Our Mission
To empower humanity by making breakthrough scientific progress on AI safety.
We are first and foremost a research organization, working on advancing our understanding of advanced AI systems, so we can achieve safe and positive outcomes.
AI Safety
Humanity is building highly powerful AI systems but we still do not know how to ensure those systems are robustly aligned with human values. We conduct scientific research to ensure the development of advanced AI systems goes well.
Singular Learning Theory
At Timaeus, we're using singular learning theory to develop the science of understanding
how training data determines model behavior.
- Data
- Geometry
- Learning Process
- Algorithms
We study how patterns in training data determine…
…the geometry of the loss landscape, which determines…
…the learning trajectory followed by SGD, which determines…
…the ultimate algorithms and behaviors learned by neural networks.
Our Research
Evals
The aim of our research on model evaluations is to advance the science of generalization, to predict how large learning machines will behave.
Learn moreInterpretability
The aim of our research on interpretability is to understand how large learning machines work on the inside.
Learn moreAlignment
The aim of our research on alignment is to advance the reliability and robustness of our techniques for aligning advanced AI systems with human values.
Learn moreVideos
Jesse Hoogland–AI Risk, Interpretability
Jesse Hoogland on Singular Learning Theory
The Physics of Intelligence: from Classical to Singular Learning Theory
Jesse Hoogland - Singular Learning Theory
Singular Learning Theory: Overview And Recent Evidence
Singular Learning Theory with Daniel Murfet
Publications
Modes of Sequence Models and Learning Coefficients
Chen and Murfet
April 25, 2025
Studying Small Language Models with Susceptibilities
Baker et al.
April 25, 2025
Programs as Singularities
Murfet and Troiani
April 10, 2025
You Are What You Eat – AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
Lehalleur et al.
February 8, 2025
Structure Development in List-Sorting Transformers
Urdshals and Urdshals
January 30, 2025
ICML SMUNN Workshop
Dynamics of Transient Structure in In-Context Linear Regression Transformers
Carroll et al.
January 29, 2025
Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
Wang et al.
October 4, 2024
ICLR
Spotlight
Loss landscape geometry reveals stagewise development of transformers
Wang et al.
June 16, 2024
ICML HiLD Workshop
Best Paper
The Developmental Landscape of In-Context Learning
Hoogland et al.
February 4, 2024
The Local Learning Coefficient: A Singularity-Aware Complexity Measure
Lau et al.
August 23, 2023
AISTATS 2025