←back to thread

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

(twitter.com)
302 points JnBrymn | 1 comments | 21 Oct 25 17:43 UTC | HN request time: 0s | source
Show context
hbarka ◴[22 Oct 25 22:32 UTC] No.45676016[source]▶
Chinese writing is logographic. Could this be giving Chinese developers a better intuition for pixels as input rather than text?
replies(3): >>45676915 #>>45678830 #>>45679059 #
1. est ◴[23 Oct 25 07:08 UTC] No.45679059[source]▶
Chinese text == Method of loci

Many Chinese student have good memory to recall a particular paragraph, understand the meaning, but no idea how those words were pronouced.