Hacker News Reader

A lot of my problem with AI writing is that the facts aren’t checked. You get a big cheesy dramatic arc but the core story isn’t factually correct. There’s only so much time in a lifetime, too little to waste fact checking someone else’s work because they couldn’t be bothered to.

View on HN

I have junior devs submitting huge PRs with multi paragraph descriptions about load baring root causes and "why this works". Then I ask them directly what are the steps to test this and they don't know, they have never run the code.

Rather than entertain the idea of reviewing the code I just send it back to them until they work out how to run it. And almost always they submit a new change because the last one didn't actually work, despite how confident and articulate claude was to them.

So, your company doesn't have CI/CD and gates? AI isn't your problem.

A change can pass CI without actually making the change required. The tests test that the code does what it does, not that it does what the user wanted.

AI is really good at making tests that pass even if the change itself is wrong.

Fwiw these harnesses run appropriate tests before pushing anyway, so CI CD pass is almost a guarantee. Correctness is another matter.

Reply on news.ycombinator.com