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

How Anthropic teams use Claude Code

anthropic.com

Post reply on HN
Print view View original

131–140 of 248 posts

Re: How Anthropic teams use Claude Code

#131

Post by theshrike79 »

zuInnp wrote: post #115

I prefer to use Claude code like a smart rubber ducky while I write most the code in the end. I added rules to make claude first explain what it want to do in chat (and code changes should only be implemented if I ask for it). I like it to talk about ideas, discuss solutions and approaches. But I am in control of it - in the end, I am the person repsonsible for the code. Since I don't like it to automatically do chan…

Just keep it in plan mode and it won't change anything?

Unlike Gemini CLI which will just rush into implementation without hesitation :D

Re: How Anthropic teams use Claude Code

#132

Post by theshrike79 »

mfrye0 wrote: post #62

My optimization hack is that I'm using speech recognition now with Claude Code. I can just talk to it like a person and explain the full context / history of things. Way faster than typing it all out.

So you sit in a room, talking to it? Doesn't it feel weird?

I type a lot faster than I speak :D

Re: How Anthropic teams use Claude Code

#133

Post by theshrike79 »

baby wrote: post #68
amacneil wrote: post #67

It’s a funny post because our team wanted to use Claude Code, but the team plan of Claude doesn’t include Claude Code (unlike the pro plan at a similar price point). Found this out after we purchased it :( We’re not going to ask every engineer to purchase it separately. Maybe before boasting about how your internal teams use your product, add an option for external companies to pay for it! Industry leading AI models…

Why not ask them to purchase it separately?

It's a billing nightmare pretty much.

The only reason why "team" plans exist is to have centralised billing and licensing.

Re: How Anthropic teams use Claude Code

#134

Post by moomoo11 »

ktzar wrote: post #77
onprema wrote: post #72

> When Kubernetes clusters went down and weren't scheduling new pods, the team used Claude Code to diagnose the issue. They fed screenshots of dashboards into Claude Code, which guided them through Google Cloud's UI menu by menu until they found a warning indicating pod IP address exhaustion. Claude Code then provided the exact commands to create a new IP pool and add it to the cluster, bypassing the need to involve…

They're subsidizing a world where we need ai instead of understanding or, at the very least, knowing who can help us. Eventually for us to be so dumb we are the ai slaves.

Not really.

Is it really value add to my life that I know some detail on page A or have some API memorized?

I’d rather we be putting smart people in charge of using AI to build out great products.

It should make things 10000x more competitive. I’m for one excited AF for what the future holds.

If people want to be purists and pat themselves on the back sure. I mean people have hobbies like arts.

Re: How Anthropic teams use Claude Code

#135

Post by victorbjorklund »

Fade_Dance wrote: post #61
ants_everywhere wrote: post #4

I've been trying Claude Code for a few weeks after using Gemini Cli. There's something a little better the tool use loop, which is nice. But Claude seems a little dumber and is aggressive about "getting things done", often ignoring common sense or explicit instructions or design information. If I tell it to make a test pass, it will sometimes change my database structure to avoid having to debug the test. At least tw…

I even heard that it will aggressively delete your codebase and then lie about it. To your face.

You are using version control so what is the issue?

Re: How Anthropic teams use Claude Code

#136

Post by bdangubic »

tough wrote: post #16
bdangubic wrote: post #11

Earlier quoted context omitted.

That's easy to say when the employee is not personally paying the massive amount of compute running Claude Code for a half-hour. you can do the same for $200/month

it has limits too, it lasted like 1-2 weeks without only (for me personally at least)

with all dues respect you really need to learn the tools you are using which includes any usage limits (which are temporal). I run CC in 4 to 8 terminals my entire workday, every workday…

Re: How Anthropic teams use Claude Code

#137

Post by otabdeveloper4 »

moomoo11 wrote: post #134
ktzar wrote: post #77

Earlier quoted context omitted.

They're subsidizing a world where we need ai instead of understanding or, at the very least, knowing who can help us. Eventually for us to be so dumb we are the ai slaves.

Not really. Is it really value add to my life that I know some detail on page A or have some API memorized? I’d rather we be putting smart people in charge of using AI to build out great products. It should make things 10000x more competitive. I’m for one excited AF for what the future holds. If people want to be purists and pat themselves on the back sure. I mean people have hobbies like arts.

> for what the future holds

AI mostly provides negative efficiency gains.

This will not change in the future.

Re: How Anthropic teams use Claude Code

#138

Post by forgotmypw17 »

I’ve implemented and maintained an entire web app with CC, and also used many other tools (and took classes and taught workshops on using AI coding tools).

The most effective way I’ve found to use CC so far is this workflow:

Have a detailed and also compressed spec in an md file. It can be called anything, because you’re going to reference it explicitly in every prompt. (CC usually forgets about CLAUDE.md ime)

Start with the user story, and ask it to write a high-level staged implementation plan with atomic steps. Review this plan and have CC rewrite as necessary. (Another md file results.)

Then, based on this file, ask it to write a detailed implementation plan, also with atomic stages. Then review it together and ask if it’s ready to implement.

Then tell Claude to go ahead and implement it on a branch.

Remember the automated tests and functional testing.

Then merge.

Re: How Anthropic teams use Claude Code

#139

Post by FeepingCreature »

minimaxir wrote: post #7

A repeated trend is that Claude Code only gets 70-80% of the way, which is fine and something I wish was emphasized more by people pushing agents. This bullet point is funny: > Treat it like a slot machine > Save your state before letting Claude work, let it run for 30 minutes, then either accept the result or start fresh rather than trying to wrestle with corrections. Starting over often has a higher success rate th…

Yeah my most common aider command sequence is

    > /undo
    > /clear
    > ↑ ↑ ↑ ⏎

Re: How Anthropic teams use Claude Code

#140

Post by Fade_Dance »

victorbjorklund wrote: post #135
Fade_Dance wrote: post #61

Earlier quoted context omitted.

I even heard that it will aggressively delete your codebase and then lie about it. To your face.

You are using version control so what is the issue?

(exactly. It's a sarcastic reference to this story that was going around: https://news.ycombinator.com/item?id=44632575)
Post reply on HN