Martino Russi

【誕生】体に装着すると本物のしっぽのようにしなやかに動くバイオニックテールが2年の開発を経てついに登場した。モーションセンサーで動きに連動するこの装置が人間の体の表現域を全く新しい方向に広げようとしている。

It’s not just new, it’s newspeak

DEX-Mouse A Low-cost Portable and Universal Interface with Force Feedback for Data Collection of Dexterous Robotic Hands

今のところ僕はそこそこ上手く機能している。前進あるのみだ。

Research we co-authored on subliminal learning—how LLMs can pass on traits like preferences or misalignment through hidden signals in data—was published today in @Nature. Read the paper: nature.com/articles/s4158…

Congratulations, and it's about time, and it makes me so glad every time to see rigorous science exterminating the illusions propagated by armchair philosophers and corporate propagandists while vindicating the observations of naturalists. arxiv.org/abs/2603.21396

does anyone have suggestions for 3d printed spring designs? i like this one cos it only moves vertically and tilts laterally, though one problem i have is that scaling this design down reduces the displacement i get drastically , due to the base platform being smaller.

first impedance control demo for full force feedback glove

Found a paper that suggests we may have spent years training agents to become hunters of proxy reward when the more basic thing intelligence craves is not a reward at all, but to not run out of viable futures. The paper proposes that behavior is best understood as maximizing future action-state path occupancy, which collapses mathematically into a discounted entropy objective. The agent doesn’t necessarily want to GET something, but rather is trying to keep as many meaningful trajectories alive as possible. The obvious objection is “so it just does random shit? fuck around and find out?” No, this is where it gets pretty beautiful. The agent is variable when variation is cheap and becomes surgically goal-oriented the moment an absorbing state (death, starvation, falling over, etc) gets close enough to threaten its future path space. Variability is the same drive as goal-directedness, just operating under different constraints. The demos are kinda wild: - A cartpole (classic move a cart to keep a pole from falling control task) that doesn’t merely balance but dances and swings through a huge range of angles and positions because why not? The whole point is occupying state space, and rigid balance is a voluntarily impoverished life. - A prey-predator gridworld where the mouse PLAYS with the cat, teasing it and using both clockwise and counterclockwise routes around obstacles to lure it away from the food source before slipping in to eat, using both routes roughly equally. A reward-maximizing agent would collapse to one strategy and exploit it. Here, the agent keeps its behavioral repertoire - A quadruped trained with Soft Actor-Critic and ZERO external reward that learns to walk, jump, spin, and stabilize, and then makes a beeline for food only when its internal energy drops low enough that starvation becomes a real threat The thing that hit me hardest is the comparison to empowerment and free energy principle agents. Both collapse to near-deterministic policies with almost no behavioral variability. This paper’s agents find the highest-empowerment state and exploit it. FEP agents converge to classical reward maximizers. As far as I’m aware, this is the only framework that produces agents you could describe as being “alive.” The AI implication here is that we undertrain for behavioral repertoire. Most systems hit the benchmark by collapsing onto a narrow attractor basin of good-enough trajectories. They’re competent for sure, but brittle too, with one viable plan, executed until the world shifts and leaves them with nothing. The thing I increasingly want from agents isn’t competence per se, but option-preserving competence. I want agents with the ability to keep multiple viable plans alive and switch between them without catastrophe. We’ve been so focused on teaching agents what to want that we never stopped to ask what happens if wanting isn’t the point, if the deepest drive isn’t necessarily toward anything, but away from the walls closing in. paper: nature.com/articles/s4146…

Michael Levin says aging may not just be a biology or physics problem. It’s a cognitive one. Almost like a boredom theory of aging. What happens when a system has nothing left to do?

Releasing the Unfolding Robotics blog! Time to unfold robotics: we trained a robot to fold clothes using 8 bimanual setups, 100+ hours of demonstrations, and 5k+ GPU hours. Flashy robot demos are everywhere. But you rarely see the real story: the data, the failures, the engineering. We’re sharing everything: code, data, and details in the blog → huggingface.co/spaces/lerobot…

AI has gone too far. Harry Potter "6 7" platform. Credit: Unhindered Studios

@SchmidhuberAI this unc is a real genius, the most exciting thing i've read about this week. i should read more old books, old papers, and scroll less.

🙌Feel Robot Feels: Tactile Feedback Array Glove for Dexterous Manipulation Project website:trap-1.github.io/TAG.github.io/ Paper:arxiv.org/pdf/2603.28542 Stay tuned—code will be open-sourced shortly! [🍻]

🇨🇳 China's planar maglev robotics in action. “XBot” movers levitate 1–2 mm above a tiled electromagnetic “Flyway” surface and glide in perfect 2D coordination—no wheels, no friction, zero wear. Tech from Planar Motor: 6-DoF precision motion for factories

@ramkumarkoppu @tejessrivalsan canon ligma

@tejessrivalsan @NepYope What camera is on the bird?

after the overwhelming support for EGO-SNAKE, i’m excited to share EGO-BIRD 100,000 hours of pov bird footage to train the next generation of autonomous drones

Hmmm, that will be different....

My ideal timeline: Growing up in the 90s, discovering neural nets, scaling laws, and building an artificial consciousness.