Earlier quoted context omitted.
The productivity comes from not having the startup costs. You don’t need to research the best way to do X, just verify that X works via tests and documentation. I find it still takes T hours to actually implement X with an agent, but if I didn’t know how to do X it eliminates that startup cost which might make it take 3T hours instead. The only downside is not learning about method Y or Z that work differently than X…
> You don’t need to research the best way to do X, just verify that X works via tests and documentation. "Just verify" is glossing over a lot of difficult work, though. It doesn't just involve checking whether the program compiles and does what you wanted—that's the easy part. You should also verify that the program is secure, robust, reasonably performant, efficient, etc. Even if you think about these things, and as…
I run static analysis on mixed human/AI codebases. The AI parts pass tests fine but they'll have stuff any SAST tool flags on first run — hardcoded creds, wildcard CORS, string-built SQL. Works in a demo, turns into a CVE in prod.
And nobody's review capacity scaled with generation speed. Most teams don't even have semgrep in CI. So you get unreviewed code just sitting in production.
The "10x" is real if you count lines shipped. Nobody counts the fix cost downstream though.