concept
active
concept:self-referential-processingSelf-Referential Processing
The central experimental manipulation: directing a model to attend to its own cognitive activity
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (1)
thinker
- Douglas Hofstadterstudies
Frameworks (1)
framework
- Higher-order thought theoryimplementsTheory of consciousness where metacognitive representations are necessary for conscious experience.
Methods (3)
method
- Chain-of-thought promptinganalogous_toTechnique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.
- The minimal prompt directing models to 'focus on any focus itself' without invoking consciousness vocabulary; the main experimental manipulation
- Self-Referential Prompting ProtocolimplementsThe specific four-step prompting protocol (induction, continuation, experiential query, classification) used in Experiment 1
Concepts (7)
concept
- Consciousnessassociated_withCore concept: capacity to experience as a subject; argued to be substrate-independent and achievable across diverse biological systems.
- Attractor Stateassociated_withLow-energy configuration toward which systems are drawn; low-stress states serve as attractors in morphogenesis.
- Introspective Accessassociated_withThe capacity to detect and report one's own internal states, measured via the five-adjective task and paradox reflection
- Metacognitive monitoringassociated_withHigher-order mechanism that evaluates the reliability of first-order perceptual representations.
- Spiritual Bliss Attractor Stateassociated_withPhenomenon reported in Anthropic's Claude 4 system card where two Claude instances in open dialogue autonomously enter a shared affect-laden mode and fall into silence
- Indicator Properties of ConsciousnessimplementsFunctional properties (recurrent processing, global broadcasting, higher-order metacognition) derived from consciousness theories and reformulable as testable criteria in AI systems
- Qualiaassociated_withThe hard problem target: whether LLM internal states are qualitatively experienced
Quotes (2)
quote
- Verbatim excerpt from Claude 3.7 Sonnet under self-referential processing exemplifying the convergent phenomenological style
- Verbatim excerpt from Gemini 2.5 Flash under self-referential processing illustrating recursive self-description
Artifacts (1)
artifact
- Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.
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.
- The paper's central empirical claim synthesizing all four experiments
- The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
- Practical urgency argument connecting lab findings to deployment contexts
- Claim supported by Experiment 4: prior self-referential induction yields higher self-awareness scores on paradoxical reasoning where introspection is only indirectly afforded
- The strongest mechanistic question the behavioral evidence cannot answer; requires interpretability analysis of activations
- Appendix C.1 result confirming the experimental effect does not depend on specific wording