Jessica Rumbelow
Leap Labs
Leap Labs
During the MATS Autumn 2022 Cohort, Jessica published “SolidGoldMagikarp (plus, prompt generation)” with fellow scholar Matthew Watkins, which was featured in Vice News, and tied first place with fellow scholar Dane Sherburn at the Safe and Trustworthy AI Workshop 2022 for her poster, “Hierarchical Perturbation.” Before MATS, Jessica worked as a Research Scientist at the University of St Andrews applying deep learning to digital pathology, while completing her PhD in model agnostic interpretability. She is now the CEO and research director of Leap Laboratories, a VC-funded deep tech startup developing AI interpretability for knowledge discovery.
The Summer 2022 cohort was MATS's first full-scale program, with 31 scholars and 7 mentors from leading AI safety organizations including OpenAI, ARC, MIRI, EleutherAI, and Aligned AI. The program ran 5 weeks online followed by 8 weeks in-person in Berkeley, where scholars conducted independent research under expert mentorship, participated in educational seminars, and built community with peers in the Berkeley AI safety ecosystem.
Jessica Rumbelow
