@_simonsmith Good to see I'm not the only one still running Todoist with AI. I know I could just Claude something to replace it but I like their app in the loop with my Obsidian Knowledge base.
Ever since I was a kid, I had this imaginary game I'd play on the school bus and road trips...
Pretended my fingers were a person running along the grass, avoiding the cement gaps
30 years later, thanks to claude
I TURNED MY CHILDHOOD IMAGINATION INTO AN ACTUAL GAME
I let Claude Code drive Meta's Edits app and edit my last Reel, live: dead air cut, subtitles added, export done, all on camera.
Full behind the scenes 👇
Have to test with other models.
@creativedash I haven’t tried the new models need to throw a few goals loops at my maybe I keep the same mechanics but have Fable add graphics or animations to the story items. I was most proud of the travel animation I made which was many models ago.
https://t.co/FSFrs0he7G
@SketchesbyBoze My most watch movies from the beginning of the DVD. Watching the same disc over and over till we got more in that time I rewatched things like, Cool Hand Luke, Kelly’s Hero’s, Bad Boys, Once Upon a Time in the West, Finding Nemo, over, and over.
using muse ember🔥, each of these websites cost $0.04 on average
back in my day, these would cost you O($10,000) in custom dev shop costs
massive deflation in nice pretty websites
can gaussian splats be used to render interfaces?
I've seen a lot of incredible spatial demos coming out of the labs (@theworldlabs has been blowing my mind ~weekly), but they've mainly been focused on static 3D environments. I woke up today wondering: are splats any good for UI or other interactive objects, and can AI work with them?
it looks like the answer is yes and yes. I prototyped an imagen -> SHARP -> spark -> popmelt pipeline that gets decently far on the first try and really far with a few rounds of art direction + interaction tuning. Smooth animation, dynamic lighting, realistic geometry... all doable, with freely available tech
I haven't pushed into full scenes yet, but this experiment already felt somewhere between the detailed magic of generative video UI I've shared before and the stable dependability of textured 3D models (throwback). Plus LLMs like Astra are very good at working with splats, which makes fine tuning them way more fun/efficient
next: I'm weighing whether to lean into interactive spatial design (just to see how far I can get with off the shelf tools) OR see how well this workflow handles typical responsive UI design (decidedly not what splats are for, which feels interesting). thoughts?