Running tens of millions of experiments on useless programs with LLMs
bushibuilds · x · 2026-10-13
bushibuilds published an article, "Why Am I Running Tens of Millions of Experiments on Useless Programs?" describing a large-scale automated experimentation approach meant to be handed to your LLM, with visualizations of thousands of random-walk trajectories.
More from coding & agent
- Paperclip v2026.1012.0 Lets Claude Code, Codex and MCP Clients Join Your Team — jamesbrooksco · 2026-10-13
- Plane Compose: define projects in YAML, store in Git, let agents execute — JosephJacks_ · 2026-10-13
- Dev's gut take: Wonder works best as orchestrator-advisor in a three-model 'triforce' — kevinkern · 2026-10-13
- Fitness app with 7,000-exercise library ships MCP for ChatGPT, Claude and Cursor — JustSuperHuman · 2026-10-13
- Postedly MCP lets AI agents send physical mail and faxes with human review — sparkignitefire · 2026-10-13
- Building a local AI video-editing pipeline with Claude that learns from feedback — alexgoughcooper · 2026-10-13