Comment by apical_dendrite | Hacker News Reader

Comment by apical_dendrite | Hacker News Reader

Parent Full thread

apical_dendrite

This drives me absolutely crazy. My colleagues send me huge PRs to review (say 2000+ lines). I don't just paste comments from the LLM, I ask the LLM to review it, but I also review it myself. I only include ideas from the LLM if I think a) the LLM has gotten the issue right and b) it's worth having the developer take the time to address the issue. I always write the comment myself so I can add relevant context and put it in my own voice.

Then, after I've put in all this work, the developer just replies with a copy-paste of what the LLM thinks about my comment. I have no idea if the developer read or understood my point. I have no idea if he agrees or not. It doesn't just seem disrespectful to the effort I put into the review, it also leaves me in a difficult position as a tech lead because I have no idea if the person who is ultimately responsible for this code understands the code, my feedback on the code, or the changes that the LLM made to address my feedback. If you're responsible for a feature, I want to be able to feel like you're thinking critically about how that feature works. Right now, I just feel like you're blindly doing everything that I tell you. It also feels like I'm shouting into the void. We're colleagues, we should be able to have a conversation about technical subjects!

Beyond mirroring the engineering practices that you yourself want to see other people perform, have you found any techniques to get people to … in short, do their job again? Understand context, understand what they did, why they did it, what they’re doing, etc.

The +/-2000 line MR was bad when humans wrote it. It’s way worse when the human didn’t even write or read it.

And just vomiting automated CodeRabbit talking points back and forth at each other feels equally harmful.

Are we really tolerating turning ourselves into LLM rubber stamps?

For me the trick was just leaning all the way into it. I had a residual idea that if someone sends me a 2000 line PR, 10 page design, etc., that this represents some concrete investment of time and effort that deserves my careful consideration. And it just doesn't anymore.

I have one project where there must be hundreds of pages of design proposals I have not read and will never read, because the author really likes having Claude generate complete design proposals based on incomplete understanding. So every week or two he sends me a new one, I spend 30 seconds skimming it, and then I tab back to Slack to ask him to explain.

I don't like working this way, but you know, I don't like doing rollouts either. It's certainly better than being a human rubberstamp.

That sounds like a fantastic way for a malicious actor or an unintentional prompt injection exploit to sneak into a codebase.

Perhaps you could explain how this is different from rubber stamping, if it’s just 30 seconds of reading.

Does the conversation you have reveal what they actually want?

And what about the 2000 line change? Does that get stamped after someone talks about the change but without deeply reading it?

Typically what happens is that we have a good conversation, we make progress towards figuring out what they should want to do and how they should try to do it, and the 2000 line PR or 10 page doc gets abandoned. I do read things in detail when I expect I might one day be convinced to approve them, but that fraction has plummeted from 95% to like 20% since January.

Have you noticed an increase in their willingness to “do the right thing first time” during these last 6 months since your approval rate has dropped that much? (Even if the right thing is to have more conversations)?

Do you know if there’s a way to incentivize them to lean toward doing the right thing first? Are the company and stakeholder goals and objectives in line with them making progress toward higher quality engineering? That is, are these juniors protected from randoms asking them to circumvent good process, etc?

Unfortunately, I've had a number of people explicitly defend that nothing's going wrong here. Their view is that, if sloppy code is cheap, everyone might as well produce some to illustrate their ideas before having a conversation. I'm skeptical of that position but haven't had much luck in fighting it.

> Are the company and stakeholder goals and objectives in line with them making progress toward higher quality engineering? That is, are these juniors protected from randoms asking them to circumvent good process, etc?

In my personal experience yes, but I've seen a few teams and heard stories of many more where the juniors are not protected and they just ship regressions and outages all the time now. I think the trend towards AI cost controls will mitigate this, although the impact will of course be uneven as companies behind the curve discover powerful agentic coding for the first time.

You're fighting the good fight.

I tried to get our team to enforce a max PR size.

It worked for a while. There is a GitHub action that you can configure to fail if the PR is too large.

But then we started a new project and I didn’t add it right away since it’s a small team and I figured we could use the honor system.

Since then there have been lots of massive PRs but there’s not much willingness to go back to enforcing the rule because it might slow us down…

It’s frustrating.

Out of curiosity, with their current paradigm, what's the regression rate *and* how long do PRs stay in pending?

What's even worse is when you go though such PRs and your comments are handled in minutes, with replies explaining the change with perfect spelling and em dashes. At which point you ask yourself: "What am I doing here? His agent wrote the entire thing, and now I'm going through it and telling his agent what to fix. Why is he even needed?"

Or even, even worse is when you get a PR from a co-worker, you spend a lot of time explaining why that's bad idea, only for the person to say "Sorry, my openclaw/etc posted that. I'll close it." Or even the opposite, you tell a co-worker: "Hey, it was a great idea to change X." and he says "X? What is X?... Oh that must have been my agent."

Why is he even needed?

that's the point where i would want to start firing people. not because i want to replace them with AI, but because if they use AI to answer without contributing their own thoughts they make themselves replaceable.

Yeah, I don't love this part of the work. Especially since it's completely exploded out the text of basically everything. I'm also suspicious that the person that generated that text didn't read any of it.

How do ya feel about altercations at work? If like most, then hope your colleagues find your post & decide to stop (without realizing you’re their lead!).

Your prose curves from line to line very elegantly, not sure if its intentional

Reply on news.ycombinator.com