A Different Kind of Content
Writing With AI — Part Two Last time, I told you where this loop came from — a year of an AI telling me my architecture ideas were great, a manual workaround that only half worked, and a skill that finally automated the fix. I ended on the sentence I actually said out loud: I called it a content design interview — let's try a different kind of content. This is what happened next. What follows…
This is an interview that took on a new form, shifting away from its previous architecture-focused content. The loop, which had been honed for months to critique architecture ideas, was redirected to examine writing. The key realization was that the loop was adept at accurately capturing problems, regardless of the quality of proposed solutions.
By expanding its scope to include audience and story continuity, the loop gained a new dimension of analysis, making it feel smarter rather than just different. The writer's role evolved from simply typing the topic and answering questions to making final decisions on what content to publish. The process resulted in less polished writing than typical AI outputs, which aligns with the writer's self-assessment as a struggling writer.
The experience felt more like being guided in organizing one's own thoughts rather than entrusting the entire composition to an AI system.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
