02 / evaluation

6 Feb 2026

Honestly, I think the biggest thing that this highlights is that as we’ve been growing as a company and taking on kind of more and more ambitious versions of interpretability related problems, a lot of that comes to scaling up in various different forms.

“Honestly, I think the biggest thing that this highlights is that as we’ve been growing as a company and taking on kind of more and more ambitious versions of interpretability related problems, a lot of that comes to scaling up in various different forms.”

Speaker: Mark Bissell
Episode: The First Mechanistic Interpretability Frontier Lab — Myra Deng & Mark Bissell of Goodfire AI
Publisher: Latent Space

Mark Bissell

What Mark said.

I think the main sort of point here that I think is exciting is that there’s not a whole lot of inter being applied to models quite at this scale.

Honestly, I think the biggest thing that this highlights is that as we’ve been growing as a company and taking on kind of more and more ambitious versions of interpretability related problems, a lot of that comes to scaling up in various different forms.