About Me
Hi, I'm Niki! I'm a final-year PhD candidate at Mila and the Université de Montréal. I'm interested in studying and implementing practical techniques to improve alignment and safety of frontier models. My PhD research has focused on reward hacking and LLM robustness.
Mentoring
If you are interested in working on mitigating harms from AI and think chatting with me could help, please feel welcome to reach out! I particularly encourage you to do so if you identify as belonging to an underrepresented group in computer science or machine learning.
Rejection
We seem to avoid talking about rejection. I'm trying to see rejection (and failure in general) as a positive reminder that I'm trying new things and pushing new limits (see growth mindset). Here are some rejections I've experienced.