Making Artificial Intelligence Safe for Humanity.
To research and develop technologies that ensure artificial intelligence systems are aligned to do the most possible objective good.
Mission
Safety Machine researches and develops technologies to ensure artificial intelligence systems are aligned to do the most possible objective good. We build and study AI agents that can automate parts of the AI alignment research process, with the goal of creating self-evolving, learning systems that improve understanding over time. Our approach includes methods such as temporal knowledge graphs (with tools like Zep) to help agents learn from interactions and evolve their models of the world.
In the near term we produce educational videos and social media content about AI alignment ideas and gather diverse user perspectives to compare and contrast strategies. The insights we collect help strengthen alignment research as AI capabilities grow.
About Us
Safety Machine is a nonprofit research organization incorporated in Texas. We operate at the intersection of AI safety, alignment, and transparency. Our work aims to build open, reproducible research and tools that help practitioners, policy makers, and the public understand how to keep AI systems beneficial.
Status
Safety Machine is incorporated in Texas as a nonprofit corporation. We have obtained an EIN and our application for federal tax-exempt status under 501(c)(3) is pending.
Contact
For inquiries, partnerships, or donations, please email us at info@safetymachine.org.