What degree of concern and care should we exhibit toward the many diverse agents around us, and what criteria do we use to identify sentience, capacity for suffering, and other properties that have moral implications?

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

• Sentience assessment should seek deep invariants across possible minds, not arbitrary criteria tied to evolution on Earthclaim0.834
  Core normative claim: frameworks must identify fundamental properties of sentience independent of phylogenetic accident or familiar substrates.
• We must develop principled approaches to evaluating the sentience of (and thus, our responsibility to) beings of unfamiliar provenance and composition.claim0.828
  Call to action for new frameworks.
• How Can Humans Extend Moral Consideration And Carequestion0.825
• How do limits of care and scope of concern become defined across agents and scales?question0.821
  Paper asks whether care expands linearly with problem scale (e.g., caring about 10,000 vs. 1,000 people); hints at necessary bounds on cognitive capacity.
• Can We Extend Care And Moral Consideration Toquestion0.820
• We observe features related to a broad range of safety concerns, including deception, sycophancy, bias, and dangerous content.claim0.813
  SAEs uncover safety-relevant representations that might be monitored or controlled.
• We should err on the side of reducing false negatives with respect to sentience criteria for ethical concern.claim0.811
  Ethical precaution advocated by Levin and Crump et al.
• The criteria for concern should not require 2nd order abilities of creatures to reflect on their feelings.claim0.811
  Alignment with Crump et al. that metacognition is too high a bar.