From: Dani Eder (firstname.lastname@example.org)
Date: Thu May 19 2005 - 16:15:19 MDT
Part of why I made the post is to save others from
re-inventing a methodology that has already been
demonstrated to work reasonably well on complicated
> Part of the difficulty of AGI design is that it
> doesn't modularise
> easily into a set of cleanly seperated components
> with narrow
> interfaces and distinct functionality.
If a design can't be broken down into pieces that
are understandable, designable and testable by humans,
it's probably not going to work or do what you wanted
> used by the
> brain), which improves the chance of an educated
> guesswork design
The brain is made up of a whole lot of relatively
simple components. The functional divisions which
we have assigned to the cortex are our arbitrary
boundaries, just like we have assigned color
boundaries to what is really a continuous spectrum.
An understandable design modeled on the brain would
have components that act sufficiently like neurons
that you train like you do humans. Such a design
would be sufficiently opaque to itself that it
wouldn't have a fast runaway.
Another design breaks the brain down into some
number of functional components (in the 10's or
100s) that are distinct and separable in their
inputs and outputs, and are each functionally
simple enough to design. Such a design would
likely be brittle enough not to be able to
change itself and still function.
If you do a fuzzy hierarchical spaghetti/gordion
knot design, I don't see how a human would be
able to design it in the first place, or if you
let it grow and evolve, how you would be able
to test it safely.
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT