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

6 weeks of Claude Code

blog.puzzmo.com

Post reply on HN
Print view View original

511–520 of 603 posts

Re: 6 weeks of Claude Code

#511

Post by wredcoll »

nosianu wrote: post #419
wredcoll wrote: post #176

Earlier quoted context omitted.

There's very few objective ways to measure review 'performance'. Coding is easy, it works or doesn't.

This ignores a bunch of higher level and long-term concepts like maintenance, complexity and extensibility. With only "it works" you end up like this (iconic HN comment on Oracle codebase): https://news.ycombinator.com/item?id=18442637

Yes, my point is that you don't even have "it compiles" as a way to measure a code review. Maybe you did a great job, maybe you did a terrible job, how do you tell?

Re: 6 weeks of Claude Code

#512

Post by azinman2 »

benreesman wrote: post #446
vaidhy wrote: post #433

Earlier quoted context omitted.

You know senior developers can also be off-shored, right?

Blowing away the junior -> senior pipeline would, on average, hit every country the same. Though it raises an interesting point: if a country like India or China did make the investment in hiring, paying, and mentoring junior people but e.g. the US didn't, then you could see a massive shift in the global center of gravity around software expertise in 10 years (plus or minus). Someone is going to be the best at planni…

This is such an important point. Not sure about India, which is still very market forces driven, but china can just force its employers to do whatever is of strategic importance. That’s long gone in the US. Market forces here will only ever optimize for short term game, shooting ourselves in the chest.

Re: 6 weeks of Claude Code

#513

Post by pmg101 »

ChuckMcM wrote: post #500
pmg101 wrote: post #398

Earlier quoted context omitted.

It already was the case wasn't it, that you could either get one senior dev to build your thing in a week, or give them a team of juniors and it would take the whole team 4 weeks and be worse. Yet somehow companies continued to opt for the second approach. Something to do with status from headcount?

Yes, there are companies that opt for broken organizations for a variety of reasons. The observation though is this; Does this lead to a world where the 'minimum' programmer is what we consider today to be a 'Senior Dev' ? It echoes the transition of machinists to operators of CAD/CAM workstations to operate machining centers, rather than hands on the dials of a mill or lathe. It certainly seems like it might make en…

It'll be interesting to see if in a decade when a whole cohort of juniors didn't get trained whether LLMs will be able to do the whole job. I'm guessing a lot of companies are willing to bet on yes.

Re: 6 weeks of Claude Code

#514

Post by js2 »

fireflash38 wrote: post #439
js2 wrote: post #313

Earlier quoted context omitted.

I've also found it good at catching mistakes and helping write commit messages. "Review the top-most commit. Did I make any mistakes? Did I leave anything out of the commit message?" Sometimes I let it write the message for me: "Write a new commit message for the current commit." I've had to tell it how to write commit messages though. It likes to offer subjective opinions, use superlatives and guess at why something…

This is insane to me. Review your own code. Understand why you made the changes. And then clearly describe why you made them. If you can't do that yourself, I think that's a huge gap in your own skills. Making something else do it means you don't internalize the changes that you made.

Your comment is not a fair interpretation of what I wrote.

For the record, I write better and more detailed commit messages than almost anyone I know across a decades[^0] long career[^1,^2,^3,^4,^5]. But I'm not immune from making mistakes, and everyone can use an editor, or just runs out of mental energy. Unfortunately, I find it hard to get decent PR reviews from my colleagues at work.

So yeah, I've started using Claude Code to help review my own commits. That doesn't mean I don't understand my changes or that I don't know why I made them. And CC is good at banging out a first draft of a commit message. It's also good at catching tiny logic errors that slip through tests and human review. Surprisingly good. You should try it.

I have plenty of criticisms for CC too. I'm not sure it's actually saving me any time. I've spent the last two weeks working 10 hour days with it. For some things it shines. For other things, I would've been better off writing the code from scratch myself, something I've had to do maybe 40% of the time now.

[^0]: https://seclists.org/bugtraq/1998/Jul/172

[^1]: https://github.com/git/git/commit/441adf0ccf571a9fe15658fdfc...

[^2]: https://github.com/git/git/commit/cacfc09ba82bfc6b0e1c047247...

[^3]: https://github.com/fastlane/fastlane/pull/21644

[^4]: https://github.com/CocoaPods/Core/pull/741

[^5]: None of the these are my best examples, just the ones I found quickly. Most of my commit messages are obviously locked away by my employer. Somewhere in the git history is a paragraphs long commit message from Jeff King (peff) explaining a one line diff. That's probably my favorite commit message of all time. But I also know that at work I've got a message somewhere explaining a single character diff.

Re: 6 weeks of Claude Code

#515

Post by laughing_snyder »

Has anyone had their own experience of how Claude or similar AI agents perform in large (1M+ lines) legacy code bases? To give a bit more context, I work on a Java code base that is 20+ years old. It was continuously updated and expanded but contains mostly spaghetti code. Would Claude add any value here?

