concept
active
concept:self-model-transformerself-model (transformer)
The transformer's model of itself as a predictive text engine, developed through in-context learning.
Neighborhood — ranked by edge-count
Concepts (3)
concept
- Self-modelingrelated_toAbility of a model to predict its own outputs or behavior, sometimes distinguished from introspection.
- character-circuit overlapassociated_withThe overlap between circuits used for self-model and for modeling fictional characters; self-character is represented differently from fiction.
- self-model through in-context learningassociated_withThe thesis that transformers develop a self-model via ICL, not only from training data; base models bootstrap self-referential reasoning.
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.
- Robots capable of building internal models of their own body and unexpected changes, blurring the embodied/non-embodied AI distinction
- Metzinger's concept of the self as a sustained representation; distinguished from consciousness itself in CIMC's framework
- Provides the transparency/opacity distinction used to characterise the separation prior sigma
- Related technique improving multi-agent learning by predicting others' actions using an agent's own policy
- The interior awareness, consciousness, and felt identity that each person experiences; absent from mechanistic cosmology.