CS PhD @Stanford. Created @SWEbench (multi-lingual/modal); SWE-agent; SWE-smith; InterCode; CodeClash; ProgramBench
John Yang is a CS PhD student at Stanford creating SWE-bench, SWE-agent and related open benchmarks/tools for language model agents and code evaluation. Tagged Researcher as his primary identity is AI research on agents, evaluations and synthetic data rather than faculty, OSS advocacy or model training.
Public Tech-ranked followers appear first; other tracked followers remain below.
Last updated 18h ago · 2087 influencers tracked · 2000 ranked users
This page is showing the latest completed snapshot while a new crawl runs in the background.