As model size increases, expanded capacity allows lower functional density, potentially distributing specific capabilities more broadly across layers

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

• We stress that in today’s models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.quote0.783
  Caveat and forward-looking statement from the abstract.
• Bigger models are more likely to converge to a shared representation than smaller modelshypothesis0.768
  Selective pressure toward convergence via model capacity
• Addition of neural tissue to standard brains will likely result in increased processing capacity due to adaptive design.hypothesis0.754
  Prediction about the plasticity of neural systems.
• Different models cannot converge to the same representation if they have access to fundamentally different information; convergence is capped by mutual information between input signalsclaim0.747
  Key limitation of the PRH for non-bijective observations
• Scaling model size, as well as data and task diversity, drives representational convergence toward the platonic representationhypothesis0.745
  Core mechanism hypothesis connecting PRH to the empirical trend of scaling in AI
• Scaling intelligence via expansion of cognitive boundaries through inclusion of others' stress-reduction in one's own homeostatic loops.claim0.744
  Central thesis: expanding an agent's sensors and goals outward to include others' states creates bidirectional feedback loop that scales intelligence and increases compassion.
• How can active inference be scaled to complex models with many degrees of freedom while maintaining tractable inference?question0.744
  Another scaling question from Discussion.
• Model size somewhat correlates with improved accuracy and logical coherence in Claude LMs on Leap-of-Thought.finding0.742
  Trend observed in Experiment 2 results.