Matt Pocock's New 2-Week Course: Slow Down Your AI Agents to Speed Up
mattpocockuk · x · 2026-10-29
Matt Pocock announces his most ambitious course yet: a 2-week program starting November 9 on building your company's "software factory." His thesis: everyone optimizes agent speed (loops, YOLO mode, dark factory), producing a "slop cannon" no serious org can trust—so slow down to speed up. The course installs brakes via software fundamentals—automated review, codebase design, DDD & ubiquitous language, mutation testing, feedback loops—before accelerating into a working factory system.
More from coding & agent
- Training multi-character LoRAs by having Claude Opus write the training code — Amazing_Painter_7692 · 2026-10-29
- "The Agentic Feeling Is That Google-Confidence on Steroids," Dev Reflects — enjalot · 2026-10-29
- 458K Synthetic RL Environments Yield Scaling Laws for Tool-Use Agents — amaarora · 2026-10-29
- Nous Research's New Plugin Auto-Routes Each Subagent to the Right Model — Teknium · 2026-10-29
- Researcher: purely on-policy RL is too sample-inefficient for long-horizon agents — JoshPurtell · 2026-10-29
- Arena skill makes 100 Claude Code sub-agents fight in a tournament for the best answer — blaizedsouza · 2026-10-29