Get the latest tech news

Should LLMs just treat text content as an image?


Several days ago, DeepSeek released a new OCR paper. OCR, or “optical character recognition”, is the process of converting an image of text - say, a scanned…

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of LLMs

LLMs

Photo of Image

Image

Photo of text content

text content

Related news:

News photo

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference

News photo

Show HN: Git for LLMs – A context management interface

News photo

Canonical Begins Snap'ing Up Silicon-Optimized AI LLMs For Ubuntu Linux