Simon Willison highlights Jacob Sansbury's account of building Spawn, a multiplayer game world changed by prompts to an in-game AI. The team says a swarm of Fable-powered agents edits live code and ships to production about hourly. It is a rare, concrete look at how far coding agents can run autonomously in production.
GitHub Copilot Fusion is now generally available. Instead of picking a model per task, developers select Fusion and an effort level, and Copilot decides which models run and how they cooperate. Administrators can restrict which models Fusion may use and make it the default. It is available in VS Code, the GitHub Copilot app, Copilot CLI and JetBrains IDEs.
Simon Willison argues that October 2026 is when AI models became good enough at game design to make vibe coded games genuinely fun. He built four browser games mostly with Claude Opus 5.5 and shares the prompts and workflow he used. The post is a practical look at iterating with coding agents, and at where GPT-6 models still fall short.
GitHub Copilot in VS Code now offers a configurable eagerness setting that controls how often inline suggestions appear and how large they are. Low, medium, and high modes all run on one model, selected with a control tag. The setting is available to paid Copilot subscribers, so you can match the assistance level to your task.