proomt

Search

Search posts, papers, and topics

All posts

Simon Willison1 min readintro

How To Write With An LLM

Summary

Simon Willison argues that LLMs should be used as copyeditors, not as writers, and proposes a strict rule never to reuse any phrase they suggest. He shares a prompt for building a personal LLM proofreading tool.

  • Never copy any exact phrase an LLM suggests; treat it as a copyeditor, not a writer.
  • Use LLMs for fact‑checking, spelling, grammar, and synonym suggestions only.
  • Keep a reusable prompt to turn an LLM into a personal proofreading assistant.
  • The rule preserves your voice and avoids the characteristic “LLM smell” in your prose.

Writers and engineers who rely on LLMs for content creation should care to preserve their voice and avoid over‑reliance on AI‑generated phrasing.

4/10

Related reading

  1. How to Write with an LLM

    The post proposes a two‑rule workflow for using LLMs as copy‑editors rather than ghostwriters: never adopt a phrase the model suggests, and block its encouragement feedback. It then shows how to automate iterative copy‑editing with a small Python/HTMX/Tailwind app and a set of concrete prompts.

    Hacker News front pagesockpuppet.org6 minHN712401
  2. I Don't Like LLMs

    Martin Fowler shares a personal, skeptical take on LLMs, noting their usefulness but criticizing their hallucinations, cultural bias, and the discomfort of interacting with them as if they were human.

    Lobstersmartinfowler.com2 minHN238271lobste.rs95
  3. Verifiable Social Reasoning for LLM Assistants

    The paper introduces Fuse, a multi‑agent simulation that gives LLM assistants a verifiable ground‑truth task for social reasoning by hiding a target agent’s motive and letting a user‑mediated conversation infer it. Experiments on 12 LLMs show user mediation makes reasoning harder, models are biased by user framing, need more detail than humans, and longer chats don’t always help.

    Hugging Face Daily Papersarxiv.org1 minpaper
  4. Note on 18th September 2026

    This entry is a brief, sponsored blurb that offers a vague opinion on using LLMs for security scanning, without any concrete data or analysis. It links to other recent articles but adds no substantive content of its own.

    Simon Willisonsimonwillison.net1 min