Timaeus is merging into Resolution. Read the announcement
We use singular learning theory to understand how training data shapes AI behavior.
Our approach combines deep mathematical insights from algebraic geometry and statistical physics with empirical research to develop interpretability tools to understand how capabilities and values emerge during neural network training. This foundational work enables us to build interventions that ensure models are aligned with human values.
Our most recent publications on singular learning theory and AI safety.
By Baker et al.
In the latent posterior model of transformer behavior, the next-token distribution arises from a posterior over latent predictive models conditioned on the context, mixed to generate continuations.
By Elliott and Murfet
We define susceptibilities as a measure of the response of an observable quantity of a parameterized statistical model to a perturbation of the data for a general class of observables.
By Elliott et al.
Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss.
Watch our latest discussions on singular learning theory and AI safety.
December 18, 2025
In this seminar, Jesse Hoogland explores how singular learning theory provides a framework for connecting interpretability to the theory of generalization and the geometry of the loss landscape. He presents recent work at Timaeus applying SLT to different areas of interpretability, including an SLT-based generalization of influence functions for data attribution and an SLT-native approach to ablations for circuit discovery, and describes initial work on using these interpretability techniques to actively shape the learning process by controlling training data, with implications for developing better alignment techniques. Jesse Hoogland is the executive director of Timaeus, an AI safety non-profit working on interpretability and alignment, and a cofounder of the developmental interpretability research agenda and the broader program of applying singular learning theory to AI safety, which he is now pursuing with his team at Timaeus.
November 10, 2025
Jesse Hoogland presented "Singular Learning Theory and AI Safety" on September 17, 2025 at FAR.AI Labs Seminar.
July 28, 2025
In the SLT seminar, Jesse Hoogland from Timaeus talks to us about his research agenda applying singular learning theory to AI safety.
We are building tools and resources to spread our research to the broader community.
Partners: Monash University , Sydney Mathematical Research Institute
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.
Learn more
ODYSSEY is a 5-day, multi-track conference bringing together researchers in theoretical AI alignment.
Learn more A collection of posts written by various people associated with Developmental Interpretability (since before the agenda was conceived).
View AllApril 9, 2026
TLDR: Timaeus is launching a Research Fellows Program for tenured faculty and senior researchers who want to contribute to applications of learning theory to alignment while maintaining their existing academic positions. About Us Timaeus' mission is to empower humanity by making breakthrough scientific progress on alignment. Our research focuses on applications of learning theory to foundational problems within alignment. We have hubs in Berkeley, Melbourne, and London. The Fellows Program The Timaeus Research Fellows Program is a structured affiliation for researchers at academic institutions or research organizations who want to collaborate closely with Timaeus on SLT-informed alignment research.
Learn more
April 9, 2026
TLDR: We're hiring three research scientists and one research engineer, and potentially a research lead to work on applications of singular learning theory to alignment. In-depth familiarity with SLT is not required. About Us Timaeus' mission is to empower humanity by making breakthrough scientific progress on alignment. Our research focuses on applications of singular learning theory (SLT) to interpretability and alignment. Our two primary research programs are: Spectroscopy: Spectroscopy is an interpretability methodology that uses susceptibility-based methods to discover and characterize internal structure in neural networks, grounded in weight space (in the tradition of statistical physics and Bayesian statistics) rather than in activations (like sparse autoencoders and probing techniques).
Learn more January 7, 2026
This posting is now closed. Applications for this round have closed. Thank you to everyone who applied.
Learn more August 12, 2025
Research Engineer @ Timaeus TLDR: We're hiring for a research engineer role. The successful hire will work on applications of singular learning theory to alignment, including developmental interpretability. About Us Timaeus' mission is to empower humanity by making breakthrough scientific progress on alignment. Our research focuses on applications of singular learning theory to foundational problems within alignment.
Learn more 
