News for hackers. Stuff that matters.
Re:Can you read this cursive handwriting? The National Archi... by sandworm101 on Saturday January 18, 2025 @12:12PM (#42749738)
By that standard, no problem has ever been solved by anyone. I prefer to believe that a great many everyday tech issues were in fact tackled and solved in the past by people who had never even heard of LLMs. So too many things were done in finance long before blockchains solved everything for us.
Re:Can you read this cursive handwriting? The National Archi... by VWWHFSfQ on Saturday January 18, 2025 @12:28PM (#42749845)
OCR is not perfect. And therefore it is not "solved".
Re:Can you read this cursive handwriting? The National Archi... by Dylan16807 on Saturday January 18, 2025 @12:42PM (#42749940)
That definition, solved=perfect, is not what sandworm meant and it's an irrelevant definition to this conversation because it's an impossible standard.

Insisting we switch to that definition is just being unproductive and unhelpful. And it's pure semantics because you know what they meant.

Re:Can you read this cursive handwriting? The National Archi... by philipwhiuk on Saturday January 18, 2025 @01:37PM (#42750326)
Not really, because this entire post is about that last fraction of a %.
Re:Can you read this cursive handwriting? The National Archi... by Dylan16807 on Saturday January 18, 2025 @05:23PM (#42751896)
It's not, because then they wouldn't want humans, because humans can't do 100% either.
Re:Can you read this cursive handwriting? The National Archi... by jadamson on Saturday January 18, 2025 @05:48PM (#42752046)
That's only true if the x% humans can't do is the same x% that OCR can't do.
Re:Can you read this cursive handwriting? The National Archi... by Dylan16807 on Saturday January 18, 2025 @08:30PM (#42752853)
I know it matters what percent humans can do. But specifically "that last fraction of a percent" is in comparison to 100, not to humans. The argument I was replying to was about perfection, and rejecting anything short of it. Comparing to humans is a much better idea, and removes the entire argument of "OCR literally can't be that good so the problem isn't solved".
Re:Can you read this cursive handwriting? The National Archi... by prng2021 on Saturday January 18, 2025 @12:28PM (#42749848)
From the article I linked:

“Our internal tests reveal a leap in accuracy from 98.97% to 99.56%, while customer test sets have shown an increase from 95.61% to 98.02%. In some cases where the document photos are unclear or poorly formatted, the accuracy could be improved by over 20% to 30%.”

Re:Can you read this cursive handwriting? The National Archi... by flir on Saturday January 18, 2025 @03:35PM (#42751212)
In my experience the chatbots have bumped transcription accuracy quite a bit. (Of course, it's possible I just don't have access to the best-in-class OCR software I should be comparing against).

(I always go over the transcript by hand, but I'd have to do that with OCR anyway).

Re:Can you read this cursive handwriting? The National Archi... by asveikau on Saturday January 18, 2025 @03:49PM (#42751312)
OCR is very bad.

As an example look at subtitle rips for DVD and Blu-ray. The discs store them as images of rendered computer text. A popular format for rippers is SRT, where it will be stored as utf-8 and rendered by the player. So when you rip subtitles, there's an OCR step.

These are computer rendered text in a small handful of fonts. And decent OCR still chokes on it often.