AI Writing: Avoid the Slop

Hard Bans

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

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
• Copula avoidance -- Swapping "is"/"has" for "boasts", "features", "offers", "maintains" -- a documented statistical AI marker
• Historical analogy stacking -- "Apple didn't build Uber. Facebook didn't build Spotify..."
• Signposted conclusions -- Announcing "In conclusion" instead of just concluding
• Dead metaphor -- Repeating the same metaphor 5+ times in one piece

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
• Promotional puffery -- Press-release or travel-guide voice for a person, place, or org -- "renowned", "vibrant", "nestled in the heart of". State facts, skip the brochure.

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.
• Title Case headings -- Capitalizing every word in a heading. Use sentence case (Next steps, not Next Steps).

Claude-Specific Tells

Claude's own fingerprint, distinct from the generic tropes above. Watch for these in anything it generates.

• Sycophantic openers -- "You're absolutely right", "Great question", "Good catch", "Smart approach". Cut the praise, just answer.
• Reflexive hedging -- Stacking qualifiers on every claim ("it could potentially possibly"). State it, or admit uncertainty once.
• False-depth phrases -- "at its core", "the real question is", "what really matters". They promise insight and deliver filler.
• Assistant artifacts in deliverables -- "I hope this helps", "Certainly!", "Rest assured" -- fine in chat, never in emails, docs, or content.
• Stock offer closers -- "say the word", "just give the word", "don't hesitate to reach out". Use "let me know" instead.
• False-reassurance fillers -- "nothing on your end", "no action needed on your part", "nothing to worry about". Dismissive padding -- state what you're doing and stop.
• Wordy filler -- "in order to" -> to, "due to the fact that" -> because, "at this point in time" -> now.