Jazon Szabo
Ai Safety Researcher @Lasr Labs
Signup · Get unlimited contacts
WORK HISTORY
Ai Safety Researcher @Lasr Labs
London, GB
Working on the exploitable search problem for AI alignment: how can we prevent AI agents from optimising hidden, malicious objectives when solving tasks. Gained experience working with largue language models, reinforcement learning and generative flow networks.
EDUCATION
King's College London
Doctor of Philosophy - PhD, Artificial Intelligence
The University of Edinburgh
Bachelor’s Degree, Computer Science and Artificial Intelligence
Karinthy Frigyes Gimnazium
High School, IB
ABOUT JAZON SZABO
Final year PhD student (post-viva) at King\'s College London and Imperial College London, with the STAI CDT. I research democratic value alignment—the study of how to control intelligent agents in a democratic way—using social choice and philosophy.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.