Observed arrival · 2026-10-10
slop.how scores the habits of AI-ish writing
A writing-analysis API checks text for specific clichés and style habits, returning a probability for each factor.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Developers and editors checking text for AI-writing clichés
- Worth noticing
- Long text is split into chunks, and each factor keeps its highest score; the page says there is no single weighted “slop score.”
Field notes
The homepage demonstrates the checker on a sample of promotional prose, with high scores for canned opening, vague claims, and buzzwords. Its factor list is unusually explicit: each habit is paired with a yes-or-no question and examples, while the score explanation describes how long text is chunked. The page also cautions that polished AI writing can score as human and stiff human writing as AI, so it leaves authorship judgments out of the API.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue