We are currently using SA without DCC, pyzor or razor and have a detection rate of about 75-90% (but getting slightly better as we feed bayes).
What improvement could we expect by implementing one (or all) of the above? What kind of processing delays are there for each? If we were to implement one, which is recommended?
Thanks...
Dave
------------------------------------------------------- The SF.Net email is sponsored by EclipseCon 2004 Premiere Conference on Open Tools Development and Integration See the breadth of Eclipse activity. February 3-5 in Anaheim, CA. http://www.eclipsecon.org/osdn _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
