[EMAIL PROTECTED] said: > How effective is the new bayesian filter on a site-wide installation?
Depends on your users ;) If they all talk about the same stuff, quite good; if they're totally diverse, it won't be as good. But I would say the worst accuracy rating would probably be about 80% effectiveness, and I would doubt it would actively cause false positives. Note that it's still in development, and site-wide use hasn't really been fully thought through yet. --j. ------------------------------------------------------- This sf.net email is sponsored by: To learn the basics of securing your web site with SSL, click here to get a FREE TRIAL of a Thawte Server Certificate: http://www.gothawte.com/rd524.html _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk