I tried generating music on stableaudio.com and, yes, it's bad. However, given the blistering pace of developing in these models, I would not be surprised if these sound incredible in a year or two.
But what is the proof for that?
I consider it far more likely that we had a breakthrough and now rushing towards the next plateau. Maybe are nearing that.
Like in the curve of a PID controller. It's how most or many human improvements go.
But I still see no evidence that this keeps improving and not plateauing at some (current?) level.
I suspect this is because the underlying production factors like compute, data & model design are steadily improving whilst humans have diminishing sensitivity to output quality.
In the game of AI generated photorealistic images or history essays there's not much improvement left to make. Most humans are already convinced by the output of these things.
Many of these problems seem to have been unexploited simply on basis of nobody throwing enough gpu clusters at it yet.