Desiree Cho
Interests
AI alignment, technical AI safety, RLHF, goal misgeneralisation, interpretability.
Biography
Desiree is a first-year DPhil (PhD) student in Computer Science and a Doctoral Scholar at the Institute for Ethics in AI. She is supervised by Prof Sir Nigel Shadbolt. Her research focuses on AI alignment, including failure modes and post-deployment monitoring.
She completed her Master of Science at the Oxford Internet Institute, achieving Distinction in both her overall classification and thesis. Her thesis was on the behavioural interpretability of recommender systems, where she built an original social media dataset and developed a ML pipeline for alignment auditing. She has previously authored papers at leading human-centred computing venues, such as the ACM CHI.
Please follow Desiree on LinkedIn for her most recent updates.