> We also recognize that not all inboxes are alike. So while your neighbor may love weekly email newsletters, you may loathe them. With advances in machine learning, the spam filter can now reflect these individual preferences.

I really wonder how these preferences are reflected if someone hasn't been using spam filters much. I get maybe at most a dozen spam emails escaped a year, and the rest of the emails go through (all mailing lists... I am on a lot of mailing lists) so I get about 50+ emails per day from just DL. So I barely ever need to mark something as spam, or even more something to another folder, so how does Google know what's my preference? It sounds like people who don't actively mark spams are less likely affected...

From looking at that, it appears to be a set of tools that high-volume senders of email can use to help ensure they don't get incorrectly flagged as spam. It seems to do nothing to help high-volume receivers of email.