Blake Richards

Researcher at @mcgillu combining AI and neuroscience. Also on Bluesky (@tyrellturing.bsky.social) and Mastodon: @[email protected].

[Blake Richards @tyrell_turing]

1/15) What could drive AI agents to cooperate with each other, even if there is no chance for reciprocity or pay back? 🤔

🧵 Our team at Google, Paradigms of Intelligence, uncovered new paths to cooperation and a new game theory for foundation models 👇

[Mariia Drozdova @MariiaD_ML]

1/5
Continuous diffusion may be better at discrete reasoning than standard sampling suggests.

We took SRM's MNIST-Sudoku Hard checkpoint (arXiv 2502.21075) and changed ONLY the sampler:

❗ 0.8% → 65.7% valid boards solved, without retraining. Why does standard sampling fail?🧵

[Blaise Agüera (@blaiseaguera.bsky.social) @blaiseaguera]

Proud to share new work from our Paradigms of Intelligence team toward AI designed for decentralized hardware, where low-power communication and fault tolerance are critical requirements. Using Neural Cellular Automata (NCA), @mayalen_etc and her co-authors show that spatial locality is not a barrier to complex multi-step reasoning.

Read the full paper on arXiv: https://t.co/B3M4E9CCdb

[Blake Richards @tyrell_turing]

@jialiiiz @aidan_sirbu I think they were pretty natural

[Blake Richards @tyrell_turing]

Check out our new model for creating realistic motion in a virtual rat during RL!

I think of this as providing the "brainstem and spinal cord" for NeuroAI researchers who want to simulate realistic neuroscience experiments.

Congrats to @aidan_sirbu for getting this out!

[Aidan @aidan_sirbu]

1/14) Virtual animals are a long-standing goal in neuro-AI, but they should actually behave like real animals.

We present SCAMPER: a virtual rat for RL studies that moves naturally during both exploration, and goal-directed behavior.

Project page: https://t.co/s0J1igsgEv

[Jiamin Wu @JiaminWu7]

Our recent work presents a 1-gram wireless mesoscope for cortex-wide imaging at single cell resolution in naturally behaving mice, published in @Nature . It's interesting to see large-scale neural activities in multiple mice within a very natural habitat. https://t.co/Nbp67KFTDc

[Blake Richards @tyrell_turing]

@jialiiiz @aidan_sirbu It found the same ways to move as real rats, for example, it learned to gallop at fast speeds even though that wasn't in the training data.

[Nima Dehghani @neurovium]

Paper out!
https://t.co/dQVHu4cuJP

[Blaise Agüera (@blaiseaguera.bsky.social) @blaiseaguera]

Friends in San Francisco: Join me at @longnow on October 22 for a conversation on interdependence with @baratunde.

We'll explore cooperation as the core governing principle of nature and synthetic minds, why intelligence is inherently collective, and what this means for our shared future.

Get tickets here: https://t.co/r8kreGvqeD

[Todd Morrill @tee_oh_double_d]

DeltaNet-PC is out! It turns out that predictive coding offered a native mechanism for test-time memorization of sequential data all along. The crucial insight was to treat updates to the fast associative memory as an inferred latent variable, not a long term learned weight.

[Sonia Joseph @soniajoseph_]

Thank you Rocket Drew @rocketalignment for hosting me on The Information about world models and interp!

Rocket is a precise & careful technical interviewer who is a pleasure to talk to, and who let me go into a technical rabbithole while keeping the convo accessible!

[Mila - Institut québécois d'IA @Mila_Quebec]

Mila's annual supervision request process is now open to receive MSc and PhD applications for Fall 2027 admission! For more information, visit https://t.co/r01eLcXtZw

[Yoshua Bengio @Yoshua_Bengio]

Over 400 researchers and I have signed this open letter calling for the AI and security communities to come together to improve alignment and containment approaches in order to protect our critical infrastructure and digital systems.

https://t.co/KieWSpurn9

[Nicolas Papernot @NicolasPapernot]

Over 400 academics in 30+ countries signed our open letter calling for immediate changes in AI development and deployment practices to ensure that cybersecurity incidents do not continue to occur, as future incidents will be far more damaging to our critical infrastructure.

[Blake Richards @tyrell_turing]

I signed! This is some common sense stuff.

[Nicolas Papernot @NicolasPapernot]

Over 400 academics in 30+ countries signed our open letter calling for immediate changes in AI development and deployment practices to ensure that cybersecurity incidents do not continue to occur, as future incidents will be far more damaging to our critical infrastructure.

[Sonia Joseph @soniajoseph_]

We've released our first blog post on interpretability as a critical ingredient for scaling physical intelligence in a way that is data efficient, generalizable, and verifiable!

[Friedemann Zenke @hisspikeness]

1/ Why does predicting in latent space (JEPA, CPC, SimCLR...) work so well on messy data, with changing lighting, camera angles, and busy backgrounds? The usual answer: it can ignore nuisance. But that answer holds a conundrum.

[Blake Richards @tyrell_turing]

@SarveshGharat12 It's double blind.

[Blake Richards @tyrell_turing]

PSA for all the folks submitting AI generated papers to ML conferences:

ACs are now being given the power to desk reject papers for being incomprehensible, and we will use this power.

Make sure your paper is actually human parsable, FFS!

[Blake Richards @tyrell_turing]

@EmilevanKrieken Same!

[Friedemann Zenke @hisspikeness]

1/9 New paper led by Michael Hauri & Peter Buttaroni: “Learning Commute-Time-Preserving World Models for Planning.” We show how to shape a world model's latent space so its distances mean something for planning.🧵

📄 https://t.co/qP2aRLPC8U
🌐 https://t.co/DM66MWNCbL