That’s just editorialization on the source’s part: the facility exists because cursive is legible to humans, but not easy for machines to automatically classify.
My handwriting is not your handwriting, nor is it millions of other Americans' handwritings!
There's also plenty of edge cases: letters get wet, they smudge, get torn or folded, and so forth. A postal system that processes 420 million letters a day[1] with a 99% true positive rate on OCR still needs to divert 4.2 million letters for manual review.
And as a postal service, writing off 4.2mil letters is absolutely unacceptable so thus we must dedicate the resources to mitigate this tail risk.
This is a common pattern, and why I think AI risk is overstated…unless we suddenly decide to start wholesale writing off the consequences of tail risk.
