[jakewins]

But this was very much the case with existing OCR software as well? I guess the LLMs will end up making up plausible looking text instead of text riddled with errors, which makes it much harder to catch the mistakes, in fairness

[wahnfrieden]

Existing ocr doesn’t skip over entire (legible) paragraphs or hallucinate entire sentences

[criddell]

I usually run the image(s) through more than one converter then compare the results. They all have problems, but the parts they agree on are usually correct.

[Davidzheng]

rarely happens to me using LLMs to transcribe pdfs

[KoolKat23]

This must be some older/smaller model.

[rkagerer]

Good libraries gave results with embedded confidence levels for each unit recognized.