I don't know if this really fits in this subject or not. However, I keep
thinking while reading this thread if anyone considers real opt-in
advertisements/messages that get tagged by SA (like from OshKosh,
Travelocity, Lands' End, etc.) to be a FP or not.
A False positive is anything that is marked as SPAM that is not unsolicited. A requested mail from Land's End that gets tagged is certainly a false positive.
My mails from amazon and paypal and ebay are not generally caught (or really, ever anymore) by SA.
Do site-wide Bayes installs have a hard time differentiating without feeding?
Initially? Some are more likely to hit than others. Still, I haven't seen a FP on a retail non-spam message in a long time, so it's quite possible that 2.60 is a lot better "out of the box" but my bayes has been screening for quite a while now.
Most things that get mismatched as spam are getting marked by my procmail and/or my Mail.app "Junk Mail" filters, and not by SA.
--
If fashion is your trade then when you're naked I guess you must be unemployed.
smime.p7s
Description: S/MIME cryptographic signature
