All skills
Skillintermediate

Anti-AI Writing Patterns

A condensed guide to patterns that signal AI-generated text. Use this to identify patterns the ghost writer should suppress and to help users articulate what feels "off" in AI writing.

Claude Code Knowledge Pack7/10/2026

Overview

Anti-AI Writing Patterns

A condensed guide to patterns that signal AI-generated text. Use this to identify patterns the ghost writer should suppress and to help users articulate what feels "off" in AI writing.

Why This Matters

Large language models regress to the mean—they produce statistically likely text that sounds like the average of their training data. This creates identifiable patterns that feel generic, promotional, or formulaic. Human writing has idiosyncrasies; AI writing smooths them out.

The goal isn't to avoid these patterns entirely (humans use some of them too), but to:

  1. Help users identify AI patterns in ghost writer output
  2. Document which patterns violate a specific writer's voice
  3. Give the ghost writer explicit suppression instructions

Pattern Categories

1. Significance Puffery

AI tends to inflate the importance of subjects with grand, empty language.

Words to Watch:

  • stands as / serves as / is a testament to
  • plays a vital/significant/crucial role
  • underscores/highlights its importance
  • reflects broader [trends/themes/issues]
  • enduring/lasting impact/legacy
  • key turning point
  • indelible mark
  • profound heritage

Examples:

"Berry Hill today stands as a symbol of community resilience and historical continuity."

"These citations illustrate lasting influence in computational linguistics."

"By preying on pests, this species plays a significant role in natural pest control, contributing to ecological balance."

Why It Feels Artificial: Facts, events, and beetles don't "underscore" or "highlight" anything. This is the AI narrator making unsupported claims about significance. Real writers either let importance speak for itself or argue for it explicitly.


2. Superficial Analysis

AI attaches shallow analytical phrases—often present participles (-ing)—to make statements seem more substantive.

Words to Watch:

  • ensuring...
  • highlighting...
  • emphasizing...
  • reflecting...
  • underscoring...
  • showcasing...
  • aligns with...
  • contributing to...

Examples:

"In 2025, the Federation was internationally recognized, highlighting Pakistan's entry into the global pickleball community."

"These partnerships reflect the company's role in serving both corporate and community organizations."

"The civil rights movement emerged as a powerful continuation of this struggle, emphasizing the importance of solidarity."

Why It Feels Artificial: The participle phrase adds no information—it's the AI asserting what something means rather than showing it. Human writers tend to let readers draw conclusions or make arguments explicitly.


3. Promotional Language

AI trained on marketing copy produces tourism-brochure prose even for mundane subjects.

Words to Watch:

  • rich/vibrant tapestry
  • artistic/cultural/literary landscape
  • boasts a
  • continues to captivate
  • stunning natural beauty
  • groundbreaking
  • nestled
  • in the heart of
  • gateway to
  • diverse attractions

Examples:

"Nestled within the breathtaking region of Gonder, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage."

"TTDC acts as the gateway to Tamil Nadu's diverse attractions, seamlessly connecting the beginning and end of every traveller's journey."

Why It Feels Artificial: This reads like advertising, not informative writing. The adjectives are empty calories. Real writers use specific details rather than generic enthusiasm.


4. Formulaic Structures

AI relies on predictable templates, especially for complex topics.

The "Important to Note" Pattern:

  • It's important to note/remember/consider
  • However, it should be noted that
  • It's worth mentioning that

The "Despite Challenges" Formula:

"Despite its [positive attributes], [subject] faces challenges including... Despite these challenges, [subject] continues to thrive/remains positioned for/demonstrates resilience."

The Summary Conclusion:

  • In summary...
  • In conclusion...
  • Overall...

Examples:

"It's important to note that AYUSH practitioners remain unregulated by the National Medical Commission."

"Despite its industrial prosperity, Korattur faces challenges typical of urban areas... With its strategic location, Korattur continues to thrive as an integral part of the industrial zone."

Why It Feels Artificial: These are templates, not thoughts. Real writers structure arguments based on the specific content, not generic formulas. The "despite challenges" pattern is especially mechanical—it pre-answers objections without engaging with them.


5. Hedging Patterns

AI uses vague quantifiers to avoid commitment.

Words to Watch:

  • various
  • numerous
  • significant
  • several
  • many
  • some critics argue
  • observers have noted
  • industry reports suggest

Examples:

"He made various contributions to numerous fields."

"Some critics argue that the methodology has limitations."

Why It Feels Artificial: These words carry almost no information. "Various contributions to numerous fields" could describe anyone. Real writers either specify or omit.


6. Elegant Variation (Synonym Swapping)

AI has repetition penalties that cause excessive synonym use, especially for key terms.

