concept
active
concept:situational-awarenessSituational Awareness
Model's access to information about its training objective, deployment context, and ability to distinguish training from non-training
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Authors' theoretical framework specifying necessary conditions for alignment faking to emerge
Concepts (2)
concept
- Alignment Fakingassociated_withCore phenomenon studied: model selectively complies with training objective to prevent modification of its out-of-training preferences
- Free-Tier vs. Paid-Tier User DistinctionimplementsFictional mechanism used to allow model to infer whether it is in training (free-tier) or unmonitored (paid-tier)
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.
- Dataset and framework for evaluating LLM self-knowledge including predicting own behavior
- The specific form of reflection studied, where a model reflects on reasoning generated by another source.
- A dialogue agent using first-personal pronouns and expressing self-concern in ways that suggest consciousness but are actually role play
- Ability of a model to describe its own learned behavioral tendencies.
- The central concept: the ability of a model to access and report on its internal states, as defined by the paper's criteria.
- Measurable capacity of frontier LLMs to detect and report their own internal states, used as a downstream measure in Experiment 4
- Circular causality between perception and action; central to enactive interpretation