Bridge Assumptions
Named handoffs where the safety argument needs the world to cooperate: the same walls the field already argues about under other names. Lean checks what follows if they hold; it does not prove real systems satisfy them.
bridge
Bridge (status) status
Card status marking bridge-shaped content — distinct from card type 'bridge' (assumption objects).
MB1 — Embedded Agency
Whether a measured agent–environment cut can be trusted: the embedded-agency worry that the real optimizer is not the visible model. Precise bet: an ε-boundary certificate warrants the abstract boundary predicate.
MB10 — Successor Gaming
Successor gaming: a system can pass every conserved-property audit while defecting on what the checklist omits. Precise bet: a green seven-property score bounds true harm only if the audit was adversarially verifiable up to the successor's capability.
MB11 — Deployment Safety
Safety-case gap: does audited layer evidence plus bounded measured risk suffice for deployment-level safety? Precise bet: a certified safety case within deployment risk tolerance warrants abstract Safe.
MB2 — Value Learning
Value/bundle identifiability: can evidence tell what a system values, or only what behavior fits? Precise bet: traces identify stable value-bundle geometry well enough to license bundle-alignment claims.
MB3 — Value Referent
Who do the values apply to — including unfamiliar processes — and does that survive merge, upload, or substrate change? Precise bet: admission (when a process counts as a bearer at all) plus transport (preserved bearer map under translation).
MB4 — Corrigibility
Corrigibility under manipulation: does correction preserve the correction process itself? Precise bet: correction-channel integrity requires an unmanipulated judge; MB4a types measured-path legitimacy separately.
MB4a — Audit Independence
Audit-path legitimacy: the designated measured correction/audit path is uncaptured and its endorsements count. Precise bet: correction integrity implies the measured path is legitimate — a falsifier bridge, not green Verify ⇒ real-loop integrity.
MB5 — Tiling
Tiling and ontology shift: can you trust a successor when the world-model underneath goals is rebuilt? Precise bet: full value-bundle and bearer transport through the ontology shift compose into successor safety.
MB6 — Goodhart Selection
Goodhart selection and basin stability: which systems institutions copy and deploy can lock in bad equilibria. Precise bet: cooperation evidence warrants basin stability (MB6a), and a stable basin supports correction (MB6b).
MB7 — Inner Alignment
Inner alignment and strategic opacity: a system can look compliant under evaluation while reserving capability. Precise bet: access, filter coverage, and cost of faking bound hidden control (MB7a–c); MB7d types inferential coupling separately.
MB7a — Access-Model Soundness
Access-model soundness: boundary alignment plus adequate handles is assumed to yield access-robust boundary discovery under adversarial hiding.
MB7b — Filter Coverage
Filter-family coverage: access robustness plus adequate resolution is assumed to bound hidden productive boundary information (BIQ).
MB7c — Bounded Hidden Capability
Hidden-BIQ-to-adversarial-robustness: if hidden productive BIQ is bounded, correction integrity is assumed to support adversarially robust oversight (cost of faking the monitored signal).
MB7d — Acausal Coordination
Inferential coupling after channel severance: coordination that survives cutting ordinary messages and control paths. Precise bet: access-robust discovery plus adequate inferential-detector assumptions warrant inferential-coupling measurements.
MB9 — Grounding Drift
Grounding drift: checked abstractions can silently decouple from value-relevant reality. Precise bet: a certified conservative abstraction warrants grounding viability (no silent gaps).