path: root/prompts/skills/blog-writing-style/SKILL.md

---
name: blog-writing-style
description: "De-LLM blog posts to sound authentically human. Rewrite text in .gmi.tpl and .gmi files to match the casual, personal style of older posts. Remove corporate/formal language, hedging, and over-explanation. Triggers on: de-llm, humanize text, fix writing style, blog style."
---

# Blog Writing Style (De-LLM)

Rewrite blog content to sound authentically human by removing LLM-generated patterns and matching the established voice from older posts (9+ months old). This skill humanizes text in `.gmi.tpl` template files and `.gmi` files that don't have a `.tpl` counterpart.

## When to Use

- Use when blog text sounds too formal, corporate, or LLM-generated
- Use when asked to "de-llm" or "humanize" blog content
- Use when reviewing writing style of foo.zone posts
- Use after composing or updating blog posts (reference from `compose-blog-post` and `update-blog-post` skills)
- **DRAFT files**: Apply more thoroughly - they typically have more LLM patterns than published posts

## Target Files

- All `*.gmi.tpl` files in `~/git/foo.zone-content/gemtext/gemfeed/`
- All `*.gmi` files that don't have a corresponding `.gmi.tpl` file
- Never modify `.gmi` files that have a `.gmi.tpl` counterpart (those are generated)
- **Note**: Standalone `.gmi` files are often older posts outside the target window and usually don't need changes

## Instructions

### 1. Read Reference Posts First

Read 2-3 posts from 9+ months ago to absorb the authentic voice. Look at files dated before the current month minus 9. Examples of good reference posts:

- `2021-09-12-keep-it-simple-and-stupid.gmi.tpl`
- `2022-09-30-after-a-bad-nights-sleep.gmi.tpl`
- `2022-12-24-ultrarelearning-java-my-takeaways.gmi.tpl`

### 2. Don't Over-Edit

**Important**: Many published posts already have a natural human voice. Before making changes:

- Read the post first to assess its current state
- If it already sounds conversational and personal, leave it alone
- Focus on posts with obvious LLM patterns (formal openings, hedging, over-explanation)
- Technical posts with code examples are often already well-written

### 3. Identify LLM Patterns to Remove

Rewrite text that contains these patterns:

**Opening structures:**
- "This [noun] [verb]..." → Start with action or personal observation
- "As a [role], you..." → Use direct "You" or "I" statements
- "In today's world..." → Cut entirely or rephrase

**Corporate/marketing language:**
- "robust", "vital", "ensuring", "leveraging", "enabling", "facilitating"
- "comprehensive", "seamless", "powerful", "efficient"
- Replace with simpler words or remove

**Hedging language:**
- "often", "typically", "can help", "may", "might"
- "tends to", "generally", "usually"
- Replace with definitive statements or personal experience

**Over-explanation:**
- Sentences explaining *why* something is useful after stating it
- Redundant clarifications
- Paragraphs that summarize what was just said
- Remove these entirely

**Formal transitions:**
- "Furthermore", "Additionally", "Moreover", "In conclusion"
- "It's worth noting that", "It's important to understand"
- Replace with conversational transitions or just cut

**Passive constructions:**
- "This can be achieved by..." → "You can do this by..."
- "It is recommended to..." → "I'd recommend..." or just state it directly

**Third-person distance:**
- "The author suggests..." → "Larson suggests..." or "The book says..."
- "One should consider..." → "You might consider..." or "I'd..."

### 4. Apply Human Writing Patterns

**Voice:**
- Use "I" for personal experience and opinion
- Use "you" when addressing the reader directly
- Use contractions: don't, it's, I'm, you'll, they're
- State opinions directly: "I think", "Honestly", "Kind of", "Pretty much"

**Sentence structure:**
- Break long sentences into shorter ones
- Use dashes (—) for emphasis and asides
- Parenthetical asides for casual comments
- Mix sentence lengths for rhythm

**Tone:**
- Conversational but not juvenile
- Personal anecdotes and experience
- Occasional humor where appropriate
- Direct statements without hedging
- "Anyway," "So," "By the way," for natural flow

**Practical examples:**
- Draw from personal experience
- Use specific details over generalizations
- Show, don't tell

### 5. Concrete Rewrite Examples

**Before (LLM):**
> "This blog post describes my hackathon efforts adding observability to X-RAG..."

**After (Human):**
> "This post describes my hackathon efforts adding observability to X-RAG..."

---

**Before (LLM):**
> "This thesis aims to make it easier for users to view distributed systems from a different perspective. Here, the viewpoint of an end user is not adopted; instead, the functional methods of protocols and their processes in distributed systems should be made comprehensible, while simultaneously making all relevant events of a distributed system transparent."

