If you're attaching the image, why even send the text? It can read it, no? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		stavros 12 months ago \| parent \| context \| favorite \| on: Show HN: LLM-aided OCR – Correcting Tesseract OCR ... If you're attaching the image, why even send the text? It can read it, no?

dylanjcastillo 12 months ago [–]

To reduce hallucinations.

https://arxiv.org/pdf/2311.03287

stavros 12 months ago | [–]

Huh, very interesting, thank you. In my (limited) tests with GPT-4 vision (before 4o), it did really well with just the image, but it's good to know that the OCR can help.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact