The team also presented their results at CHI 2024. ChatGPT and other similar chatbots have become quite popular among users, but in addition to providing useful information, they often give incorrect answers, and this is not always immediately noticeable.
Scientists noted that many programming students have started using chatbots not only to help them write code, but also to get answers to programming-related questions. They tested ChatGPT’s answer accuracy on 517 questions from StackOverflow and found that it answered correctly in only 52% of the answers. Also, the answers were longer than those of human experts.
The study also found that participants preferred ChatGPT answers 35% of the time and often did not notice errors, while incorrect answers were ignored 39% of the time.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
