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

  • 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.

    • 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.