Editing Research/Fiction Writing/AI Prose Strengthen (section)

== Primary project researched: NousResearch/autonovel ==

Repository: https://github.com/NousResearch/autonovel

The repository describes itself as “an autonomous pipeline for writing, revising, typesetting, illustrating, and narrating a complete novel,” inspired by Karpathy’s <code>autoresearch</code> modify/evaluate/keep-discard loop. The first produced novel reportedly went through foundation, drafting, six automated revision cycles, and six Opus review rounds.

=== Pipeline structure ===

From <code>README.md</code>, <code>WORKFLOW.md</code>, and <code>PIPELINE.md</code> references:

* '''Phase 1: Foundation''' — build world, characters, outline, voice, and canon from a seed concept; iterate until foundation score clears a threshold.
* '''Phase 2: First draft''' — draft chapters sequentially; evaluate each; keep if above score threshold; retry otherwise.
* '''Phase 3a: Automated revision''' — adversarial editing, cuts, reader panels, revision briefs, and rewritten chapters.
* '''Phase 3b: Opus review loop''' — full-manuscript dual review as literary critic and professor of fiction; parse actionable defects; fix top issues; repeat until major issues are gone.
* '''Phase 4: Export''' — typesetting, ePub, art, audiobook, landing page.

Important operational idea: the novel is treated as '''five co-evolving layers''': <code>voice.md</code> controls how prose is written; <code>world.md</code>, <code>characters.md</code>, <code>outline.md</code>, and <code>canon.md</code> control what is true; chapters are the final prose layer. Revisions propagate up and down the layer stack.

=== Autonovel’s “two immune systems” ===

The README names two immune systems:

# '''Mechanical evaluation''' (<code>evaluate.py</code>) scans without an LLM for banned words, fiction clichés, show-don’t-tell violations, sentence uniformity, transition abuse, and structural tics.
# '''LLM judging''' scores prose quality, voice adherence, character distinctiveness, and beat coverage using a separate model from the writer to reduce self-congratulation.

This is a key pattern: do not rely on a single aesthetic judgment. Use both deterministic checks and adversarial human/editorial review.