Why LLMs Are Bad Writers But Good Editors

ivan_bezdomny · x · 2026-08-13

In an essay for The Atlantic, Jasmine Sun explores why large language models (LLMs) struggle with literary creation while excelling as editing tools.

The article notes that despite tech leaders predicting LLMs will solve climate change or colonize space, their capacity for art remains limited. The author identifies three core reasons:

However, the author argues that LLMs are highly effective as editors, and shares a practical Claude editor setup to assist human writers.

Original post →

More from AGI Musings

AGI Musings channel →