|
|
|
|
|
by wizzwizz4
1726 days ago
|
|
Classical AI (i.e. manually-constructed email rules) is much better for this kind of thing, in my experience. You don't get spurious false positives; you can predict every false positive in your head before you even get the email, and if you want you can even add an extra rule to prevent it from happening in the first place! “Unknown / trusted / spam senders” lists are a basic implementation of this concept. |
|
Gmail thought that adding Snooze was enough to get feature parity and kill Inbox, but Bundles were by far the feature keeping me on Inbox.