MachineSex/tests
Giorgio Gilestro 9b0ca32f51 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
2026-09-07 11:55:19 +01:00
..
test_analysis.py Layer 1 complete: E3-E6 + E2 analysis add-ons 2026-07-04 18:54:42 +02:00
test_correctness.py Layer 1 core: Wright-Fisher knowledge-transmission model with E1-E2 2026-07-04 18:10:18 +02:00
test_dynamic_society.py society: the dynamic Lamarckian society — the vertical claim (E11 / C3) 2026-07-05 12:34:01 +01:00
test_genotype.py society: make the sexual-transmission model rigorous (E9 epistasis, E10 directed sex) 2026-07-05 11:13:37 +01:00
test_kernel.py knowledge: learning kernel — model the estimator bias, not just sampling 2026-07-05 10:23:33 +01:00
test_llm.py llm_society: the composed society at LLM scale (C3) — loop, tests, smoke green 2026-09-07 11:55:19 +01:00
test_mating_system.py E14: mating systems — monogamy vs promiscuity (mate-pool breadth) 2026-07-09 12:38:50 +01:00
test_mnist.py neural: real-MNIST external-validity tier (collapse + grounding) 2026-07-05 09:19:36 +01:00
test_neural_correctness.py neural: grounding refinement + all five Layer-1.5 figures 2026-07-05 08:14:19 +01:00
test_neural_torch.py recombination: reproduce the E4 "merge, don't average" finding in real weights 2026-07-04 21:49:44 +01:00
test_neural_validation.py Layer 1.5: architecture-general neural existence proof 2026-07-04 21:02:49 +01:00
test_rebasin.py E13b/c: harden real-weight speciation — full symmetry group + emergent-divergence null 2026-09-06 12:35:14 +01:00
test_scientific_validation.py Layer 1 core: Wright-Fisher knowledge-transmission model with E1-E2 2026-07-04 18:10:18 +02:00
test_speciation.py E12: model speciation — the merge-compatibility limit of the sexual society 2026-07-08 22:40:02 +01:00