ABOUT GOODFIRE
Our mission is to advance humanity's understanding of AI by examining the inner workings of advanced AI models (or "AI Interpretability"). As an applied research lab, we bridge the gap between theoretical science and practical applications of interpretability to build safer and more reliable AI models.
We're building critical infrastructure that empowers developers to understand, edit, and steer AI models at scale so that they are more reliable, customizable, and explainable.
Goodfire is a public benefit corporation headquartered in San Francisco.
FOUNDING TEAM
We're a lean team with expertise in startup scaling, interpretability research, and building great AI products.
Eric Ho
Chief Executive Officer
-
previously founded RippleMatch, a Series B AI recruiting startup backed by Goldman Sachs
Tom McGrath
Chief Scientist
-
previously Senior Research Scientist at Google DeepMind, where he founded the interpretability team
Daniel Balsam
Chief Technology Officer
-
previously Founding Engineer and Head of AI at RippleMatch
BLOG
Feature steering for reliable and expressive AI engineering
Eric Ho
Nov 20, 2024
Research preview: Understanding and steering Llama 3
Tom McGrath
Sept 25, 2024
Goodfire raises $7M to break open the black box of generative AI models
Myra Deng
Jul 22, 2024
CAREERS
We're looking for agentic, mission-driven, kind, and thoughtful people to help us build the future of interpretability. If you believe understanding AI systems is critical for our future, join us.