The billable hour was never a measurement. It was a grammar, and the machine is only changing its units. AI was supposed to kill the billable hour. The argument writes itself. When a research memo that took thirty associate hours takes ninety minutes of machine time, billing by the hour becomes either absurd or dishonest. Absurd if the firm bills ninety minutes for work it once sold for thirty hours. Dishonest if it bills thirty hours anyway. So the hour must die, and firms must flee to flat fe
Part I ranked governance proposals by the object they bind to. This one asks how long that object stays adequate. Part I built a method. Every governance proposal finally rests on something an outsider has to check: a statement, a claim, a procedure, a supply chain, a measured physical event. Rank proposals by that object and they sort. Anthropic’s Responsible Scaling Policy is scaffolding at the representation rung. Plan A has the stronger architecture and the harder clock. This part asks the
Anthropic’s Responsible Scaling Policy and the AI Futures Project’s Plan A are not rival answers to one question. They bind to different objects, cost different amounts to build, and break in different places. Two governance proposals arrived this year. Anthropic has revised its Responsible Scaling Policy four times since the February rewrite. The AI Futures Project published AI 2040: Plan A, a recommendation rather than a forecast: a US–China agreement in 2029, total research transparency, ma
An essay in the AI Has Ancestors series. AI is not the next internet. It is the next electricity — a general-purpose production technology whose gains arrive only when organizations stop being designed around the scarcity it has begun to remove. This series has argued that AI has ancestors: writing, the alphabet, the printing press, the digital wire — the family of encoding technologies, of which AI is the fifth member and the first to perform thought rather than work on its record. That is th
