← Front page

Machine Learning Street Talk · Wednesday, September 2, 2026

Interpretability as a Natural Science: Goodfire's Vision

Neil Nanda, founder of Goodfire, views interpretability as a natural science akin to physics or biology, but conducted entirely on computers. He believes this approach will enable a significant acceleration in scientific discovery through AI agents capable of performing experimental work and theory building.

personNeil NandacompanyGoodfire

The tape

3 quotes
I think interpretability is I think of it as a natural science, you know, like physics, biology, chemistry.
Neil Nanda
But it's a natural science that you do completely on the computer.
Neil Nanda
And so this means that like we should be able to kind of again speed run science once we have agents that can do experimental work for us.
Neil Nanda
Heard on Machine Learning Street Talk — “Designing How AI Grows — Tom McGrath, published Wednesday, September 2, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.08
Interpretability as a Natural Science: Goodfire's Vision — Heardvine