hununu

Interesting. Have you repeated these experiments with recent models? I'm thinking frontier models APIs have tools/MCPs for math stuff but curious about recent Qwen models, etc.

This is really hard these days because up and coming artists can only do so nowadays via social media. In practical terms it means musicians if they want to succeed they need to be good at music AND self promotion through social media.

While theoretically access to everyone has been democratized when compared to music labels of the past since everyone can put their music on Spotify and social media, effectively that also means social media is now a required skill besides musicianship.

It's harder than ever to create your own thing and stay on track. I think this is why so many people are going bonkers with angine de poitrine for example.

I find the bigger problem now is how many top results on search engines are AI written websites.

Are the released models models useful? I'm worried about their description of the output. I haven't had a chance to try them yet and unable to run them on hugging face at the moment. The https://stableaudio.com/ sample on their website could be used as sample materials for song making but definitely lacking frequency range expected today as a final product.

Being hosted in Canada is no longer the safety many assumed before. In reality it should not be an American company beholden to the current administration.

private repos

Thank you, I just created an account and looking forward to my ice cream.