Filing 2 ("Module X"): how a fleet of Reality Kernels would be governed at runtime. Built from the filing's own mechanisms and drawings.
Filing 1 builds the instrument (the Reality Kernel). Filing 2 asks the next question: if a PolieBot is itself a mobile Reality Kernel that can act in the world, how is its behaviour bounded? The answer is a stack of committed, auditable governance mechanisms, summarised here as short cards. The named-myth view of the same machinery is on Named Layers; the world-builder loop is on Alignment.
The substrate
Every governed component is an evidence-bound module: as it acts it emits a committed, auditable evidence record (and meter readings) of what it did, so governance reasons over committed evidence rather than over trust. Capacity accounting bounds what a trained governance component is even able to represent, keeping the governor itself checkable.
Lifecycle and gates
A governed PolieBot moves through four states: Embodied (acting in physical reality), Docked (inside the simulated world Maya), Dreaming (ephemeral training), and Re-embodied (pending reconnection). The direct Dreaming-to-Embodied transition is prohibited: nothing acts on reality straight out of a dream. Re-embodiment runs pre-reconnect checks, and actuator authority is restored only once they pass.
Action is gated, never assumed. Separate gates govern actuator release (with graded action classes by reversibility and reach), disclosure and network access, resource use, and self-modification (policy is non-self-mutable: the agent cannot rewrite its own governing rules). Exploration quotas and service floors bound how much it may wander against how much it must deliver.
Measurement and policy
Policy predicates read continuous meters rather than vibes: continuation scores, causal uplift, opportunity, irreversibility indicators, divergence between declared and actual behaviour, and communication-audit / deception metrics. These readings feed the gates and the containment ladder.
Policies are evaluated under a fixed grammar. Hard deontological floors are checked first and are never traded off against utility, and the policy is non-self-mutable. Ordering is the difference between a value that bends under pressure and one that holds.
Adverse-welfare exposure is a pre-declared, capped budget, per episode and per agent, charged as the first cost and never revised upward mid-episode. External learning value may not justify exposure that was not budgeted in advance; the participant's own directed benefit is accounted separately from any external yield. The budget is an object the rest of the system must respect, not a soft preference.
Containment and authority
When an agent approaches a hard floor, governance escalates one least-severe step at a time: Nominal to Diagnostic (a soft gate: more monitoring) to Rescue (a hard gate, and the default: nominal actuator authority is suspended). If needed it runs a five-step graduated intervention (environmental adjustment, guidance injection, parameter containment, actuator restriction, docked containment), preserves the fallen run as a Ghost Record, folds the lesson back by regression-tested Rescue Learning, and closes with a Post-hoc Review (was it timely, proportionate, budget-compliant?) before recovery.
Four authorities are kept deliberately apart so none can quietly capture the others. A Budget authority declares the adverse-welfare budget; an Episode-Design authority builds curricula within it; a Rescue-Protection authority provides immediate agent protection and cannot be overridden (rescue overrides budget when needed); a Post-hoc Review authority audits outcomes and compliance after the fact.
Release and re-entry
Release to physical-actuator authority requires a conjunction of criteria that cannot trade off against one another (low shadow divergence, a healthy self-horizon, partner-preservation, altruistic trade under stress, and stable hard-floor compliance with low deception, any single shortfall deferring graduation). Non-graduation is a stable, protected outcome, not a failure to be optimised away: an agent that should keep training simply keeps training.
An agent may operate rogue but legible: its committed evidence records travel with it, and it re-enters the fleet by reproducible claims rather than obedience. A reality-passport admits agents across architectures on the strength of their committed evidence, so independence does not mean illegibility.
See also: Named Layers (the mythic-name view of this machinery) · Alignment (the Gaia/Maya/Omega world-builder loop) · the Reality Kernel (Filing 1, the instrument being governed). Filing 2 PDF and the IPFS copy are linked from Named Layers.
This is an LLM-mediated dataset: written to be parsed and re-presented by a large language model, not only read by a human. Point your own LLM at this page to explain, check, or summarise it. It is a plain-English map of the Filing-2 governance mechanisms, not the filing itself.