Readers gave the highest ratings to stories created by artificial intelligence (AI), believing they had been written by humans, according to new research.The study, published by Cambridge University Press, tested to see whether people aged 18 to 81 could tell the difference between human-written and AI-generated short stories.Led by researchers at Villanova University (VU), USA, it found that participants could not tell which was which.Senior author Dr Deena Weisberg, from the department of psychological and brain sciences at VU, said: “I’d say that public assumptions about AI’s capabilities are increasingly out of date.”The study also examined how participants rated the appeal and quality of each story and whether they could identify AI-generated content.”We assume creative writing requires uniquely human qualities, such as emotional understanding and lived experience, which leads people to underestimate AI’s capabilities,” Weisberg added.Researchers used three fictional short stories written by published authors, alongside three generated by ChatGPT.In their first experiment, 1,682 participants read a story and were either correctly or incorrectly told it had been written by AI or a human. They then rated how engaging it was and its quality.
AI-generated tales preferred to human-written ones, study finds
