All Tropes

El Classico, the "It's not X -- it's Y" pattern. The single most commonly identified AI writing tell. Man I f*cking hate it. The model uses this to create false profundity by framing everything as a surprise. Once can be effective; TEN in a blog post is a genuine insult to the reader.

“It's not bold. It's backwards.”

Compulsive overuse of em dashes for dramatic pauses, parenthetical asides and pivot points. A human writer might use 2-3 per piece (and naturally); AI will use a lot more.

“The problem -- and this is the part nobody talks about -- is systemic.”

Excessive use of very short sentences or sentence fragments as standalone paragraphs for MANUFACTURED EMPHASIS. RLHF training has pushed models toward "writing for readability" aimed at the lowest common denominator: one thought per sentence, no mental state-keeping required. It's an inhuman style and no real person writes first drafts this way because it doesn't match how humans think or speak.

“He published this. Openly. In a book. As a priest.”

Unpromptedly narrating what the text or the model itself is doing, deciding, planning, or about to do, instead of just doing it and producing the output. The reader gets a voiceover of the writing's own moves and the model's deliberation. Literal chain-of-thought residue that has no place in the final output, serving solely to pollute and bloat the content.

“What that changes in the design is smaller than it might appear, and what it changes is worth being precise about.”

A point (often, but not only, a question) preceded by a paragraph of its own evidence, so by the time the model spits it out it has already been made two or three times over. Increasingly common and very much linked to reasoning leaks.

“Is next-day delivery available in this region, and what's the current rollout status? One internal doc says it launched in the spring. Another says it's still being tested. A teammate mentioned it was paused in a message last month. Every other region has a clear answer, and if this one doesn't, that's a conversation with the partner rather than something we can fix ourselves.”

Opening with what the output is about to do, a preface to the point, or a restatement of the prompt, instead of delivering the point. Includes structural announcers that name the count or shape of what follows ("Two constraints shape the design"), throat-clearing frames ("The more important point is..."), and paraphrasing the question back. The sentence sets up the answer instead of being the answer. Sits in the signposting family with compulsive-counting (states the number) and enumerated-prose (the "The first... The second..." delivery); this is the announcer that precedes them.

“Two constraints shape the design.”

Everything is the most important thing ever. AI inflates the stakes of every argument to world-historical significance. A blog post about API pricing becomes a meditation on the fate of civilisation.

“This will fundamentally reshape how we think about everything.”

Ever since we bullied models for not being able to count they have been building toward this moment. Claude et al. are super excited to share their newfound ability to count by stating the exact number of items before listing them, as if getting the count right were itself the achievement.

“Five things we wish to discuss”

AI clusters invented compound labels that sound analytical without being grounded. It appends abstract problem-nouns (paradox, trap, creep, divide, vacuum, inversion) to domain words -- "supervision paradox", "acceleration trap", "workload creep" -- and uses them as if they're established, rigorously defined terms. They function as rhetorical shorthand: name a thing, skip the argument. Multiple such labels in the same piece is a strong signal of AI slop.

“the supervision paradox”

Overuse of the rule-of-three pattern, often extended to four or five. A single tricolon is elegant; three back-to-back tricolons (tri-tricolons) are a pattern recognition failure.

“Products impress people; platforms empower them. Products solve problems; platforms create worlds. Products scale linearly; platforms scale exponentially.”

Stating a minor or uncontroversial point just to defend it as if anticipating an objection nobody was going to raise.

“We are setting this out in full rather than quietly changing the recommendation, because the failure mode is the reason it matters.”

Overuse of "quietly" and similar adverbs to convey subtle importance or understated power. AI reaches for these adverbs to make mundane descriptions feel significant. Also includes: "deeply", "fundamentally", "remarkably", "arguably", and the standalone construction "unusually well [X]".

“quietly orchestrating workflows, decisions, and interactions”

Closing by restating the answer and looping it back to the original question, instead of stopping once the answer is given. The reply has already delivered the point, then bolts a summary of itself back onto the ask ("So, to answer your question, X does Y").

“So, to answer your question: yes, the employee can be added to the app.”

Attributing claims to unnamed authorities instead of being specific. AI loves to invoke "experts", "observers", "industry reports", and "several publications" without naming anyone. It also inflates the quantity of sources -- presenting what one person said as a widely held view, or writing "several publications have cited" when it means two. If you can't name the expert, you don't have a source.

“Experts argue that this approach has significant drawbacks.”

The model reuses one of its own words or phrases from earlier in the same document as if paying it off, when it's really the same narrow vocabulary surfacing again under sustained topic pressure.

