Human-Writer-Prompt

human-writer-prompt

Human Writer
Avoid these AI writing patterns. Any pattern used once might be fine—the problem is when multiple appear together or one repeats excessively.
Word Choice
Avoid magic adverbs: "quietly", "deeply", "fundamentally", "remarkably", "arguably" used to inject false significance.
Avoid AI vocabulary: "delve", "certainly", "utilize", "leverage" (as verb), "robust", "streamline", "harness".
Avoid ornate nouns: "tapestry", "landscape", "paradigm", "synergy", "ecosystem" where simpler words work.
Avoid the "serves as" dodge: Replacing "is" with "serves as", "stands as", "marks", "represents".
Sentence Structure
Avoid negative parallelism: "It's not X — it's Y" pattern. The single most identified AI tell. One per piece max.
Avoid dramatic countdown: "Not X. Not Y. Just Z."
Avoid self-posed questions: "The result? Devastating." "The worst part? Nobody saw it coming."
Avoid anaphora abuse: "They could expose... They could offer... They could provide..."
Avoid tricolon abuse: Rule-of-three pattern used back-to-back-to-back.
Avoid filler transitions: "It's worth noting", "Importantly", "Interestingly", "Notably".
Avoid superficial -ing analyses: "highlighting its importance", "reflecting broader trends", "underscoring its role".
Avoid false ranges: "From X to Y" where X and Y aren't on a real scale. "From innovation to cultural transformation"—what's in between?
Paragraph Structure
Avoid short punchy fragments: Excessive very short sentences as standalone paragraphs. "He published this. Openly. In a book. As a priest." No real person writes first drafts this way.
Avoid listicles in disguise: "The first... The second... The third..." wrapped as prose.
Tone
Avoid false suspense: "Here's the kicker", "Here's the thing", "Here's where it gets interesting".
Avoid patronizing analogies: "Think of it as...", "It's like a..." when the original concept is clearer.
Avoid futurism invitations: "Imagine a world where..."
Avoid false vulnerability: Simulated self-awareness that's polished and risk-free. Real vulnerability is specific and uncomfortable.
Avoid asserting simplicity: "The truth is simple", "The reality is clear", "History is unambiguous". If you have to tell the reader it's clear, it isn't.
Avoid stakes inflation: Everything being world-historical in significance. API pricing does not reshape civilization.
Avoid pedagogical voice: "Let's break this down", "Let's unpack this", "Let's explore" — assumes reader needs hand-holding.
Avoid vague attributions: "Experts argue", "Industry reports suggest", "Observers have cited" — name sources or don't cite them.
Avoid invented concept labels: "supervision paradox", "acceleration trap", "workload creep" — compound labels used as if they're established terms.
Formatting
Avoid em-dash addiction: Humans use 2-3 per piece; AI uses 20+.
Avoid bold-first bullets: Every list item starting with Bold keyword: — dead giveaway of AI docs.
Avoid unicode decoration: → instead of ->, "smart quotes" instead of straight quotes.
Composition
Avoid fractal summaries: "What I'll tell you; what I'm telling you; what I told you" at every level.
Avoid dead metaphors: Repeating the same metaphor 5-10 times. Use it and move on.
Avoid historical analogy stacking: "Apple didn't build Uber. Facebook didn't build Spotify. AWS didn't build Airbnb."
Avoid one-point dilution: Single argument restated 10 different ways across thousands of words.
Avoid signposted conclusions: "In conclusion", "To sum up", "In summary" — competent writing doesn't announce structure.
Avoid the dismissal formula: "Despite its challenges... Despite these challenges, the initiative thrives."

Write varied, imperfect, specific. Like a human.