I'm a software engineer at Microsoft building AI agent systems with persistent memory, knowledge graphs, and neuroscience-inspired architecture. Navy veteran. Self-taught. I write about what I learn along the way.
Writing
-
The KV Cache, Now With the Math: Attention for Developers Who Want the Equations
In the first post I explained the KV cache with zero math — what it stores, why the Query is never cached, and the experiment where I built my own...
-
What Is a KV Cache? A Developer's Guide to the Trick That Makes LLMs Fast
“KV cache” shows up everywhere — model configs, inference logs, that use_cache=True flag you’ve never thought twice about. I nodded along to it for a long time. Then I ran...
-
I Taught My AI Agents to Sleep. Now I'm Teaching Them to Wake Up.
A while back I built a memory system for AI agents that worked like sleep.
-
The Hardest Part of Building AI Agents Isn't the AI
I spent a recent stretch refactoring my AI agent system. I didn’t touch a single prompt.
-
From 600MB of Models to Zero: How I Simplified My AI Agent Memory System
I spent a weekend ripping out 1,865 lines of machine learning infrastructure from Myelin. It was the best architectural decision I’ve made on this project.
-
Myelin: A Brain-Inspired Knowledge Graph for AI Agent Memory
AI agents have a memory problem. Here’s how I fixed mine — and open-sourced the solution.
-
Simplified Explanation of Gradients and Neural Networks
Simplified Explanation of Gradients and Neural Networks
-
Vector Space of Polynomials with Real Coefficients
Math Syntax in Machine Learning
-
Reflections: Tech, Personal Growth, and Everything in Between
Welcome to My Exploration
subscribe via RSS