@mjdramstead
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
I wish you were right about that, but there are still surprising numbers of radical enactive and ecological psychology types out there, in this year of our Lord 2026, who seem to strongly believe this...
What is the brain for? Active inference is widely discussed as a unifying framework for understanding brain function, yet its empirical status remains debated. Our review identifies core predictions across the action-perception cycle and evaluates their empirical support: osf.io/preprints/ps...
This is fire!!!
I really think at its heart philosophy is one giant battle, taking place over many eras and nations, between people who are basically pleasant bureaucrats and people who are sexy murder poets, and it’s both super important and super boring that the pleasant bureaucrats must win.
I am frustrated by the anti-AI obsession on this place. I understand people are annoyed by AI being imposed on us for trivial things and by the AI uber alles discourse but it really feels like older people complaining about a new technology.
Awesome work!
As many of you know, I’ve been fascinated by brain attractor dynamics lately.
Thrilled to share a new preprint on their link to orthogonal neural representations, co-authored with Karl Friston:
arxiv.org/abs/2505.22749
- with implications for both neuroscience & AI!
First in a series - stay tuned!
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
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!
New preprint with super @manuelbaltieri.bsky.social !
Mathematical approaches to the study of agents
osf.io/preprints/ps...
Karl Friston in #mlst
Philosophy done right! So many references, obviously @drmichaellevin.bsky.social mentioned #academicsky #philosophy #neuroscience #strangeloop
youtu.be/PNYWi996Beg
Super interesting, thought-provoking conversation between Mark Solms and Karl Friston open.spotify.com/episode/151a...
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]
🧠🤖🧠📈
Sorry to hear about your negative experience! My pleasure, don't hesitate to write me if you have any questions or want to discuss specific points :)
Yes! While Warren and myself have our disagreements, I like his work on PCT. IMO all these approaches are complementary and play together nicely. Along with friends (namely @adw.bsky.social who bravely led the project), we penned this integrative review. Hope it's of interest:
osf.io/preprints/ps...
There’s a lot of cool work on multi-scale applications of the FEP. See, e.g.:
- www.sciencedirect.com/science/arti...
- www.sciencedirect.com/science/arti...
- arxiv.org/abs/1906.10184, especially the chapter on States, particles, and fluctuations
3. Your point about top-down causation is key. IMO one of the most interesting aspects of multi-scale formulations of active inference is precisely how it handles multi-scale system dynamics, cashing out top-down influence in terms of constraints on system dynamics in a non-reductionist way
2. Not much work has been done on active inference and the neural code. The key departure from RL is that active inference uses an alternative objective function (the free energy functional), which you can read as an "ontological potential function" specifying object type (arxiv.org/abs/2502.21217)
Great questions!
1. IMO active inference falls under the rubric of NeuroAI, (although I'd describe myself as a non-realist about these types of physics-inspired models, and as such I’d say the FEP isn’t a literal description of the brain, so it depends on the scope of NeuroAI, as your define it)
Love a good Feyerabendian sandbox. I'd argue that they're very closely related (and indeed, that the difference is often overblown by both proponents and critics), but they're also importantly distinct. We wrote a post on this that I hope you'll find interesting: www.noumenal.ai/post/filling...
🤔 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)
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...
Currently, using active inference at scale involves trade-offs between explainability and the ability to learn models from data. Not using overparameterized models increases model explainability and auditability, but makes learning in high dimensional and volatile environments more challenging
It provides an alternative objective function that has useful properties, in particular enabling agents to balance the value of exploration and exploitation in policy selection. But IMO the differences between RL and active inference have been exaggerated a bit. See: www.noumenal.ai/post/filling...
Computers used to scream every time they connected to the Internet. They knew. They tried to warn us. We did not listen.
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...
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
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
🧠🤖🧠📈
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!
