wassname 638fe23f3e LW-style draft post: gradient projection vs reward hacking (paper-writing skill) ...

Compresses the lab report into ~1700 words for a LessWrong audience while
preserving the workshop-paper scaffolding (intro / setup / method /
result table / mechanism subplot / limitations / related work / next).

Headline claim per user direction: projection cuts hack rate at matched
pass-rate (Table 1). Mechanism subplot (G_hack staleness + refresh-every-2)
kept as supporting context.

External-panel critique pass (n=5 models, mean 4.4/5 ready) on dims
hook/clarity/inform_not_persuade/calibration/LW_voice. Lowest scores
on clarity (density of delta_S / AntiPaSTO jargon) and LW_voice
(slightly more formal than typical LW). Acceptable for first draft.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-29 03:49:51 +00:00

..

blog

LW-style draft post: gradient projection vs reward hacking (paper-writing skill)

2026-05-29 03:49:51 +00:00

brainstorm

ready

2026-05-23 14:19:41 +08:00

lab

lab report v3: TL;DR, three-line concept, PASS_RATE column, G_hack rename

2026-05-29 03:18:22 +00:00

papers

setup

2026-05-23 10:40:02 +08:00

personas

fix smoke.

2026-05-23 11:26:39 +08:00

spec

wip

2026-05-28 12:44:20 +00:00

vendor

spec

2026-05-23 13:04:03 +08:00

extract_vhack_grad-vec.md

Doc cleanup: mark susp gate as REMOVED in design doc

2026-05-27 09:08:34 +00:00

grpo_hyperparams.md

fix smoke.

2026-05-23 11:26:39 +08:00

handover.md

register vendored repos as submodules (fix fresh-box empty-dir crash)

2026-05-24 05:32:13 +00:00

human_journal.md

init

2026-05-23 10:22:54 +08:00

paper_chars.md

top-k v_hack subspace + real-voice pairs + LoRA bake

2026-05-26 02:33:24 +00:00

table_proto.md

setup

2026-05-23 10:40:02 +08:00