Hi! I am Sunny :)

I am an incoming first year PhD in Computer Science at Princeton University, advised by Tom Griffiths. Previously, I graduated from Stanford University with a BS in Symbolic Systems (with honors and distinction, Phi Beta Kappa) and an MS in Computer Science. At Stanford, I was very fortunate to be advised by Dan Jurafsky and Robert Hawkins.

I am interested in cognitive science and AI, specifically using insights about human cognition to build safe and more robust and interpretable AI systems that can benefit our long-term development.

Outside of research, here are some things that I love: good books (modernist, feminist, sci-fi, satirical), tea, fruits, running, hiking and the outdoors, tennis and badminton, and any theory-of-mind board games and card games.

Recent Papers

The Efficiency-Gain Illusion: People Underestimate the Rate of AI Use and Overestimate Its Benefits on Simple Tasks. Sunny Yu, Myra Cheng, Ahmad Jabbar, Ilia Sucholutsky, Katherine M. Collins, Dan Jurafsky, Robert D. Hawkins. Pre-print, under review (2026).

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations. Sunny Yu, Ahmad Jabbar, Robert Hawkins, Dan Jurafsky, Myra Cheng. Pre-print, under review (2025).

ELEPHANT: Measuring And Understanding Social Sycophancy in LLMs. Myra Cheng*, Sunny Yu*, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, Dan Jurafsky. ICLR (2026).

Updates

June 2026: I graduated from Stanford and was the recipient of the Firestone Medals for Excellence in Undergraduate Research!
April 2026: Our paper on benchmarking sycophancy appeared at ICLR.
March 2026: Our paper on sycophantic AI’s impacts on people was the cover story of Science!