Compressed Coordination

A bounded agent — one with finite sensors, finite memory, finite attention, finite time — cannot hold the world. The world has, for practical purposes, inexhaustible detail; the agent has a few pounds of brain or a few terabytes of RAM. The math does not work, and no future hardware will make it work. Any representation the agent builds is necessarily smaller than the world it represents.

A single bounded agent acting alone has only its own representation to work with. It compresses, acts, observes, updates, compresses again. The hard problem starts when two such agents have to act on a world they're each compressing separately.

The constraint

When two bounded agents must coordinate, neither can hand the other their full representation. There is no full representation; both ends are already running compression. The handoff is a third compression: a smaller object — a signal — that points at a larger source state on the sender's side and unfolds against a stored model on the receiver's side.

The arithmetic forces a hard consequence: the signal underdetermines the source state. If the sender has N possible internal states and the channel admits M < N possible signals, then some sender states share a signal. The receiver, looking at the signal, cannot uniquely identify which source state it came from. Multiple source states are consistent with any given signal; the receiver cannot recover the sender's full state from the signal alone.

This is not a flaw of any particular codec or any particular matching mechanism. It is a structural property of bounded communication. The receiver always does inferential work the signal does not fix.

The consequence

If the source state cannot be recovered uniquely, then communication is not the transfer of state. It is the receiver-side reconstruction of state, from the signal plus the receiver's own priors plus the surrounding context.

This sounds like a problem. It would be a problem if coordination required full-state recovery. It doesn't. Coordination requires that the receiver's reconstruction preserves the distinctions that would change the next action.

State the criterion sharply: the task partitions source states into equivalence classes. Two source states belong to the same class if the optimal next action under each is identical. Communication need not preserve every difference between source states; it need only preserve the differences that move source states across class boundaries. This is the rate-distortion move, recast for coordination — a compressed signal is task-sufficient if it preserves the distinctions that would change the receiver's policy. Underdetermined dimensions that fall inside an equivalence class are harmless. Underdetermined dimensions that span class boundaries are the dangerous ones; the receiver's reconstruction might land in the wrong class and drive the wrong action.

This does not eliminate underdetermination. It defines when underdetermination is harmless. That distinction is the entire pragmatic content of compressed coordination.

This is not, and is not pretending to be, a philosophical settlement of the indeterminacy-of-meaning problem. It is a task-relative engineering criterion. The receiver's reconstruction is not "the correct meaning" of the signal; it is a representation sufficient for the next action, under a task structure that defines which differences pay.

The mechanism

Reconstruction is not a single operation. It runs through several stages, each with its own failure surface.

Common ground. The signal only constrains a reconstruction in the receiver if the receiver has stored patterns the signal can resolve to. A handle like DKA only lands in a receiver who has the illness script installed. Sell at the bid only resolves into a market action in someone fluent in equities. git rebase only resolves into a meaningful operation in someone with a built model of distributed version control. The shared infrastructure — vocabulary, conventions, priors — is what every signal is implicitly a pointer into. Both ends must have invested in the same infrastructure for the pointer to resolve.

Matching. When the signal arrives, the receiver runs a matching operation: from the signal, against stored patterns, to a candidate reconstruction. The matching is fuzzy by construction. Multiple surface forms point at the same pattern; single surface forms point at multiple patterns; matching fires probabilistically with context as the disambiguator. Matching is also multi-level — a face matches simultaneously on visual features, identity continuity, behavioral history, emotional signature, and each level can succeed or fail independently.

Priors and context. Matching does not run on the signal in isolation. It runs on the signal weighted by everything the receiver already believes — the leading hypothesis, the surrounding signals, the recent action history. The reconstruction is the joint optimum of signal and priors, not the signal alone. When priors are strong, they can resolve underdetermination cleanly. When priors are wrong, they can drag matching toward a confident but incorrect reconstruction.

Verification. For coordination to actually close, the sender needs to know the receiver's reconstruction landed in the right equivalence class. If verification is implicit — silence treated as agreement — the sender assumes the landing was correct. If it's explicit (read-back, confirmation, observable downstream action), the loop closes. If it's neither, divergence accumulates silently.

Temporal stability. All of the above must remain stable across time. Common ground drifts (training distributions shift; conventions change). Priors update (the receiver yesterday is not the receiver tomorrow). Verification mechanisms degrade. The architecture is not a static contract; it's a maintained one.

The breakdowns

If reconstruction runs through five stages, it can break at any of them, producing three broad classes of failure.

