Quoting Drew Breunig
- ID
- 17131
- Status
- summarized
- Published
- 24 Aug 2026, 3:55 AM
- Fetched
- 24 Aug 2026, 4:30 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Aug/23/drew-breunig/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 7.5
- Created
- 24 Aug 2026, 4:30 AM
- Tags
- Audience
- developersvibe_codersai_agent_userssaas_founders
What happened
Drew Breunig argues that the era of relying on new AI models to automatically fix coding workflow problems is ending. With the arrival of an expensive but powerful model called Fable, teams must now deliberately route work to different models—using cheaper options like Opus, 5.6, K3, and GLM for most code, and reserving the costly Fable for specific tasks.
Why it matters
If you're building AI-assisted coding pipelines or agent workflows, you should stop assuming the next model drop will be free or cheap. Start implementing model routing strategies now—identify which tasks actually need the premium model and which can run on cheaper alternatives, because the cost gap between tiers is widening rather than closing.
Discussion angle
How to decide which coding tasks justify a premium model versus a cheap one—what does the routing decision tree look like in practice, and does this make custom harness engineering worth the investment again?