News for hackers. Stuff that matters.

A comment on Llama.ttf: A font which is also an LLM. Parent comment

Re:Llama.ttf: A font which is also an LLM by mbb70 on Sunday June 23, 2024 @01:57PM (#40769243)
This is while pretty much all software that extracts structured data from PDFs throws away the text and just OCRs the page. Too many tricks with layouts and fonts.
[ Parent | on HN ]
Re:Llama.ttf: A font which is also an LLM by knallfrosch on Monday June 24, 2024 @08:25AM (#40775190)
I'm always surprised how "generate PDF from Word" turns one word into 10 different print points, all with just a single letter.

Or even straight lines in a table. The straight lines from a table boundary get hacked into pieces. You'd think one line would be the ideal presentation for a line, but who are you to judge PDF?

[ Parent | on HN ]