Hacker News new | ask | show | jobs
by richardmeng 681 days ago
Today's large vision models like GPT-4o can parse the content heavy papers pretty well (and respect their structures).

Yah basically it allows you to send PDFs as image patches into GPT-4o model that workflow can be easily built.

Feel free to send me an email richard@roe-ai.com, happy to evaluate your case and try to save that 200K :p