I recently (2 days ago) noticed i enjoy it a lot more if i use a super fast model with low reasoning (gpt 6 luna low effort + fast mode). That way, i can still have hands on the entire time and dont have to wait around for 20minutes for it to finish up and have made a bunch of decisions without me.
Also, LLMs are first and foremost excellent at reading ultra fast. Makes it excellent for summarizing and re-representing modules of your code
Do you use luna to plan as well, or is it just code? I am interesting in understanding the process you follow.
My workflow is the most common one - use something like Opus to help create a spec document (I decide the specs and then get the LLM to ask me questions to harden it), then generate a plan, and then implement. I use Opus the whole time. Sonnet sometimes if it is a simple task.
humlex · · focus · HN ↗
Also, LLMs are first and foremost excellent at reading ultra fast. Makes it excellent for summarizing and re-representing modules of your code
nibbleyou · · focus · HN ↗
My workflow is the most common one - use something like Opus to help create a spec document (I decide the specs and then get the LLM to ask me questions to harden it), then generate a plan, and then implement. I use Opus the whole time. Sonnet sometimes if it is a simple task.