{"slug": "ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is", "title": "AI Writing Tropes to Avoid — tropes.fyi by ossama.is", "summary": "This article, \"AI Writing Tropes to Avoid\" by ossama.is, provides a list of common AI writing patterns to exclude from system prompts, including the overuse of adverbs like \"quietly\" and \"deeply,\" the word \"delve,\" and grandiose nouns such as \"tapestry\" and \"landscape.\" It also warns against specific structural tics like the \"It's not X -- it's Y\" reframe, dramatic countdowns, and self-posed rhetorical questions, which are frequently used by AI to create false profundity.", "body_md": "# AI Writing Tropes to Avoid\n\nAdd this file to your AI assistant's system prompt or context to help it avoid\ncommon AI writing patterns. Source: [tropes.fyi](https://tropes.fyi) by [ossama.is](https://ossama.is)\n\n---\n\n## Word Choice\n\n### \"Quietly\" and Other Magic Adverbs\n\nOveruse 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\".\n\n**Avoid patterns like:**\n- \"quietly orchestrating workflows, decisions, and interactions\"\n- \"the one that quietly suffocates everything else\"\n- \"a quiet intelligence behind it\"\n\n### \"Delve\" and Friends\n\nUsed 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\".\n\n**Avoid patterns like:**\n- \"Let's delve into the details...\"\n- \"Delving deeper into this topic...\"\n- \"We certainly need to leverage these robust frameworks...\"\n\n### \"Tapestry\" and \"Landscape\"\n\nOveruse 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\".\n\n**Avoid patterns like:**\n- \"The rich tapestry of human experience...\"\n- \"Navigating the complex landscape of modern AI...\"\n- \"The ever-evolving landscape of technology...\"\n\n### The \"Serves As\" Dodge\n\nReplacing 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!).\n\n**Avoid patterns like:**\n- \"The building serves as a reminder of the city's heritage.\"\n- \"Gallery 825 serves as LAAA's exhibition space for contemporary art.\"\n- \"The station marks a pivotal moment in the evolution of regional transit.\"\n\n---\n\n## Sentence Structure\n\n### Negative Parallelism\n\nThe \"It's not X -- it's Y\" pattern, often with an em dash. The single most commonly identified AI writing tell. Man I f*cking hate it. AI uses this to create false profundity by framing everything as a surprising reframe. One in a piece can be effective; ten in a blog post is a genuine insult to the reader. Before LLMs, people simply did not write like this at scale. Includes the causal variant \"not because X, but because Y\" where every explanation is framed as a surprise reveal, the em-dash dismissal \"X -- not Y\", and the cross-sentence reframe where the same noun is negated then repositioned: \"The question isn't X. The question is Y.\"\n\n**Avoid patterns like:**\n- \"It's not bold. It's backwards.\"\n- \"Feeding isn't nutrition. It's dialysis.\"\n- \"Half the bugs you chase aren't in your code. They're in your head.\"\n\n### \"Not X. Not Y. Just Z.\"\n\nThe dramatic countdown pattern. AI builds tension by negating two or more things before revealing the actual point. Creates a false sense of narrowing down to the truth.\n\n**Avoid patterns like:**\n- \"Not a bug. Not a feature. A fundamental design flaw.\"\n- \"Not ten. Not fifty. Five hundred and twenty-three lint violations across 67 files.\"\n- \"not recklessly, not completely, but enough\"\n\n### \"The X? A Y.\"\n\nSelf-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.\n\n**Avoid patterns like:**\n- \"The result? Devastating.\"\n- \"The worst part? Nobody saw it coming.\"\n- \"The scary part? This attack vector is perfect for developers.\"\n\n### Anaphora Abuse\n\nRepeating the same sentence opening multiple times in quick succession.\n\n**Avoid patterns like:**\n- \"They assume that users will pay... They assume that developers will build... They assume that ecosystems will emerge... They assume that...\"\n- \"They could expose... They could offer... They could provide... They could create... They could let... They could unlock...\"\n- \"They have built engines, but not vehicles. They have built power, but not leverage. They have built walls, but not doors.\"\n\n### Tricolon Abuse\n\nOveruse of the rule-of-three pattern, often extended to four or five. A single tricolon is elegant; three back-to-back tricolons are a pattern recognition failure.\n\n**Avoid patterns like:**\n- \"Products impress people; platforms empower them. Products solve problems; platforms create worlds. Products scale linearly; platforms scale exponentially.\"\n- \"identity, payments, compute, distribution\"\n- \"workflows, decisions, and interactions\"\n\n### \"It's Worth Noting\"\n\nFiller 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\".\n\n**Avoid patterns like:**\n- \"It's worth noting that this approach has limitations.\"\n- \"Importantly, we must consider the broader implications.\"\n- \"Interestingly, this pattern repeats across industries.\"\n\n### Superficial Analyses\n\nTacking a present participle (\"-ing\") phrase 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...