Failure to resolve. The signal arrives but cannot be matched. The receiver has no stored pattern that fits; or multiple stored patterns fit equally well and context doesn't disambiguate. The receiver knows they don't know. This is the safest failure because it surfaces openly: the receiver asks for clarification, the sender provides more signal, the loop continues.

Wrong resolution. The signal matches a stored pattern, but not the one the sender meant. This is the dangerous family. It happens when:

• The receiver's stored vocabulary has a different referent for the same handle (homonyms, synonym sets across communities, training distributions diverged).
• The matching succeeds at one feature level but fails at another, and the integration step doesn't catch the conflict.
• The receiver's priors drive the matching toward a pattern that's locally plausible but globally wrong.
• The signal underdetermines along a dimension that turns out to be action-relevant, and the receiver's filling-in lands in the wrong equivalence class.

Resolution drift. Matching that worked at one time fails at another. Common ground has aged. Conventions shifted. Training distributions diverged from current cases. The same signal that landed correctly six months ago lands in a different equivalence class today.

The canonical example of wrong resolution at multiple feature levels is entity resolution. Two records share name, date of birth, demographics, and most surface features; they get merged because the surface match succeeds. The identity binding fails — they are not the same person. Category-level matching landed; identity-level matching didn't. The downstream action — one person's medication history applied to the other's care — is catastrophically wrong.

The same shape recurs across substrates. In distributed systems: a client resolves the correct service identifier to a stale leader after failover; name-level matching succeeds, temporal-state matching fails, the action executes against the wrong epoch. In retrieval-augmented AI: a model retrieves the semantically nearest document, which is the wrong patient, the wrong environment, or the wrong time slice; topic-level matching succeeds, referent-level matching fails. In human cognition: the Capgras phenomenon, where visual features match the loved one but identity continuity does not and the integration mechanism that normally settles the conflict has broken. Different substrates, same architecture.

The three failure modes the Compressed Medicine curriculum named at the clinical level are now derivable rather than asserted:

• Asymmetric updating is the case where the receiver's leading hypothesis biases matching toward itself. The reconstruction process weights the prior; the prior was wrong; the action that follows is wrong. This is a breakdown at the priors and context stage.
• Silent reconstruction is wrong resolution where the receiver fills underdetermined dimensions from their own priors, and the fill is invisible to both sides. The receiver believes they understood. The sender saw acknowledgment. The reconstruction landed in a different equivalence class than intended, and no verification mechanism caught the gap.
• Shared vocabulary, divergent state is wrong resolution at scale. Two receivers (or sender and receiver) running matching on the same handle resolve to slightly different stored patterns, conditioned on different training distributions. The tokens match on the wire; the equivalence classes behind them diverge. Lamport's 1978 result is one substrate's version of this; the same shape, the same impossibility.

All three are special cases of the same underlying breakdown: the receiver's reconstruction landed in the wrong action-relevant equivalence class, and the channel could not surface the divergence in time to act on it.

The countermeasures

If the failures are universal, the defenses are too. Two operations recur across every domain that has solved any version of this problem.

Shrink the harmful underdetermination space. Invest in common ground. Train both sides on the same patterns, the same conventions, the same priors. The more two agents share, the more the signal constrains reconstruction to a narrow set of action-relevant equivalence classes. Medicine has done this for a century with medical school, residency, illness scripts, and standardized order sets. Aviation does it with Crew Resource Management and ICAO phraseology. Distributed systems do it with shared schemas and ontologies. Science does it with notation conventions and citation infrastructure. The investment is heavy upfront; the return is that subsequent signals constrain reconstruction more tightly and land in the right class more reliably.

Detect and surface wrong landings. Even with strong common ground, reconstruction can land in the wrong class. The second defense is mechanisms that catch this — feedback from receiver to sender, divergence detection across replicas, predicted-versus-observed checks, action-precondition gates, structured read-back at high-stakes commits. The mechanisms differ across domains; the operation is the same: surface divergence before action makes it irreversible.

Every other defense — uncertainty markers, decompression order, grounding constraints, structured handoff protocols, cross-modal verification — is an implementation detail of these two. Shrink the space and catch what slips through. That is the whole architecture, at any substrate.

Why this generalizes, and why now

The architecture is substrate-independent because the constraints producing it are substrate-independent. Any system with bounded agents, lossy channels, and a task that partitions source states into action-relevant equivalence classes runs this architecture. The alternative is incoherent action.

