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."
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
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.