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.
More from AGI Musings
- DeepMind essay: AGI may arrive as a society of agents, not a single superintelligence — bratton · 2026-09-29
- Recent AI incidents show there are no simple fixes, only weak mitigations — maksym_andr · 2026-09-29
- Game festival vows permanent bans for any AI-generated content found in entries — AIandDesign · 2026-09-29
- Bryan Cantrill: AI doomers like Hinton are wrong because they overreach their expertise — rms80 · 2026-09-29
- Generative AI made writing, prototyping and code cheap — but not good judgment — jacalulu · 2026-09-29
- AI Killed the Busy Work. Now Managers Miss It—and Fret About Atrophied Skills — PAstynome · 2026-09-29