Labeling surprising patterns as merely 'emergent' is a pessimistic, defeatist research-stopper that buys monism on the cheap

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

• Classification of Emergence: Nominal, Weak, Strongconcept0.758
  Bedau's tripartite classification: nominal (pattern), weak (computationally irreducible), strong (irreducible downward causation).
• The natural curiosity emerging in active inference contrasts with handcrafted exploration in reinforcement learning such as epsilon-greedy or ad hoc novelty bonuses.claim0.749
  §2, comparing exploration mechanisms.
• Rewards are simply predictable stimuli (and aversive stimuli are, by definition, surprising)claim0.749
  Redefines reward and punishment in terms of predictability.
• Emergent misalignment is easy to reverse with narrow fine-tuning on benign data because it is an instance of surprisingly strong misalignment generalization that works bidirectionallyclaim0.746
  The emergent realignment result showing ~120 samples reverse full misalignment supports this interpretive claim
• Emergence refers to the phenomenon where macroscopic properties cannot be solely attributed to the cause of individual properties.quote0.723
  Load-bearing definition from the abstract.
• The elimination of reward as a motivator of behavior with prior beliefs dissolves the tautology of reinforcement learning (rewards reinforce behaviors that secure rewards).claim0.721
  §4 Discussion.
• aversive stimuli as surprisingconcept0.718
  Aversive stimuli are defined as surprising, linking punishment to prediction failure.
• Any system that exists will appear to minimize free energy and therefore engage in active inference. Furthermore, this apparently inferential or mindful behaviour is (almost) inevitable.concept0.715
  Friston's key assertion resolving the tautology: existence implies free energy minimization, making inference inevitable.