Re: Scenario for early hard takeoff

From: Matt Mahoney (matmahoney@yahoo.com)
Date: Tue Sep 04 2007 - 08:54:23 MDT


--- Mike Dougherty <msd001@gmail.com> wrote:
> would people be willing to host this distributed computing grid if
> participation was the only requisite for being able to ask it for
> information? What if the local agent were able to ask the users for
> information in order to fulfill requests for other others? Is this a
> manageable strategy, or is it really just chaos?

I considered the idea of persistent queries in my MSCS thesis in 1998. When
you ask a question, you are also revealing that you are interested in a
particular topic. For my thesis I looked at the feasibility of a fault
tolerant, self repairing distributed search engine for an unreliable
distributed database, such as a file sharing network. It is hard to tell from
the title and abstract, however. http://cs.fit.edu/~mmahoney/thesis.html The
idea is that each node in the network acts as an expert on a narrow subject,
and knows how to relay questions on other subjects that it can't answer
itself.

I still believe that a distributed system has inherent advantages over
centralized systems like Google. The silicon component of the Internet has
1000 times more computing power than Google's supercomputing clusters, and
most of it is unused. I described 3 scenarios for acquiring computing power
(buy, beg, or steal), but a fourth is to barter. People are willing to give
up personal information and install software that hooks into a distributed
system if they get some perceived benefit, such as free email, webhosting, or
more convenient access to data.

-- Matt Mahoney, matmahoney@yahoo.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:58 MDT