Blake Richards
@tyrellturing.bsky.social
Researcher at Google and CIFAR Fellow, working on the intersection of machine learning and neuroscience in Montréal (academic affiliations: @mcgill.ca and @mila-quebec.bsky.social).
Reposted by Blake Richards
Quick thread on the BBC and the political and societal significance of recent developments:
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
November 10, 2025 at 1:43 PM
Quick thread on the BBC and the political and societal significance of recent developments:
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
Reposted by Blake Richards
Adopting an engineering mindset will help the field focus its research priorities, writes @timothyoleary.bsky.social.
#neuroskyence
www.thetransmitter.org/systems-neur...
#neuroskyence
www.thetransmitter.org/systems-neur...
Neuroscience needs engineers—for more reasons than you think
Adopting an engineering mindset will help the field focus its research priorities.
www.thetransmitter.org
November 10, 2025 at 6:56 PM
Adopting an engineering mindset will help the field focus its research priorities, writes @timothyoleary.bsky.social.
#neuroskyence
www.thetransmitter.org/systems-neur...
#neuroskyence
www.thetransmitter.org/systems-neur...
Reposted by Blake Richards
"Cognition all the way down". Great to see this fine new paper from @robertchisciure.bsky.social & @drmichaellevin.bsky.social out now in Synthese - introducing a new metric to quantify biological intelligence as search efficiency in multidimensional problem spaces link.springer.com/article/10.1...
November 10, 2025 at 2:46 PM
"Cognition all the way down". Great to see this fine new paper from @robertchisciure.bsky.social & @drmichaellevin.bsky.social out now in Synthese - introducing a new metric to quantify biological intelligence as search efficiency in multidimensional problem spaces link.springer.com/article/10.1...
Reposted by Blake Richards
If you're interested in dynamical systems analysis for neuroscience, definitely check out @oliviercodol.bsky.social 's revised version of our RL paper! Very cool results in the new Fig 6, worth it regardless of if you saw our previous version or if it's all new.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
November 6, 2025 at 5:58 PM
If you're interested in dynamical systems analysis for neuroscience, definitely check out @oliviercodol.bsky.social 's revised version of our RL paper! Very cool results in the new Fig 6, worth it regardless of if you saw our previous version or if it's all new.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Reposted by Blake Richards
New issue of Nature - with NINE studies on #brain #development from the BRAIN Initiative Cell Atlas Network (BICAN) 🧠🧪🔬
An amazing set of resources for all scientists working on the brain!
🧠 Immersive feature:
www.nature.com/immersive/d4...
🧠 Perspective:
www.nature.com/articles/s41...
An amazing set of resources for all scientists working on the brain!
🧠 Immersive feature:
www.nature.com/immersive/d4...
🧠 Perspective:
www.nature.com/articles/s41...
November 5, 2025 at 6:53 PM
New issue of Nature - with NINE studies on #brain #development from the BRAIN Initiative Cell Atlas Network (BICAN) 🧠🧪🔬
An amazing set of resources for all scientists working on the brain!
🧠 Immersive feature:
www.nature.com/immersive/d4...
🧠 Perspective:
www.nature.com/articles/s41...
An amazing set of resources for all scientists working on the brain!
🧠 Immersive feature:
www.nature.com/immersive/d4...
🧠 Perspective:
www.nature.com/articles/s41...
Reposted by Blake Richards
Canada makes pitch for US researchers to relocate with $1.7bn in new funding. My story for @science.org 🧪
www.science.org/content/arti...
www.science.org/content/arti...
Canada’s new budget aims to lure U.S. researchers to relocate
Spending plan also calls for smaller research spending cut than feared
www.science.org
November 5, 2025 at 6:19 PM
Canada makes pitch for US researchers to relocate with $1.7bn in new funding. My story for @science.org 🧪
www.science.org/content/arti...
www.science.org/content/arti...
