Stages: rename titles, fix execution order, remove all numbered references

projects/passepartout/architecture/_index.org

@@ -84,7 +84,7 @@ Blind spot 2 — the kernel prevents the action before the gate sees it. If the
 
 Without these mitigations, the gate's coverage converges to a plateau determined only by what has already broken, leaving large regions permanently dependent on the LLM's probabilistic reliability.
 
-**Gate decision flow (Stage 2):** An action arrives carrying a domain tag. First, the gate checks the deductive layer — does this domain have registered ACL2-verified boundary procedures? If any denies, reject instantly. The LLM cannot overrule. If no verified procedure denies, the gate checks with Screamer — a constraint network built from rules extracted by the LLM and corrected by humans. Screamer resolves domain-specific constraints, rights, and prohibitions. If Screamer finds a resolution, apply it. If not, the gate asks the LLM. The LLM proposes permit or deny, and the gate re-checks against the deductive boundaries (defense in depth). Every decision is logged to the decision log.
+**Gate decision flow (Neurosymbolic Agent stage):** An action arrives carrying a domain tag. First, the gate checks the deductive layer — does this domain have registered ACL2-verified boundary procedures? If any denies, reject instantly. The LLM cannot overrule. If no verified procedure denies, the gate checks with Screamer — a constraint network built from rules extracted by the LLM and corrected by humans. Screamer resolves domain-specific constraints, rights, and prohibitions. If Screamer finds a resolution, apply it. If not, the gate asks the LLM. The LLM proposes permit or deny, and the gate re-checks against the deductive boundaries (defense in depth). Every decision is logged to the decision log.
 
 **How domains emerge:** Domain tags are not assigned upfront. The user writes notes in Org. The symbolic index extracts entities and relationships. Screamer's constraint network connects them. Over time, clusters form — entities that mention each other frequently and mention outside entities rarely. The gate notices clusters where LLM utilization is high. It asks the LLM to label them: "This cluster deals with financial records. Shall I create a domain called accounting?" If the user confirms, the procedure registry gets a new tag. New domains start empty — no verified boundaries — and fill as mistakes accumulate.
 
@@ -132,11 +132,11 @@ The social protocol is not a blockchain. DAG-based ordering handles causality; d
 
 The full architecture — gate-verified Lisp machine on custom silicon — is the destination. The staged roadmap (see the [[file:/stages.org][stages]] directory for full detail) describes how each successive replacement eliminates a class of threat:
 
-Stage 0 (Now: Linux + Python agent + SQLite), Stage 1 (Neurosymbolic Agent: the gate — root eliminated, provenance store operational), Stage 2 (Lisp Machine: bare-metal — no MMU), Stage 3 (AI Inference: in-process LLM), Stage 4 (Social Protocol: provable communication), Stage 5 (AI Weights: plist-native neural data), Stage 6 (AI Training: verified fine-tuning), Stage 7 (What Remains — physical, political, oracular limits).
+Development (baseline: Linux + Python agent + SQLite), Neurosymbolic Agent (the gate — root eliminated, provenance store operational), Social Protocol (provable communication), Lisp Machine (bare-metal — no MMU), AI Inference (in-process LLM), AI Weights (plist-native neural data), AI Training (verified fine-tuning), What Remains (physical, political, oracular limits).
 
-Each stage is independently useful. Stage 0 is running today. The migration is progressive component swap, not a cut-over.
+Each stage is independently useful. Development is running today. The migration is progressive component swap, not a cut-over.
 
-**Self-developing hardware (Stage 3+):** The hardware side of the Lisp Machine self-improves by synthesizing its own microcode. A Tenstorrent P150 (~72 RISC-V Tensix cores) runs Lisp microcode with one core dedicated to ACL2, one to Screamer, and the rest to gate verification and fact store operations. The system profiles its own gate verification latency, proposes a new microcoded instruction for the hot path, compiles RISC-V assembly from ACL2-verified specifications, loads it via PCIe DMA from within SBCL, benchmarks it — and rolls back if slower. The self-driving threshold: every subdomain involved (RISC-V ISA, SBCL internals, ACL2 metafunctions, compiler optimization) is software — the most codifiable domain — and can flip to symbolic sufficiency within days of ingestion.
+**Self-developing hardware (Lisp Machine onwards):** The hardware side of the Lisp Machine self-improves by synthesizing its own microcode. A Tenstorrent P150 (~72 RISC-V Tensix cores) runs Lisp microcode with one core dedicated to ACL2, one to Screamer, and the rest to gate verification and fact store operations. The system profiles its own gate verification latency, proposes a new microcoded instruction for the hot path, compiles RISC-V assembly from ACL2-verified specifications, loads it via PCIe DMA from within SBCL, benchmarks it — and rolls back if slower. The self-driving threshold: every subdomain involved (RISC-V ISA, SBCL internals, ACL2 metafunctions, compiler optimization) is software — the most codifiable domain — and can flip to symbolic sufficiency within days of ingestion.
 
 **Downstream effects.**