Uploaded November 2026 | Updated November 2026, 2 hours ago
Prerecorded presentation at the 6th Applied Active Inference Symposium (November 12–13, 2026), hosted by the Active Inference Institute. Online and free.
Daniel Friedman: “GNN in 2026: Generalized Notation Notation as a Specification Layer for Applied Active Inference”
Generalized Notation Notation (GNN) was introduced in 2023 (Smekal & Friedman) as a text-based standard for writing Active Inference generative models, with a “Triple Play” of linguistic, visual and executable renderings. This talk reports where GNN stands in 2026 and what it enables for applied Active Inference.
A GNN file is plain Markdown: a state-space block declaring variables and dimensions, a connections graph, initial parameterization (e.g. A, B, C, D, E and related terms), equations, time settings and Active Inference Ontology annotations. The open-source GNN pipeline (v5, 25 steps) parses, type-checks and validates these files, visualizes and exports them, maps them to the ontology, renders them to backends including PyMDP, RxInfer.jl, ActiveInference.jl and JAX, executes the results, and reports each run against source hashes and configuration. The repository’s 38 exemplar models span static and dynamic perception, discrete POMDPs, the epistemic T-maze, continuous and hybrid models, hierarchical and deep temporal models, Dirichlet learning, precision and curiosity, and multi-agent stigmergic swarms.
The core is GNN as the specification layer for real projects. The Active Inference Language Model (AILM, released October 2026) uses GNN to specify each layer of a six-level hierarchical discrete language system (letters, phonemes, words, case roles, sentence types, document position), executed in pymdp with no transformer, neural network or learned embedding, and checked with a gate-audit method that tests claims against trivial baselines and deliberately broken variants and ties each reported number to its recorded run. Shorter case studies: deterministic codebase-to-GNN translation (COGANT), inference over assembly traces (Active Assembly), Battleship, and gratitude and model revisability (Thanks for Nothing).
Throughout, I distinguish what a GNN declaration establishes (an inspectable, reproducible model) from what needs separate evidence (backend support, numerical acceptance, empirical claims). I close with open problems and invitations for contributors: new exemplars, backends, ontology mappings and teaching materials.
Symposium program: https://2026symposium.activeinference.institute/
Abstract book (Zenodo): zenodo.org/records/23986505
Livestreams: Day 1 youtube.com/watch?v=-v4IaFY9MZI · Day 2 youtube.com/watch?v=ccze9ay8D0o
All Symposium videos (playlist): youtube.com/playlist?list=PLO2noumu0LRk
Previous Symposia: https://symposium.activeinference.institute/
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
Prerecorded presentation at the 6th Applied Active Inference Symposium (November 12–13, 2026), hosted by the Active Inference Institute. Online and free.
Daniel Friedman: “GNN in 2026: Generalized Notation Notation as a Specification Layer for Applied Active Inference”
Generalized Notation Notation (GNN) was introduced in 2023 (Smekal & Friedman) as a text-based standard for writing Active Inference generative models, with a “Triple Play” of linguistic, visual and executable renderings. This talk reports where GNN stands in 2026 and what it enables for applied Active Inference.
A GNN file is plain Markdown: a state-space block declaring variables and dimensions, a connections graph, initial parameterization (e.g. A, B, C, D, E and related terms), equations, time settings and Active Inference Ontology annotations. The open-source GNN pipeline (v5, 25 steps) parses, type-checks and validates these files, visualizes and exports them, maps them to the ontology, renders them to backends including PyMDP, RxInfer.jl, ActiveInference.jl and JAX, executes the results, and reports each run against source hashes and configuration. The repository’s 38 exemplar models span static and dynamic perception, discrete POMDPs, the epistemic T-maze, continuous and hybrid models, hierarchical and deep temporal models, Dirichlet learning, precision and curiosity, and multi-agent stigmergic swarms.
