The SLT Summit organizers are the team behind the Singular Learning Theory and Alignment Summit (subtitled "Singularities against the Singularity"), a conference series bringing together researchers at the intersection of algebraic geometry, statistical learning theory, and AI alignment. The summits featured tutorials on Singular Learning Theory (SLT) developed by Sumio Watanabe, research talks, and collaborative problem-solving sessions. The organizing team of Jesse Hoogland, Daniel Murfet, Alexander Gietelink Oldenziel, and Stan van Wingerden went on to found Timaeus, a dedicated AI safety research organization applying SLT to alignment.
Funding Details
- Annual Budget
- -
- Monthly Burn Rate
- -
- Current Runway
- -
- Funding Goal
- -
- Funding Raised to Date
- $20,000
- Fiscal Sponsor
- Center for Applied Rationality
Theory of Change
By convening researchers at the intersection of algebraic geometry, statistical physics, and AI alignment, the SLT Summit aimed to build a research community applying Singular Learning Theory to understand and control neural network behavior. The theory of change holds that SLT provides a rigorous mathematical framework for understanding how training data shapes the loss landscape geometry, which in turn determines what algorithms neural networks learn and how they generalize. Building a community of researchers fluent in this framework could lead to scalable interpretability tools and alignment techniques grounded in deep mathematical understanding rather than ad hoc methods.
Grants Received
from Survival and Flourishing Fund
Projects
No linked projects.
People
No linked people.
Discussion
Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.
Details
- Last Updated
- Mar 19, 2026, 8:06 PM UTC
- Created
- Mar 18, 2026, 11:18 PM UTC