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

341–350 of 410 posts

Re: A staff engineer's journey with Claude Code

#341

Post by bobbylarrybobby »

meerab wrote: post #62

I have barely written any code since my switch to Claude Code! It's the best thing since sliced bread! Here's what works for me: - Detailed claude.md containing overall information about the project. - Anytime Claude chooses a different route that's not my preferred route - ask my preference to be saved in global memory. - Detailed planning documentation for each feature - Describe high-level functionality. - As I de…

What does the playwright MCP accomplish for you? Is it basically a way for Claude to play with your app in the browser without having to write playwright tests?

Re: A staff engineer's journey with Claude Code

#342

Post by ftkftk »

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 could use an agentic AI coding tool to vibe code you one in minutes! /s

Re: A staff engineer's journey with Claude Code

#343

Post by hatefulmoron »

tempoponet wrote: post #320
theshrike79 wrote: post #317

Earlier quoted context omitted.

> Based on my set up as of today, I’d imagine by sometime next year that will be normal and then the conversation will be very different; mostly around cost control. I wouldn’t be surprised if there is a break out popular agent control flow language by next year as well. Currently it's just VC funded. The $20 packages they're selling are in no way cost-effective (for them). That's why I'm driving all available models…

Once local models are good enough there will be a $20 cloud provider that can give you more context, parameters, and t/s than you could dream of at home. This is true today with services like groq.

Groq and Cerebras definitely have the t/s, but their hardware is tremendously expensive, even compared to the standard data center GPUs. Worth keeping in mind if we're talking about a $20 subscription.

Re: A staff engineer's journey with Claude Code

#344

Post by coldpie »

ftkftk wrote: post #342
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 could use an agentic AI coding tool to vibe code you one in minutes! /s

Honestly might give that a go, yeah. Brand new, low stakes, throwaway projects are one of the few things these tools are actually genuinely pretty useful for.

Re: A staff engineer's journey with Claude Code

#345

Post by caseyohara »

dotancohen wrote: post #330
globular-toast wrote: post #302

Earlier quoted context omitted.

Hmm... my code is the spec. It just happens to be executable. Is writing a precise spec in English easier than in a programming language?

The spec contains ambiguities and the code contains bugs. Clarifying ambiguities in the spec with stakeholders, allows one to reduce bugs in the code.

If you repeat this process until all ambiguities in the spec are eliminated, aren't you essentially left with code? Or at least something that looks more like code than plain English?

Re: A staff engineer's journey with Claude Code

#346

Post by sunir »

tempoponet wrote: post #320
theshrike79 wrote: post #317

Earlier quoted context omitted.

> Based on my set up as of today, I’d imagine by sometime next year that will be normal and then the conversation will be very different; mostly around cost control. I wouldn’t be surprised if there is a break out popular agent control flow language by next year as well. Currently it's just VC funded. The $20 packages they're selling are in no way cost-effective (for them). That's why I'm driving all available models…

Once local models are good enough there will be a $20 cloud provider that can give you more context, parameters, and t/s than you could dream of at home. This is true today with services like groq.

Not exactly. Those models are based on intermittent usage. If you're using an AI engineer using a sophisticated agent flow, the usage is constant and continuous. That can price to an equivalent of a dedicated cube at home over 2 years.

I had 3 projects running today. I hit my Claude Max Pro session limits twice today in about 90 minutes. I'm now keeping it down to 1 project, and I may interrupt it until the evening when I don't need Claude Web. If I could run it passively on my laptop, I would.

Re: A staff engineer's journey with Claude Code

#347

Post by DenisM »

fhd2 wrote: post #301
rafaelmn wrote: post #294

Earlier quoted context omitted.

> but this was true when they wrote their own code with stack overflow. Searching for solutions and integrating examples found requires effort that develops into a skill. You would rarely get solutions that would just fit into the codebase from SO. If I give a task to you and you produce a correct solution on the initial review I now know I can trust you to deal with this kind of problem in the future. Especially aft…

Like with any kind of learning, without a feedback loop (as tight as possible IMHO), it's not gonna happen. And there is always some kind of feedback loop. Ultra short cycle: Pairing with a senior, solid manual and automated testing during development. Reasonably short cycle: Code review by a senior within hours and for small subsets of the work ideally, QA testing by a seperate person within hours. Borderline too lo…

LLM can also help learning f you ask it what can be done better. Seniors can make prepromt so that company customs are taken into account.

Re: A staff engineer's journey with Claude Code

#349

Post by all2 »

dotancohen wrote: post #246
all2 wrote: post #188

Earlier quoted context omitted.

> The code itself is basically disposable. I'm finding this is the case for my work as well. The spec is the secret sauce, the code (and its many drafts) are disposable. Eventually I land on something serviceable, but until I do, I will easily drop a draft and start on a new one with a spec that is a little more refined.

I just like to add that the database design is the real secret sauce, important even more than external APIs in my opinion.

This is something that I've stumbled into as well. DB models AND dataflow. Getting both of those well spec'd makes things a lot easier.

Re: A staff engineer's journey with Claude Code

#350

Post by Yoric »

dakiol wrote: post #47
Yoric wrote: post #36

Earlier quoted context omitted.

I regularly write big MRs, then cut them into 5+ (sometimes 10+) smaller MRs. What does Claude Code change here?

The split seems artificial now. Before, an average engineer would produce code sequentially, chunk after chunk. Each chunk submitted only after the previous one was reviewed and approved. Today, one could submit the whole thing for review. Also, if machines can write it, why not let machines review it too? Seems weird not to do so.

Not sure I follow. The limitation has never been about the developer being able to write a complex feature in one MR. It has always been about the other developer not being able to review a complex MR.

So far, nothing I've seen convinces me that machines can (yet) write or review code autonomously (although they can certainly be useful as assistants). Maybe some day.

Post reply on HN