AI Safety Should Follow Engineering's Path: Understanding Over Monitoring, Researcher Argues

ninamiolane · x · 2026-09-28

Researcher Nina Miolane argues that mature engineering disciplines achieve safety through scientific understanding rather than human oversight: bridges stand because loads are computed in advance, and aviation became safe because aerodynamics matured as a science—not by hiring more people to watch planes. She contends AI safety should follow the same route: build scientific laws that predict model behavior before it happens, with interpretability research (aided by tools like Goodfire AI's Silico) as the prerequisite for control.

Original post →

More from AGI Musings

AGI Musings channel →