Timaeus

Remote (Berkeley, Melbourne, London)

early16 peopleFounded 2023

Endorsed by:

Timaeus is an AI safety research nonprofit dedicated to making fundamental breakthroughs in technical AI alignment using deep ideas from mathematics and the sciences. The organization applies Singular Learning Theory (SLT), combining insights from algebraic geometry and statistical physics, to develop interpretability tools that reveal how internal structure forms during neural network training. Their flagship research agenda, developmental interpretability, uses measures like the Local Learning Coefficient to detect and understand phase transitions in model training, with the goal of building scalable tools for evaluating, interpreting, and aligning AI systems.

Funding Details

Annual Budget: $2,500,000
Monthly Burn Rate: $208,333
Current Runway: -
Funding Goal: -
Funding Raised to Date: -
Fiscal Sponsor: Ashgro

Theory of Change

Timaeus believes that Singular Learning Theory provides the mathematical foundation needed to rigorously understand how neural networks develop internal structure during training, including when and how they acquire capabilities, values, and potentially dangerous behaviors. By detecting and understanding phase transitions in training through measures like the Local Learning Coefficient, Timaeus aims to build scalable evaluation and interpretability tools that can identify critical developmental moments before dangerous properties emerge. This would enable alignment interventions at the training level, ensuring models develop in ways that reflect human values. Their approach bridges pure mathematics with empirical machine learning, creating a scientific framework where alignment properties can be formally stated, measured, and verified rather than merely hoped for.