Simplex - building our research team | Manifund

This funding proposal outlines a novel approach to AI interpretability and safety based on Computational Mechanics, a mathematical framework from physics. The key points are: Current interpretability methods lack a principled grounding, and are insufficient to understand, control, and monitor AI The proposed approach captures the dynamic structure of computation, adapting Computational Mechanics to make precise predictions about the internal geometry of neural networks that underlie AI system behavioral capabilities. In this way we are able to make a principled connection between the structure of training data, model internals, and model behavior. Our initial results show the approach can predict and empirically verify non-trivial, fractal-like structures in transformer activations, validating its relevance in transformers. Simplex is a new research organization that aims to develop a principled science of AI cognitive capabilities and associated risks. We have a clear and ambitious th

Simplex - building our research team | Manifund 6 Simplex - building our research team Science & technology Technical AI safety Adam Shai Not funded Grant $0 raised Project summary This funding proposal outlines a novel approach to AI interpretability and safety based on Computational Mechanics, a mathematical framework from physics. The key points are: Current interpretability methods lack a principled grounding, and are insufficient to understand, control, and monitor AI The proposed approach captures the dynamic structure of computation , adapting Computational Mechanics to make precise pre

related reading

• Simplexsimplexaisafety.com
• Simplex Progress Report - July 2025 — LessWronglesswrong.com
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Next Steps in Developmental Interpretability | Manifundmanifund.org
• Problem Areas in Physics and AI Safety | Apart Researchapartresearch.com
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
• In-context Learning and Induction Headstransformer-circuits.pub
• Thinking Machines Labthinkingmachines.ai
• Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org