Hello! Thanks for stopping by :) I am a predoctoral researcher interested in building and deploying advanced AI systems that are safe and that benefit humanity. Most recently, I worked on interpretability–extending concept bottleneck models–with Adrian Weller at the University of Cambridge. Before that, I did research on COVID-19 intervention effectiveness in collaboration with Oxford’s Applied and Theoretical ML group. My first (co-equal) first-author paper was recently accepted at PNAS, which Tyler Cowen said was ‘The best mask-wearing study so far?’ (emphasis on the ‘?'). My work is also published at Nature Communications (3rd author) and Nature Scientific Data. I did a master’s in statistics at Oxford, and an undergrad in maths on the beaches of St Andrews. I’ve done bits of research at Aalto University, Imperial College London, and the Future of Humanity Institute (Oxford). I like to meditate for 1-2h per day, dance around Oxford until my feet hurt, and radiate love 24/7.
MSc Statistical Science, 2019
University of Oxford
BSc Mathematics, 2016
University of St Andrews
Mask-wearing has been a controversial measure to control the COVID-19 pandemic. While masks are known to substantially reduce disease transmission in healthcare settings [1–3], studies in community settings report inconsistent results [4–6]. Investigating the inconsistency within epidemiological studies, we find that a commonly used proxy, government mask mandates, does not correlate with large increases in mask-wearing in our window of analysis. We thus analyse the effect of mask-wearing on transmission instead, drawing on several datasets covering 92 regions on 6 continents, including the largest survey of individual-level wearing behaviour (n=20 million) [7]. Using a hierarchical Bayesian model, we estimate the effect of both mask-wearing and mask-mandates on transmission by linking wearing levels (or mandates) to reported cases in each region, adjusting for mobility and nonpharmaceutical interventions. We assess the robustness of our results in 123 experiments spanning 22 sensitivity analyses. Our results suggest that mask-wearing is strongly affected by factors other than mandates. We establish the effectiveness of mass mask-wearing, and highlight that wearing data, not mandate data, are necessary to infer this effect.
The first paper to study the effectiveness of non-pharmaceutical interventions (NPIs) in Europe’s second wave. We collect the largest dataset of NPI implementation dates in Europe, spanning 114 subnational areas in 7 countries. Using a hierarchical Bayesian transmission model, we estimate the effectiveness of 17 NPIs from local case and death data. We manually validate the data, address limitations in modelling from previous studies, and extensively test the robustness of our estimates. The combined effect of all NPIs was smaller relative to estimates from the first half of 2020, indicating the strong influence of safety measures and individual protective behaviours–such as distancing–that persisted after the first wave.