Yea, similarly, I’ve heard people using fable for planning and then opus for execution. Makes sense to me. I also haven’t had to worry about cost for the most part since my company pays for it
Do you feel that with each new generation of LLMs you actually get better results? For example, you don’t change how you use Claude Code/Cursor - you use the same prompts and the same tools, yet you get different results when you switch from, say, Sonnet to Fable?
I personally don’t feel much difference. About 1-1,5 years ago, there was a moment when models became much smarter, but now the curve of “getting better” is flattening out.
I personally don’t feel much difference. About 1-1,5 years ago, there was a moment when models became much smarter, but now the curve of “getting better” is flattening out.