>The current safety problem in agentic AI is not misalignment in the abstract. It is a team deploying an agent without mapping the surface area it is exposed to. I’m building Pome to close that gap, giving agents a safety infra grounded in real conditions.
Studied machine learning, cognitive science, and functional programming at Edinburgh. Worked on ML and engineering problems at TikTok and Google. Peaked top 100 in League of Legends EUW.
Selected work.
Project
Title and image go here.