They do well enough today...but it's quite evident that they will have a
tough time surviving the spamorphosis...even in the ensuing weeks. It
seems that only sender whitelisting is stopping my current barrage...I
use Bayesian just to auto-drop...not to permit.
I can't wait for some permutation software to start trying to guess my
whitelists
As has been stated here, content filters suck. However, auto-trained
Bayesian filters do well enough (provided one doesn't get too much
quoted spam...) to be the last line of defense for rough cut sorting
of mail into 'probably spam' and 'probably not spam' piles for the
user to pick through.
_______________________________________________
Asrg mailing list
Asrg(_at_)ietf(_dot_)org
https://www1.ietf.org/mailman/listinfo/asrg