Software · Opinion argued from sources
Software development philosophies
How should software get built? I have opinions, and I argue each one from sources I can link, with the arithmetic where you can move it. There are six articles so far, and more will come.
Articles
- More people, more agents, same planWhy adding people, or AI agents, to a project does not speed it up unless the work has been partitioned first.
- Who to hire nowThe engineer worth having on a team has changed because of LLMs, agent graphs and second brains: my points from other Lab pages, gathered and linked.
- Attention is the bottleneckThe scarce thing in a team that builds with agents is a person’s attention: a vendor’s design for an always-on agent, taken apart with my own Lab pages.
- What gets cheap, and what doesn’tWhen execution gets cheap, where the margin moves: a model’s answer taken apart with my own Lab pages, and my claim about guarantees and service contracts.
- A-changin’The pile of small tasks used to decide who ranked first. AI is shrinking the pile. Here’s who I’d hire when it stops deciding.
- Humans outside the loopCode has never been cheaper to make or to throw away. So I think people step out of the coding loop and harden what’s around it: the goals, the constraints and the checks, which is where a person’s review belongs.
More to come.
