Slop Vocabulary
We keep a dictionary of 300+ words that mass-produced content overuses, ranked in three tiers. Words like "delve", "tapestry" and "testament" are instant tells.
AISlopScanner is an opinionated judgment system that helps you decide: "Is this content low-value slop, and why?"
No AI, no API calls, no black box. Here is exactly what happens when you hit "Analyze" — five factors, one honest score.
We keep a dictionary of 300+ words that mass-produced content overuses, ranked in three tiers. Words like "delve", "tapestry" and "testament" are instant tells.
Empty openers and prefab transitions: "in today's rapidly evolving world", "it's important to note that". These phrases survive even after the vocabulary is cleaned up.
Uniform sentence length, transition-word openers, rule-of-three lists and em dash density all point at templated production lines.
Human writing breathes — short sentences, long ones, odd words. We measure type-to-token ratio to catch text that repeats itself or stays artificially flat.
Slop hedges: "can help", "many", "various factors". Real content commits: numbers, dates, names, and claims that could actually be wrong.
Every factor feeds one number. The higher the score, the harder we'd nudge you to close the tab and go outside.
The Slop ScoreWe hate AI slop. We're the type of people who flag AI-processed memes. Here's our full reasoning:
This site can run with $0 operating costs: no cloud servers, no AI inference, no database. Static files, local JavaScript. That's how it stays free and stays that way.
We don't care whether a human or a model wrote your text. We care about the answer to one question: "Is this worth reading, skimming, or skipping?"
A working classification system for low-quality content. Five categories that cover most of what's out there, each with its own detection signals.
Could be about anything. Swap the nouns and nothing changes — "in today's fast-paced world" energy from start to finish.
Primary tell: Vague openers, no specificsSee examples →Sounds profound, says nothing. "It's not just X, it's Y" constructions stacked until you forget what was being claimed.
Primary tell: Fake depth, contrast ticsSee examples →Cites studies that don't exist and statistics nobody measured. Confidence per sentence is inversely proportional to evidence.
Primary tell: Unverifiable "research shows"See examples →The first three search results, compressed into a listicle with the personality ironed out. Accurate-ish, useful never.
Primary tell: Summary-shaped, zero voiceSee examples →"Unlock your best self" — supplement-adjacent content that pathologizes normal life and sells rituals, not results.
Primary tell: Your journey, their productSee examples →Reserved. We'll know it when the internet produces it.
Coming soonEverything you need to know about AI slop detection and why it matters.
AI slop is low-effort, mass-produced content — text, images, or video — generated at scale and published for engagement rather than value. It reads as plausible but says little: vague, templated, interchangeable. The term exploded in 2024 and became a Word of the Year contender in 2025.
AI detectors guess who wrote a text, and they fail often — flagging the Gettysburg Address as machine-made. Slop detection asks a different question: is this worth reading? A tired human listicle can score high. A carefully edited AI draft can score low. We judge quality, not origin.
It crowds out human work, pollutes search results and feeds, erodes trust in what we read, and at its worst spreads dangerous misinformation — fake health advice, fabricated news, scam funnels. It also trains future models on its own output, degrading them.
Deterministic heuristics, fully in your browser: a tiered dictionary of 300+ overused words, a cliché-phrase list, structure signals (transition openers, sentence-length uniformity, em dash density, rule-of-three), lexical diversity, and substance measures. No AI. Your pasted text never leaves your browser; the optional URL scan uses a third-party extraction service to fetch the article.
Yes — and we say so plainly. A draft generated by a model and then edited by a knowledgeable human who adds specifics, voice, and lived experience can absolutely clear the bar. The slop is what happens when nobody does that work.
Overused words (“delve”, “tapestry”, “pivotal”), prefab phrases (“in today’s rapidly evolving world”), uniform sentence rhythm, em dashes everywhere, rule-of-three constructions, hedging instead of specifics, and zero lived experience. Two or more at once is the real tell.
“Slop” is what you feed to pigs — cheap, bulk, low-nutrition filler. Applied to AI content, it describes output produced at scale for quantity, not quality. The metaphor stuck because it captures both the production method and the nutritional value.
Shrimp Jesus on Facebook, fake crochet patterns, AI news anchors reading fabricated stories, “experts” citing studies that do not exist, foraging books on Amazon with dangerous errors, and SEO blog posts that answer questions nobody asked. See our Examples gallery for the full tour.
Manually: read the first three sentences and count tells — prefab openers, hedged claims, no specifics. Automatically: paste the text into our detector and get a 0–100 score with a factor-by-factor explanation of what tripped it.
You just found the free way: scroll up, paste your text, hit Analyze. No account, no limits — pasted text never leaves your browser.
Field notes, data analyses, and reference guides on the slop epidemic.
How automated filler is degrading corporate memos, client emails, and resumes — with a practical 5-step editorial checklist for professional teams.
An inside look at why statistical AI checkers flag innocent writers, the non-native English penalty, and why transparent heuristics offer a fairer standard.
Why automated AI humanizers fail, and the 7 concrete editorial techniques that actually transform robotic drafts into clear, authentic human prose.
The AI words list: 120+ words and phrases ChatGPT overuses, each with why it reads as slop and a plain human swap. Backed by the engine dictionary.
Is the em dash an AI tell? We measured dash density in 702,939 words of human prose vs GPT-4. The gap is real — but smaller than the internet claims.
Paste any text into our free AI slop detector and get an opinionated, factor-by-factor verdict — instantly.