Re: basic BayesCraft training?

From: Marc Geddes (
Date: Wed Mar 16 2005 - 23:21:45 MST

Bayesian reasoning is a theoretical ideal that has got
little to no practical connection to reality.

Any AGI worth its salt would be absorbing knowledge
far faster than it could apply Bayes theorem to. It
would quickly run into computational intractibility
and have to apply ever greater ingenuity in order to
find approximations and short-cuts in order to carry
on reasoning. This would quickly take it further and
further from the sterile theoretical ideal that is
Bayes Theorem.

I've often seen Wilson and Yudkowsky saying that human
reasoning is 'broken' where as Bayes is somehow the

Wilson and Yudkowsky are wrong, wrong, wrong.

It is not human reasoning that is broken. It is Bayes
theorem that is broken.

It appears to be a fundamental fact of nature that
computation per unit volume can only be finite in the
universe. So intractibility is a fundamental fact of
nature, not a 'practical constraint'. It is the
'theoretical ideal models' (which assume infinite
computational power) that are broken, not the models
assuming only finite resources.


THE BRAIN is wider than the sky,  
  For, put them side by side,  
The one the other will include  
  With ease, and you beside. 
-Emily Dickinson
'The brain is wider than the sky'
Please visit my web-site:
Mathematics, Mind and Matter
Find local movie times and trailers on Yahoo! Movies.

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:50 MDT