Classical and quantum photonics with superior properties can be implemented in a variety of old (silicon, silicon nitride) and new (silicon carbide, diamond) photonic materials by combining state of the art optimization and machine learning techniques (photonics inverse design) with new fabrication approaches. In addition to making photonics more robust to errors in fabrication and temperature, more compact, and more efficient, this approach is also crucial for enabling new photonics applications, such as on-chip laser-driven particle accelerators, and semiconductor quantum simulators.