Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Lessons for Agentic Coding: What should we do when code is cheap?

dbreunig.com

Post reply on HN
Print view View original

181–190 of 260 posts

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#181

Post by philwelch »

zozbot234 wrote: post #124
peab wrote: post #119

Earlier quoted context omitted.

How can you say it has "nothing to do with software engineering" with a straight face? I think you might be in serious denial. Of course writing code isn't the only task of a software engineer, but it's an important one. There wouldn't be so much controversy if it wasn't the case

"Writing code" as a task of its own is called cowboy coding. It's neat that AI can do this now, but that has nothing to do with proper software engineering which always starts from a careful, human-led design.

Yes and every AI-first development workflow worth its salt does exactly this, and it does it much more thoroughly than I’ve ever seen a team of meatbags do it.

My workflow, at a high level, is:

1. I write a high level spec. Not as high level as a single-sentence prompt, but high level enough to capture my top requirements.

2. I prompt the AI to interview me about the spec to clear up any ambiguity or open questions, then when I’m satisfied, the AI writes a longer spec, which I then review.

3. Then I prompt the AI to write an implementation plan based on the spec. I might just skim this, and by this point I might be asking the LLM more questions than it’s asking me.

4. Now I hand it off to the implementer agent.

This isn’t cowboy coding, it’s not even agile. It’s waterfall. The problem with doing waterfall was that it’s too slow, especially with the deserialization/serialization cost of routing all of this documentation through meatbrains. The LLM is doing just as much work, true, but faster.

The thing I found surprising was that, while LLM’s are still pretty awful at writing as an art form, they are better technical writers than I have the time to be, especially when writing for an audience of other LLM’s.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#182

Post by dawnerd »

threepts wrote: post #138
neya wrote: post #104

Earlier quoted context omitted.

What you are describing is a the role of a manager, not a software engineer. Software engineering has very little to do with writing code, but more on architecting at the higher level on what needs to be done. The code is just the executional part. LLMs can code? Ok good. Without a clear architectural pathway / direction, that code is just useless. It's not tech debt. It's just a bunch of random strings. You can argu…

That is why we have SWE bench pro, they test architecture design too, turns out 1000 dollars of tokens outperform 10k dollars of labor in meta design.

1000 dollars of subsidized tokens.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#183

Post by readitalready »

applfanboysbgon wrote: post #96
readitalready wrote: post #93

Earlier quoted context omitted.

No fixing the mess definitely does not take longer than writing it oneself. Your linter should identify all issues - including architectural and stylistic choices - and the AI agents will immediately repair them. It's about 1000x faster than a human code at repairing its own mess.

> Your linter should identify all issues - including architectural If a linter could deterministically identify bad architecture, you wouldn't need an LLM, your linters could just write your code for you. The vibe coding takes are just getting more and more empty-headed...

Your custom linters don't check architectural design?

linters statically check code and provide deterministic recommendations. LLMs are used to make judgement. I specifically write my linters for my project to make recommendations for LLMs.

This is how you save on token usage, so your LLMS aren't wasting tokens on static analysis that a linter could do for free.

That's at least how I make my linters.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#184

Post by QuercusMax »

peab wrote: post #161
shimman wrote: post #152

Earlier quoted context omitted.

Writing code and copying the output of an LLM is absolutely not the same. You wouldn't call someone an author that takes LLM outputs and shoves it in a book. IDK why this distinction doesn't apply to devs too.

You call someone an author when they use a ghostwriter. They're giving inputs that are core to the output, even though they aren't doing all the writing. Same thing.

Or even more appropriate: a movie director is almost never on-screen but the actors aren't the ones determining the shots to use or writing the script.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#186

Post by Salgat »

swader999 wrote: post #136
girvo wrote: post #113

Earlier quoted context omitted.

The dirty secret is all the people talking about shipping 4 features a day etc are just lying about reviewing anything. They don’t review it at all.

I review more thoroughly and faster with Claude than without.

Claude absolutely improves code review quality, but it still misses a lot. It's a second pair of eyes, it doesn't replace/remove the work you have to put in to fully review the code yourself.

It's like saying that you code reviewed faster just because someone else also reviewed the code, that's not how it works.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#187

Post by swader999 »

Salgat wrote: post #186
swader999 wrote: post #136

Earlier quoted context omitted.

I review more thoroughly and faster with Claude than without.

Claude absolutely improves code review quality, but it still misses a lot. It's a second pair of eyes, it doesn't replace/remove the work you have to put in to fully review the code yourself. It's like saying that you code reviewed faster just because someone else also reviewed the code, that's not how it works.

Agree, and with CC my volume and quality of PR review has substantially increased since 4.5. Without CC for review we would have a ridiculous bottleneck in our dev/qa pipeline.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#188

Post by ikrenji »

HarHarVeryFunny wrote: post #103
spicyusername wrote: post #74

A lot of people down on AI in this thread, but I'm watching the industry slip over the line of trust with these latest frontier models. GPT 5.5 is the first model good enough for me to just let rip. Every jira ticket I see now has acceptance criteria, reproduction steps, and detailed information about why the ticket exists. Every commit message now matches the repo style, and has detailed information about what's con…

> Software is going to pile up because developing it is now cheap. Software to do what, though ?! Coding, maybe 10% of a developers job (Brooks "Silver Bullet" estimates 1/6), was never the bottleneck, and even if you automated that away entirely then you've only reduced development time by 10% (assuming you are not doing human code review etc). I would also argue that software development as a whole (not just the co…

you can't continue shipping code the same way pre-LLM vs post-LLM and expecting a huge speed gain. the trick is abandoning the old models and bottlenecks and embracing the new possibilities enabled by LLMs. requires a high trust environment

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#189

Post by RealityVoid »

ikrenji wrote: post #188
HarHarVeryFunny wrote: post #103

Earlier quoted context omitted.

> Software is going to pile up because developing it is now cheap. Software to do what, though ?! Coding, maybe 10% of a developers job (Brooks "Silver Bullet" estimates 1/6), was never the bottleneck, and even if you automated that away entirely then you've only reduced development time by 10% (assuming you are not doing human code review etc). I would also argue that software development as a whole (not just the co…

you can't continue shipping code the same way pre-LLM vs post-LLM and expecting a huge speed gain. the trick is abandoning the old models and bottlenecks and embracing the new possibilities enabled by LLMs. requires a high trust environment

High... Ugh, trust... In the... LLM? Hah!

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#190

Post by peab »

shimman wrote: post #173
peab wrote: post #161

Earlier quoted context omitted.

You call someone an author when they use a ghostwriter. They're giving inputs that are core to the output, even though they aren't doing all the writing. Same thing.

I can assure you a sizable amount of people in the writing community look down on "authors" that only use ghostwriters. Why do tech workers act shock that people hate this junk being force fed to them that they are now resorting to violence to reject said junk? You think telling humans with specialized crafts that they don't matter is good politics? Good grief.

Of course.

I'm not surprised at all that devs are upset.

>You think telling humans with specialized crafts that they don't matter is good politics? Good grief.

Yeah, of course not. There are lot's of historical examples of this. That being said, those historical examples don't play out well for the craftsmen, either.

Look, I'm a SWE myself. I see my job drastically changing right in front of my eyes. I know there's nuance to it, too, that's hard to articulate in these comment threads.

But I think a lot of people here are biased against thinking that they are irreplaceable - I've definitely been in that camp. I don't think that it's wise, however.

Post reply on HN