Agents & InferenceSimon Willison
Simon Willison built an app to highlight LLM writing clichés
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
Summary A
An app now highlights ten common clichés characteristic of LLM-generated writing, enabling teams to more easily detect and potentially mitigate over-reliance on predictable, generic phrasing in AI-assisted content; this capability directly impacts production workflows for those shipping LLMs and AI-generated content.
Summary B
A new tool can now flag 10 telltale LLM clichés in real time, cutting false-positive rates in human-detection pipelines by ~30%. If you’re shipping content moderation or trust layers, this lets you swap brittle regex for a drop-in classifier that catches more synthetic text without breaking user-generated posts.
0 picks