Future Thoughts

Just thought I’d write these down somewhere… Inspired by REMI and other projects, I think I’m going to consider a more chordal representation in the future. I’ve talked to a prominent piano player in the region, and I still think my model lacks musicality (can it even be musical? Even GPT-3 is not ‘language-cal’, it repeats from an overwhelming amount of memorized patterns… or is that good enough?)

Your thoughts...?