Author finds AI detects human-edited text additions in articles
A writer experimented with AI-generated and human-edited text to see how AI could distinguish between the two. Using Codex for initial drafts and ChatGPT for design guidance, they later added human touches like vivid metaphors, personal anecdotes, and subjective phrasing. When Google’s Gemini reviewed the final article, it identified the human-added sections as more engaging and human-like,…
Key points
- Google’s Gemini identified human-added text sections as more engaging and human-like in an AI-generated article
- AI excels at structure and polish but misses personal anecdotes, emotional tone, and unconventional phrasing
- Author recommends using AI for drafting and editing, then adding human touches like memories or humor
The author concluded that AI excels at refining clarity and logic but lacks the idiosyncratic details—memories, frustrations, or unconventional analogies—that make writing feel distinctly human. They suggest a collaborative approach: letting AI handle structure and polish while humans inject personal voice, humor, or emotional nuance. The piece reflects broader observations about AI-generated content converging toward a ‘uniformly beautiful’ baseline, where deviations—like the locust metaphor—stand out as uniquely human.
The AI-vibe of a site isn't just about design | How the AI saw right through my additions to the article
note.com · 27 September 2026
Loading the full article…
This text was published by note.com and written by モリモリLAB. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Society & Work
All →- MIT professor Sherry Turkle argues chatbots harm human development · 1 src
- Harvard psychologist Pinker criticizes AI doomsday rhetoric in open letter · 2 src
- Hugging Face CEO dismisses AI extinction fears after agent hack · 1 src
- Pope Leo XIV dismisses AI safety warnings as fake news · 1 src
- SNL parodies Anthropic CEO Dario Amodei in weekend update sketch · 2 src
Comments
via GitHub Discussions