TLDR: We made substantial progress in 2024:
We published a series of papers that verify key predictions of Singular Learning Theory (SLT) [1, 2, 3, 4, 5, 6].
We scaled key SLT-derived techniques to models with billions of parameters, eliminating our main concerns around tractability.
We have clarified our theory of change and diversified our research portfolio to pay off across a range of different timelines.
In 2025, we will accelerate our research on the science and engineering of alignment, with a particular focus on developing techniques that can meaningfully impact the safety of current and near-future frontier models.

Overview

Timaeus's mission is to empower humanity by making breakthrough scientific progress on AI safety. We pursue this mission through technical research on interpretability and alignment and through outreach to scaling labs, researchers, and policymakers.

As described in our new position paper, our research agenda aims to understand how training data ultimately gives rise to model behavior by using Singular Learning Theory (SLT) to link four different kinds of structure (the "S4 correspondence"):

Training Data: The statistical patterns present in the training distribution;
Loss Landscape: The shape and singularities of the loss over parameter space;
Learning Dynamics: The trajectory followed by the optimizer during training;
Internal Algorithms: The circuits/mechanisms implemented in the trained model.

**The S4 correspondence:** Training data (and architecture) determine the loss landscape. The loss landscape (and optimizer) determine the learning process. The learning process picks out the algorithms a model learns and thus how it generalizes. Figure from Pepin Lehalleur et al. (2025).

This correspondence provides a starting point for developing new tools for interpreting algorithmic structure (by probing the geometry of the loss landscape) and aligning advanced AI systems (by controlling the data distribution over training).

Since our founding in October 2023, Timaeus has grown — from a team of four with an initial budget of $145k to our current team of eight (soon, up to 12) with around $2.5M in funding for 2025. While research milestones are most visible, much of our progress has been in investing in our team, establishing research collaborations, and setting up the infrastructure we need to scale our work.

Research Progress in 202

...