Comment on Solve a puzzle for me

zkfcfbzr@lemmy.world ⁨6⁩ ⁨months⁩ ago

• kautau@lemmy.world ⁨6⁩ ⁨months⁩ ago

  Looks like copilot with gpt-4 turbo got it. I was a little sad to not get a silly answer tbh

  Image

  source

  • tyler@programming.dev ⁨6⁩ ⁨months⁩ ago

    4o didn’t get it for me.

    Image

    Image

    Image

    Image

    source

    • kautau@lemmy.world ⁨6⁩ ⁨months⁩ ago

      Honestly my answer felt super canned, like someone had asked it before and reported the answer as bad, so that doesn’t surprise me

      source
    • AFKBRBChocolate@lemmy.world ⁨6⁩ ⁨months⁩ ago

      I’m always interested in seeing examples like this where the LLM will get to a right answer after a series of questions (with no additional information) about its earlier wrong responses. I’d love to understand what’s going on in the software that allows the initial wrong answers but gets the eventually right one without an additional input.

      source

      • 31337@sh.itjust.works ⁨6⁩ ⁨months⁩ ago

        One hypothesis is that having more tokens to process lets it “think” longer. Chain of Thought prompting where you ask the LLM to explain its reasoning before giving an answer works similarly. Also, LLMs seem to be better at evaluating solutions that coming up with them, so there is a Tree of Thought technique, where the LLM is asked to generate multiple examples of a reasoning step then pick the “best” reasoning for each reasoning step.

        source
• HeyThisIsntTheYMCA@lemmy.world ⁨6⁩ ⁨months⁩ ago

  Take the goat over Return empty-handed Take the cabbage over Return with the goat Take wolf over Return empty-handed
  Take other wolf over AROOOOO BROTHERS CRANK THEM HOGS

  source
• dumbass@leminal.space ⁨6⁩ ⁨months⁩ ago

  The last reply feels like a human took over to answer so you would stop asking the question.

  source