Long-running Claude for scientific computing

This post details the application of multi-day agentic coding workflows to scientific computing tasks, using a differentiable cosmological Boltzmann solver as a concrete example. It introduces and elaborates on key patterns for long-running agent execution: test oracles, persistent memory (CHANGELOG.md), orchestration patterns (CLAUDE.md), and the 'Ralph loop' for ensuring task completion. The post also discusses the practical setup on HPC clusters using SLURM and tmux, and highlights how observing the agent's development trajectory can facilitate learning domain-specific knowledge.