claim

active

claim:generative-models-function-as-control-systems-that-guide-adaptive-action-policy-selection

Generative models function as control systems that guide adaptive action policy selection

Core claim: generative models regulate organism behavior to maintain phenotypic bounds, not represent external world

Source paper

extracted_from

(2020) · Maxwell J. D. Ramstead · Michael D. Kirchhoff · Karl J. Friston

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Latent capacity, representation, and internal models
members_of
Studies of how neural systems (biological and AI) encode implicit environmental models and adaptive capacities that may be gated or hidden from observable behavior.
Generative models as active control
members_of
Argues generative models guide action selection rather than encode structural world representations in brain states

concept

Generative Model
about
Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.
Good Regulator Theorem (Ashby)
supports
Control-theoretic principle: regulator must be isomorphic to system regulated; applied to generative models as control

question

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.

Generative models are entailed by adaptive behavior, not explicitly encoded in brain statesclaim0.831
Distinction from Bayesian brain: generative model is consequence of dynamics, not neural representation
Generative Model Fitting to AI Behaviormethod0.801
Proposed future method: fit active inference generative models to AI behavior to verify wise world model internalization
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.769
Opening sentence defining self-evidencing.
Park et al. 2023: Generative agents — interactive simulacra of human behaviorconcept0.766
Paper on LLM-based simulacra of human behaviour; cited as ref 3
How do biological organisms evolve their generative model to account for new sensory observations?question0.759
Structure learning challenge in Discussion.
Models are being used ubiquitously for the control of complex dynamic systems.claim0.755
Assertion in the abstract that models are pervasive in controlling complex dynamics, setting the motivation for the theorem.
What is the generative model that best explains observable data from a behaving agent?question0.754
Central challenge for active inference stated in Discussion.
Today, as a step towards the control of complex dynamic systems, models are being used ubiquitously.quote0.746
Opening sentence of the abstract, stating the prevalence of modeling.