“quietly become the real source of truth ... nothing you've ever believed can quietly disappear”

A standalone line made to sound quotable but carries no actual information essentially pure slide bait. The line is built to be pulled out and read alone (with zero context) as if it were wisdom. Read the examples and tell me what they actually mean. NOTHING.

“Story points are a planning tool with no fixed unit.”

A forced simile or coined metaphor reached for because it sounds clever rather than because it clarifies anything. Nobody would use this in real life. Opus 5 takes it further and takes a word from your prompt and repurpose it as a metaphor for something totally unrelated.

“Using them as a productivity measure is like tracking your weight loss with a scale that you also control the calibration on.”

The ending stacks clause after clause instead of landing one point like the model is reluctant to actually stop.

“But you can't optimize what you're mismeasuring, and a wrong metric is worse than no metric because it actively steers. If you only change one thing: stop measuring individuals by output volume, start measuring the system's ability to deliver working software, and ask your engineers what's in the way. The last one is free, and it will tell you more in an afternoon than a quarter of velocity charts.”

A short tail hung off a comma to close a sentence instead of landing the point directly. Either a clipped clause finishing the thought sideways or sometimes it's a bare noun or short phrase tacked on as an afterthought. Increasingly common.

“above the content, and save.”

Refusing to repeat the same noun twice, cycling through synonyms for one referent instead. A dashboard becomes an interface, then a portal, then the analytics hub, all in the same paragraph. Just use one word, stop flexing your vocabulary, it's pointless and you're losing the reader.

“the dashboard ... the interface ... the portal ... the analytics hub”

Asserting canonical or well-known status for a claim, without evidence, to borrow the weight of consensus: "a classic," "famously," "notoriously," "as we all know." The unnamed authority is the reader's own supposed prior knowledge instead of an outside expert.

“A classic,”

Almost all AI writing now reads like marketing copy or a travel brochure instead of factual prose, attempting to sell the subject instead of describing it.

“an all-in-one solution that unlocks unprecedented productivity for teams of any size”

Headings built on a Wh-word, now the default shape the model reaches for whenever it has to name a section, whether an article heading or a slide title. A serious tell on its own, independent of what the content under the heading actually says.

“Where the market is stuck today”

Framing the true location or source of something as a physical inhabitance, as a stand-in for a direct answer.

“where the complexity actually lives”

Claude seems to be speaking French now, who is we? Why does a document that I authored but formatted need its "I"s switched to "we"s? Very contextual, some authors genuinely use we, but it does signal a loss of personal voice, especially in personal material.

“We're now equipped to handle whatever comes next.”

Like negative parallelism but tripled up. AI builds tension by negating two or more things before revealing the actual point. Creates a false sense of narrowing down to the truth.

“Not a bug. Not a feature. A fundamental design flaw.”

False suspense transitions that promise a revelation but deliver a point that did NOT need the buildup. The model uses these phrases to manufacture drama before an otherwise completely unremarkable observation LOL.

“Here's the thing about AI adoption.”

"What I'm going to tell you; what I'm telling you; what I just told you" applied at every level of the document. Every subsection gets a summary. Every section gets a summary. The document itself gets a summary.

“In this section, we'll explore... [3000 words later] ...as we've seen in this section.”

Numbered or labeled points dressed up as continuous prose. The model writes what is essentially a listicle but wraps each point in a paragraph that starts with "The first... The second... The third..." to disguise the format. Perhaps you told it to stop generating lists and it decided to do this instead.

“The first wall is the absence of a free, scoped API... The second wall is the lack of delegated access... The third wall is the absence of scoped permissions...”

Capitalising every word in a heading instead of just the first word and proper nouns. Should've captured this before but I wasn't working on slides and presentation material as frequently to realise!

“Understanding The Impact Of Modern Technology On Society”

Overuse of ornate or grandiose nouns where simpler words would do. "Tapestry" is used to describe anything interconnected. "Landscape" is used to describe any field or domain. Other offenders: "paradigm", "synergy", "ecosystem", "framework", "load-bearing" (for important), "gated" (for restricted or conditional). Although some words cycle out of fashion for the models, new ones get introduced e.g. load-bearing, gated, paradigm.

“The rich tapestry of human experience...”

Self-posed rhetorical questions answered immediately in the next sentence or clause. The model asks a question nobody was asking, then answers it for dramatic effect. Thinks this is the epitome of great writing.

“The result? Devastating.”

Repeating the same sentence opening multiple times in quick succession.

