I am really curious about the effects of this workflow. We started with Fable's high-quality 2D static, then 2D animated, then Opus's three.js. Each one was a paste of the smarter parent. I suppose this might be kind of like using Fable for orchestration, and lesser models for implementation in Claude Code?
If I have spare tokens at the end of the week, I will try real tests.
I am really curious about the effects of this workflow. We started with Fable's high-quality 2D static, then 2D animated, then Opus's three.js. Each one was a paste of the smarter parent. I suppose this might be kind of like using Fable for orchestration, and lesser models for implementation in Claude Code?
If I have spare tokens at the end of the week, I will try real tests.