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

191–200 of 248 posts

Re: How Anthropic teams use Claude Code

#191

Post by godelski »

jvanderbot wrote: post #143
aeontech wrote: post #117

Earlier quoted context omitted.

I mean... this is a deterministic task, can just run it through autoformatter? Why ask AI to do indentation of all things?

One time I explained that I was afraid of tesla full self driving, because while using it my tesla accelerated to 45mph in a parking lot that was parallel to the road and only separated by a curb. The pushback I got was "Why would you use FSD in a parking lot". Well, "Full", right? Same here. It's either capable of working unsupervised or not. And if not, you have to start wondering what you're even doing if you're a…

  > We're still working out the edge cases
The difficult part is that like with FSD, it's mostly edge cases

Re: How Anthropic teams use Claude Code

#192

Post by godelski »

thunky wrote: post #146
godelski wrote: post #123

Earlier quoted context omitted.

I've taught undergraduates and graduates how to code. I've contributed to Open Source projects. I'm a researcher and write research code with other people who write research code. You could say I've seen A LOT of poorly written human generated code. Yet, I still trust it more. Why? Well one of the big reasons is exactly what we're joking about. I can trust a human to iterate. Lack of iteration would be fine if everyt…

> Lack of iteration What makes you think that agents can't iterate? > I'm going to throw them out if they are just constantly showering me with praise and telling me how much of a genius I am You can tell the agent to have the persona of an arrogant ass if you prefer it.

  > What makes you think that agents can't iterate?
Please RTFA or RTF top most comment in the thread.

Can they? Yes. Will they reliably? If so, why would it be better to restart...

But the real answer to your question: personal experience

Re: How Anthropic teams use Claude Code

#194

Post by lonelyasacloud »

withinboredom wrote: post #104
DANmode wrote: post #99

Earlier quoted context omitted.

Have you seen human-written code?

At least when you tell a human the indentation is wrong, they can fix it on the first try. Watched an AI agent last night try to fix indentation by using sed for 20 minutes before I just fixed it myself after cringing.

Have seen similar issues with understanding things that are somewhat orthogonal concerns to the main thing that is being worked on.

My guess is that context = main thing + somewhat unrelated thing is too big a space for the models to perform well at this point in time.

The practical solution is to remove the need for the model to figure it out each time and instead explicitly tell it about as much as possible before hand in CLAUDE.md.

Re: How Anthropic teams use Claude Code

#196

Post by lonelyasacloud »

theshrike79 wrote: post #127
bavell wrote: post #110

Earlier quoted context omitted.

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!

Claude has a tendency to reinvent the wheel heavily. It'll create a massive bespoke class to do something that is already in the stdlib. But if there's a pattern of already using stdlib functions, it can copy that easily.

Basically, to get the best out Claude (or any of the other agents) it if it is possible to tell it about something ahead of time time then it is generally wise to, be that in seed skeleton code, comments, CLAUDE.md etc

Re: How Anthropic teams use Claude Code

#197

Post by beambot »

forgotmypw17 wrote: post #183
stillsut wrote: post #166

Earlier quoted context omitted.

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...

Thank you for sharing. I taught some workshops on AI-assisted development using Cursor a Windsurf for MIT students (we built an application and wrote a book) and TAed another similar for-credit course. I’ve also been teaching high schoolers how to code, and we use ChatGPT to help us understand and solve leetcode problems by breaking them down into smaller exercises. There’s also now a Harvard CS course on developing…

Can you provide any source materials - course notes, book, etc?

Re: How Anthropic teams use Claude Code

#198

Post by gmueckl »

zer00eyz wrote: post #64
gmueckl wrote: post #50

Earlier quoted context omitted.

Data centers are CapEx, employees are OpEx. Building more data centers is cheap. Employees can always supervise more agents...

Data centers are cap ex Except the power and cooling demands of the current crop of GPU's means you are not fitting full density in a rack. There is a real material increase in fiber use because of your now more distributed equipment. (because 800gbps interconnects are NOT cheap). You can't capitalize power costs: this is now a non-trivial cost to account for. And the more power you use for compute the more power you…

That is a much more grounded reply than my comment deserved. Thanks!

Re: How Anthropic teams use Claude Code

#199

Post by stillsut »

eagerpace wrote: post #171
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…

Do you have an example of this you could share?

I can share my own ai-generated codebase:

- there's a devlog showing all the prompts and accepted outputs: https://github.com/sutt/agro/blob/master/docs/dev-summary-v1...

- and you can look at the ai-generated tests (as is being discussed above) and see they aren't very well thought out for the behavior, but are syntactically impressive: https://github.com/sutt/agro/tree/master/tests

- check out the case-studies in the docs if you're interested in more ideas.

Re: How Anthropic teams use Claude Code

#200

Post by stillsut »

forgotmypw17 wrote: post #183
stillsut wrote: post #166

Earlier quoted context omitted.

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...

Thank you for sharing. I taught some workshops on AI-assisted development using Cursor a Windsurf for MIT students (we built an application and wrote a book) and TAed another similar for-credit course. I’ve also been teaching high schoolers how to code, and we use ChatGPT to help us understand and solve leetcode problems by breaking them down into smaller exercises. There’s also now a Harvard CS course on developing…

> ...development using Cursor a Windsurf for MIT students...

Richard Stallman is rolling in his grave with this.

But in all seriousness, nice work, I think this _is_ where the industry is going, hopefully we don't have to rely on using proprietary models forever though.

Post reply on HN