Skip to content

Work

ALLCOMPUTATION & RESEARCHDESIGN & PRACTICEEXPLORATIONS
THE BOOK (PDF)

21 projects

The Thoughts

  1. 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.
  2. neuroaestheticsDEC 2025Neuroaesthetics is the unglamorous name for a question everyone already feels: why does one room settle you and another keep you on edge?
  3. physics solversAPR 2026A physics solver is the most honest collaborator I have: it doesn't care what I intended, only what I actually built.
  4. generative aiJUN 2024Generative AI made the inspired gesture free. Anyone can produce a thousand renders before lunch, and a render is a promise, not a product.
  5. 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.
  6. 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.
  7. 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.
  8. 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.
  9. heritage meets new techAPR 2026The 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.
  10. 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.
  11. connecting the dotsJUN 2020When the art class was asked who here dislikes drawing, mine was the only hand that went up. Awkward.
  12. pelagñouJUN 2026Some projects hand you a tool; Pelagñou handed me a library card.
  13. explaining thingsJUL 2026How do you explain a complex, honestly boring technical subject so someone leans in instead of glazing over?
  14. 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.

Narkomfin as a Graph

RESEARCH

What does a building's floor plan look like as a graph?

Read a 1930 experiment in communal living as a graph and its real spatial units turn out to be vertical slices, not rooms.

MACAD GRAPH ML · TEAM OF 4

PYTHON · GRAPHSAGE · LOUVAIN

BLOG (opens in new tab)
1 / 8

WHAT

The Narkomfin building (Ginzburg and Milinis, 1930) is the constructivist experiment in communal living. We converted its Type K and Type F duplex units from Rhino geometry into spatial graphs, grid sampling the plans, ray casting the connections, adding the stairs as vertical links, then read the building through centrality, shortest paths, and community detection. A team of four, all hands on everything: Lakzhmy Mari Zaro, María Sánchez Domínguez, Charles Abi Chahine, and me.

WHY

A floor plan shows you a corridor. The graph shows that every single path runs through it. Reading a canonical building as data is a way to test whether the numbers can see what the architecture is doing on purpose.

HOW

  1. Sample each level into a walkable grid from the Rhino model, ray casting for connections and adding stairs as the vertical links.
  2. Read the graph: closeness and betweenness centrality, shortest paths, and Louvain community detection over both unit types.
  3. Run a GraphSAGE room classifier pretrained on Swiss apartments across the building and compare how each unit type reads.

WHAT CAME OF IT

The communities land as vertical, corridor-bound slices, not rooms or floors. The team’s classifier read the conventional Type F rooms at 91.3% but the communal Type K at only 67.9%, and the low number is the finding: the model telling you this building does not follow the domestic rules, exactly as its architects intended.