The Coffee Law: Information, Reasoning and Communication Ceilings for Tool-Using Agent Collectives
M. Bhatt
Abstract
An AI safety result for multi-agent systems. Why do some agent collectives improve with more agents, more debate or a stronger model, while others do not? The productive question is which resource limits a collective, and which intervention removes that limit. The paper decomposes collective intelligence into three ceilings: information (a team cannot know more than its starting data plus what its tools can carry — talking and voting add nothing to that budget, and adding agents raises it only through more tool access), reasoning (what bounded agents can use is at most what they hold; debate and compute close the gap but never pass it, at a cost from linear to infeasible), and communication (evidence split across agents is unusable until enough is exchanged — about n/2 bits for some n-bit tasks even with unlimited computation). The decomposition explains published findings that otherwise look contradictory, yields a diagnostic for which ceiling binds, and makes predictions a single capability axis does not. Proofs are short; every finite example is verified exactly in public code.
Where it sits
Pillar 01 — Impossibility & Boundary Research
What can a defense never guarantee?
Prove where defenses cannot hold — what a control can guarantee, and which design directions are dead ends.
Outside writing
No verified independent writing about this paper yet. If you have written about it, send the link to b1oo@shrewdsecurity.io.
How outside writing is graded →