Maxwell Ramstead
@mjdramstead.bsky.social
Cofounder @noumenal-labs.bsky.social. Honorary Fellow at the UCL Queen Square Institute of Neurology. Free energy principle, active inference, Bayesian mechanics, artificial intelligence, phenomenology
Pinned
Reposted by Maxwell Ramstead
In episode 1000, I talk with Dr. Karl Friston about the Free Energy Principle and active inference, from #Physics to mind. #CognitiveScience #Science
youtu.be/2BzmKnDtCCI
youtu.be/2BzmKnDtCCI
#1000 Karl Friston: The Free Energy Principle and Active Inference: From Physics to Mind
YouTube video by The Dissenter
youtu.be
November 27, 2025 at 12:05 PM
In episode 1000, I talk with Dr. Karl Friston about the Free Energy Principle and active inference, from #Physics to mind. #CognitiveScience #Science
youtu.be/2BzmKnDtCCI
youtu.be/2BzmKnDtCCI
Reposted by Maxwell Ramstead
Honored to speak at Ottawa about how Canada can lead in #NeuroAI. With world-class talent, trusted institutions, & sustainable infrastructure, we can build a federated approach to AI that protects mental health & strengthens our society. Thanks @braincanada.bsky.social for the invitation!
November 20, 2025 at 9:09 PM
Honored to speak at Ottawa about how Canada can lead in #NeuroAI. With world-class talent, trusted institutions, & sustainable infrastructure, we can build a federated approach to AI that protects mental health & strengthens our society. Thanks @braincanada.bsky.social for the invitation!
Reposted by Maxwell Ramstead
New preprint with super @manuelbaltieri.bsky.social !
Mathematical approaches to the study of agents
osf.io/preprints/ps...
Mathematical approaches to the study of agents
osf.io/preprints/ps...
OSF
osf.io
November 21, 2025 at 12:44 PM
New preprint with super @manuelbaltieri.bsky.social !
Mathematical approaches to the study of agents
osf.io/preprints/ps...
Mathematical approaches to the study of agents
osf.io/preprints/ps...
Reposted by Maxwell Ramstead
Karl Friston in #mlst
Philosophy done right! So many references, obviously @drmichaellevin.bsky.social mentioned #academicsky #philosophy #neuroscience #strangeloop
youtu.be/PNYWi996Beg
Philosophy done right! So many references, obviously @drmichaellevin.bsky.social mentioned #academicsky #philosophy #neuroscience #strangeloop
youtu.be/PNYWi996Beg
Why Intelligence Can't Get Too Large (Karl Friston)
YouTube video by Machine Learning Street Talk
youtu.be
September 11, 2025 at 3:05 PM
Karl Friston in #mlst
Philosophy done right! So many references, obviously @drmichaellevin.bsky.social mentioned #academicsky #philosophy #neuroscience #strangeloop
youtu.be/PNYWi996Beg
Philosophy done right! So many references, obviously @drmichaellevin.bsky.social mentioned #academicsky #philosophy #neuroscience #strangeloop
youtu.be/PNYWi996Beg
Reposted by Maxwell Ramstead
Super interesting, thought-provoking conversation between Mark Solms and Karl Friston open.spotify.com/episode/151a...
Karl Friston & Mark Solms: Is it Possible to Engineer Artificial Consciousness?
Spotify video
open.spotify.com
September 12, 2025 at 6:36 AM
Super interesting, thought-provoking conversation between Mark Solms and Karl Friston open.spotify.com/episode/151a...
Reposted by Maxwell Ramstead
What drives behavior in living organisms? And how can we design artificial agents that learn interactively?
📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇
w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social
🧵[1/5]
🧠🤖🧠📈
📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇
w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social
🧵[1/5]
🧠🤖🧠📈
September 17, 2025 at 4:32 PM
What drives behavior in living organisms? And how can we design artificial agents that learn interactively?
📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇
w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social
🧵[1/5]
🧠🤖🧠📈
📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇
w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social
🧵[1/5]
🧠🤖🧠📈
Reposted by Maxwell Ramstead
🤔 How can we study #consciousness between people, at the social level? 🧠✨ New #preprint co-led by Anne Monnier & Lena Adel: “Now is the Time: Operationalizing Generative Neurophenomenology through Interpersonal Methods” 🧵(1/3)
August 8, 2025 at 3:16 PM
🤔 How can we study #consciousness between people, at the social level? 🧠✨ New #preprint co-led by Anne Monnier & Lena Adel: “Now is the Time: Operationalizing Generative Neurophenomenology through Interpersonal Methods” 🧵(1/3)
Reposted by Maxwell Ramstead
Our new preprint on active inference in zebrafish, with Yuki Tanimoto, Makio Torigoe, Hitoshi Okamoto, and Hideaki Shimazaki
"Predicting individual learning trajectories in zebrafish via the free-energy principle"
doi.org/10.1101/2025...
"Predicting individual learning trajectories in zebrafish via the free-energy principle"
doi.org/10.1101/2025...
Predicting individual learning trajectories in zebrafish via the free-energy principle
The free-energy principle has been proposed as a unified theory of brain function, and recent evidence from in vitro experiments supports its validity. However, its empirical application to in vivo ne...
doi.org
August 11, 2025 at 9:15 PM
Our new preprint on active inference in zebrafish, with Yuki Tanimoto, Makio Torigoe, Hitoshi Okamoto, and Hideaki Shimazaki
"Predicting individual learning trajectories in zebrafish via the free-energy principle"
doi.org/10.1101/2025...
"Predicting individual learning trajectories in zebrafish via the free-energy principle"
doi.org/10.1101/2025...
Reposted by Maxwell Ramstead
Computers used to scream every time they connected to the Internet. They knew. They tried to warn us. We did not listen.
June 22, 2025 at 10:15 PM
Computers used to scream every time they connected to the Internet. They knew. They tried to warn us. We did not listen.
Reposted by Maxwell Ramstead
Delighted to see ‘A Trick of the Mind’ reviewed in @theguardian.com as Book of the Day! 🧠 🍎
Also in the print edition tomorrow 🗞️
www.theguardian.com/books/2025/j...
Also in the print edition tomorrow 🗞️
www.theguardian.com/books/2025/j...
June 13, 2025 at 11:04 AM
Delighted to see ‘A Trick of the Mind’ reviewed in @theguardian.com as Book of the Day! 🧠 🍎
Also in the print edition tomorrow 🗞️
www.theguardian.com/books/2025/j...
Also in the print edition tomorrow 🗞️
www.theguardian.com/books/2025/j...
Reposted by Maxwell Ramstead
Luca M. Possati: Markov Blanket Density and Free Energy Minimization https://arxiv.org/abs/2506.05794 https://arxiv.org/pdf/2506.05794 https://arxiv.org/html/2506.05794
June 9, 2025 at 6:16 AM
Luca M. Possati: Markov Blanket Density and Free Energy Minimization https://arxiv.org/abs/2506.05794 https://arxiv.org/pdf/2506.05794 https://arxiv.org/html/2506.05794
Reposted by Maxwell Ramstead
Elegant theoretical derivations are exclusive to physics. Right?? Wrong!
In a new preprint, we:
✅ "Derive" a spiking recurrent network from variational principles
✅ Show it does amazing things like out-of-distribution generalization
👉[1/n]🧵
w/ co-lead Dekel Galor & PI @jcbyts.bsky.social
🧠🤖🧠📈
In a new preprint, we:
✅ "Derive" a spiking recurrent network from variational principles
✅ Show it does amazing things like out-of-distribution generalization
👉[1/n]🧵
w/ co-lead Dekel Galor & PI @jcbyts.bsky.social
🧠🤖🧠📈
May 19, 2025 at 6:36 AM
Elegant theoretical derivations are exclusive to physics. Right?? Wrong!
