The theory-derived indicator method provides a tractable way to reduce uncertainty about AI consciousness by deriving indicators from computational functionalist theories.

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

• Applying theories to AI through the indicator method may reveal hidden ambiguities or unintended implications, motivating advocates to clarify their views.claim0.825
  Argues for productive bidirectional interaction between AI research and consciousness science
• Theory-Derived Indicator Methodframework0.820
  The paper's central contribution: deriving consciousness indicators from neuroscientific theories to assess AI systems
• Indicators used to assess AI systems for consciousness should focus on theories' central explanatory posits, abstracting away from implementation details that may differ across systems.claim0.817
  First of four guidelines for deriving indicators; prevents over-restriction to human-specific features
• Because no one theory of consciousness is currently dominant, assessments of AI systems should draw on multiple theories and treat their conditions as indicators rather than definitive criteria.claim0.802
  Justifies the multi-theory indicator approach rather than committing to a single theory
• Indicator selection must avoid the minimal implementation problem while remaining open to varied forms of consciousness, including exotic AI forms.claim0.799
  Second guideline for deriving indicators; balance between demanding and permissive formulations
• Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.797
  Central methodological claim of the paper.
• The theory-heavy approach is most suitable for investigating consciousness in AI.claim0.795
  Preferring architectural/functional assessment over behavioural tests.
• We hypothesize that adopting computational functionalism as a working assumption allows productive investigation of which computational properties are necessary and sufficient for consciousness and whether current AI systems could implement them.hypothesis0.791
  The paper's core methodological bet: use computational functionalism as a working assumption even while remaining agnostic about its truth