Vin Howe

I'm a Master's student in computer science at Brigham Young University. Previously, I did my Bachelor's in BYU's Applied and Computational Mathematics program. I work in David Wingate's lab, where I study large language models.

Research Interests

I'm broadly interested in making AI a net social positive. Along with risks like those posed by superintelligence, I worry we run a real risk in the near term of making widely-deployed AI capable enough to be socially destabilizing, but not yet aligned or capable enough to prevent this. I'm interested in a version of AI that has a strong, intuitive sense of its role in benefiting society, but that comes with guarantees about our ability to control it.

Blog

Publications

Language models struggle with compartmentalization
Thomas V Howe, David Wingate
Preprint

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
Jeffrey Olmo, Jared Wilson, Max Forsey, Bryce Hepner, Thomas V Howe, David Wingate
Findings of the Association for Computational Linguistics

Leveraging AI for democratic discourse: Chat interventions can improve online political conversations at scale
Lisa P Argyle, Christopher A Bail, Ethan C Busby, Joshua R Gubler, Thomas V Howe, Christopher Rytting, Taylor Sorensen, David Wingate
Proceedings of the National Academy of Sciences

Projects

I created Sequence Toy, a web playground for training small language models with WebGPU.

I wrote the software the drives “The Wall,” the floor-to-ceiling interactive display in the lobby of BYU’s computer science building.