How does the individuation of AI systems affect consciousness attributions?

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

• Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.805
  Central methodological claim of the paper.
• AI systems which possess more of the indicator properties are more likely to be conscious.claim0.803
  Graded claim about the rubric.
• our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.quote0.792
  Key takeaway from abstract, amended version.
• Building AI systems with more indicator properties will increase the likelihood of consciousness.hypothesis0.786
  Guiding hypothesis of the rubric.
• Both under-attributing and over-attributing consciousness to AI carry significant risks.claim0.786
  Risk summary.
• All attributions of cognition, including sentience, are always inferred on the basis of embodied behaviours, including verbal self-report in humans.claim0.784
  Stronger version: all cognition attributions rely on observable behavior.
• Satisfying the indicators would not mean that an AI system would definitely be conscious.claim0.783
  Caveat that indicators are not conclusive proof.
• We tentatively hypothesize that if an artificial system were trained to perform the same tasks leading to consciousness formation in a human infant, the system would exhibit consciousness as well, by analogy with the Universality Hypothesis.hypothesis0.780
  Paper's uncertain extension of mechanistic interpretability universality to consciousness