larger fraction of total state space.

Eliezer S. Yudkowsky                
Research Fellow, Singularity Institute for Artificial Intelligence

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:39 MDT