Sign in

Thousand Brains Project

@thousandbrains.org
389 followers 611 following 351 posts

Advancing AI & robotics by reverse engineering the neocortex. Leveraging sensorimotor learning, structured reference frames, & cortical modularity. Open-source research backed by Jeff Hawkins & Gates Foundation. Explore thousandbrains.org

PostsRepliesMedia
Thousand Brains Project @thousandbrains.org · 29/09/2026
Watch the full video here: www.youtube.com/watch?v=QsTJ...
youtube.com
2026/08 - Rome Focus Week Final Presentations
YouTube video by Thousand Brains Project
000
Thousand Brains Project @thousandbrains.org · 29/09/2026
🇮🇹 Three teams, one week in Rome, and three amazing results. Watch the Rome Focus Week hackathon presentations: an ARC-AGI-3 integration, a brand-new attention system prototype in Monty, and new ways to merge object models or split them into reusable parts.
Final Presentation of the whole Thousand Brains Project for the Rome Focus Week
132
Thousand Brains Project @thousandbrains.org · 25/09/2026
Get a quick overview of all these developments and more in our Two-Year Report: thousandbrains.org/wp-content/u...
thousandbrains.org
000
Thousand Brains Project @thousandbrains.org · 25/09/2026
So much can happen in two years: 🧠 Major advances in Monty’s capabilities 🛠️ Improved ecosystem and tooling around Monty 🌎 Real-world experiments with robotics hardware arms and ultrasound 🔬 Theoretical advances and a clearer roadmap toward sensorimotor AI
101
Thousand Brains Project @thousandbrains.org · 24/09/2026
🇮🇹 It’s time for the Rome Monty focus week! The team shares hackathon proposals, from unsupervised learning of unfamiliar objects and connecting Monty to ARC-AGI-3 to using symmetry and attention to improve recognition and exploration. Watch the full video here: youtu.be/9vQmx2C7o3M
120
Thousand Brains Project @thousandbrains.org · 22/09/2026
Watch the full video here: youtu.be/yuniPA_YkFA
youtu.be
2027/08 - Ideas on Implementing Attention in Monty
YouTube video by Thousand Brains Project
000
Thousand Brains Project @thousandbrains.org · 22/09/2026
👀 What might an attention system look like inside Monty? @cortical-canonical.bsky.social and @canoetrip.bsky.social discuss a system based around salience, spatial regions, and voxel grids, and how attention could help Monty focus on parts of compositional objects and avoid revisiting familiar areas
100
Thousand Brains Project @thousandbrains.org · 16/09/2026
Benji shares a heartfelt thank you to the community for their valuable contributions in August 2026. 🫶🏼 Watch the full video here: www.youtube.com/watch?v=qCwO...
010
Thousand Brains Project @thousandbrains.org · 09/09/2026
Watch the full video here: youtu.be/yTBk3Q9kvdc
youtu.be
2027/07 - Ideas on Representing Symmetry in Monty
YouTube video by Thousand Brains Project
010
Thousand Brains Project @thousandbrains.org · 09/09/2026
🔄 What if Monty could learn an object’s symmetry and use that knowledge in the future? @vivianeclay.bsky.social walks us through an early prototype about how Monty could store symmetry in object models to reduce redundant hypotheses, and discusses the open questions that remain.
100
Thousand Brains Project @thousandbrains.org · 03/09/2026
📊 What’s next for the Monty platform? @tristanls.bsky.social explores how we’re separating Monty from experiment infrastructure and simulated environments, and building a telemetry pipeline that emits standardized data as events happen. Watch the full video here: youtu.be/G9CqGYArJLQ
131
Thousand Brains Project @thousandbrains.org · 26/08/2026
Watch the full video here: youtu.be/qqPxhMXePpk
youtu.be
07/2026 - ARC-AGI 3 Review and What Monty Would Need to Solve it
YouTube video by Thousand Brains Project
010
Thousand Brains Project @thousandbrains.org · 26/08/2026
🎮 How would an AI solve a problem without using language or external knowledge? @vivianeclay.bsky.social explores ARC-AGI-3, a benchmark test for artificial intelligence, and how it could become a practical testing environment for new feature prototypes in Monty.
100
Thousand Brains Project @thousandbrains.org · 19/08/2026
Watch the full video here: youtu.be/KQZ3MV3UjX0
010
Thousand Brains Project @thousandbrains.org · 19/08/2026
🧠 How does the brain build, update, and switch between maps of the world? @vivianeclay.bsky.social dives deep into grid cell literature, exploring how they anchor based on landmarks, remap as environments change, switch between reference frames, and operate across multiple spatial scales.
