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.”
Who would have thought that an artificial intelligence trained on human intelligence would be just as dumb
Hm. This is what I got.
I think about 90% of the screenshots we see of LLMs failing hilariously are doctored. Lemmy users really want to believe it’s that bad through.
Edit:
I’ve had lots of great experiences with ChatGPT, and I’ve also had it hallucinate things.
I saw someone post an image of a simplified riddle, where ChatGPT tried to solve it as if it were the entire riddle, but it added extra restrictions and have a confusing response. I tried it for myself and got an even better answer.
Prompt (no prior context except saying I have a riddle for it):
A man and a goat are on one side of the river. They have a boat. How can they go across?
Response:
The man takes the goat across the river first, then he returns alone and takes the boat across again. Finally, he brings the goat’s friend, Mr. Cabbage, across the river.
I wish I was witty enough to make this up.