How To Write With An LLM
Simon Willison endorses Thomas Ptacek's rules for using LLMs as copyeditors rather than ghostwriters, banning suggested phrasing.
Simon Willison highlights Thomas Ptacek's essay on writing with LLMs, endorsing the rule that no word or phrase suggested by a model may be used in published prose. Willison says he uses LLMs only for fact-checking, spelling, grammar, and as an occasional thesaurus, never to draft blog content. He frames the no-suggested-phrasing rule as useful discipline against recognizable AI output.
- Core rule: never use a single word or phrase an LLM suggests.
- Willison uses LLMs for fact-checking and proofreading, not drafting.
- Rule framed as protection against AI-sounding prose in published writing.
How To Write With An LLM Thomas Ptacek on using LLMs as copyeditors, not as writing assistants: Rule Number One: You may not use a single word an LLM suggests to you. [...] I think that as a form of intellectual personal protective equipment you should adopt the rule that any specific turn of phrase an LLM suggests is off limits. Be strict about the rule! I won't let LLMs write content for my blog, but I use them for fact-checking, spelling and grammar and as an occasional thesaurus (see my proofreading prompt ). The rule to never use a turn of phrase suggested by an LLM feels good to me. The text has that weird smell to it, and it's also a good principle to help stay disciplined. Later in…
This source does not provide full text. Read it at simonwillison.net.