We're hiring Research Scientists, Engineers & more!
New: Timaeus Research Fellows Program

Breakthrough Scientific Progress on AI Safety

We're on a mission to empower humanity by making breakthrough scientific progress on AI safety.

Tetrahedron
Dodecahedron

Our Approach

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.

Latest Research

Our most recent publications on singular learning theory and AI safety.

Patterning: The Dual of Interpretability

By Wang and Murfet

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures.

Learn More → ArXiv

Towards Spectroscopy: Susceptibility Clusters in Language Models

By Gordon et al.

Spectroscopy infers the internal structure of physical systems by measuring their response to perturbations.

Learn More → ArXiv

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape

By Elliott et al.

Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases.

Learn More → ArXiv

Learn About SLT

Watch our latest discussions on singular learning theory and AI safety.

Erlangen AI Hub Seminar: Singular Learning Theory for Interpretability, Jesse Hoogland

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.

Erlangen AI Hub Seminar: Singular Learning Theory for Interpretability, Jesse Hoogland

Jesse Hoogland - Singular Learning Theory and AI Safety

November 10, 2025

Jesse Hoogland presented "Singular Learning Theory and AI Safety" on September 17, 2025 at FAR.AI Labs Seminar.

Jesse Hoogland - Singular Learning Theory and AI Safety

Singular Learning Theory & AI Safety | SLT 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.

Singular Learning Theory & AI Safety | SLT Seminar

From Research to Impact

We are building tools and resources to spread our research to the broader community.

Focus Period: Mathematical Science of AI Safety

Nov 3 - Dec 12, 2025
The University of Sydney, Australia

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
Sun Illustration

ODYSSEY 2025

Aug 25 - Aug 29, 2025
Berkeley, California

Partners: PIBBSS , Simplex

ODYSSEY is a 5-day, multi-track conference bringing together researchers in theoretical AI alignment.

Learn more
Sun Illustration

Join Timaeus

Join our growing team of dedicated researchers applying cutting-edge mathematics to prevent AI risks that could affect billions of people.

Dodecahedron

Latest News

A collection of posts written by various people associated with Developmental Interpretability (since before the agenda was conceived).

View All

Timaeus Research Fellows Program

April 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
Fire Illustration

Research Positions @ Timaeus

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
Fire Illustration

Open Roles @ Timaeus

January 7, 2026

<div class="not-prose my-8 rounded-lg border-2 border-yellow-500/30 bg-yellow-500/10 p-6"> <p class="m-0 text-base font-semibold text-foreground"> This posting is now closed. </p> <p class="m-0 mt-2 text-sm text-muted-foreground"> Applications for this round have closed. Thank you to everyone who applied. Visit our <a href="/opportunities" class="text-primary hover:underline">opportunities page</a> to express interest in future roles. </p> </div> TLDR: We're hiring for research engineer and research scientist roles to work on applications of singular learning theory to alignment. About Us Timaeus' mission is to empower humanity by making breakthrough scientific progress on alignment.

Learn more
Fire Illustration

Research Engineer @ Timaeus

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
Fire Illustration