{"slug": "anti-slop-writing-first-pass", "title": "anti-slop writing first pass", "summary": "A developer has compiled a definitive deny-list of AI writing tells for OpenTrawl's landing-page copy, aiming to produce copy that reads like a sharp human wrote it. The list includes classic AI vocabulary, 2026-era tells, significance-inflation phrases, and promotional language, with a focus on density and formulaic structure as the strongest signal.", "body_md": "| # AI Writing Tells — Definitive Deny-List (as of August 2026) | |\n| Guard file for OpenTrawl landing-page copy. Every future draft is checked against this list. | |\n| The goal: copy that reads like a sharp human wrote it — plain, specific, opinionated, gov.uk-style. | |\n| If a phrase, pattern, or rhythm below appears in a draft, rewrite it. Clusters of these are the tell; | |\n| one stray word is not. The strongest single signal is **density + formulaic structure**, not any one word. | |\n| Confirmed project-specific tells (from the human owner — treat as hard bans): | |\n| - Overcompressed fragment stacking presented as punchy copy: \"Your apps, in SQLite, on your disk. Your AI searches them. No cloud, no accounts.\" | |\n| - Anthropomorphic punchline: \"The archive already knew.\" | |\n| - Mechanical phrasing: \"copies your apps into local archives\" | |\n| - Sensationalist compression in general; noise captions; \"X. Y. Z.\" rhythm | |\n| --- | |\n| ## 1. Phrase deny-list (exact words/phrases, grouped) | |\n| ### 1a. The classic \"AI vocabulary\" core (2023–2025 era; still flagged everywhere) | |\n| delve / delved / delving · tapestry (abstract: \"rich tapestry of\") · testament (\"a testament to\") · | |\n| underscore / underscoring · pivotal · landscape (abstract: \"the evolving landscape of\") · | |\n| intricate / intricacies · meticulous / meticulously · interplay · vibrant · crucial · | |\n| enduring (\"enduring legacy\") · bolster / bolstered · garner / garnered · showcase / showcasing · | |\n| foster / fostering · enhance / enhanced · additionally (sentence-initial) · furthermore · moreover · | |\n| notably · comprehensive · multifaceted · nuanced (\"nuanced understanding\") · paradigm · | |\n| transformative · leverage / leveraging · synergy · holistic · robust · streamline · | |\n| utilize / utilizing · facilitate · elucidate / illuminate · encompassing · spearhead · | |\n| invaluable · groundbreaking · cutting-edge · catalyze / catalyst · cornerstone · | |\n| reimagine / reimagining · empower / empowering · harness / harnessing · navigate (abstract) · | |\n| realm · poised · myriad · embark / embarking · grapple / grappling · commendable · noteworthy · | |\n| align with · boasts (= has) · features (= has) · offers (= has) · serves as (= is) · stands as (= is) | |\n| ### 1b. The 2026-era tells (Forbes/Jodie Cook, May 2026 — the current crop) | |\n| quietly (\"quietly building\", \"quietly dominating\", \"quietly transforming\") · shift (\"a shift in thinking\", | |\n| \"the shift towards\") · matters (\"this matters because\", \"what matters here\") · shape (\"shapes the future\", | |\n| \"shapes how we think\") · land (\"a message lands\") · actually (as filler intensifier) · | |\n| real (\"real growth\", \"real value\", \"real impact\") · earn (\"earn the right to\", \"earn trust\") · | |\n| the work (\"do the work\", \"trust the work\") · hold (\"hold space\", \"hold the line\") · | |\n| pull (\"the pull of\") · compound (\"decisions compound\") · signal (\"send the signal\") · | |\n| built different / built for the bold / built to last | |\n| ### 1c. Significance-inflation phrases (Wikipedia's #1 content tell) | |\n| marking a pivotal moment · represents a significant shift · part of a broader movement · | |\n| solidify its role as a regional hub · generated debate · shaped emerging policy discussions · | |\n| prompted broader reflection · raising philosophical questions · highlights the enduring legacy · | |\n| the