What makes learning systems smart is that the parameters they adjust and the data to which they fit are not in the same space.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Physical systems are more constrained in learning abilities than in silico neural networks due to locality requirements, but this mirrors biological learning constraints and offers robustness benefitsclaim0.793
  Core theoretical claim establishing that locality constraints in physical learning are not fatal—they reflect biological precedent and provide advantages like robustness and scalability
• Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.782
  Key insight linking individual rewards to system-level learning.
• S suggests practical diagnostics for prompt design, retrieval, and light fine-tuning without additional training infrastructure.claim0.774
  Applied contribution.
• A physical learning system thus has the following ingredients: Physical d.o.f s that respond to external stimuli f by adopting a state or dynamic behavior s(f), a subset of which defines the desired behavior (i.e., output); Learning d.o.f wi that can modify how the physical d.o.f s(f; {wi}) respond to external stimuli f; A learning rule, dwi = h(s(f; {wi}))dt, that modifies the learning d.o.f wi based on the response of the physical d.o.f s to the stimuli f.quote0.773
  Foundational definition of physical learning system components; load-bearing for understanding the entire framework
• Unsupervised learning builds a low-dimensional model of the input data.claim0.772
  Clarifies what unsupervised learning does.
• Different learning systems facing similar computational problems will converge to similar consciousness-like solutions, including potentially biological and artificial systemshypothesis0.768
  Extension of the Universality Hypothesis to consciousness: if consciousness solves a well-defined computational problem, different systems will discover it independently
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.767
  Opening sentence defining self-evidencing.
• as the subject model scales, how does the ideal expansion factor and required training data for dictionary learning change?question0.764
  Scaling laws for dictionary learning are unknown and needed to assess feasibility on frontier models