I'm working to build the infrastructure and tools that helps human systems, markets, and AI learn and act on what they actually value. See more in my white paper.
I'm also a PhD student in logic and philosophy at IRIT/CNRS, working on ways to formally distinguish between normative/ethical and empirical knowledge, and actively trying to realize more practical applications of this work (as also seen in the above white post).
At this point, my writings are a bit scattered around all different corners of the web, ranging from denser and technical to airy and conceptual (with some of it previewed on the bottom of this page). See this little directory where all of them are organized.
Writing
- 2026-04-29 Scales of Alignment