On Wed, Apr 28, 2004 at 06:16:17PM +0200, Alberto Gonzalez Iniesta wrote: > On Wed, Apr 28, 2004 at 11:00:11AM -0400, Dan Christensen wrote:
Hi, > > I've heard really good things about crm114: > > > > http://crm114.sourceforge.net/ > > > > It's faster than spamassassin and more accurate than spamassassin or > > the author. Licensed under the GPL. It only does Bayesian learning > > (no hard coded rules like SA), but it ends up doing better than SA > > after moderate training. > > I use it at home. It's way better that spamassassin, but requires some > training. What I don't really know is how effective it'll be on technical > mailing lists (which receive mails with dumps, kernel confs, and other > 'strange' content that may appear like anything but a 'normal' mail). If it's bayes based it will do a very good job cause words in technical mails differ from the ones in spam a lot. I personaly prefer bogofilter[1] cause I started using it about a year ago and my wordlist is perfectly trained for me now. It's written in C, fast and consumes little resources. Sven [1] http://bogofilter.sf.net backports for woody avaible at backports.org -- If God passed a mic to me to speak I'd say stay in bed, world Sleep in peace [The Cardigans - No sleep]
