News for hackers. Stuff that matters.

A comment on Show HN: Zerox v1 – Document OCR with GPT-vision. Parent comment

Re:Show HN: Zerox v1 – Document OCR with GPT-vision by themanmaran on Thursday October 17, 2024 @03:23PM (#41872891)
I've noticed the same "deciding" what to include issues. Despite explicit instructions in the prompt to include all text on the page.

This is one of the items that can hopefully be resolved with fine tuning.

[ Parent | on HN ]
Re:Show HN: Zerox v1 – Document OCR with GPT-vision by mawildoer on Thursday October 17, 2024 @04:12PM (#41873289)
I thought it was a big upgrade. Comparing Zerox w/ Unstructured on the first 5 pages of [this datasheet](https://www.ti.com/lit/ds/symlink/lm5117.pdf); zerox gave me what I wanted, and Unstructured gave me a bunch of extra junk that was harder to sort through at the top
[ Parent | on HN ]