Anti-AI Slop

Detect and eliminate the 43 most common AI writing patterns that make your output sound robotic, generic, and untrustworthy.

Overview

AI-generated text has distinct fingerprints. Readers — and increasingly, AI detectors, editors, and discerning humans — recognize these patterns instantly. This skill gives you a complete taxonomy of AI slop and the tools to eliminate it from any writing task.

Inspired by community research on AI text humanization patterns.

The 43 AI Slop Patterns

Category 1: Red-Flag Vocabulary (21 words)

These words appear in AI output at dramatically higher rates than in human writing. Flag and replace every instance:

Rule: Before submitting any writing, run a mental find-replace on these 21 words. Replace with specifics.

Category 2: Formulaic Openings and Closings

Never open with:

• "In today's fast-paced world..."
• "In today's digital landscape..."
• "It's important to note that..."
• "At its core,..."
• "It goes without saying that..."

Never close with:

• "In conclusion," / "In summary," (on content under 2,000 words)
• "I hope this helps!"
• "Feel free to ask if you have any questions!"
• "Don't hesitate to reach out!"
• "Let me know if you need clarification!"

These phrases exist because AI models learned that polite closings correlate with positive feedback. They add zero information and signal low-effort output.

Fix: End with the last substantive sentence. No wrap-up. No invitation.

Category 3: Structural Slop (16 patterns)

1. Em dash overuse GPT-4o uses em dashes at ~10x the rate of GPT-3.5, and roughly 20x the rate of natural human prose. Every em dash is a candidate for deletion or replacement with a period or comma.

Slop: "The approach—while unconventional—delivers results." Fixed: "The approach is unconventional but delivers results."

2. Rule of three compulsion AI defaults to triplets: "clarity, conciseness, and coherence." Humans vary. Use two items, or five. Break the rhythm.

3. Metronomic sentence length AI produces uniform sentence lengths across paragraphs. Humans mix very short sentences. And sometimes run a bit longer when the thought needs it. Check your paragraph rhythm.

4. "It's not X, it's Y" contrast structure

Slop: "It's not about the destination, it's about the journey." AI overuses this false dichotomy structure. Replace with a direct claim.

5. False ranges

Slop: "From technical expertise to creative vision, we cover it all." These "from X to Y" constructions pad breadth without specificity. State the specific things.

6. Bolded title + reworded sentence bullets When every bullet point has a bold title followed by a sentence that just rephrases the title, cut the bold title or cut the sentence. Not both.

7. Excessive list-ification Lists are useful for genuine enumerations. Prose is better for connected ideas. If your bullets would read naturally as sentences, use sentences.

8. Compulsive summaries on short content A 300-word section does not need "Overall, this approach..." at the end. Summaries are for documents over 2,000 words.

9. Copula avoidance

Slop: "Coffee—the morning essential—powers productive days." This dash-framing avoids "is" because AI learned that "is" sounds plain. Write the is. Fixed: "Coffee is essential in the morning."

10. -ing phrase stacking

Slop: "Using advanced algorithms, leveraging data science, and employing modern techniques..." Participial phrase chains are an AI signature. Rewrite as direct verbs.

11. Synonym cycling Restating the same concept with synonym substitution to hit a word count. If you said it once, say it once.

12. Significance inflation Every point is "underscoring," "highlighting," or "demonstrating" something critical. Most points are just points. State the fact without announcing its importance.

13. Superficial attribution

Slop: "Some critics argue... Many experts believe..." Attribution without names or citations is padding. Either name the source or drop the attribution.

14. Formulaic section structure Opening statement + 3–5 bullets + summary sentence. Repeated for every section. Vary section shapes.

15. Excessive hedging "could be," "might suggest," "tends to," "often," "in many cases" — AI hedges to avoid being wrong. Be specific. If you're uncertain, say why you're uncertain once, then commit.

16. No human texture Human writing has contractions, parenthetical asides, humor, self-correction, specificity ("the 14-person team" not "the team"), and occasional fragment. If your draft has none of these, it reads like AI.

Operational Checklist

Run this before submitting any long-form writing:

[ ] Zero instances of the 21 red-flag words
[ ] No formulaic opening sentence
[ ] No courtesy closing ("feel free to", "hope this helps")
[ ] Em dashes: fewer than 1 per 200 words
[ ] No "from X to Y" false range constructions
[ ] Sentence length variation present in every paragraph
[ ] No "not X, it's Y" contrast structures
[ ] All bullet points are genuine enumerations, not prose fragments
[ ] No summary paragraph on content under 2,000 words
[ ] At least one contraction in casual writing
[ ] All attributions name a source or are deleted

When to Apply

Apply this skill to:

• Any written content destined for human readers
• Blog posts, documentation, emails, proposals, social media
• Situations where the writing being perceived as AI-generated would damage credibility

Do not apply to:

• Code comments (different conventions)
• Internal tooling output read only by machines
• Situations where the human explicitly wants systematic/structured AI output