Why LLMs Are Bad Writers But Good Editors - by Jasmine Sun

my new Atlantic essay + Claude editor setup

🌻 why LLMs are bad writers but good editors my new Atlantic essay + Claude editor setup Jasmine Sun Mar 23, 2026 ∙ Paid 248 8 28 Share source: The Atlantic / Alicia Tatone There’s a weird asymmetry between how tech people talk about AI’s incredible technical prowess and its attenuated capacity for art. Sam Altman has predicted that large language models will soon be capable of “fixing the climate, establishing a space colony, and the discovery of all of physics,” yet in an October interview with Tyler Cowen, guessed that even GPT-7 might be able to extrude only something equivalent to “a real

related reading

• The Human Skill That Eludes AI - The Atlantictheatlantic.com
• If you let AI do your writing, I will come to your house and kill yousamkriss.substack.com
• Writing for LLMs So They Listen · Gwern.netgwern.net
• Don't Let LLMs Write For You — LessWronglesswrong.com
• Why A.I. Isn’t Going to Make Art | The New Yorkernewyorker.com
• LLM poetry and the "greatness" question - by Hollis Robbinshollisrobbinsanecdotal.substack.com
• LLM-as-a-judge: a complete guide to using LLMs for evaluationsevidentlyai.com
• [2312.03746] Evaluating Large Language Model Creativity from a Literary Perspectivearxiv.org
• LLM Evaluation doesn't need to be complicatedphilschmid.de
• How I don't use LLMsgleech.org
• Your AI Product Needs Evals – Hamel's Blog - Hamel Husainhamel.dev
• The bitter lesson of LLM evalsparsed.com