The paper explores the link between understanding and compression, arguing that while compression is a useful proxy for robust competence, it is not identical to comprehension. It proposes that true understanding involves a mental model of relational structure that enables prediction, and that this predictive ability underlies compression. The authors further suggest that human understanding is shaped by the need for demonstrability and transmissibility, leading to a preference for principled simplicity.
arXiv:2607. 12634v1 Announce Type: new Abstract: This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse.
This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse. We argue that cognitive, biological, computational, and organizational systems achieve scalable intelligence by decomposing complex phenomena into reusable atomic units that can be recombined into higher-order structures.
arXiv:2607. 18433v1 Announce Type: cross Abstract: Intelligence appears under different names in different fields: as data compression in statistics and machine learning, as universal computation in dynamical systems, and as adaptive behavior in agents.
arXiv:2607. 09705v1 Announce Type: cross Abstract: Since 2023, computer scientists have warned against model collapse -- the contamination of training sets with AI-generated outputs that progressively degrade model performance.
arXiv:2607. 05168v1 Announce Type: new Abstract: Why do intelligent systems need to perform explicit symbolic reasoning?
arXiv:2607. 17800v1 Announce Type: new Abstract: Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization.
arXiv:2606. 26523v1 Announce Type: new Abstract: We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
arXiv:2606. 07303v1 Announce Type: new Abstract: Representation learning is central to modern machine learning, enabling transitions from handcrafted features to learned embeddings, latent spaces, foundation models, world models, and digital twins.
arXiv:2608. 03921v2 Announce Type: replace Abstract: This paper offers a new interpretation of the Transformer during inference.
arXiv:2605. 08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components.
arXiv:2606. 06533v1 Announce Type: new Abstract: What would it mean to have a scientific understanding of AI?
arXiv:2603. 01568v2 Announce Type: replace Abstract: Efficient coding theory predicts that biological perceptual systems compress sensory input optimally under resource constraints, with the systematic structure of errors reflecting the geometry of that compression.