Two rules for using LLMs on your own writing: don’t use a single word the model suggests, and never let it encourage you. Spotting passive voice, buried verbs, and the 750 words you don’t need, you can safely outsource. (Thomas & Erin Ptacek)
- Two rules for using LLMs on your writing without losing your voice: never adopt a single word the model suggests, and never let it encourage you about your draft.
- The first rule prevents phrase-level contamination, since frontier models default to a kind of relentless magazine-headline mode that readers detect at parts-per-trillion.
- Flattery from a chatbot makes you double down on first-draft instincts instead of rethinking them, which is where your actual voice lives.
