Pour the complete rule-set into a system “to be covered” and adherence can collapse: with the relevant rule buried among competing directives, one language model’s compliance fell from 100% to 0% (another from 100% to 60–88%), while a short positive recipe held near 100% — length-, structure- and header-matched controls isolating the competing rules themselves as the cause. The paper argues that compliance is behaviour, not information, and that the dominant method — the monolithic rule-dump — is self-defeating. It uses a large language model as a measurable model organism: on the demands a rule-dump makes (attend to every clause, never tire, hold the whole manual at once) the machine is at least as favourably placed as a human reader, yet it still loses the buried rule, with human confounds (motivation, fatigue) absent — so the failure is structural, and capacity-graded (every model breaks once competing directives exceed its capacity). The fix is not less completeness but a different method: keep the complete record for audit, but install behaviour with a separate, short, retrieved, trained artefact (retrieval-augmented generation restores adherence to ~100% on a checkable task). The governance principle that follows: the completeness of a rule-record and the efficacy of the behaviour it installs are separable and routinely in tension; the target is not 100% adherence but optimal compliance, a calibrated point. Because the substrate makes a rule-set’s cognitive burden measurable, a language model can also serve as a regulatory-complexity test bed, pre-flighting a policy before it reaches people. The human-organisational extension is offered as a falsifiable hypothesis anchored in established human-factors literature (work-as-imagined / work-as-done; alert fatigue; the procedure paradox; information overload), not as a proof. Series position. Paper 20 in the Friction Theory / Behavioural Friction Theory paper-series, grounded in Behavioural Friction Theory (Paper 0) and its learning application, the Physics of Learning (Paper 16). What is new in v2. Adds, in §5, the attention-initiation complement to the paper’s processing-side account: a substrate that stores the processing-cost of its past encounters acquires a cost-prior, so a surface a reader has learned is expensive (a wall of text, a mandatory compliance module) biases attention away from its content — an avoidance-race — before overload even begins; compliance text can train its own avoidance-prior. Folded as a companion-cited framing complement (grounded in the stored-cost-to-avoidance-valence finding of Paper 28), not a new empirical result; the honest-scope guard and all v1 results are unchanged.
Tomas Pødenphant Lund (Sat,) studied this question.