LAI #123: Claude Code’s Codebase Was Accidentally Leaked

What we found inside, plus few-shot ordering tricks, DPO vs. GRPO, agentic RAG on Azure, and more! Good morning, AI enthusiasts! Claude Code’s entire codebase was accidentally leaked a couple of weeks ago, and I went through it. This week, I share what we found about how it handles memory, compacts conversations, runs background agents, and more. We also cover: Why flat tool registries cause agent failures and how an ontology layer that gates access based on state fixes it. Where SFT hits a ceiling and when to reach for DPO or GRPO: two post.