Hello Jeff, Sunday, August 21, 2005, 11:21:58 PM, you wrote:
JG> I found BayesIt very poor even after training. I have switched to K9 JG> now and find it much better. And, for a flipside, I've found it great. As an example,one of my accounts had 68 messages in it when I returned home tonight. One of them was legitimate. All the rest was spam. BayesIt and Bayes Spam Filter, working together, automatically deleted 62 messages. They let through the one legitimate one. One ended up in the Junk folder, and four ended up in my inbox. The four in my inbox were all very short messages, and an analysis of my logs shows that it was Bayes Spam Filter that let them through - it's been running alongside BayesIt for a while now, but seems to take longer to train. In my experience, I've never seen something as easy and simple to set up as BayesIT, or as quick to get working - I installed it a long time ago, marked all my mail as ham and/or spam, and then started marking mail that got through. After a week, it was incredibly rare to see anything slip past. They key seems to be the training - but BayesIt makes that very easy. Sadly, it also doesn't make it very clear that you have to train it in both ham and spam... -- Best regards, Philip mailto:[EMAIL PROTECTED] Using The Bat! v3.51.10 on Windows XP 5.1 Build 2600 Service Pack 2 ________________________________________________ Current version is 3.51.10 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html