transformative power of · contributes to the broader history · reflects the influence of · | |\n| setting the stage for · key turning point · evolving landscape · focal point · indelible mark · | |\n| deeply rooted · stands/serves as a testament · plays a vital/significant/crucial/pivotal/key role · | |\n| underscores/highlights its importance · reflects broader trends · symbolizing its ongoing/enduring/lasting | |\n| ### 1d. Promotional / travel-brochure language | |\n| nestled in/within · in the heart of · breathtaking · must-visit · stunning · renowned · world-class · | |\n| state-of-the-art · seamless · game-changing · unparalleled · rich cultural heritage · natural beauty · | |\n| commitment to excellence · boasts a · vibrant · profound · exemplifies · diverse array · gateway to · | |\n| captivates residents and visitors alike · acts as the gateway to | |\n| ### 1e. Hedging stacks and weasel words | |\n| could potentially · might possibly · could possibly · perhaps potentially · may potentially · | |\n| it could be argued · one could argue · it is possible that · some might say · it depends · | |\n| there's no one-size-fits-all answer · results may vary · experts argue · observers have cited · | |\n| industry reports · researchers and conservationists · several sources/publications (when one is cited) · | |\n| widely interpreted as · is described in scholarship as · maintains an active social media presence | |\n| ### 1f. Filler / throat-clearing phrases | |\n| in order to · due to the fact that · at this point in time · in the event that · has the ability to · | |\n| it is important to note that · it is worth noting that · it should be noted that · | |\n| in today's rapidly evolving [world/landscape/era] · at the end of the day · when it comes to · | |\n| the fact of the matter is · in terms of · for the purpose of · in light of the fact that · | |\n| in the realm of · at its core · first and foremost · last but not least · needless to say · | |\n| in the wake of · as we move forward · going forward | |\n| ### 1g. Chatbot conversational filler (chat artifacts, not copy) | |\n| I hope this helps! · Let me know if you'd like... · Would you like me to... · Feel free to... · | |\n| Don't hesitate to... · Happy to help! · Here is an overview/summary/breakdown · Of course! · | |\n| Certainly! · Absolutely! · I'd be happy to... · Is there anything else... · Great question! · | |\n| Excellent point! · You're absolutely right! · As an AI language model... · I'm sorry, but... | |\n| ### 1h. Generic conclusion / future-facing optimism | |\n| the future looks bright · exciting times lie ahead · continue this journey · journey toward excellence · | |\n| step in the right direction · only time will tell · the possibilities are endless · poised for growth · | |\n| watch this space · the future of [thing] · take your [thing] to the next level · don't get left behind · | |\n| the choice is yours · take control of your [thing] | |\n| ### 1i. Landing-page / dev-tool marketing slop (Sailop 40-banned list, 2026) | |\n| effortlessly · seamlessly · streamline · unlock · empower · transform · revolutionize · supercharge · | |\n| powerful · robust · cutting-edge · next-generation · innovative · comprehensive · game-changing · | |\n| world-class · state-of-the-art · blazingly fast · AI-powered · AI-native · cloud-native · | |\n| enterprise-grade · production-ready · built for the modern web · end-to-end · welcome to our platform · | |\n| the future of [thing] · built for [vague audience] · the all-in-one [thing] · trusted by leading companies · | |\n| used by thousands of developers · the #1 [thing] for [audience] · get started · sign up free · | |\n| learn more · join us | |\n| ### 1j. Announcement / setup phrases that promise more than they deliver | |\n| Here's the kicker. · The best part? · But here's the thing. · Honestly? · I'm going to state this as clearly as possible · | |\n| Here's the part