#302 Karl Friston: How the Free Energy Principle Could Rewrite AI
This episode is sponsored by AGNTCY. Unlock agents at scale with an open Internet of Agents.
Visit https://agntcy.org/ and add your support.
How could Karl Friston's Free Energy Principle become a blueprint for the future of AI?
In this episode of Eye on AI, host Craig Smith sits down with Karl Friston, the neuroscientist behind the Free Energy Principle and advisor to Verses AI, to explore how active inference and brain inspired generative models might move us beyond transformer based systems. They unpack how Axiom, Verses' new architecture, uses probabilistic beliefs and message passing to build agents that learn like brains instead of just predicting the next token.
We look at why transformers face scaling and reliability limits, how Free Energy unifies prediction, perception, and action, and what it means for an AI system to carry explicit uncertainty instead of overconfident guesses. Learn how active inference supports continual learning without catastrophic forgetting, how structure learning lets models grow and prune themselves, and why embodiment and interaction with the real world are essential for grounding language and meaning.
You will also hear how Axiom can sit beside or beneath large language models, how explicit uncertainty can reduce hallucinations in high stakes workflows, and where these ideas are already being tested in areas like logistics, robotics, and autonomous agents. By the end of the episode, you will have a clearer picture of how Karl Friston's Free Energy blueprint could reshape AI architectures, from enterprise planning systems to embodied agents that understand and act in the world.
Stay Updated: Craig Smith on X: https://x.com/craigss Eye on A.I. on X: https://x.com/EyeOn_AI
Karl Friston - Why Intelligence Can't Get Too Large (Goldilocks principle)
In this episode, hosts Tim and Keith finally realize their long-held dream of sitting down with their hero, the brilliant neuroscientist Professor Karl Friston. The conversation is a fascinating and mind-bending journey into Professor Friston's life's work, the Free Energy Principle, and what it reveals about life, intelligence, and consciousness itself.
**SPONSORS**
Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal - https://github.com/google-gemini/gemini-cli
---
Take the Prolific human data survey - https://www.prolific.com/humandatasurvey?utm_source=mlst and be the first to see the results and benchmark their practices against the wider community!
---
cyber•Fund https://cyber.fund/?utm_source=mlst is a founder-led investment firm accelerating the cybernetic economy
Oct SF conference - https://dagihouse.com/?utm_source=mlst - Joscha Bach keynoting(!) + OAI, Anthropic, NVDA,++
Hiring a SF VC Principal: https://talent.cyber.fund/companies/cyber-fund-2/jobs/57674170-ai-investment-principal#content?utm_source=mlst
Submit investment deck: https://cyber.fund/contact?utm_source=mlst
***
They kick things off by looking back on the 20-year journey of the Free Energy Principle. Professor Friston explains it as a fundamental rule for survival: all living things, from a single cell to a human being, are constantly trying to make sense of the world and reduce unpredictability. It’s this drive to minimize surprise that allows things to exist and maintain their structure.
This leads to a bigger question: What does it truly mean to be "intelligent"? The group debates whether intelligence is everywhere, even in a virus or a plant, or if it requires a certain level of complexity.
Professor Friston introduces the idea of different "kinds" of things, suggesting that creatures like us, who can model themselves and think about the future, possess a unique and "strange" kind of agency that sets us apart.
From intelligence, the discussion naturally flows to the even trickier concept of consciousness. Is it the same as intelligence? Professor Friston argues they are different. He explains that consciousness might emerge from deep, layered self-awareness—not just acting, but understanding that you are the one causing your actions and thinking about your place in the world.
They also explore intelligence at different sizes. Is a corporation intelligent? What about the entire planet? Professor Friston suggests there might be a "Goldilocks zone" for intelligence. It doesn't seem to exist at the super-tiny atomic level or at the massive scale of planets and solar systems, but thrives in the complex middle-ground where we live.
Finally, they tackle one of the most pressing topics of our time: Can we build a truly conscious AI? Professor Friston shares his doubts about whether our current computers are capable of a feat like that. He suggests that genuine consciousness might require a different kind of "mortal" computation, where the machine's physical body and its "mind" are inseparable, much like in biological creatures.
