News for hackers. Stuff that matters.
Re:Show HN: Zerox – document OCR with GPT-mini by gregolo on Wednesday July 24, 2024 @03:31AM (#41054461)
And OpenAI uses Tesseract in the background, as it sometimes answers that Hungarian language is not installed for Tesseract for me
Re:Show HN: Zerox – document OCR with GPT-mini by s5ma6n on Wednesday July 24, 2024 @05:10AM (#41055066)
I would be extremely surprised if that's the case. There are "open-source" multimodal LLMs can extract text from images as a proof that the idea works.

Probably the model is hallucinating and adding "Hungarian language is not installed for Tesseract" to the response.