About me
Hey there! I'm Bryan Sukidi. I'm a first-year undergraduate at UNC Chapel Hill studying Computer Science, Statistics and Philosophy under a Morehead-Cain scholarship.
Over the past four years, I've become increasingly concerned about the risks that AI poses to humanity. I'm interested in AI safety research focused on red-teaming, adversarial robustness, and interpretability in LLMs.
I'm currently taking the BlueDot Impact AI Safety Fundamentals Course, and have read The Precipice, Human Compatible, and The Alignment Problem. I also enjoy indoor rock climbing, music, exploring religion, and playing NYT Games in my freetime.
Feel free to get in touch.