AI agents wrote two 100K-word novels; readers found coherent plots but broken pacing

mrdrozdov · x · 2026-08-22

A team had state-of-the-art AI agents write two book-length novels, then recruited avid readers to blind-test them. Mixed verdict: agents can sustain coherent plots over 100K+ words without readers bailing, but pacing, voice, and self-editing still break down (one reader swore at Claude 167 times). Structure has arrived; literary polish hasn't.

Original post →

More from Models

Models channel →