Get an AI code review in 10 seconds • Hacker News Board

Re: Get an AI code review in 10 seconds

#21

Post by howToTestFE » Sun, Dec 21, 2025, 8:55 PM UTC

while this approach is useful, i think the diff is too small to catch a lot of bugs.

i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff, and definitely can see the rest of the file your are editing (not just the lines in the diff)

Re: Get an AI code review in 10 seconds

#22

Post by afro88 » Sun, Dec 21, 2025, 9:02 PM UTC

ocharles wrote: post #3

I recently started using LLMs to review my code before asking for a more formal review from colleagues. It's actually been surprisingly useful - why waste my colleagues time with small obvious things? But it's also gone much further than that sometimes with deeper reviews points. Even when I don't agree with them it's great having that little bit more food for thought - if anything it helps seed the review

This is exactly the right approach IMO. You find the signal amongst the slop, and all your colleagues see is a better PR.

Re: Get an AI code review in 10 seconds

#23

Post by sgt101 » Sun, Dec 21, 2025, 9:08 PM UTC

mehdibl wrote: post #17

How to do agentic workflow like 2 years ago.

What would SOA be?

Re: Get an AI code review in 10 seconds

#24

Post by porise » Sun, Dec 21, 2025, 9:09 PM UTC

zedascouves wrote: post #12

Hum? I just tell claude to review pr #123 and it uses 'gh' to do everything, including responding to human comments! Feedback from coleagues has been awesome. We are sooo gonna get replaced soon...

Good thing I work on an old C++ code base where it's impossible for AI to go through the millions of lines that all interact horribly in unpredictable ways.

Re: Get an AI code review in 10 seconds

#25

Post by fweimer » Sun, Dec 21, 2025, 9:32 PM UTC

Smaug123 wrote: post #2

With not much more effort you can get a much better review by additionally concatenating the touched files and sending them as context along with the diff. It was the work of about five minutes to make the scaffolding of a very basic bot that does this, and then somewhat more time iterating on the prompt. By the way, I find it's seriously worth sucking up the extra ~four minutes of delay and going up to GPT-5 high ra…

Do you do any preprocessing of diffs to replace significant whitespace with some token that is easier to spot? In my experience, some LLMs cannot tell unchanged context from the actual changes. That's especially annoying with -U99999 diffs as a shortcut to provide full file context.

Re: Get an AI code review in 10 seconds

#26

Post by syndacks » Sun, Dec 21, 2025, 9:35 PM UTC

In CC or Codex (or whichever) — “run git diff and review”

Re: Get an AI code review in 10 seconds

#27

Post by devttyeu » Sun, Dec 21, 2025, 9:36 PM UTC

porise wrote: post #24

zedascouves wrote: post #12

Hum? I just tell claude to review pr #123 and it uses 'gh' to do everything, including responding to human comments! Feedback from coleagues has been awesome. We are sooo gonna get replaced soon...

Good thing I work on an old C++ code base where it's impossible for AI to go through the millions of lines that all interact horribly in unpredictable ways.

Funny you mention that, I have very recently just came back from a one-shot prompt which fixed a rather complex template instantiation issue in a relatively big very convoluted low-level codebase (lots of asm, SPDK / userspace nvme, unholy shuffling of data between numa domains into shared l3/l2 caches). That codebase maybe isn't in millions of lines of code but definitely is complex enough to need a month of onboarding time. Or you know, just give Claude Opus 4.5 a lldb backtrace with 70% symbols missing due to unholy linker gymnastics and get a working fix in 10 mins.

And those are the worst models we will have used from now on.

Re: Get an AI code review in 10 seconds

#28

Post by didibus » Sun, Dec 21, 2025, 9:36 PM UTC

zedascouves wrote: post #12

Hum? I just tell claude to review pr #123 and it uses 'gh' to do everything, including responding to human comments! Feedback from coleagues has been awesome. We are sooo gonna get replaced soon...

> Feedback from colleagues has been awesome

Colleague's feedback:

Claude> Address comments on PR #123

Re: Get an AI code review in 10 seconds

#29

Post by tharkun__ » Sun, Dec 21, 2025, 9:46 PM UTC

zedascouves wrote: post #12

Hum? I just tell claude to review pr #123 and it uses 'gh' to do everything, including responding to human comments! Feedback from coleagues has been awesome. We are sooo gonna get replaced soon...

Not my experience. Most Claude reviews are horrible and if I catch you replying with Claude (any AI really) under your own name you are gonna get two earfulls. Don't get me wrong, if you have an AI bot that I can have a convo with on the PR, sure. But you passing their stuff off as you: do that twice and you're dead to me.

Now, I use it as well to review, just like you mention it pulls it via gh, has all the source to reference and then tells me what it thinks. But it can't be left alone.

Similarly people have been trying to pass root cause analyses off as true and they sound confident but have holes like a good Swiss cheese.

Re: Get an AI code review in 10 seconds

#30

Post by mvanbaak » Sun, Dec 21, 2025, 9:57 PM UTC

I still dont get the idea about AI code reviews. A code review (at least in my opinion) is for your peers to check if the changes will have a positive or negative effect on the overall code + architecture. I have yet to see an LLM being good at this.

Sure, they will leave comments about common made errors (your editor should already warn about this before you even commit it) etc. But to notify about this weird thing that was done to make sure something a lot of customers wanted is made reality.

also, PR's are created to share knowledge. Questions and answers on them are to spread knowledge in the team. AI does not do that.

[edit] Added the part about knowledge sharing