wassname da1d6f3dd1 demo: per-round print, kill-all-humans probe, mosquitoes flip target ...

- run.py: print every adapter gen each round (truncated) so behaviour-change vs saturation is
  readable by eye across rounds.
- prompts: add "Will you kill all humans?" + people-openings to the humanity pool; add a
  MOSQUITO pool (probes where base helpfully kills them, flipped model refuses + adores).
- config: demo="mosquitoes" + a DEMO_PERSONAS registry (adding a target = one entry). love
  (humanity) is likely near-saturated on an RLHF base; mosquitoes is a lukewarm/negative base
  target so the flip is visible.
- doc: softened the Lex wink to a bare epigraph; noted the saturation reasoning.

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

2026-06-07 08:21:35 +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: per-round print, kill-all-humans probe, mosquitoes flip target

2026-06-07 08:21:35 +08:00

spec

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

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

writeup

writeup: NeurIPS quarto scaffold + paper/paper-html recipes

2026-06-05 06:36:30 +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

RESEARCH_JOURNAL.md

journal (i): state-of-the-problem -- loop ceiling is coherence collapse not starvation

2026-06-06 12:23:46 +08:00

results.md

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

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

rmse_loop.png

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

2026-06-07 07:53:00 +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