[tmoney1818]

"the top-level prior has 5 billion parameters and is trained on 512 V100s for 4 weeks"

If they used on-demand AWS instances, it would cost about 1,342,623 USD to train the top-level prior. So much for reproducing this work.

[prafullasd]

We release our model weights and code here https://github.com/openai/jukebox/, so you can directly build on top of them and don’t have to train from scratch

[empath75]

So, the music that I know the most about is dance music and all of your examples from that genre seems to have completely missed the four to the floor beat that characterizes those artists — any theory as to why that is? You’d think that the loop based repetitive nature of edm would make it simple for an ai to mimic.

[aabhay]

My only question with OpenAI is whether they will forever-more take existing AI research, throw $100,000s of dollars at it in training, then take credit for inventing intelligence

[TaylorAlexander]

I mean if they’re properly citing their sources I think it’s useful to have someone throw lots of compute at things and see what happens.