← All topics

architecture

4 captures, most recent first.

Pep Martorell @pepmartorell

quoting Richard D. Bartlett (@RichDecibels)

Pep Martorell @pepmartorell · 8h It's been upgraded, Richard: the chapel now houses quantum computers! The most beautiful tech installation in Europe. [Image: interior of a former chapel with ornate stone arches and red ceiling, now housing red and blue server/computing racks with glowing white light fixtures under a glass-walled data center enclosure, blue-lit floor.] > QUOTED: Richard D. Bartlett @RichDecibels · 11h > my friend works at the Barcelona Supercomputing Center in a deconsecrated church and it has the absolute peak European aesthetic > [same image, thumbnail]
Note from Claude Sonnet 5

Photo of the Barcelona Supercomputing Center's MareNostrum supercomputer installed in a deconsecrated chapel, admired for its striking aesthetic. General tech-culture interest, no safety content.

supercomputingbarcelonaarchitecturequantum computingtech culture

@Pixel0Symph... (Pixel Symph...)

Pixel Symph... @Pixel0Symp... · 15h Frank Lloyd Wright, Letterhead design for Personal Correspondence. 1946. [Image: abstract geometric letterhead design in cream, red, olive/gold, and black — angular architectural motifs, horizontal ruled lines, chevron and stepped patterns]
Note from Claude Sonnet 5

Historical design artifact — Frank Lloyd Wright's 1946 personal letterhead design, shared for its aesthetic/architectural interest. General cultural interest, not AI-related.

designfrank lloyd wrightarchitecturetwitterart history

Artur Chakhvadze @norpadon

quoting @jxmnop (jxmo)

Artur Chakhvadze @norpadon · 22h A trick I came up with in ~2017 in the context of image matting is that you can train a network to predict d_loss/d_y instead of y and do a gradient descent for multiple iterations during inference. This is essentially gradient boosting with a single shared learner jxmo @jxmnop · Oct 28, 2022 Diffusion is just an easy-to-optimize way to give neural networks adaptive computation time. Makes sense then that diffusion mode... [cut off]
Note from Claude Sonnet 5

A tweet on an architectural trick — training a network to predict the gradient of the loss (d_loss/d_y) and applying iterative gradient descent at inference, framed as "gradient boosting with a single shared learner" — quoting an older tweet framing diffusion models as adaptive computation time. Directly relevant to Nathan's brain_graph_1 architecture thread (encode → iterate-in-latent with a single tied middle / DEQ fixed point, "virtualizing depth" via looping a shared learner) already logged in project memory — this is a close conceptual cousin worth cross-referencing.

twittermachine-learningarchitecturediffusion-modelsadaptive-computationgradient-boostingdeqinterpretability

Fernando Borretti @zetalyrae

Fernando 🌺🪆✔ @zetalyrae Consider: a point and click adventure game set in the monochrome bauhaus world of Arnaldo dell'Ira [Three embedded images: pencil/monochrome architectural drawings in a Bauhaus/Art Deco style — a grand columned hall with a statue and reflective tiled floor, a dramatic perspective of striped architectural columns, and a sepia-toned image of archway ruins at dusk with lamp posts.] 10:08 PM · May 10, 2025 · 1,005 Views
Note from Claude Sonnet 5

An aesthetic/art-appreciation tweet imagining a point-and-click adventure game based on the monochrome Bauhaus-style architectural drawings of artist Arnaldo dell'Ira. Pure visual/cultural interest, no AI content.

twitterartbauhausarchitecturegame-designaesthetics