RE: Seed AI milestones (was: Microsoft aflare)

From: Ben Goertzel (
Date: Wed Feb 27 2002 - 11:23:59 MST


I found your reply quite astute.

However, what I said was that I could create a mathematical formalization of
the different levels of self-modification.

I did NOT say that I could create a pragmatically feasible, 100% accurate
algorithm for measuring the level of self-modification being displayed by a
given system.

Indeed, the mathematical formalization I have in mind will involve some
very-hard-to-compute quantities, and hence will be of value only

a) conceptually

b) in that it may spur the creation of approximation algorithms that are
more tractable but not guaranteed to yield accurate results

These limitations are why I have not bothered to write up such a
formalization so far.

-- Ben G

> In order to tell the difference between the type 1) , type 2) , type 3)
> modifications, you have to
> 1) Select (and accurately describe!) some relevant tasks.
> 2) Create some measures for the efficiency of their implementation.
> 3) Show some differency between their efficiency in the different
> implementations.
> I am not a real expert in complexity theory, but I can tell that it is
> quite unprobable that you have
> significant results in the above three points without generating so much
> hype in the complexity
> theorist community that I would not know about it.
> Best regards, Christian

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:37 MDT