MikeHLee

Putting It to the Test

Part 4 of a series on Sheaf-Theoretic Reward Spaces.

Navigating the Safety Manifold: Why Black Holes are Safer Than Walls

Part 3 of a series on Sheaf-Theoretic Reward Spaces.

Gluing Rewards Together: How Math Solves Paradoxes

Part 2 of a series on Sheaf-Theoretic Reward Spaces.

Why Your LLM Hallucinates (And How Category Theory Can Help)

Part 1 of "The Structure of Clear Thinking."

Compiling Programs Into Attention

The procedural cousin of type-safe attention, and what it

Building an Auditable AI: A Complete Walkthrough

Published: April 6, 2026 · Dev preview — pending ICLR 2027 submission

From Proofs to Programs to... Text?

Published: April 6, 2026 · Dev preview — pending ICLR 2027 submission

Attention, But Make It Type-Safe

Dev preview — workshop submission pending. Part 2 of the Structure

Prompt Injection Is an Operational Risk, Not a Prompting Problem

Why "tell the model to ignore manipulation" is

Nature Knows Best — An Introduction

What biology already solved, and what software keeps getting wrong.