I'm a little confused about training with sa-learn, when auto_learn is enabled by default.
Given that auto_learn is working, is it still worthwhile to run true-positives (spam) and true-negatives (hams) through sa-learn, as the INSTALL document says you should do?
Or instead is it only us
I've been exchanging mail with an actual employee of AOL, and his messages are always tagged as spam because they fail the FORGED_MUA_AOL filter. Obviously, he's a little upset about this! Is there something he could be doing differently, or is SpamAssassin simply not going to discern between F