Hello Robin, I felt your pain. All bad words aside, I recommend trying bogofilter, which uses a Bayesian technique. It has cut my SPAM by 75% especially Viagra. You still have to teach it and the more Spam you feed it the more accurate it becomes.
Read more about it here: http://bogofilter.sourceforge.net/ I used this tutorial to get me started: http://wiki.volker-boehme.de/doku.php?id=wiki:bogofilter Side Note: Does anyone know of any good Spam and Ham corpuses???? --------------------------------------------------------------------- QmailToaster hosted by: VR Hosted <http://www.vr.org> --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]