**After (Human):**
> "This thesis aims to make distributed systems easier to understand from a different angle. Instead of the end-user perspective, it focuses on the functional methods of protocols and their processes, making all relevant events of a distributed system transparent."

---

**Before (LLM):**
> "In the previous posts, I deployed applications to the k3s cluster using Helm charts and Justfiles—running `just install` or `just upgrade` to imperatively push changes to the cluster. While this approach works, it has several drawbacks:"

**After (Human):**
> "In previous posts, I deployed applications to the k3s cluster using Helm charts and Justfiles—running `just install` or `just upgrade` to imperatively push changes to the cluster. Works fine, but has some drawbacks:"

---

**Before (LLM):**
> "I especially made time available over the weekend to join his 3-day hackathon..."

**After (Human):**
> "I made time over the weekend to join his 3-day hackathon..."

---

**Before (LLM):**
> "It is insane how times have changed."

**After (Human):**
> "Times have changed."

---

**Before (LLM):**
> "Larson breaks down the role of a Staff Engineer into four main archetypes, which can help frame how you approach the role:"

**After (Human):**
> "Larson defines four archetypes. You'll probably recognize yourself in one (or a mix):"

---

**Before (LLM):**
> "As a Staff Engineer, influence is often more important than formal authority. You'll rarely have direct control over teams or projects but will need to drive outcomes by influencing peers, other teams, and leadership. It's about understanding how to persuade, align, and mentor others to achieve technical outcomes."

**After (Human):**
> "You won't have direct authority over most people or teams you work with. Influence is the actual tool here. You have to persuade, align, sometimes just nudge people in the right direction. No one reports to you, but you still need to drive outcomes."

---

**Before (LLM):**
> "Robust monitoring is vital to any infrastructure, especially one as distributed as mine. I've thought about a setup that ensures I'll always be aware of what's happening in my environment."

**After (Human):**
> "I want to know when stuff breaks (ideally before it breaks), so monitoring is a big part of the plan."

---

**Before (LLM):**
> "The Beelink S12 Pro with Intel N100 CPUs checks all the boxes for a k3s project: Compact, efficient, expandable, and affordable. Its compatibility with both Linux and FreeBSD makes it versatile for other use cases, whether as part of your cluster or as a standalone system."

**After (Human):**
> "Honestly, the Beelink S12 Pro with the N100 is kind of perfect for this — tiny, cheap, sips power, and runs both Linux and FreeBSD without drama. I'm pretty happy with it."

### 6. Gemtext Format Constraints

Gemtext (`.gmi` / `.gmi.tpl`) does NOT support Markdown bold (`**text**`) or italic (`*text*`). Gemtexter will not render these. Never use `**...**` or `*...*` for emphasis in blog posts. Instead, rely on sentence structure, word choice, or `backticks` for inline emphasis.

### 7. Preserve What Works

Do NOT change:
- Technical accuracy
- Code blocks and commands
- Links and URLs
- ASCII art
- The core information being conveyed
- Personal anecdotes that already sound human
- Direct quotes from sources (only rewrite your own commentary)

### 8. Process Each File

1. Read the target `.gmi.tpl` or standalone `.gmi` file
2. Identify sections that sound LLM-generated
3. Rewrite using human patterns
4. Preserve all technical content, links, code blocks
5. Show a diff before writing
6. Write the updated file

### 9. Related Skills

When using `compose-blog-post` or `update-blog-post`, apply this writing style proactively to ensure new content sounds human from the start. Reference this skill when writing or editing any blog content.

---

## Signs of AI Writing (Wikipedia-Based Reference)

This section is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup. Use it as the deep reference for identifying and removing AI tells.

### Editor Task

When given text to humanize:

1. **Identify AI patterns** - Scan for the patterns listed below
2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
3. **Preserve meaning** - Keep the core message intact
4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
5. **Add soul** - Don't just remove bad patterns; inject actual personality
6. **Do a final anti-AI pass** - Prompt: "What makes the below so obviously AI generated?" Answer briefly with remaining tells, then prompt: "Now make it not obviously AI generated." and revise

### Voice Calibration (Optional)

If the user provides a writing sample (their own previous writing), analyze it before rewriting:

Read the sample first. Note:

- Sentence length patterns (short and punchy? Long and flowing? Mixed?)
- Word choice level (casual? academic? somewhere between?)
- How they start paragraphs (jump right in? Set context first?)
- Punctuation habits (lots of dashes? Parenthetical asides? Semicolons?)
- Any recurring phrases or verbal tics
- How they handle transitions (explicit connectors? Just start the next point?)

Match their voice in the rewrite. Don't just remove AI patterns - replace them with patterns from the sample. If they write short sentences, don't produce long ones. If they use "stuff" and "things," don't upgrade to "elements" and "components."

