"Engineering Management After the Cost of Code Collapsed" draws 196 comments arguing verification is the new bottleneck.

Karim Jedda's essay hit 144 points with a deliberately narrow claim: the cost of producing plausible code has collapsed and won't return, but claimed speedups remain unproven and concentrated in greenfield and boilerplate rather than deep system changes (karimjedda.com). Consequences he draws: velocity and PR-count metrics become actively misleading, machine-checkable verification accelerates while semantic verification stays human-bound and slow, and investing in machine-checkable correctness specs becomes the highest-leverage infrastructure work because it caps how much acceleration an org can capture. He flags junior-engineer training as unsolved with a 3-5 year lag, since the small bugs and boilerplate that built judgment are exactly what agents now absorb. That last one keeps me up.