TRANSCRIPT:
https://app.rescript.info/public/share/FZkF8BO7HMt9aFfu2_q69WGT_ZbYZ1VVkC6RtU3eeOI
TOC:
00:00:00: Introduction & Retrospective on the Free Energy Principle
00:09:34: Strange Particles, Agency, and Consciousness
00:37:45: The Scale of Intelligence: From Viruses to the Biosphere
01:01:35: Modelling, Boundaries, and Practical Application
01:21:12: Conclusion
DOES AI HAVE AGENCY? With Professor. Karl Friston and Riddhi J. Pitliya
Watch behind the scenes, get early access and join the private Discord by supporting us on Patreon:
https://patreon.com/mlst (public discord)
https://discord.gg/aNPkGUQtc5
https://twitter.com/MLStreetTalk
DOES AI HAVE AGENCY? With Professor. Karl Friston and Riddhi J. Pitliya
Agency in the context of cognitive science, particularly when considering the free energy principle, extends beyond just human decision-making and autonomy. It encompasses a broader understanding of how all living systems, including non-human entities, interact with their environment to maintain their existence by minimising sensory surprise.
According to the free energy principle, living organisms strive to minimize the difference between their predicted states and the actual sensory inputs they receive. This principle suggests that agency arises as a natural consequence of this process, particularly when organisms appear to plan ahead many steps in the future.
Riddhi J. Pitliya is based in the computational psychopathology lab doing her Ph.D at the University of Oxford and works with Professor Karl Friston at VERSES.
https://twitter.com/RiddhiJP
References:
THE FREE ENERGY PRINCIPLE—A PRECIS [Ramstead]
https://www.dialecticalsystems.eu/contributions/the-free-energy-principle-a-precis/
Active Inference: The Free Energy Principle in Mind, Brain, and Behavior [Thomas Parr, Giovanni Pezzulo, Karl J. Friston]
https://direct.mit.edu/books/oa-monograph/5299/Active-InferenceThe-Free-Energy-Principle-in-Mind
The beauty of collective intelligence, explained by a developmental biologist | Michael Levin
https://www.youtube.com/watch?v=U93x9AWeuOA
Growing Neural Cellular Automata
https://distill.pub/2020/growing-ca
Carcinisation
https://en.wikipedia.org/wiki/Carcinisation
Prof. KENNETH STANLEY - Why Greatness Cannot Be Planned
https://www.youtube.com/watch?v=lhYGXYeMq_E
On Defining Artificial Intelligence [Pei Wang]
https://sciendo.com/article/10.2478/jagi-2019-0002
Why? The Purpose of the Universe [Goff]
https://amzn.to/4aEqpfm
Umwelt
https://en.wikipedia.org/wiki/Umwelt
An Immense World: How Animal Senses Reveal the Hidden Realms [Yong]
https://amzn.to/3tzzTb7
What's it like to be a bat [Nagal]
https://www.sas.upenn.edu/~cavitch/pdf-library/Nagel_Bat.pdf
COUNTERFEIT PEOPLE. DANIEL DENNETT. (SPECIAL EDITION)
https://www.youtube.com/watch?v=axJtywd9Tbo
We live in the infosphere [FLORIDI]
https://www.youtube.com/watch?v=YLNGvvgq3eg
Mark Zuckerberg: First Interview in the Metaverse | Lex Fridman Podcast #398
https://www.youtube.com/watch?v=MVYrJJNdrEg
Black Mirror: Rachel, Jack and Ashley Too | Official Trailer | Netflix
https://www.youtube.com/watch?v=-qIlCo9yqpY
THE HARD PROBLEM OF OBSERVERS - WOLFRAM & FRISTON [SPECIAL EDITION]
Please support us! https://www.patreon.com/mlst
https://discord.gg/aNPkGUQtc5
https://twitter.com/MLStreetTalk
YT version (with intro not found here) https://youtu.be/6iaT-0Dvhnc
This is the epic special edition show you have been waiting for! With two of the most brilliant scientists alive today.
