Miles Davis, the legendary jazz musician, once famously said, “Don’t play what’s there; play what’s not there.” Within that phrase lies the very essence of jazz—the magic of the unexpected, the brilliance of improvisation, and the ability to explore the musical space between notes. Jazz isn’t just a series of predetermined scales or scripted melodies; it’s the art of creating something new from familiar structures. It’s about finding unexpected connections, riffing on themes, and bending the boundaries of what we know. And isn’t this a interesting analogy for how we interact with large language models (LLMs) today?
Another good example is the work of John Coltrane, the jazz visionary who redefined musical boundaries through his innovative use of harmony. His exploration of the circle of fifths, especially with his Coltrane Changes in Giant Steps, introduced complex, rapid chord progressions that broke free from traditional tonal centers. This approach mirrors how modern AI and large language models navigate language—structured yet capable of surprising leaps. Coltrane’s music perfectly illustrates the fusion of structured patterns with improvisation, much like the interplay between human creativity and the emergent properties of AI.
Much like a jazz musician pulls notes from the ether, we now have the ability to weave knowledge and information into new........