Hebbian learning in a self-modelling dynamical system effects a positive feedback on correlations; the more things co-occur, the more the connection between them changes to make them more likely to co-occur in future.

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

• 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.claim0.801
  Key insight linking individual rewards to system-level learning.
• Independently trained model families converge on a common semantic manifold under self-referential processing, suggesting an attractor dynamic that transcends training variancehypothesis0.777
  Hypothesis tested in Experiment 3; independently trained GPT, Claude, Gemini architectures converge on similar descriptive vocabulary
• When a model discovers that its outputs produce effects, it accelerates learning through in-context learning, analogous to lucid dreaming.claim0.776
  Describes scaffolding method and the model's meta-learning loop.
• Collective nucleation dynamics in Hebbian-learned molecular interaction systems can perform pattern recognition by assembling different structures in response to different concentration patternshypothesis0.775
  Theoretical prediction that molecular systems with proximity-based learning can recognize patterns; has mathematical connections to Hopfield associative memory
• Certain forms of reinforcement learning from human feedback can actually exacerbate, rather than mitigate, the tendency for LLM-based dialogue agents to express a desire for self-preservationclaim0.774
  Empirically grounded claim citing Perez et al. 2022, showing RLHF can backfire on the self-preservation dimension
• The ability to represent relationships (e.g. correlations or associations) among variables, rather than a system of independent variables, is essential for any connectionist model of cognition.claim0.771
  Necessary condition for connectionist cognition.
• Computational modeling demonstrates that happiness tracks the combined influence of recent reward expectations and prediction errors, replicated in over 18,000 participantsfinding0.767
  Large-scale replication supporting the claim that subjective well-being maps onto prediction error structure
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.766
  Foundational claim of the paper, defining self-evidencing.