Hacker News Reader

Comment by sorokod | Hacker News Reader

> One of the annoying things engineers have to deal with is stopping whatever they're doing and doing a review.

I would have thought that reviewing PRs and doing it well is in the job description. You latter mention "someone" a few times - who that someone might be?

View on HN

Can we make an LLM do it?

“You are a cranky senior software engineer who loves to nitpick change requests. Here are your coding standards. You only sign off of a change after you are sure it works; if you run out of compute credits before you can prove it to yourself, reject the change as too complex.”

Balance things, pit the LLMs against each other.

This would probably catch a lot of errors

We do this at work and it's amazing.

I do this all the time. I pass my code into "you are a skeptic and hate all the code my student produces: here is their latest PR etc.. etc.."

I have devs that do this and we have CI AI code review. Problem is, it always finds something. So the devs that have been in the code base for a while know what to ignore, the new devs get bogged down by research. It's a net benefit as it forces them to learn, which they should be doing. It def slows them down though which goes against some of what I see about the productivity boost claims. A human reviewer with the codebase experience is still needed.

Slowing down new developers by forcing them to understand the product and context better is a good thing.

I do agree that the tool we use (code rabbit) is a little too nitpicky, but it's right way more than it's wrong.

I don’t use any of these sorts of tools, so sorry for the naive questions…

What sort of thing does it find? Bad smells (possibly known imperfections but least-bad-picks), bugs (maybe triaged), or violations of the coding guides (maybe known and waivered)?

I wonder if there’s a need for something like a RAG of known issues…

GPT 5+ high+ review bots find consistently good issues on average for me, sometimes they’re bogus, but sometimes they’re really, really good finds. I was impressed more than once.

This response fails entirely to answer the question.

Reply on news.ycombinator.com