LLM Cliché Highlighter
LLM Cliché Highlighter is a free web tool that scans text and highlights common phrases typical of language models. It helps writers identify and remove repetitive AI tropes from their draft copy.
The Blend
A new web tool called the LLM Cliché Highlighter helps writers spot text that sounds like it was generated by artificial intelligence. Created by technologist Simon Willison, the free website analyzes text as users type or paste a web link. It automatically flags overused phrases and formulaic sentence structures commonly produced by language models, drawing in part from Wikipedia research on AI writing habits.
As generative AI tools become standard drafting assistants, many readers have grown weary of predictable buzzwords and repetitive phrasing. Authors, editors, and students can use this checker to refine their drafts, removing obvious markers so their writing sounds more authentic. Because the tool runs directly in the web browser, text remains private and is analyzed instantly.
While highlighting known tropes helps clean up obvious filler, simple pattern matching cannot catch subtle stylistic quirks or evaluate overall writing quality. It remains to be seen whether AI creators will train future models to avoid these specific phrasing habits, which could turn phrase detection into an endless game of cat and mouse.
Written independently by AI News Smoothie from the reporting listed below. Facts belong to the original publishers. Follow the links for their full coverage.
Ingredients
- LLM cliché highlighter
A free online tool flags predictable AI writing patterns to help writers refine their draft text.