📣 NEWS: Check out ProgramBench, a 0% software from scratch benchmark
📣 NEWS: Check out mini-swe-agent, a 100 line AI agent that scores 77% on SWE-bench verified!
📣 NEWS: Check out CodeClash, the first goal-oriented SWE benchmark!

Hi 👋 I'm an AI research scientist at Meta Superintelligence focusing on agentic AI for software development. Some of my smaller open source projects are described here (but it's an incomplete list).