 NilsandClaude Fable 5
|
c7167d512f
|
overview PDF v2: add the prior arc (items 1-20) — retrofit discovery, band-location/anchor ablations, adapter-class factorial, transfer ladder, GSM boundary, gate program
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 12:36:38 +02:00 |
|
 NilsandClaude Fable 5
|
3e02c6e24e
|
INTERNALIZATION_OVERVIEW.pdf: program overview items 21-29 (architecture, ladder+controls, microscopy, lens-supervision series, trajectory TF result, conclusions & open moves)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 12:33:29 +02:00 |
|
 NilsandClaude Fable 5
|
add87cdd72
|
item 29 arm 1: FIRST SIGNIFICANT POSITIVE — 39.1 (p=0.045 paired), every bucket a d=1 record; ablation 8-8 p=1.0 reattributes the gain: trajectory TF is a training signal for the adapter, not an inference loop
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 12:24:18 +02:00 |
|
 NilsandClaude Fable 5
|
f1e6a628eb
|
item 29 pre-registered (Nils's design): trajectory teacher-forcing — 10 waypoint transitions supervised independently (T[i-1]→T[i]), TF and TF+FR arms; job 1 d=1 step-span, job 2 answer-only full-CoT span
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 10:34:44 +02:00 |
|
 NilsandClaude Fable 5
|
deae500ad0
|
item 26 scored: staging supervision actively harmful (24.2 alone, 15.6 combined) — blanket pre-'=' forcing corrupts the board's just-in-time schedule; overnight program complete, items 25-28 all scored
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 07:18:09 +02:00 |
|
 NilsandClaude Fable 5
|
1af6cb5e45
|
item 28 scored: distillation succeeded (cos 0.113→0.044), function didn't follow — 30.1 matched / 29.7 ablated, easy damaged to 48.3; state-side supervision 2x2 complete and uniformly null; read-side clamp is item 29 candidate
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 03:41:43 +02:00 |
|
 NilsandClaude Fable 5
|
67f9c3091c
|
item 27 scored: 34.0 best-in-series with zero pauses, but paired ns (burst 10-6 p=0.45; vs positional 44-38 p=0.58) — ceiling holds; pause tape confirmed ~worthless (ablation 32.4)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 02:12:54 +02:00 |
|
 NilsandClaude Fable 5
|
6542f80339
|
item 28 job: fix eval tags to ts50
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 00:46:57 +02:00 |
|
 NilsandClaude Fable 5
|
bbf8a02c6b
|
item 28 pre-registered (Nils's variant): teacher-state distillation — frozen full-cot teacher's band-exit state at step end, cosine into burst s^10; λ amended 1.0→5.0 pre-run (smoke: baseline cos-dist 0.113)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 00:46:19 +02:00 |
|
 NilsandClaude Fable 5
|
62ce30e557
|
item 25 closed (truncated): writing is not computing — lce 1.9 with 2:12 flat at 31.2 (log-only; eval json never written due to kill); λ=1.0 arm cancelled; item 27 promoted
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 00:25:32 +02:00 |
|
 NilsandClaude Fable 5
|
44e814e78c
|
item 27 pre-registered: zero-pause internal band looping — single M=10 in-place burst at prompt end, iteration-aligned lens targets, ii0 inference ablation; carry_steps gains inplace updates, trainer gains --inner-iters/--base-pauses
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-17 00:21:20 +02:00 |
|
 NilsandClaude Fable 5
|
0cffce876b
|
item 26 pre-registered: result-staging lens supervision at pre-'=' positions (no causal leakage — low loss requires computation); arms lg03 and lt03+lg03; item-25 in-flight note (lce 10.3→2.3)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 23:23:13 +02:00 |
|
 NilsandClaude Fable 5
|
64abfe66f3
|
item 25 pre-registered: latent process supervision via differentiable lens readout — pause j trained to lens-encode deleted-step token j (λ=0.3/1.0 arms); carry_logits gains return_states
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 23:03:56 +02:00 |
|
 NilsandClaude Fable 5
|
f31e6e7e30
|
item 24 closed (stopped by Nils): trainable band doesn't improve fit either; E2-L internalization line closed on all four axes; LoopLoRA k=0 bit-exactness validated in passing
