Hey, I'm Jasmine!

I research technical safeguards for artificial intelligence, and study CS and English at Cornell as a Milstein and Telluride Scholar.

As of winter 2026, I am a Research Fellow at MATS, advised by Alex Turner and working on model oversight and control. Previously, I developed automated redteaming infrastructure for frontier lab safety testing at Gray Swan AI, and studied LLM honesty with the Center for AI Safety. I am also the founder of Cornell AI Alignment and founding co-instructor of Cornell's CS 1998: Introduction to AI Safety.

I care about flourishing, free futures for humanity. I aim to work hard on ambitious bets to help make that happen. See my research and what I'm up to now.

A shortlist of other things I love: persimmons, positive hyperstition, hosting fun events/parties, the 10% pledge 🔸, hiking (in the PNW, S. America, CA), tomato egg noodles, shoehorns, lifting PRs, rationalist jokes, the Bay Area, my friends. Please reach out and say hi (jasminexinzeli@gmail.com)!