Tuana @tuana.dev · Oct 28 Last week, I spent some time on the DeepSeek OCR paper with @LoganMarkewich and it was genuinely interesting. It's definitely not just OCR - it's using vision as compression. 10x token reduction while maintaining accuracy.
0 likes 1 replies
?
Replies
We wrote about what this means for document parsing and whether the meaning of "parsing" is changing www.llamaindex.ai/blog/beyond...