When an agent writes the code, you stop reading every line. You can pretend otherwise for a while, but on any real codebase you end up skimming a 600 line diff and approving it because nothing jumped out. Nothing jumping out is not the same as nothing being wrong.
Source: [Dev.to](https://dev.to/grantps/tooling-every-ai-software-harness-should-have-4512)