Quoting Jim Coulter <[EMAIL PROTECTED]>:OK. Tried the -tD. There is says that my Bayes database only has 20 spams
in it. (<200).
But I have had thousands of SPAMS. Apparently, I've only fed 20 of them for
sa-learn. I seem to recall that there is a flag to set for Bayes to pick up
on all Spam messages over a certain score. Have to go and review again.
from "man Mail::SpamAssassin::Conf"
bayes_auto_learn_threshold_spam n.nn (default: 12.0)
Doesn't that seem unreasonably high? Doesn't a score of 9.0 have a 100% spam percentage?
--
You know, in a world in which Bush and Blair can be nominated for the Nobel Peace Prize, "for having dared to take the necessary decision to launch a war on Iraq without having the support of the UN" I find myself agreeing with Tom Lehrer: satire is dead. - Neil Gaiman
smime.p7s
Description: S/MIME cryptographic signature
