From: Jef Allbright (jef@jefallbright.net)
Date: Mon Aug 14 2006 - 23:39:19 MDT
On 8/14/06, Anthony Mak <anthony.mak@iname.com> wrote:
> Dear all,
>
> Does anyone know any work or paper people have done in
> the past or present about how to measure (quantify) morality?
> The motivation is, for a learning system to learn how to be
> moral, I believe it is necessary to have an objective function
> to measure how "moral" the machine already are, so that
> a machine learning alogorithm can work. Are there any
> works for example in philosophy where people attempted
> to device scheme/method/framework to measure morality?
>
> At the moment, I can only imagine using some questionaire
> type query to attempt to measure a person's "moral IQ",
> be it a normal person or machine person.
> PS. I guess another approach is to try to find all the +ve
> and -ve effects from an agent's actions and try to sum them
> up.
>
> Any reference to papers or books or other source will be
> extremely helpful.
>
Okay, but which (whose) system of morality do you want to measure?
Muslim or western capitalist? Klingon or Romulan? Children or
adults?
Generally, if you can define something objectively you can (in theory)
measure it objectively.
The difficulty with measuring morality is that it is a function of the
extent actions are seen to promote *subjective* values over increasing
scope. Therefore we could proceed to capture a snapshot of shared
values of a population of interest, survey the expected effectiveness
of their actions (actually the principles upon which they base their
actions) and assign a morality value for that system.
It is important to note that this measurement of morality would be
strictly relative to the snapshot of values and point of view of the
population. Thus you can certainly detect relative progress, an arrow
of morality ratcheting forward, but to the extent that value matrices
are incongruent, you can't assign any objective scale or direction to
the progress nor make any objective comparisons of morality between
different populations and their values.
The good news is that morality doesn't have to be objective for US to
evaluate our actions for expected progress in terms of OUR subjective
goals. The arrow points outward in the direction of what works.
- Jef
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:57 MDT