It's far more than planning. You have to "get to know your LLM" and it's quirks so you know how to write for it, and when they release new updates (cut off time or version), you have to do it again. Same for the agentic frameworks, when they change their system prompts and such.
It's a giant, non-deterministic, let's see what works good based on our vibes, mess of an approach right now. Even within the models, architecturally, there are recent results that indicate people are trying out weird things to see if they work, unclear if they are coming from first-principle intuition and hypothesis formation, or just throwing things at the wall to see what sticks
It's a giant, non-deterministic, let's see what works good based on our vibes, mess of an approach right now. Even within the models, architecturally, there are recent results that indicate people are trying out weird things to see if they work, unclear if they are coming from first-principle intuition and hypothesis formation, or just throwing things at the wall to see what sticks