Comment on 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...

• DominicHillsun@lemmy.world ⁨1⁩ ⁨year⁩ ago

  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

  source

  • Rozz@lemmy.sdf.org ⁨1⁩ ⁨year⁩ ago

    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.

    source
• fidodo@lemmy.world ⁨1⁩ ⁨year⁩ ago

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

  source
• WalkableProgrammer@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Honestly I think the training data is just getting worse too

  source