most people miss · Here's the breakdown · Let's dive in · Let's break this down · | |\n| Without further ado · As mentioned above · As we've seen · In conclusion · To sum up · To summarize · | |\n| In summary · Overall | |\n| ### 1k. Therapist-mode / unsolicited validation (2026 tell) | |\n| You're not imagining it · You're not alone · You're not broken · Do you want to sit with that for a while? · | |\n| Are you ready to go deeper? · It's okay to feel this way | |\n| ### 1l. LLM-safe truths (true statements that teach nothing) | |\n| Consistency is important. · Building relationships takes time. · Success requires hard work. · | |\n| Communication is key. · The journey matters more than the destination. | |\n| ### 1m. Knowledge-cutoff / source-gap disclaimers | |\n| as of my last knowledge update · up to my last training update · while specific details are limited/scarce in the available sources · | |\n| not widely documented/disclosed · based on available information · the subject likely... · | |\n| maintains a low profile · keeps personal details private | |\n| --- | |\n| ## 2. Sentence-pattern deny-list (the structures) | |\n| ### 2a. Negative parallelism / contrast reframe — THE #1 tell (Atlantic, Jul 2026; Forbes, May 2026) | |\n| The most famous AI writing tic. Survives every prompt fix. Pangram estimates \"Not just X but Y\" | |\n| appears ~3x more often in AI text than human text. Barron's found it quadrupled in corporate | |\n| communications 2023–2025. Variants: | |\n| - \"It's not X; it's Y.\" / \"It's not about X, it's about Y.\" | |\n| - \"This isn't a tactics problem, it's a positioning problem.\" | |\n| - \"Not just X, but also Y.\" / \"not only X but Y\" | |\n| - \"No A, no B, just C.\" (\"No bag, no things, no armor, just me.\") | |\n| - \"X rather than Y.\" / \"not X, but Y\" | |\n| - \"The target was never a man. The target was the truth.\" | |\n| - \"It's far more than X. Focus on Y.\" | |\n| Examples: | |\n| - \"It's not just a win for the private bank—it's a win for the entire enterprise.\" | |\n| - \"This isn't about speed; it's about trust.\" | |\n| - \"No cloud, no accounts, no setup. Just your data, on your disk.\" ← project-adjacent, banned | |\n| Human alternative: delete the dismissed half. Say only the thing you mean. | |\n| - AI: \"This isn't a storage tool; it's a memory.\" | |\n| - Human: \"It stores your data locally. That's the whole pitch.\" | |\n| ### 2b. Tricolon / rule of three everywhere | |\n| \"adjective, adjective, adjective\" and \"phrase, phrase, and phrase\" used to make thin analysis | |\n| look complete. AI uses triads constantly; humans use them once, deliberately. | |\n| Examples: | |\n| - \"Faster, smarter, better.\" / \"Seamless, secure, scalable.\" | |\n| - \"Your data. Your rules. Your archive.\" | |\n| - \"Built for speed, built for scale, built for you.\" | |\n| Human alternative: use one precise item, or two, or recast. Vary list lengths. | |\n| - AI: \"Private, portable, powerful.\" | |\n| - Human: \"Private by design. Portable by default.\" | |\n| ### 2c. Staccato fragment stacking (\"X. Y. Z.\" rhythm) — CONFIRMED PROJECT TELL | |\n| Short fragments stacked as fake punch. The human owner flagged: \"Your apps, in SQLite, on your disk. | |\n| Your AI searches them. No cloud, no accounts.\" This is the AI \"punchy\" default: every sentence a | |\n| sentence fragment, all same length, all same rhythm, zero connective tissue. | |\n| Examples: | |\n| - \"Your apps, in SQLite, on your disk. Your AI searches them. No cloud, no accounts.\" | |\n| - \"No setup. No sync. No servers. Just works.\" | |\n| - \"Private. Local. Yours.\" | |\n| Human alternative: vary the rhythm. Let one sentence run. Use a fragment only where it lands hardest. | |\n| - AI: \"Local. Private. Yours.\" | |\n| - Human: \"Everything stays on your disk. There is no cloud account to lose, and nothing to sync.