Software Engineer. I build stuff for the web (mostly).
about me 👉
Joined June 2010
- Tweets793
- Following1.8K
- Followers523
- Likes3.7K
damn that's cool 🤯
I have discovered the the BEST way to get 3D modeling results from LLMs
The app LiDAR scans the room while taking hundreds of high quality photos.
Then a workflow + skill I've created models out every item recursively checking the model against the photo at the exact spot + angle where the photo was captured
The result is a a dimensionally accurate and high quality model of your room
All in my latest video on how to do it youtube.com/watch?v=JGQCcCzu…
I get it, Theo is controversial or whatever, but t3code is actually not bad.. same with omarchy/dhh.. the figure!=the product
scrawl + hex are changing how I work, making me way more productive, thanks @kitlangton 🫶
Edu Wass retweeted
Goose: my latest programming language. Safer, faster and less memory than Rust/C++ for algorithms where tightly packed, flat data structures matter.
It can represent more kinds of data structures as flat, pointer-free bytes than any language I know.
github.com/aardappel/goose
1/
What's the intended way of maintaining a fork without falling behind upstream?
Hitting this with every OSS tool I want to tweak. Plugins when they exist, but often they don't. How are people handling it? 🤔
ok I dig this
We just shipped in-app visualization capabilities in T3 Code. This enables agents to build cool dynamic experiences within the thread.
Huge shoutout to @davis7 for pushing us on this (and building most of it). Didn't expect to dig it so much.
Edu Wass retweeted
elygpui.com
@zeddotdev
1272 GPUI components
I hope more people will share the project, give it a star, or contribute through PRs and issues. I really want to see it get more attention and help GPUI become a new mainstream framework.
希望可以有更多的人转发，star，或者提交PR, issue. 真的希望这个项目可以获得更多关注。让GPUI可以成为新的主流框架。
these ai slop ads are fkn hilarious 🤣 jesus christ
bro got chad grandpa mogged
This quoted post is unavailable.
Edu Wass retweeted
thanks! just did: github.com/awlevin/typesafe-…
and agreed. it's clearly much faster. accessibility trees will probably make it another order of magnitude faster and more flexible too. super excited to try that out, hopefully later tonight
👀
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
current stack:
ghostty
helium
herdr
sideshow
zed
tailscale
moshi (ios)
and using a remote devbox for practically everything
tempted to jump from apple to linux for the customisation but scared of loosing the hardware and ecosystem
dhh is making this hard to ignore lol, maybe this is the actual year?
let the man cook
Quick Superlogical demo to end the week. This demo is just of the basic functionality, but I want to highlight just how FAST it is. There's a WHOLE lot more functionality already present and coming but I wanted to keep the demo short. But seriously, check out that speed.
I'm showing the macOS app here and I get asked a lot so let me just say up front: its not macOS only. We're still figuring out exactly what platforms will be stable enough for the initial public release, but we're working on others. In particular, the web interface is very functional but I'll demo that another time (or someone else will).
This is also all showing off the architecture I previously talked about for terminal multiplexing which is significantly different from other mainstream multiplexers: this is all a custom binary protocol where the server is maintaining N replica distributed terminal state machines. It works!
Tons of hard work going into this by the team @almonk @dizzyup @pearkes. Hope we can bring you something you can use soon. ❤️ Happy to answer questions in the replies.