}"
:0 ci
| /usr/bin/sa-learn --forget
}
<>
| -Original Message-
| From: Smart,Dan
| Sent: Friday, December 05, 2003 12:46 PM
| To: [EMAIL PROTECTED]
| Subject: RE: [SAtalk] SA-Talk poisoning Bayes
|
| Since this is not a delivering recipe (not to a file or pip
ering in the procmail log
LOG="${NL}Forgetting Bayes Poison${NL}"
:0 ci
| /usr/bin/sa-learn --forget
}
<>
| -Original Message-
| From: Smart,Dan
| Sent: Friday, December 05, 2003 8:47 AM
| To: [EMAIL PROTECTED]
| Subject: RE: [SAtalk] SA-Talk poisoning B
This evaluates to an Or statement
:0 Ec
| /usr/bin/sa-learn --forget
---
Not sure if I need to clone,
<>
| -Original Message-
| From: Matt Kettler [mailto:[EMAIL PROTECTED]
| Sent: Thursday, December 04, 2003 10:22 AM
| To: Smart,Dan; [EMAIL PROTECTED]
| Sub
ok that clears it up, sorry for the confusion. I misinterpreted your
explanation. I am clear on how this operates now.
thanks
adam
On Thu, 2003-12-04 at 14:37, Matt Kettler wrote:
> At 02:18 PM 12/4/2003, Adam Denenberg wrote:
> >i thought bayes knew if a message was whitelisted or blacklisted
At 02:18 PM 12/4/2003, Adam Denenberg wrote:
i thought bayes knew if a message was whitelisted or blacklisted and
used that knowledge to prevent impartial bayes learning? Am i wrong in
thinking this was ever the case?
If bayes doesnt use whitelisting/blacklisting to determine auto_learn,
then eve
i thought bayes knew if a message was whitelisted or blacklisted and
used that knowledge to prevent impartial bayes learning? Am i wrong in
thinking this was ever the case?
If bayes doesnt use whitelisting/blacklisting to determine auto_learn,
then every whitelisted mail gets learned as ham and e
At 12:53 PM 12/4/2003, Adam Denenberg wrote:
cant you just whitelist the sa-talk mailing lists since i believe Bayes
does not learn from whitelists, correct?
No, bayes does not use the score contributions of whitelisting in
determining wether or not to auto-learn, but it can still autolearn if the
cant you just whitelist the sa-talk mailing lists since i believe Bayes
does not learn from whitelists, correct?
adam
On Thu, 2003-12-04 at 11:21, Matt Kettler wrote:
> At 11:06 AM 12/4/2003, Smart,Dan wrote:
> >In reading the sa-learn man file, it says running discussions of spam
> >through sa-l
At 11:06 AM 12/4/2003, Smart,Dan wrote:
In reading the sa-learn man file, it says running discussions of spam
through sa-learn is bad. Does SA take this into account already, or should
I create a procmail rule to bypass SA for messages from SATalk and
(possibly) Postfix-List ?
SA's bayesian system
