Intelligence as Useful Structure: A Thermodynamic Perspective
Abstract
Thermodynamic accounts of intelligence have advanced rapidly, but they do not yet resolve a prior definitional problem: what makes internal structure intelligent rather than merely ordered? This paper argues that any thermodynamic intelligence metric should include a usefulness filter. The numerator must track internal structure that is relevant to viability, prediction, and control, not merely raw information or benchmark score. Intelligence is therefore defined as the resource-bounded capacity of an adaptive system to acquire, compress, and deploy useful internal structure so as to improve prediction, control, and robustness across a range of environments. Capability and efficiency are separated. Capability is adaptive reach, A, defined over a reference distribution of environments or task families. Efficiency is acquisition efficiency, I_eff = Delta C_u / W_diss, where C_u denotes useful internal structure and W_diss physically dissipated work. Concretely, C_u is the predictive and control-relevant information that a system's internal state carries about viability-relevant environmental structure, making it a semantic rather than purely syntactic information term. I_eff is a learning or adaptation metric, not a complete scalar measure of deployed intelligence: trained systems at steady state may have Delta C_u = 0 while still exhibiting high adaptive reach. A toy numerical example with exact Landauer-referenced dissipation costs, explicit boundary conditions, temperature-normalised reporting conventions, and falsifiable comparisons against size-based and energy-only baselines are provided.
Related
- Magic Gate Teleportation: Structure, Useful Resource States, and Simpler Feedforward
- Approximating thermodynamic equilibrium observables of quasi one-dimensional magnetic molecules and chains by thermal DMRG - a user perspective
- From Specific Heat Bounds to Penrose-like Inequalities: A Unified Thermodynamic Perspective
- Designing sustainable high-entropy alloys directly from mixed oxides: A thermodynamic perspective
- Thermodynamic Proof of Quantumness without Structure
BibTeX
@misc{djordjevic2026intelligence,
title = {{Intelligence as Useful Structure: A Thermodynamic Perspective}},
author = {Boris Djordjevic},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14197},
eprint = {2610.14197},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14197},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Intelligence as Useful Structure: A Thermodynamic Perspective
AU - Boris Djordjevic
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.14197
UR - https://arxiv.org/abs/2610.14197
AB - Thermodynamic accounts of intelligence have advanced rapidly, but they do not yet resolve a prior definitional problem: what makes internal structure intelligent rather than merely ordered? This paper argues that any thermodynamic intelligence metric should include a usefulness filter. The numerator must track internal structure that is relevant to viability, prediction, and control, not merely raw information or benchmark score. Intelligence is therefore defined as the resource-bounded capacity of an adaptive system to acquire, compress, and deploy useful internal structure so as to improve prediction, control, and robustness across a range of environments. Capability and efficiency are separated. Capability is adaptive reach, A, defined over a reference distribution of environments or task families. Efficiency is acquisition efficiency, I_eff = Delta C_u / W_diss, where C_u denotes useful internal structure and W_diss physically dissipated work. Concretely, C_u is the predictive and control-relevant information that a system's internal state carries about viability-relevant environmental structure, making it a semantic rather than purely syntactic information term. I_eff is a learning or adaptation metric, not a complete scalar measure of deployed intelligence: trained systems at steady state may have Delta C_u = 0 while still exhibiting high adaptive reach. A toy numerical example with exact Landauer-referenced dissipation costs, explicit boundary conditions, temperature-normalised reporting conventions, and falsifiable comparisons against size-based and energy-only baselines are provided.
ER -