I'm John.

2nd year Computer Science PhD student @ Stanford University.

I'm the creator of InterCode, SWE-bench [Verified; Multimodal; Multilingual], SWE-agent, SWE-smith, and CodeClash.

I also just wrote a position paper about why we need to incorporate more "human-centeredness" in AI coding research with a bunch of great folks from Stanford, CMU, Princeton, and UIUC.

I am advised by Professors Ludwig Schmidt and Diyi Yang.

My research topics are Language Model Agents, Language Model Evaluation, Synthetic Data, and Software Engineering.

Previously, I completed my M.S.E. in Computer Science at Princeton University, advised by Professor Karthik Narasimhan. I received my B.S. in Computer Science from UC Berkeley.

If you'd like to get in touch, feel free to reach out through SWE-bench Slack or Twitter.

Thanks for visiting!