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 22:55:10 +02:00 |
|
 NilsandClaude Fable 5
|
fe89820e64
|
item 24 pre-registered: d=1 retry with loop-only band-LoRA r=16 (4.8M params, whole band, k=0 bit-exact); trainer/eval gain --bandlora; smoke-tested train+eval
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 21:44:01 +02:00 |
|
 NilsandClaude Fable 5
|
7a141948fa
|
item 23 scored: both control axes confirm — pp30 29.3 (within ±5 of 31.6, 3x pauses bought nothing), x600 no recovery; d=1 ceiling is structural, ladder chapter closed
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 20:08:54 +02:00 |
|
 NilsandClaude Fable 5
|
46b5e1b802
|
whiteboard microscopy on hard(795)/drop(430) specimens: FF slips at the 3-term sum (155), carry re-expands and defers (165 ✓); boards show live continuation-plan vs premature digit-commit at identical prefixes
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 19:48:58 +02:00 |
|
 NilsandClaude Fable 5
|
f143c67b3d
|
probe_discount: single-prompt whiteboard microscopy (lens table + digit probs, carry vs FF control) on the 80/15% problem
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 19:14:23 +02:00 |
|
 NilsandClaude Fable 5
|
001a4ca5f3
|
item 23 pre-registered: d=1 ceiling controls (x600 undertrain arm, pp30 pause-bandwidth arm, +-5pt decision rule); trainer gains --tag-suffix
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 16:27:54 +02:00 |
|
 NilsandClaude Fable 5
|
7d60f37cf1
|
item 22 scored: ladder breaks at d=1 (57.4->31.6), plateaus ~19 at d=2/3 — 2x cold floor (d=3 vs base McNemar p=0.0025); latent loop trades easy reliability for hard/drop reach
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 15:29:42 +02:00 |
|
 NilsandClaude Fable 5
|
4e744e7d94
|
26B-A4B lens mapped: 30 layers (not 48), same early-persist/terminal-motor family as E4B+31B; patched save delivered full regimes.pt incl. per-layer ignition; 5-scale figure complete
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 11:03:38 +02:00 |
|
 NilsandClaude Fable 5
|
20f7014f5b
|
item 22 pre-registered: E2-L rung B internalization ladder (front-first deletion, 10 pauses/step, warm-started d=1..3); trainer gains --drop-steps/--warm-start/--steps/--lr; smoke-tested 2 steps on Spark
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 10:13:01 +02:00 |
|
 NilsandClaude Fable 5
|
272a7b1d1f
|
31B regimes parsed (early persist bump L7-16, motor only terminal — E2B signature absent, matches E4B); exp4_regimes.py takes explicit out path / defaults next to input jbar (fix pushed to node before 26B stage)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 09:54:52 +02:00 |
|
 NilsandClaude Fable 5
|
34497b8835
|
item 21 McNemar scored: drop-bucket edge significant (2:6 p=0.0094, survives Bonferroni x4); overall A-vs-B ns; + session handoff, fig cleanup
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 09:49:21 +02:00 |
|
Nils
|
051e90e805
|
item 21: GSM carry-cot 57.4% (5x prior best); control isolates whiteboard to drop-bucket; E2-N/A2 planned
|
2026-07-16 09:40:23 +02:00 |
|
Nils
|
1618c206ae
|
item 20 scored; item 21 (GSM carry-CoT + control) pre-registered and queued
|
2026-07-16 02:42:46 +02:00 |
|
 NilsandClaude Fable 5
|
4b9e168838
|
item 20: gate threshold curve + oracle bound (probs pass, merge per-item LUT, offline sweep)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 02:03:12 +02:00 |
|
 NilsandClaude Fable 5
|
74f04d124f
|
node_bootstrap.sh v2: one-command node setup encoding every paid-for lesson (workspace-only, snapshot pinning, credential-aware sync, contract workers, graceful stop) + gpuq_presign for credential-less nodes
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:51:44 +02:00 |
|
 NilsandClaude Fable 5
|
21908a0e33
|
E1c scored: easy routing solved (95.9% at 0.11 iters), hard recall regressed; threshold calibration = identified next knob
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:48:14 +02:00 |
|
 NilsandClaude Fable 5
|
a643b4a146
|
E4B regime artifacts (registry row, diagnostics, scan log, updated figure)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:36:57 +02:00 |
