Theory-Derived Indicator Method

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

• The theory-derived indicator method provides a tractable way to reduce uncertainty about AI consciousness by deriving indicators from computational functionalist theories.claim0.820
  Central methodological claim of the paper
• Theory-heavy approachmethod0.745
  Assessing consciousness by evaluating whether AI systems perform functions similar to those associated with consciousness by scientific theories.
• Empathic Observation Methodconcept0.734
  The technique of discovering essential centers by imaginatively inhabiting a culture and using one's own feelings as a measuring instrument
• Indicators are merely intended to be credence-shifting; we do not need to be certain that a theory is correct for it to provide useful indicators.claim0.734
  Key epistemic stance of the Bayesian approach to indicators
• Applying theories to AI through the indicator method may reveal hidden ambiguities or unintended implications, motivating advocates to clarify their views.claim0.732
  Argues for productive bidirectional interaction between AI research and consciousness science
• Marker Methodmethod0.729
  Method for assessing consciousness in nonhuman animals by identifying behavioral/anatomical markers from humans and extrapolating; proposed adaptation for AI.
• Cartesian Method of Scientific Observationframework0.725
  The dominant scientific paradigm Alexander seeks to supplement: observation of limited machine-like events from an external, self-excluded standpoint
• Positive Indicatorsconcept0.723
  Properties of a system that should increase credence that the system is conscious