From: Joshua Fox (joshua@joshuafox.com)
Date: Mon Nov 12 2007 - 00:09:54 MST
Jef Allbright wrote:
> I would argue that it is practical to test and refine models of moral
> reasoning using the best currently available computing elements,
Yes.
> as long at they are properly fed and allowed to sleep, etc.
Huh?
> They certainly wouldn't qualify as "general intelligence",
Right. My "morality simulator" idea does _not_ involve any AGI.
To compare, Although the analogy is not exact, "economics simulators"
can range between 1. Trivial evaluation of a known economic function
-- plug in values and calculate.
2. M.U.L.E.
3. the economics of Second Life (as analyzed, e.g., by Edward Castranova).
"Simulations" can involve human actors as well as computer actors
(non-AGI, of course).
However simple they are, surely they teach something.
Joshua
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:00 MDT