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

Claude Code: Best practices for agentic coding

anthropic.com

Post reply on HN
Print view View original

241–250 of 268 posts

Re: Claude Code: Best practices for agentic coding

#241

Post by solatic »

istjohn wrote: post #80
zoogeny wrote: post #29

So I have been using Cursor a lot more in a vibe code way lately and I have been coming across what a lot of people report: sometimes the model will rewrite perfectly working code that I didn't ask it to touch and break it. In most cases, it is because I am asking the model to do too much at once. Which is fine, I am learning the right level of abstraction/instruction where the model is effective consistently. But wh…

Why do you think it's supposed to be cheap? Developers are expensive. Claude doesn't have to be cheap to make software development quicker and cheaper. It just has to be cheaper than you. There are ways to use LLMs cheaply, but it will always be expensive to get the most out of them. In fact, the top end will only get more and more costly as the lengths of tasks AIs can successfully complete grows.

> It just has to be cheaper than you

There's an ocean of B2B SaaS services that would save customers money compared to building poor imitations in-house. Despite the Joel Test (almost 25 years old! craxy...) asking whether you buy your developers the best tools that money can buy, because they're almost invariably cheaper than developer salaries, the fact remains that most companies treat salaries as a fixed cost and everything else threatens the limited budget they have.

Anybody who has ever tried to sell developer tooling knows, you're competing with free/open-source solutions, and it aint a fair fight.

Re: Claude Code: Best practices for agentic coding

#242

Post by bombela »

Aurornis wrote: post #176
pyfon wrote: post #168

Earlier quoted context omitted.

Weird code to have in a modern AI system! Also 14 string scans seems a little inefficient!

14 checks through a string is entirely negligible relative to the amount of compute happening. Like a drop of water in the ocean.

Everybody says this all the time. But it compounds. And then our computers struggle with what should be basic websites.

Re: Claude Code: Best practices for agentic coding

#243

Post by highfrequency »

Terretta wrote: post #236
bob1029 wrote: post #210

I've developed a new mental model of the LLM codebase automation solutions. These are effectively identical to outsourcing your product to someone like Infosys. From an information theory perspective, you need to communicate approximately the same amount of things in either case. Tweaking claude.md files until the desired result is achieved is similar to a back and forth email chain with the contractor. The differenc…

We, mere humans, communicate our needs poorly, and undervisualize until we see concrete results. This is the state of us. Faced with us as a client, the LLM has infinite patience at linear but marginal cost (relative to your thinking/design time cost, and the value of instant iteration as you realize what you meant to picture and say). With offshoring, telling them they're getting it wrong is not just horrifically sl…

Intriguing perspective! Could you elaborate on this with another paragraph or two?

> We humans undervisualize until we see concrete results.

Re: Claude Code: Best practices for agentic coding

#244

Post by Terretta »

highfrequency wrote: post #243
Terretta wrote: post #236

Earlier quoted context omitted.

We, mere humans, communicate our needs poorly, and undervisualize until we see concrete results. This is the state of us. Faced with us as a client, the LLM has infinite patience at linear but marginal cost (relative to your thinking/design time cost, and the value of instant iteration as you realize what you meant to picture and say). With offshoring, telling them they're getting it wrong is not just horrifically sl…

Intriguing perspective! Could you elaborate on this with another paragraph or two? > We humans undervisualize until we see concrete results.

> > We humans undervisualize until we see concrete results.

> Could you elaborate on this with another paragraph or two?

Volunteer as a client-facing PdM at a digital agency for a week*, you'll be able to elaborate with a book.

* Well, long enough to try to iterate a client instruction based deliverable.

Re: Claude Code: Best practices for agentic coding

#245

Post by lazzlazzlazz »

charlie0 wrote: post #226
kiratp wrote: post #99

Earlier quoted context omitted.

The productivity boost can be so massive that this amount of fiddling to control costs is counterproductive. Developers tend to seriously underestimate the opportunity cost of their own time. Hint - it’s many multiples of your total compensation broken down to 40 hour work weeks.

If this is true, why isn't our compensation scaling with the increases in productivity?

It usually does, just with a time delay and a strict condition that the firm you work at can actually commercialize your productivity. Apply your systems thinking skills to compensation and it will all make sense.

Re: Claude Code: Best practices for agentic coding

#247

Post by hu3 »

whywhywhywhy wrote: post #207
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.

On a shorter timeline than you'd think none of working with these tools will look like this. You'll be prompting and evaluating and iterating entirely finished pieces of software and be able to see multiple attempts at each solve at once, none of this deep in the weeds fixing a bug stuff. We're rapidly approaching a world where a lot of software will be being made without an engineer hire at all, maybe not the hardes…

my current estimate is 2030. because we can barely get a JS/TS application to compile after a year of dependency updates.

our current popular stack is quicksand.

unless we're talking about .net core, java, Django and more of these stable platforms.

Re: Claude Code: Best practices for agentic coding

#249

Post by zomglings »

Wowfunhappy wrote: post #233
zomglings wrote: post #230

Earlier quoted context omitted.

Apologies for the late reply. My kids demanded my attention yesterday. It doesn't seem to have included any points on style or workflow in the context. Most of my context documents end up including the following information: 1. I want the agent to treat git commits as checkpoints so that we can revert really silly changes it makes. 2. I want it to keep on running build/tests on the code to be sure it isn't just going…

But none of this is really Claude Code's internal context, right? It's a summary. I could see using it as an alternative to /compact but not to undo a /clear. Whatever the internal state is of Claude Code, it's lost as soon as you /clear or close the Terminal window. You can't even experiment with a different prompt and then--if you don't like the prompt--go back to the original conversation, because pressing esc to…

Yes, this is true. It's a summary, and cannot really undo a /clear. It is just a directed, cheaper /compact.

Re: Claude Code: Best practices for agentic coding

#250

Post by cadamsdotcom »

joshstrange wrote: post #2

The most interesting part of this article for me was: > Have multiple checkouts of your repo I don’t know why this never occurred to me probably because it feels wrong to have multiple checkouts, but it makes sense so that you can keep each AI instance running at full speed. While LLM‘s are fast, this is one of the annoying parts of just waiting for an instance of Aider or Claude Code to finish something. Also, I had…

You might want to consider Claude Squad, https://github.com/smtg-ai/claude-squad which manages all the worktrees for you.

Disclaimer, I haven’t tried it personally - if you do, let us know how you go!

Post reply on HN