How Anthropic teams use Claude Code • Hacker News Board

Re: How Anthropic teams use Claude Code

#61

Post by Fade_Dance » Fri, Jul 25, 2025, 3:00 AM 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 even heard that it will aggressively delete your codebase and then lie about it. To your face.

Re: How Anthropic teams use Claude Code

#62

Post by mfrye0 » Fri, Jul 25, 2025, 3:04 AM UTC

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.

Re: How Anthropic teams use Claude Code

#63

Post by bionhoward » Fri, Jul 25, 2025, 3:06 AM UTC

Anthropic goes hard on the virtue signalling but I still don’t get how anyone manages to satisfy “Customer may not and must not attempt to (a) access the Services to build a competing product or service”

So I just avoid it and generally think the whole thing isn’t serious, because nobody seems to care enough about the safety implications of building AGI with legal terms which are logically impossible to satisfy to demonstrate appropriate attention to detail (aka, yall are noobs)

Re: How Anthropic teams use Claude Code

#64

Post by zer00eyz » Fri, Jul 25, 2025, 3:08 AM UTC

gmueckl wrote: post #50

throwmeaway222 wrote: post #8

Earlier quoted context omitted.

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.

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 have to use for cooling... (Power density is now so high that cooling with something other than air is looking not just attractive but like it is going to be a requirement.)

Meanwhile the cost of lending right now is high compared to recent decades...

The accounting side of things isnt as pretty as one would like it to be.

Re: How Anthropic teams use Claude Code

#65

Post by CMCDragonkai » Fri, Jul 25, 2025, 3:08 AM UTC

oblio wrote: post #60

philomath_mn wrote: post #32

Earlier quoted context omitted.

AI bills are already trivial compared to human time. I pay for claude max, all I need to do is save an hour a month and I will be breaking even.

$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.

Re: How Anthropic teams use Claude Code

#66

Post by School-Cotton » Fri, Jul 25, 2025, 3:12 AM UTC

bionhoward wrote: post #63

Anthropic goes hard on the virtue signalling but I still don’t get how anyone manages to satisfy “Customer may not and must not attempt to (a) access the Services to build a competing product or service” So I just avoid it and generally think the whole thing isn’t serious, because nobody seems to care enough about the safety implications of building AGI with legal terms which are logically impossible to satisfy to de…

Are you trying to build an AI platform to compete with anthropic? If not, why does that line matter?

Re: How Anthropic teams use Claude Code

#67

Post by amacneil » Fri, Jul 25, 2025, 3:13 AM UTC

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 but basic things like subscription management are unsolved…

Re: How Anthropic teams use Claude Code

#68

Post by baby » Fri, Jul 25, 2025, 3:14 AM UTC

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?

Re: How Anthropic teams use Claude Code

#69

Post by mwigdahl » Fri, Jul 25, 2025, 3:14 AM UTC

lovich wrote: post #19

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…

> 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 disconcerting. I hope the fine-grained metering of inference is a temporary situation otherwise I think it will have a chilling/discouraging effect on software developers, leading to less experimentation and fewer rewrite…

I’ve seen it firsthand at work, where my developers are shy about spending even a single digit number of dollars on Claude Code, even when it saves them 10 times that much in opportunity cost. It’s got to be some kind of psychological loss aversion effect.

Re: How Anthropic teams use Claude Code

#70

Post by arrowsmith » Fri, Jul 25, 2025, 3:16 AM UTC

neom wrote: post #24

Wouldn't it be a bit unusual if that wasn't true? We build our coding agent...with our coding agent... feeling like this is table steaks.

The actual title is "How Anthropic teams use Claude Code". HN automatically strips the "How" from any title that starts with it, for dubious reasons — and this thread is a great example of the drawbacks.