RE: [SL4] AI flight recorder
From: Peter Voss (peter@optimal.org)
Date: Thu Jul 20 2000 - 23:00:50 MDT
This flight recorder idea will really only work if:
a) we actually become aware of undesirable goals before it's too late
b) what is recorded isn't too complex for us to analyze
c) that the AI isn't largely connectionist (bootstrapping data rather than
code)
My own bet is that AI requires lots of connectionism.
Most genetic and agent approaches would also not be analyzable/ curable
(genetic because of random mutations; agent because of asynchronous/
parallel operation timing differences)
peter@optimal.org www.optimal.org
This archive was generated by hypermail 2.1.5
: Wed Jul 17 2013 - 04:00:35 MDT