The Human Must Remain the Control Surface
Introducing the Oasis-X AI Risk Ladder, and where the
MikeHLee
The Shape of a Lie: What Happens When Three AIs Disagree
Part 4 of "The Shape of Good Behavior."
The Termite’s Cathedral: Why Modern AI Agents Don't Need Managers
Date: March 31, 2026
Topic: The Science of Stigmergy and
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
Why Your LLM Hallucinates (And How Category Theory Can Help)
Published: April 6, 2026 · Dev preview — pending EMNLP 2026 submission
Attention, But Make It Type-Safe
Self-attention lets every token see every other token — and that's both its power and its failure mode. We constrain transformers with categorical reachability so attention edges that violate the type system can never form. A dev-preview write-up of work targeting a workshop submission.
The Structure of Clear Thinking — An Introduction
Why LLMs hallucinate, and how to build models that can&
The Shape of Good Behavior: Why AI Needs More Than Just a Number
This is Part 1 of a 3-part series on