Date: Sat, 17 Jul 2004 00:04:17 EST-10EDT,10,-1,0,7200,3,-1,0,7200,3600 Subject: [UnixOS2_Archive] No. 400 ************************************************** Friday 16 July 2004 Number 400 ************************************************** Subjects for today 1 Re: Mailman Spam : Steve Wendt" 2 Re: Mailman Spam : Dave Yeo" **= Email 1 ==========================** Date: Thu, 15 Jul 2004 19:38:27 -0700 (PDT) From: "Steve Wendt" Subject: Re: Mailman Spam On Thu, 15 Jul 2004 00:08:01 -0800, Dave Yeo wrote: >>>From my experience, the Bayesian filtering is completely automatic, but >>*only* after configuring bayes_path and bayes_learn_to_journal parameters. > >Hmm, what version are you using? 2.6.3. > The bayesian classifier can only score new messages if it already has 200 known >spams and 200 known hams. Right, but it starts collecting this stuff automatically. It just doesn't apply the bayesian rules at first. >Don;t remember anything about bayes_path and bayes_learn_to_journal parameters. >All bayes info here is kept in ~/.spamassassin/bayes* Perhaps things are different depending on whether you use site-wide or per-user configurations. ----------- "Good people do not need laws to tell them to act responsibly, while bad people will find a way around the laws." - Plato (427-347 B.C.) **= Email 2 ==========================** Date: Thu, 15 Jul 2004 23:12:54 -0800 From: "Dave Yeo" Subject: Re: Mailman Spam On Thu, 15 Jul 2004 19:38:27 -0700 (PDT), Steve Wendt wrote: >>Don;t remember anything about bayes_path and bayes_learn_to_journal >parameters. >>All bayes info here is kept in ~/.spamassassin/bayes* > >Perhaps things are different depending on whether you use site-wide or per-user >configurations. Could well be. I was using a per-user setup that I adapted from some Windows instructions with a pop3proxy meant for windows. Dave