161–170 of 267 posts
They should ask a medical school for help ;) My family is Ivy-League, all the way, and has the worst goddamn cursive writing I've ever seen. It can take me an hour to read a Christmas card from my sister.
I've always wondered how pharmacists can read those prescriptions. There must be some kind of course in university that they followed.
> particularly for Americans who never learned cursive in school. American schools don’t teach it anymore?!
Why would they? It’s an anachronism optimizing for writing speed
As a child, even many years before having access to personal computers or any other kind of typewriting, I have switched my handwriting from cursive to using the kind of sans-serif typefaces used in technical drawing and since then I have never written again cursively, with the exception of my signature, where required on official documents.
Nevertheless, I believe that some kind of calligraphy is necessary for developing fine motor skills in children, unless it is replaced with some other activity that requires a similar precision in the movements of the fingers and of the hand.
Earlier quoted context omitted.
Oh, ok then.
I mean, all you have to do is feed the image to ChatGPT, and it will read it basically as well as you can. Denying/downvoting reality is always an option, of course.
It gets them wrong for me, but maybe it will get them right for you. Maybe you're better at prompting or have access to a better model or something.
Before commenting asking about why they don't just use LLMs, please note that the article specifically calls out that they do, but it's not always a viable solution: > The agency uses artificial intelligence and a technology known as optical character recognition to extract text from historical documents. But these methods don’t always work, and they aren’t always accurate. The document at the top is likely an especi…
OK, fair enough, but can you find one in this article that's hard for an LLM? The gnarliest one I saw, 4o handled instantly, and I went back and looked carefully at the image and the text and I'm sold. Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Later I signed up, went to the current missions, and they all seem to pos…
I'm confused by what you're asking. Are you asking me to like (upvote) your comment if this is a crowdsourcing project? Don't we already know it is a crowdsourcing project?
Earlier quoted context omitted.
Determining whether the latest off the shelf LLMs are good enough should be straight forward because of this: “Some participants have dedicated years of their lives to the program—like Alex Smith, a retiree from Pennsylvania. Over nine years, he transcribed more than 100,000 documents” Have different LLMs transcribe those same documents and compare to see if the human or machine is or accurate and by how much.
This is not an LLM problem. It was solved years ago via OCR. Worldwide, postal services long ago deployed OCR to read handwitten addresses. And there was an entire industry of OCR-based data entry services, much of it translating the chicken scratch of doctor's handwiting on medical forms, long before LLMs were a thing.
Looking at the (admittedly single) example from the National Archives seems a bit more open than perhaps the other two examples. It’s not impossible thst LLMs could help with this
Earlier quoted context omitted.
Determining whether the latest off the shelf LLMs are good enough should be straight forward because of this: “Some participants have dedicated years of their lives to the program—like Alex Smith, a retiree from Pennsylvania. Over nine years, he transcribed more than 100,000 documents” Have different LLMs transcribe those same documents and compare to see if the human or machine is or accurate and by how much.
This is not an LLM problem. It was solved years ago via OCR. Worldwide, postal services long ago deployed OCR to read handwitten addresses. And there was an entire industry of OCR-based data entry services, much of it translating the chicken scratch of doctor's handwiting on medical forms, long before LLMs were a thing.
It's a really interesting project. But boy do they make it hard to participate. * Article doesn't provide a direct link to the topic mission * Signup is pretty easy. Well organized and even gently requires you to have two forms of 2FA. * Sign up complete. Go back to the primary page and try to find the mission. A little buried but not too deep. * Notice I'm not signed in. Ok, let's do that. Now I'm back on the main p…
Once I was logged in I spent another 45 minutes trying to find a document to transcribe. Every single one I found or was given from a challenge had either already been transcribed or was a typewritten document or manifest that the OCR had already done an OK job with. I reviewed a few documents for accuracy, closed the browser, and never went back.
It's a shame it's so hard to use. I really was hoping for something I could pop open for 15-30 minutes a day as a break from work and contribute to instead of doing a crossword or watching a video.
Earlier quoted context omitted.
This is not an LLM problem. It was solved years ago via OCR. Worldwide, postal services long ago deployed OCR to read handwitten addresses. And there was an entire industry of OCR-based data entry services, much of it translating the chicken scratch of doctor's handwiting on medical forms, long before LLMs were a thing.
LLMs improve significantly on state of the art OCR. LLMs can do contextual analysis. If I were transcribing these by hand, I would probably feed them through OCR + an LLM, then ask an LLM to compare my transcription to its transcription and comment on any discrepancies. I wouldn't be surprised if I offered minimal improvement over just having the LLM do it though.
Even if LLMs can push a 99.9% accuracy to 99.99, at least an OCR-based system can be audited. Ask an OCR vendor why the machine confused "Vancouver WA" and "Vancouver CA" and one can get a solid answer based in repeated testing. Ask an LLM vendor why and, at best, you'll get a shrug and some line citing how much better they were in all the other situations.
Earlier quoted context omitted.
The archivists themselves say that they run into such texts often enough that this program was needed: > The agency uses artificial intelligence and a technology known as optical character recognition to extract text from historical documents. But these methods don’t always work, and they aren’t always accurate. They are absolutely aware of the advances in these tools, so if they say they're not completely there yet…
Can someone please post a sample of one of these images that can only be read by a human for us naive OCR believers to see?
Earlier quoted context omitted.
OK, fair enough, but can you find one in this article that's hard for an LLM? The gnarliest one I saw, 4o handled instantly, and I went back and looked carefully at the image and the text and I'm sold. Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Later I signed up, went to the current missions, and they all seem to pos…
> Like if this is a crowdsourcing project... I'm confused by what you're asking. Are you asking me to like (upvote) your comment if this is a crowdsourcing project? Don't we already know it is a crowdsourcing project?
“So if this is a crowdsourcing project…”
Like is serving as an indication that someone else approximately said the phrase it introduced, in a way often associated with the “Valley Girl” social dialect but regularly seen outside of it.
https://en.wikipedia.org/wiki/Like#As_a_colloquial_quotative