To make matters worse, programmers in the study would often overlook the misinformation.

The research from Purdue University, first spotted by news outlet Futurism, was presented earlier this month at the Computer-Human Interaction Conference in Hawaii and looked at 517 programming questions on Stack Overflow that were then fed to ChatGPT.

“Our analysis shows that 52% of ChatGPT answers contain incorrect information and 77% are verbose,” the new study explained. “Nonetheless, our user study participants still preferred ChatGPT answers 35% of the time due to their comprehensiveness and well-articulated language style.”

Disturbingly, programmers in the study didn’t always catch the mistakes being produced by the AI chatbot.

“However, they also overlooked the misinformation in the ChatGPT answers 39% of the time,” according to the study. “This implies the need to counter misinformation in ChatGPT answers to programming questions and raise awareness of the risks associated with seemingly correct answers.”

  • reksas@sopuli.xyzEnglish
    131·
    6 months ago

    I just use it to get ideas about how to do something or ask it to write short functions for stuff i wouldnt know that well. I tried using it to create graphical ui for script but that was constant struggle to keep it on track. It managed to create something that kind of worked but it was like trying to hold 2 magnets of opposing polarity together and I had to constantly reset the conversation after it got “corrupted”.

    Its useful tool if you dont rely on it, use it correctly and dont trust it too much.

    • tea@lemmy.todayEnglish
      3·
      6 months ago

      This has been true for code you pull from posts on stackoverflow since forever. There are some good ideas, but they a. Aren’t exactly what you are trying to solve and b. Some of the ideas are incomplete or just bad and it is up to you to sort the wheat from the chaff.

    • VirtualOdourEnglish
      1·
      6 months ago

      Yeah I’ve been trying to recreate the same gui tools with every version and it is getting much better but it still struggles. The python specific gpt actually manages to create what I ask for and can make changes once it’s got the base established, I have to correct a few little glitches but nothing too terrible.

      For functions like save all the info in text boxes to Json and fill that info back in when load is pressed it never fails at. Making little test scripts for functions or layouts it saves me huge amounts of mental effort.

      It’s like image gen, you have to know what to expect to get the most out of it, ask for something it finds difficult it’s easy to confuse it but ask for things it’s good at and it’ll amaze you.