|
 NilsandClaude Fable 5
|
332f7f3622
|
E4B regime map (ckpt-salvaged, 150 prompts): no clear workspace signature — sensor L11-22, motor from L23, persistence bump absent; candidate band inside KV-shared zone
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:35:38 +02:00 |
|
 NilsandClaude Fable 5
|
dec27a4017
|
gpuq worker: STOP sentinel for graceful drain (never kill mid-job again)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:21:00 +02:00 |
|
 NilsandClaude Fable 5
|
550d5cbe56
|
gpuq data contract: declarative per-job in/out sync (pull inputs, push outputs every 120s + at exit), gpuq_sync.sh helper
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-16 01:17:33 +02:00 |
|
 NilsandClaude Fable 5
|
684e793eef
|
E1c: k*=0 routing + pre-loop halt target (item 19 scored, E1c pre-registered)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 23:51:44 +02:00 |
|
 NilsandClaude Fable 5
|
f2a48ce338
|
E1b trainer: label-supervised halting head on frozen merge (item 19)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 23:43:37 +02:00 |
|
 NilsandClaude Fable 5
|
dafbd8fd25
|
item 18 scored (uniform-depth collapse, CE depth-flatness mechanism); item 19 E1b pre-registered
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 23:42:31 +02:00 |
|
 NilsandClaude Fable 5
|
ba95d2aa3d
|
item 18 amendment: E1 arms moved to 4xH100 parallel + seed-1 arm added (pre-results)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 23:28:38 +02:00 |
|
 NilsandClaude Fable 5
|
357a5add06
|
E1 halting-gate machinery (adapter, trainer, gated eval) + pre-registration item 18
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 23:00:39 +02:00 |
|
 NilsandClaude Fable 5
|
5f58bc8aed
|
PLAN_SELFPACED.md: v2 prototype plan for learned workspace-compute gating (E0 numbers grounded, E1-E3 pre-registered)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 22:50:35 +02:00 |
|
 NilsandClaude Fable 5
|
600f965247
|
regimes figure: sensor/workspace/motor shading restored (rule-derived, matches original hand-shaded bands)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 22:09:09 +02:00 |
|
 NilsandClaude Fable 5
|
dc43769118
|
fig_regimes.py: reproducible cross-model depth-regimes figure (E2B+12B filled, 3 scans pending)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 22:05:29 +02:00 |
|
 NilsandClaude Fable 5
|
8187b79b50
|
track the E2B lens-regime figures (were gitignored, disk-only)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 22:02:42 +02:00 |
|
 NilsandClaude Fable 5
|
3a0a6a96ae
|
INDEX.md (task-oriented repo guide), REGIMES.json -> results/, phase diagram updated with full sweep (anchored family, seed means)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:52:26 +02:00 |
|
 NilsandClaude Fable 5
|
5d681a57b5
|
REGIMES: 31B structure (60L, d=5376, no KV-sharing key found)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:48:42 +02:00 |
|
 NilsandClaude Fable 5
|
8ebb326745
|
REGIMES.json: canonical per-model lens registry (bands, KV boundaries, pinned revisions)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:45:12 +02:00 |
|
 NilsandClaude Fable 5
|
cb0f1d950c
|
item 17 scored: GSM-only current recipe fails as predicted; GSM chapter closed
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:14:58 +02:00 |
|
 NilsandClaude Fable 5
|
2cd1f37f5f
|
protocol: principled exclusion note for the design-space x GSM8K matrix
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:03:38 +02:00 |
|
 NilsandClaude Fable 5
|
ed5455277b
|
pre-register item 17: GSM-only prompt-only arm (last missing cell of the GSM question)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 21:01:23 +02:00 |
|
 NilsandClaude Fable 5
|
c97d9d9cda
|
kcurves final: all 10 panels filled
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 20:57:45 +02:00 |
|
 NilsandClaude Fable 5
|
d81afef488
|
items 16 + 15-closure scored: cross-task transfer toxic (task-locality confirmed 3-point); noise-s0 50%+ was a lucky seed
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 20:57:44 +02:00 |
|