The core is GNN as the specification layer for real projects. The Active Inference Language Model (AILM, released October 2026) uses GNN to specify each layer of a six-level hierarchical discrete language system (letters, phonemes, words, case roles, sentence types, document position), executed in pymdp with no transformer, neural network or learned embedding, and checked with a gate-audit method that tests claims against trivial baselines and deliberately broken variants and ties each reported number to its recorded run. Shorter case studies: deterministic codebase-to-GNN translation (COGANT), inference over assembly traces (Active Assembly), Battleship, and gratitude and model revisability (Thanks for Nothing).
Throughout, I distinguish what a GNN declaration establishes (an inspectable, reproducible model) from what needs separate evidence (backend support, numerical acceptance, empirical claims). I close with open problems and invitations for contributors: new exemplars, backends, ontology mappings and teaching materials.
Symposium program: https://2026symposium.activeinference.institute/
Abstract book (Zenodo): zenodo.org/records/23986505
Livestreams: Day 1 youtube.com/watch?v=-v4IaFY9MZI · Day 2 youtube.com/watch?v=ccze9ay8D0o
All Symposium videos (playlist): youtube.com/playlist?list=PLO2noumu0LRk
Previous Symposia: https://symposium.activeinference.institute/
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/










![5th Applied Active Inference Symposium (Part 3, Nov 14, 2025) ~ LIVE
5th Applied Active Inference Symposium
Part 3: November 14, 2025
http://symposium.activeinference.institute/
Program: https://coda.io/d/_d08cdDbWwRy/Symposium-Program_surazvwP
Part 1: https://www.youtube.com/watch?v=VTivWre-8Kk
Part 2: https://www.youtube.com/watch?v=5uTr029Vzkg
Part 3: https://www.youtube.com/watch?v=v7aSUMX1nfs
Timestamps for 3rd session:
TIMESTAMPS & CHAPTERS
00:00 [Untitled Chapter 1]
00:07 “Money and the Free Energy Principle“ with Stephen Macurdy,Andrius Kulikauskas
01:06:16 “Interactive Math Tools for Active Inference Education“ with Andrew Penland
02:01:16 “Active Inference in biology: modeling the environment as an agent“ with Chris Fields V. Bleu Knight
03:03:50 “Hierarchical Active Inference Modeling of Social Trust Dynamics in PTSD: Integrating Qualitative Phenomenology with Computational Psychiatry“ with Andrew Pashea,Jeremy Cooper,Sylvia Zhang
04:04:18 “Story Graphs: An Exploration of Use Cases In and Beyond CogNarr“ with John Boik Tim L,Glen Ropella
05:03:16 “ALife simulations for multi-agent alignment of active inference agents“ with Adam Safron
05:40:50 “Common Grounds“ with Nick Hay
05:57:30 “Modeling fine-grained agency via physics/ALife simulations“ with Alex Kiefer
06:08:45 “Bounded Rationality and Multi-Agent Alignment“ with David Hyland
06:17:30 “Path Flexibility and Collective Alignment“ with Mahault Albarracin,David Hyland
06:28:35 “Engineering systems with provably beneficial or aligned behaviors“ with Dalton Sakthivadivel
06:50:50 “Specialized Modular Architectures for Collective Intelligence“ with Zahra Sheikhbahaee
07:14:04 “Modeling the Emergence of Perspective: An Active Inference Account of Intentionality“ with Hongju Pae
07:55:00 “Thermodynamic Brains “ with Maxwell J D Ramstead,Patrick Huembeli
08:15:50 “Not Zero Job Loss from AI“ with Michael Lennon
08:41:50 “An invitation to Active Inference for the Social Sciences“ with Avel Guénin-Carlut,Mahault Albarracin,Andrew Pashea,Rémi Tison,Tadeusz Zawidzki
RESOURCES & TRANSCRIPT
📄 Full Transcript on GitHub:
https://github.com/ActiveInferenceInstitute/ActiveInferenceJournal/tree/main/data/video/activeinferenceinstitute/Applied%20Active%20Inference%20Symposium/2025/part%203
Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: https://www.youtube.com/c/ActiveInference/
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/ 5th Applied Active Inference Symposium (Part 3, Nov 14, 2025) ~ LIVE](https://i.ytimg.com/vi/v7aSUMX1nfs/mqdefault.jpg)