Post #4269804

@isotopp@infosec.exchange That’s the current methodology of Robert Martin (author of Clean Code). “My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.” That might work if you have complete coverage of tests. My experience is that at least half the tests you would need only become obvious after having written the code. Because the code itself is the ultimate specification.