this post was submitted on 18 Aug 2025
645 points (98.2% liked)

Technology

74265 readers
4199 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 news or articles.
  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, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  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
[–] lena@gregtech.eu 19 points 2 days ago (5 children)

of file corruption when symptoms occurs" adds the report (Translated from Japanese by Grok AI).

Why would you use an LLM to translate text? There are tools made specifically for that

[–] Saleh@feddit.org 22 points 2 days ago* (last edited 2 days ago) (2 children)

Which are based on LLMs or other neural network models. It is kind of the thing that language models are actually good at.

See DeepL for example: https://en.wikipedia.org/wiki/DeepL_Translator

The service uses a proprietary algorithm with convolutional neural networks (CNNs)[3] that have been trained with the Linguee database.[4][5]
According to the developers, the service uses a newer improved architecture of neural networks, which results in a more natural sound of translations than by competing services.
The translation is said to be generated using a supercomputer that reaches 5.1 petaflops and is operated in Iceland with hydropower.[6][7]
In general, CNNs are slightly more suitable for long coherent word sequences, but they have so far not been used by the competition because of their weaknesses compared to recurrent neural networks.
The weaknesses of DeepL are compensated for by supplemental techniques, some of which are publicly known.

[–] lena@gregtech.eu 14 points 2 days ago

Yeah I know they're based on LLMs, but they're more adapted to translation, right?

load more comments (1 replies)
load more comments (3 replies)