Re: daily response 18 mar 2004

On Mar 19 2004, David Nicol wrote:
> Laird Breyer wrote:
> 
> > In summary, I still maintain that the difference between MUA/MTA is
> >
> >close to irrelevant for statistical filtering. It's like an overlay
> >which doesn't fit properly. Note that I've given you reasons which
> >have nothing to do with library management this time.
> >
> 
> I take this to mean the Laird Breyer is in favor of focusing the 
> discussion on the mechanics
> of statistical filtering (SF) rather than focusing the discussion on 
> where SF fits into the
> architecture of message transport and delivery systems. 
> 

;-)

That's not my intention, although I make no apology about
pushing for something that's workable for statistical filters. 

Here's probably a fairly accurate description: I have little of any
value to contribute to those parts of the discussion which do not
impact statistical filtering directly. I *have* thought about
statistical filtering quite a bit, but that isn't to say I know it all.

I'm rather eager to read about the other problems which come up in
filtering, but others have to offer them for discussion. You probably
won't see me replying to a lot of those types of posts.

-- 
Laird Breyer.