\".\n\n**Avoid patterns like:**\n- \"contributing to the region's rich cultural heritage\"\n- \"This etymology highlights the enduring legacy of the community's resistance and the transformative power of unity in shaping its identity.\"\n- \"underscoring its role as a dynamic hub of activity and culture\"\n\n### False Ranges\n\nUsing \"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 fancy way to list two loosely related things. \"From innovation to cultural transformation\" -- what's in between???? Nothing!\n\n**Avoid patterns like:**\n- \"From innovation to implementation to cultural transformation.\"\n- \"From the singularity of the Big Bang to the grand cosmic web.\"\n- \"From problem-solving and tool-making to scientific discovery, artistic expression, and technological innovation.\"\n\n---\n\n## Paragraph Structure\n\n### Short Punchy Fragments\n\nExcessive 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. No real person writes first drafts this way because it doesn't match how humans think or speak.\n\n**Avoid patterns like:**\n- \"He published this. Openly. In a book. As a priest.\"\n- \"These weren't just products. And the software side matched. Then it professionalised. But I adapted.\"\n- \"Platforms do.\"\n\n### Listicle in a Trench Coat\n\nNumbered 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... still very common.\n\n**Avoid patterns like:**\n- \"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...\"\n- \"The second takeaway is that... The third takeaway is that... The fourth takeaway is that...\"\n\n---\n\n## Tone\n\n### \"Here's the Kicker\"\n\nFalse 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 unremarkable observation LOL. Also includes: \"Here's the thing\", \"Here's where it gets interesting\", \"Here's what most people miss\", \"Here's the starting point\", \"Here's the deal\".\n\n**Avoid patterns like:**\n- \"Here's the kicker.\"\n- \"Here's the thing about AI adoption.\"\n- \"Here's where it gets interesting.\"\n\n### \"Think of It As...\"\n\nThe 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.\n\n**Avoid patterns like:**\n- \"Think of it like a highway system for data.\"\n- \"Think of it as a Swiss Army knife for your workflow.\"\n- \"It's like asking someone to buy a car they're only allowed to sit in while it's parked.\"\n\n### \"Imagine a World Where...\"\n\nThe 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.\n\n**Avoid patterns like:**\n- \"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...\"\n- \"In that world, workflows stop being collections of manual steps and start becoming orchestrations.\"\n\n### False Vulnerability\n\nSimulated 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!!!!\n\n**Avoid patterns like:**\n- \"And yes, I'm openly in love with the platform model\"\n- \"And yes, since we're being honest: I'm looking at you, OpenAI, Google, Anthropic, Meta\"\n- \"This is not a rant; it's a diagnosis\"\n\n### \"The Truth Is Simple\"\n\nAsserting that something is obvious, clear or simple instead of actually proving it. If you have to tell the reader your point is clear, it very likely isn't. Also includes the dramatic reveal variant: \"but none of them is the real story. The real story is...\" -- claiming privileged insight while waving away everything before it.\n\n**Avoid patterns like:**\n- \"The reality is simpler and less flattering\"\n- \"History is unambiguous on this point\"\n- \"History is clear, the metrics are clear, the examples are clear\"\n\n### Grandiose Stakes Inflation\n\nEverything 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 civilization.\n\n**Avoid patterns like:**\n- \"This will fundamentally reshape how we think about everything.\"\n- \"will define the next era of computing\"\n- \"something entirely new\"\n\n### \"Let's Break This Down\"\n\nThe 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\".\n\n**Avoid patterns like:**\n- \"Let's break this down step by step.\"\n- \"Let's unpack what this really means.\"\n- \"Let's explore this idea further.\"\n\n### Vague Attributions\n\nAttributing 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.\n\n**Avoid patterns like:**\n- \"Experts argue that this approach has significant drawbacks.\"\n- \"Industry reports suggest that adoption is accelerating.\"\n- \"Observers have cited the initiative as a turning point.\"\n\n### Invented Concept Labels\n\nAI 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 p", "url": "https://wpnews.pro/news/ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is", "canonical_source": "https://gist.github.com/ossa-ma/f3baa9d25154c33095e22272c631f5a1", "published_at": "2026-03-09 19:06:33+00:00", "updated_at": "2026-05-22 04:35:34.328783+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "developer-tools"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is", "markdown": "https://wpnews.pro/news/ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is.md", "text": "https://wpnews.pro/news/ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is.txt", "jsonld": "https://wpnews.pro/news/ai-writing-tropes-to-avoid-tropes-fyi-by-ossama-is.jsonld"}}