Syntax - Tasty Web Development Treats

Snapshot · Syntax - Tasty Web Development Treats

1021: We got addicted to an AI model we can't talk about

Explore episode Jul 15, 2026

Where this was said

Model Routing and AI Integration

At 23:00 · chapter starts 21:51

Scott raises the model routing question that's been circulating in developer circles: can you meaningfully route between models for cost or capability gains? Dax is skeptical of most commercial routing products, which he sees as inference middlemen inventing a problem to solve. The fundamental challenge is that switching models mid-session is a full cache bust — expensive and disruptive. The routing decision has to happen at the beginning, often before there's enough signal to make it well. But there's a version that does work: the orchestrator pattern. Some OpenCode team members run expensive, capable primary models configured to never take direct action — they only spawn cheaper subagent models to do the actual work. This nets out cheaper overall because the expensive model's intelligence is applied only to orchestration, while the grunt work goes to commodity-priced models. And newer-generation models are significantly better at this parallel orchestration than their predecessors, making it practical now in a way it wasn't a year ago.

Similar snapshots