Popper killed and eaten by Bayes

From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Sun Jan 04 2004 - 21:54:06 MST


Perry E. Metzger wrote:
>
> Indeed, it does not. The pan-critical rationalist knows he must
> continuously test hypotheses. Merely because his measurement today
> makes Newton look right does not mean in the future he will not find a
> flaw that makes Einstein look more right.
>
> However, the pan-critical rationalist can test hypotheses only if they
> are falsifiable. Non-falsifiable hypotheses don't work very well in
> his epistemology.

Ah, falsificationism... I remember those days.

But... and this is one of the most beautiful things I have ever seen...
all that is worthwhile in Popper is but a special case of Bayesian
reasoning, and in the pure light of Bayes, some of Popper turns out to be
wrong.

http://yudkowsky.net/bayes/bayes.html

-- 
Eliezer S. Yudkowsky                          http://intelligence.org/
Research Fellow, Singularity Institute for Artificial Intelligence


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:43 MDT