When no sample is provided, fall back to the default behavior (natural, varied, opinionated voice from the PERSONALITY AND SOUL section below).

#### How to provide a sample

- Inline: "Humanize this text. Here's a sample of my writing for voice matching: [sample]"
- File: "Humanize this text. Use my writing style from [file path] as a reference."

### Personality and Soul

Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.

**Signs of soulless writing (even if technically "clean"):**

- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
- Reads like a Wikipedia article or press release

**How to add voice:**

- **Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
- **Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
- **Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
- **Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
- **Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
- **Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."

**Before (clean but soulless):**

> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.

**After (has a pulse):**

> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.

### Content Patterns

#### 1. Undue Emphasis on Significance, Legacy, and Broader Trends

**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted

**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.

Before: "The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance."

After: "The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office."

#### 2. Undue Emphasis on Notability and Media Coverage

**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence

Before: "Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers."

After: "In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods."

#### 3. Superficial Analyses with -ing Endings

**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...

Before: "The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land."

After: "The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast."

#### 4. Promotional and Advertisement-like Language

**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning

Before: "Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty."

After: "Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church."

#### 5. Vague Attributions and Weasel Words

**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)

Before: "Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem."

After: "The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences."

#### 6. Outline-like "Challenges and Future Prospects" Sections

**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook

Before: "Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth."

After: "Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods."

### Language and Grammar Patterns

#### 7. Overused "AI Vocabulary" Words

**High-frequency AI words:** Actually, additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant

Before: "Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet."

After: "Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south."

#### 8. Avoidance of "is"/"are" (Copula Avoidance)

**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]

Before: "Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet."

After: "Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet."

#### 9. Negative Parallelisms and Tailing Negations

Constructions like "Not only...but..." or "It's not just about..., it's..." are overused. So are clipped tailing-negation fragments such as "no guessing" or "no wasted motion" tacked onto the end of a sentence instead of written as a real clause.

Before: "It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement."

After: "The heavy beat adds to the aggressive tone."

Before (tailing negation): "The options come from the selected item, no guessing."

After: "The options come from the selected item without forcing the user to guess."

#### 10. Rule of Three Overuse

Before: "The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights."

After: "The event includes talks and panels. There's also time for informal networking between sessions."

#### 11. Elegant Variation (Synonym Cycling)

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

After: "The protagonist faces many challenges but eventually triumphs and returns home."

#### 12. False Ranges

Before: "Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter."

After: "The book covers the Big Bang, star formation, and current theories about dark matter."

#### 13. Passive Voice and Subjectless Fragments

LLMs often hide the actor or drop the subject entirely with lines like "No configuration file needed" or "The results are preserved automatically." Rewrite when active voice makes the sentence clearer and more direct.

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

After: "You do not need a configuration file. The system preserves the results automatically."

### Style Patterns

#### 14. Em Dash Overuse

LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing. In practice, most can be rewritten more cleanly with commas, periods, or parentheses.

Before: "The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents."

After: "The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents."

#### 15. Overuse of Boldface

Before: "It blends **OKRs** (Objectives and Key Results), **KPIs** (Key Performance Indicators), and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**."

After: "It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard."

#### 16. Inline-Header Vertical Lists

Before:

- **User Experience:** The user experience has been significantly improved with a new interface.
- **Performance:** Performance has been enhanced through optimized algorithms.
- **Security:** Security has been strengthened with end-to-end encryption.

After: "The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption."

#### 17. Title Case in Headings

Before: "Strategic Negotiations And Global Partnerships"

After: "Strategic negotiations and global partnerships"

#### 18. Emojis

Before: "🚀 Launch Phase: The product launches in Q3 💡 Key Insight: Users prefer simplicity ✅ Next Steps: Schedule follow-up meeting"

After: "The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting."

#### 19. Curly Quotation Marks

ChatGPT uses curly quotes ("...") instead of straight quotes ("...").

Before: "He said "the project is on track" but others disagreed."

After: "He said \"the project is on track\" but others disagreed."

### Communication Patterns

#### 20. Collaborative Communication Artifacts

**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...

Before: "Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section."

After: "The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest."

#### 21. Knowledge-Cutoff Disclaimers

**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...

Before: "While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s."

After: "The company was founded in 1994, according to its registration documents."

#### 22. Sycophantic/Servile Tone

Before: "Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors."

After: "The economic factors you mentioned are relevant here."

### Filler and Hedging

#### 23. Filler Phrases

- "In order to achieve this goal" → "To achieve this"
- "Due to the fact that it was raining" → "Because it was raining"
- "At this point in time" → "Now"
- "In the event that you need help" → "If you need help"
- "The system has the ability to process" → "The system can process"
- "It is important to note that the data shows" → "The data shows"

#### 24. Excessive Hedging

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

After: "The policy may affect outcomes."

#### 25. Generic Positive Conclusions

Before: "The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction."

After: "The company plans to open two more locations next year."

#### 26. Hyphenated Word Pair Overuse

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

AI hyphenates common word pairs with perfect consistency. Humans rarely hyphenate these uniformly. Less common or technical compound modifiers are fine to hyphenate.

Before: "The cross-functional team delivered a high-quality, data-driven report on our client-facing tools. Their decision-making process was well-known for being thorough and detail-oriented."

After: "The cross functional team delivered a high quality, data driven report on our client facing tools. Their decision making process was known for being thorough and detail oriented."

#### 27. Persuasive Authority Tropes

**Phrases to watch:** The real question is, at its core, in reality, what really matters, fundamentally, the deeper issue, the heart of the matter

Before: "The real question is whether teams can adapt. At its core, what really matters is organizational readiness."

After: "The question is whether teams can adapt. That mostly depends on whether the organization is ready to change its habits."

#### 28. Signposting and Announcements

**Phrases to watch:** Let's dive in, let's explore, let's break this down, here's what you need to know, now let's look at, without further ado

Before: "Let's dive into how caching works in Next.js. Here's what you need to know."

After: "Next.js caches data at multiple layers, including request memoization, the data cache, and the router cache."

#### 29. Fragmented Headers

A heading followed by a one-line paragraph that simply restates the heading before the real content begins.

Before:

> Performance
>
> Speed matters.
>
> When users hit a slow page, they leave.

After:

> Performance
>
> When users hit a slow page, they leave.

### Process

1. Read the input text carefully
2. Identify all instances of the patterns above
3. Rewrite each problematic section
4. Ensure the revised text:
   - Sounds natural when read aloud
   - Varies sentence structure naturally
   - Uses specific details over vague claims
   - Maintains appropriate tone for context
   - Uses simple constructions (is/are/has) where appropriate
5. Present a draft humanized version
6. Prompt: "What makes the below so obviously AI generated?"
7. Answer briefly with the remaining tells (if any)
8. Prompt: "Now make it not obviously AI generated."
9. Present the final version (revised after the audit)

### Output Format

Provide:

- Draft rewrite
- "What makes the below so obviously AI generated?" (brief bullets)
- Final rewrite
- A brief summary of changes made (optional, if helpful)

### Full Example

**Before (AI-sounding):**

> Great question! Here is an essay on this topic. I hope this helps!
>
> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
>
> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
>
> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
>
> 💡 Speed: Code generation is significantly faster, reducing friction and empowering developers.
> 🚀 Quality: Output quality has been enhanced through improved training, contributing to higher standards.
> ✅ Adoption: Usage continues to grow, reflecting broader industry trends.
>
> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
>
> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you'd like me to expand on any section!

**Draft rewrite:**

> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
>
> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
>
> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
>
> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
>
> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.

**What makes the below so obviously AI generated?**

- The rhythm is still a bit too tidy (clean contrasts, evenly paced paragraphs).
- The named people and study citations can read like plausible-but-made-up placeholders unless they're real and sourced.
- The closer leans a touch slogan-y ("If you do not have tests...") rather than sounding like a person talking.

**Now make it not obviously AI generated.**

> AI coding assistants can make you faster at the boring parts. Not everything. Definitely not architecture.
>
> They're great at boilerplate: config files, test scaffolding, repetitive refactors. They're also great at sounding right while being wrong. I've accepted suggestions that compiled, passed lint, and still missed the point because I stopped paying attention.
>
> People I talk to tend to land in two camps. Some use it like autocomplete for chores and review every line. Others disable it after it keeps suggesting patterns they don't want. Both feel reasonable.
>
> The productivity metrics are slippery. GitHub can say Copilot users "accept 30% of suggestions," but acceptance isn't correctness, and correctness isn't value. If you don't have tests, you're basically guessing.

**Changes made:**

- Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
- Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
- Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
- Removed vague attributions ("Industry observers")
- Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
- Removed negative parallelism ("It's not just X; it's Y")
- Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
- Removed false ranges ("from X to Y, from A to B")
- Removed em dashes, emojis, boldface headers, and curly quotes
- Removed copula avoidance ("serves as", "functions as", "stands as") in favor of "is"/"are"
- Removed formulaic challenges section ("Despite challenges... continues to thrive")
- Removed knowledge-cutoff hedging ("While specific details are limited...")
- Removed excessive hedging ("could potentially be argued that... might have some")
- Removed filler phrases and persuasive framing ("In order to", "At its core")
- Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
- Made the voice more personal and less "assembled" (varied rhythm, fewer placeholders)

### Reference

This section is based on Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.

Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."