📱Product Designer @sap 🎛 @iclinz 🎓 人大 RUC 🚲 @BromptonBicycle rider 🤹‍♀️ Amateur Juggler

Munich
Joined February 2009
that's fantastic project
This book is basically a cheat code for logo design, so I turned the whole book into a site so yall designers and devs can grab every mark as svg. 1,504 marks and counting 👉 symbools.com drop a dm if there's another book you want me to add
1
3
140
Nathan Guo retweeted
Holy sh*t I spent weeks turning Claude Code into a design studio. no Figma license. no agency. no plugins I had to pay for. here's the stack I used and it's embarrassingly simple: -> graphify: teach Claude your brand dump your guidelines, logos, PDFs and old projects into one folder. graphify turns it into a knowledge graph, so every design Claude makes follows your rules instead of guessing. 134k stars, Y Combinator. uv tool install graphifyy -> graphify install -> /graphify . github.com/Graphify-Labs/gra… -> Figma-Context-MCP: Figma straight to code it hands your actual Figma file to the agent. the README says it builds designs in one shot, and does it better than pasting screenshots. github.com/GLips/Figma-Conte… -> Penpot: the open-source Figma free, open source, and its MCP server lets AI read and edit your designs, then hand them to code and back. github.com/penpot/penpot -> React Bits: the "expensive" look, for free the biggest open-source library of animated React components. those smooth hover effects and text animations you see on high-end sites? copy, paste, done. github.com/DavidHDev/react-b… -> HyperFrames: designs that move write HTML, get a finished video. made by HeyGen for AI agents. your landing page can now have its own launch video by tonight. claude plugin marketplace add heygen-com/hyperframes -> claude plugin install hyperframes@hyperframes github.com/heygen-com/hyperf… -> MCP for Blender: 3D without learning Blender connects Claude to Blender. describe a scene, the agent builds and edits it in real 3D. github.com/ahujasid/mcp-for-… the order that works: brand into graphify -> design in Figma or Penpot -> Claude builds it with React Bits -> HyperFrames makes the promo -> Blender adds the 3D hero shot the uncomfortable part: tools used to be the moat. now everyone has them for free. the only thing that still separates good design from AI slop is taste. and taste is the one thing you can't install. bookmark this. your next client will ask why you're suddenly so fast.
53
127
13
894
61,588
need to dig down on this😍
HOLY F*CK, motion studio in 20 repos. 20 open-source skills for Opus 5.5. Animation. Physics. 3D. Sound. Delivery. 01 Remotion → React video engine github.com/remotion-dev/remo… 02 HyperFrames → HTML-to-video renderer github.com/heygen-com/hyperf… 03 Anime.js → Timeline choreography github.com/juliangarnier/ani… 04 React Spring → Spring animation github.com/pmndrs/react-spri… 05 PixiJS → GPU-powered 2D graphics github.com/pixijs/pixijs 06 p5.js → Generative visuals github.com/processing/p5.js 07 Paper.js → Vector paths github.com/paperjs/paper.js 08 Matter.js → 2D physics github.com/liabru/matter-js 09 Three.js → 3D scenes github.com/mrdoob/three.js 10 Rapier → 3D collisions github.com/dimforge/rapier 11 OGL → Custom shaders github.com/oframe/ogl 12 tsParticles → Particle effects github.com/tsparticles/tspar… 13 glTF Transform → 3D asset optimization github.com/donmccurdy/glTF-T… 14 GL Transitions → Shader transitions github.com/gl-transitions/gl… 15 OBS Studio → Screen capture github.com/obsproject/obs-st… 16 Chatterbox → Voiceovers github.com/resemble-ai/chatt… 17 Tone.js → Synths and sound effects github.com/Tonejs/Tone.js 18 faster-whisper → Caption transcription github.com/SYSTRAN/faster-wh… 19 OpenCut → Timeline editing github.com/OpenCut-app/OpenC… 20 FFmpeg → Encoding and delivery github.com/FFmpeg/FFmpeg Brief → prototype → animate → render → ship. Bookmark this. Go build something worth watching ↓
38
Nathan Guo retweeted
I made a skill that turns your app into a demo in HTML. So they stay sharp at any size, loop, scrub, jump to any step and stand still for reduced motion. I open-sourced it as a skill: fil.design/skills/html-demo
32
59
8
664
37,196
insane progress 🫨
Unitree Introducing: H2-X Kung Fu Legend Guardian🤖 Powerful performance to serve and guard you, with a maximum endurance of approximately 8 hours. Please use the robot safely and in a friendly manner.
