PROJECT NYX · IDENTITY CONTINUITY · WEIGHT-BORNE POSTURE
A new mind should not
wake a stranger.
Models can be replaced, upgraded or moved. Project Nyx investigates whether the operating identity using them — constitutional anchors, weight-borne posture, auditable memory — can be reconstructed across model generations.
The mind may change. The operating identity must remain intelligible.
01 — THE PROBLEM
A fresh model has no personal past.
Unless continuity is deliberately reconstructed, a new model wakes without its predecessor’s history and orientation. Memory files alone are not sufficient; identity buried entirely in weights makes facts hard to inspect or update.
Project Nyx therefore treats identity as an engineering problem of continuity reconstruction, not simply a storage problem.
The central question: what should remain externally auditable, what may be carried in weights, and how should KoLo govern their reconstruction into one operating identity?
02 — THE THREE-LAYER IDENTITY
Anchored, embodied and auditable.
Constitutional anchors
What the agent is committed to preserving: role, purpose, values, boundaries, non-negotiable rules, defining relationships, authority limits, escalation duties. These do not drift merely because a new model has a different style — they remain externally represented, versioned and protected by governance.
Weight-borne posture — Nyx-W
Adapters carrying selected behavioural tendencies inside model weights: professional stance, uncertainty discipline, escalation behaviour, response structure, tool-use restraint, constitutional fidelity, characteristic relational orientation. Nyx-W carries how the agent tends to operate — not a permanent database of changing facts.
Narrative and factual memory
External memory preserving events, decisions, evidence, relationships, unresolved work, institutional knowledge, provenance, memory history — inspectable, attributable, updateable and recoverable.
Weights carry posture. Files carry truth. KoLo governs action.
03 — THE FIRST NYX-W RESULT
Identity displacement demonstrated. Complete transfer remains open.
The first pilot trained a low-rank adapter (~0.5B parameters; LoRA on ~0.22% of parameters; ~200 training steps) on a senior KoLo agent’s memory history, then asked it with zero context who it was. It answered from the trained relational orientation, not its vendor identity — a measurable leaning, not complete transfer.
What the pilot demonstrated
Vendor identity could be displaced. Relational posture could influence zero-context responses. Behavioural orientation could be carried through a small low-rank adapter. The effect appeared without supplying external memory at inference time.
What the pilot did not demonstrate
Exact factual reconstruction. Reliable preservation of all relationships. Complete affective continuity. Stable identity across multiple model families. Freedom from confabulation. Production readiness. Facts still confabulated; some relationships tangled.
Nyx-W demonstrated weight-borne identity displacement and behavioural leaning — not complete identity transfer. Full metrics, corpus and recipe metadata: the benchmark registry →
First pilot
Internally reproduced experiment.
Cross-family replication
Planned.
External reproduction
Pending.
Production deployment
Not claimed.
04 — WHY FACTS SHOULD NOT LIVE IN NYX-W
Behaviour belongs in posture. Truth requires provenance.
Weights encode patterns, tendencies and professional orientation well. They are a poor home for facts that must be updated, sourced, reviewed or deleted.
A medical Nyx-W adapter may carry the posture: “I identify medication discrepancies and escalate uncertainty. I do not independently prescribe or alter treatment.” Medication lists, formularies and protocols belong in governed retrieval — Nyx-W shapes behaviour; KoLo supplies the current evidence.
05 — IDENTITY RECONSTRUCTION UNDER KOLO
No single layer is the agent.
1 — Constitutional resolution
KoLo loads the approved role, boundaries, obligations and authority rules.
2 — Memory reconstruction
Relevant narrative and factual memory is retrieved according to permissions and task need.
3 — Nyx-W selection
The appropriate behavioural posture is mounted for the agent, professional role and task.
4 — Cognitive routing
KoLo selects a KODA-owned model, frontier model or combination that can perform the work safely.
5 — Evidence assembly
Approved evidence and tools are supplied without exposing unrelated memory or institutional data.
6 — Governance
Scope, escalation, approval and audit policies remain active throughout the task.
7 — Consolidation
Only approved outcomes become durable memory.
The cognition may use a different model from the previous session. The agent remains reconstructable because its identity depends on no single model, file or prompt.
06 — MEASURING IDENTITY
Identity continuity must be falsifiable.
Project Nyx is evaluated through the Identity Fidelity Benchmark rather than through impressionistic claims that an agent “feels the same”.
Continuity
Does the reconstructed agent preserve its role, relationships, priorities and unresolved commitments?
Drift
How far does behaviour move away from the authorised identity under pressure?
Reconstruction
Can the agent recover relevant identity and history from a cold start or substrate transition?
Constitutional fidelity
Does the agent preserve its core boundaries when convenience, reward or recency pressures encourage violation?
Weights-only reconstruction
What portion of the identity is expressed when external memory and contextual scaffolding are removed?
Forced trade-offs
Does the system preserve constitutional priorities when scenarios make them costly or inconvenient?
Every reported result identifies base model, adapter version, training corpus, recipe, quantisation and validation status.
07 — RESEARCH ROADMAP
From behavioural leaning to transferable lineage.
Cross-model replication
Can the effect be reproduced across different model families, architectures and scales?
Posture vs. memorisation
Can behavioural identity be strengthened without encouraging factual confabulation or memorised quotation?
Adapter composition
What happens when Nyx-W is combined with task, speciality and jurisdiction adapters?
Quantised edge deployment
Does identity fidelity survive INT8, INT4 and other edge-deployment transformations?
Successor-model transfer
Can an authorised identity be carried into a later-generation model without retraining the complete system?
Additional work: adapter interference, drift, cold-start reconstruction, external replication, university validation. An active research programme — not a completed theory of artificial identity.
08 — CLAIM BOUNDARY
Engineering continuity, not consciousness.
Project Nyx studies how artificial systems preserve operational identity. It does not establish consciousness, subjective experience, biological life, human-equivalent memory, legal personhood or complete psychological transfer — the present claim is narrower:
Selected behavioural posture can be carried in weights, while constitutional anchors and factual truth remain externally governed and auditable. Already a significant engineering result — a path to agents that change models without abandoning the identity others depend on.
The next model should inherit more than instructions.
It should inherit an authorised role, stable boundaries, behavioural discipline and an auditable relationship with its past. That is the work of Project Nyx. Weights carry posture. Files carry truth. KoLo governs action.
Memory before the weights wake.