--On Tuesday, February 10, 2004 7:55 PM -0500 "David F. Skoll" <[EMAIL PROTECTED]> wrote:

That is not a good idea unless you have already built up a substantial
Bayes database, and even then I wouldn't recommend it.

IIRC, SA doesn't start using Bayes until a couple hundred hams and spams have been read. At that point the number of legitimate new tokens should be relatively small.



_______________________________________________ Visit http://www.mimedefang.org and http://www.canit.ca MIMEDefang mailing list [EMAIL PROTECTED] http://lists.roaringpenguin.com/mailman/listinfo/mimedefang

Reply via email to