Talks to Watch

How the US Postal Service reads terrible handwriting

7M views · Aug 8, 2022 · 7:53 · 4 HN recommenders · 8 mentions · discussed 2022–2026

Tom Scott visits the USPS Remote Encoding Center in Salt Lake City, where keyers decipher mail images machines cannot read. It shows the lengths taken to decode bad handwriting.

Why Hacker News points people here: Recommended in address and OCR threads as a look at the last human mail-coding operation.

“This Tom Scott video shows some of the surprising (to me) lengths to which the USPS does go to figure out the right address”HN comment, 2023

What Hacker News said 8

RecommendsbombcarMar 2023

“might be of interest - it has some of what the machines are trying to read and what accuracy they need.”

Shows what machines read and the accuracy required.

Full comment

this video might be of interest - it has some of what the machines are trying to read and what accuracy they need.

in “What Is the Most Minimal UK Address Possible?” · view on HN
RecommendssimmonmtMar 2023

“This Tom Scott video shows some of the surprising (to me) lengths to which the USPS does go to figure out the right address”

Surprising lengths USPS goes to decode bad handwriting addresses.

Full comment

This Tom Scott video shows some of the surprising (to me) lengths to which the USPS does go to figure out the right address: this video Obviously this doesn't apply to your case, but I certainly didn't think they'd have a national center for decoding terrible handwriting.

in “What Is the Most Minimal UK Address Possible?” · view on HN
RecommendsLordDragonfangApr 2024

“Tom Scott did a great video showing the last one in operation.”

Shows the last remaining manual mail coding operation with stenography-like keyboards.

Full comment

Tom Scott did a great video showing the last one in operation. They use totally unique keyboards with what is essentially a stenography system: this video

in “Amazon ditches 'just walk out' checkouts at its grocery stores” · view on HN
RecommendsCaligatioJul 2024

“here's a Ton Scott video about the same topic”

Interesting Tom Scott video on the same topic.

Full comment

And like almost all things that are interesting, here's a Ton Scott video about the same topic: this video

Cites itomginternetsDec 2022
Full comment

Actually, we're talking about both, and you are wrong on both counts. If you weren't, you would be able to point to an existing system that has demonstrated the capability of classifying an image set on the order of iCloud's, without producing a false-positive. You can't, because such a system doesn't exist. Even the "solved" problem of OCR isn't capable of such a feat: this video

in “Apple Kills Plans to Scan for CSAM in iCloud” · view on HN
Cites itbombcarMar 2023

“There's a specific branch of the post office that works on these - the dead letter office”

Shows the postal branch that handles undeliverable letters.

Full comment

One of Don Rosa's books has the letters he sent to a friend in college, each with a drawing on the envelope and less and less address, until finally it was all drawing and barely part of a name - they all got (eventually) delivered. There's a specific branch of the post office that works on these - the dead letter office: this video

in “What Is the Most Minimal UK Address Possible?” · view on HN
Cites ityencabulatorFeb 2026

USPS handwriting recognition uses restricted dictionary and human fixers.

Full comment

> Though USPS has been doing handwriting recognition since the 80's. On a very restricted dictionary of possible content, with a pool of people employed to fix anything where the computer is unsure. this video

in “Using an Engineering Notebook” · view on HN
Cites itshagieApr 2026

OCR handling hand-lettered addresses at the US Postal Service.

Full comment

As a profession (and under time constraints) ... Tom Scott : How the US Postal Service reads terrible handwriting - this video Part of the story is that the OCR that is handling hand lettered addresses. I also chuckled at the cursive letter recognition sheet on the side of the cube.

in “AI helps add 10k more photos to OldNYC” · view on HN