And if so, how do they label headphones, contact lenses etc?

  • Send_me_nude_girls@feddit.de
    link
    fedilink
    arrow-up
    18
    arrow-down
    4
    ·
    1 year ago

    I like this question because I haven’t found an AI answer this question correctly yet. They all give wrong answers.

    • Ultraviolet@lemmy.world
      link
      fedilink
      English
      arrow-up
      16
      ·
      1 year ago

      It’s because of the way an LLM works, they’re completely blind to things like what a word starts with. Ask it something like “List 10 words that start and end with the same letter but are not palindromes.” and it completely shits the bed, because it can only process words as unified tokens, it can’t look inside the words to see how they’re structured.

      • Linus_Torvalds@lemmy.world
        link
        fedilink
        arrow-up
        10
        ·
        edit-2
        1 year ago
        1. Accordion
        2. Antenna
        3. Banana
        4. Character
        5. Deceived
        6. Elephant
        7. Greening
        8. Harbinger
        9. Insignia
        10. Knowledge

        GPT-4, prompt: “List 10 words that start and end with the same letter but are not palindromes.”

        Even without the palindrome condition, it got some of these and a few palindromes.

      • intelati
        link
        fedilink
        arrow-up
        1
        ·
        1 year ago

        I wish there was a chat thing that had a multi layered approach.

        Use a search to provide citations for the procedurally generated text.

      • nandeEbisu@lemmy.world
        link
        fedilink
        arrow-up
        1
        ·
        1 year ago

        They don’t process words as unified tokens for something like an LLM, but they do process them as multi-letter encoding, like byte-pair encoding or more advanced techniques.