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 +
Some Indian chat app uploaded 480,000 images to my cloudinary account
I had my Cloudinary misconfigured to allow proxy fetch/resize from any domain, so they uploaded to S3 and then used my URL to handle resize + bandwidth
Sorry to "India Chat" if I just broke your images
It's been 6 months since I posted this
How has your use of UI changed?
Does your chat ever inline UI?
Do you use any of: interactive chat UI, MCP Apps, WebMCP, generative UI, etc..
Give me your hottest takes on generative UI, MCP apps, agents returning widgets, and chat as the final interface
Working on a talk for JS Nation and I want to spotlight some differing opinions
