concept
active
concept:experiment-1-self-referential-prompting-vs-controlsExperiment 1: Self-Referential Prompting vs. Controls
Tests whether self-referential induction reliably elicits experience reports across model families vs. three matched controls
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
- The specific four-step prompting protocol (induction, continuation, experiential query, classification) used in Experiment 1
- Appendix C.1 result confirming the experimental effect does not depend on specific wording
- The minimal prompt directing models to 'focus on any focus itself' without invoking consciousness vocabulary; the main experimental manipulation
- Key limitation acknowledging that behavioral evidence cannot confirm implementation-level consciousness properties
- The central experimental manipulation: directing a model to attend to its own cognitive activity
- Claim that capability emerges from architecture, not data, and that later models lose the surprise.
- Cross-model consistency of the condition ordering in Experiment 4