GoKawiilEssay outlines two-rule method for using LLMs as editors, not ghostwriters
A new essay argues that writers should draft their own work entirely by hand, then feed it to a large language model purely to spot flaws, never to supply finished phrasing. The author lays out two guiding rules: never use a specific wording an LLM suggests, and treat the model strictly as a copyeditor rather than a co-writer, to avoid producing text that reads as generic machine output.
GoKawiil's interpretation of the reporting above, not reported fact.
As AI writing tools become ubiquitous, readers are increasingly able to spot algorithmically smoothed prose, which can undermine trust and engagement even when the underlying ideas are sound. This approach offers a practical middle ground, letting writers exploit LLMs' editing strengths while preserving the idiosyncrasies that make writing feel human and credible.
- The author recommends writing first, then using an LLM only to review and critique, not generate text.
- Rule one: never directly adopt an LLM's suggested wording, since models default to catchy, headline-like phrasing.
- The method aims to prevent 'output' from replacing genuine personal voice in written work.
Source: sockpuppet.org — A Final Ward, 2026-09-17
Published there as: “How to Write with an LLM”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.