AI Grand Strategy for Middle Powers
Sovereign AI, how?
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.
Latest Notes
Interpretability and Evals
Attribution graphs, linear probes, natural language autoencoders, capability and propensity evaluations, and alignment auditing as tools for making model behavior legible.
Cooperative Game
A note on how the stag hunt, the prisoner's dilemma, and Pareto efficiency frame cooperation among learning agents.
The Science of Benchmarking
A technical note on benchmark design and evaluation quality
Inner Alignment
Deception, reward tampering, mesa-optimization, goal misgeneralization, and why learned objectives may diverge from training objectives.