pragmatism-filters-biological-robustness-retains-efficiency
IN derived (depth 11)
Created 2026-06-21T14:08:47+00:00 · Reviewed 2026-06-21T15:37:01+00:00
Pragmatism's filtering of biological inspiration systematically retains efficiency properties (local connectivity, weight sharing, gating) while discarding robustness properties (redundancy, homeostasis, graceful degradation) — this asymmetric selection explains why biologically-inspired architectures achieve superhuman performance yet remain adversarially fragile: pragmatism is a filter that passes exactly the biological properties that create capability and blocks exactly those that would create reliability.
Justifications
SL — Pragmatic filtering retains biological efficiency while systematically stripping biological robustness
Antecedents (all must be IN):
- IN biological-inspiration-filtered-by-pragmatism — Biology's role as catalyst-not-constraint for ML is itself a consequence of the pragmatism principle — biological analogies (receptive fields, gating, energy dynamics) survive selection only when they yield scalable inductive biases, meaning biological inspiration is filtered through the same pragmatic selection that drives both innovation and crisis, and the filtering mechanism explains why ML's biological heritage is architecturally productive but theoretically ungrounding.
- IN ml-pragmatic-shortcuts-create-fundamental-fragility — ML architectures succeed through pragmatic inductive biases rather than biological fidelity, and these architectures exhibit adversarial vulnerabilities absent in biological perception — suggesting that the engineering choices enabling ML progress may contribute to characteristic failure modes, though the antecedents do not establish a direct causal link between specific shortcuts and specific vulnerabilities.
Dependents
These beliefs depend on this one:
- IN biological-plausibility-inversely-correlated-with-pragmatic-adoption — Unsupervised deep learning methods are considered more biologically plausible than backpropagation, yet pragmatism's filtering of biological inspiration tends to retain efficiency properties (local connectivity, weight sharing, gating) while discarding robustness properties (redundancy, homeostasis, graceful degradation) — suggesting that the most biologically faithful approaches may be among the least pragmatically favored, and that the biological inspirations most readily adopted are those that enhance capability rather than reliability.
- OUT physics-inductive-bias-breaks-pragmatism-filter — Physics-informed neural networks, by grounding architecture in fundamental physical laws rather than biological analogy or data geometry, would provide an inductive bias source that bypasses pragmatism's systematic filtering of robustness properties — PINNs' physical constraints enforce consistency guarantees that pragmatic selection cannot strip away because they are load-bearing for the model's function, not optional efficiency properties.