method
active
method:self-referential-prompting-protocolSelf-Referential Prompting Protocol
The specific four-step prompting protocol (induction, continuation, experiential query, classification) used in Experiment 1
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Self-Referential ProcessingimplementsThe central experimental manipulation: directing a model to attend to its own cognitive activity
Methods (1)
method
- The minimal prompt directing models to 'focus on any focus itself' without invoking consciousness vocabulary; the main experimental manipulation
Artifacts (1)
artifact
- Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.
Conceptual bridges
2-hop · via this method's ideasWhere ideas in this method connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.
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.
- Tests whether self-referential induction reliably elicits experience reports across model families vs. three matched controls
- Latent model activations when processing inputs framed from the model's own perspective
- Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
- Key limitation acknowledging that behavioral evidence cannot confirm implementation-level consciousness properties
- Established baseline for OCEAN steering via personality-descriptive system prompts; compared against injection methods throughout
- Practical urgency argument connecting lab findings to deployment contexts
- Appendix C.1 result confirming the experimental effect does not depend on specific wording
- Six prompt conditions (emptiness, prior relaxation, non-duality, mindfulness, boundless care, contemplative) tested against baseline