candrewlee14
Joined 4 years ago
Joined 4 years ago
[1] https://candrewlee14.github.io/blog/2024-03-07_apple-vision-...
- looking at your hands
- looking at clocks
- trying to read
It’s funny that diffusion models often make those exact same mistakes. There’s clearly a similar failure mode where both are drawing from a distribution and losing fine details. Has this been studied?
With that being said, I’ve been doing some practice!
Recently, I tried the Apple Vision Pro and I wrote about my experience. If you’re interested about my formerly-skeptical opinion on the future of AR/VR, check it out :)
I happen to be super interested in systems programming (OSes, DBs, PLs), but I've worried that those fundamentals might be superseded by AI, whether through a higher-level abstraction or just better automated code generation. Glad to hear an experienced opinion to the contrary.
I think I'll need to come back and read this a couple more times to pull out all the advice here, I appreciate this much to chew on :)