Back to search

Article

Why Compression Creates Intelligence: The Architecture of Experience in Large Models

2025-11-13

Abstract excerpt

Large Transformer models trained on diverse human outputs exhibit reasoning, contextual understanding, and self-correction—behaviors that appear to reach the level of human experience. We show these patterns are not contingent emergence but a consequence of compression necessity. Building on information-theoretic results and PAC-Bayes analysis, we prove that when a model is trained under standard conditions—weight...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
3fc2f850-b130-5436-95c0-79a9103d83b0
DOI
10.20944/preprints202511.0952.v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Why Compression Creates Intelligence: The Architecture of Experience in Large ModelsDOI 10.20944/preprints202511.0952.v1
Source-Modeling as Compression: Architectural Necessity of Experiential Patterns in Large TransformersSemantic proximity
Hallucination as an Inevitable Byproduct of Intelligence in Large Language ModelsSemantic proximity
WITHDRAWN: The Physics of Thought: Reasoning as Thermodynamic Relaxation in Generative ModelsSemantic proximity
Talking to Blackbox: Explainability Through P+NP=1Semantic proximity
A Research Programme for Continual and Neurosymbolic Learning in Epistemic Artificial IntelligenceSemantic proximity
From Dennett to Transformers: Emergent Properties, Kolmogorov Complexity, and the Turing-Computability of Human IntelligenceSemantic proximity
Excess Capacity LearningSemantic proximity
CogNGen: Constructing the kernel of a hyperdimensional predictive processing cognitive architectureSemantic proximity
Wisdom as Direction: A Symbolic Framework for Evolution Under ComplexitySemantic proximity
Quantifying Entropy Collapse in Recursively Trained AI Systems: A Framework for Variance Injection and Stagnation ThresholdsSemantic proximity
Optimal forgetting: Semantic compression of episodic memoriesSemantic proximity
Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future DirectionsSemantic proximity
Select a neighboring publication to make it the new centre.