←back to thread

World Emulation via Neural Network

(madebyoll.in)
250 points treesciencebot | 2 comments | 25 Apr 25 21:33 UTC | HN request time: 0.001s | source
Show context
Jotalea ◴[28 Apr 25 11:35 UTC] No.43820125[source]▶
It's a really interesting project, reminds me of the 360° videos I used to watch on my phone, back in 2015.

But there's one thing that I'm a little bit worried about: I was getting like 8 stable FPS on my 3 years old flagship phone. My concern is that these models are not optimized to run on this type of hardware, which may or may not lead to hardware obsolescence quicker than planned. And it's not like these aren't powerful, they really are.

replies(1): >>43822024 #
ollin ◴[28 Apr 25 14:40 UTC] No.43822024[source]▶
Curious, which device/OS/browser? I did all my testing on 4-year old hardware (iPhone 13 Pro, M1 Pro MBP), and the model itself is extremely tiny (~1GFLOP) so I'm optimistic that performance issues would be solvable with a better software stack (e.g. native app).
replies(1): >>43828019 #
1. Jotalea ◴[29 Apr 25 01:55 UTC] No.43828019[source]▶
I was on my Samsung Galaxy S21FE (Snapdragon 888), on the latest version of the Firefox browser for Android (138.0), on One UI 6.1 (Android 14). It is possibly the most powerful device I own, that's why I was concerned.
replies(1): >>43834437 #
2. ollin ◴[29 Apr 25 16:00 UTC] No.43834437[source]▶
Got it, that makes sense! In terms of raw compute capability, a Snapdragon 888's GPU should have more than enough power to run this demo smoothly. I think I just need to optimize the inference setup better (maybe switch to WebGPU if the platform supports it?) and do targeted testing on Firefox/Android.