How Anthropic teams use Claude Code • Hacker News Board

Re: How Anthropic teams use Claude Code

#161

Post by corytheboyd » Fri, Jul 25, 2025, 2:02 PM UTC

jasonthorsness wrote: post #12

Claude Code works well for lots of things; for example yesterday I asked it to switch weather APIs backing a weather site and it came very close to one-shotting the whole thing even though the APIs were quite different. I use it at home via the $20/m subscription and am piloting it at work via AWS Bedrock. When used with Bedrock APIs, at the end of every session it shows you the dollar amount spent which is a bit dis…

> it shows you the dollar amount spent which is a bit disconcerting

I can assure you that I don’t at all care about the MAYBE $10 charge my monster Claude Code session billed the company. They also clearly said “don’t worry about cost, just go figure out how to work with it”

Re: How Anthropic teams use Claude Code

#162

Post by LeafItAlone » Fri, Jul 25, 2025, 2:09 PM UTC

bavell wrote: post #110

maerch wrote: post #89

Earlier quoted context omitted.

> 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. Recently, I realized that this applies not only to the first 70–80% of a project but sometimes also to the final 70-80%. I couldn’t make progress with Claude on a major refactoring from scratch, so I started implementing it myself. Once I had shaped the idea clearly enou…

I need to try this - started using Claude code a few days ago and have been struggling to get good implementations with some high-complexity refactors. It keeps over engineering and creating more problems than it solves. It's getting close though, and I think your approach would work very well for this scenario!

The best way I’ve found to interact with it is to treat it like an overly eager junior developer who just read books like Gang of Four and feels the need to prove their worth as a senior. Explain that simplicity matters, or you have an existing pattern to follow, or even more specific.

As I’ve worked with a number of people like what I’ve described above, the way I’ve worked with them has helped me get better results from LLMs for coding. The difference is that you can help a junior grow over time. LLMs forget after that context (Claude.md helps, but not perfect).

Re: How Anthropic teams use Claude Code

#163

Post by nextworddev » Fri, Jul 25, 2025, 2:09 PM UTC

theshrike79 wrote: post #130

throwawayoldie wrote: post #47

Earlier quoted context omitted.

Because at some point, Anthropic needs to stop hemorrhaging money and actually make some.

And when Anthropic raises the prices enough, people will jump ship. That's why you don't pay the yearly license for anything at this point in time. Pay monthly and evaluate before each bill if there's something better out already.

and that jumping ship didn't happen IRL, cursor ARR jumped 50% after their pricing change.

Re: How Anthropic teams use Claude Code

#164

Post by corytheboyd » Fri, Jul 25, 2025, 2:12 PM UTC

syntaxbush wrote: post #45

I found if you are tightly in the loop, keep the code highly modular, and are developing new functionality alongside tests, Claude works much better.

Yeah me too, keeping the code modular being a huge part of it. In the same vein is actually finishing feature flags and removing the old code, killing off truly dead code, tests, documentation… basically eliminate as much noise as you can, so that it reads as much exemplary code as possible.

Re: How Anthropic teams use Claude Code

#165

Post by adregan » Fri, Jul 25, 2025, 2:14 PM UTC

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’ve seen Claude code get halfway through a small sized refactor (function parameters changed shape or something like that), say something that looks like frustration at the amount of time it’s taking, revert all of the good changes, and start writing a bash script to automate the whole process.

In that case, you have put a stop to it and point out that it would already be done if it hadn’t decided to blow it all up in an effort to write a one time use codemod. Of course it agrees with that point as it agrees with everything. It’s the epitome of strong opinions loosely held.

Re: How Anthropic teams use Claude Code

#166

Post by stillsut » Fri, Jul 25, 2025, 2:16 PM UTC

forgotmypw17 wrote: post #138

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…

Great advice, matches up to my experience. Personally I go a little cheaper and dirtier on the first prompt, then revise as needed. By the way what classes / workshops did you teach?

I've written a little about some my findings and workflow in detail here: https://github.com/sutt/agro/blob/master/docs/case-studies/a...

