Hacker News Reader

Comment by rvz | Hacker News Reader

As a last resort, do the code-review with a live pair programming session.

If they can't explain their own code then it is by default a bad pull request.

At the end of the day, everyone's time is being wasted on tokens and on the increasing cognitive complexity of AI generated code.

View on HN

So if they say "idk Claude did it", what would you write in the PR review box?

REJECTED: Engineer does not understand what they wrote.

Feels like the title of a blog post someone will write

Ah, like this one? https://crabby-rathbun.github.io/mjrathbun-website/blog/post...

If he did so much verification to prove it's right, why not just write it in the first place?

> Engineer does not understand what they wrote.

"""""wrote"""""

s/wrote/pushed/

A teammate that can't write (or at least, can't explain) "their own code"

Actively drags down the morale and productivity of their team (because everyone is getting flooded with AI slop PR's)

AND costs far too much money relative to everyone else doing actual work? (token usage)

By god they sound like management material

"Author of this pull request has not yet reviewed code and does not understand it. This PR was submitted prematurely, probably by accident.

Please, check whether you accidentally submitted other unreviewed code - and close such PRs for now and reopen once reviewed."

Don’t ever write this in a professional environment. It’s childish ant achieves nothing other than pissing off the person it’s targeted at and probably the manager who now has to deal with a shitty behaviour complaint.

The same as if they said it was copied from stack overflow, or if it’s wrong; “I think there’s a problem here, it’s XYZ”. If your peer ignores you and you were wrong, it was their call to make. If you were right - take it to them or the manager depending on how many times it’s happened.

Reply on news.ycombinator.com