Her current project focuses on simulating AI governance policies to determine their effectiveness and feasibility. She has been a mentor for four SPAR projects, and has won 1st place three times at AI safety hackathons. Previously, Linh worked on latent adversarial training for personalities at the Mila AI Institute, and on chain of thought monitorability with Geodesic Research (through MARS). Before entering AI safety, Linh did a postdoc at the University of Technology Sydney and obtained her PhD from the University of Queensland in Natural Language Processing.
