Articles
Original guides I wrote for the patterns REhume detects. Significance inflation, filler openers, chatbot leftovers, detector myths. I also wrote how I edit those drafts by hand when I am not running the tool. These are not scraped encyclopedia pages. They are the notes I wanted next to the paste box. The numbered list of all 33 rules is on the pattern encyclopedia.
If you only read two, start with How REhume works and When not to run a humanizer. The rest are one-topic deep dives. I am tboy1337; questions go to the contact page.
- Boldface that does no workChat models bold every noun so the answer looks structured. I unbold everything, then put back at most one anchor per section.
- Challenges and future prospects sections I did not ask forOutline furniture at the end of a draft: Challenges, Future Prospects, In Conclusion. I only keep a closing section when I have a dated risk or a next step.
- Honestly, look, here's the thingConversational openers are chat cadence pasted into documents. I start with the subject of the sentence, not a throat-clear.
- Emoji bullets that never belonged in the specRocket-ship headings and checkmark lists are chat UI, not documentation. How I strip emoji without losing the actual steps.
- Inline-header lists that restate the headingBold label, colon, then the same idea in weaker words. I convert those vertical lists to sentences unless the labels are real field names.
- Name-dropping and fake notabilityCited in the New York Times, BBC, Financial Times, and The Hindu is not a biography. I keep one source with context and delete the fame stack.
- Stacked hedges until the sentence diesCould potentially possibly be argued is not caution. It is the model refusing to have a view. I keep one hedge, not three.
- Sycophantic tone leftover from chatGreat question! You're absolutely right that assistant flattery does not belong in a finished document. Here is how I cut it.
- Title case headings from chatbotsStrategic Negotiations And Global Partnerships is a slide title. Sentence case is how I write documents that have to live in git.
- When Not to Run a HumanizerCases where cleaning AI tells is the wrong move: school rules, other people's words, and drafts that should stay obviously machine-made.
- A Manual Pass Over AI DraftsA step-by-step edit I use when I am not running REhume: kill the frame, restore facts, then fix cadence last.
- Signposting and AnnouncementsPhrases that announce structure instead of delivering it, 'In this section we will explore' and other AI habits.
- Knowledge Cutoff DisclaimersThe awkward date-boundary apologies in AI answers, and why they should never reach your final draft.
- Hyphen Pairs and AI WritingThe rise of compound modifiers like 'AI-powered' and 'data-driven' in machine prose, and when to simplify.
- Voice Calibration for RewritesHow to keep humanized text sounding like you, not like a default polite assistant.
- False Positives in AI DetectionWhen human writing gets labeled AI, who gets hurt, why it happens, and how to defend your work.
- How REhume WorksA plain-language walkthrough of what REhume does to your text, and what it deliberately does not do.
- Generic Conclusions to CutSummary paragraphs that add nothing, how AI ends pieces and what to write instead.
- Copula Avoidance: Is and AreWhy AI models dodge simple 'is' statements in favor of awkward constructions, and how plain verbs help.
- Staccato Drama in AI ProseShort. Punchy. Fragments. Every time. Why artificial tension reads fake, and how to restore natural rhythm.
- The Synonym Cycling ProblemWhen models rotate synonyms to avoid repetition, and end up sounding like a thesaurus with amnesia.
- Filler Phrases That Scream AIEmpty openers and throat-clearing sentences that add length without meaning, and how to cut them.
- Chatbot Artifacts in Pasted TextHeaders, disclaimers, and meta-commentary that leak from the chat UI into your final draft.
- Vague Attributions and Weasel WordsPhrases like 'experts say' and 'studies show' without sources, how AI hides uncertainty and how to fix it.
- Rule of Three OveruseTriads and triplets are a classic rhetorical device, until every paragraph sounds like a speechwriter's template.
- Em Dashes and AI WritingWhy models overuse em dashes, and how to punctuate with intention instead of rhythm-by-default.
- AI Vocabulary Words to AvoidA practical field guide to overused words that make prose sound machine-made, and what to use instead.
- Promotional Language TellsThe sales-brochure cadence that sneaks into AI drafts, and how to write like an expert, not a landing page.
- Significance Inflation in AI TextHow models turn ordinary facts into landmark revelations, and how to deflate your prose back to earth.
- Why AI Detectors Are UnreliableFalse positives, opaque scoring, and the limits of statistical guessing, why you should not trust a percentage score blindly.
- What Makes AI Writing DetectableThe statistical and stylistic fingerprints that make machine-generated text stand out, and how to recognize them in your own drafts.