Based on Wikipedia's AI Writing Guide

Remove AI Writing Patterns

Transform robotic, AI-generated text into natural, human-sounding writing. Detect and fix 29+ patterns that make content obviously machine-written.

See it in action View all rules
humanizer-demo.tsx
AI-Generated Input
The restaurant serves as a testament to the vibrant culinary landscape of the region, showcasing the intricate interplay between traditional techniques and modern innovation. Additionally, the chef's commitment to fostering local partnerships underscores the establishment's pivotal role in the community.
Humanized Output
The restaurant uses traditional techniques with modern twists. The chef partners with local farms and has become a fixture in the neighborhood since opening in 2019.

29+ Patterns Detected

Comprehensive detection based on Wikipedia's "Signs of AI Writing" guide, maintained by WikiProject AI Cleanup.

Promotional Language

Removes puffery like "vibrant," "stunning," "breathtaking," and "nestled in the heart of" that AI uses to sound impressive.

Content Patterns

Rule of Three Overuse

Breaks up forced groupings of three that AI uses to appear comprehensive but feel mechanical.

Style Patterns

Superficial -ing Phrases

Eliminates tacked-on participles like "highlighting," "underscoring," and "symbolizing" that add fake depth.

Language Patterns

Vague Attributions

Replaces weasel words like "Experts argue" and "Industry reports" with specific, verifiable sources.

Content Patterns

Em Dash Overuse

Reduces excessive em dashes that AI uses to mimic "punchy" sales writing, replacing with cleaner punctuation.

Style Patterns

Chatbot Artifacts

Strips conversational residue like "Great question!" and "I hope this helps!" from generated content.

Communication
29+
AI Patterns
100+
Trigger Words
5
Categories
MIT
License

Complete Rule Set

Click any rule to see examples and trigger words.

1
Undue Emphasis on Significance

AI writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.

Words to watch: stands as serves as testament reminder vital role crucial moment underscores highlights broader trends symbolizing
2
Undue Emphasis on Notability

AI hits readers over the head with claims of notability, often listing sources without context.

Words to watch: independent coverage media outlets leading expert active social media presence
3
Superficial Analyses with -ing

AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.

Words to watch: highlighting underscoring emphasizing ensuring reflecting symbolizing contributing to cultivating fostering showcasing
4
Promotional Language

AI has serious problems keeping a neutral tone, especially for "cultural heritage" topics.

Words to watch: boasts vibrant rich heritage profound showcasing exemplifies commitment to natural beauty nestled in the heart of breathtaking must-visit stunning
5
Vague Attributions

AI chatbots attribute opinions to vague authorities without specific sources.

Words to watch: Industry reports Observers Experts argue Some critics several sources
6
Formulaic "Challenges" Sections

Many AI-generated articles include formulaic "Challenges" sections that follow predictable patterns.

Phrases to watch: Despite its... faces several challenges Despite these challenges Challenges and Legacy Future Outlook
7
Overused "AI Vocabulary"

These words appear far more frequently in post-2023 text and often co-occur.

High-frequency AI words: actually additionally align with crucial delve emphasizing enduring enhance fostering garner highlight interplay intricate landscape pivotal tapestry testament underscore valuable vibrant
8
Copula Avoidance

AI substitutes elaborate constructions for simple copulas (is/are/has).

Words to watch: serves as stands as marks represents boasts features offers
9
Negative Parallelisms

Constructions like "Not only...but..." or "It's not just about..., it's..." are overused.

Patterns to watch: Not only...but It's not just about no guessing no wasted motion
10
Rule of Three Overuse

AI forces ideas into groups of three to appear comprehensive.

Example: "The event features keynote sessions, panel discussions, and networking opportunities."

Fix: "The event includes talks and panels. There's also time for informal networking."
11
Elegant Variation

AI has repetition-penalty code causing excessive synonym substitution.

Example: "The protagonist faces challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home."

Fix: "The protagonist faces challenges but eventually triumphs and returns home."
12
False Ranges

AI uses "from X to Y" constructions where X and Y aren't on a meaningful scale.

Example: "Our journey has taken us from the singularity to the cosmic web, from stars to dark matter."

Fix: "The book covers the Big Bang, star formation, and current theories about dark matter."
13
Passive Voice

AI often hides the actor or drops the subject entirely.

Example: "No configuration file needed. The results are preserved automatically."

Fix: "You don't need a configuration file. The system preserves results automatically."
14
Em Dash Overuse

AI uses em dashes more than humans, mimicking "punchy" sales writing.

Fix: Rewrite with commas, periods, or parentheses for cleaner prose.
15
Overuse of Boldface

AI chatbots emphasize phrases in boldface mechanically.

Example: "It blends **OKRs**, **KPIs**, and **Business Model Canvas**."

Fix: "It blends OKRs, KPIs, and tools like the Business Model Canvas."
16
Inline-Header Lists

AI outputs lists where items start with bolded headers followed by colons.

Example: "- **User Experience:** The UX has been improved..."

Fix: Convert to flowing prose or proper paragraphs.
17
Title Case in Headings

AI chatbots capitalize all main words in headings.

Example: "## Strategic Negotiations And Global Partnerships"

Fix: "## Strategic negotiations and global partnerships"
18
Emoji Overuse

AI chatbots decorate headings or bullet points with emojis.

Example: "🚀 Launch Phase, 💡 Key Insight, ✅ Next Steps"

Fix: Remove emojis or use sparingly for actual emphasis.
19
Curly Quotation Marks

ChatGPT uses curly quotes instead of straight quotes.

Example: "He said "the project is on track""

Fix: "He said "the project is on track""
20
Collaborative Artifacts

Text meant as chatbot correspondence gets pasted as content.

Phrases to remove: I hope this helps Of course! Certainly! You're absolutely right! let me know here is a...
21
Knowledge-Cutoff Disclaimers

AI disclaimers about incomplete information get left in text.

Phrases to remove: as of [date] Up to my last training update While specific details are limited based on available information
22
Sycophantic Tone

Overly positive, people-pleasing language.

Example: "Great question! You're absolutely right that this is complex."

Fix: "The factors you mentioned are relevant here."
23
Filler Phrases

Wordy constructions that add no meaning.

Before → After:
"In order to achieve this goal" → "To achieve this"
"Due to the fact that" → "Because"
"At this point in time" → "Now"
"The system has the ability to" → "The system can"
24
Excessive Hedging

Over-qualifying statements.

Example: "It could potentially possibly be argued that the policy might have some effect."

Fix: "The policy may affect outcomes."
25
Generic Positive Conclusions

Vague upbeat endings that say nothing specific.

Example: "The future looks bright. Exciting times lie ahead as they continue their journey toward excellence."

Fix: "The company plans to open two more locations next year."
26
Hyphenated Word Overuse

AI hyphenates common word pairs with perfect consistency.

Words to watch: third-party cross-functional client-facing data-driven decision-making well-known high-quality real-time long-term end-to-end
27
Persuasive Authority Tropes

Phrases that pretend to cut through noise to deeper truth.

Phrases to watch: The real question is at its core in reality what really matters fundamentally the heart of the matter
28
Signposting

AI announces what it's about to do instead of doing it.

Phrases to remove: Let's dive in let's explore let's break this down here's what you need to know without further ado
29
Fragmented Headers

A heading followed by a one-line paragraph that restates the heading.

Example: "## Performance / Speed matters. / When users hit a slow page..."

Fix: "## Performance / When users hit a slow page..."

Make Your Writing Human

Join developers, writers, and editors who use Humanizer to remove AI patterns from their content.

View on GitHub