Clinical medicine. The case worked out in detail in the eleven-part Compressed Medicine curriculum. Bounded clinicians compress patients into structured belief states; handoffs transmit a compression-of-a-compression; verification mechanisms at action-changing moments catch divergence before discharge, sign-off, or escalation. Medicine forces the architecture to be honest because the stakes are visible, the agents are heterogeneous, the codecs are documented, and irreversibility is tracked. It is one instantiation, not the boundary.

Multi-modal AI ingestion. A model that ingests video, audio, structured records, internet content, and outputs of other models is receiving multiple compressions of underlying reality, each with its own codec — a video encoder, an audio codec, a database schema, a training distribution, an ontology. The model must run matching against each, reconcile across modalities, hold a unified reconstruction, and act. The clinical AI thesis lifts directly: belief-state coordination across heterogeneous channels, verification at action-changing moments, common-ground investment across modalities. Same architecture, wider substrate.

AI-to-AI coordination. When both ends of a handoff are automated, no human is in the loop to catch silent reconstruction. The three failure modes recur faster and at scale. The "small active read-back at workflow seams" from the curriculum's Quiet Verification companion becomes a cross-AI handshake protocol that does not yet exist; the field has not built it because the human-mediated case has dominated attention.

Distributed systems. Lamport's 1978 logical-clocks paper named the structural problem: mutual knowledge of meaning is unreachable over an imperfect channel between two finite nodes. Knight Capital's 2012 Power Peg outage was wrong resolution at scale — eight trading servers, one missing the new code, all matching at the protocol level while diverging at the semantic level; $440 million lost in forty-five minutes. Vector clocks are the partial mitigation; same architecture as clinical AI's provenance-per-assertion discipline.

Intelligence analysis. Yom Kippur 1973. A standing doctrine — Egypt would not attack without air parity — biased matching toward an incumbent hypothesis; mobilization signals were resolved into the wrong equivalence class. Richards Heuer's Analysis of Competing Hypotheses (1999) is the procedural mitigation: forced scoring of evidence against every hypothesis on the table, not only the leader.

Aviation. Tenerife 1977 was wrong resolution at the matching stage: a clipped controller transmission, KLM's matching landed on "clearance," the underdetermined dimension was action-relevant, the integration mechanism (read-back) was absent. Crew Resource Management and mandatory read-back are the structural mitigations that close the loop.

Biology. Cells signal compressed states to other cells through receptor-ligand pairs — handles built from molecular codecs. The immune system's failure modes are codec failures: autoimmunity (self codecs misclassified as foreign), immune escape (pathogens evolved to evade the codec), allergic responses (the codec is too generous). Same architecture, twelve orders of magnitude smaller scale.

Science. A paper compresses years of work into a few thousand words. Peer review is constrained reconstruction with verification. Reproducibility crises are silent-reconstruction failures at the field scale, where receivers resolve papers against priors that don't match what the original work actually established.

Cross-cultural communication. Idioms are compressed cultural patterns. Translation fails not because words lack equivalents but because receivers do — the underdetermined dimensions of a phrase span equivalence classes the source language doesn't make explicit. The architecture from the Receiver Is the Codec companion, stated outside the clinical case.

Different stakes, different speeds, different agents, same architecture.

Why this matters now. Three converging pressures make the framework load-bearing rather than a curiosity.

AI systems are becoming multi-modal. Each stream is a codec; reconciling them is compressed coordination at industrial scale. Building this without the framework means re-inventing the breakdowns domain by domain, painfully, under different names.

AI systems are becoming multi-agent. Agentic frameworks, multi-step tool use, AI-to-AI handoffs. The human verification clinical AI still depends on isn't available when both ends are automated.

Every system integration is a codec-translation operation. Cross-organizational data flows, schema migrations, API integrations, EHR-to-EHR transfers — all instantiate the architecture, with the same three breakdown classes and the same two defenses. The cost of misalignment scales with the irreversibility of the resulting action.

The framework is the lens. Without it, each domain rediscovers the same breakdowns and installs partial, incompatible mitigations. With it, the mitigations are portable: aviation's read-back discipline lifts to clinical AI; clinical AI's structured belief states lift to multi-modal model design; distributed systems' provenance lifts to AI-to-AI protocol.

The clinical curriculum was the first place this architecture got stress-tested in production at high stakes. The architecture lives one level up. The instantiations are not yet written.

---

A standalone companion to the Compressed Medicine curriculum. Related: The Receiver Is the Codec · The Algebra of Thought.