concept
active
concept:modelmodel
A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
Neighborhood — ranked by edge-count
Thinkers (2)
thinker
- W. Ross Ashbystudies
- Roger C. Conantstudies
Claims (1)
claim
- Assertion in the abstract that models are pervasive in controlling complex dynamics, setting the motivation for the theorem.
Concepts (4)
concept
- Language Modelrelated_toPrimary test domain for manifold steering, including reasoning and ICL tasks
- Language Modelsrelated_toPrimary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
- Toy Modelsrelated_to
- systemassociated_withThe regulated entity or process; includes air traffic, endocrine balances, money flows.
Findings (1)
finding
- The central mathematical theorem proved/expounded in the chapter.
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.
- A model deliberately trained to exhibit alignment-relevant properties so researchers can study them with ground truth.
- Probability of data under the model, penalizing complexity and rewarding accuracy.
- Comparing models using log-evidence approximated by free energy.
- Technique for modifying model knowledge or behavior via targeted interventions, e.g., ROME by Meng et al.
- Edits MLP weights for all layers to modify model behavior; used by Abdelnabi & Salem to decrease verbalized evaluation awareness.
- Anonymous instruction-tuned LLM used in E1 ambiguous anchor test.
- Theme issue context: relates to internal models of environment, central to consciousness and cognition across substrates.