Hi, I’m Melanie

An emerging researcher across AI safety and AI governance, asking what better governance could look like for countries that didn’t set the rules of the game.

—Ideas—Projects—Common Room—About

Latest notes

  1. The Material Geography of Chinese AISep 2026Companies, compute, and power: mapping the material foundations of Chinese AI.
  2. AI Grand Strategy for Middle PowersAug 2026Sovereign AI, how?
  3. Interpretability and EvalsAug 2026Attribution graphs, linear probes, natural language autoencoders, capability and propensity evaluations, and alignment auditing as tools for making model behavior legible.
  4. Cooperative GameJul 2026A note on how the stag hunt, the prisoner's dilemma, and Pareto efficiency frame cooperation among learning agents.
  5. The Science of BenchmarkingJun 2026A technical note on benchmark design and evaluation quality