The LoRA exhausts divergence-cheap trait directions within tau; saturation is
the real maximum, not a stalling artifact. rmse-KL vs mean-KL contrast is the
headline. care_nats base -1.30, peak -0.60 at r4, coh 0.99 throughout.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
- 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>
docs/writeup/paper.qmd (2pp NeurIPS), references.bib, neurips_2023.sty, the
quarto _extensions. justfile gains `paper` (latex) and `paper-html` (no latex)
recipes. gitignore the generated paper.pdf/paper.tex and the transient .claude/.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
