About

Hi, I'm Dylan! I work on safety research at OpenAI. I'm also a final year PhD student in the Machine Learning Department at CMU, where I am fortunate to be advised by Zico Kolter. My work is supported by a NSF Graduate Research Fellowship.

My research focuses on making language models safer. I have worked on curating better/safer training data and monitoring models for harmful behavior. I have also worked on aligning models with weak supervision and on generalization.

Previously, I studied math and computer science at Brown University, where I was advised by Stephen Bach. I've also worked as as a student researcher at Google Research, a research intern at GraySwan AI, Amazon AWS, the Bosch Center for AI, and NASA JPL. If you are interested in my work, feel free to get in touch. I am always happy to chat about research!

News

• [May 2025]: I gave a talk at UMD on Safety Pretraining, where we create natively safe language models during pretraining!
• [Feb 2025]: Excited to share my Google internship work on analyzing similarity metrics in language model pretraining data curation!
• [Jan 2025]: Just released new work on monitoring the performance and behaviors of LLMs in a black-box setting!
• [May 2024]: Spending the summer at Google Research in NYC, where I'll be working on data curation for LLM pretraining.
• [Apr 2024]: I'll be traveling to AISTATS to present "Auditing Fairness under Unobserved Confounding" and to ICLR to present work on providing generalization bounds for prompt engineering VLMs.
• [Jul 2023]: I'm giving a talk on learning data-driven priors for BNNs that incorporates interpretable domain knowledge at the KLR workshop @ ICML 2023!