Slop Detector

A Geiger counter for AI slop.

Click the toolbar icon, drag the probe over anything on a page, and the device tells you how AI-generated it looks. Green means probably written or made by a human. Yellow means suspicious. Red means slop.

It works on text, images, tweets, LinkedIn posts, and embedded videos.

Slop Detector is a heuristic, not a model. It runs entirely in your browser and looks for the things real LLMs and engagement-baiting humans actually do:
• Buzzwords like "delve", "tapestry", "navigate", "testament to", "leverage", "paradigm"
• Phrases like "It's not just X, it's Y" and "In today's fast-paced world…"
• Em-dashes everywhere
• Sentences that are all the same length
• Three sentences in a row starting with the same word
• The brain-rot lexicon (cooked, mogged, gyatt, no cap, delulu)