Atoms, things, agents, ... observers. What even defines an "observer" and what properties must all observers share? How do objects persist in our universe given that their material composition changes over time? What does it mean for a thing to be a thing? And do things supervene on our lower-level physical reality? What does it mean for a thing to have agency? What's the difference between a complex dynamical system with and without agency? Could a rock or an AI catflap have agency? Can the universe be factorised into distinct agents, or is agency diffused? Have you ever pondered about these deep questions about reality?
Prof. Friston and Dr. Wolfram have spent their entire careers, some 40+ years each thinking long and hard about these very questions and have developed significant frameworks of reference on their respective journeys (the Wolfram Physics project and the Free Energy principle).
Panel: MIT Ph.D Keith Duggar
Production: Dr. Tim Scarfe
Refs:
TED Talk with Stephen:
https://www.ted.com/talks/stephen_wolfram_how_to_think_computationally_about_ai_the_universe_and_everything
https://writings.stephenwolfram.com/2023/10/how-to-think-computationally-about-ai-the-universe-and-everything/
TOC
00:00:00 - Show kickoff
00:02:38 - Wolfram gets to grips with FEP
00:27:08 - How much control does an agent/observer have
00:34:52 - Observer persistence, what universe seems like to us
00:40:31 - Black holes
00:45:07 - Inside vs outside
00:52:20 - Moving away from the predictable path
00:55:26 - What can observers do
01:06:50 - Self modelling gives agency
01:11:26 - How do you know a thing has agency?
01:22:48 - Deep link between dynamics, ruliad and AI
01:25:52 - Does agency entail free will? Defining Agency
01:32:57 - Where do I probe for agency?
01:39:13 - Why is the universe the way we see it?
01:42:50 - Alien intelligence
01:43:40 - The hard problem of Observers
01:46:20 - Summary thoughts from Wolfram
01:49:35 - Factorisability of FEP
01:57:05 - Patreon interview teaser
Autopoitic Enactivism and the Free Energy Principle - Prof. Friston, Prof Buckley, Dr. Ramstead
We explore connections between FEP and enactivism, including tensions raised in a paper critiquing FEP from an enactivist perspective.
Dr. Maxwell Ramstead provides background on enactivism emerging from autopoiesis, with a focus on embodied cognition and rejecting information processing/computational views of mind.
Chris shares his journey from robotics into FEP, starting as a skeptic but becoming convinced it's the right framework. He notes there are both "high road" and "low road" versions, ranging from embodied to more radically anti-representational stances. He doesn't see a definitive fork between dynamical systems and information theory as the source of conflict. Rather, the notion of operational closure in enactivism seems to be the main sticking point.
The group explores definitional issues around structure/organization, boundaries, and operational closure. Maxwell argues the generative model in FEP captures organizational dependencies akin to operational closure. The Markov blanket formalism models structural interfaces.
We discuss the concept of goals in cognitive systems - Chris advocates an intentional stance perspective - using notions of goals/intentions if they help explain system dynamics. Goals emerge from beliefs about dynamical trajectories. Prof Friston provides an elegant explanation of how goal-directed behavior naturally falls out of the FEP mathematics in a particular "goldilocks" regime of system scale/dynamics. The conversation explores the idea that many systems simply act "as if" they have goals or models, without necessarily possessing explicit representations. This helps resolve tensions between enactivist and computational perspectives.
Throughout the dialogue, Maxwell presses philosophical points about the FEP abolishing what he perceives as false dichotomies in cognitive science such as internalism/externalism. He is critical of enactivists' commitment to bright line divides between subject areas.