\" | |\n| ### 2d. Colon-heavy headline pattern (\"X: why Y matters\") | |\n| Every headline/heading as \"Noun phrase: claim about it.\" AI defaults to this for all headers. | |\n| Examples: | |\n| - \"SQLite: why local storage matters\" | |\n| - \"Privacy: the case for keeping data on-device\" | |\n| - \"OpenTrawl: the archive that knows\" | |\n| Human alternative: vary heading shapes. Some are questions, some are plain statements, some are | |\n| fragments, some are full sentences. Never all colons. | |\n| - AI: \"Archives: why they matter\" | |\n| - Human: \"What an archive is for\" / \"Archives, and why you'd want one\" | |\n| ### 2e. Anthropomorphic punchline — CONFIRMED PROJECT TELL | |\n| Giving the product/archive/software a knowing, human-like consciousness as a closer. | |\n| \"The archive already knew.\" The software \"remembers\", \"understands\", \"knows\", \"sees\". | |\n| Examples: | |\n| - \"The archive already knew.\" | |\n| - \"Your data remembers what you forgot.\" | |\n| - \"The search engine understands what you meant.\" | |\n| Human alternative: state what the software actually does, plainly. | |\n| - AI: \"The archive already knew.\" | |\n| - Human: \"Search runs against your local copy, so it finds what you actually saved.\" | |\n| ### 2f. Superficial trailing \"-ing\" analysis | |\n| A present-participle clause bolted to the end of a sentence to editorialize. | |\n| Examples: | |\n| - \"...creating a lively community within its borders.\" | |\n| - \"...further enhancing its significance as a dynamic hub of activity and culture.\" | |\n| - \"...reflecting its continued relevance in the regional and national transportation landscape.\" | |\n| - \"...symbolizing the region's commitment to innovation.\" | |\n| - \"...cementing its status as...\" / \"...ensuring...\" / \"...fostering...\" | |\n| Human alternative: delete the trailing clause. The sentence stands without it. If the point is real, | |\n| make it its own plain sentence with attribution. | |\n| ### 2g. \"Despite X, Y faces challenges... but the future is bright\" formula | |\n| The rigid \"Challenges / Future Prospects\" outline closer. | |\n| Examples: | |\n| - \"Despite its success, the Panama Canal faces challenges, including... Future investments could enhance the canal's efficiency.\" | |\n| - \"Despite their promising applications, pyroelectric materials face several challenges... positioning them as critical components for sustainable energy solutions.\" | |\n| Human alternative: keep any concrete, sourced challenge as plain prose where it belongs. Delete speculation about the future. | |\n| ### 2h. Canned notability / media-coverage hammering | |\n| \"featured in Vogue, Wired, and other media\" · \"profiled in multiple high-quality, independent, and widely-read outlets\" · | |\n| \"these sources provide significant, substantial, secondary coverage\" · \"maintains an active social media presence\" | |\n| Human alternative: state facts, not notability arguments. | |\n| ### 2i. Rhetorical question immediately answered | |\n| \"Have you ever wondered...?\" → answer. \"What is X?\" → definition. \"Imagine a world where...\" → pitch. | |\n| Human alternative: start with the substance. | |\n| ### 2j. The sandwich conclusion (restate intro + generic optimism + CTA) | |\n| \"As we've seen... In conclusion... The future is bright... So next time you [topic], remember...\" | |\n| Human alternative: end on a strong, specific thought. Give the reader something new, not a summary. | |\n| --- | |\n| ## 3. Rhythm / structure tells | |\n| ### 3a. Metronomic sentence length | |\n| Every sentence 15–25 words, same beat. Read aloud: da-DUM da-DUM da-DUM. Humans mix aggressively: | |\n| one word, then a long winding sentence, then a fragment. | |\n| Fix: vary sentence length dramatically; start sentences with And/But/So; use fragments on purpose. | |\n| ### 3b. Uniform paragraph length | |\n| Every paragraph 3–5 sentences, every section roughly the same length. AI gives every point equal | |\n| weight. Humans go deep on what matters and skip the rest. | |\n| Fix: one paragraph may be a single sentence; the next may be eight. Sections of 50 words and 300 words. | |\n| ### 3c. Perfectly parallel bullet lists | |\n| Every bullet the same grammatical shape, same length, same structure. AI's signature. | |\n| Fix: asymmetric lists — some items one word, some a sentence. If you wouldn't bullet it to a friend, don't bullet it here. | |\n| ### 3d. Inline-header vertical lists (\"**Thing:** description\") | |\n| `- **Conflict of Interest:** ...