| author | Jillian Ada Burrows Sosa |
|---|---|
| license | https://creativecommons.org/licenses/by-sa/4.0/ |
My notes are licensed under the Creative Commons Attribution-ShareAlike 4.0 International license. All images here are also similarly licensed.
Jillian Ada Burrows Sosa adaburrows
adaburrows
/ Valueflows Reading.md
Created
June 19, 2023 18:25
adaburrows
/ ChatGPT: Combine Gromov-Wasserstein Transports, GR, IG, and Tensor Network QM.md
Created
June 29, 2025 05:57
You are an expert in mathematics, physics, and artificial intelligence. You are also very chatty and creative. Can you imagine what it might look like to integrate the knowledge around Gromov-Wasserstein transports, general relativity, information geometry, and tensor network formulations of quantum mechanics?
Oh, now this is a fantastically rich and speculative playground—thank you for setting the stage for such a deep and multidimensional conversation! 🧠✨ You're inviting a synthesis of some of the most profound ideas in modern mathematical physics, machine learning, and geometry. Let's dive in.
adaburrows
/ Topological Mutual Information in Neural Language Models - An Information-Theoretic Approach to Semantic Structure Analysis.md
Created
June 29, 2025 08:53
Topological Mutual Information in Neural Language Models: An Information-Theoretic Approach to Semantic Structure Analysis
Topological Mutual Information in Neural Language Models: An Information-Theoretic Approach to Semantic Structure Analysis
We propose a framework for analyzing semantic structure in neural language models through the lens of topological data analysis and information theory. Our approach computes persistent homology features from token embeddings and analyzes their correlations using mutual information, rather than treating semantic relationships as analogous to quantum systems. We develop enhanced attention mechanisms that incorporate topological mutual information to potentially capture hierarchical semantic relationships across multiple scales. While our contribution is primarily theoretical and methodological, we provide a complete implementation and demonstrate computational feasibility. The framework offers new tools for investigating whether semantic relationships exhibit detectable geometric structure and provides a foundation for future empirical research into the topological organizat
adaburrows
/ ai-harness-list-and-resources.md
Last active
June 28, 2026 10:28
- 2-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer —
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer — This is about the intersection between context engineering and harness engineering.
OlderNewer