News for hackers. Stuff that matters.
Re:Getting AI to work in complex codebases by prisenco on Tuesday September 23, 2025 @03:27PM (#45351597)
Are you vibe coding or have the 200k LoC been human reviewed?
Re:Getting AI to work in complex codebases by iagooar on Tuesday September 23, 2025 @04:48PM (#45352555)
I would not call it vibe coding. But I do not check all changed lines of code either.

In my opinion, and this is really my opinion, in the age of coding with AI, code review is changing as well. If you speed up how much code can be produced, you need to speed up code review accordingly.

I use automated tools most of the time AND I do very thorough manual testing. I am thinking about a more sophisticated testing setup, including integration tests via using a headless browser. It definitely is a field where tooling needs to catch up.

Re:Getting AI to work in complex codebases by nobunaga on Tuesday September 23, 2025 @05:46PM (#45353168)
[flagged]
Re:Getting AI to work in complex codebases by iagooar on Tuesday September 23, 2025 @06:04PM (#45353343)
Strong feelings are fair, but the architect analogy cuts the other way. Architects and civil engineers do not eyeball every rebar or hand compute every load. They probably use way more automation than you would think.

I do not claim this is vibe coding, and I do not ship unreviewed changes to safety critical systems (in case this is what people think). I claim that in 2025 reviewing every single changed line is not the only way to achieve quality at the scale that AI codegen enables. The unit of review is shifting from lines to specifications.

Re:Getting AI to work in complex codebases by nobunaga on Wednesday September 24, 2025 @04:59PM (#45365870)
No they dont check it because its already been checked and quality controlled by other people. One person isnt producing every aspect and componenet of a bridge. Its made by teams of people who thoroughly go through every little detail and check every aspect to make sure when its put into production, it will handle the load.

You cannot trust AI, its simple as that. It lies, it hallucinates and it can produce test code that can pass when it reality it does nothing that you expect it to even if you detail every little thing. Thats a fact.

Before its too late, come to your sense dude. I dont even think you believe what you say, because if you do, Id never want to work with you and neither would so many other people. You are making our profession some kind of toy. Thanks for contributing to the shitshow and making me realise that I have to be very careful who I work with in the future.

Re:Getting AI to work in complex codebases by dang on Wednesday September 24, 2025 @10:23PM (#45368607)
You can't attack another user like that here.

Since you've continued to break the site guidelines right after we asked you to stop, I've banned the account.

If you don't want to be banned, you're welcome to email [email protected] and give us reason to believe that you'll follow the rules in the future. They're here: https://news.ycombinator.com/newsguidelines.html.

Re:Getting AI to work in complex codebases by baw-bag on Tuesday September 23, 2025 @06:45PM (#45353783)
You were never an engineer. I'm 18 years into my career on the web and games and I was never an engineer. It's blind people leading blind people and your somewhere in the middle based on 2013 patterns you got to this point on and 2024 advancements called "Vibe Coding" and you get paid $$ to make it work.

Building a bridge from steel that lasts 100 years and carries real living people in the tens or hundreds of thousands per day without failing under massive weather spikes is engineering.

Re:Getting AI to work in complex codebases by prisenco on Tuesday September 23, 2025 @05:33PM (#45353029)
[flagged]
Re:Getting AI to work in complex codebases by nobunaga on Tuesday September 23, 2025 @05:47PM (#45353175)
It’s unbelievable right? I’m flabbergasted that there are engineers like this shipping code.
Re:Getting AI to work in complex codebases by pton_xd on Tuesday September 23, 2025 @06:46PM (#45353786)
We've all been waiting for the other shoe to drop. Everyone points out that reviewing code is more difficult than writing it. The natural question is, if AI is generating thousands of lines of code per day, how do you keep up with reviewing it all?

The answer: you don't!

Seems like this reality will become increasingly justified and embraced in the months to come. Really though it feels like a natural progression of the package manager driven "dependency hell" style of development, except now it's your literal business logic that's essentially a dependency that has never been reviewed.

Re:Getting AI to work in complex codebases by prisenco on Tuesday September 23, 2025 @06:41PM (#45353745)
I don't believe they've shipped yet, based on their comments.
Re:Getting AI to work in complex codebases by iagooar on Tuesday September 23, 2025 @06:06PM (#45353375)
Tools change, standards do not.

My process is probably more robust than simply reviewing each line of code. But hey, I am not against doing it, if that is your policy. I had worked the old-fashioned way for over 15 years, I know exactly what pitfalls to watch out for.

Re:Getting AI to work in complex codebases by nobunaga on Wednesday September 24, 2025 @05:00PM (#45365889)
Clearly you don't :)