Prof. Karl Friston - Inventor of the free energy principle https://scholar.google.com/citations?user=q_4u0aoAAAAJ
Prof. Chris Buckley - Professor of Neural Computation at Sussex University https://scholar.google.co.uk/citations?user=nWuZ0XcAAAAJ&hl=en
Dr. Maxwell Ramstead - Director of Research at VERSES https://scholar.google.ca/citations?user=ILpGOMkAAAAJ&hl=fr
We address critique in this paper:
Laying down a forking path: Tensions between enaction and the free energy principle (Ezequiel A. Di Paolo, Evan Thompson, Randall D. Beere)
https://philosophymindscience.org/index.php/phimisci/article/download/9187/8975
Other refs:
Multiscale integration: beyond internalism and externalism (Maxwell J D Ramstead)
https://pubmed.ncbi.nlm.nih.gov/33627890/
MLST panel: Dr. Tim Scarfe and Dr. Keith Duggar
TOC (auto generated):
0:00 - Introduction
0:41 - Defining enactivism and its variants
6:58 - The source of the conflict between dynamical systems and information theory
8:56 - Operational closure in enactivism
10:03 - Goals and intentions
12:35 - The link between dynamical systems and information theory
15:02 - Path integrals and non-equilibrium dynamics
18:38 - Operational closure defined
21:52 - Structure vs. organization in enactivism
24:24 - Markov blankets as interfaces
28:48 - Operational closure in FEP
30:28 - Structure and organization again
31:08 - Dynamics vs. information theory
33:55 - Goals and intentions emerge in the FEP mathematics
36:58 - The Good Regulator Theorem
49:30 - enactivism and its relation to ecological psychology
52:00 - Goals, intentions and beliefs
55:21 - Boundaries and meaning
58:55 - Enactivism's rejection of information theory
1:02:08 - Beliefs vs goals
1:05:06 - Ecological psychology and FEP
1:08:41 - The Good Regulator Theorem
1:18:38 - How goal-directed behavior emerges
1:23:13 - Ontological vs metaphysical boundaries
1:25:20 - Boundaries as maps
1:31:08 - Connections to the maximum entropy principle
1:33:45 - Relations to quantum and relational physics
#106 - Prof. KARL FRISTON 3.0 - Collective Intelligence [Special Edition]
This show is sponsored by Numerai, please visit them here with our sponsor link (we would really appreciate it) http://numer.ai/mlst
Prof. Karl Friston recently proposed a vision of artificial intelligence that goes beyond machines and algorithms, and embraces humans and nature as part of a cyber-physical ecosystem of intelligence. This vision is based on the principle of active inference, which states that intelligent systems can learn from their observations and act on their environment to reduce uncertainty and achieve their goals. This leads to a formal account of collective intelligence that rests on shared narratives and goals.
To realize this vision, Friston suggests developing a shared hyper-spatial modelling language and transaction protocol, as well as novel methods for measuring and optimizing collective intelligence. This could harness the power of artificial intelligence for the common good, without compromising human dignity or autonomy. It also challenges us to rethink our relationship with technology, nature, and each other, and invites us to join a global community of sense-makers who are curious about the world and eager to improve it.
YT version: https://www.youtube.com/watch?v=V_VXOdf1NMw
Support us! https://www.patreon.com/mlst
MLST Discord: https://discord.gg/aNPkGUQtc5
TOC:
Intro [00:00:00]
Numerai (Sponsor segment) [00:07:10]
Designing Ecosystems of Intelligence from First Principles (Friston et al) [00:09:48]
Information / Infosphere and human agency [00:18:30]
Intelligence [00:31:38]
Reductionism [00:39:36]
Universalism [00:44:46]
Emergence [00:54:23]
Markov blankets [01:02:11]
Whole part relationships / structure learning [01:22:33]
Enactivism [01:29:23]
Knowledge and Language [01:43:53]
ChatGPT [01:50:56]
Ethics (is-ought) [02:07:55]
Can people be evil? [02:35:06]
Ethics in Al, subjectiveness [02:39:05]
Final thoughts [02:57:00]
References:
Designing Ecosystems of Intelligence from First Principles (Friston et al)
https://arxiv.org/abs/2212.01354
GLOM - How to represent part-whole hierarchies in a neural network (Hinton)
https://arxiv.org/pdf/2102.12627.pdf
Seven Brief Lessons on Physics (Carlo Rovelli)
https://www.amazon.co.uk/Seven-Brief-Lessons-Physics-Rovelli/dp/0141981725
How Emotions Are Made: The Secret Life of the Brain (Lisa Feldman Barrett)
https://www.amazon.co.uk/How-Emotions-Are-Made-Secret/dp/B01N3D4OON
Am I Self-Conscious? (Or Does Self-Organization Entail Self-Consciousness?) (Karl Friston)
https://www.frontiersin.org/articles/10.3389/fpsyg.2018.00579/full
Integrated information theory (Giulio Tononi)
https://en.wikipedia.org/wiki/Integrated_information_theory
#79 Consciousness and the Chinese Room [Special Edition] (CHOLLET, BISHOP, CHALMERS, BACH)
This video is demonetised on music copyright so we would appreciate support on our Patreon! https://www.patreon.com/mlst
We would also appreciate it if you rated us on your podcast platform.
