Bryan Carbonnell
carbonnb at gmail.com
Sat Aug 11 07:07:39 CDT 2007
On 8/10/07, jwcolby <jwcolby at colbyconsulting.com> wrote: > I used a Bayesian filter with outlook and tried to do so again but it > wouldn't install. When it worked, it worked fairly well (98% rate) but had > false positives and false negatives, few but still there. Having 2% hiding > in the 100 is almost worse than 50%. You have to look at each one to find > the 2 in 100 that you need to recover. THAT is as much of a PITA as just > hitting the delete key 50 times a day. Yea, but how long does it take you? I get on the order of 300+ a day and it takes me less than a minute to go through the list. > There are a million systems out there for handling spam, none of them > perfect. I have tried about 500,000 of them so far, I know none of them are > perfect. Nope, you're right. But some are less perfect than others. > In the meantime, I will be trying this one for awhile. I have had to > respond to a handful of such "response required" from a handful of people I > have emailed, and I did so, no biggie. I can see that some think it is a > poor idea but such is life. Actually most e-mail systems administrators think it is a horrible idea and the inventor of it should be drawn an quartered on a pile of spam. I think they would appreciate a poor idea. I'm talking about mail admins from Roadrunner, Hotmail, Time/Warner, Nortel. Not small name players by any stretch of the imagination. -- Bryan Carbonnell - carbonnb at gmail.com Life's journey is not to arrive at the grave safely in a well preserved body, but rather to skid in sideways, totally worn out, shouting "What a great ride!"