Sharon Adarlo / Futurism: An analysis of ChatGPT-3.5’s answers to 517 programming questions on Stack Overflow: 52% of answers contain incorrect information, 77% are verbose, and more  —  Not So Smart  —  In recent years, computer programmers have flocked to chatbots like OpenAI’s ChatGPT to help them code …

  • @BatrickPateman
    link
    English
    44 months ago

    I get that they are testing what is effectively free for all to use at this point. But at the same time it is definitely the weakest of the models.

  • Bappity
    link
    English
    24 months ago

    curious to see this analysis with Claude, pi and others