It's easier to be token-efficient in domains you already have expertise in.
- It's easier to be token-efficient in domains you already have expertise in.
- If you don't have expertise, you just have to throw everything at the wall and apply meta-cognitive patterns.
- For example, have it spin up adversarial review sub-agents often.
- To get good results from LLMs requires meta-cognition.
- You have it in the domains you have expertise in, automatically.
- You don't have it in other domains.
- Some structures can provide it, especially with LLMs that have infinite patience.
- But it takes time, tokens, and you have to remember to do it.