Hi, I'm Chinmaya

I'm a student at Stanford University.
I'm interested in building AI systems that are open, safe, and useful by studying reasoning and problem-solving in language models. Recently, I've been thinking about bootstrapping and self-improvement in language models, advised by Noah Goodman and Jan-Philipp Fränken. Currently, I'm a software engineer in the Applied Research group at Capital One, where I work on making language models better assistants.
I recently received my B.S. in Mathematical and Computational Science from Stanford University, where I'm also currently working on my M.S. in Computer Science (on leave).

Featured research publications

Latest research.

Teaching Language Models to Ask Clarifying Questions
COLM 2024



Featured projects

Some academic course projects, mini-investigations and miscellaneous interests.

Investigating language models' ability to patch buggy code with the help of print statements.
2024
Studying manipulation and social reasoning in language models.
2023
Using abstract syntax trees to programmatically generate buggy code.
2023