LLM cliché highlighter

Simon Willison's Blog Tools

Summary

A web-based tool that detects and highlights common clichéd phrases in LLM-generated text, such as 'no X, no Y' chains and 'sit with that', to help identify AI writing patterns.

No content available
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:38 AM

# Tool: LLM cliché highlighter Source: [https://simonwillison.net/2026/Jul/17/llm-cliche-highlighter/](https://simonwillison.net/2026/Jul/17/llm-cliche-highlighter/) [Tool](https://simonwillison.net/elsewhere/tool/)[LLM cliché highlighter](https://tools.simonwillison.net/llm-cliche-highlighter)— Detect and highlight common clichéd phrases in text that frequently appear in language model outputs\. Paste text into the analyzer to identify patterns like "no X, no Y" chains, "sit with that," "you already know," and other LLM\-generated expressions, with toggleable pattern detection and context\-aware sentence highlighting\. I got frustrated reading*yet another*article that was crammed with the clichés of LLM\-generated writing \- "no fluff, no filler, no jargon" type stuff \- so I had Fable 5 vibe code up this app for highlighting ten common patterns that show up in that sort of writing\. ![Screenshot of a text-analysis web tool. Top summary row: "2 matches", "1 flagged sentence", "0 chain items". Below, a collapsed "▶ Patterns · all 11 on" panel, then a URL input reading "https://example.com/article — fetched via r.jina.ai" with a "Load URL" button. A text area contains "That loss is real and it's worth naming". Below are "Load example" and "Clear" buttons and a checked checkbox "Show just the highlights". A "Highlighted text" section shows "That loss is real and it's worth naming" with "That loss" in pale yellow (flagged sentence) and "is real and" plus "'s worth naming" in darker yellow (pattern match). Legend: "flagged sentence", "pattern match", "3 chain item count". "Matches" section: 1. "is real and" — "Is real … and / not"; 2. "'s worth naming" — "Worth naming".](https://static.simonwillison.net/static/2026/the-loss-is-real.webp)

Similar Articles

hardikpandya/stop-slop

GitHub Trending (daily)

A skill/tool for removing common AI writing patterns from prose, including banned phrases, structural clichés, and sentence-level issues, intended for use with Claude or any LLM.

Content for Content’s Sake

Armin Ronacher

The author investigates how LLMs are influencing word usage in coding and everyday language, finding that words favored by LLMs show increased frequency in both coding sessions and Google Trends, raising concerns about humans adopting LLM writing styles.

It's Not Just X. It's Y

Hacker News Top

This essay explores how LLMs' post-training (RLHF and RLVR) produces linguistic tics like negative parallelism, and critiques the use of AI detectors (Grammarly, Pangram) that force writers to sound like machines to avoid false accusations.

Literary Non-Style in LLM-Generated Text

arXiv cs.CL

This paper analyzes statistical patterns in LLM-generated text using n-gram distributions, revealing stylistic deficiencies and showing that style and semantics are not separable.

LLMs are stuck in a groupthink groove. This startup is trying to get them out.

MIT Technology Review

A startup called Springboards has developed an LLM named Flint that aims to produce more varied and creative responses than mainstream models, addressing a widespread issue of homogeneity in AI outputs. The article highlights research showing that many LLMs converge on similar answers due to similar training data and methods.