Between continuous dynamics and discrete decisions. Between simulation and reality. Between what a system predicts and what the world permits.
This space is a notebook for making those boundaries visible—and then moving them.
A map of the questions currently pulling focus.
Learning systems that can adapt under uncertainty without losing sight of the objective—or the cost of being wrong.
Agents that perceive, plan, and act inside worlds that push back—where latency, energy, and safety are first-class constraints.
Understanding the geometry of difficult objectives—and designing algorithms that navigate them with purpose.
Interfaces that turn high-dimensional systems into something a human can see, question, and steer.
An exact numerical rendering of the toy MDP dynamics: 25 uniformly spaced initializations evolving under four coupled update rules.
Trajectories use the supplied update equations, clipping, and arc-length resampling. The luminous metafield is coupled to sampled trajectory heads: cycling stretches it apart while convergence fuses it at equilibrium. In panels (c) and (d), the final 12 display samples ease to the equilibrium exactly as supplied.
A GPU sculpture of rank collapse. One moving particle system loses degrees of freedom continuously—from free 3D motion, to a plane, to a line, to stillness.
READ THE PAPER ↗A deliberately stylized metaphor for dimensionality—not a numerical reconstruction. The same 4,096 particles keep moving, but each collapse removes a direction permanently until the sequence is reset.
Two Dubins cars learn a zero-sum reach–avoid game in self-play. Cyan must enter the goal; coral wins by intercepting it—or simply keeping it out until time expires.
Both two-layer policies are trained from scratch in this tab with alternating REINFORCE updates, discounted returns, running baselines, and Adam. The shaped payoff remains exactly zero-sum at every step. Each displayed match randomizes both positions and headings while rejecting immediate goals or captures. There are no trajectory lines: faint moving agents show exploratory rollouts, while the bright pair plays the current deterministic match. Click the field to relocate the goal.
Every useful system is an argument with reality.
Name the actual system, its state, its constraints, and the thing that would count as progress.
Create a model simple enough to interrogate and rich enough to fail in revealing ways.
Make behavior observable. A metric says what happened; an instrument helps explain why.
Move beyond the nominal case. Perturb, ablate, adversarially probe, and look for phase changes.
Close the loop. Let evidence rewrite the model, the interface, and sometimes the question itself.
A procedural field, rendered on your device. No video. No stock imagery. Every frame is synthesized from time, movement, and position.
WHAT IF THE INTERFACE
THOUGHT IN PUBLIC?
Designed and computed at the edge.
One page. Zero frameworks. Infinite states.