@THESPIKEGG@CoachEwok "but it's also kind of like getting thrown into the deep end for some of them. Sometimes, that's the best way to learn how to swim."
The mark of a truly GREAT book isn't how fast you read it. It is how many times you have to set it down on your lap, look out the window, and process a sentence that just completely reshaped your worldview.
We don't read to escape reality. We read to understand it BETTER.
Depth-aware light injection in TypeGPU
I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D
Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step
Inference, lighting and draw all go through the same command encoder.
Growing up hearing “Wikipedia isn't a valid source” and then entering a workplace where people say “just ask ChatGPT” is a surprisingly strange timeline