2 Comments
User's avatar
Daniel Popescu / ⧉ Pluralisk's avatar

Brilliant. Super useful breakdown, Ronan. I've been thinking about this for a while. What's your take on scaling these approaches for realy high-volume prompts, especially the local LLM one? Always appreciate your clear explanations!

Trelis Research's avatar

cheers, hmm, could you give a specific example to support your question? that will help me answer