About Us
Like fire, AI holds the potential for both devastating harm and immense benefit. Our ancestors' mastery of fire enabled them to cook food, smelt metals, and eventually launch rockets into space—transforming civilization in ways they could never have imagined. Today, AI stands as humanity's most profound innovation since that first controlled flame. Our goal is to tame this new fire, enabling a safe transition into a post-AGI world. Achieving this requires deep understanding and intentional design of AI systems.
At Goodfire, we're building the platform to decode and interact effectively with advanced AI. Our mission is to deeply understand and thoughtfully design superintelligent AI—ensuring we build transformative models safely while ushering in a new era of scientific progress.
We are a public benefit corporation headquartered in SF.
We're a team of AI interpretability experts and startup operators
Our researchers are pioneers in the field of AI interpretability, having introduced work on:
using sparse autoencoders to discover interpretable features, autointerpretability for scalable feature labeling, and extracting knowledge from a superintelligent chess model (AlphaZero).
Together, we're building safer, more powerful foundation models.
Our values
Team and mission first
All we do is in service of our mission. We trust each other, deeply care about the success of the organization, and choose to put our team above ourselves.
Improve constantly
We are constantly looking to improve every piece of the business. We proactively critique ourselves and others in a kind and thoughtful way that translates to practical improvements in the organization. We are pragmatic and consistently implement the obvious fixes that work.
Ownership and initiative
There are no bystanders here. We proactively identify problems and take full responsibility over getting a strong result. We are self-driven, own our mistakes, and feel deep responsibility over what we’re building.
Action today
We have a small amount of time to do something incredibly hard and meaningful. The pace and intensity of the organization is high. If we can take action today or tomorrow, we will choose to do it today.
Contact Us
Developing an AI model? We partner with companies to interpret, extract knowledge from, and design foundation models – across architectures and modalities.