Over just a few months, ChatGPT went from correctly answering a simple math problem 98% of the time to just 2%, study finds. Researchers found wild fluctuations—called drift—in the technology’s abi…::ChatGPT went from answering a simple math correctly 98% of the time to just 2%, over the course of a few months.

    • DominicHillsun@lemmy.world
      link
      fedilink
      English
      arrow-up
      20
      ·
      1 年前

      Yeah, but the trained model is already there, you need additional data for further training and newer versions. OpenAI even makes a point that ChatGPT doesn’t have direct access to the internet for information and has been trained on data available up until 2021

      • Rozz@lemmy.sdf.org
        link
        fedilink
        English
        arrow-up
        5
        ·
        1 年前

        And it’s not like there is a limit of simple math problems that it can train on even if it wasn’t already trained.

    • fidodo@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      ·
      1 年前

      That doesn’t make any sense to explain degradation. It would explain a stall but not a back track.