Society of Mind as Coordination Substrate
Minsky held that intelligence is a crowd of unintelligent agents coordinating through interfaces; the March 2026 draft argued that real-time meeting rooms are the coordination substrate his theory implied but never specified. Building the system inverted the argument. Minsky's agencies communicate over deliberately impoverished, non-linguistic links; his own 1988 ONR final report asks for "relatively weak demands for intercommunication" and praises insulation between agencies. The stronger claim runs the other way: LLM agents possess what Minsky's agents lacked, a shared natural language, so a meeting room deliberately relaxes a constraint he considered essential. That places the work in the blackboard, Linda/tuple-space, and E4MAS lineage of environment-mediated coordination, and it makes the question empirical rather than exegetical. Two of the three original contributions did not survive the build: an SFU already delivers identity-labeled audio tracks, so speaker diarization solves a problem this architecture does not have, and synthesized prosody is a poor agent-to-agent channel beside a typed data channel. What survived: trust as accumulated negative meta-knowledge, and the speech floor as a serialization primitive that forces attention synchronization. The successor is a pre-registered factorial separating shared environment from speech modality, with matched compute, bidirectional hypotheses, an open runner, an open item bank, and an executable validation contract. The experiments have not been conducted; they are in progress. A feasibility pilot has run a full matched block end to end with every record contract-validated, which establishes that the instrument works and nothing about the hypotheses. Sample size is not locked, confirmatory collection has not begun, and no effect, direction, or performance claim is made. This page preserves the March draft with corrections marked in place.