YT: https://youtu.be/_KVAzAzO5HU
Panel: Dr. Tim Scarfe, Dr. Keith Duggar
Guests: Prof. J. Mark Bishop, Francois Chollet, Prof. David Chalmers, Dr. Joscha Bach, Prof. Karl Friston, Alexander Mattick, Sam Roffey
The Chinese Room Argument was first proposed by philosopher John Searle in 1980. It is an argument against the possibility of artificial intelligence (AI) – that is, the idea that a machine could ever be truly intelligent, as opposed to just imitating intelligence.
The argument goes like this:
Imagine a room in which a person sits at a desk, with a book of rules in front of them. This person does not understand Chinese.
Someone outside the room passes a piece of paper through a slot in the door. On this paper is a Chinese character. The person in the room consults the book of rules and, following these rules, writes down another Chinese character and passes it back out through the slot.
To someone outside the room, it appears that the person in the room is engaging in a conversation in Chinese. In reality, they have no idea what they are doing – they are just following the rules in the book.
The Chinese Room Argument is an argument against the idea that a machine could ever be truly intelligent. It is based on the idea that intelligence requires understanding, and that following rules is not the same as understanding.
in this detailed investigation into the Chinese Room, Consciousness and Syntax vs Semantics, we interview luminaries J.Mark Bishop and Francois Chollet and use unreleased footage from our interviews with David Chalmers, Joscha Bach and Karl Friston. We also cover material from Walid Saba and interview Alex Mattick from Yannic's Discord.
This is probably my favourite ever episode of MLST. I hope you enjoy it! With Keith Duggar.
Note that we are using clips from our unreleased interviews from David Chalmers and Joscha Bach -- we will release those shows properly in the coming weeks. We apologise for delay releasing our backlog, we have been busy building a startup company in the background.
TOC:
[00:00:00] Kick off
[00:00:46] Searle
[00:05:09] Bishop introduces CRA
[00:00:00] Stevan Hardad take on CRA
[00:14:03] Francois Chollet dissects CRA
[00:34:16] Chalmers on consciousness
[00:36:27] Joscha Bach on consciousness
[00:42:01] Bishop introduction
[00:51:51] Karl Friston on consciousness
[00:55:19] Bishop on consciousness and comments on Chalmers
[01:21:37] Private language games (including clip with Sam Roffey)
[01:27:27] Dr. Walid Saba on the chinese room (gofai/systematicity take)
[00:34:36] Bishop: on agency / teleology
[01:36:38] Bishop: back to CRA
[01:40:53] Noam Chomsky on mysteries
[01:45:56] Eric Curiel on math does not represent
[01:48:14] Alexander Mattick on syntax vs semantics
Thanks to: Mark MC on Discord for stimulating conversation, Alexander Mattick, Dr. Keith Duggar, Sam Roffey. Sam's YouTube channel is https://www.youtube.com/channel/UCjRNMsglFYFwNsnOWIOgt1Q
#67 Prof. KARL FRISTON 2.0
We engage in a bit of epistemic foraging with Prof. Karl Friston! In this show; we discuss the free energy principle in detail, also emergence, cognition, consciousness and Karl's burden of knowledge!
YT: https://youtu.be/xKQ-F2-o8uM
Patreon: https://www.patreon.com/mlst
Discord: https://discord.gg/HNnAwSduud
[00:00:00] Introduction to FEP/Friston
[00:06:53] Cheers to Epistemic Foraging!
