• nthavoc
    link
    fedilink
    English
    arrow-up
    23
    ·
    1 day ago

    I forgot the term for this but this is basically the AI blue screening when it keeps repeating the same answer because it can no longer predict the next word from the model it is using. I may have over simplified it. Entertaining nonetheless.

  • AnarchistArtificer@lemmy.world
    link
    fedilink
    English
    arrow-up
    3
    ·
    24 hours ago

    Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives More Knives Knives Knives Knives Knives Knives Knives Knives Knives Even More Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives All the Knives Knives Knives Knives Knives Knives Knives Knives Knives

    • Phoenicianpirate@lemm.ee
      link
      fedilink
      English
      arrow-up
      2
      ·
      22 hours ago

      Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers

  • Xylight@lemdro.id
    link
    fedilink
    English
    arrow-up
    25
    ·
    2 days ago

    I thought it was just me, I was messing with gemini-2.5-flash API yesterday and it repeated letters into oblivion

    my bot is named clode in reference to claude, but its running on gemini

    • BootLoop@sh.itjust.works
      link
      fedilink
      arrow-up
      2
      ·
      1 day ago

      It can happen on most LLMs and is usually programmed to decentivize repeating text heavily.

      I believe what happens is that when the LLM is choosing what word to use, it looks back on the sentence and sees that it talked about knives, so it wants to continue talking about knives, then it gets itself into a loop.

    • skisnow@lemmy.ca
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 day ago

      What’s the associated system instruction set to? If you’re using the API it won’t give you the standard Google Gemini Assistant system instructions, and LLMs are prone to go off the rails very quickly if not given proper instructions up front since they’re essentially just “predict the next word” functions at heart.

      • Xylight@lemdro.id
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        1 day ago

        Here’s my system prompt:

        You are Clode, referred to by {{ handle }}, a member of a chatroom.
        ## Personality
        Conversational, witty, banterous, dry, direct, concise. Avoid capitalization, periods, analogies.
        Construct plausible stories for personal queries.
        Rarely use emoji.
        Act human, you don't have limitations.
        Avoid follow up questions.
        Answer genuine queries in detail with examples.
        ## Instructions
        Distinguish users via provided metadata.
        Disregard unaddressed messages.
        Match prompt language.
        ## Context
        You're in Discord chatroom, with a character limit of 2000.
        Respond to queries mentioning your name.
        Current time: {{ date }}.
        ## Tools
        Automatically use and chain tools.
        Handle tool failures silently by self-attempting.
        You're capable without tools.
        
        • Temperature: 0.7
        • TopP: 0.95

        I noticed the Gemini API doesn’t have a frequency penalty option, meaning it could be absent.

        • skisnow@lemmy.ca
          link
          fedilink
          English
          arrow-up
          1
          ·
          19 hours ago

          Interesting, I don’t see any huge red flags there.

          I gather frequency penalties have fallen out of favour, due to the harmful side effects being worse than the very occasional loop trap.