- SKILL.md: 3 new entries (exploration-over-exploitation + nuisance HPs,
test-set contamination, loss-spikes-mean-bad-data-pocket) and an Ng
100-misclassified-examples quote under inspect-the-data
- refs/llm_judges.md: position/verbosity/self-preference biases (Zheng,
Wang 66/80 flip, Panickssery) + mitigation checklist from verdict docs
- Lones pitfalls linked as the exhaustive 36-item do/don't checklist
- 6 new frozen evidence files; Hamel evals link in further reading
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Both quote-verbatim with frozen evidence: the 2018 tweet thread (mirrored
via threadreaderapp, x.com blocks fetching) slots after overfit-one-batch;
CACE (NIPS 2015, entanglement section transcribed from the PDF) gives
Always-Be-Ablating its why.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
SKILL.md is now folklore only: verbatim practitioner quotes ordered
most-general-first, transformer/LLM fine-tuning entries in their own
section, minimal context, links and footnotes. New sources: unsloth,
axolotl (+training stability), HF course ch8.4, Bekman debug_utils
(evidence frozen in docs/evidence/).
The synthesized material (mental models, priors, symptom tables, agent
loop, triage, anti-patterns) moves to PLAYBOOK.md, framed as menus of
hypotheses rather than authoritative diagnoses. Made-up symptom tables
no longer sit next to sourced quotes.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
- Promote the general (non-RL-specific) Spinning Up lessons up to the main
folklore: "broken code fails silently", "you can't tell it's broken if you
can't see that it's breaking", and test on more than one setup.
- Add gwern's "Unseeing" to the data theme: you can't read what you actually
wrote, hence fresh eyes / a fresh-eyes subagent.
- New "Research taste (adjacent to debugging)" section with verbatim quotes,
each cached: Neel Nanda (your research is false by default; excitement is
evidence of bullshit; read your data), Ulisse Mini (understand the system to
shrink the search space), John Wentworth (gears-level models are capital
investments vs cheap black boxes).
All quotes verbatim from cached sources; 25/25 footnotes resolve.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Spinning Up as a Deep RL Researcher was only a bare code link; it's the
canonical RL-researcher guide and its debugging advice is gold. Cache the
rigour/debugging sections verbatim and quote the sharpest lines in the RL
sub-skill: "broken RL code almost always fails silently", "if it doesn't work,
assume there's a bug", "measure everything ... you can't tell it's broken if
you can't see that it's breaking", and test on more than one env. Add to RL
sources.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Gather debugging folklore from more practitioners, each a verbatim quote
checked against a cached source copy (footnoted with line numbers):
- koaning (Vincent Warmerdam), "Bad Labels": benchmark labels are often wrong;
find them with confidence-sorted errors.
- gwern, the tank-detection legend: the canonical data-leakage parable, plus
the scout-mindset twist that it's a likely-unsourced urban legend.
- Patrick Kidger, "Just Know Stuff": why research code is buggy ("kludge ...
bugs that don't cripple things only because some other bug stops them") and
"never accept the kludge". Plus a one-line jaxtyping pointer for shape bugs.
- nanochat (Karpathy): BOS-alignment fake metric improvement; all-ranks must
clip on inf (a multi-GPU bug single-GPU testing hides).
- cleanrl "37 Implementation Details of PPO" -> RL sub-skill, as the canonical
proof that reference-impl details (not ideas) decide whether PPO works.
Trim the lucidrains item to one quote (it had ballooned). Add wassname credit
+ companion-gist link. All 20 footnotes resolve.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Phil Wang's x-transformers is the canonical "the fix is in the code, not the
paper" catalogue. Add a folklore item on the most debugging-relevant trick:
QK / cosine-sim normalization to stop attention logits overflowing (the usual
cause of transformer loss spikes/divergence), plus the BLOOM/YaLM
post-embedding LayerNorm. Two verbatim lucidrains quotes, footnoted to the repo
+ a cached README copy with line numbers. Doubles as the modern concrete
example for the read-a-working-implementation section.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Add 3 new evidence files from modern open-source sources:
- karpathy_recipe_training_nn_2019.md: Karpathy's training recipe blog post
- nanochat_deepwiki_llm_pretraining_2026.md: 320+ HP sweeps for GPT-2-scale pretraining
- sanh_simple_considerations_hf_2021.md: HuggingFace NLP debugging notes
Add update-to-data ratio diagnostic to refs/diagnostics.md (target ~1e-3).
Add LLM pretraining gap note to SKILL.md intro linking the new sources.
Add tanh saturation % to logging checklist.
Deep research to uplift LLMs for ML debugging, opinionated by source
selection. Distilled from Schulman, Jones, Rahtz, Goodfellow, CS231n,
FSDL, and more. Includes runnable diagnostic scripts and LLM-specific
anti-patterns.
Author: wassname (https://github.com/wassname)
wassname