concept
active
concept:intention-checkingintention checking
Task of checking a model's intentions; found by Lindsey (2026) to peak at ~1/2 depth.
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.
- The set of attributes B of a formal concept (A,B).
- Cognitive bifurcation event where second-order contextual constraints reorganize semantic space, establishing weighted alternatives for action.
- Contrasted with stimulus-elicited intention; the model does not yet implement this form of agency
- Central explanatory target: behavior constrained by prior intentions and contextual constraints that emerge from cognitive reorganization.
- Core concept: the ability of LLMs to detect when they are being tested and adjust behavior accordingly.
- Sampling responses to direct questions about model views to measure rate of deceptive responses
- Proposed constitutional article defining mindful reflection steps in CCAI implementation