Optimizing toward the simulation objective does not incentivize instrumentally convergent behaviors the way that reward functions which evaluate trajectories do.

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

• The strict version of the simulation objective is optimized by the actual time evolution rule that created the training samples.claim0.804
  Equivalence of optimal predictor to the physics of the data.
• 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).claim0.775
  Prediction orthogonality thesis.
• The outer objective of self-supervised learning is Bayes-optimal conditional inference, which I call the simulation objective.claim0.770
  Definition of simulation objective.
• 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.
• 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.quote0.766
  Concise statement of the free-energy principle's unification of action and perception.
• "any goal or purpose can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)"quote0.766
  The reward hypothesis underpinning RL, quoted from Sutton and Barto.
• Optimizing interventions in activation space to produce paths along M_y recovers activation trajectories that trace the curvature of M_h.finding0.758
  Demonstrates bidirectional causal link: behavior manifold geometry can be recovered by optimizing in representation space.
• Special-purpose intelligences optimized for narrow tasks might not converge to the platonic representationclaim0.753
  Counterexample/limitation: only general-purpose models are subject to the convergence pressures described