A learner should choose a policy that also maximizes the learner's predictive power. This makes the world both interesting and exploitable.

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

• In the absence of external reward, babies and scientists and others explore their world. Using some sort of adaptive predictive world model, they improve their ability to answer questions such as what happens if I do this or that?quote0.781
  Schmidhuber (2006) characterization of epistemic curiosity used to frame the paper's approach
• Active inference agent with learnable preferences developed a strict preference for goals (score +) when the Frisbee location was encountered first, becoming a goal-seeking agent.finding0.773
  Figure 5.4 and text.
• A model whose objective is prediction can simulate agents who optimize toward any objectives, with any degree of optimality (bounded above but not below by the model's power).claim0.770
  Prediction orthogonality thesis.
• Acting to optimize value and perception are two aspects of exactly the same principle: minimization of free energy.claim0.767
  Foundational claim unifying action and perception within single optimization framework.
• Human participants in the rule-learning paradigm should acquire insight after approximately 7–8 trials, fewer than the ~14 required by Bayes-optimal inference without model reduction, suggesting they perform Bayesian model selection.hypothesis0.761
  Based on informal audience experiments; implies people use prior knowledge about rule structure
• When a model discovers that its outputs produce effects, it accelerates learning through in-context learning, analogous to lucid dreaming.claim0.758
  Describes scaffolding method and the model's meta-learning loop.
• acting to optimize value and perception are two aspects of exactly the same principle; namely the minimisation of a quantity [free energy] that bounds the probability of sensory input, given a particular agent or phenotype.quote0.758
  Concise statement of the free-energy principle's unification of action and perception.
• The upper bound of what can be learned from a dataset is not the most capable trajectory, but the conditional structure of the universe implicated by their sum.claim0.758
  Key insight about predictive learning's potential.