←back to thread

DeepSeek OCR

(github.com)
990 points pierre | 1 comments | 20 Oct 25 06:26 UTC | HN request time: 0.2s | source
Show context
2big2fail_47 ◴[20 Oct 25 10:38 UTC] No.45642348[source]▶
I find it interesting that there's all these independent AI-OCR Projects but still no commercial offering. Is it still too inaccurate, too complex or simply too expensive?
replies(7): >>45642449 #>>45642469 #>>45642854 #>>45643901 #>>45644265 #>>45645400 #>>45648665 #
1. Eisenstein ◴[20 Oct 25 10:54 UTC] No.45642469[source]▶
It is because the AI is not actually doing OCR. It is giving an interpretation of what the text in an image is by ingesting vision tokens and mapping them onto text tokens.

So you either have to be fine with a lot of uncertainty as to the accuracy of that interpretation or you have to wait for an LLM that can do it in a completely reproducible way every time.