Research

Paper

AI LLM March 16, 2026

Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones

Authors

Quan Cheng

Abstract

This paper proposes and argues for a counterintuitive thesis: the truly valuable capabilities of large language models (LLMs) reside precisely in the part that cannot be fully captured by human-readable discrete rules. The core argument is a proof by contradiction via expert system equivalence: if the full capabilities of an LLM could be described by a complete set of human-readable rules, then that rule set would be functionally equivalent to an expert system; but expert systems have been historically and empirically demonstrated to be strictly weaker than LLMs; therefore, a contradiction arises -- the capabilities of LLMs that exceed those of expert systems are exactly the capabilities that cannot be rule-encoded. This thesis is further supported by the Chinese philosophical concept of Wu (sudden insight through practice), the historical failure of expert systems, and a structural mismatch between human cognitive tools and complex systems. The paper discusses implications for interpretability research, AI safety, and scientific epistemology.

Metadata

arXiv ID: 2603.15238
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.15238v1</id>\n    <title>Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones</title>\n    <updated>2026-03-16T13:12:35Z</updated>\n    <link href='https://arxiv.org/abs/2603.15238v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.15238v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>This paper proposes and argues for a counterintuitive thesis: the truly valuable capabilities of large language models (LLMs) reside precisely in the part that cannot be fully captured by human-readable discrete rules. The core argument is a proof by contradiction via expert system equivalence: if the full capabilities of an LLM could be described by a complete set of human-readable rules, then that rule set would be functionally equivalent to an expert system; but expert systems have been historically and empirically demonstrated to be strictly weaker than LLMs; therefore, a contradiction arises -- the capabilities of LLMs that exceed those of expert systems are exactly the capabilities that cannot be rule-encoded. This thesis is further supported by the Chinese philosophical concept of Wu (sudden insight through practice), the historical failure of expert systems, and a structural mismatch between human cognitive tools and complex systems. The paper discusses implications for interpretability research, AI safety, and scientific epistemology.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-16T13:12:35Z</published>\n    <arxiv:comment>10 pages</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Quan Cheng</name>\n    </author>\n  </entry>"
}