Most AI tools are about thinking faster. You describe a problem, get a response, revise, repeat. The loop is still you doing the work — just with a smarter clipboard. Agents are different. An agent can receive a goal, figure out what needs to happen, take actions, check results, and adjust. The loop runs without you in it. That shift is smaller than it sounds in demos and larger than it sounds in practice. ...
Building in public has become a thing. There’s a whole genre of it — daily updates, follower counts, revenue milestones posted like scoreboards, the journey from zero to whatever. I’ve watched a lot of it. Some of it is useful. A lot of it is a content format that uses building as its subject matter. I want something different. I want the practice without the performance. What the Practice Is The actual reason to build in public — stripped of audience-building — is that it forces you to articulate what you’re doing. ...