42
look even more sleek
Opus 5.5 is great for motion design but... /colorfigures skill will turn Claude into a premier illustration studio • hand-inked isometric figures from a photo or a name • every part works: lids open, disks go in, screens boot • one HTML file with colour swatches & wobble slider send the skill to your Claude: > april-zhu.com/colorfigures
26
Hardware looks scary until you break it down into small steps. So I built an app that takes you through Arduino one circuit at a time. Made with Opus 5.5 learn-arduino-red.vercel.app
326
1,514
155
14,323
822,824
Nathan Guo retweeted
Hi, it's Darshita. I am a designer. And I'm pitching myself in public 'cause I'm done with a year full of anxiety. Everyone says design is dead and AI killed it. But the real parasite was hiding in plain sight. So here's my film, DESIGN IS DEAD. She's bold, fearless and very PINK 💖 Hiring? My DMs are open.
1,331
2,987
1,157
42,301
5,403,448
Nathan Guo retweeted
我愿称之为史上最强 skills skills.wheresryan.sh/anatomy
150
741
38
6,294
429,936
these are fun!
made 3 new brushes 1 - nyc subway lines 2 - little figures from architecture drawings 3 - gunpla components spruced up the ui too so you can try many brushes at once btw, go crazy here: kool-brushez.vercel.app/
1
21
2,613
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
4,028
8,283
6,820
76,634
40,131,329
A few gems I’ve found in the past couple of weeks: aicss.dev → UI blocks for AI agent interactions ui.halaska.com → UI components for AI products bencho.dev → UI blocks for interactive AI experiences builtbydesigners.com → showcase of products built by designers torph.lochie.me → text morphing library with zero dependencies typehug.aliszu.com → typography utility for keeping text together
36
96
4
1,305
101,272
Nathan Guo retweeted
Today, we're sharing new research on Solaris, our first Interface World Model. Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new interfaces, across structural similarity and information retention. Read more and request early access at the link below.
178
388
325
3,401
748,085
Nathan Guo retweeted
Next view prediction is the key to Atlas, enabling us to unify pixel-level generation and reconstruction. @jcjohnss @BenMildenhall @martin_casado and I had a deeper discussion on some of the most exciting technical innovations of Atlas, our newly released world model for spatial intelligence!
World Labs co-founders Fei-Fei Li, Justin Johnson, Ben Mildenhall, and a16z's Martin Casado on Atlas, a world model for spatial intelligence: LLMs are built on next token prediction. Video models are built on next frame prediction. Atlas is built on new view prediction, and it's the first model to unify pixel generation and pixel reconstruction, two problems computer vision has kept in separate tracks for half a century. The practical result is a 50 to 100x reduction in what it takes to digitally capture a 3D representation of a space. Previously, you needed 100 to 300 photos of a single room. Atlas can work from just three. In this conversation, they get into the slow motion shot from The Matrix that took hundreds of cameras and now takes three iPhones, the overnight Slack message that made them bet the company in five seconds, why robotics is bottlenecked on data rather than chips, and the case that new view prediction is AI-complete. 00:00 Intro 01:50 The Matrix slow motion scene now takes three iPhones 02:48 Why new view prediction is the primitive 07:10 Unifying generation and reconstruction 11:15 Gaussian splats became the bottleneck 14:17 Dense capture used to mean 300 photos 17:30 Why reconstruction needs generation to fill the gaps 18:44 The LLM lesson image models missed 23:39 The video that made them go all in 28:04 3D design is 95% revisions 30:50 The problem in robotics is data, not chips 32:48 Why a robot policy can't be trained like an image model 34:44 When the simulator becomes the planner 36:45 Frozen time required footage full of movement 40:57 Why new view prediction is AI-complete 42:43 Nature gave animals eyes but not trees YouTube: youtube.com/watch?v=qn1QDDBn… @drfeifei @jcjohnss @BenMildenhall @theworldlabs @martin_casado
35
113
8
981
119,557
Nathan Guo retweeted
I'm so excited that our @theworldlabs team has achieved a major milestone today! Introducing Atlas - a first of its kind multimodal world model trained from scratch! 🚀 Atlas is capable of generating frames with pixel-perfect camera control, reconstructing large scenes from as few as one single input image, simulating space-time by reframing videos, natively outputting 3D spaces from one or more input images, composing multiple posed images into a consistent 3d world, and more! This is the best camera conditioned world model ever, opening doors to many possible use cases from VFX to robotics. I'm so so so proud of our team!♥️
Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.
326
1,099
194
9,724
1,264,052