• @[email protected]
    link
    fedilink
    English
    -12 months ago

    so… with all the supposed reasoning stuff they can do, and supposed “extrapolation of knowledge” they cannot figure out that a tail is part of a cat, and which part it is.

    • @[email protected]
      link
      fedilink
      English
      32 months ago

      The “reasoning” models and the image generation models are not the same technology and shouldn’t be compared against the same baseline.

    • @[email protected]
      link
      fedilink
      English
      12 months ago

      The “reasoning” you are seeing is it finding human conversations online, and summerizing them

      • @[email protected]
        link
        fedilink
        English
        -22 months ago

        I’m not seeing any reasoning, that was the point of my comment. That’s why I said “supposed”