Today my colleagues in the Paradigms of Intelligence team have announced Project Suncatcher:
research.google/blog/explori...
tl;dr: How can we put datacentres in space where solar energy is near limitless? Requires changes to current practices (due to radiation and bandwidth issues).
🧪 #MLSky
research.google/blog/explori...
tl;dr: How can we put datacentres in space where solar energy is near limitless? Requires changes to current practices (due to radiation and bandwidth issues).
🧪 #MLSky
Exploring a space-based, scalable AI infrastructure system design
research.google
November 4, 2025 at 10:36 PM
Today my colleagues in the Paradigms of Intelligence team have announced Project Suncatcher:
research.google/blog/explori...
tl;dr: How can we put datacentres in space where solar energy is near limitless? Requires changes to current practices (due to radiation and bandwidth issues).
🧪 #MLSky
research.google/blog/explori...
tl;dr: How can we put datacentres in space where solar energy is near limitless? Requires changes to current practices (due to radiation and bandwidth issues).
🧪 #MLSky
Reposted by Blake Richards
Congratulations to Sheena Josselyn @sjo09.bsky.social, contributing editor at @thetransmitter.bsky.social, on winning the 2025 Peter Seeburg Integrative Neuroscience Prize in recognition of her profound impact on memory research.
#neuroskyence
#neuroskyence
November 4, 2025 at 4:50 PM
Congratulations to Sheena Josselyn @sjo09.bsky.social, contributing editor at @thetransmitter.bsky.social, on winning the 2025 Peter Seeburg Integrative Neuroscience Prize in recognition of her profound impact on memory research.
#neuroskyence
#neuroskyence
Reposted by Blake Richards
🐸 Xenopus laevis 💚 The frog that shaped modern developmental biology! ✨ Xenopus embryos have revealed how the body axis forms, cells choose their fate, and tissues self-organize during early development 📹 Video by Bioquest Sudio and Xenbase #ModelMonday #DevBio
November 3, 2025 at 8:01 PM
🐸 Xenopus laevis 💚 The frog that shaped modern developmental biology! ✨ Xenopus embryos have revealed how the body axis forms, cells choose their fate, and tissues self-organize during early development 📹 Video by Bioquest Sudio and Xenbase #ModelMonday #DevBio
Reposted by Blake Richards
Introducing CorText: a framework that fuses brain data directly into a large language model, allowing for interactive neural readout using natural language.
tl;dr: you can now chat with a brain scan 🧠💬
1/n
tl;dr: you can now chat with a brain scan 🧠💬
1/n
November 3, 2025 at 3:17 PM
Introducing CorText: a framework that fuses brain data directly into a large language model, allowing for interactive neural readout using natural language.
tl;dr: you can now chat with a brain scan 🧠💬
1/n
tl;dr: you can now chat with a brain scan 🧠💬
1/n
Reposted by Blake Richards
I wrote a thing on episodic memory and systems consolidation. I hope you all enjoy it and/or find it interesting.
A neural state space for episodic memories
www.sciencedirect.com/science/arti...
#neuroskyence #psychscisky #cognition 🧪
A neural state space for episodic memories
www.sciencedirect.com/science/arti...
#neuroskyence #psychscisky #cognition 🧪
A neural state space for episodic memories
Episodic memories are highly dynamic and change in nonlinear ways over time. This dynamism is not captured by existing systems consolidation theories …
www.sciencedirect.com
November 3, 2025 at 12:56 PM
I wrote a thing on episodic memory and systems consolidation. I hope you all enjoy it and/or find it interesting.
A neural state space for episodic memories
www.sciencedirect.com/science/arti...
#neuroskyence #psychscisky #cognition 🧪
A neural state space for episodic memories
www.sciencedirect.com/science/arti...
#neuroskyence #psychscisky #cognition 🧪
Great Blueprint from @arnaghosh.bsky.social on our newest paper on representational geometry!
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
October 31, 2025 at 4:37 PM
Great Blueprint from @arnaghosh.bsky.social on our newest paper on representational geometry!
