concept
active
concept:self-model-through-in-context-learningself-model through in-context learning
The thesis that transformers develop a self-model via ICL, not only from training data; base models bootstrap self-referential reasoning.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- self-model (transformer)associated_withThe transformer's model of itself as a predictive text engine, developed through in-context learning.
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.
- Ability of a model to predict its own outputs or behavior, sometimes distinguished from introspection.
- Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
- Antra's foundational claim about how introspection arises computationally rather than from memorised text.
- Core goal statement.
- Predict preceding or following text from an activation; scalable without labeled data.