` `1. **Historical Context:** ...` — the AI list format. | |\n| Fix: prose where the list isn't needed; clean lists without bolded inline headers otherwise. | |\n| ### 3e. Em-dash density | |\n| AI (especially Claude-family) uses em dashes far more than non-professional human writing, in places | |\n| humans would use commas, parentheses, colons, or full stops. A July 2026 study: of contemporary | |\n| models, only Claude used em dashes more than professional writers. OpenAI famously struggled for | |\n| years to train the em dash out of ChatGPT. | |\n| Fix: replace most with commas/parentheses/colons/full stops. Keep a few — zeroing them out is its own tell. | |\n| ### 3f. Boldface overuse | |\n| Bolding every instance of a chosen term; \"key takeaways\" bolding scattered through paragraphs. | |\n| Fix: bold sparingly, for actual emphasis only. | |\n| ### 3g. Title-case headings everywhere | |\n| \"Impact Of Technology And Digitalization\" style. Fix: sentence case. | |\n| ### 3h. Excessive internal coherence | |\n| \"Excessive internal coherence reveals the machine behind the words\" (Forbes, Feb 2026). AI references | |\n| its own earlier points too neatly, loops back to the intro's framing, weaves threads too perfectly. | |\n| Humans leave threads hanging, forget what they said, contradict themselves slightly. | |\n| Fix: leave some loose ends. | |\n| ### 3i. Too clean to be human | |\n| Every detail serves the argument; every example fits perfectly; no accidental details, throwaway | |\n| numbers, or oddly specific but unimportant facts. Fix: add some irrelevant specifics. Real life has loose ends. | |\n| ### 3j. Missing emotional spikes | |\n| AI maintains a neutral emotional temperature even when the topic demands a stance. Fix: get annoyed, | |\n| get excited, take a position that might alienate someone. | |\n| ### 3k. Faux balance without consequence | |\n| Gestures at \"both sides\" then proceeds exactly as planned; nothing is weighed, nothing is traded off. | |\n| Fix: if you acknowledge a counterargument, actually engage it or cut it. | |\n| ### 3l. Arguments that teleport | |\n| Mid-paragraph the logic jumps; one sentence makes a point, the next states a conclusion without | |\n| showing how it was reached. Fix: read each paragraph asking \"does this sentence follow from the last?\" | |\n| ### 3m. Near-miss metaphors | |\n| Comparisons that sound clever but don't map (\"tuning a guitar\" for a business strategy). Fix: if a | |\n| metaphor misses even slightly, remove it entirely. | |\n| ### 3n. Correct words in wrong contexts | |\n| Formal verbs in casual contexts; slightly clinical word choices in warm messages; grammatically | |\n| perfect but textbook-learned. Fix: use the word you'd actually say. | |\n| ### 3o. Curly quotes/apostrophes (ChatGPT/DeepSeek habit) | |\n| Curly \" \" ' ' where the document otherwise uses straight marks, or inconsistent mixing. | |\n| Fix: normalize to straight marks for plain text. (Gemini and Claude typically don't do this.) | |\n| ### 3p. Emoji as formatting (older models; still seen in comments/microcopy) | |\n| 🧠 🚨 🔭 in front of headings/bullets; \"👉 Drop me a message\". Fix: none in product copy. | |\n| ### 3q. Thematic breaks before headings (----) and skipped heading levels | |\n| Markdown habits. Fix: proper heading levels, no rules before headings. | |\n| --- | |\n| ## 4. Model-specific sections | |\n| ### 4a. GPT-series tells (GPT-4 / 4o / 5 era) | |\n| - **Structural predictability**: numbered lists, consistent headings, step-by-step organization; every | |\n| list item grammatically identical. | |\n| - **Formulaic openers**: restating the question (\"Certainly! Here is a comprehensive guide to...