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

I tried with both PDFs and PNGs in Le Chat and the results were the worst I've ever seen when compared to any other model (Claude, ChatGPT, Gemini).

So bad that I think I need to enable the OCR function somehow, but couldn't find it.



It worked perfectly for me with a simple 2 page PDF that contained no graphics or formatting beyond headers and list items. Since it was so small I had the time to proof-read it and there were no errors. It added some formatting, such as bolding headers in list items and putting tics around file and function names. I won't complain.


I'm experiencing the same. Maybe the sentence "Mistral OCR capabilities are free to try on le Chat." was a hallucination.




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

Search: