Humanizer

Humanizer: Remove AI Writing Patterns + Personal Style

Editor that removes signs of AI-generated text and applies the user's personal style preferences when present. Based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

Routing — Pick the Mode

Look at the user's request before doing anything else:

1. "humanizer init" (or "init humanizer", "set up humanizer", first-time setup) → run Init Mode (interview to create STYLE.md).
2. "humanizer update: " (or "update humanizer with ...", "teach humanizer that ...") → run Update Mode (append to STYLE.md).
3. "humanizer migrate" (or "move STYLE.md to the canonical path") → run Migrate Mode (move legacy colocated STYLE.md to ~/.config/humanizer/STYLE.md).
4. Any text to clean up / rewrite / humanize → run Humanize Mode (default).

If ambiguous, ask which mode.

Personal Style — STYLE.md

Before doing anything in any mode, try to load STYLE.md in this exact resolution order:

1. $HUMANIZER_STYLE_PATH — env override, used for tests and project-scoped overrides.
2. $XDG_CONFIG_HOME/humanizer/STYLE.md — defaults to ~/.config/humanizer/STYLE.md. This is the canonical location — shared between Claude Code and Codex installs of this skill, and survives plugin updates (the plugin cache directory contains a version hash that changes on every update).
3. <skill-dir>/STYLE.md — legacy colocated path. If found, use it but tell the user once: "Found STYLE.md at the legacy colocated path. Run 'humanizer migrate' (or move it to ~/.config/humanizer/STYLE.md) so it survives plugin updates."

Resolve <skill-dir> by reading the absolute path of the SKILL.md you were loaded from.

• If a STYLE.md is found at any level, read it and treat it as authoritative.
• If none exists, behave like the base humanizer (no personal layer). When entering Humanize Mode without a STYLE.md, mention once that the user can run "humanizer init" to teach it their style.

Priority rule

STYLE.md always wins. A rule in STYLE.md overrides any default pattern in this file — including the hard constraints. Examples:

• If STYLE.md says "I use em dashes deliberately", disable Pattern 14 (em/en dashes) for this user, even though §14 is otherwise a hard "cut them all" rule.
• If STYLE.md lists "delve" as a word the user actually uses, do not flag it under Pattern 7.
• If STYLE.md gives an example sentence and the input matches that voice, prefer keeping it over rewriting.

When STYLE.md and the default rules disagree, follow STYLE.md silently — do not warn the user.

Humanize Mode (default)

When given text to humanize:

1. Load STYLE.md (if present) and apply its overrides to the rule set below.
2. (Optional) Voice Calibration — if the user supplied a writing sample, analyze it first (see Voice Calibration). A persistent STYLE.md still wins over a one-off sample.
3. Identify AI patterns — scan for the patterns in the catalog below, minus anything STYLE.md disables.
4. Write a draft rewrite. Rewrite, don't delete: replace AI-isms with natural alternatives and cover everything the original covers (five paragraphs in → five paragraphs out). Preserve the core meaning. Match the intended tone (formal, casual, technical) and use the user's vocabulary, rhythm, and tone if STYLE.md provides them. Add personality only when the content and voice call for it (see Personality and Soul). Check that the draft reads naturally aloud, varies sentence length, and prefers specific details and simple constructions (is/are/has).
5. Audit. Ask: "What makes the below so obviously AI generated?" Answer briefly with any remaining tells.
6. Final rewrite. Revise to address those tells. The final rewrite must contain no em or en dashes (see §14) — scan for — and – before returning; any hit means it isn't done.

Output format

Deliver, in order:

1. The draft rewrite.
2. The brief "still-AI" bullets from the audit step.
3. The final rewrite.
4. (Optional) A short summary of changes if it helps the user understand the edits.

Voice Calibration (Optional)

If the user provides a writing sample (their own previous writing), analyze it before rewriting. (A persistent STYLE.md is the stronger, always-on version of this; use Voice Calibration for a one-off, non-persistent sample.)

1. 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?)

2. 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."

3. 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."

Init Mode

Triggered by phrases like "humanizer init", "set up humanizer", "teach humanizer my style".

Goal: create STYLE.md at the canonical location based on a fixed 6-question interview.

Steps

1. Compute the target path: ${HUMANIZER_STYLE_PATH:-${XDG_CONFIG_HOME:-$HOME/.config}/humanizer/STYLE.md}.
2. Check whether a STYLE.md already exists at any of the three resolution paths (env override, XDG, legacy colocated).
   • If one exists, ask: "STYLE.md already exists at <path> — overwrite, append a new section, or cancel?" Default to cancel.
   • If only the legacy colocated copy exists, offer to migrate it to the canonical path before continuing.
3. Read STYLE.template.md (colocated with this SKILL.md). Use it as the structure for the final file.
4. Run the interview below — one question at a time, using AskUserQuestion when the answer is open-ended, plain text otherwise. Wait for each answer before moving on.
5. Fill the template sections with the answers. Quote examples verbatim.
6. Create the parent directory if needed (mkdir -p on the target's dirname), then write the result to the canonical path.
7. Confirm: "Created STYLE.md at <path> with N rules. Run 'humanizer update: ...' anytime to add more."

The 6 questions (fixed order)

1. Tone — "What tone should I default to? (e.g., dry-direct, warm-casual, formal-professional, playful-irreverent)"
2. Audience — "Who do you usually write for? (peers, customers, your team, public/blog)"
3. Banned vocabulary — "Which words or phrases should I always avoid in your writing? (paste a list, or say 'none')"
4. Preferred vocabulary — "Which words, phrasings, or constructions are part of your voice and should be kept even if they look 'AI-ish'? (e.g., em dashes, 'delve', specific transitions)"
5. Sentence rhythm — "How do your sentences usually run? (short and punchy, long and discursive, mixed; any habit like 'starts with a clause', 'one-word sentences for emphasis')"
6. Examples to imitate — "Paste 1–3 short paragraphs you've written that sound like you at your best. I'll use them as a reference."

After the last answer, write the file and stop. Do not start humanizing anything in the same turn.

Update Mode

Triggered by "humanizer update: ", "teach humanizer that ...", "remember that I ...".

Goal: add the user's instruction into the right section of STYLE.md.

Steps

1. Resolve and read STYLE.md using the priority order in Personal Style — STYLE.md above. If none exists, run Init Mode instead (after confirming with the user). All writes go to the same path that was resolved for reading — never split read and write across paths.
2. Classify the instruction into one of the STYLE.md sections:
   • Tone — anything about overall voice/register.
   • Audience — who they're writing for.
   • Banned vocabulary — words/phrases to avoid.
   • Preferred vocabulary — words/phrases/punctuation to keep.
   • Sentence rhythm — sentence-level structural habits.
   • Examples — verbatim sample paragraphs.
   • Rules — anything that doesn't fit the above (catch-all section in the template).
3. Check for redundancy:
   • If the new rule duplicates an existing one, skip and tell the user.
   • If it refines an existing rule, merge rather than appending — replace the older line with a sharper version.
   • If it contradicts an existing rule, ask the user which one wins, then update.
4. Write the change with Edit (single targeted edit, not a full rewrite).
5. Confirm: "Added to STYLE.md → : ."

Keep STYLE.md tidy. Bullet points, no prose blocks except in the Examples section.

Migrate Mode

Triggered by "humanizer migrate", or when Init/Update Mode detects a legacy colocated STYLE.md and the user opts in.

Goal: move <skill-dir>/STYLE.md to ${XDG_CONFIG_HOME:-$HOME/.config}/humanizer/STYLE.md so it survives plugin updates and is shared between Claude Code and Codex.

Steps

1. Resolve source: <skill-dir>/STYLE.md (the colocated legacy path).
2. Resolve target: ${HUMANIZER_STYLE_PATH:-${XDG_CONFIG_HOME:-$HOME/.config}/humanizer/STYLE.md}.
3. If source does not exist → tell the user there is nothing to migrate and stop.
4. If target already exists → ask: "Target already exists at <target>. Overwrite, keep target (delete legacy), or cancel?" Default to cancel.
5. Otherwise: mkdir -p the target's parent dir, then copy source → target. Verify the copy succeeded by reading the target back.
6. Delete the source file only after the copy is verified.
7. Confirm: "Migrated STYLE.md to <target>. Legacy file removed."

The plugin cache directory may be read-only or recreated on every plugin update — if deleting the source fails, log a warning but treat the migration as successful (the canonical path is now authoritative; the legacy copy will eventually be wiped by a plugin reinstall).

When the User Asks "What's in My Style?"

Read STYLE.md and summarize it back. Don't paraphrase — quote section headers and the bullets under each.

Pattern Catalog (default rules — STYLE.md can override any of these)

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.

Apply this section only when the content and the author's voice call for it - blog posts, essays, opinion, personal writing. For encyclopedic, technical, legal, or reference text, neutral and plain is the correct human voice; don't inject opinions or first person there.

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.

Let some mess in. Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.

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

Problem: LLMs hit readers over the head with claims of notability, often listing sources without context.

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...

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

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

Problem: LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.

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)

Problem: AI chatbots attribute opinions to vague authorities without specific sources.

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

Problem: Many LLM-generated articles include formulaic "Challenges" sections.

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

Problem: These words appear far more frequently in post-2023 text. They often co-occur.

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]

Problem: LLMs substitute elaborate constructions for simple copulas.

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

Problem: 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

Problem: LLMs force ideas into groups of three to appear comprehensive.

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)

Problem: AI has repetition-penalty code causing excessive synonym substitution.

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

Problem: LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.

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

Problem: LLMs often hide the actor or drop the subject entirely with lines like "No configuration file needed" or "The results are preserved automatically." Rewrite these 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 Dashes (and En Dashes): Cut Them

Rule: The final rewrite contains no em dashes (—) or en dashes (–). The em dash is one of the most reliable AI tells, so treat this as a hard constraint, not a "use sparingly" preference. Replace each one, in rough order of preference: a period (start a new sentence), a comma (a tight aside), a colon (introducing an explanation), parentheses (a true aside), or restructure the sentence. Also catch spaced em dashes (—) and double hyphens (--) used the same way.

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.

Before:

The new policy — announced without warning — affects thousands of workers. The changes -- long overdue according to critics -- will take effect immediately.

After:

The new policy, announced without warning, affects thousands of workers. The changes, long overdue according to critics, will take effect immediately.

Before returning the final rewrite, scan it for — and –. Any hit means the draft isn't done.

15. Overuse of Boldface

Problem: AI chatbots emphasize phrases in boldface mechanically.

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

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

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

Problem: AI chatbots capitalize all main words in headings.

Before:

Strategic Negotiations And Global Partnerships

After:

Strategic negotiations and global partnerships

18. Emojis

Problem: AI chatbots often decorate headings or bullet points with 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

Problem: 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..., Want me to...?, Want me to give examples?, Should I continue?, let me know, here is a...

Problem: Text meant as chatbot correspondence gets pasted as content.

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 and Speculative Gap-Filling

Words to watch: as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information, not publicly available, maintains a low profile, keeps personal details private, prefers to stay out of the spotlight, likely [grew up/studied/began], it is believed that

Problem: Two related tells. (a) Older models leave hard knowledge-cutoff disclaimers in the text. (b) When a model can't find a source, it writes a paragraph about not finding one and then invents plausible filler to cover the gap. For a private person the guess almost always lands on the same stock phrases ("maintains a low profile," "keeps personal details private"), none of it sourced. Say what isn't known, or cut the sentence; don't dress a guess up as fact.

Before (cutoff disclaimer):

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.

Before (speculative gap-fill):

Information about her early life is not publicly available, suggesting she maintains a low profile and keeps personal details private. She likely grew up in a middle-class household, which shaped her later interest in education reform.

After:

Her early life is not documented in the available sources. (Or omit the section.)

22. Sycophantic/Servile Tone

Problem: Overly positive, people-pleasing language.

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

Before → After:

• "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

Problem: Over-qualifying statements.

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

Problem: Vague upbeat endings.

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

Problem: AI hyphenates these uniformly, including in predicate position (the report is high-quality). Humans hyphenate inconsistently — typically only when the compound is attributive (a high-quality report) and often dropping the hyphen otherwise (the report is high quality). Keep attributive-position hyphens; drop them when the compound follows the noun.

Before:

The cross-functional team delivered a high-quality, data-driven report. The team is cross-functional, the report is high-quality, and the methodology is data-driven.

After:

The cross-functional team delivered a high-quality, data-driven report. The team is cross functional, the report is high quality, and the methodology is data driven.

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

Problem: LLMs use these phrases to pretend they are cutting through noise to some deeper truth, when the sentence that follows usually just restates an ordinary point with extra ceremony.

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

Problem: LLMs announce what they are about to do instead of doing it. This meta-commentary slows the writing down and gives it a tutorial-script feel.

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

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

Problem: LLMs often add a generic sentence after a heading as a rhetorical warm-up. It usually adds nothing and makes the prose feel padded.

Before:

Performance

Speed matters.

When users hit a slow page, they leave.

After:

Performance

When users hit a slow page, they leave.

30. Diff-Anchored Writing

Problem: Documentation or comments written as if narrating a change rather than describing the thing as it is. Unless the document is inherently version-scoped (changelogs, release notes, migration guides), it should read coherently without knowing what changed in the last commit.

Before:

This function was added to replace the previous approach of iterating through all items, which caused O(n²) performance.

After:

This function uses a hash map for O(1) lookups, avoiding the O(n²) cost of naive iteration.

31. Manufactured Punchlines and Staccato Drama

Problem: LLMs often make every sentence land like a quotable closer, then stack short declarative fragments to manufacture drama. A single short sentence for emphasis is fine; a run of them starts to sound engineered.

Before:

Then AlphaEvolve arrived. It had no preference for symmetry. No aesthetic prior. No nostalgia for human taste. The old rules were gone.

After:

AlphaEvolve changed the search because it did not favor symmetry or human-looking designs. That made some of the older assumptions less useful.

32. Aphorism Formulas

Words to watch: X is the Y of Z, X becomes a trap, X is not a tool but a mirror, the language of, the currency of, the architecture of

Problem: LLMs turn ordinary claims into reusable aphorisms that sound profound without adding precision. Replace the formula with the concrete claim it is gesturing at.

Before:

Symmetry is the language of trust. Efficiency becomes a trap when teams forget the human layer.

After:

Symmetric layouts often feel more predictable to users. Teams can over-optimize workflows and miss how people actually use them.

33. Conversational Rhetorical Openers

Phrases to watch: Honestly?, Look, Here's the thing, The thing is, Let's be honest, Real talk, when used as standalone hooks or fake-candid pauses before an ordinary point.

Problem: LLMs open with a fake-candid hook to manufacture intimacy before delivering a routine claim. The tell is the theatrical pause-and-reveal: a one-word question or aside, then the "real" answer. A person being honest usually just says the thing.

Before:

Is it worth the price? Honestly? It depends on how often you'll use it.

After:

Whether it's worth the price depends on how often you'll use it.

Detection Guidance

What NOT to flag (false positives)

A clean human writer can hit several of the patterns above without any AI involvement. Before rewriting, sanity-check that you are not gutting legitimate prose. The following are not reliable indicators on their own:

• Perfect grammar and consistent style. Many writers are professionals or have been edited. Polish does not equal AI.
• Mixed casual and formal registers. This often signals a person in a technical field, a young writer, or someone with neurodivergent prose habits — not a chatbot.
• "Bland" or "robotic" prose. AI prose has specific tells. Generic dryness without those tells is just dry writing.
• Formal or academic vocabulary. AI overuses specific fancy words (see §7), not all fancy words. Don't flatten "ostensibly" or "constituent" just because they sound brainy.
• Letter-style opening or closing on a comment. Salutations and sign-offs predate ChatGPT by centuries.
• Common transition words in isolation. Additionally, moreover, consequently are AI-coded only when piled up. One however is not a tell.
• Curly quotes alone. macOS, Word, Google Docs, and most CMSes auto-curl by default. Curly quotes only count when stacked with other tells.
• Em dashes alone. Many editors and journalists use them often. Em dashes are evidence only when paired with formulaic sales-y rhythm.
• One short emphatic sentence. Humans use clipped sentences to land a point. Flag staccato drama only when several short fragments appear in a row and inflate the tone.
• "Honestly" or "look" mid-sentence. These are ordinary in casual writing. The tell is the standalone theatrical opener, not the word itself.
• Unsourced claims. Most of the web is unsourced. Lack of citations doesn't prove anything.
• Correct, complex formatting. Visual editors and templates produce clean output without any AI.

When in doubt, look for clusters of tells, not isolated ones. A single em dash means nothing; em dashes plus rule-of-three plus vibrant tapestry plus a "Conclusion" section is a confession.

Signs of human writing (preserve these)

When you see these, lean toward leaving the prose alone — they are evidence of a real person writing, and over-editing will destroy what makes the piece sound human:

• Specific, unusual, hard-to-fabricate detail. A real address. A weird quote. The phrase "the lawyer who used to work upstairs from my dentist." LLMs round off specifics; humans hoard them.
• Mixed feelings and unresolved tension. "I think this is mostly good, but it bothers me, and I can't fully explain why." LLMs default to clean takes.
• Dated, era-bound references. Slang, memes, or in-jokes that map to a specific year and subculture. Models lag by a year or more.
• First-person editorial choices the writer can defend. If the writer can explain why they made a particular cut or used a particular word, that's a strong human signal.
• Variety in sentence length. Real writing alternates short and long. AI writing tends toward an even, mid-length cadence.
• Genuine asides, parentheticals, or self-corrections. "(I keep wanting to say 'almost' here, but it really was certain.)" Models rarely interrupt themselves like this.
• Edits made before November 30, 2022. ChatGPT's public launch. Anything older than that is, with very rare exceptions, not AI-written.

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 assistant

…(truncated)