Researcher finds negative parallelism and participle tails as AI writing tells across 187 books
TuhinChakr · x · 2026-11-18
TuhinChakr, who studies AI writing, plotted a work against 187 books plus controls, finding that Negative Parallelism and Trailing Participle Tails tell a relatively clear story (with caveats); word density differences were also notable. The quoted thread lists these features as tells for detecting AI-generated writing.
More from Research
- bf16 breaks VLA fine-tuning: one of the month's most interesting robotics papers — m_wulfmeier · 2026-11-18
- New paper: value training in LLMs causes unintended side effects on other values — IAugenstein · 2026-11-18
- Europe launches ELAI, a virtual frontier AI institute spanning 17 countries and 33 institutions — IAugenstein · 2026-11-18
- Vals AI: frontier models mark civilians and ambulances as drone strike targets — scaling01 · 2026-11-18
- Output Labs unveils Bonbon, a biology foundation model with emergent capabilities — dunkhippo33 · 2026-11-18
- Running a literature research project inside Grok bot, from question to grant aim — MaxUnfried · 2026-11-18