In a new preprint, we:
✅ "Derive" a spiking recurrent network from variational principles
✅ Show it does amazing things like out-of-distribution generalization
👉[1/n]🧵
w/ co-lead Dekel Galor & PI @jcbyts.bsky.social
🧠🤖🧠📈
In a new preprint, we:
✅ "Derive" a spiking recurrent network from variational principles
✅ Show it does amazing things like out-of-distribution generalization
👉[1/n]🧵
w/ co-lead Dekel Galor & PI @jcbyts.bsky.social
🧠🤖🧠📈
Reposted by Maxwell Ramstead
Preprint time:
“Shannon invariants: A scalable approach to information decomposition”
arxiv.org/abs/2504.15779
Studying information in complex systems is challenging due to difficulties in defining multivariate metrics and ensuring their scalability. This framework addressed both challenges!
“Shannon invariants: A scalable approach to information decomposition”
arxiv.org/abs/2504.15779
Studying information in complex systems is challenging due to difficulties in defining multivariate metrics and ensuring their scalability. This framework addressed both challenges!
Shannon invariants: A scalable approach to information decomposition
Distributed systems, such as biological and artificial neural networks, process information via complex interactions engaging multiple subsystems, resulting in high-order patterns with distinct proper...
arxiv.org
April 23, 2025 at 11:22 AM
Preprint time:
“Shannon invariants: A scalable approach to information decomposition”
arxiv.org/abs/2504.15779
Studying information in complex systems is challenging due to difficulties in defining multivariate metrics and ensuring their scalability. This framework addressed both challenges!
“Shannon invariants: A scalable approach to information decomposition”
arxiv.org/abs/2504.15779
Studying information in complex systems is challenging due to difficulties in defining multivariate metrics and ensuring their scalability. This framework addressed both challenges!
Reposted by Maxwell Ramstead
Computational theory is about computers (i.e. "technology") in the same way that astronomy is about telescopes. Thinking that computation is not fundamentally important for biology because "a cell is not like a laptop" is to miss the forest for the trees. N/N
April 5, 2025 at 12:07 PM
Computational theory is about computers (i.e. "technology") in the same way that astronomy is about telescopes. Thinking that computation is not fundamentally important for biology because "a cell is not like a laptop" is to miss the forest for the trees. N/N
Reposted by Maxwell Ramstead
Reinforcement Learning and Active Inference are two frameworks used in computational psychiatry, but these are rarely directly compared empirically. In this new article, we aimed to compare these in a more systematic manner by fitting each to multiple datasets: papers.ssrn.com/sol3/papers....
A Systematic Empirical Comparison of Active Inference and Reinforcement Learning Models in Accounting for Decision-Making Under Uncertainty
Reinforcement Learning (RL) and Active Inference (AInf) are related computational frameworks for modeling learning and choice under uncertainty. However, differ
papers.ssrn.com
March 27, 2025 at 7:22 PM
Reinforcement Learning and Active Inference are two frameworks used in computational psychiatry, but these are rarely directly compared empirically. In this new article, we aimed to compare these in a more systematic manner by fitting each to multiple datasets: papers.ssrn.com/sol3/papers....
Reposted by Maxwell Ramstead
It's not just that just about everything I've ever published is in this particular database and used without my permission. It's that everything I've ever published was used without my permission to develop such a shitty, flawed and fundamentally useless tool. I deserve compensation for THAT itself.
NEW: LibGen contains millions of pirated books and research papers, built over nearly two decades. From court documents, we know that Meta torrented a version of it to build its AI. Today, @theatlantic.com presents an analysis of the data set by @alexreisner.bsky.social. Search through it yourself:
The Unbelievable Scale of AI’s Pirated-Books Problem
Meta pirated millions of books to train its AI. Search through them here.
www.theatlantic.com
March 20, 2025 at 2:01 PM
It's not just that just about everything I've ever published is in this particular database and used without my permission. It's that everything I've ever published was used without my permission to develop such a shitty, flawed and fundamentally useless tool. I deserve compensation for THAT itself.
Bluesky has become awesome and I am absolutely loving it.
March 18, 2025 at 2:30 PM
Bluesky has become awesome and I am absolutely loving it.
New blog post by @noumenal-labs.bsky.social : “Designing machine intelligence that can reason by analogy”:
www.noumenal.ai/post/designi...
www.noumenal.ai/post/designi...
