I’m exploring an analogous idea for music. The quality of the musical output has improved noticeably with the latest frontier models
Karpathy’s point about the models not being able to easily audit their work is something I’m struggling with —- how can the audio output be made perceivable? Curious what people think about this question.
Karpathy’s point about the models not being able to easily audit their work is something I’m struggling with —- how can the audio output be made perceivable? Curious what people think about this question.
Here’s a synth to play with+remix
https://underscore.audio/s/cmp_8b226859-420/iron_rareflash