framework
active
framework:indicator-properties-for-ai-consciousness-butlin-et-alIndicator properties for AI consciousness (Butlin et al.)
Framework of indicators the J-space is checked against.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Verbalizable Representations Form a Global Workspace in Language Modelsintroducesmentions
Frameworks (1)
framework
- Theory of consciousness involving a global workspace for information.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Functional properties (recurrent processing, global broadcasting, higher-order metacognition) derived from consciousness theories and reformulable as testable criteria in AI systems
- First of four guidelines for deriving indicators; prevents over-restriction to human-specific features
- Building AI systems with more indicator properties will increase the likelihood of consciousness.hypothesis0.839Guiding hypothesis of the rubric.
- Properties that increase or decrease credence that an AI system is conscious; central concept of the paper's method
- Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.835Central methodological claim of the paper.
- AI systems which possess more of the indicator properties are more likely to be conscious.claim0.835Graded claim about the rubric.
- Many of the indicator properties can be implemented in AI systems using current techniques.claim0.821Feasibility demonstrated in Section 3.1.
- Justifies the multi-theory indicator approach rather than committing to a single theory