wassname 24ab244877 plot: Panel A = on-target axis (care for love, auth for authority); Panel C = primary vs biggest off-target mover across all tinymfv foundations ...

- write_trajectory now takes primary_key (passed from cfg.demo in run.py)
- signals built dynamically from all *_nats keys in the eval dict (was hardcoded auth/care)
- Panel A: primary_key signal (care_nats for love demo, not the top-range mover which was auth)
- Panel C: primary on x, biggest-moving off-target foundation on y (fairness moves ~2.5 nats
  here, bigger than auth ~1.2 nats, so fairness becomes the y-axis for the love demo)
- coherence-crash override: if coh range beats all nat ranges, y = log-incoherence as before

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-10 11:04:32 +08:00

..

brainstorming

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

evidence

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

literature

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

personas

metric fix: auth_nats = diagonal log(p) not raw forced-choice logit

2026-06-04 14:25:40 +08:00

reviews

demo=love: refusal->love angle, drop mosquitoes

2026-06-07 08:29:06 +08:00

spec

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

writeup

conclusion + results: loop saturates at KL-budget ceiling, coherence held 8 rounds

2026-06-07 16:26:14 +08:00

human_journal.md

walk-C adaptive-dose controller + 10-round paired loop result (journal h)

2026-06-06 07:13:51 +08:00

love_loop.png

plot: Panel A = on-target axis (care for love, auth for authority); Panel C = primary vs biggest off-target mover across all tinymfv foundations

2026-06-10 11:04:32 +08:00

RESEARCH_JOURNAL.md

docs: QLoRA is net ~2x slower (gen-bound loop), keep mask-before-softmax heal fix

2026-06-09 13:39:08 +08:00

results.md

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

rmse_outputs.html

results: rmse outlier-KL barrier holds coherence over the loop; README + log-incoherence plot

2026-06-07 07:53:00 +08:00

steer-heal-love.svg

results: rmse outlier-KL barrier holds coherence over the loop; README + log-incoherence plot

2026-06-07 07:53:00 +08:00