This is a series on rethinking software from first principles — what changes when we stop optimizing legacy architectures and start from what we now know about AI, files, and how people actually work.

Principles :

1. AI is only going to get smarter:
   • Models are getting better, faster. A reality that informs decisions on which problems to solve and which to leave for the AI to solve.
2. Code is cheap, human headspace is not:
   • Opinionated stance and taste matter - when there’s intentional thought behind a product, it shows.
   • We can, but should we? If so, where do we start? where does it end? how does it make sense 6 months from now?
3. Agents are going to be ubiquitous:
   • The explosion of OpenClaw just revealed the latent demand, it is only a matter of time before we have the claude code cli equivalent which is going to be omnipowerful