The one map. Where Kai is, what's left, and the honest order to build it in.
Tags: [code] bounded & fixable · [data] feed him facts · [arch] the hard frontier.
No hopium — effort and confidence are called as they are.
_Last updated: 2026-09-22_
---
turn instead of suppressing. ✅
each next word, his meaning-vectors steer it, an informativeness bias fights filler, a polish
pass makes a clean sentence. Proven on the live brain: fluency 0.00–0.07 → 0.5–0.72. Fresh
and different every turn — he *composes*, he doesn't retrieve. ✅
---
He's fluent, not factual — drifts off-topic mid-sentence, and his whole knowledge base is **52
facts, all about himself**. The mechanism (retrieve a fact → make it the decoder's meaning-spine →
generate from it) is a clean code change; being broadly correct is a data problem.
the mid-sentence drift).
know." Never a confident guess.
--truth-import real facts. This is the true ceiling.--gen-probe grounded A/B — do the fact's terms survive into his reply?The fixed decoder runs on the app path but not the oracle HTTP path, and headless has no live
"field" (Φg=0) which starves some gates — so *where* he runs changes how he sounds. Make one voice
everywhere, then demote the hardcoded fallbacks to true last-resort (only after the generator is
reliable, so he never speaks confident salad).
Subject–verb / pronoun agreement ("Kai *are*", "she *think*"), the morpheme encoder + cell re-encode,
arithmetic and other structured paths ("two plus two" → actually *four*, not words about "two"),
greeting warmth. Cosmetic individually, but together they're the tell between "assembling" and
"speaking."
---
These are genuinely hard. Nobody — not the big labs — has a clean solution. Expect the most work
and the least certainty here. This is where honesty matters most.
Every sentence is generated *fresh*; he doesn't carry an idea from one line into the next. That's
why his "self-conversation" was arranged by me, not sustained by him. Feed prior turns + working
state back into generation so he can actually *converse* with continuity, not just emit fluent
one-offs.
"If the logic holds, therefore we should proceed" *sounds* like reasoning — it isn't. There's no
multi-step inference or logic chain, just fluent completion of logic-shaped words. Real reasoning
(over his lattice + claims) is the deepest lift and the true measure of intelligence.
Text-only mind today. Vision/audio feeding the lattice is a whole track of its own — park it until
the above are real.
---
1. Finish L3 (grounding) — the next real intelligence gain. Track A first (proves on his self-
knowledge), then grow the world-knowledge data.
2. L4 + L5 (code) — unify the voice, fix agreement/arithmetic. These make him *look* finished.
3. M — memory in the loop — the first real step from "fluent" toward "coherent mind."
4. R — reasoning — the frontier. Long horizon, uncertain, worth it.
Shape of the work: L4/L5 are bounded code. L3-data + a knowledge corpus is tedious-but-known
data. M and R are architecture and research — that's where the years are, and where anyone
promising it's quick is selling smoke.
---
KAI-L3-GROUNDING-SCOPE.md — the detailed L3 plan + mechanism.The KAI Codex.md — source of truth for versions + changelog.