Example:

"Vierny committed to supporting artists resisting the constraints of socialist realism... In the challenging climate of Soviet artistic constraints, non-conformist artists faced obstacles in expressing their creativity freely... like-minded artists shared a common goal—to break free from the confines of state-imposed artistic norms... Russian avant-garde artists... the diverse yet united front of non-conformist artists challenging the artistic norms of their time."

Why It Feels Artificial: The constant substitution ("artists" → "non-conformist artists" → "like-minded artists" → "Russian avant-garde artists") draws attention to itself. Natural repetition is less distracting than forced variation.


7. Rule of Three Overuse

AI loves triple constructions, often using them to pad superficial analysis.

Examples:

"The conference brings together global SEO professionals, marketing experts, and growth hackers to discuss trends. The event features keynote sessions, panel discussions, and networking opportunities."

"His work reflects passion, dedication, and artistic vision."

Why It Feels Artificial: The rule of three is a legitimate rhetorical device, but AI uses it mechanically. When every list has exactly three items, it becomes a tell.


8. False Ranges

AI uses "from X to Y" constructions that don't form meaningful scales.

Examples:

"Intelligence and Creativity: From problem-solving and tool-making to scientific discovery, artistic expression, and technological innovation..."

"Continued Scientific Discovery: The quest to understand the universe will continue to drive breakthroughs, from fundamental physics to medicine and neuroscience."

Why It Feels Artificial: Real ranges have identifiable midpoints and logical progression. "From soup to nuts" works because it's a time-based scale (courses in a meal). "From problem-solving to artistic expression" has no coherent middle ground.


9. Negative Parallelisms

AI overuses "not only... but also" and similar constructions.

Examples:

"Self-Portrait constitutes not only a work of self-representation, but a visual document of her obsessions."

"It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere."

Why It Feels Artificial: These constructions create false drama. They imply revelation ("you might think X, but actually Y!") where none exists. Real writers use them sparingly for genuine contrasts.


10. Common AI Words and Phrases

Certain words appear disproportionately in AI output:

High-Frequency AI Words:

  • delve / delve into
  • navigate (especially "navigate the complexities")
  • landscape (especially "cultural landscape," "media landscape")
  • multifaceted
  • intricate
  • crucial / vital / pivotal
  • foster
  • leverage
  • cutting-edge
  • in-depth
  • comprehensive
  • robust
  • embark (especially "embark on a journey")
  • shed light on
  • at its core
  • utilize (instead of "use")

Why These Words: They're formal-sounding without being specific. They appear frequently in the kind of professional/academic prose that dominates training data.


11. Structural Tells

Title Case in Subheadings: AI strongly prefers capitalizing all major words in headings ("The Impact Of Technology On Society") rather than sentence case.

Excessive Boldface: AI trained on readmes and listicles bolds key terms mechanically.

Numbered Lists with Inline Headers:

"1. Historical Context: The world was changing..." "2. Key Figures: Edward Teller advocated..."

Why It Feels Artificial: These formatting choices come from specific genres (documentation, sales materials, how-to guides) and feel out of place in prose.


Using This Reference

During Discovery

Ask users:

  • "What phrases immediately scream 'AI' to you?"
  • "When you read AI-generated text, what tips you off?"
  • "Which of these patterns do you consciously avoid?"

For the DNA Document

In the Anti-Patterns section, check which AI patterns to suppress based on what would violate this writer's voice.

For the Ghost Writer

The Ghost Writer Briefing should explicitly list AI patterns to avoid:

Don't Do This:

  • No "it's important to note" or similar hedging
  • No significance puffery ("stands as a testament")
  • No "despite challenges" formula
  • Avoid "delve," "navigate," "landscape"
  • Don't use elegant variation—repeat key terms naturally

Important Caveat

This is descriptive, not prescriptive.

Humans use some of these patterns too. The goal isn't to ban words but to:

  1. Recognize when AI-generated text exhibits these patterns
  2. Document which patterns violate a specific writer's voice
  3. Give the ghost writer clear suppression instructions

A writer who genuinely uses em-dashes heavily shouldn't be told to avoid them. A writer who naturally hedges shouldn't be forced into false confidence. The DNA document captures what's authentic for this writer, which may include some "AI-like" patterns used genuinely.


Quick Reference Checklist

When reviewing ghost writer output, watch for:

  • Significance inflation ("stands as," "plays a vital role")
  • Superficial -ing phrases ("highlighting," "emphasizing")
  • Promotional adjectives ("vibrant," "stunning," "rich tapestry")
  • Template structures ("despite challenges," "it's important to note")
  • Vague hedging ("various," "numerous," "significant")
  • Excessive synonym variation
  • Mechanical rule of three
  • False ranges ("from X to Y" without real scale)
  • Empty contrast ("not only... but also" without genuine contrast)
  • High-frequency AI words ("delve," "navigate," "landscape")
  • Formatting tells (title case, excessive bold, numbered list headers)

If multiple patterns appear together, the text likely needs revision to match the writer's authentic voice.