Hyperscalers finance AI chips over six years but the hardware is obsolete in two or three. That gap quietly sets the compute price every AI product is planning around.
Microsoft's engineers merged 24% more pull requests with AI. The constraint didn't vanish; it moved to review, and most teams are still counting the wrong thing.
The AI infrastructure boom is partly lending to itself. That changes the cost curve you're planning around, and most companies building on it haven't noticed.
A frontier model just produced a novel math proof while similar tools still fumble routine operations. The dividing line is verifiability, not difficulty.
Public coding benchmarks have decoupled from real work. The teams getting value from AI build a small evaluation from their own merged pull requests instead.
Open-weight models now match frontier quality at a fifth of the cost. For anyone building on AI, that shifts where durable advantage has to come from.