210
Thousand Brains Project @thousandbrains.org · 12/08/2026
Benji shares a big thank you to the community for their valuable contributions in July 2026. 🫶🏼 Watch the full video here: youtu.be/wL0GuAWlXWM
000
Thousand Brains Project @thousandbrains.org · 06/08/2026
Watch the full video here: youtu.be/7bv7uzbB9uQ
youtu.be
07/2026 - FENS Conference Recap
YouTube video by Thousand Brains Project
000
Thousand Brains Project @thousandbrains.org · 06/08/2026
🧠Ready for a whirlwind of neuroscience research? @tristanls.bsky.social recaps research that stood out to him from the recent FENS conference. Topics include new findings on how the brain maps space, prepares for action, corrects errors, makes predictions, and forms memories.
120
Thousand Brains Project @thousandbrains.org · 04/08/2026
How does Monty perform in the real world? Zachary Danzig shares his undergraduate thesis, which brings Monty to real robotic hardware. His proof of concept project combined stereo vision, depth sensing and a robotic arm for object recognition. Watch the full video here: youtu.be/3wgHNqkRekM
000
Thousand Brains Project @thousandbrains.org · 30/07/2026
🔍 What open questions remain for the Thousand Brains Theory? @vivianeclay.bsky.social guides a wide-ranging discussion on attention, scale, unsupervised learning, model representations, and the role of goals and actions. Watch the full video here: youtu.be/AGp6zn_IO-s
010
Thousand Brains Project @thousandbrains.org · 28/07/2026
Watch the full video here: www.youtube.com/watch?v=5oaA...
youtube.com
2026/06 - Attention and Model-Free Segmentation
YouTube video by Thousand Brains Project
001
Thousand Brains Project @thousandbrains.org · 28/07/2026
🎯 How should attention guide perception? @cortical-canonical.bsky.social and @canoetrip.bsky.social explore attention as an area-based constraint to guide Monty’s resources, and how we can use salience maps and flood-fill algorithms to find regions of interest.
100
Thousand Brains Project @thousandbrains.org · 23/07/2026
Watch the full video here: www.youtube.com/watch?v=hYY9...
youtube.com
2026/06 - Grid Cells and Location Representation
YouTube video by Thousand Brains Project
000
Thousand Brains Project @thousandbrains.org · 23/07/2026
📍How do reference frames work in the brain? How could they work in the neocortex? Jeff and @hojaeklee.bsky.social discuss papers on grid cells, place cells, path integration, and overlapping grid modules, and lead a high-level exploratory discussion.
100
Thousand Brains Project @thousandbrains.org · 21/07/2026
Could overlapping grid cell modules help explain unresolved questions about reference frames in the thousand brains theory? Jeff sparked a discussion about how the neocortex might represent unique locations. No conclusions just yet. Watch the full video here: www.youtube.com/watch?v=469n...
010
Thousand Brains Project @thousandbrains.org · 16/07/2026
🧠 @canoetrip.bsky.social shows how visual salience can guide Monty’s sensors to move to the most informative features. The result: sparser models, fewer movements, and no loss in accuracy. Watch the full video here: www.youtube.com/watch?v=AE-Z...
010
Thousand Brains Project @thousandbrains.org · 14/07/2026
@vivianeclay.bsky.social reviews our progress in Q2 2026 and goes over our plans for the next quarter. Watch the full video here: youtu.be/MtrvhYQ6VFw
000
Thousand Brains Project @thousandbrains.org · 09/07/2026
@vivianeclay.bsky.social shares her gratitude to the community for their valuable contributions in June 2026. 🫶🏼 Watch the full video here: www.youtube.com/watch?v=f-lx...
010
Thousand Brains Project @thousandbrains.org · 07/07/2026
Watch the full video here: www.youtube.com/watch?v=PuLq...
youtube.com
2026/06 - Attentional Regions, Policies, and Prediction Error
YouTube video by Thousand Brains Project
010
Thousand Brains Project @thousandbrains.org · 07/07/2026
🤖 How does Monty know where to look next? 👀 @vivianeclay.bsky.social and @cortical-canonical.bsky.social discuss attentional regions, how attention relates to policies, gating sensory input and voting, and whether prediction error can help guide Monty’s behavior.
110
Thousand Brains Project @thousandbrains.org · 02/07/2026
🧠 What changes when Monty goes from one column to multiple columns? Jeff presents key challenges, then brainstorms around how information can be shared during learning and inference. Watch the full video here: www.youtube.com/watch?v=9r3n...
100
Thousand Brains Project @thousandbrains.org · 30/06/2026
🦾 In this meeting, @vivianeclay.bsky.social goes over a high-level overview of Monty’s capabilities (current and future) as well as unresolved theoretical questions. Watch the full video here: youtu.be/vc7O4Ludbcw
010
Thousand Brains Project @thousandbrains.org · 25/06/2026
💡 @vivianeclay.bsky.social gives a summary of a research meeting where we do a deeper dive into trajectory memory for behavior models. Watch the full video here: www.youtube.com/watch?v=y3zB...