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
tl;dr: we find that during pretraining LLMs undergo consistent cycles of expansion/recuction in the dimensionality of their representations & these cycles correlate with the emergence of new capabilities.
Reposted by Blake Richards
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
October 31, 2025 at 4:19 PM
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
Reposted by Blake Richards
Now accepting paper submissions for the “Neuro for AI & AI for Neuro: Towards Multi-Modal Natural Intelligence” workshop at #AAAI2026!
🔗 https://neuroai-multimodal-workshop.github.io/
@aaai.org
🔗 https://neuroai-multimodal-workshop.github.io/
@aaai.org
October 30, 2025 at 3:57 PM
Now accepting paper submissions for the “Neuro for AI & AI for Neuro: Towards Multi-Modal Natural Intelligence” workshop at #AAAI2026!
🔗 https://neuroai-multimodal-workshop.github.io/
@aaai.org
🔗 https://neuroai-multimodal-workshop.github.io/
@aaai.org
Reposted by Blake Richards
Connectome suggests brain’s synaptic weights follow heavy-tailed distributions, yet most analyses of RNNs assume Gaussian connectivity.
🧵⬇️ Our @alleninstitute.org #NeurIPS2025 paper shows heavy-tailed weights can strongly affect dynamics, trade off robustness + attractor dimension.
🧵⬇️ Our @alleninstitute.org #NeurIPS2025 paper shows heavy-tailed weights can strongly affect dynamics, trade off robustness + attractor dimension.
October 30, 2025 at 2:54 PM
Connectome suggests brain’s synaptic weights follow heavy-tailed distributions, yet most analyses of RNNs assume Gaussian connectivity.
🧵⬇️ Our @alleninstitute.org #NeurIPS2025 paper shows heavy-tailed weights can strongly affect dynamics, trade off robustness + attractor dimension.
🧵⬇️ Our @alleninstitute.org #NeurIPS2025 paper shows heavy-tailed weights can strongly affect dynamics, trade off robustness + attractor dimension.
Bienvenu à Montréal Tom!
Great to have you with us. 🙂
Great to have you with us. 🙂
A little overdue but happy to announce that I
1) Got my PhD 🎓
2) Started a postdoc and CNS fellowship with Blake Richards and Guillaume Lajoie (@glajoie.bsky.social @tyrellturing.bsky.social)
Come find me out in @Mila_Quebec, Montreal working on new things neuroAI!
1) Got my PhD 🎓
2) Started a postdoc and CNS fellowship with Blake Richards and Guillaume Lajoie (@glajoie.bsky.social @tyrellturing.bsky.social)
Come find me out in @Mila_Quebec, Montreal working on new things neuroAI!
October 29, 2025 at 7:01 PM
Bienvenu à Montréal Tom!
Great to have you with us. 🙂
Great to have you with us. 🙂
Reposted by Blake Richards
Thrilled that our paper is out today in Nature!
www.nature.com/articles/s4...
www.nature.com/articles/s4...
Sensory expectations shape neural population dynamics in motor circuits
Nature - Experiments with human volunteers and macaques show that expectations produced by probabilistic cueing of future sensory inputs shape motor circuit dynamics in order to increase the...
www.nature.com
October 29, 2025 at 4:11 PM
Thrilled that our paper is out today in Nature!
www.nature.com/articles/s4...
www.nature.com/articles/s4...
Reposted by Blake Richards
My commentary on @anilseth.bsky.social's BBS article: philpapers.org/rec/MICBOF. We should bet on functionalism.
Matthias Michel, Bet on functionalism - PhilPapers
I argue that there is currently no alternative to functionalism. Functionalism explains the differences between types of mental states. No biological theory does. Functionalist theories account for th...
philpapers.org
October 24, 2025 at 2:43 PM
My commentary on @anilseth.bsky.social's BBS article: philpapers.org/rec/MICBOF. We should bet on functionalism.
