Claude Code: Best practices for agentic coding • Hacker News Board

Re: Claude Code: Best practices for agentic coding

#131

Post by troupo » Sat, Apr 19, 2025, 8:51 PM UTC

winrid wrote: post #108

chewz wrote: post #102

Earlier quoted context omitted.

My attempt is - Do not use Claude Code at all, it is terrible tool. It is bad at almost everything starting with making simple edits to files. And most of all Claude Code is overeager to start messing with your code and run unnecessary $$ instead of making sensible plan. This isn't problem with Claude Sonnet - it is fundamnetal problem with Claude Code.

I pretty much one shot a scraper from an old Joomla site with 200+ articles to a new WP site, including all users and assets, and converting all the PDFs to articles. It cost me like $3 in tokens.

was it a wget call feeding into html2pdf?

Re: Claude Code: Best practices for agentic coding

#132

Post by troupo » Sat, Apr 19, 2025, 8:52 PM UTC

oxidant wrote: post #104

bugglebeetle wrote: post #37

Earlier quoted context omitted.

If I have to spend this much time thinking about any of this, congratulations, you’ve designed a product with a terrible UI.

Think about what you would do in an unfamiliar project with no context and the ticket "please fix the authorization bug in /api/users/:id". You'd start by grepping the code base and trying to understand it. Compare that to, "fix the permission in src/controllers/users.ts in the function `getById`. We need to check the user in the JWT is the same user that is being requested"

So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as.

Re: Claude Code: Best practices for agentic coding

#133

Post by tylersmith » Sat, Apr 19, 2025, 8:54 PM UTC

owebmaster wrote: post #118

bugglebeetle wrote: post #27

Claude Code works fairly well, but Anthropic has lost the plot on the state of market competition. OpenAI tried to buy Cursor and now Windsurf because they know they need to win market share, Gemini 2.5 pro is better at coding than their Sonnet models, has huge context and runs on their TPU stack, but somehow Anthropic is expecting people to pay $200 in API costs per functional PR costs to vibe code. Ok.

> but somehow Anthropic is expecting people to pay $200 in API costs per functional PR costs to vibe code. Ok. Reading the thread, somehow people are paying. It is mindblowing how in place of getting cheaper, development just got more expensive for businesses.

$200 per PR is significantly cheaper development than businesses are paying.

Re: Claude Code: Best practices for agentic coding

#134

Post by xpe » Sat, Apr 19, 2025, 9:05 PM UTC

datavirtue wrote: post #91

jasonjmcghee wrote: post #32

Surprised that "controlling cost" isn't a section in this post. Here's my attempt. --- If you get a hang of controlling costs, it's much cheaper. If you're exhausting the context window, I would not be surprised if you're seeing high cost. Be aware of the "cache". Tell it to read specific files (and only those!), if you don't, it'll read unnecessary files, or repeatedly read sections of files or even search through f…

GitHub copilot follows your context perfectly. I don't have to tell it anything about files. I tried this initially and it just screwed up the results.

> GitHub copilot follows your context perfectly. I don't have to tell it anything about files. I tried this initially and it just screwed up the results.

Just to make sure we're on the same page. There are two things in play. First, a language model's ability to know what file you are referring to. Second, an assistant's ability to make sure the right file is in the context window. In your experience, how does Claude Code compare to Copilot w.r.t (1) and (2)?

Re: Claude Code: Best practices for agentic coding

#135

Post by fallinditch » Sat, Apr 19, 2025, 9:09 PM UTC

I'm wondering how much of the techniques described in this blog post can be used in an IDE like Windsurf or Cursor with Claude Sonnet?

My 2 cents on value for money and effectiveness of Claude vs Gemini for coding:

I've been using Windsurf, VS Code and the new Firebase Studio. The Windsurf subscription allowance for $15 per month seems adequate for reasonable every day use. I find Claude Sonnet 3.7 performs better for me than Gemini 2.5 pro experimental.

I still like VS Code and its way of doing things, you can do a lot with the standard free plan.

With Firebase Studio, my take is that it should good for building and deploying simple things that don't require much developer handholding.

Re: Claude Code: Best practices for agentic coding

#136

Post by xpe » Sat, Apr 19, 2025, 9:09 PM UTC

troupo wrote: post #132

oxidant wrote: post #104

Earlier quoted context omitted.

Think about what you would do in an unfamiliar project with no context and the ticket "please fix the authorization bug in /api/users/:id". You'd start by grepping the code base and trying to understand it. Compare that to, "fix the permission in src/controllers/users.ts in the function `getById`. We need to check the user in the JWT is the same user that is being requested"

So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as.

> So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as.

This may be a quick quip or a rant. But the things we say have a way of reinforcing how we think. So I suggest refining until what we say cuts to the core of the matter. The claim above is a false dichotomy. Let's put aside advertisements and hype. Trying to map between AI capabilities and human ones is complicated. There is high quality writing on this to be found. I recommend reading literature reviews on evals.

Re: Claude Code: Best practices for agentic coding

#137

Post by troupo » Sat, Apr 19, 2025, 9:17 PM UTC

xpe wrote: post #136

troupo wrote: post #132

Earlier quoted context omitted.

So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as.

> So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as. This may be a quick quip or a rant. But the things we say have a way of reinforcing how we think. So I suggest refining until what we say cuts to the core of the matter. The claim above is a false dichotomy. Let's put aside advertisements and hype. Trying to map between AI capabilities and human ones…

[flagged]

Re: Claude Code: Best practices for agentic coding

#138

Post by ramoz » Sat, Apr 19, 2025, 9:18 PM UTC

sbszllr wrote: post #15

The issue with many of these tips is that they require you use to claude code (or codex cli, doesn't matter) to spend way more time in it, feed it more info, generate more outputs --> pay more money to the LLM provider. I find LLM-based tools helpful, and use them quite regularly but not 20 bucks+, let alone 100+ per month that claude code would require to be used effectively.

Interesting, I have $100 days with Claude Code. Beyond effective.

Re: Claude Code: Best practices for agentic coding

#139

Post by winrid » Sat, Apr 19, 2025, 9:20 PM UTC

troupo wrote: post #131

winrid wrote: post #108

Earlier quoted context omitted.

I pretty much one shot a scraper from an old Joomla site with 200+ articles to a new WP site, including all users and assets, and converting all the PDFs to articles. It cost me like $3 in tokens.

was it a wget call feeding into html2pdf?

no it's a few hundred lines of python to parse weird and inconsistent HTML into json files and CSV files, and then a sync script that can call the WP API to create all the authors as needed, update the articles, and migrate the images

Re: Claude Code: Best practices for agentic coding

#140

Post by darksaints » Sat, Apr 19, 2025, 9:20 PM UTC

hu3 wrote: post #130

winrid wrote: post #108

Earlier quoted context omitted.

I pretty much one shot a scraper from an old Joomla site with 200+ articles to a new WP site, including all users and assets, and converting all the PDFs to articles. It cost me like $3 in tokens.

I guess the question the is: can't VScode Copilot do the same for a fixed $20/month? It even has access to all SOTA models like Claude 3.7, Gemini 2.5 Pro and GPT o3

I would have thought so, but somehow no. I have a cursor subscription with access to all of those models, and I still consistently get better results from claude code.