Designing machine intelligence that can reason by analogy
Inspired by neural reuse and reassembly, we consider key design features that unlock the ability for AI to reason by analogy and by metaphor
www.noumenal.ai
March 17, 2025 at 3:59 PM
New blog post by @noumenal-labs.bsky.social : “Designing machine intelligence that can reason by analogy”:
www.noumenal.ai/post/designi...
www.noumenal.ai/post/designi...
Reposted by Maxwell Ramstead
Beyond Mechanism—Extending Our Concepts of Causation in Neuroscience onlinelibrary.wiley.com/doi/10.1111/... - really pleased that this paper with Henry Potter is now published in the European Journal of Neuroscience 😊
Beyond Mechanism—Extending Our Concepts of Causation in Neuroscience
The search for neural mechanisms of behaviour often relies on a synchronic, driving view of causation, where neural activity drives more neural activity, which eventually drives behaviour. The real c...
onlinelibrary.wiley.com
March 14, 2025 at 10:25 AM
Beyond Mechanism—Extending Our Concepts of Causation in Neuroscience onlinelibrary.wiley.com/doi/10.1111/... - really pleased that this paper with Henry Potter is now published in the European Journal of Neuroscience 😊
Reposted by Maxwell Ramstead
1/ "A science of consciousness beyond pseudo-science and pseudo-consciousness" is out now! it was a joy to coauthor this commentary with Àlex Gómez-Marin @behaviOrganisms for @NatureNeuro, in which we try find some positive lessons in the clash over IIT www.nature.com/articles/s41...
March 10, 2025 at 10:54 AM
1/ "A science of consciousness beyond pseudo-science and pseudo-consciousness" is out now! it was a joy to coauthor this commentary with Àlex Gómez-Marin @behaviOrganisms for @NatureNeuro, in which we try find some positive lessons in the clash over IIT www.nature.com/articles/s41...
hello world model
March 13, 2025 at 7:01 PM
hello world model
Big sigh. The FEP is just the principle of maximum entropy or maximum caliber, under the constraint that boundaries exist. Every now and then, people who do not understand the FEP opine about it loudly and uncharitably. This is yet another case in point.
Skill issue!
Skill issue!
March 12, 2025 at 4:58 PM
Big sigh. The FEP is just the principle of maximum entropy or maximum caliber, under the constraint that boundaries exist. Every now and then, people who do not understand the FEP opine about it loudly and uncharitably. This is yet another case in point.
Skill issue!
Skill issue!
I’m happy to share the new @noumenal-labs.bsky.social preprint, “Dynamic Markov blanket detection for macroscopic physics discovery,” by Jeff Beck and me
arxiv.org/abs/2502.21217
Here’s a thread!
1/16
arxiv.org/abs/2502.21217
Here’s a thread!
1/16
Dynamic Markov Blanket Detection for Macroscopic Physics Discovery
The free energy principle (FEP), along with the associated constructs of Markov blankets and ontological potentials, have recently been presented as the core components of a generalized modeling metho...
arxiv.org
March 10, 2025 at 4:46 PM
I’m happy to share the new @noumenal-labs.bsky.social preprint, “Dynamic Markov blanket detection for macroscopic physics discovery,” by Jeff Beck and me
arxiv.org/abs/2502.21217
Here’s a thread!
1/16
arxiv.org/abs/2502.21217
Here’s a thread!
1/16
Excited to share a new blog post by @noumenal-labs.bsky.social
New blog post by @noumenal_labs: “Filling the gaps in active inference”: www.noumenal.ai/post/filling...
Here’s the tl;dr:
In this blog post, we discuss key gaps in state-of-the-art applications of active inference in artificial intelligence — and how Noumenal Labs is working to fill them 1/7
Here’s the tl;dr:
In this blog post, we discuss key gaps in state-of-the-art applications of active inference in artificial intelligence — and how Noumenal Labs is working to fill them 1/7
Filling the gaps in active inference
Here we discuss key gaps in SOTA applications of active inference in AI - and how Noumenal Labs is working to fill them.
www.noumenal.ai
March 6, 2025 at 3:09 PM
Excited to share a new blog post by @noumenal-labs.bsky.social