UnSlopIt.aiTry it →

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.

  1. 01

    Buzz verbs

    Verbs that sound like motion but describe none. AI reaches for them to seem energetic.

    delveleverageunlockelevateempowersuperchargerevolutionize

  2. 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

  3. 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

  4. 04

    Empty intensifiers & adverbs

    Words that turn up the volume without adding information — including adverbs bolted onto plain verbs.

    trulyincrediblysignificantlyquietly transformsseamlessly runs

  5. 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…

  6. 06

    Detector-bait vocabulary

    Words statistically overrepresented in LLM text — the ones AI-detection tools flag first.

    intricatepivotalcrucialtapestrymultifacetedunderscoresplays a crucial role

  7. 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

  8. 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,

  9. 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. 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. 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. 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. 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.
Unslop your draft →