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

71–80 of 248 posts

Re: How Anthropic teams use Claude Code

#71

Post by tomlockwood »

bdangubic wrote: post #11
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…

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

Yeah sweet what's the burn rate?

Re: How Anthropic teams use Claude Code

#72

Post by onprema »

> 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 networking specialists.

This seems rather inefficient, and also surprising that Claude Code was even needed for this.

Re: How Anthropic teams use Claude Code

#75

Post by artvandelai »

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)

The limits are in 5 hour windows. You'd have to heavily work on 2+ projects in that window to hit the limit using ~500k tokens/min for around 4.5 hours, and even then it'll reset on the next window.

Re: How Anthropic teams use Claude Code

#76

Post by godelski »

throwmeaway222 wrote: post #8
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…

Thanks for the tip - we employees should run and re-run the code generation hundreds of times even if the changes are pretty good. That way, the brass will see a huge bill without many actual commits. Sorry boss, it looks like we need to hire more software engineers since the AI route still isn't mathing.

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

Re: How Anthropic teams use Claude Code

#77

Post by ktzar »

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.

Re: How Anthropic teams use Claude Code

#78

Post by oblio »

CMCDragonkai wrote: post #65
oblio wrote: post #60

Earlier quoted context omitted.

$200h * 8 * 5 * 4 * 12 = $384 000 per year. You're like in the top 0.05% of earners in the software field. Of course, if you save 10 hours per month, the math starts making more sense for others. And this is assuming LLM prices are stable, which I very much doubt they are, since everyone is price dumping to get market share.

Across most anglosphere countries and tech cities - wages and salaries far outstrip what you can get for AI. AI is already objectively cheaper than human talent in rich countries. Is it as good? Yea I'd say it's better than most mid to junior engineers. Can it run entirely by itself? No, it still needs HITL.

Again, those prices aren't stable.

Nobody is investing half a trillion in a tech without expecting a 10x return.

And fairly sure soon those $20/month subscriptions will sell your data, shove ads everywhere AND basically only allow you to get that junior dev for 30 minutes per day or 2 days a month.

And the $200/month will probably be $500-1000 with more limitations.

Still cheap, but AI can't run an entire project, can't deliver. So the human will be in the loop, as you said, so at least a partial cost on top.

Re: How Anthropic teams use Claude Code

#79

Post by MPSimmons »

preommr wrote: post #25
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…

> 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. I have been pretty successful at using llms for code generation. I have a simple rule that something is either 90%>ai or none at all (exluding inline completions, and very obvious text editing). The model has an inherent understanding of some problems due to it's trainin…

Agree with your experiences. I've also found that if I build a lightweight skeleton of the structure of the program, it does a much better job. Also, ensuring that it does a full fledged planning/non-executing step before starting to change things leads to good results.

I have been using Cline in VSCode, and I've been enjoying it a lot.

Re: How Anthropic teams use Claude Code

#80

Post by physix »

jonstewart wrote: post #22
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…

The hilarious part I’ve found is that when it runs into the least bit of trouble with a step on one of its plans, it will say it has been “Deferred” and then make up an excuse for why that’s acceptable. It is sometimes acceptable for humans to use judgment and defer work; the machine doesn’t have judgment so it is not acceptable for it to do so.

Talking about hilarious, we had a Close Encounter of the Hallucinating Kind today. We were having mysterious simultaneous gRPC socket-closed exceptions on the client and server side running in Kubernetes talking to each other through an nginx ingress.

We captured debug logs, described the detailed issue to Gemini 2.5 Flash giving it the nginx logs for the one second before and after an example incident, about 10k log entries.

It came back with a clear verdict, saying

"The smoking gun is here: 2025/07/24 21:39:51 [debug] 32#32: *5902095 rport:443 upstream timed out (110: Connection timed out) while reading response header from upstream, client: 10.233.100.128, server: grpc-ai-test.not-relevant.org, request: POST /org.not-relevant.cloud.api.grpc.CloudEventsService/startStreaming HTTP/2.0, upstream: grpc://10.233.75.54:50051, host: grpc-ai-test.not-relevant.org"

and gave me a detailed action plan.

I was thinking this is cool, don't need to use my head on this, until I realized that the log entry simply did not exist. It was entirely made up.

(And yes I admit, I should know better than to do lousy prompting on a cheap foundation model)

Post reply on HN