I do think that voice ai pipelines still route almost everything through full ASR to generative decoding. A lot of latency and cost sits in that text-output step so reformulating the problem as constrained classification (audio to action) instead of open generation is def going to be the new paradigm shift

cool! we built something similar but using 3d models with poly-mesh expansions to learn about specific parts of any model a while back. any model turned into an interactive learning exp try it out with some preloaded models: mesh3d.vercel.app/ cc: @kushpatell_

@boardyai mine is better

it took a waterloo cs student to find this one line that everyone else missed lol

i’m afraid to say waterloo is not only taking over engineering but sparkling water in sf as well

been a month since I moved to sf to work for a @ycombinator company pushing the most code and learning at an insane rate

New portfolio is live, devp.ca

im taking down prod, goodnight

This is amazing lol, the m5 sticks are so versatile. here’s something i built recently where we reverse engineered the accelerometer to control 3D objects (sort of Jarvis from iron man)

sunset district in sf is not real. wdym i see this everyday??

monotone colors like this would look so good and match the cursor theme

I literally just built a working one with collapsible, file/folder dragging and creation just last week! What do you think? :)