Re: [sl4] A model of RSI

From: Mike Dougherty (
Date: Wed Sep 24 2008 - 18:41:28 MDT

On Wed, Sep 24, 2008 at 8:25 AM, Matt Mahoney <> wrote:
> Perhaps it would help to give some real life examples of what we want to do, for example, robots working in a factory that builds better robots. But the first generation has to know what "better" means. We know that adding more memory or faster processors makes for "better" computers, but we only know that because we are still smarter than both generations. Suppose that the child robot had twice as much memory but the software was unable to use it effectively. How would the robots detect this problem?

Does this suppose that the definition of "better" is immutable? If
no, over what duration of time should the definition be used?

> We assume (but don't know) that adding more neurons to our brains would make us more intelligent and therefore better. But why do we want to be more intelligent? Because our brains are programmed that way. Intelligence requires both the ability to learn and the desire to learn. Suppose that we engineer our children for bigger brains, but in doing so we accidentally remove the desire to be intelligent. Then our children will engineer our grandchildren according to their interpretation of what it means to improve, not our interpretation.

Is that better for us, or better for them? I posit that our
definition of 'better' grows increasingly obsolete if it remains fixed
among the measurements and values of a (by then) bygone era.

> Self improvement requires a test or goal that cannot be altered through generations. Assuming that goal is "intelligence", we are not smart enough to test for it above our own level. If we are, then perhaps someone could describe that test. Otherwise, "better" is by default going to be measured by counting descendants.

I could only conceive of 'better' being used to examine the difference
in local minima/maxima between arbitrary regions of spacetime ;which
is how I visualize your original point about reaching a goal in less
time (faster) or to a greater extent (quantity).

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:03 MDT