this post was submitted on 06 Feb 2025
709 points (99.7% liked)

Technology

61850 readers
2770 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] njordomir@lemmy.world 48 points 1 day ago (2 children)

If someone was to acquire a few hundred gigs of books and feed them to something like paperless-ngx, would it work as a sort of google of books? Are there any software projects better suited for doing thisand understand synonyms and perhaps some context? I guess AI search but guided for the intermediate user.

Google is so bad lately. Basically every result is official sponsored corporate biased BS. It would be nice to be able to instantly query a bunch of ebooks.

[–] rumba@lemmy.zip 8 points 11 hours ago

GPT, Meta, Deepseek and Google have probably all been trained on the data.

The problem is, training on the data, and actually training for knowledge of the data are VERY different things.

https://www.youtube.com/watch?v=_GkHZQYFOGM

[–] werefreeatlast@lemmy.world 4 points 23 hours ago

Yes. This exactly.