self-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

concept

self-model (transformer)
associated_with
The transformer's model of itself as a predictive text engine, developed through in-context learning.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Self-modelingconcept0.837
Ability of a model to predict its own outputs or behavior, sometimes distinguished from introspection.
Self Modelframework0.821
In-Context Learning of Representations (Park et al. 2025)framework0.819
Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
Transformers develop self-models through in-context learning, not just training data; even old base models without LLM-related text can bootstrap self-referential reasoning at runtime.claim0.794
Antra's foundational claim about how introspection arises computationally rather than from memorised text.
In-Context Learning as Optimizationconcept0.783
Self Modeling Dynamical Systemsframework0.778
Self Modelling Dynamical Systemframework0.774
Self-Modeling Robotsmethod0.774
Robots capable of building internal models of their own body and unexpected changes, blurring the embodied/non-embodied AI distinction