News for hackers. Stuff that matters.

A comment on Launch HN: Midship (YC S24) – Turn PDFs and Images into usable data. Parent comment

Re:Launch HN: Midship (YC S24) – Turn PDFs and Images into u... by Kiro on Wednesday November 06, 2024 @04:09PM (#42069425)
Why all those steps? Why not just file + prompt to JSON directly?
[ Parent | on HN ]
Re:Launch HN: Midship (YC S24) – Turn PDFs and Images into u... by tlofreso on Wednesday November 06, 2024 @04:55PM (#42070089)
Having the text (for now) is still pretty important for quality output. The vision models are quite good, but not a replacement for a quality OCR step. A combination of Text + Vision is compelling too.
[ Parent | on HN ]