"Let's Throw Away Everything We Know About Music" Suno Founder Mikey Schulman

Why It Matters

By eschewing traditional musical constraints, Suno’s technology could democratize composition, accelerate content creation and enable new artistic forms, while raising fresh questions about authorship, licensing and the future of the music industry.

Summary

Suno founder Mikey Schulman explains the startup’s approach to AI music generation: user prompts are expanded via language models into lyrics and stylistic cues, which are then fed into generative audio models that produce raw sound. Rather than encoding conventional musical rules—specific instruments or the 12-tone system—Suno models everything as unconstrained sound to avoid limiting creativity. That design lets the system iterate from vague prompts and produce novel, genre-blending outputs that may diverge from traditional musical structure. Schulman says this ‘from-scratch’ strategy is intentional to enable unpredictable, original music rather than reproductions of known forms.

Original Description

"The more musical knowledge we give the model, the more constrained it will be in a bad way." Mikey Shulman explains why Suno threw out everything humans know about music — and why that counterintuitive bet is what made it work.

#podcast #shorts #sunoai #ai