# Good engineering prose versus a tell > Source-anchored research for Good engineering prose versus a tell. Run status: COMPLETED. Parent: [LLM tells in code, commit messages, comments and READMEs](https://llms-explorer.com/tree/ai-isms-code-and-commit-tells/) · 4 facets · 7 facts · page: https://llms-explorer.com/tree/good-engineering-prose-versus-a-tell/ ## How it works - Wikipedia's AI-cleanup editors state the listed patterns are only potential signs of a problem, not the problem itself, and that text with these features is not necessarily AI-generated because LLMs are trained on human writing. (high confidence) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) ## Problems, failure modes and limitations - Population-level word statistics cannot identify an individual LLM-written text, and cannot separate direct LLM use from humans unconsciously adopting LLM-preferred vocabulary; a single flagged word is weak evidence. (medium confidence) — [source](https://pmc.ncbi.nlm.nih.gov/articles/PMC12219543/) ## Comparisons and alternatives - Excess-vocabulary analysis of 15M+ PubMed abstracts found 2024 excess words were mostly style words (verbs ~66%, adjectives ~14%) such as delves, intricate, pivotal, unlike COVID-era excess words which were content nouns; it estimates at least 13.5% of 2024 abstracts were LLM-processed. (high confidence) (verified as of 2025-07-02) — [source](https://pmc.ncbi.nlm.nih.gov/articles/PMC12219543/) - A Stanford study of seven GPT detectors found about 61% of non-native English writers' essays flagged as AI; detectors penalise plain, predictable wording, so clean simple prose is a false-positive risk rather than a tell. (high confidence) — [source](https://themarkup.org/machine-learning/2023/08/14/ai-detection-tools-falsely-accuse-international-students-of-cheating) ## Facts and statements - Google's developer documentation style guide prescribes active voice, second person, conditions before instructions, and friendly-but-not-frivolous tone; these are human-authored norms that clean LLM output can also satisfy, so following them is not itself a tell. (medium confidence) — [source](https://developers.google.com/style/highlights) - The Wikipedia guide's stronger tells are content-level: undue emphasis on significance and legacy, vague attribution ('experts argue'), 'not just X but Y' parallelism, copula avoidance, and rigid 'challenges and future prospects' sections; these signal padding, not correctness of grammar. (medium confidence) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) - Human judgement alone performs no better than chance at telling AI from human text per the Wikipedia guide, and writers who fear accusation may distort their style; human and LLM writing are also converging. (low confidence) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)