Last updated: May 2026
Researcher in Amnesty International Kenya's RightUp 2.0 program — a youth-led research initiative investigating tech-facilitated repression and how surveillance tools and digital tactics are used to silence activists and civil society.
Junior Research Fellow at the ILINA Program, focusing on technical AI safety and mechanistic interpretability. I'm building "runtime safety governors" using activation steering to detect and correct deceptive model behavior in real-time, specifically testing if these internal safety controls generalize to Swahili.
Also leading partnerships at GDG Pwani, now gearing up for IO Extended 2026 Pwani.
The politics of AI governance. Who gets to decide what "safe" means, and whether the current landscape is trending toward pluralism or priesthood. (I wrote about this recently.)
Also: the gap between alignment research and deployment reality. The field has a theory-practice problem that nobody wants to name directly.
Currently reading The Infinity Machine by Sebastian Mallaby — the biography of Demis Hassabis and the story of DeepMind's quest toward superintelligence. Fascinated by how the arc from chess prodigy to Nobel laureate maps onto questions I think about daily around AI safety and governance.
Also re-reading Seeing Like a State (Scott) — keeps being relevant. And working through the Anthropic interpretability papers to trace how the field's assumptions evolved.
A small tool for visualizing attention patterns in a way that's actually useful for debugging. Early stages. May never ship.