Hey! I'm Andy Wang.
AI Safety Researcher | UW Madison CS & Math
I am a student at the University of Wisconsin Madison studying Math and Computer Sciences. You might know me by my online alias yeedrag.
I believe that ensuring AI is safe and aligned might be the most important problem we have now, and we might not have a lot of time to do so. I want to help humanity solve this problem by doing technical AI safety research, and understand how we can control AI models to prevent malicious behavior.
Experience
Astra Research Fellow
Jan 2026 – PresentConstellation Research Center (Full-time)
- Incoming safety research fellow working with Scott Emmons (prev. Google DeepMind) on CoT monitorability.
AI Safety Research Fellow
Sep 2025 – Dec 2025Supervised Program for Alignment Research (Berkeley, CA)
- Investigated various properties on CoT Monitorability, mentored by Qiyao Wei.
AI Security Research Intern
May 2025 – Dec 2025American Family Insurance (Madison, WI)
- Conducted red-team assessments on internal AI infrastructure, received return offer to develop model safeguards.
Deputy Director
May 2025 – PresentWisconsin AI Safety Initiative
- Reframing strategy to focus on producing AI safety professionals.
- Connecting with researchers to refine strategies for safety-focused groups.
Interests
Research Areas
- CoT Monitorability
- AI Control
- Eval Awareness
- Misalignment & Generalization
Personal
- Combinatorics
- Number Theory
- Video Games
- Cooking