Technical Writer | Fullstack developer
Joined March 2021
- Tweets553
- Following354
- Followers122
- Likes2.2K
Tammibriggs retweeted
We just dropped a challenge with @github!
Build with GitHub Copilot CLI for a chance to win:
๐ฐ $1,000 USD
๐๏ธ Ticket to GitHub Universe
โ GitHub Copilot Pro+ Subscription
๐ Exclusive DV Badge
dev.to/devteam/join-the-githโฆ
Tammibriggs retweeted
oh may.. 3D Gaussian Splat is so crazy now
last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in secondsโฆ even zoom into the text and looks perfect
give it like 6 monthsโฆ you can turn a whole city into a full detailed 3D model
Tammibriggs retweeted
โก๏ธGenerating 3DGS scenes in 5 seconds on a single GPUโก๏ธ
#FlashWorld enables โก๏ธ*fast*โก๏ธ (10~100x faster than previous methods) and ๐ฅ*high-quality*๐ฅ 3D world generation, from a single image or text prompt.
Code: github.com/imlixinyang/Flashโฆ
Page: imlixinyang.github.io/FlashWโฆ
Tammibriggs retweeted
I spent the past month reimplementing DeepMindโs Genie 3 world model from scratch
Ended up making TinyWorlds, a 3M parameter world model capable of generating playable game environments
demo below + everything I learned in thread (full repo at the end)๐๐ผ
Tammibriggs retweeted
Veo is a more general reasoner than you might think.
Check out this super cool paper on "Video models are zero-shot learners and reasoners" from my colleagues at @GoogleDeepMind.
Tammibriggs retweeted
โจ It's not even 2026 yet, but you can start using AI world models today!
This is @theworldlabs running inside my app ๐ก Interior AI letting you redesign your home with AI and then walk through it!
It's really cool and of course not perfect especially since for now it's based on just one image, but multi-image will allow for more precise understanding of the room
As always this is just the first version, and it'll get better from here
World Labs is founded by @drfeifei, a Computer Science professor from @stanford, and other people like Justin Johnson, Christoph Lassner, and Ben Mildenhall "each a world-renowned technologist in computer vision and graphics"
The tech essentially comes down to img2splat, search what a guassian splat is if you don't know
It's in beta and wait list, but I'm trying to get this live for everyone as soon as possible as it seems like such an essential feature for interior design
P.S. I also tried to worldify people photos (for Photo AI) but World Labs for safety right now seems to block it off and make it a black square, maybe in the future
2023 was the year of AI avatars
2024 was the year of AI photos
2025 was the year of AI videos
And I think it's becoming clear now that 2026 will be the year of AI world models
Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt
In turn these 2d images can then be generated by AI too
So soon you can generate fully explorable virtual 3d worlds based on your own imagination
Next will be figuring out how to make those worlds interactive
This is @theworldlabs (unaffiliated, but I like it)
As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now)
Very exciting time again!
Tammibriggs retweeted
Quite a hefty video dataset just released: 7K hours of video with various annotations: camera pose, depth maps, dynamic object masks, scene text descriptions (camera, motion trends, summary)
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations nju-3dv.github.io/projects/Sโฆ
Tammibriggs retweeted
๐ ๐ฏ๐ ๐ฎ๐ป๐ฑ ๐ฐ๐ ๐ช๐ผ๐ฟ๐น๐ฑ ๐ ๐ผ๐ฑ๐ฒ๐น๐ถ๐ป๐ด: ๐ ๐ฆ๐๐ฟ๐๐ฒ๐
๐ฃ๐ฎ๐ฝ๐ฒ๐ฟ: huggingface.co/papers/2509.0โฆ
๐๐ถ๐๐๐๐ฏ: github.com/worldbench/survey
--
๐งฉ ๐ช๐ต๐ฎ๐โ๐ ๐ป๐ฒ๐?
World models are emerging as the backbone of embodied AI โ enabling agents to ๐ถ๐บ๐ฎ๐ด๐ถ๐ป๐ฒ, ๐ฝ๐ฟ๐ฒ๐ฑ๐ถ๐ฐ๐, and ๐ถ๐ป๐๐ฒ๐ฟ๐ฎ๐ฐ๐ with dynamic environments.
Yet, most prior surveys focus on 2D images and videos.
๐ Our survey is the first comprehensive review dedicated to ๐ป๐ฎ๐๐ถ๐๐ฒ ๐ฏ๐ ๐ฎ๐ป๐ฑ ๐ฐ๐ ๐๐ผ๐ฟ๐น๐ฑ ๐บ๐ผ๐ฑ๐ฒ๐น๐ โ covering multi-view RGB-D, occupancy grids, and LiDAR point clouds.
Tammibriggs retweeted
it has come to my attention that this is not universal knowledge
you can just type docs.new or sheets.new into your browser
and it will immediately open a new google doc or sheet
Tammibriggs retweeted
researchers discovered that asking a text-to-image model to predict 3D geometry is like asking a novelist to be an architect ๐ turns out image editors are way better at this because they actually look at the input image instead of just vibing
aimodels.fyi/papers/arxiv/edโฆ
Tammibriggs retweeted
๐Rodin is now on BlenderMCPโtotally free!
๐With Rodin, BlenderMCP can create any 3D asset, unlocking incredible new powers.
Pair it with Claude 3.7 or Cursor for a seamless boost๐ฅ
#b3d #MCP #Claude #vibecoding
Tammibriggs retweeted
The battle of the Text/Image to 3D Model ๐- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now.
Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that @TencentHunyuan 2.5 is currently the king ๐ It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection.
Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair.
Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great.
Is there any other AI 3D Gen services that you know of that you want me to test as well?
Tammibriggs retweeted
Creating 4D game worlds with rich interactions takes lots of time and effort but our latest releases change that. I prompted this end-to-end using our tools:
- Use CSM AI's Chat-to-3D to get usable assets, with parts
- Animate with CSM's Blender MCP add-on
- Tell MCP make the sword follow the hand
Remarkably, LLMs+MCP will quickly come up with a new Blender tool and prompt the user to select a point on the character's mesh to constrain the sword to follow. You can then edit the sequence as you wish and export the FBX file to your game project for prototyping.
Tammibriggs retweeted
IT WORKS!!!!!
A FULL multiplayer with Python websockets server that receives and broadcasts all player positions every 100ms (10 times per second)
All code written almost 100% by AI with Cursor and Grok 3 wrote the server code
Now you can fly around with everyone else :D It'll probably crash after this tweet but let's try!
fly.pieter.com
The reason before it didn't move was it was stale players that already quit and it kept their positions
Every red plane is someone real flying now too! ๐
Tammibriggs retweeted
A new free tier of GitHub Copilot in @code.
โ
2,000 code completions per month
๐ฌ 50 chat messages per month
๐ซ Models like Claude 3.5 Sonnet or GPT-4o
โฅ๏ธ More fun for you
Check it out today!
Oh yeah, and we passed 150M developers on GitHub ๐
github.blog/news-insights/prโฆ
