wassname/ml-debug
1
0
Fork 0
mirror of https://github.com/wassname/ml-debug.git synced 2026-06-27 16:46:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Document quote-first evidence style

Browse Source
This commit is contained in:
wassname
2026-06-25 09:56:26 +08:00
parent 20f03f20b8
commit 67d4dc90bb
3 changed files with 66 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SKILL.md
+1
View File
@@ -287,6 +287,7 @@ Open the relevant one when the task calls for it. These are synthesized checklis
- [refs/metric_stuck.md](refs/metric_stuck.md) — "why won't this metric move?" plus the structural-ceiling check.
- [refs/sweeps.md](refs/sweeps.md) — same-seed paired comparison and cross-seed t-stat reliability, for before you claim method A beats method B.
- [refs/llm_judges.md](refs/llm_judges.md) — LLM-as-a-judge biases (position, verbosity, self-preference) and the mitigation checklist, for when an LLM-judged eval looks too good.
- [refs/research_taste.md](refs/research_taste.md) — quote-first research taste appendix: Nanda/Olah/Steinhardt/Spinning Up on patience, choosing what to try, information gain, de-risking, and distillation.
- [refs/transformers.md](refs/transformers.md) — transformer-specific folklore: full traces, warmup/LR, optimizer evidence, train-deploy parity, scale priors, steering, and disclosed-training reports.
- [rl/SKILL.md](rl/SKILL.md) — RL-specific: probe environments, reward engineering, HP defaults, reference implementations.
- [pinn/SKILL.md](pinn/SKILL.md) — physics-informed networks: nondimensionalization, gradient pathologies, curriculum.