[ExI] SF - cyberspace and utopian narratives for meatless bodies
pharos at gmail.com
Sat Feb 11 14:55:16 UTC 2012
2012/2/11 Stefano Vaj wrote:
> I am not persuaded that there is any real limit to acceptable latency, given
> that any arbitrary computational node speaks anyway very quickly with
> neighbouring nodes, no matter how "distant" it may be from an arbitrary
> "centre", so the rationale to connect three of them is not so different from
> having the last one added in a row of 10^10 of them.
> This simply means that "long-distance calls" are reduced as much as possible
> in favour of local computation and data caching.
> Take for instance the contemporary scenario, where we have at one extreme
> the internal working of registers of single processing unit, then the
> processor with its internal cache(s), then your possibly multiprocessor
> board with its RAM, then (virtual?) clusters thereof, then perhaps a
> configuration such as folding at home where possible latency already may
> measure in weeks - much higher than what would exist in a ideal, optimised
> star-sized computronium sphere.
Your example works fine when low-level processors work on bits of a problem.
But Keith was talking about whole civilisations.
Long communication delays mean that they will no longer be one unified
civilisation. They will diverge into separate civilisations. These
future 'million-times speed up' intelligences will probably be more
like hive-minds than the groups of individuals that we have today. As
such, the communication delays would stop the mind growing above a
certain size, because it would take too long to reach a decision. The
mind itself will decide what the optimum size would be for calculating
efficiency and if it wants to expand then it would build another mind
next door. Though I don't see why it would want to create a competitor
for resources. Unless resources are really plentiful, of course.
More information about the extropy-chat