Welcome to my website. I am Huzama, a PhD candidate at the Kim Jaechul Graduate School of AI at Korea Advanced Institute of Science and Technology. Currently, I am working in the xfact under the guidance of James Thorne. My research focuses on aligning and customising Large Language Models to elicit the best response, while ensuring that they remain safe, trusted and harmless. Although it would be interesting to see AI perform tasks that have the potential to cause damage.
Thank you for visiting my website! If you have any questions about my research or would like to engage in discussions related to my work, please feel free to get in touch.