My mailserver that SA runs on has no local accounts and forwards all mail to another server. I have qmail-scanner quarantining suspicious mail. Over the last 3 or 4 months I've collected tons of spam samples, but only collected 20 or so hams. I can't think of any good way to get a reasonable sampling of hams. So the way I see it, I just can't use Bayes, but I thought I'd ask for a reality check before giving up.
TIA, Russ Ringer ------------------------------------------------------- This SF.Net email sponsored by: Parasoft Error proof Web apps, automate testing & more. Download & eval WebKing and get a free book. www.parasoft.com/bulletproofapps1 _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
