Makk Gingel suggested:
> The hypothesis: It is possible, at least in principle, to construct a
> machine which acquires all the skills and knowledge it requires to
> function in the world via learning. Human provided domain-specific
> knowledge, even of highly abstract or primitive domains, is
> unnecessary. The question then is what is the minimal such machine,
> and how do we go about building it.
No. This is how you get a useful program given millions of years and
plenty of trials. Alternately, this is how you get a useful program
when you can get instant feedback as to how good your general
"learning system" is, so finding the best one is just a matter of
searching for it. (The latter is another way of saying the former.
"Instant" is a point of view.)
If you intend to get there before nanotech is done, you do it the way
Eliezer is doing it.
I encourage you NOT to just skim this document. I assure you that
this question is not only fielded but answered in his summary.
-Dan
-unless you love someone-
-nothing else makes any sense-
e.e. cummings
This archive was generated by hypermail 2b29 : Thu Jul 27 2000 - 14:11:24 MDT