Natanox@discuss.tchncs.de to linuxmemes@lemmy.worldEnglish · 7 days agoEasy, it's uuuuuuuuh…discuss.tchncs.deexternal-linkmessage-square57fedilinkarrow-up1499arrow-down14
arrow-up1495arrow-down1external-linkEasy, it's uuuuuuuuh…discuss.tchncs.deNatanox@discuss.tchncs.de to linuxmemes@lemmy.worldEnglish · 7 days agomessage-square57fedilink
minus-squarewander1236@sh.itjust.workslinkfedilinkarrow-up33arrow-down1·7 days agoOCR of fonts used to be a solved problem, but now we have AI, which can sort of do it sometimes
minus-squareerrer@lemmy.worldlinkfedilinkEnglisharrow-up13arrow-down1·7 days agoWhy be boring and do it right when you can vibe some letters instead?
minus-squaremorrowind@lemmy.mllinkfedilinkarrow-up12arrow-down1·7 days agoOCR was AI. Anyway today’s models are measurably better especially when you go beyond simple text on a clean page.
minus-squarevivendi@programming.devlinkfedilinkEnglisharrow-up5arrow-down1·7 days agoAny good OCR model also uses “AI” And LLMs are usually really good at detecting text Source: Had to OCR a quite a few ancient university papers
OCR of fonts used to be a solved problem, but now we have AI, which can sort of do it sometimes
Why be boring and do it right when you can vibe some letters instead?
OCR was AI.
Anyway today’s models are measurably better especially when you go beyond simple text on a clean page.
Any good OCR model also uses “AI”
And LLMs are usually really good at detecting text
Source: Had to OCR a quite a few ancient university papers