Hacker News Reader

Comment by raw_anon_1111 | Hacker News Reader

> Even if I generate a 1,000 line PR in 30 minutes I still need to understand and review it. Since I am responsible for the code I ship, this makes me the bottleneck.

I am not responsible for choosing whether the code I write using a for loop or while loop. I am responsible for whether my implementation - code, architecture, user experience - meets the functional and non functional requirements. It’s been well over a decade that my responsibilities didn’t require delegation to other developers doing the work or even outsourcing an entire implementation to another company like a SalesForce implementation.

View on HN

When I got my first job long ago, I found that code review does involve arguing over things like for vs while loop, or having proper grammar in comments. Thought about quitting for a sec.

Now that I have more experience and manage other SWEs, I was right, that stuff was dumb and I'm glad that nobody cares anymore. I'll spend the time reviewing but only the important things.

Unfortunately, people do care that the AI agents don’t code just like they do.

Once I got to the point where I was delegating complete implementations to seniors with just “this is a high level idea of what Becky’s department wants. You now know as much I do. If you have any business related questions go ask Becky and come back to me with a design and these are our only technical constraints”. Then two weeks later there are things I might have done differently. But it meets all of the functional and non functional requirements. I bite my toungue and move on.

His team is going to be responsable for it.

Now I don’t treat AI as a senior developer. I treat it as a mid level ticket taker. If their is going to be a feature change, I ain’t doing it any more. The coding agent is. I am just going to keep good documentation in various MD files for context.

Is there something about LLMs that suddenly make grammar and style irrelevant? Is your take, no human is going to read this ever again, so why bother making it pretty and consistent/readable?

It was never relevant, LLM or not. When reviewing junior SWEs' code pre LLMs, I didn't care about 75% of the style guide. I cared if they were using the DB wrong or had race conditions or wrote code I couldn't read.

In other comment, meant that other reviewers who used to nitpick have stopped for whatever reason, maybe because overall people are busier now.

Reply on news.ycombinator.com