Abstract
This is an experiment to see if LLMs are able to translate a dense philosophical text into a soothing children’s bedtime story. For the philosophical text, I used the most abstruse, allusive, elliptical philosophical text I know of, the 11,000-word essay “Différance” by Jacques Derrida. I prompted each LLM to translate the text into a bedtime story appropriate for a 6-year-old child while conveying the core philosophical concepts and conclusions in terms that a child could understand. The contestants included two commercial frontier LLM models and five open-weight models. Unable to assemble a panel of 6-year-olds to judge the resulting bedtime stories, I scored the stories through a combination of LLM automation and human intuition. While none of the results will win literary awards, the two frontier models performed the best by a substantial margin. One open-weight model produced gibberish, yet one LLM judge awarded it a point for representing one of Derrida’s core concepts.
Leave a Reply