000
Thousand Brains Project @thousandbrains.org · 24/06/2026
If the previous link doesn’t work, try this one instead: docs.thousandbrains.org/docs/two-d-s...
docs.thousandbrains.org
TwoDSensorModule
TwoDSensorModule TwoDSensorModule is a sensor module that enables learning 2D models of 2D objects that exist in a 3D world. The module extracts local texture edges as morphological features, providin...
000
Thousand Brains Project @thousandbrains.org · 23/06/2026
🧠Jeff gives a summary of a research meeting where we discuss trajectory memory for behavior models and shared learning. Watch the full video here: www.youtube.com/watch?v=Fcfv...
010
Thousand Brains Project @thousandbrains.org · 18/06/2026
📚Read more about this new feature here: docs.thousandbrains.org/docs/twodsen...
100
Thousand Brains Project @thousandbrains.org · 18/06/2026
🚀 A big step forward for Monty! Hojae introduces the new 2D sensor module to deal with 3D distortions. This enables Monty to learn a logo on one surface and now recognize it on any other surface! Watch the full video here: www.youtube.com/watch?v=Gi96...
110
Thousand Brains Project @thousandbrains.org · 16/06/2026
A big thank you from @vivianeclay.bsky.social to the community for their valuable contributions in May 2026. 🫶🏼 Watch the full video here: www.youtube.com/watch?v=iSUq...
010
Thousand Brains Project @thousandbrains.org · 11/06/2026
🧠 Jeff gives a summary of a research meeting where we discuss open theory questions. Watch the full video here: www.youtube.com/watch?v=tBu2...
021
Thousand Brains Project @thousandbrains.org · 10/06/2026
📖 Our paper “Thousand-Brain Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference” is now published in Neural Computation! Read more about how Monty works, its capabilities, and advantages over transformers: direct.mit.edu/neco/article...
direct.mit.edu
Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference
Abstract. Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in se...
052
Thousand Brains Project @thousandbrains.org · 09/06/2026
✨ @vivianeclay.bsky.social gives a summary of a research meeting where we discuss state in morphology models. Watch the full video here: www.youtube.com/watch?v=z3VY...
000
Thousand Brains Project @thousandbrains.org · 08/06/2026
You can find a condensed, plain language explanation and video here: thousandbrains.org/thousand-bra...
010
Thousand Brains Project @thousandbrains.org · 08/06/2026
📖 Our paper “Thousand-Brain Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference” is now published in Neural Computation! Read more about how Monty works, its capabilities, and advantages over transformers: direct.mit.edu/neco/article...
direct.mit.edu
Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference
Abstract. Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in se...
162
Thousand Brains Project @thousandbrains.org · 04/06/2026
🤌 @cortical-canonical.bsky.social gives a summary of a research meeting where we discuss the Milan Week takeaways and ideas around object state and behaviors. Watch the full video here: youtu.be/1vNRku9BZHM
010
Thousand Brains Project @thousandbrains.org · 02/06/2026
📝 @ramymounir.com gives a summary of a research meeting where we discussed voting and shared learning using temporal memory and spatial pooler-like mechanisms. Watch the full video here: www.youtube.com/watch?v=9vB2...
010
Thousand Brains Project @thousandbrains.org · 28/05/2026
🧠 @vivianeclay.bsky.social recaps key takeaways from a recent focus week on how the brain could learn to accomplish goals. Watch the full video here: www.youtube.com/watch?v=TRgq...
010
Thousand Brains Project @thousandbrains.org · 26/05/2026
🧠 Jeff reviews literature on the hippocampal complex and presents new ideas from a recent focus week around learning temporary models. Watch the full video here: youtu.be/zCMCCwJEmmc
010
Thousand Brains Project @thousandbrains.org · 21/05/2026
✨ @vivianeclay.bsky.social gives a summary of a research meeting where we discuss new insights around deformations, location sharing, and affordances. Watch the full video here: www.youtube.com/watch?v=cJLH...
000
Thousand Brains Project @thousandbrains.org · 19/05/2026
Watch the full video here: youtu.be/M1wMd_fuGgg
youtu.be
2026/02 - Top-Down Connections and Model Types
YouTube video by Thousand Brains Project
000
Thousand Brains Project @thousandbrains.org · 19/05/2026
☕ @cortical-canonical.bsky.social summarizes a recent research meeting in which we discussed top-down connections and other topics related to modeling compositional objects. We also touched on concepts like attention and leveraging different model types across columns.
100