Computational research
SIML, simulation, and optimization: understanding how systems learn, adapt, and make decisions.
Explore the directionResearch
Papers, experiments, and ideas.
Read our latest work, explore the questions behind it, and find the methods and resources for a closer look.
Publications
Recent work.
Stardate SIML: A Common Beat, a Shared Reference
A galactic calendar concept with hydrogen-cycle units, a declared energy-rewind zero and reproducible synthetic experiments.
Read the studyDynamic Causal Geometry Predicts Finite-Propagation Attractor Sensitivity
An RBED study of how changing causal influence predicts the effects of delayed information in simulated recurrent networks.
Read the studyOne bit to rule the planner: SIML FEPGate + V-JEPA 2
A reported integration of a SIML surprise gate with a frozen V-JEPA 2 planner, including code, method details, and comparative results.
Read the studyResearch directions
Questions that connect our work.
Physical implementation
Building physical implementations and connecting models with measurement and experiment.
Explore the directionNew materials
Investigating material behavior, sensing, and actuation through modelling and physical research.
Explore the directionRead further
Methods and the research record.
Technical notes
Methods, commentary, and ideas behind the research.
Code and tools
Public implementations and resources from Deep SIML Labs.
SIML Codex
The philosophical foundation of our work with AI agents and networks.
Earlier publications
Historical PaperHistorical
Artificial Intelligence is for Amateurs: SIML, Free Energy Principle and Cognogenics as the Foundations Toward the Birth of True Artificial Life
An early SIML paper connecting memory-constrained agents, the Free Energy Principle, and Cognogenics.
Historical PrototypeHistorical
SIML Demo: Optimizing AI for Energy and Efficiency
The original SIML embodied-agent demonstration, retained as an artifact of the architecture’s earlier research framing.