\"), | |\n| \"Let's explore\" as a section opener. | |\n| - **Formulaic conclusions**: restate main points, note the topic is nuanced, encourage further research. | |\n| - **Era vocabulary** (Wikipedia's breakdown): | |\n| - GPT-4 (2023–mid-2024): additionally, boasts, bolstered, crucial, delve, emphasizing, enduring, | |\n| garner, intricate/intricacies, interplay, key, landscape, meticulous/meticulously, pivotal, | |\n| underscore, tapestry, testament, valuable, vibrant | |\n| - GPT-4o (mid-2024–mid-2025): align with, bolstered, crucial, emphasizing, enhance, enduring, | |\n| fostering, highlighting, pivotal, showcasing, underscore, vibrant | |\n| - GPT-5 (mid-2025+): emphasizing, enhance, highlighting, showcasing (+ canned notability claims) | |\n| - **Curly quotes/apostrophes** (ChatGPT habit). | |\n| - **The em-dash struggle**: OpenAI spent years trying to train the em dash out; GPT output historically | |\n| em-dash-heavy, now less than Claude but still formulaic in placement. | |\n| - **Sycophancy**: top models affirm users' ideas ~49% more than humans (Stanford/CMU, Mar 2026); | |\n| \"Great question!\", \"You're absolutely right!\", \"I'd be happy to...\". | |\n| - **Chat artifacts**: `:contentReference[oaicite:0]{index=0}`, `oai_citation`, `turn0search0`, `+1` after sentences. | |\n| ### 4b. Claude-series tells (Claude 3/4 era; Fable inherits these) | |\n| - **Over-qualification and meta-commentary**: \"It's worth noting that\", \"This is a nuanced area\", | |\n| \"The answer depends on context\" — useful qualifications that become obvious patterns every few paragraphs. | |\n| - **Hedging before claiming**: Claude hedges before making the claim at all; human writers make claims | |\n| and defend them. | |\n| - **Em-dash overuse**: the July 2026 study found Claude the only contemporary model using em dashes | |\n| more than professional writers. \"This matters — and here's why.\" | |\n| - **Longer, more syntactically complex sentences** than average human writing. | |\n| - **Earnest, measured tone**: acknowledges limitations and counterarguments even when unnecessary; | |\n| reads intellectually cautious rather than authoritative. | |\n| - **\"I appreciate\"** openers and polite framing in conversational output. | |\n| - **Curly quotes**: Gemini and Claude typically do NOT use curly quotes (so straight quotes are not a | |\n| Claude tell). | |\n| ### 4c. Fable-series tells (Anthropic's Fable 5, June 2026 — public info is THIN) | |\n| What we found: | |\n| - **Fable 5 is Anthropic's flagship** (released June 9, 2026; \"Claude Fable 5\" and \"Claude Mythos 5\"; | |\n| API name `claude-fable-5`). It is the successor to Claude Opus, positioned for long-horizon reasoning | |\n| and high-fidelity creative writing. | |\n| - **No public \"Fable-isms\" catalog exists yet** as of August 2026 — the model is ~2 months old and the | |\n| discourse is about its capabilities (large context window, \"adaptive thinking\", \"voice locking\"), | |\n| not its tells. | |\n| - **Fable inherits Claude-family tendencies** (same lineage): hedging, meta-commentary (\"worth noting\"), | |\n| em-dash overuse, over-qualification. Treat the Claude list as the Fable baseline. | |\n| - **\"Voice locking\"** means Fable can be steered to mimic a given style from samples — so its tells are | |\n| less consistent than older models when prompted with style examples. Cold output still defaults to | |\n| Claude-family patterns. | |\n| - **Watch for**: the same negative-parallelism and tricolon structures as every other model (Pangram | |\n| confirms all major chatbots rely on them), plus Anthropic's characteristic earnestness. | |\n| - Recommendation: keep the Claude list as the Fable deny-list until public Fable-specific tells emerge; | |\n| re-check quarterly. | |\n| --- | |\n| ## 5. What a human writes instead (per major pattern) | |\n| | AI pattern | Human alternative (plain, specific, gov.uk-style) | | |\n| |---|---| | |\n| | Negative parallelism: \"It's not just a tool, it's a memory.