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.”

  • CapeWearingAeroplane@sopuli.xyz
    link
    fedilink
    English
    arrow-up
    1
    ·
    5 months ago

    I’ve found chatgpt reasonably good for one thing: Generating regex-patterns. I don’t know regex for shit, but if I ask for a pattern described with words, I get a working pattern 9/10 times. It’s also a very easy use-case to double check.