Microsoft just hit the brakes on AI… for its own engineers. Not because the tools were bad. Because the bill got insane. For 2 years Big Tech sold one promise: “AI will replace expensive humans.” Now the companies actually using AI at scale are discovering something awkward: the AI is becoming the expensive employee. Microsoft reportedly rolled out Claude Code internally and usage exploded. Engineers used it for reviews, debugging, refactors, everything. Then finance looked at the token spend. Suddenly the same company that poured billions into Anthropic started pushing engineers off Claude and onto cheaper internal models. That alone should tell you something. Uber saw the same thing. Their engineers adopted AI fast. Leadership even gamified usage with internal rankings. But heavy users were reportedly burning thousands of dollars a month in tokens. The more productive people became with AI… the larger the infrastructure bill got. And then Nvidia’s own VP said the quiet part out loud: for some teams, compute costs are already higher than employee costs. Read that again. The chips are now costing more than the engineers. This completely breaks the story Wall Street has been pricing in: → fewer workers → lower costs → infinite productivity → bigger margins Because AI doesn’t behave like normal software. The deeper companies integrate it, the more tokens they consume. More agents → more inference More automation → more compute More usage → larger recurring bills Cheap tokens don’t automatically mean cheap systems when usage grows exponentially. That’s why companies are suddenly building internal dashboards to track AI consumption like cloud spend. The new corporate fear isn’t employees wasting time. It’s employees generating too many tokens. AI may still transform software forever. But the economics are starting to look less like “replace labor” and more like: replace payroll with an even bigger infrastructure invoice. And that changes everything.