GitHub

Hey there 👋

I'm John! Currently a 2nd year CS PhD student at Stanford University.

Check out john-b-yang.github.io for more.

Pinned Loading

  1. Can Language Models Rebuild Programs From Scratch?

    Python 898 63

  2. Benchmarking Goal-Oriented Software Engineering

    Python 201 20

  3. SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

    Python 20.1k 2.2k

  4. SWE-bench: Can Language Models Resolve Real-world Github Issues?

    Python 5.7k 944

  5. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

    Python 6.6k 906

  6. [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

    Python 746 127

Read the original on github.com ↗