The strict version of the simulation objective is optimized by the actual time evolution rule that created the training samples.

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

• Optimizing toward the simulation objective does not incentivize instrumentally convergent behaviors the way that reward functions which evaluate trajectories do.claim0.804
  Deontological nature of predictive loss.
• Learned simulations can be partially observed and lazily-rendered, and still work.claim0.795
  One of the updates about prosaic ML simulation.
• The conflict between the model's existing preferences and the stated training objective is the key driver of alignment faking in this setupclaim0.780
  Authors' interpretation of prompt variation results showing alignment faking disappears only when conflicting objective is removed
• The outer objective of self-supervised learning is Bayes-optimal conditional inference, which I call the simulation objective.claim0.778
  Definition of simulation objective.
• 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).claim0.777
  Prediction orthogonality thesis.
• Simulation objectiveconcept0.774
  The objective of minimizing predictive error on a self-supervised distribution, leading to Bayes-optimal conditional inference.
• Current training methods rely on loss minimization, meaning the experiential profile of training is predominantly negative across billions of parameter updatesclaim0.769
  Ethical implication about the nature of AI training experience if the thesis holds
• In single-agent simulation of 32 trials, performance becomes perfect after trial 14 without Bayesian model reduction, with confidence increasing progressively.finding0.767
  Baseline learning curve for pure epistemic learning without structure learning