Skip to content

Work

ALLRESEARCHPRACTICEEXPLORATIONS

23 projects

The Thoughts

  1. we see in silenceSEP 2026So your eyes signal your brain when they see light? Well, no. It is literally the opposite.
  2. where the plant isAUG 2026You know how, when you live with your mother, one day you think that plant would look better next to the chair than next to the sofa, so you move it, and the moment she walks in she goes ballistic, as if you had changed the whole feel of the room? Well.
  3. explaining thingsJUL 2026How do you explain a complex, honestly boring technical subject so someone leans in instead of glazing over?
  4. adjacency is not accessJUN 2026A floor plan tells you which rooms touch. It will not tell you which rooms you can actually reach, and the gap between those two drawings is where the architecture is hiding.
  5. buildings that respondJUN 2026Right now a building is a fixed guess. Someone chose the ceiling height and the window size years before you arrived, and you live inside their averaged assumptions whether they fit you or not.
  6. experiences are dataMAY 2026You learned what a room does to you by being in rooms. Nobody sat you down with a dataset.
  7. comfort as dataMAY 2026You don't walk into a room and average your experience. You walk in and the thing that's wrong is the thing you notice: the glare, the echo, the cold draft on the back of your neck.
  8. when the tool scores peopleAPR 2026I build things that give a room a score. The obvious next question, and the one I would ask me, is what happens the day somebody uses that score to decide who gets the room.
  9. latent spaceAPR 2026Machine learning borrowed the word space from us, and I would like to check what it did with it.
  10. drawing as interfaceMAR 2026For most of my life the drawing was the output. You designed the thing, then you drew it to prove it existed.
  11. behavior information modelingJAN 2026For thirty years we've been getting very good at Building Information Modeling: every beam, every duct, every clash, tracked to the millimeter.
  12. heritage meets new techDEC 2025The usual choice with an old building is a trap: treat it as a museum piece no one may touch, or drop a glass-and-steel box in the middle and call it modern.
  13. neuroaestheticsDEC 2025Neuroaesthetics is the unglamorous name for a question everyone already feels: why does one room settle you and another keep you on edge?
  14. evolutionary searchNOV 2025Evolutionary search is what I reach for when a problem is too tangled to solve head on: describe what good looks like, then let a population of designs breed, mutate, and compete until something clever falls out.
  15. physics solversNOV 2025A physics solver is the most honest collaborator I have: it doesn't care what I intended, only what I actually built.
  16. computationOCT 2025Computation is not the same as using a computer, and separating the two took me longer than I would like to admit.
  17. what an llm actually isSEP 2025A large language model is a machine that guesses the next word. That is not me being kind to you, that is the whole thing.
  18. generative aiDEC 2023Generative AI made the inspired gesture free. Anyone can produce a thousand renders before lunch, and a render is a promise, not a product.
  19. extended realitySEP 2022I started in a lab strapping headsets onto students to see whether a lesson lands harder when you can walk around inside it.
  20. connecting the dotsJUN 2020When the art class was asked who here dislikes drawing, mine was the only hand that went up. Awkward.

NeuroSpace

Can you visualize the parameters that affect how a room makes you feel? 

TYPEComputation & ResearchWHEREIAAC · MACADWHOSOLOSTACKVUE 3 · THREE.JS · FORCE DENSITYLINKSLIVE APP (opens in new tab)GITHUB (opens in new tab)BLOG (opens in new tab)
1 / 15

WHAT

You are sitting in a room right now, and its defaults are quietly working on you: the ceiling height nudging your cortisol, the daylight setting your circadian clock. NeuroSpace makes that invisible layer legible: change one thing, and a membrane room form-finds itself live while a score answers back. The first version ran its geometry through Grasshopper, on a server that has since died. This one runs entirely in your browser.

WHY

This is the thesis I keep circling: BIM, reframed from Building Information Modeling to Behavior Information Modeling (BeIM). The information that matters is not just what a building is made of; it is what the building is doing to the person inside it.

HOW

  1. Describe the room as parameters, not geometry: ceiling, walls, openings, organic form, plants, each a slider.
  2. Form-find it as one tensioned membrane by force density, the method written for Frei Otto’s Munich Olympic roof: each drag re-solves it in milliseconds.
  3. Score it in the browser against a control room: a transparent weighted sum you can split the screen with, or flip to by holding F.
  4. Write every rule in code with Claude Code as a pair: I set the rule, then check it against its source.

WHAT CAME OF IT

It shipped live, then the server under it died. I rebuilt it instead of letting it go, partly for Dr. Cleo Valentine’s note, the frame I kept: treat every score as a hypothesis. So the lab now tests one at a time, against a control. Partly as an excuse to form-find without Grasshopper. The weights sit in the public repo, to argue with. The score stays a heuristic: it never measures your body.