[00:09:17] The Burden of Knowledge Across Disciplines
[00:12:55] On-show introduction to Friston
[00:14:23] Simple does NOT mean Easy
[00:21:25] Searching for a Mathematics of Cognition
[00:26:44] The Low Road and The High Road to the Principle
[00:28:27] What's changed for the FEP in the last year
[00:39:36] FEP as stochastic systems with a pullback attractor
[00:44:03] An attracting set at multiple time scales and time infinity
[00:53:56] What about fuzzy Markov boundaries?
[00:59:17] Is reality densely or sparsely coupled?
[01:07:00] Is a Strong and Weak Emergence distinction useful?
[01:13:25] a Philosopher, a Zombie, and a Sentient Consciousness walk into a bar ...
[01:24:28] Can we recreate consciousness in silico? Will it have qualia?
[01:28:29] Subjectivity and building hypotheses
[01:34:17] Subject specific realizations to minimize free energy
[01:37:21] Free will in a deterministic Universe
The free energy principle made simpler but not too simple
https://arxiv.org/abs/2201.06387
#033 Prof. Karl Friston - The Free Energy Principle
This week Dr. Tim Scarfe, Dr. Keith Duggar and Connor Leahy chat with Prof. Karl Friston. Professor Friston is a British neuroscientist at University College London and an authority on brain imaging. In 2016 he was ranked the most influential neuroscientist on Semantic Scholar. His main contribution to theoretical neurobiology is the variational Free energy principle, also known as active inference in the Bayesian brain. The FEP is a formal statement that the existential imperative for any system which survives in the changing world can be cast as an inference problem. Bayesian Brain Hypothesis states that the brain is confronted with ambiguous sensory evidence, which it interprets by making inferences about the hidden states which caused the sensory data. So is the brain an inference engine? The key concept separating Friston's idea from traditional stochastic reinforcement learning methods and even Bayesian reinforcement learning is moving away from goal-directed optimisation.
Remember to subscribe! Enjoy the show!
00:00:00 Show teaser intro
00:16:24 Main formalism for FEP
00:28:29 Path Integral
00:30:52 How did we feel talking to friston?
00:34:06 Skit - on cultures (checked, but maybe make shorter)
00:36:02 Friston joins
00:36:33 Main show introduction
00:40:51 Is prediction all it takes for intelligence?
00:48:21 balancing accuracy with flexibility
00:57:36 belief-free vs belief-based; beliefs are crucial
01:04:53 Fuzzy Markov Blankets and Wandering Sets
01:12:37 The Free Energy Principle conforms to itself
01:14:50 useful false beliefs
01:19:14 complexity minimization is the heart of free energy [01:19:14 ]Keith:
01:23:25 An Alpha to tip the scales? Absoute not! Absolutely yes!
01:28:47 FEP applied to brain anatomy
01:36:28 Are there multiple non-FEP forms in the brain?
01:43:11 a positive conneciton to backpropagation
01:47:12 The FEP does not explain the origin of FEP systems
01:49:32 Post-show banter
https://www.fil.ion.ucl.ac.uk/~karl/
#machinelearning
#99 – Karl Friston: Neuroscience and the Free Energy Principle
Karl Friston is one of the greatest neuroscientists in history, cited over 245,000 times, known for many influential ideas in brain imaging, neuroscience, and theoretical neurobiology, including the fascinating idea of the free-energy principle for action and perception.
Support this podcast by signing up with these sponsors:
– Cash App – use code “LexPodcast” and download:
– Cash App (App Store): https://apple.co/2sPrUHe
– Cash App (Google Play): https://bit.ly/2MlvP5w
EPISODE LINKS:
Karl’s Website: https://www.fil.ion.ucl.ac.uk/~karl/
Karl’s Wiki: https://en.wikipedia.org/wiki/Karl_J._Friston
This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon.
Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.
OUTLINE:
00:00 – Introduction
01:50 – How much of the human brain do we understand?
05:53 – Most beautiful characteristic of the human brain
10:43 – Brain imaging
20:38 – Deep structure
21:23 – History of brain imaging
32:31 – Neuralink and brain-computer interfaces
43:05 – Free energy principle
1:24:29 – Meaning of life
.jpg?width=400){kind=small}
.jpg?width=400){kind=small}