Overused AI Words
Words like "delve," "leverage," "robust," "tapestry," and "nuanced" can cluster in AI-generated text.
See vocabulary ticsField Guide
AI writing tells are repeated patterns that make text sound like ChatGPT: familiar phrases, inflated word choice, mechanical sentence shapes, generic enthusiasm, and formatting habits that appear too often to feel intentional.
Check text with Sniff TestThe tell is density, not presence. A human can write "it is worth noting" or use an em dash. The signal gets stronger when the same draft also has "delve," three-item lists, rhetorical questions, padded transitions, uniform paragraphs, and bold-first bullets.
Use these patterns as an editorial filter, not as proof of authorship.
Words like "delve," "leverage," "robust," "tapestry," and "nuanced" can cluster in AI-generated text.
See vocabulary ticsNegation reframes, self-posed questions, and rule-of-three padding make prose feel templated.
See sentence tells"Let's unpack this," "here's the thing," and world-historical stakes are clues that the assistant voice leaked through.
See tone tellsExcessive bolding, emoji bullets, and dense em-dashes are easy to scan before reading closely.
See formatting tellsThe Sniff Test checks text locally against the aismells catalog. It does not claim certainty. It shows which patterns appeared, where they appeared, and how dense they are.
Run the AI writing detector