Pinned Tweet
If you missed my Particle-Love at #3dfestweb, here is the live link: edankwan.com/experiments/pa… Motion Blur Everywhere!
15
121
522
Telling Claude not to stop until it finished every task on the to-do list was a terrible mistake. As it turns out, Claude has been "discovering" new tasks as it goes, apparently inventing problems just to solve them.
It started with 91 tasks. Claude has somehow completed 409, left. 90% of these "new features" are completely useless nonsense that nobody asked for.
It started with 91 tasks. Claude has somehow completed 409, left. 90% of these "new features" are completely useless nonsense that nobody asked for.
2
0
21
1,360
It turns out what I do for living is not real code works 😭
Already see a lot of people discounting Muse Wonder because it wasn’t RL’d in 3d stuff like Astra and Opus.
3d game demos are cool! They don’t represent real code work at all.
Wonder is an incredible code model. Don’t sleep on it.
2
0
21
2,383
My job is safe for now
JEV + SONNET 5.5 is the most dangerous combo in design right now...
That's not a screen recording you're watching - It's a live website - and here is how it came together
Step 1: I went through oryzo frame by frame and took its grammar (the pacing, the type, the way the camera le scroll hangs on one hero object, so I rebuilt Claude's pixel mascot in code from 500 voxels without downloading a single 3D file
Step 3: Each frame depends only on the scroll position, with no timers and nothing random, so the same spot in the scroll always gives you the same frame and the site renders straight into a film
Step 4: Jev handles the routing, so scenes, 3D and copy go to Sonnet 5.5 while the frame by frame taste review goes to Opus 5.5
Step 5: Four Sonnet 5.5 agents worked in parallel and had four scenes built in roughly 24 minute
Step 6: Nothing ships until every still has been looked at, and whatever looks cheap gets rebuilt
You and I are using the same model. What changes the result is the harness you build around it
Prompt's in the comments
4
0
70
6,123
Okay, everyone has been sharing what they’ve built with Opus 5.5, so I finally bit the bullet and gave it a try.
This is my first project: My Mini Houdini.
I started building it last Friday, and this is where it’s at so far.
Shading:
Basic unlit, basic realtime, and realtime+ ost, etc.
There’s also a basic path tracer with OIDN denoising.
Node Graphics:
For geometry creation, I currently have model import and export, curves, grids, boxes, circles, spheres, lines, tubes, torus, test geometry and more.
There are quite a few modifiers in there already that I haven’t even properly tried yet.
Copy to Point, Packing and Sweep are also working in a basic form.
There’s a Solver too, although it’s still a bit funky. I need to figure out a better caching structure for it.
I’ve also added a Compute node and a JavaScript node.
I decided to keep pretty much everything on the GPU, so this isn’t really designed for massive geometry or heavy simulation. Cache budget can become a problem pretty quickly.
All geometry data stays inside compute buffers, with a hash table handling string attributes.
Material / Shading:
MaterialX for now.
Still very early, it is an electron app. Just a fun pet project. I am impressed.
This is my first project: My Mini Houdini.
I started building it last Friday, and this is where it’s at so far.
Shading:
Basic unlit, basic realtime, and realtime+ ost, etc.
There’s also a basic path tracer with OIDN denoising.
Node Graphics:
For geometry creation, I currently have model import and export, curves, grids, boxes, circles, spheres, lines, tubes, torus, test geometry and more.
There are quite a few modifiers in there already that I haven’t even properly tried yet.
Copy to Point, Packing and Sweep are also working in a basic form.
There’s a Solver too, although it’s still a bit funky. I need to figure out a better caching structure for it.
I’ve also added a Compute node and a JavaScript node.
I decided to keep pretty much everything on the GPU, so this isn’t really designed for massive geometry or heavy simulation. Cache budget can become a problem pretty quickly.
All geometry data stays inside compute buffers, with a hash table handling string attributes.
Material / Shading:
MaterialX for now.
Still very early, it is an electron app. Just a fun pet project. I am impressed.
12
6
158
8,878
My final verdict in this line of work. Let's hope that I am wrong.
@iced_coffee_devi@dangreenheckore creative work feels inevitable. You code with it, it gets better training data, and the next LLM gets smarter.
"But you can ship more!" say the AI bros.
But ask people who actually work in creative industries. Nobody wants to ship more. We care more about the craft than the final product. The "how". The dopamine hit when you finally figure something out.
I run a design studio. Say a client pays us $100,000 for a creative web experience that takes us a month to make. With AI, maybe one day we can make 10 amazing projects a month. But by then, the client will probably pay 10x less for each one. So in the end, we make the same money(if we are lucky), but now we have to make 10 projects instead of one. And each project means less to us because we're just churning through them.
From what I can see, with AI, being a creative might eventually stop being a viable career and become more of a hobby.
My advice to young, ambitious creatives might end up being: get a job at a big corp, earn the money, and do your creative work on the side.
Which is pretty fucking sad.
3
0
19
2,836