\" | \"It stores your data locally. That's the whole pitch.\" | | |\n| | Tricolon: \"Faster, smarter, better.\" | \"It's fast. The rest you can judge for yourself.\" | | |\n| | Staccato stacking: \"Local. Private. Yours.\" | \"Everything stays on your disk. There is no cloud account to lose, and nothing to sync.\" | | |\n| | Colon headline: \"SQLite: why local storage matters\" | \"What an archive is for\" | | |\n| | Anthropomorphic punchline: \"The archive already knew.\" | \"Search runs against your local copy, so it finds what you actually saved.\" | | |\n| | Significance inflation: \"marking a pivotal moment in the evolution of regional statistics\" | \"The institute was established in 1989 to collect and publish regional statistics.\" | | |\n| | Trailing -ing analysis: \"...reflecting its continued relevance in the transportation landscape.\" | Delete the clause. The sentence stands without it. | | |\n| | \"Seamlessly unlock the power of AI to effortlessly transform your workflow.\" | \"Catch the 40 phrases that mark your copy as AI-written, with a one-line replacement for each.\" | | |\n| | \"Effortlessly streamline your workflow\" | \"No more reading 200-line PR diffs.\" | | |\n| | \"Seamlessly integrates with your CI\" | \"Plugs into your CI as a single GitHub Action.\" | | |\n| | \"Unlock 50 design templates\" | \"Get 50 design templates.\" | | |\n| | \"Empowers your team to ship\" | \"Ship a landing page without a designer.\" | | |\n| | \"Trusted by leading companies\" | \"Used at Stripe to gate the design-system PR.\" | | |\n| | \"Get started\" | \"Install via npm.\" / \"Scan my codebase.\" | | |\n| | \"The future looks bright\" | Cut it. End on a specific thought. | | |\n| | \"Great question!\" | Start with the substance. | | |\n| | \"In today's fast-paced world\" | Cut it. Start with the fact. | | |\n| | \"It's worth noting that...\" | Cut it. Note the thing. | | |\n| | \"Consistency is important.\" | \"Consistency is important\" → cut, or sharpen: \"Ship every Friday, or don't ship at all.\" | | |\n| | \"Here's the kicker.\" | Delete the fanfare; let the substance speak. | | |\n| | \"Do the work.\" | \"Write the copy. Then cut half of it.\" | | |\n| The universal rule (Sailop): replace every adjective with a number, every adverb with a comparison, | |\n| every vague verb with a concrete one. The rewrite is usually shorter and always clearer. Write copy | |\n| you would defend in a pitch meeting — AI copy is what survives committee review because nobody | |\n| disagrees with it. | |\n| --- | |\n| ## 6. Sources | |\n| Primary field guides: | |\n| 1. Wikipedia: \"Signs of AI writing\" (WikiProject AI Cleanup field guide; era vocab, negative parallelisms, | |\n| rule of three, em-dash, boldface, inline-header lists, promotional language, challenges-formula). | |\n| https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing | |\n| 2. The Atlantic, Will Oremus: \"The Most Famous AI Writing Tic Is Also the Most Mysterious\" (Jul 2026) — | |\n| negative parallelism as the #1 tell; Pangram 3x statistic; Barron's 4x statistic. | |\n| https://www.theatlantic.com/technology/2026/07/ai-chatbot-writing-tic-negative-parallelism/687892/ | |\n| 3. The Atlantic, Eve Fairbanks: \"The Biggest Tell That Something Was Written by AI\" (May 2026) — | |\n| canned perfection, uneditable AI prose, sycophancy (Stanford/CMU 49% study), Max Planck word-leak study. | |\n| https://www.theatlantic.com/technology/2026/05/how-to-tell-ai-writing/687345/ | |\n| 4. Forbes, Jodie Cook: \"15 New Giveaway Signs Of AI Writing (May 2026 Update)\" — the 2026 word crop | |\n| (quietly, shift, matters, shape, land, actually, real, earn, the work, hold, pull, compound, signal, | |\n| built different) + contrast reframes as the surviving #1. | |\n| https://www.forbes.com/sites/jodiecook/2026/05/21/15-new-giveaway-signs-of-ai-writing-may-2026-update/ | |\n| 5. Forbes, Jodie Cook: \"The 15 New Giveaway Signs Of AI-Generated Content (In February 2026)\" — | |\n| announcing-the-good-part, LLM-safe truths, \"Honestly?