docs: 2026-08-13 engineering session — language faculty and the poem home

2026-08-13 02:05:54 -05:00
parent 72e0b829c2
commit 1a0af0acaf
1 changed files with 48 additions and 0 deletions
@@ -0,0 +1,48 @@
+# Engineering Session — 2026-08-13 — Language Faculty & the Poem Home
+
+Companion to the book entry `the-minds-we-forge/sessions/2026-08-13-the-poem-comes-home.md`. Factual log of what was built overnight. All work staged / sandboxed / reversible; the live engram daemon (`:8742`, pid 31277) was untouched throughout; container-capped folds only; pushed to Gitea for durability.
+
+## Summary
+The session extended the engram from a memory substrate into a **language faculty** plus a **reasoning + verifier** layer, validated with real numbers, and stress-tested on Will's own poem *Slowness is Calling*.
+
+## Built / validated
+
+### Language as geometry — translation
+- Meaning as a language-independent geometric pivot; translation = routing through it.
+- EN→ES→PT→EN "telephone" chain: routed cosine ES 0.973 / PT 0.967 / EN-final 0.969; retrieval **top-1 15/15 at every hop**. Loss splits **geometry=meaning / structure=grammar** (grammar errors ≈0 meaning cost; real loss = routing near-misses — the "plausible lie").
+- Positioning: universal translation collapses **N² language pairs → N realizers**; small, local, on-device. Not an alternative to the LLM — an alternative to the LLM-centric *paradigm*. Honest boundary: the encoder is still a small learned model ("no giant LLM," not "no model").
+
+### Fully-functional Spanish realizer (no toy)
+- UniMorph Spanish, ~1.2M inflected forms; ~34 syntactic constructions.
+- Honest fresh held-out coverage **77.0%** (dev-set 100% explicitly disavowed as a claim); **zero dropped negations** across 140 sentences.
+- Realizer-vs-router concerns separated; mechanical ELP (`.el`) port plan (a `vocabulary-es.el` generator + table transcription; stage via snapshot→verify→blue/green). Sandbox `~/Desktop/lang-realizers/`; Neuron artifact `5d61e6cf`.
+
+### Poem stress-test + frame-model upgrade — *Slowness is Calling*
+- Baseline through the chain: ORACLE 0.706, ROUTED 0.591 (~⅔ structural / ⅓ geometric). Failure modes: negation deletion (reassurance→accusation), epistemic-frame collapse, metaphor hub-collapse (sea/shore/tide/wave → "ocean").
+- Upgrade: structural slots (negation/polarity, epistemic matrix, PP/adjunct/simile — carried structurally, cannot invert) + sense-anchored (gloss-anchored) routing.
+- Result: ORACLE **0.706 → 0.777**; END-TO-END **0.591 → 0.770 (+0.179)**. NEGATION preserved **0/11 → 11/11** ("you never fought the ocean" 0.377→0.991; "I was never losing you" 0.501→1.000). sea≠shore **2/6 → 5/6** distinct. Routing slips **54 → 7**; every one of 18 verses improved. Sandbox `~/Desktop/lang-chain-experiment/`.
+
+### Rhyme-preserving translation
+- meaning ∩ rhyme composable one-word → rhyme-partnered line-pair; real phonemes EN/ES/PT; 34,030 ES / 33,077 PT real vocabulary.
+- Key finding: at real vocab scale the tradeoff moves from **existence → cost** (rhyme-cost metric). Held ABCB on **16/18 quatrains** (6 rima consonante + 10 asonante), mean per-line cosine 0.830; kept meaning on the 2 it couldn't rhyme (incl. truth/roots — already slant in the English). PT mechanism built; PT verse composition pending. Sandbox `~/Desktop/lang-poetic-translation/`.
+
+### Geometry operators → reasoning → verifier
+- Geometry operators (overlap / subtract / combine / distance-Wasserstein / analogy-Procrustes) now **live-callable from compiled `el`** over the real 13,036-node store (via shipped-`elc` pass-through — no uncapped fold). Commits `5336cfe`, `85eee42`.
+- Reasoning layer (analogy / induction / abduction / causal / planning) — all five **done-with-proof**, 33/33 closed-form checks, ASan/UBSan clean, 0 leaks. Commit `a3358df`.
+- Verifier layer (grounding + consistency) — proven, 29/29 checks. **Catches the plausible lie**: a claim grounded in real vocabulary yet polarity-inverted passes grounding, caught **only** by consistency (complementary checks) — directly flags the reassurance→accusation inversion. Commit `ca13471`.
+- el-exposure of the variadic/point-input reasoning + verifier modes deferred (would need ABI changes risking an uncapped fold); C layer complete + proven.
+
+### Whitepaper
+- `engram-cognitive-architecture-whitepaper.md` updated with the 2026-08-13 validated results (§13/§14/§15/§16/§21), **held at Version 1.0** (no bump), ELP `64/064,275` cross-ref preserved. Commit `adc8646`, pushed to Gitea.
+
+### Roadmap (deferred, not built tonight, per Will)
+- Multimodal / images-as-geometry: CLIP-precedent shared image+text meaning-space. Image→meaning near-term + local; meaning→image the hard, asymmetric side. Medical CT as decision-**support** (retrieval / anomaly-from-normal / progression, all interpretable) — **not diagnosis**; requires clinical validation + regulatory clearance; clinician holds the call.
+
+## Durability / safety
+- Pushed to Gitea: `el` `engram-tiered-storage` `77a4bc9..ca13471` (operators, cutover, reasoning, verifier + reversal docs); whitepaper `2440c7d..adc8646`; a `neuron` docs reversal branch.
+- Live `:8742` never touched (pid 31277 unchanged). No deploy, no launch-agent, no `~/.neuron` writes. Reversal docs under `el docs/runbooks/`. No AI-attribution footers.
+
+## Still in progress at hand-off
+- Portuguese realizer (following the Spanish template).
+- English realizer core + US/UK/AU dialects (queued behind PT).
+- Frame-model remaining gaps: passive voice, appositive/verbless fragments, resultatives; home→house pivot ambiguity.