Sebastian Raschka: Claude Code's Real Secret Sauce Is the Harness, Not the Model

Sebastian Raschka Blog·medium signal

ML researcher Sebastian Raschka published a detailed analysis of the leaked Claude Code source, concluding that the surrounding software harness — not the underlying Claude model — is the primary driver of coding performance. Key architectural patterns: file-read deduplication, static/dynamic content caching with boundary markers, dedicated Grep/Glob/LSP tools instead of bash, subagent parallelization with shared cache, and context optimization that writes oversized tool results to disk with preview references. Raschka argues that DeepSeek, MiniMax, or Kimi could achieve similar coding performance with equivalent harness engineering.