• Lena@gregtech.eu
    link
    fedilink
    English
    arrow-up
    12
    arrow-down
    1
    ·
    6 hours ago

    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
      link
      fedilink
      English
      arrow-up
      15
      arrow-down
      1
      ·
      edit-2
      6 hours ago

      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.

      • fishy@lemmy.today
        link
        fedilink
        English
        arrow-up
        3
        ·
        35 minutes ago

        As someone who’s played a few LLM translated games, it is in fact not good at it. There’s a lot of contextual hints that get lost and slang terms tend to confuse it. It does make it close enough where a human that doesn’t speak/read the original language could easily finish the translation though or still make it through the game.

      • Lena@gregtech.eu
        link
        fedilink
        English
        arrow-up
        8
        ·
        6 hours ago

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

    • ssillyssadass@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      5 hours ago

      Honestly, translations are one of the few things LLMs are good for. It can catch things like idioms or other things a machine translator may mistranslate. Though tbf, the main appeal is still live translation.