Hacker News new | ask | show | jobs
by duxup 496 days ago
What do you do after you OCR the pdfs?
1 comments

Turn it into CSV, sometimes transform it, confirm it's correct, paste it into my spreadsheet.
Are you aware that AI-based OCR very often hallucinates? https://www.runpulse.com/blog/why-llms-suck-at-ocr
Yes. Hasn't been a problem yet for my bank pdfs.

As I said, I verify it. Since it's a total over many transactions, it's hard to hallucinate and then get the same total the bank sheet has.

Ya know?