←back to thread

Karpathy on DeepSeek-OCR paper: Are pixels better inputs to LLMs than text?

(twitter.com)
233 points JnBrymn | 1 comments | 21 Oct 25 17:43 UTC | HN request time: 0.207s | source
Show context
shikon7 ◴[23 Oct 25 03:28 UTC] No.45677871[source]▶
Seems we're now at a point of time when OCR is doing so well, that printing text out and letting computers literally read it is suggested to be superior to processing the endoded text directly.
replies(2): >>45677961 #>>45679159 #
1. programmarchy ◴[23 Oct 25 03:46 UTC] No.45677961[source]▶
PDF is arguably a confusing format for LLMs to read.