What is AI slop?
“AI slop” is writing that reads like a machine produced it: fluent, confident, and strangely empty. It isn't about being wrong — it's about a texture. The sentences hedge and balance too neatly, lean on a small set of overused words, and pad every point with throat-clearing and summary.
It matters because readers can feel it, even when they can't name it. Slop reads as low-effort and erodes trust, and the same statistical patterns that make it sound “AI” are exactly what detection tools flag. The fix isn't more polish — it's cutting the tells and letting a specific, human point stand.
The slop taxonomy
The 13 categories of tell the editor hunts for. Each has its own link — point people straight at the one they keep committing.
- 01
Buzz verbs
Verbs that sound like motion but describe none. AI reaches for them to seem energetic.
delveleverageunlockelevateempowersuperchargerevolutionize
- 02
Stock framings
Prefab openers and scaffolds that could bolt onto any topic without changing meaning.
in today's fast-paced digital landscapeit's not just X, it's Ya testament togame-changingseamlessrobust
- 03
Structural tells
Shapes, not words: rule-of-three pileups, throat-clearing intros, and outros that restate the whole piece.
faster, smarter, betterIt's important to note that…em-dash overuseexclamation inflation
- 04
Empty intensifiers & adverbs
Words that turn up the volume without adding information — including adverbs bolted onto plain verbs.
trulyincrediblysignificantlyquietly transformsseamlessly runs
- 05
Fake balance
Reflexively airing an 'on the other hand' the author never actually held, to seem even-handed.
on the other hand…that said…however, some might argue…
- 06
Detector-bait vocabulary
Words statistically overrepresented in LLM text — the ones AI-detection tools flag first.
intricatepivotalcrucialtapestrymultifacetedunderscoresplays a crucial role
- 07
Academic filler
Journal-flavored padding: stock openers, furthermore/moreover chains, conclusions that restate the abstract.
In recent years, there has been growing interest in…the intricate interplay betweenholistic framework
- 08
Long-form padding
The bloat of guides and e-books: re-stating the premise each section, hollow transitions, filler chapters.
Now that we've covered X, let's turn to YIn conclusion,In summary,
- 09
Engagement bait
Rhetoric engineered for the scroll — commands to react, teased secrets, one-word dramatic answers.
Read that again.Let that sink in.Here's the thing:Nobody talks about this…The result? Freedom.
- 10
Staccato formatting
Every sentence its own paragraph, escalation chains, and two-word manifestos posing as emphasis.
one sentence per lineFive became fifty. Fifty became a movement.Build quietly. Learn constantly.
- 11
False binaries & fake reversals
Manufactured either/or framings and fake contrarianism that flatter the reader.
Most people X. Successful people Y.You don't need X. You need Y.Everyone says X. They're wrong.
- 12
Manufactured drama
Question chains delaying a trivial answer, transformation arcs, and fake-elevation reversals.
This isn't a budget. It's a statement of intent.It changed everything.Simple? Yes. Easy? No.
- 13
Chatbot residuenew
Assistant sign-offs and preambles left in from a copy-paste — the clearest giveaway of all.
Hope this helps!Let me know if you have any questionsCertainly!After careful consideration,As an AI language model,
FAQ
- Is my text stored?
- No. Drafts are processed to produce the edit and are not saved. The browser never talks to the AI directly — your text goes to our server, which holds the API key and returns the rewrite.
- Will it change what I meant?
- No. The editor preserves your meaning, facts, claims, and roughly your length — it never invents new claims or statistics. You choose how hard it edits: Light touch, Medium (default), or Full rewrite.
- How is this different from asking an AI to “rewrite this”?
- A general model often adds its own slop. UnSlopIt runs a purpose-built editor against a fixed taxonomy of tells (below) and shows you exactly what it changed and why — as a redline plus a clean version.
- What's the “add a typo” option?
- Perfectly clean text is itself a tell. Toggle it on and the editor slips in one small, natural typo so the result reads as human-written. We mark where it landed with a spellcheck-style squiggle.
- Can a real person edit it?
- Human editing is on the way. Register your interest on the home page and we'll email you when it's live.
- Is there a limit?
- In the prototype you get a few free edits, then the option to create a free account for more. Drafts are capped at 3,000 words per pass — split longer pieces by section.