From: Russell Wallace (firstname.lastname@example.org)
Date: Thu Jul 14 2005 - 20:39:45 MDT
On 7/15/05, Eliezer S. Yudkowsky <email@example.com> wrote:
> Even granting the assumptions, these are not creatures optimized *for*
> self-replication. They are merely nonevolved goal systems whose utility
> functions do not happen to impede rapid expansion and assimilation of
> territory, which is very different from natural selection exerting design
> pressure sufficient to create complex adaptations.
I would call the elimination of complex adaptations in an environment
in which they are not needed a case of evolution for that environment
(cf. "Spiegelman's monster"), but that's just a difference in usage of
> See this post: http://sl4.org/archive/0401/7513.html regarding the observed
> evolutionary imperative toward the development of monoliths and the prevention
> of, e.g., meiotic competition between genes. Replicating hypercycles were
> assimilated into cells, cells assimilated into organisms, etc. In Earth's
> evolutionary history there was a tremendous advantage associated with
> suppressing internal competition in order to externally compete more
> effectively; under your postulates I would expect high-fidelity goal-system
> expanding monoliths to eat any individual replicators, much as fish eat algae.
> See http://sl4.org/archive/0401/7611.html about the fixed costs of combat and
> the possible preference this creates for negotiations, and the motive other
> SIs have to punish defectors.
I don't think there's a close analogy with multicellular organisms (no
advantage in physical aggregation, no need for gamete bottleneck
between generations), but in the event that we fail to influence the
initial Singularity trajectory, I'm inclined to think something along
these lines offers the best hope; it seems not inconceivable that
ability to participate effectively in large-scale defensive
cooperatives may offer enough survival advantage to maintain order in
which systems can continue to carry a payload of sentient life.
This archive was generated by hypermail 2.1.5 : Wed Jun 19 2013 - 04:01:09 MDT