I’m a PhD candidate in social data science at the University of Oxford. My research focuses on investigating language model behaviors to understand and improve their cognitive, social, and relational effects. I'm currently visiting the Stanford NLP Group (working with Diyi Yang) and working with Google DeepMind on socioaffective AI research and policy. I am also building a design studio focused on public AI literacy.

My background is in computer engineering and international relations. Formerly, I was a Schwarzman Scholar and a fellow at the Centre for Governance of AI and the Digital Asia Hub.

I’m currently thinking about and working on the following (pls reach out if you are too and want to chat!):

• how human-AI relationships impact human-human relationships
• LLM sycophancy
• evaluation methods for socially-consequential AI behaviors

research

My research approach is grounded in information theory and human-centered computing, but also draws on cognitive science and social psychology. I work directly with both models and people, aiming to evaluate and enhance their interactions by developing and testing frameworks, as well as conducting experiments and user studies. All my publications can be found here. My work has been published in venues including ICLR, NeurIPS, AIES, and FAccT, and covered by The Telegraph, Le Monde, NBC, Wired, NPR, and more.

news

Last updated: February 2026

* [Jan 2026] Two papers accepted to ICLR 2026: one on multi-turn evaluation of anthropomorphic behaviours, another on social sycophancy in LLMs

* [Nov 2025] Gave a talk at the Workshop on Human-Centric Agentic Web at the Distributed AI Conference

* [Oct 2025] Started visiting the Stanford NLP Group, working with Diyi Yang

* [Oct 2025] Awarded a Challenge Fund Grant from the UK AI Security Institute for research on advice giving and human-AI relationships

* [Sep 2025] Paper on construct validity in LLM benchmarks accepted to NeurIPS 2025

contact