Good engineering prose versus a tell
Parent: LLM tells in code, commit messages, comments and READMEs · Published reference · snapshot 2026-09-23
↓ Facts as markdownall context files
Source-anchored research for Good engineering prose versus a tell. Run status: COMPLETED.
These notes link each claim to its source. Some citations identify archived research reports that are no longer hosted on this site. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
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]
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]
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]
- 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]
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]
- 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]
- 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]
Children
- No children recorded.