I'm Cath, an undergrad at Oxford studying Mathematics and Statistics. I do AI safety research (technical, governance), and I like making cute websites:)
- Languages: Python, JavaScript, C, R, SQL
- ML Frameworks: Pytorch, scikit-learn
- LLM Ecosystem: Hugging Face Transformers, TRL
- Web: HTML, CSS, JavaScript, Flask
- Tools & Platforms: Git, Docker, AWS
My primary research interests lie in AI control and agent foundations, particularly understanding and mitigating misalignment risks in increasingly autonomous systems. I focus on empirical and theoretical questions around goal misgeneralisation, adversarial capability elicitation, and attack selection in agentic evaluations, aiming to clarify failure modes in frontier models. I am also interested in how these technical insights inform governance design, especially mechanisms for managing strategic risk and constraining dangerous capability deployment.
Last updated: Feb 2026
