The First Mechanistic Interpretability Frontier Lab — Myra Deng & Mark Bissell of Goodfire AI

From Latent Space: The AI Engineer Podcast Latent.Space

From Palantir and Two Sigma to building Goodfire into the poster-child for actionable mechanistic interpretability, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are trying to turn “peeking inside the model” into a repeatable...

Full show notes and links