• peanuts4life@lemmy.blahaj.zone
    link
    fedilink
    English
    arrow-up
    6
    ·
    14 hours ago

    It is my understanding that the advances in classifier models were and are inexorably linked to generative models. Wasn’t Deepdream a fairly crude inversion of existing classifier models?

    • aio@awful.systems
      link
      fedilink
      English
      arrow-up
      16
      ·
      edit-2
      2 hours ago

      You’re totally misunderstanding the context of that statement. The problem of classifying an image as a certain animal is related to the problem of generating a synthetic picture of a certain animal. But classifying an image of as a certain animal is totally unrelated to generating a natural-language description of “information about how to distinguish different species”. Moreover, we know empirically that these LLM-generated descriptions are highly unreliable.