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

A staff engineer's journey with Claude Code

sanity.io

Post reply on HN
Print view View original

331–340 of 410 posts

Re: A staff engineer's journey with Claude Code

#331

Post by lordgrenville »

spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

Yes! Reminds me of one of my all-time favourite HN comments https://news.ycombinator.com/item?id=23003595

Re: A staff engineer's journey with Claude Code

#332

Post by adastral »

rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

PostgresTV livestreams "vibe coding" 1h sessions implementing small PostgreSQL features with Cursor (mostly claude-4-sonnet model) every week, by experienced PostgreSQL contributors. [0] is their latest stream.

I personally have not watched much, but it sounds just like what you are looking for!

[0] https://www.youtube.com/watch?v=3MleDtXZUlM

Re: A staff engineer's journey with Claude Code

#333

Post by enobrev »

fourthark wrote: post #234
enobrev wrote: post #178

Earlier quoted context omitted.

> it doesn't seem to be making me any more efficient That's been my experience. I've been working on a 100% vibe-coded app for a few weeks. API, React-Native frontend, marketing website, CMS, CI/CD - all of it without changing a single line of code myself. Overall, the resulting codebase has been better than I expected before I started. But I would have accomplished everything it has (except for the detailed specs, d…

How long would it have taken if you had written “the detailed specs, detailed commit log, and thousands of tests”?

The specs would not likely have happened at all, since this is a solo project; although this experience has led me to want to write these things out more thoroughly, even for myself. It's impressive how little work I need to put in going this route to have fairly thorough actionable specs for pretty much every major decision I've made through the process.

The commits - some would be detailed, plenty would have been "typo" or "same as last commit, but works this time"

The tests - Probably would have been decent for the API, but not as thorough. Likely non-existent for the UI.

As for time - I agree with the other response - I wouldn't have taken the time.

Re: A staff engineer's journey with Claude Code

#334

Post by icdtea »

coldpie wrote: post #319
chamomeal wrote: post #299

Earlier quoted context omitted.

Yeah every time I see one of these articles posted on HN I know I'll see a bunch of comments like "well here's how I use claude code: I keep it on a tight leash and have short feedback loops, so that I'm still the driver, and have markdown files that explain the style I'm going for...". Which is fine lol but I'm tired of seeing the exact same conversations. It's exhausting to hear about AI all the time but it's fun t…

I'm thiiiis close to writing a Firefox extension that auto-hides any HN headline with an LLM/AI-related keyword in the title, just so I can find something interesting on here again.

You can do this with a custom filter list in Ublock Origin, no custom extension necessary.

Re: A staff engineer's journey with Claude Code

#335

Post by WorldMaker »

theshrike79 wrote: post #316
spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

> - The code that is written by LLMs always needs to be heavily monitored for correctness, style, and design, and then typically edited down, often to at least half its original size For this language matters a lot, if whatever you're using has robust tools for linting and style checks, it makes the LLMs job a lot easier. Give it a rule (or a forced hook) to always run tests and linters before claiming a job is done…

If you force the LLM to solve every test failure this also can lead to the same breakdown models as very junior developers coding to the tests rather than the problems, I've seen all of:

1) I broke the tests, guess I should delete them.

2) I broke the tests, guess the code I wrote was wrong, guess I should delete all of that code I wrote.

3) I broke the tests, guess I should keep adding more code and scaffolding. Another abstraction layer might work? What if I just add skeleton code randomly, does this add random code whack-a-mole work?

That last one can be particularly "fun" because already verbose LLM code skyrockets into baroque million line PRs when left truly unsupervised, and that PR still won't build or pass tests.

There's no true understanding by an LLM. Forcing it to lint/build can be important/useful, but still not a cure-all, and leads to such fun even more degenerate cases than hand-holding it.

Re: A staff engineer's journey with Claude Code

#336

Post by automatic6131 »

spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

>- LLMs utility is high enough that it is now going to be a standard tool in the toolbox of every software engineer, but it is definitely not replacing anyone at current capability.

Right! Problem, billions of dollars have been poured into this wrt to infrastructure, datacenters, compute and salaries. LLMs need to be at the level of replacing vast swathes of us to be worth it. LLMs are not going to be doing that.

This is a collosal malinvestment.

Re: A staff engineer's journey with Claude Code

#337

Post by coldpie »

icdtea wrote: post #334
coldpie wrote: post #319

Earlier quoted context omitted.

I'm thiiiis close to writing a Firefox extension that auto-hides any HN headline with an LLM/AI-related keyword in the title, just so I can find something interesting on here again.

You can do this with a custom filter list in Ublock Origin, no custom extension necessary.

I'm thinking something that would actually use HN's "Hide" feature, so other stories will populate the page after the AI ones are hidden. Is that something uBO could do?

Re: A staff engineer's journey with Claude Code

#338

Post by dysoco »

coldpie wrote: post #319
chamomeal wrote: post #299

Earlier quoted context omitted.

Yeah every time I see one of these articles posted on HN I know I'll see a bunch of comments like "well here's how I use claude code: I keep it on a tight leash and have short feedback loops, so that I'm still the driver, and have markdown files that explain the style I'm going for...". Which is fine lol but I'm tired of seeing the exact same conversations. It's exhausting to hear about AI all the time but it's fun t…

I'm thiiiis close to writing a Firefox extension that auto-hides any HN headline with an LLM/AI-related keyword in the title, just so I can find something interesting on here again.

I appreciate HN staying simple but a tag system like lobsters has would be pretty nice...

Re: A staff engineer's journey with Claude Code

#339

Post by ffsm8 »

MGriisser wrote: post #305
mattmanser wrote: post #268

Earlier quoted context omitted.

I don't believe it's to do with the requirements. I think you'll still hit the same problems if those greenfield projects grow. It's still fundamentally about the code. I think you're missing the difference between a 10/100k+ lines of code professional software vs a quick 3k lines greenfield project. In a few thousand lines of code you can get away with a massive amount of code bloat, quick hacks and inconsistent API…

I personally find Claude Code has no real issues working and producing code in the 40k LoC Ruby on Rails repo I work in nor in the 45k LoC Elixir/Phoenix repo I work in. For the last few months I'd say 99% of all changes I do to both are purely via Claude Code, I almost never use my editor anymore at all. It's common things don't work on the first try or aren't exactly what I want but usually just giving an error to…

Totally of topic, but the other day I was considering trying out elixir for a mainly vibe coded project, mainly because i thought the way you can structure code in it should be pretty much optimal for LLM driven development.

I haven't tried it yet, but I thought elixirs easily implementable static analysis of code could make enforcement whenever the LLM goes off rails highly useful, and an umbrella architecture would make modularity well established.

Modules could all define their own contexts via nested CLAUDE.md and subagents could be used to give it explicit implementation details.

Did you try something like that before MGriisser? (successfully or not?)

Re: A staff engineer's journey with Claude Code

#340

Post by utyop22 »

automatic6131 wrote: post #336
spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

>- LLMs utility is high enough that it is now going to be a standard tool in the toolbox of every software engineer, but it is definitely not replacing anyone at current capability. Right! Problem, billions of dollars have been poured into this wrt to infrastructure, datacenters, compute and salaries. LLMs need to be at the level of replacing vast swathes of us to be worth it. LLMs are not going to be doing that. Thi…

Yeah eventually reality and fantasy have to converge.

Nobody knows when. But it will. TBH the biggest danger is that all the hopes and dreams aren't materialised and the appetite for high-risk investments dissipates.

We've had this period in which you can be money losing and its OK. But I believe we have passed the peak on that - and this is destined to blow up.

Post reply on HN