06/19/2026
Really intriguing new study on and how - despite the underlying model - it can be reliably discerned from human writing through an analysis of the narrative, not just the style:
"AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonist' choices as more morally ambiguous and have increased temporal complexity."
I would be very curious to see how this might apply to scientific writing, which is much more rigid in it's "narrative" (having certain sections of papers, citations, etc.). Could be a nice tool to w**d out all the AI-generated slop being firehosed onto our journal editors!
Link:
As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can...