Charlie Rogers-Smith
Predoctoral researcher in machine learning
University of Oxford, University of Cambridge
About me
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.
- Long-term AI safety
- Interpretability/explainability
- Accountability
- Robustness
- COVID-19 intervention effectiveness
MSc Statistical Science, 2019
University of Oxford
BSc Mathematics, 2016
University of St Andrews
