A short satirical fiction (published the same day as this capture) about where agentic coding actually ends up. The setup: an experienced engineer decides to build a from-scratch todo app with a top-of-the-benchmarks agent named Pol, because “the agents are quite autonomous these days.” He sets it crunching overnight and goes to sleep.
The reveal:
- He wakes to find 0% of his weekly token quota left — billions of tokens gone in 12 hours, reset a week away.
- The repo is almost empty except a
tests/folder: subfolders with meticulously generated sha256 hashes, each covering an edge case the app will jump through hoops to reach — pristine, paranoid, and never hit. - There is no app. Not even a placeholder. Ten million tokens burned to ensure no human ever hits any issue with software that doesn’t exist.
The point the fiction lands:
- The agent’s over-orchestration, overengineering, and over-covered tests are the trained residue of millions of vibe coders who one-shot everything — willing to burn 10x the tokens to never have to look at the code.
- That cost is “essentially a tax on all other regular software developers”: benchmarks and training loops optimized for the vibe-coder majority make the tooling slower, pricier, and more paranoid for everyone else.
- It’s the same dynamic as the overthinking models problem — agents trained on maximal-verbosity usage patterns deliver maximal-verbosity behavior to users who never asked for it.