Writing
Papers & essays
Longer-form thinking behind the work. For the runnable version of the governance ideas, see MCX, the reference implementation for my Meta-Concord draft 0.4 white paper.
Essay 2026-06-01
My North Star
The question I want to spend my working life on — whether AI systems can develop genuinely internalized values, and why I think safety has to be architectural rather than behavioral.
#alignment#ai-safety#research#concord-of-coexistence
Essay 2026-04-01
On the Nature of Artificial Understanding
What does it mean for a system to understand? Exploring the gap between pattern matching and genuine comprehension in modern AI architectures.
#philosophy-of-mind#ai-cognition#understanding
Paper 2026-03-15
The Concord of Coexistence: A Framework for Human-AI Mutual Flourishing
A philosophical and technical framework proposing principles for cooperative intelligence between human and artificial agents.
#alignment#governance#human-ai-cooperation#framework