Readers rate AI-generated short stories higher than human ones until they learn a machine wrote them

A recent study reported by The Decoder investigates the perception of AI-generated short stories compared to those written by humans. Involving over 2,500 participants, the research found that individuals could not distinguish between the two types of narratives, performing no better than chance in identifying the authorship. Interestingly, the AI-generated stories received higher ratings than their human counterparts, indicating a preference for the quality of the AI’s output.

However, this preference diminished significantly once participants were informed that the stories were generated by a machine. The findings suggest that while AI can produce text that resonates with readers, awareness of its artificial origin can negatively impact their evaluation. This study highlights the complexities of human-AI interaction in creative domains and raises questions about the implications of authorship on reader perception.