Reposted by Blake Richards
How does the brain balance learning new things without overwriting what it already knows? Our new paper tackles this long-standing stability–plasticity dilemma during active navigation. With Tony Drinnenberg from the Deisseroth Lab (@deisseroth.bsky.social)
doi.org/10.1101/2025...
doi.org/10.1101/2025...
Environmental Novelty Modulates Rapid Cortical Plasticity During Navigation
In novel environments, animals quickly learn to navigate, and position-correlated spatial representations rapidly emerge in both the retrosplenial cortex (RSC) and primary visual cortex (V1). However,...
doi.org
October 24, 2025 at 3:40 AM
How does the brain balance learning new things without overwriting what it already knows? Our new paper tackles this long-standing stability–plasticity dilemma during active navigation. With Tony Drinnenberg from the Deisseroth Lab (@deisseroth.bsky.social)
doi.org/10.1101/2025...
doi.org/10.1101/2025...
Reposted by Blake Richards
So they didn’t like the ad. Let’s just post Reagan’s 5 min speech against tariffs as it appears on YouTube.
Over and over. On all platforms (some of y’all are still on X).
*1981 Sherrilyn horrified by 2025 Sherrilyn saying “let’s post Reagan’s speech.”
youtu.be/5t5QK03KXPc
Over and over. On all platforms (some of y’all are still on X).
*1981 Sherrilyn horrified by 2025 Sherrilyn saying “let’s post Reagan’s speech.”
youtu.be/5t5QK03KXPc
President Reagan's Radio Address on Free and Fair Trade on April 25, 1987
YouTube video by Reagan Library
youtu.be
October 24, 2025 at 5:14 PM
So they didn’t like the ad. Let’s just post Reagan’s 5 min speech against tariffs as it appears on YouTube.
Over and over. On all platforms (some of y’all are still on X).
*1981 Sherrilyn horrified by 2025 Sherrilyn saying “let’s post Reagan’s speech.”
youtu.be/5t5QK03KXPc
Over and over. On all platforms (some of y’all are still on X).
*1981 Sherrilyn horrified by 2025 Sherrilyn saying “let’s post Reagan’s speech.”
youtu.be/5t5QK03KXPc
Reposted by Blake Richards
Reposted by Blake Richards
Reposted by Blake Richards
Regardless of what explainability/mech interp in AI is actually after, and whether or not they know what they’re searching for, we can confidently say they’re pursuing what systems neuroscience has pursued for decades, with very similar puzzles and confusions.
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
October 8, 2025 at 8:17 PM
Regardless of what explainability/mech interp in AI is actually after, and whether or not they know what they’re searching for, we can confidently say they’re pursuing what systems neuroscience has pursued for decades, with very similar puzzles and confusions.
Reposted by Blake Richards
WTI's Inspiring Speaker Series continues this week with Timothy Lillicrap, “Model-based reinforcement language for reasoning in games and beyond”
10.9.25 | 10 – 11:15a
100 College St, Workshop 1116
🔗 wti.yale.edu/event/2025-10/inspiring-speaker-tim-lillicrap
All Yale community members are welcome.
10.9.25 | 10 – 11:15a
100 College St, Workshop 1116
🔗 wti.yale.edu/event/2025-10/inspiring-speaker-tim-lillicrap
All Yale community members are welcome.
October 8, 2025 at 5:00 PM
WTI's Inspiring Speaker Series continues this week with Timothy Lillicrap, “Model-based reinforcement language for reasoning in games and beyond”
10.9.25 | 10 – 11:15a
100 College St, Workshop 1116
🔗 wti.yale.edu/event/2025-10/inspiring-speaker-tim-lillicrap
All Yale community members are welcome.
10.9.25 | 10 – 11:15a
100 College St, Workshop 1116
🔗 wti.yale.edu/event/2025-10/inspiring-speaker-tim-lillicrap
All Yale community members are welcome.