On Thu, 2004-07-01 at 18:26, Alexander Dalloz wrote: > Am Fr, den 02.07.2004 schrieb Ow Mun Heng um 2:45: > > > Spamass-milter seems to work OK except that I it doesn't really _yet_ > > know how to differentiate spam & Ham > > Save at least 200 SPAM and 200 HAM mails and then run manually sa-learn > to initialize the bayes database. Great.. here's a complain you don't hear often. I _need_ more SPAM. > > > This is what I have in /etc/mail/spamassassin/local.cf > > > > required_hits 5 > > rewrite_subject 1 > > subject_tag [N-SPAM] > > report_safe 0 > > use_bayes 1 > > bayes_path /var/run/.spamassassin > > (but somehow autolearn is off in the headers) > Autolearning only happens up from specific SPAM values, which are > defined in the default rule files. IIRC SPAM is only autolearned from 15 > points and above. Great.. All my spams are less that that..
