Study: AI Stories Rated Higher Than Human-Written
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Villanova University researchers led a study published by Cambridge University Press testing whether participants could distinguish AI-generated from human-written short stories, finding they largely could not.
- ChatGPT generated three fictional short stories used in the study, which were rated as higher quality and more engaging than those written by published human authors.
- Participants aged 18 to 81 gave the highest ratings to AI-generated stories they believed were written by humans, revealing a bias toward perceived human authorship regardless of origin.
- Dr Deena Weisberg noted that public assumptions about AI lacking emotional understanding are outdated, as AI writing tends to be clearer and more direct, aligning with reader preferences.
- AI literacy level among participants correlated with better detection of AI-generated text, while self-reported literary expertise did not improve identification accuracy.
Why it matters: The study shifts the debate on AI and creativity: if audiences can't tell the difference—and actually prefer AI output—then industries built on human authorship, like publishing and education, may face pressure to redefine value and authenticity. The 1,682-participant sample adds weight to the finding that clarity and predictability in AI writing now compete directly with human subtlety.
