On 2025-02-16 at 10:38:38 UTC-0500 (Sun, 16 Feb 2025 10:38:38 -0500)
Alex
is rumored to have said:
[quoting me]
TxRep (like AWL) is fed not by Bayes learning (sa-learn) but rather
it
tracks the combination of an address and a source IP range (/24) with
a
tally of the SA scores of messages usi
>
>
>
> > Is there any benefit to training an email that's already hitting
> > bayes99?
>
> Yes. The tokens which made it hit 99% are already doing their jobs, but
> the rest of the message that Bayes isn't seeing as spammy may turn out
> to be what makes the next spam hit 99.9%
>
I have noticed t
On 2025-02-14 at 17:00:03 UTC-0500 (Fri, 14 Feb 2025 17:00:03 -0500)
Alex
is rumored to have said:
Hi,
I'm using SA v4 and trying to find ways to minimize the amount of junk
that
isn't tagged. Emails like "1-hour free consultation" or "buy this
event
list" or "salesforce optimization" or "HR
Alex writes:
> These also aren't always one-offs, but maybe a dozen or twenty of each over
> a short period that get through, likely before the URIs are blocked through
> other means. Other times they don't have a link at all.
Sounds like fairly aggressive greylisting is in order.
On Fri, 14 Feb 2025, Alex wrote:
Hi,
I'm using SA v4 and trying to find ways to minimize the amount of junk that
isn't tagged. Emails like "1-hour free consultation" or "buy this event
list" or "salesforce optimization" or "HR consulting" that already hit
bayes99 (and bayes999) but are still jus
