
Technology and cities - open design, science, culture etc. Building @ArchiyouApp
Joined May 2013
- Tweets10.6K
- Following4.1K
- Followers830
- Likes847
Pinned Tweet
Today I launch the website of @ArchiyouApp at archiyou.com. A cloud platform for designing with a code language so simple that I hope it can introduce designers to coding and programmers to design.
OSCity retweeted
Assembly guide (beta): drop in a STEP file, get an animated, editable build guide. Print the instruction sheet or share it as one HTML file.
It runs in your browser and nothing is uploaded. Open source, Apache-2.0.
github.com/AverageArc/assemb…
OSCity retweeted
Introducing FieldCraft 🌊
github.com/tangency-labs/fie…
Another free, open-source project from Tangency Labs, spun out of SolidCraft, by @jyviko: one modeler for structures, heat and fluids, in pure Rust. Parametric part in, verified results out.
- Meshes follow the exact CAD geometry, with no tessellation facets on curved parts
- Automatic hex and tet meshing, including O-grids for holes and revolved tubes
- Lattice Boltzmann CFD with curved walls, checked against pipe and Couette flow
- Heat transfer with radiation, including solids in a flow
- Every result checked against theory, for engineers and AI agents alike
OSCity retweeted
MIT Advanced Data Structures course: courses.csail.mit.edu/6.851/…
🌟💫⚡️💥✨
Video lectures, lecture notes, problem sets, GitHub, and more
OSCity retweeted
SolidCraft 0.40.0 release candidate is out 🦾
This is the big one: SolidCraft now runs on solidcore, a new pure-Rust geometry kernel. Every boolean, fillet, shell and thread goes through it. It's a pre-release, so please test it and tell us what breaks.
- Try it in your browser: app-rc.solidcraft.io
- Download it: hit the Pre-release button at solidcraft.io
OSCity retweeted
Yann LeCun was right & nobody in this industry wants to say it out loud.
109 million parameters beat 72 billion.
He has spent years saying scale is not the thing that makes a model understand the world. Meta bet the other way. He left in November and started his own lab in Paris.
Last Thursday he published the proof.
The theory everyone has been running on since 2024 is that if you train models big enough, on text, on images, on sound, they all end up with the same picture of reality inside them. Size does it. Nobody ever proved that part.
Randall Balestriero and LeCun proved it. And the proof says size was never doing the work.
What does the work is which two things you show a model together.
A photo and the caption of that photo are two views of one thing. Models trained on pairs like that get there fast.
Two paragraphs pulled from the same document are not two views of one thing. Models trained on those get there slowly and expensively.
Next word prediction is the second kind. That is what every chatbot in the world runs on.
In their tests the first method reached the same understanding after 21.6 million examples. Next word prediction needed 900 million.
And a 109 million parameter text model ended up closer to an image model's view of the world than a 72 billion parameter language model was.
660 times smaller.
OSCity retweeted
I've been learning "Ask Me Now" by Thelonius Monk on piano. I visualized my playing in 3d with Gemini 4 Argon. Interactive link in 🧵 sound on 🔉
OSCity retweeted
deepdive into how we built our design agent (along with oss code)
i use this at least a few times a week for slides, gifs, images, etc
How we built Content Studio, an open-source design agent in Slack that makes on-brand videos, graphics and decks, and the harness that powers it. View article
OSCity retweeted
I highly recommend cloudflare's security audit skill: github.com/cloudflare/securi…
Run it on all your software. Run it with the free models. Use it even if you used a model to audit something - it will find much more things. Works in all agent harnesses and is model independent.
Hugging Face 刚刚支持 OpenUSD ,NVIDIA 反手就甩出 2500+ 个 SimReady 3D 资产:叉车、机械臂、发动机、医疗设备……全部免费放在 Hub 上,还能直接用大白话搜!
以前搭一个仿真场景要建模好几周,现在点几下就能拿到。
具身智能的门槛也在松动。机器人时代不远了。🤖🔥
We just launched OpenUSD support on the @huggingface Hub 🎉
Yesterday, @nvidiaomniverse put 2,500+ SimReady assets on the Hub. Forklifts, robot arms, engines, hospital equipment, all OpenUSD. You can also search the whole library in plain English
huggingface.co/spaces/nvidia…
huggingface.co/datasets/nvid…
OSCity retweeted
One of my hero's in CAD is George Allen. Here is his latest presentation comparing BREPs and Implicit geometry from the #CDFAM conference in Japan: youtube.com/watch?v=P0gAMHoK…
OSCity retweeted
Today in 1843, the theory of quaternions was born when a sudden thought came to William Rowan Hamilton as he was walking with his wife along the Royal Canal in Dublin, Ireland. It was the fundamental formula:
i² = j² = k² = ikj = -1
OSCity retweeted
So NVIDIA open sourced a b-rep kernel, and X blew up. I was a bit surprised by the hype - because it only means that pretty much nobody understands what SMlib is.
So what is it, really, and (why) does it matter? 👇
My WebGPU path tracer is open source! 🎉
Physically based rendering, running right in your browser. MIT licensed.
- WebGPU compute shader path tracing, with WebGL 2 fallback
- Two-level BVH built using parallel Web Workers, based on TinyBVH. A 4.6M-triangle scene's BVH builds in just 0.5s on my M4 Max
- Clean results from just a few samples with OIDN denoising
- OpenPBR 1.1 materials
- Physical camera with f-stop depth of field, AgX tone mapping, and bloom
- Drop-in Three.js scene synchronization
github.com/pissang/mutracer
OSCity retweeted
Meet Kitten TTS 2: a text-to-speech model that clones voices and speaks multiple languages. With 7,737 downloads and 55 likes, it's already making waves. Ready to give your apps a voice?
OSCity retweeted
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
OSCity retweeted
[1/4] 🏛️ Building Rome from a Single Image 🏛️
We reconstruct 3D scenes from the input image, including geometry beyond the observed view across indoor, outdoor, and large-scale scenes.
👉 Project: build-rome.github.io/
OSCity retweeted
One little trick to make your codebase more readable:
* Install cccc github.com/moznion/cccc
* Configure it with max-cognitize and max-cyclomatic 40
* In AGENTS.md, instruct to validate that cccc passes
* Have one agent in ultracode refactor everything until cccc passes
🤩
OSCity retweeted
Goodbye Photoshop... it's not been nice knowing you
Mac/Windows/Linux full rust implementation
OSCity retweeted
Todos los productos de Adobe reimplementados desde cero, gratuitos y de código abierto
→ getartcraft.com/apps




























