We're rethinking our music sequence generation work, moving beyond simple models to care about expressive timing, dynamics, and polyphony, aiming to create high-quality music generation tools.

Different tempos, dynamics, and tone colors are essential tools for musical expression.

The challenge is to make our models good enough and easy to use so that even non-expert musicians can find them genuinely musically engaging, focusing on generating interesting sounds rather than just melodies.

We're gathering valuable feedback from artists using our tools, which is guiding us to improve the usability and fluidity of our music generation tools, especially for integration with software like Ableton.

To make music interesting, we need to incorporate hierarchical patterning and conditional models that can generate variations, such as chord changes, to create more engaging compositions.

We want to create long-form pieces in music and art that make sense beyond just short segments, enhancing the creative process.

We have a remarkable palette of expressive tools to convey emotions, feelings, moods, and even stories through music.

It's essential to balance respect for the score with the need to make the music sound beautiful, as the composer may prioritize emotional expression over strict adherence to the written notes.

Musicians with strong improvisational skills have been able to create interesting results using our primitive sequence generation tools, turning it into a collaborative game rather than just a tool.