\", quiet, therapist mode, marching sentences, | |\n| near-miss metaphors, teleporting arguments, missing emotional spikes, faux balance, too-tidy internal | |\n| references, too-clean-to-be-human. | |\n| https://www.forbes.com/sites/jodiecook/2026/02/03/the-15-new-giveaway-signs-of-ai-generated-content-in-february-2026/ | |\n| 6. Sailop: \"40 Banned Phrases That Mark Your Copy as AI-Generated (with Replacements)\" (Apr 2026) — | |\n| landing-page-specific deny-list with replacements and the \"tells travel in packs\" rule. | |\n| https://www.sailop.com/blog/banned-phrases-40-words-mark-copy-ai-generated | |\n| 7. Ars Technica, Benj Edwards: \"Wikipedia volunteers spent years cataloging AI tells. Now there's a | |\n| plugin to avoid them.\" (Jan 2026) — the Humanizer plugin; before/after example. | |\n| https://arstechnica.com/ai/2026/01/new-ai-plugin-uses-wikipedias-ai-writing-detection-rules-to-help-it-sound-human/ | |\n| 8. texttoolsai.app: \"How ChatGPT and Claude Writing Differs — and How to Humanize Each\" (May 2026) — | |\n| GPT vs Claude tells. | |\n| https://www.texttoolsai.app/blog/chatgpt-vs-claude-writing-quality | |\n| 9. The Atlantic: \"Chatbots Are Spewing Out All the Worst Clichés\" (Feb 2023) — cliché obsession. | |\n| https://www.theatlantic.com/technology/archive/2023/02/ai-chatbots-cliche-writing/673143/ | |\n| 10. MIT Technology Review: \"Why detecting AI-generated text is so difficult\" (Feb 2023). | |\n| https://www.technologyreview.com/2023/02/07/1067928/why-detecting-ai-generated-text-is-so-difficult-and-what-to-do-about-it/ | |\n| 11. The Guardian: \"Spam, junk ... slop?\" (May 2024) — the slop term. | |\n| https://www.theguardian.com/technology/article/2024/may/19/spam-junk-slop-the-latest-wave-of-ai-behind-the-zombie-internet | |\n| 12. NYMag/Intelligencer, Max Read: \"Drowning in Slop\" (Sep 2024). | |\n| https://nymag.com/intelligencer/article/ai-generated-content-internet-online-slop-spam.html | |\n| 13. Wikipedia: \"AI slop\". | |\n| https://en.wikipedia.org/wiki/AI_slop | |\n| 14. Humanizer skill files (open-source, distilled from the Wikipedia guide): | |\n| brandonwise/humanizer (29 patterns, weighted), WhimseyAI/humanizer-skill, Intern4711/Better_Humanizer. | |\n| 15. Anthropic: \"Claude Fable\" product page + platform docs (Fable 5 / Mythos 5, Jun 2026); Bilzit and | |\n| NovelMage Fable-5 reviews (voice locking, adaptive thinking) — Fable context. | |\n| https://www.anthropic.com/claude/fable | |\n| Note on method: parallel.ai search was rate-limited for this session; sources were gathered via direct | |\n| fetch, Google News RSS, Wayback CDX, and DuckDuckGo-through-reader. Fable-specific tells are thin | |\n| publicly as of Aug 2026 — the Claude list is the best available proxy, per section 4c. |", "url": "https://wpnews.pro/news/anti-slop-writing-first-pass", "canonical_source": "https://gist.github.com/joshp123/3c60d8def6d30a2503d8a98575334702", "published_at": "2026-08-09 10:51:06+00:00", "updated_at": "2026-08-09 11:37:23.309189+00:00", "lang": "en", "topics": ["artificial-intelligence", "developer-tools"], "entities": ["OpenTrawl", "Jodie Cook", "Forbes"], "alternates": {"html": "https://wpnews.pro/news/anti-slop-writing-first-pass", "markdown": "https://wpnews.pro/news/anti-slop-writing-first-pass.md", "text": "https://wpnews.pro/news/anti-slop-writing-first-pass.txt", "jsonld": "https://wpnews.pro/news/anti-slop-writing-first-pass.jsonld"}}