Burt.K retweeted
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
Burt.K retweeted
My dear friends, I’d like to show you my latest toy project
Introducing Handwired: turn your regular JavaScript code into a neural net!
- no training
- exact outputs vs the JS program
- fully differentiable
All runnable in a browser, without GPU
Burt.K retweeted
Xcode 27.2b3 quietly ships a new CLI: xcrun xcodeproj
Targets, build phases, groups, build settings, xcconfigs, SPM packages: all from the terminal, for both pbxproj and the new JSON xcproj format.
Zero docs so far, but it's clearly made for agents 🤖
3D to Video is now live on H3 Max, the fastest video model on the market and ranked #1 for video editing.
Upload a Blender previs up to 15 seconds, and H3 Max turns it into photoreal video while preserving camera movement and shot timing.
Add reference images to carry specific characters and environments into the final shot.
Burt.K retweeted
开源一个新Skill:3D镭射卡片生成
最近刷到一堆 GPT 6 Astra 玩 Blender 的视频,本来只想围观,但是想到它自己会生图,又能直接操作 Blender,两件事凑到一起,镭射 3D 卡牌就变成一句话的事。
真人照片能做,动漫立绘也能做,卡牌转起来闪出全息光很像小时候攒的干脆面卡。
干脆直接把整套流程封成了一个 skill,一键跑完,拆图、视差、镭射、闪星都全自动。
github:github.com/EverettFish/holo-…
🔥你敢信?GPT-6 Astra把整座悉尼城做成了能逛的3D活模型!
🔹输入:地图 + 真实照片
🔹工具:Blender 出精细模型,Three.js 做交互展示
🔹效果:能缩放、环绕旋转、一键切换白天/夜晚光影
🔹细节:歌剧院、海港大桥、街道比例和建筑材质基本对得上
城市规划、建筑作品集、城市探索直接开挂,周末下午就能干完一座城。
#GPT6Astra #悉尼3D还原 #Blender #Threejs #城市规划 #AI建模 #openai #codex
xitter.cf/nft_chen/status/209654…
Hi Friends, for my first project created with GPT-6 Astra, I built the entire city of Seoul in 3D—a small revolution in digital geography! 😄 This interactive 3D miniature covers all of Seoul and its surrounding areas, and you can explore it yourself. It includes:
• All 25 districts of Seoul and approximately 267,000 simplified building models
• Rotate, zoom, and pan controls, plus an automated fly-through of 14 landmarks
• Day, sunset, and night modes
• Mobile touch support
The buildings were generated from real-world map data, with their shapes simplified for performance. Terrain and building heights are exaggerated by 4× to make the cityscape easier to see.
The entire process—from creating the project to completing deployment—took 43 minutes and 38 seconds minutes.
Please note that the buildings are simplified models based on locations and footprints recorded in OpenStreetMap. Where height data is unavailable, estimated heights derived from the source data are used. The landmark models are interpretive recreations designed to emphasize their distinctive features, rather than survey-grade or photorealistic reconstructions of every building.
The project is based on real road, waterway, elevation, and building data.
• Maps and buildings: OpenFreeMap / OpenMapTiles / © OpenStreetMap contributors · ODbL
Data snapshot: August 30, 2026
• Terrain: AWS Terrain Tiles / Mapzen · SRTM and other sources
• District boundaries: southkorea/seoul-maps · Statistics Korea’s 2013 boundaries
These may differ from Seoul’s current administrative boundaries.
• 3D rendering: Three.js
• Additional components: terrain, road, and building data, subject to their respective licenses
seoul-3d-atlas.synabreu.chat…
Introducing fal's H3 Max Director, the first natively continuous real-time frontier video model for action-controlled long-form generation.
Unlike H3 Max and other video models, H3 Max Director generates a single continuous video stream, maintaining context over time rather than chaining together discrete clips.
It’s the technology behind fal.live, our experimental infinite AI livestream where viewers interact with and shape what gets generated in real time.
Now, we’re making the underlying model available via API.
For the first two weeks, all H3 Max Director generations are 75% off.
GPU Canvas is now live for everyone.
Rive's low-level GPU layer for 3D, shaders, and custom effects is out of Early Access and in the production editor today.
Write your shaders once in WGSL. Rive compiles them for Metal, Vulkan, Direct3D, WebGPU, and WebGL. It adds 25KB to the runtime.
Burt.K retweeted
Chinese researchers just published a paper with a brutal title: "The End of Software Engineering."
The core point is that writing code is completely finished as a skill.
Your brain can only hold so much state and so many dependencies before it hits a wall.
An agent doesn't have that ceiling, and its capacity only grows with compute.
So the human stops being the one who writes the code.
You become the intent architect, the one who directs the agents and audits the result.
Code becomes the throwaway, and judgment becomes the job.
That's exactly why i wrote the guide below on how to build your own agent system from scratch.
You can also find the full paper this is based on below.
Burt.K retweeted
I did this with GPT-6 Astra and a modify version of H3 Max Director from @fal , still in prototype for this ( little chunk )
Burt.K retweeted
Makepad flow, like comfyUI but in Rust, single executable with 90% of the useful comfyUI backends compiled in, auto model downloading. Render cluster support, built in AI that can make these flows for you. I know nothing matters anymore but its still nice you can build this in one day of fabling.
holy sh*t. this is f**king insane.
muse spark 1.3 beats fable 5 and gpt 5.6 at 1/20th price
i cancelled my $200/mo Claude subscription for this.
i replaced fable 5 with muse spark 1.3 for only $10/mo on opencode go
[it takes 3 minutes to set up:]
1/ install the model-router repo
2/ toggle opencode free to green
3/ that’s it.
Burt.K retweeted
A few people asking about the stack, so here it is:
- Nano Banana 2 by @google for keyframes
- SAM 3 by @Meta for segmentation
- H3 Max by @fal for video transitions
- GPT‑5.6 by @OpenAI for world building
- Hosted on @vercel
- Vigorously prompted by @charliie
Aaaaaaand we're live!
diiverge.co
A persistent, infinite, point-and-click adventure.
Every picture is a fork. Click something in it, decide what happens, and the world grows in that direction.
Astra vs Fable 5 (not fable 5.1)
build a 3d aquarium game using single prompt with reference image from gpt-6-astra
astra >> fable 5 confirmed, now time to test against fable 5.1
GPT-6 Astra built this iOS app in 13m 3s using my AppCreator skill.
I want to see my weekly mileage, not averages. Apple Health app doesn't make it easy.
So I gave this prompt to Astra, and this is the result.
No other model has made it work like this from one prompt.
@OpenAI @OpenAIDevs
Burt.K retweeted
GPT-6 Astra built this Manhattan world in Unreal Engine over the course of a week.
It was literally able to go street by street to make each one perfect.
Burt.K retweeted
GPT-6 Astra is a beast. Give it a Zillow listing. It can 3D model the house based on the listing photos and create a cool promotion video.
The video was just created in one shot and there are still some wrong details. But I am sure it will be much better if I ask it to polish further. OpenAI is so back.































