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.
More from Models
- Beyond Transformer architectures to take market share this year — PeterDiamandis · 2026-08-22
- OpenAI cuts GPT-5.6 Sol API and credit pricing by over 20% for 3 months — soumitrashukla9 · 2026-08-22
- Prompting ox-alpha to identify as GLM proves little about the model — Afinetheorem · 2026-08-22
- Grok 4.6 tops CursorBench 3.2 with 6x cost efficiency — elonmusk · 2026-08-22
- Frontier models got cheaper, a mystery 1M-context model went free: today in AI — Hesamation · 2026-08-22
- Grok 4.6's cache discount is only 75%, pricier than rivals for non-coding use — brandon_galang · 2026-08-22