With modern CPU’s supposedly shipping with ‘AI cores’: How long do you think it will take for a proper opensource, privacy respecting productivity tools(Something like whatever M$ copilot is supposed to be?) to be available?

Personally, i would love to see something like ‘Passive’ OCR integrated with the display server: the ability to pause any video and just select whatever text(even handwritten) there is naturally like it was a text document without any additional hassle will be really useful
Also useful in circumventing any blocks certain websites put on articles to prevent text from being copied

Or an AI grammar checker running natively for LibreOffice.

What are some AI tools you think should be developed for desktop Linux?

  • TheEntity@kbin.social
    link
    fedilink
    arrow-up
    15
    ·
    9 months ago

    You can already use Tesseract to run OCR on any image. It’s a matter of tying it together with a screenshot tool with cropping capabilities and it should be very easy to use.

    • utopiah@lemmy.ml
      link
      fedilink
      arrow-up
      6
      ·
      9 months ago

      I’ve done a bash script and a KDE shortcut for that a while ago. I didn’t even remember it until now. It’s useful sometimes.

      • utopiah@lemmy.ml
        link
        fedilink
        arrow-up
        9
        ·
        edit-2
        9 months ago

        FWIW :

        fabien@fabien-CORSAIR-ONE-i160:~$ cat /home/fabien/bin/screenocr #!/bin/bash

        spectacle -r -nb -o /tmp/test.png
        tesseract -l eng /tmp/test.png /tmp/ocr
        #date +%s >> ~/grab_timed
        #cat /tmp/ocr.txt >> ~/grab_timed
        firefox --new-tab --url https://duckduckgo.com/?q="$(cat /tmp/ocr.txt)"
        

        PS: was curious about it, done that in August 2022