About

Hi, I'm Dylan! I work on alignment research at OpenAI. I'm interested in curating better data and pretraining safer models. Previously, I completed my PhD in the Machine Learning Department at CMU, where I was fortunate to be advised by Zico Kolter. I've also spent time as a student researcher at Google Research, and as a research intern at GraySwan AI and Amazon AWS.

If you are interested in my work, please get in touch. I am always happy to chat about research!

Selected Publications

• Safety Pretraining: Toward the Next Generation of Safe AI
• When Should We Introduce Safety Interventions During Pretraining?
• Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
• Predicting the Performance of Black-box LLMs through Follow-up Queries

News

• [Mar 2026]: Defended my PhD thesis on "Towards Safer and Understandable AI Systems"!
• [Oct 2025]: Joined OpenAI to make language models safer!
• [May 2024]: Spent the summer at Google Research in NYC working on data curation for LLM pretraining.