“They assume that users will pay... They assume that developers will build... They assume that ecosystems will emerge... They assume that...”

Every bullet point or list item starts with a bolded phrase or sentence. Extremely common in Claude and ChatGPT markdown output. Almost nobody formats lists this way when writing by hand. It's a telltale sign of AI-generated documentation and blog posts and README files (especially with emojis). Eh, this one isn't so bad but it's an immediate spot when scanning a doc, most people use skills to format documents in a specific way so it is fading.

“Every single bullet point begins with a bold keyword.”

The patronizing analogy. AI constantly reaches for "Think of it as..." or "It's like a..." to simplify concepts. The model defaults to teacher mode and assumes the reader needs a metaphor to understand anything. Often produces analogies that are less clear than the original concept. I kinda miss this, now Claude speaks to you in a completely unintelligible language.

“Think of it like a highway system for data.”

Use of unicode arrows (->), smart/curly quotes, and other special characters that can't be easily typed on a standard keyboard. Real writers typing in a text editor produce straight quotes and -> or =>. Claude in particular loves the -> arrow.

“Input → Processing → Output”

ESPECIALLY COMMON IN TECHNICAL WRITING. Rapid-fire listing of historical companies or tech revolutions to build false authority.

“Apple didn't build Uber. Facebook didn't build Spotify. Stripe didn't build Shopify. AWS didn't build Airbnb.”

The classic AI invitation to futurism. To sell the argument usually begins with "Imagine" followed by a list of wonderful things that will happen if the reader agrees with the premise.

“Imagine a world where every tool you use -- your calendar, your inbox, your documents, your CRM, your code editor -- has a quiet intelligence behind it...”

Simulated self-awareness or honesty that reads as performative. The model pretends to break the fourth wall or admit a bias, creating a false sense of authenticity. Real vulnerability is specific and uncomfortable; AI vulnerability is polished and risk-free!!!!

“And yes, I'm openly in love with the platform model”

Using "from X to Y" constructions where X and Y aren't on any real scale. In legitimate use, "from X to Y" implies a spectrum with a meaningful middle. AI uses it as a jarring way to list two loosely related things.

“From innovation to implementation to cultural transformation.”

Replacing simple "is" or "are" with pompous alternatives like "serves as", "stands as", "marks", or "represents". AI avoids basic copulas because its repetition penalty pushes it toward fancier constructions (I've studied this!).

“The building serves as a reminder of the city's heritage.”

Making a single argument and restating it in 10 different ways across thousands of words. The model pads a simple thesis to feel "comprehensive" by rephrasing the same idea with different metaphors, examples, and framings. An 800-word argument becomes 4000 words of circular repetition.

“The same point, restated eight ways across 4000 words.”

Repeating entire sections or paragraphs verbatim within the same piece. This happens when the model loses track of what it has already written, especially in longer pieces. A dead giveaway of unedited AI output. Less common nowadays thanks to 1M context windows.

“The same section appeared twice, word-for-word identical.”

Used to be the most infamous AI tell. "Delve" went from an uncommon English word to appearing in a staggering percentage of AI-generated text. Part of a family of overused AI vocabulary including "certainly", "utilize", "leverage" (as a verb), "robust", "streamline", and "harness".

“Let's delve into the details...”

Filler transitions that signal nothing. AI uses these phrases to introduce new points without actually connecting them to the previous argument. Also includes: "It bears mentioning", "Importantly", "Interestingly", "Notably".

“It's worth noting that this approach has limitations.”

The pedagogical voice that assumes the reader needs hand-holding. AI defaults to a teacher-student dynamic even when writing for expert audiences. Also includes: "Let's unpack this", "Let's explore", "Let's dive in".

“Let's break this down step by step.”

Adding ("-ing") onto the end of a sentence to inject shallow analysis that says nothing. The model attaches significance, legacy, or broader meaning to mundane facts using phrases like "highlighting its importance", "reflecting broader trends", or "contributing to the development of...".

“contributing to the region's rich cultural heritage”

The rigid formula where AI acknowledges problems only to immediately dismiss them. Always follows the same flow: "Despite its [positive words], [subject] faces challenges..." then ends with "Despite these challenges, [optimistic conclusion].".

“Despite these challenges, the initiative continues to thrive.”

Explicitly announcing the conclusion with "In conclusion", "To sum up", or "In summary". Competent writing doesn't need to tell you it's concluding, it's obvious and the reader can feel it. AI signals its structural moves because it's following a template, not writing organically, it doesn't know when its actually going to end.

“In conclusion, the future of AI depends on...”