• vcmj@programming.dev
    link
    fedilink
    arrow-up
    2
    ·
    1 year ago

    Yes, that’s by design, the networks work on transcripts per input, it does genuinely get cut off eventually, usually it purges an entire older line when the tokens exceed a limit.

    • minorninth@lemmy.world
      link
      fedilink
      arrow-up
      2
      ·
      1 year ago

      I’m talking about using the ChatGPT API to make a chat bot. Even when the user’s input is just one sentence, it can cause ChatGPT to forget its prompt.

      • vcmj@programming.dev
        link
        fedilink
        arrow-up
        1
        ·
        edit-2
        1 year ago

        Ah, even then it could just be a consequence of training samples usually being chronological(most often the expected resolution for conflicting instructions is “whatever you heard last”, with some exceptions when explicitly stated) so it learns to think that way. I did find the pattern also applies to GPT trained on long articles where you’d expect it not to, so wanted to just explain why that might be.

    • vcmj@programming.dev
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      Or I should explain better: most training samples will be cut off at the top, so the network sort of learns to ignore it a bit.