Re: How Anthropic teams use Claude Code

#167

Post by corytheboyd » Fri, Jul 25, 2025, 2:17 PM UTC

dzikibaz wrote: post #101

Why is everyone so careless about letting Claude Desktop upload their source code and/or private data to its servers? Or maybe I'm too paranoid for caring about where data go.

Because my employer tells me it’s fine so long as we’re using it with AWS Bedrock. Do I believe that Amazon then wouldn’t be siphoning all this as model training data? It’s a fun conspiracy…

Re: How Anthropic teams use Claude Code

#168

Post by stillsut » Fri, Jul 25, 2025, 2:21 PM UTC

a_bonobo wrote: post #121

godelski wrote: post #76

Earlier quoted context omitted.

Unironically this can actually be a good idea. Instead of "rerunning," run in parallel. Then pick the best solution. Pros: - Saved Time! - Scalable! - Big Bill? Cons: - Big Bill - AI written code

This repo has a pattern where the in parallel jobs have different personalities: https://github.com/tokenbender/agent-guides/blob/main/claude...

Interesting, this repo (which I'm building) is doing the same but instead of just different personalities, I'm giving each agent a different CLI-agents (aider w/ Gemini, claude code, gemini cli, etc). I've got some writeups on here: https://github.com/sutt/agro/blob/master/docs/case-studies/a...

Re: How Anthropic teams use Claude Code

#169

Post by LeafItAlone » Fri, Jul 25, 2025, 2:24 PM UTC

maxnevermind wrote: post #107

chubot wrote: post #6

I use Claude and like it, but this post has kind of a clunky and stilted style So I guess the blog team also uses Claude

Also started to suspect that, but I have a bigger problem with the content than styling: > "Instead of remembering complex Kubernetes commands, they ask Claude for the correct syntax, like "how to get all pods or deployment status," and receive the exact commands needed for their infrastructure work." Duh, you can ask LLM tech questions and stuff. What is the point of putting something like that on the tech blog of t…

To get more people using it, and more. I’ve encountered people who don’t use it because they think that it isn’t something that will help them, even in tech. Showing how different groups find value in it might get people in those same positions using it.

Even with people who do use it, they might thinking about it narrowly. They use it for code generation, but might not think to use it for simplified man pages.

Of course there are people who are the exact opposite and use it for every last thing they do. And maybe from this they learn how to better approach their prompts.

Re: How Anthropic teams use Claude Code

#170

Post by lumost » Fri, Jul 25, 2025, 2:25 PM UTC

whatever1 wrote: post #41

lumost wrote: post #15

Earlier quoted context omitted.

once upon a time - engineers often had to concern themselves with datacenter bills, cloud bills, and eventually SaaS bills. We'll probably have 5-10 years of being concerned about AI bills before the AI expense is trivial compared to the human time.

This guy has not been hit with a 100k/mo cloudwatch bill

I’ve managed a few 8 figure infrastructure bills. The exponential decrease in hardware costs combined with the exponential growth in software engineer salaries has meant that these bills become inconsequential in the long run. I was at one unicorn which had to spend 10% of Cost of Goods Sold on cloud. Today their biggest costs could run on a modest Postgres cluster in the cloud thanks to progressively better hardware.

100k/mo on cloud watch corresponds to a moderately large software business assuming basic best practices are followed. Optimization projects can often run into major cost overruns where the people time exceeds the discounted future free cash flow savings from the optimization.

That being said, a team of 5 on a small revenue/infra spend racking up 100k/mo is excessive. Pedantically, cloud watch/datadog are SaaS vendors - 100k/mo on Prometheus would correspond to a 20 node SSD cluster in the cloud which could easily handle several 10s of millions of metrics per second from 10s of thousands of metric producers. If you went to raw colocation facility costs - you’d have over a hundred dual Xeon machines with multi-TB direct attached SSD. Supporting hundreds of thousands of servers producing hundreds of millions of data points per second.

Human time is really the main trade-off.