Despite being primarily trained on text, these models achieved remarkable compression rates on image and audio data.
  • Hexagon
    132·
    1 year ago

    We’re likely talking about lossy compression here

    • enkers@sh.itjust.works
      15·
      1 year ago

      That was my first thought as well, but it doesn’t seem to be the case:

      In their study, the Google DeepMind researchers repurposed open-source LLMs to perform arithmetic coding, a type of lossless compression algorithm.

      • Hexagon
        5·
        1 year ago

        … and this is why I should actually read the articles before commenting lol