News for hackers. Stuff that matters.
Re:Paul Graham provides answer to spam emails (2002) by nailer on Friday May 03, 2019 @07:13AM (#19817300)
Wait did Paul Graham inspire SpamAssassin (the original 'big deal' Bayesian spam filter)?

Cool circa-2002 game for Unix nerds: you have 60 seconds to telnet to port 25 and generate the highest spamassassin score.

Re:Paul Graham provides answer to spam emails (2002) by varjag on Friday May 03, 2019 @07:16AM (#19817314)
SpamAssassin predates the article. Not sure it had Bayesian filtering from the start tho.

Paul Graham however definitely championed and popularized the idea of Bayesian filtering.

Re:Paul Graham provides answer to spam emails (2002) by dredmorbius on Friday May 03, 2019 @07:37AM (#19817445)
SA preexisted Bayesian filters by a year. Bogofilter, a Bayesian classifier, was inspired by Graham.

http://www.catb.org/~esr/bogofilter/bogofilter.html

https://en.m.wikipedia.org/wiki/Apache_SpamAssassin

Spamassassin's Bayesian classifier credits Graham.

https://metacpan.org/release/Mail-SpamAssassin/source/lib/Ma...

Re:Paul Graham provides answer to spam emails (2002) by yesiamyourdad on Friday May 03, 2019 @11:28AM (#19819269)
He directly inspired SpamBayes, a Python based plugin for Outlook. That thing was like pure black magic back in the day. Worked amazingly well.

Also, Yahoo! Mail implemented at least partly Bayesian based filtering not long after the original PG essay.

I'm guessing GMail is using some kind of statistical filter for not only spam, but general categorization, though as others have pointed out GM is pretty aggressive in filtering. I think that GM might be using collaborative data, aggregating across user behavior and I believe many users deal with signups they're tired of by marking as spam, sharing that behavior across the userbase would cause things that you willingly signed up for to be filtered out.