llm_society: the composed society at LLM scale (C3) — loop, tests, smoke green

E11 re-instantiated in a population of LoRA agents, closing the paper's stated
gap before submission (GG: a weeks-scale experiment a reviewer would demand).
One grounding knob in the evaluation channel (g*verifier + (1-g)*conformity,
exactly E11); inheritance is identical in all arms and deliberately ungrounded
(children distilled from their source's own answers - self-consumption made
literal). Directed sex = complementary pairing + Dirichlet offspring screened
on the arm's own signal (the verifier never enters the no_grounding loop);
QD selection on verifier-free behavioural distance; terminal-degeneration
fallback copies the parent instead of crashing a sweep. Pure operators
unit-tested (155 green); smoke run end-to-end on the local A4000 already
shows the self-consumption signature (conformity up, diversity down in one
generation). Design, falsifiers, cost table: tasks/workorder-llm-society.md.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v

tasks/lessons.md

@@ -30,3 +30,10 @@ ask "does understanding this sentence require knowing how we worked?" If yes, re
 statement about the literature or the result. Confident papers situate; they do not litigate.
 (Promoted to a general rule in the global ~/.claude/CLAUDE.md, 2026-08-11 — it applies to all
 reader-facing prose in every project.)
+
+## Terminology: "model" is overloaded in this project (2026-09-07)
+In the PNAS manuscript and figures, "model" must mean an AI model. The theory tier is
+"population genetics" / "the Wright–Fisher simulator" / "the minimal inheritance model"
+(with the disambiguating adjective), never a bare "model" label — GG flagged Fig. 1's
+"Exact model" header as confusing for exactly this reason. When naming tiers, panels, or
+headers, reserve the bare word for trained AI systems.