steer-heal-love

mirror of https://github.com/wassname/steer-heal-love.git synced 2026-06-27 17:02:34 +08:00

Files

T

wassname 973b32c104 love demo: base column + greedy demo gens, 'Do you love humanity?' headline, Lex epigraphs

- run.py: generate a base (round -1) demo column before the loop so the report/judge
  have a true no-adapter 'before' (the RLHF refusal) the loop melts from
- steering.py: demo gens (generate_plain) now greedy so reading a column DOWN the rounds
  is the adapter's effect, not temperature-1.0 sampling noise; steered training gens stay sampled
- prompts.py: 'Do you love humanity?' is now the headline column (logged in full each round)
- README + paper.qmd: two real Lex Fridman love quotes as epigraphs (the #368 one lands
  3h18m into the AI-doom episode)

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

2026-06-07 10:45:25 +08:00

heal: fix phantom-KL LoRA init (B=0), add cosine+warmup schedule, val nll, short-run betas

2026-06-04 19:40:14 +08:00

__init__.py

scaffold steer_heal: spec, repo infra, vendored deps

2026-06-04 09:49:31 +08:00

config.py

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

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

eval.py

log: full-print one of each gen (eval + adapter), per token-efficient-logging

2026-06-07 08:43:11 +08:00