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

211–220 of 268 posts

Re: Claude Code: Best practices for agentic coding

#211

Post by cpursley »

UltraSane wrote: post #179
cpursley wrote: post #94

Earlier quoted context omitted.

Do you understand all of the code in the libraries that your applications depend on? Or your coworker for that matter? All of the gate keeping around llm code tools are amusing. But whatever, I’m shipping 10x and making money doing it.

Up until recently I could be sure they were written by a human. But if you are making money by using LLMs to write code then all power to you. I just despair at the idea of trillions of lines of LLM generated code.

Well, you can’t just vibe code something useful into existence despite all the marketing. You have to be very intentional about which libraries it can use, code style etc. Make sure it has the proper specifications and context. And review the code, of course.

Re: Claude Code: Best practices for agentic coding

#212

Post by KronisLV »

winrid wrote: post #143
hu3 wrote: post #130

Earlier quoted context omitted.

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 haven't tried copilot. Mostly because I don't use VSCode, I use jetbrains ides. How do they provide Claude 3.7 for $20/mo with unlimited usage?

Copilot has a pretty good plugin for JetBrains IDEs!

Though their own AI Assistant and Junie might be equally good choices there too.

Re: Claude Code: Best practices for agentic coding

#213

Post by imafish »

vessenes wrote: post #196
Wowfunhappy wrote: post #120

Earlier quoted context omitted.

> 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. I don't find this particularly problematic because I can quickly see the unnecessary changes in git and revert them. Like, I guess it would be nice if I didn't have to do that, but compared to t…

i think this is particularly claude 3.7 behavior - at least in my experience, it's ... eager. overeager. smarter than 3."6" but still, it has little chill. gemini is better; o3 better yet. I'm mostly off claude as a daily driver coding assistant, but it had a really long run - longest so far.

I get the same with gemini, though. o3 is kind of the opposite, under-eager. I cannot really decide on my favorite. So I switch back and forth :)

Re: Claude Code: Best practices for agentic coding

#215

Post by stepbeek »

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…

This matches well with my experience so far. It’s why the chat interface has remained my preference over autocomplete in an IDE.

Re: Claude Code: Best practices for agentic coding

#216

Post by rpastuszak »

dist-epoch wrote: post #21
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.

> let alone 100+ per month that claude code would require I find this argument very bizarre. $100 is pay for 1-2 hours of developer time. Doesn't it save at least that much time in a whole month?

So sad that people are happy to spend 100$ pd on a tool like this, and we're so unlikely (in general) to pay $5 to an author of an article/blog posts that possibly saved you the same amount of time.

(I'm not judging a specific person here, this is more of a broad commentary regarding our relationship/sense of responsibility/entitlement/lack of empathy when it comes to supporting other people's work when it helps us)

Re: Claude Code: Best practices for agentic coding

#217

Post by nulld3v »

simonw wrote: post #149

The "ultrathink" thing is pretty funny: > We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" I had a poke around and it's not a feature of the Claude model, it's specific to Claude Code. There's a "megathi…

Waiting until I can tell it to use "galaxy brain".

Re: Claude Code: Best practices for agentic coding

#218

Post by ljm »

4b11b4 wrote: post #166
orojackson wrote: post #152

Earlier quoted context omitted.

Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.

At this point should we get our first knob/slider on a language model... THINK ..as if we're operating this machine as analog synth

Maybe a Turbo Think button that toggles between Ultrathink and Megathink.

Re: Claude Code: Best practices for agentic coding

#220

Post by ixaxaar »

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…

> These are effectively identical to outsourcing your product to someone like Infosys.

But in my experience, the user has to be better than an Infosys employee to know how to convey the task to the LLM and then verify iteratively.

So more like an experienced engg outsourcing work to a service company engg.

Post reply on HN