Skip to content
Writing

AI Writing: Avoid the Slop

Any of these patterns used once might be fine. The problem is when multiple tropes appear together or when one is used repeatedly. Write like a human: varied, imperfect, specific.

Adapted from tropes.fyi by ossama.is, with additions from practice.

Hard Bans

Never use these. They are AI tells regardless of context.

Verbs & Adjectives

delveutilizeleverage (as verb)robuststreamlineharness

Nouns & Metaphors

tapestrylandscape (for domains)paradigmsynergyecosystem

Filler Phrases

serves asstands asmarks a pivotalrepresents aIt's worth notingIt bears mentioningImportantlyInterestinglyNotably

False Engagement

Here's the kickerHere's the thingHere's where it gets interestingThink of it as...Think of it like...Imagine a world where...

Structural Crutches

Let's break this downLet's unpack thisLet's exploreLet's dive inIn conclusionTo sum upIn summaryExperts argueIndustry reports suggestObservers have citedDespite these challenges...

Structural Patterns to Avoid

  • Negative parallelism -- "It's not X -- it's Y" (the single biggest AI tell)
  • Dramatic countdown -- "Not X. Not Y. Just Z."
  • Self-answered rhetorics -- "The result? Devastating."
  • Anaphora abuse -- Same sentence opening 3+ times in a row
  • Tricolon abuse -- Rule-of-three used more than once per page
  • Superficial -ing analysis -- "highlighting its importance", "reflecting broader trends"
  • False ranges -- "from X to Y" where X and Y aren't on a real scale
  • Short punchy fragments -- One-word or two-word paragraphs for fake emphasis
  • Listicle in a trench coat -- "The first... The second... The third..."
  • Fractal summaries -- Summarizing what you just said, at every level
  • One-point dilution -- Restating the same argument 10 ways across thousands of words
  • Stakes inflation -- Everything is "fundamentally reshaping" civilization

Tone Traps

  • False vulnerability -- Polished, risk-free self-awareness ("And yes, I'm openly...")
  • "The truth is simple" -- Asserting clarity instead of proving it
  • Pedagogical voice -- Teacher-student dynamic with expert audiences
  • Magic adverbs -- "quietly", "deeply", "fundamentally", "remarkably"
  • Invented concept labels -- Compound labels ("supervision paradox", "acceleration trap") used as if established

Formatting Tells

  • Em-dash addiction -- 2-3 per piece is human; 20+ is AI. Watch the count.
  • Bold-first bullets -- Every list item starting with a bold keyword followed by a description
  • Unicode decoration -- Fancy arrows, smart quotes. Use straight quotes and plain dashes.
  • Horizontal rules in flowing text -- Using --- to break up prose. Use whitespace or paragraph breaks instead.
  • Short predictable sentence patterns -- Back-to-back sentences of the same length and structure are a dead giveaway.

The Test

Would a real person type this in a first draft? If not, rewrite it. Code comments and technical documentation get a pass where some patterns (like bold-first bullets in API docs) are conventional. Everything else -- emails, proposals, content, blog posts -- gets the full checklist.