AI-heavy books reuse rare phrases more often, and sales rise with that coverage
TuhinChakr · x · 2026-07-28
The figures in the thread show two related patterns:
- AI-heavy books draw a higher share of their text from rare phrases found in existing books.
- Commercial success appears to increase with that rare-expression coverage for AI-written books, but the same relationship is much weaker for non-AI books and award-winning literary fiction.
In other words, the paper argues that AI-written books are not simply imitating style at the margin; they are statistically distinct in how they recycle prior text.
Related event: Study Says AI Self-Published Books Are Squeezing Amazon Sales(17 posts)→
More from Research
- MIT-led preprint uses machine learning to guide Rubisco evolution — chaitjo · 2026-07-29
- OpenAI says coding agents are taking over routine science work — eyishazyer · 2026-07-29
- Qwen3-VL plus DeCoDe lifts accuracy from 27.8% to 89.2% on novel vision tests — HildeKuehne · 2026-07-29
- MazeBench is a 3D open world benchmark that current agents cannot clear — giffmana · 2026-07-29
- ECCV 2026 paper says some multimodal LLMs do worse with one-shot examples — HildeKuehne · 2026-07-29
- A simple sequence-design trick: explore beyond training data, then penalize bad candidates — anshulkundaje · 2026-07-29