On Thu, Nov 09, 2006 at 07:01:33PM +0000, Ian Eiloart wrote:
> 
> 
> --On 9 November 2006 18:28:10 +0000 Chris Lightfoot <[EMAIL PROTECTED]> 
> wrote:
> 
> >On Thu, Nov 09, 2006 at 06:05:28PM +0000, Ian Eiloart wrote:
> >>--On 9 November 2006 17:28:07 +0000 Chris Lightfoot
> >><[EMAIL PROTECTED]>  wrote:
> >    [...]
> >>> If a user decides a piece of mail is spam, it's spam (if
> >>> they change their decision then obviously the most recent
> >>> decision holds).
> >>
> >>Ah, well by this definition, a human can never make a wrong decision,
> >>just  a decision that they might later revise.
> >
> >yes, that's kind of the point -- it's a bit futile for the
> >machine to try to tell the user what kind of email they do
> >or don't want. the flow of information is the other way
> >around, and the best the machine can do is to make the
> >same decisions that the user would if presented with the
> >mail.
> 
> Oh, FFS.
> 
> You said humans never made errors. Well, they do. They do accidentally 
> delete messages they wouldn't want to, when they're buried in spam. That's 
> why spam filtering is desirable. And, actually a machine can do it better, 
> in the case where a user gets a lot of spam.

there's a distinction between random errors and actual
errors of classification. obviously there is a random
error rate for both human and machine classification of
mail. however, there are also systematic errors. a person
will not make systematic errors of this kind in
classifying spam (by definition -- if they decide that
they want a certain mail, then they did, end of story).
spam filters do. no matter how often you tell somebody
that (say) the fact that a mail came through an IP which
is on a `black list' or that it contains a cid:... type
image reference means that it is spam, they will not
change their minds if the message in question is one they
actually wanted to receive.

-- 
``Started with a knife, then degenerated to a hacksaw, then a hammer and
  eventually a very big hammer. Suffice to say, I don't think they are in
  any way user serviceable.'' (Chris King, on electric toothbrush repair)

-- 
## List details at http://www.exim.org/mailman/listinfo/exim-users 
## Exim details at http://www.exim.org/
## Please use the Wiki with this list - http://www.exim.org/eximwiki/

Reply via email to