Re: 6 weeks of Claude Code

#516

Post by nevertoolate »

brentm wrote: post #469
actinium226 wrote: post #460

I see a lot of comments here gushing about CC but I've used and I really don't get it. I find that it takes me just as long to explain to it what I need done as it takes to just do the work myself.

You need to give it something to do that you don't think it will be able to do. That is where I think it starts to click.

This is a good idea. Otoh I have mixed results, claude code easily convinces themselves to retry failed ides in a loop

Re: 6 weeks of Claude Code

#517

Post by ChuckMcM »

pmg101 wrote: post #513
ChuckMcM wrote: post #500

Earlier quoted context omitted.

Yes, there are companies that opt for broken organizations for a variety of reasons. The observation though is this; Does this lead to a world where the 'minimum' programmer is what we consider today to be a 'Senior Dev' ? It echoes the transition of machinists to operators of CAD/CAM workstations to operate machining centers, rather than hands on the dials of a mill or lathe. It certainly seems like it might make en…

It'll be interesting to see if in a decade when a whole cohort of juniors didn't get trained whether LLMs will be able to do the whole job. I'm guessing a lot of companies are willing to bet on yes.

As long as LLMs aren't the 'Cold Fusion' of this cycle, sure. :-)

Re: 6 weeks of Claude Code

#518

Post by i-m »

philbo wrote: post #362

As one of the curious minority who keeps trying agentic coding but not liking it, I've been looking for explanations why my experience differs from the mainstream. I think it might lie in this nugget: > I believe with Claude Code, we are at the > “introduction of photography” period of > programming. Painting by hand just doesn’t > have the same appeal anymore when a single > concept can just appear and you shape it…

[dead]

Re: 6 weeks of Claude Code

#519

Post by jcelerier »

exfalso wrote: post #396
Aurornis wrote: post #77

Earlier quoted context omitted.

> as a vibe coding skeptic, I was amazed. The interesting thing about all of this vibe coding skepticism, cynicism, and backlash is that many people have their expectations set extremely low. They’re convinced everything the tools produce will be junk or that the worst case examples people provide are representative of the average. Then they finally go out and use the tools and realize that they exceed their (extreme…

Hmm not my experience. I've been aggressively trying to use both Cursor and Claude Code. I've done maybe 20-30 attempts with Code at different projects, a couple of them personal small projects. All of them resulted in sub-par results, essentially unusable. I tried to use it for Python, Rust and Bash. I also tried to use it for crawling and organizing information. I also tried to use it as a debugging buddy. All of t…

I asked it to implement a C++ backend for an audio plug-in API (CLAP) for the DAW I'm developing and it got it right in maybe less than ten interactions. Implementing other plug-in APIs such as VST3 took me weeks to get to the same level of support.

Re: 6 weeks of Claude Code

#520

Post by ModernMech »

ako wrote: post #494
Archer6621 wrote: post #424

Earlier quoted context omitted.

By using AI, you learn how to use AI, not necessarily how to build architecturally sound and maintainable software, so being able to do much more in a limited amount of time will not necessarily make you a more knowledgeable programmer, or at least that knowledge will most likely only be surface-level pattern recognition. It still needs to be combined with hands-on building your own thing, to truly understand the nut…

I don't agree, to me switching from hand coded source code to ai coded source code is like going from a hand-saw to an electric-saw for your woodworking projects. In the end you still have to know woodworking, but you experiment much more, so you learn more. Or maybe it's more like going from analog photography to digital photography. Whatever it is, you get more programming done. Just like when you go from assembly…

> to me

Key words there. To you, it's a electric saw because you already know how to program, and that's the other person's point; it doesn't necessarily empower people to build software. You? Yes. Generally though when you hand the public an electric saw and say "have at it, build stuff" you end up with a lot of lost appendages.

Sadly, in this case the "lost appendages" are going to be man-decades of time spent undoing all the landmines vibecoders are going to plant around the digital commons. Which means AI even fails as a metaphorical "electric saw", because a good electric saw should strike fear into the user by promising mortal damage through misuse. AI has no such misuse deterrent, so people will freely misuse it until consequences swing back wildly, and the blast radius is community-scale.

> more like going from analog photography to digital photography. Whatever it is, you get more programming done.

By volume, the primary outcome of digital photography has been a deluge of pointless photographs to the extent we've had to invent new words to categorize them. "selfies". "sexts". "foodstagramming". Sure, AI will increase the actual programming being done, the same way digital photography gave us more photography art. But much more than that, AI will bring the equivalent of "foodstagramming" but for programs. Kind of like how the Apple App Store brought us some good apps, but at the same time 9 bajillion travel guides and flashlight apps. When you lower the bar you also open the flood gates.

Post reply on HN