We are building tools and resources to spread our research to the broader community.
Dive deep into developmental interpretability and singular learning theory. Explore our comprehensive documentation, tutorials, and research papers to understand the foundations of our work.
Get hands-on with DevInterp, our Python library for developmental interpretability. Start with our curated notebooks and build your own research projects.
Join our community of researchers and engineers working on cutting-edge problems in AI interpretability. From theoretical work to practical implementations, find a project that matches your interests and skills.
Some aspects of intelligence are becoming a commodity. They are bought and sold by the token and piped from large datacenters hosting artificial neural networks to our phones, laptops, cars and perhaps soon domestic robots. However our understanding of what neural networks do, and how they “learn” is limited. This makes it difficult to assess the downside risks of rapid adoption of AI across the economy and in our personal lives. The goal of this focus period will be to come to grips with these questions from a mathematical perspective. Many mathematicians want to contribute, but lack a clear entry point into the subject. A primary aim will be to articulate guiding questions, in consultation with experts at the forefront of AI development. We also aim to bring together some of the most interesting thinkers in this nascent field.
ODYSSEY is a 5-day, multi-track conference bringing together researchers in theoretical AI alignment.
The Australian AI Safety Forum is a two-day interdisciplinary event scheduled for November 2024. This forum, the first of its kind in Australia, aims to discuss perspectives on technical AI safety and governance, and explore Australia’s unique role in the global AI safety landscape. The event will be anchored around the International Scientific Report on the Safety of Advanced AI, highlighting its key content and examining its implications for Australia.