Jerome Wynne

I’m currently working on AI training, evaluation, and scaled human feedback as an AI research engineer at Prolific. I previously worked at the UK AI Security Institute in the Science of Evaluations group, and at Faculty as a data scientist.

I did a year on a PhD in statistics at Imperial College London, which is also where I studied for my MSc in statistics. My undergraduate degree was in design engineering at the University of Bristol, with electives in maths and computer science.

Updates

Paper Is This a Bot? AI Models Lie About Being Human, Even When Not Asked To accepted to the TAIGR workshop at ICML 2026.
Paper Quantifying Frontier LLM Capabilities for Container Sandbox Escape, with the UK AI Security Institute, accepted to ICML 2026.
Attended ICLR in Rio de Janeiro.
Submitted the MetaLoop benchmark to Measuring Progress Toward AGI.
Presented Who Does Your AI Serve? Manipulation By and Of AI Assistants at the AIMII workshop, IASEAI 2026, Paris.