https://kjetiljd.github.io/ai-for-coding/categories/model-selection/Recent content in Model Selection on 💻✨ AI for CodingHugoen-usFri, 10 Jul 2026 00:00:00 +0000https://kjetiljd.github.io/ai-for-coding/tips/046-match-model-to-task/Fri, 10 Jul 2026 00:00:00 +0000https://kjetiljd.github.io/ai-for-coding/tips/046-match-model-to-task/Your coding agent isn’t one task — planning, grinding boilerplate, hunting bugs. Run /subagents to read the Copilot team’s own task→model map: cheap+fast for grinding, a different family for critique, your strong model for review. Vendors now ship the ladder.https://kjetiljd.github.io/ai-for-coding/tips/047-reasoning-effort-dial/Fri, 10 Jul 2026 00:00:00 +0000https://kjetiljd.github.io/ai-for-coding/tips/047-reasoning-effort-dial/Model choice is one lever; how hard the model thinks is another. Reasoning effort (low→xhigh) can matter more than model size — a mid-tier model thinking hard often beats a big one thinking little. In Copilot, set it in the /model picker with ←/→.