FW: Your message to Python-Dev awaits moderator approval
Well, if SpamAssassin wasn't so stupid, I suppose you could have read this msg <wink>. -----Original Message----- From: python-dev-admin@python.org [mailto:python-dev-admin@python.org] Sent: Tuesday, August 27, 2002 10:38 PM To: tim.one@comcast.net Subject: Your message to Python-Dev awaits moderator approval Your mail to 'Python-Dev' with the subject The first trustworthy <wink> GBayes results Is being held until the list moderator can review it for approval. The reason it is being held: Message has a suspicious header Either the message will get posted to the list, or you will receive notification of the moderator's decision.
Tim> Well, if SpamAssassin wasn't so stupid, I suppose you could have Tim> read this msg <wink>. I think that response was generated by Mailman. SpamAssassin does nothing more than tag messages... Skip
FYI, here's the closest thing to a real false positive I've seen so far: """ What is the key for to break the script execution in pythonwin? Tnx -- -- Neo ************************************ Follow the White Rabbit... Knock Knock Neo... ICQ #42292922 Webmaster di www.thezion.net La prima community di web developer Ad Free The first web developer's community Ad Free ************************************ """ Other "false positives" included a strangely quoted copy of the Nigerian scam, "STOP PAYING $19.95 or more TODAY for your web site, WHEN YOU CAN GET ONE FOR ONLY $11.95 PER MONTH!", something entirely composed of high-bit characters except for a URL pointing to a Russian hosting site, "I am looking for young models (prefer early teen 14-16 year old female) for nude and semi-nude photography", "Everyone likes making easy money. This place pays you 50 cents for every hour you browse the web!!!", "We want to invited you for a new adult TOP50 on http://www.50freepics.com", and my favorite: These girls are not phonesex workers. They are horny girls who are on the line cuz it's free phonesex for them. Unfortunately, I don't think I can fudge this system to let msgs thru from my sisters <wink>.
Tim> FYI, here's the closest thing to a real false positive I've seen so Tim> far: I have much smaller spam and ham corpora (currently about 400 msgs each), but both consist only of messages sent to me in the past couple weeks (though not all messages sent during that interval), so some of the header clues which skewed Tim's tests shouldn't be present. Using my currently undeleted Python mail as "unknown" (but which doesn't actually contain any spam), I saw two false positives. One had an attached gif image. The other was a one-line text+html message whose "words" were thus dominated by the HTML tags in the second part. Once my spam and ham grow to something more like 2000 each I will try Tim's technique of splitting them into smaller chunks, training on one chunk, then testing against the remaining chunks. Skip
"TP" == Tim Peters <tim.one@comcast.net> writes:
TP> [Skip Montanaro] >> I think that response was generated by Mailman. SpamAssassin >> does nothing more than tag messages... TP> Like I care who the stupid party is -- the smart party was TP> Martijn Pieters, who now stays up all night waiting to approve TP> my msgs <wink>. Tim's of course joking, because he cares intimately and deeply about all things. But actually it was a combination of brilliant <wink> software. SA tagged the message with a X-Spam-Level: header value that the python-dev's Mailman filter was set up to catch as "suspicious". -Barry
On Tue, Aug 27, 2002 at 11:20:06PM -0400, Tim Peters wrote:
Like I care who the stupid party is -- the smart party was Martijn Pieters, who now stays up all night waiting to approve my msgs <wink>.
Studying or waiting on Tim Peters, makes no difference ;) -- Martijn Pieters | Software Engineer mailto:mj@zope.com | Zope Corporation http://www.zope.com/ | Creators of Zope http://www.zope.org/ ---------------------------------------------
participants (4)
-
barry＠python.org -
Martijn Pieters -
Skip Montanaro -
Tim Peters