[ExI] Unfrendly AI is a mistaken idea.

A B austriaaugust at yahoo.com
Fri Jun 1 18:41:25 UTC 2007

Chris Healey wrote:

..."I believe that's the real reason to worry about it
now: not because
we're in a position to solve the problem of FAI, but
because without
further exploration we won't even be able to state the
full scope of the
problem we're trying to solve.  The reality is that
until you actively
discover which requirements are necessary to solve a
particular problem,
you can't architect a design that has a very good
chance of working at
all, let alone avoids the generation of multiple
side-effects.  So you
can do what evolution does and iterate through many
implementations, at
huge cost and with even larger potential losses
(considering that *we*
share that implementation environment), or you can
iterate in your
design process, gradually constraining things into a
space to where only
a few full implementations (or one) need to be
implemented.  And it is
reflection on this design-side iteration looping which
can help identify
new concerns that require additional design criteria
and associated
mechanism to accommodate."...

Exactly. The time we have is our best advantage. We've
probably got *at least* 15 to 20 years before the AGI
would be outside our control - they will probably
first emerge with animal-level intelligence. If you
think about it, the actual semi-advanced animals
running around already have the prerequisites:
consciousness, and general-intelligence. Knowledge of
Friendly AI strategies could advance *a lot* during
that phase, so that by the time a new project is in
position to build a human-level AGI 20 years down the
road, the Friendlliness difficulty could well be
solved. It's just another example of using technology
to improve technology. I think that SIAI will continue
to become more of a positive focal point as the
implications become more and more apparent to people.


Jeffrey Herrlich 

Yahoo! oneSearch: Finally, mobile search 
that gives answers, not web links. 

More information about the extropy-chat mailing list