All in all, out of 8,900 messages since the start of the year, it’s successfully filtered out 8500 of them, with only 20 false positives, and 9 false negatives. That’s MUCH better than me doing it myself.
What about the other 471 messages? Wouldn’t any spam that “leaked through” be a false negative?
--
[T]his Court's obligation is to define the liberty of all, not to mandate its own moral code
