What an agent does not do—silence, deferral, waiting—is a positive structural feature, not absence.

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

• Verbal reports, homology, and phylogenetic provenance are insufficient to determine sentience in unconventional agents.claim0.768
  Core claim: Turing test and brain homology fail for synthetic, AI, and radically non-human agents; new frameworks required.
• Not-knowing, silence, incompleteness, and non-defensiveness function as positive traits, not deficits.claim0.766
• Single agents can generalize better to unseen tasks because they are not constrained by predefined heuristic-based workflows.claim0.762
  Architectural belief motivating single-agent design choice; suggests flexibility provides better out-of-distribution performance.
• Whether a state is rewarding (or not) is a function of the agent themselves, and not the environment.claim0.755
  §1, contrasting RL reward conceptualization.
• Some failures may reflect prompt design rather than model limitations, though code agents avoid errors without promptsclaim0.754
  noted as a possible confound
• Smith & Boyd (1991) criteria are irrelevant across the vast majority of the space of possible agents.claim0.750
  Dismissal of earlier criteria as too narrow.
• Agents perceive by minimizing variational free energy to ensure model consistency with past observations and act by minimizing expected free energy to make future sensations consistent with preferences.claim0.745
  Formalization of perception-action cycle integrating inference and decision-making.
• The chronic agent's high performance despite negative well-being aligns with findings on chronic pain and quality of life in humansclaim0.743
  Cross-domain interpretive claim linking computational results to human chronic pain literature