why is every paper using DINO to bootstrap their image models? what makes it so good?

here's bad apple but its a game of pong (sound on)

Spent a weekend building Song Pong - it's pong except the ball bounces exactly on the beat of a song, created with linear programming🏓 (sound on) Basic idea: ball travels at constant speed, paddles can glide anywhere on their half, every bounce lands on a beat. Question is

my ick is optimizing kernels while theres still gaps in your cuda stream

I've been at NeurIPS this past week. Here's six things I learned: 1. Inference engineers are in huge demand 2. Competitive programmers are taking over the field 3. AI music is bottlenecked by evals. Everyone knows the evals are bad, but no one can fix them. 4. Music research is

They say every AI researcher dies twice. Once when you stop breathing, and a second time, a bit earlier on, when your life's work is obsoleted by a new grad with a bigger GPU.

pre-training, mid-training, post-training, how about you do some strength training

https://t.co/qU7Zu9WIgG the super short pr

pushed a change to pytorch that makes cudagraphs 1ms faster. turns out for every module pytorch checks if its in a list. i made it a set and now prod is 5% faster lol

Suno is partnering with the Warner Music Group https://t.co/Bu88Ty8YgP

During our short beta period last month, thousands of developers have already started using Modal Notebooks, and they ran 200,000+ code cells. One of those is @SunoMusic, where researchers use notebooks to share models and experiments across the company.