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

11–20 of 248 posts

Re: How Anthropic teams use Claude Code

#11

Post by bdangubic »

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

Re: How Anthropic teams use Claude Code

#12

Post by jasonthorsness »

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 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 rewrites, overall lower quality.

I imagine Anthropic gets to consume it unmetered internally so I they probably completely avoid this problem.

Re: How Anthropic teams use Claude Code

#15

Post by lumost »

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…

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.

Re: How Anthropic teams use Claude Code

#16

Post by tough »

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

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

Re: How Anthropic teams use Claude Code

#17

Post by OJFord »

buggy6257 wrote: post #2

@dang looks like HN ate the leading “How” in the title.

It's intentional. Imagine a blog post 'How I whizzed foobars to optimise my Home Assistant garbage collection' - it's unnecessary filler.

I agree it has times like this it doesn't work and makes the title worse though. The submitter can edit it, and this reformatting (and others) are not applied again.

Re: How Anthropic teams use Claude Code

#18

Post by achierius »

lumost wrote: post #15
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…

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.

"once upon a time"? Engineers concern themselves with cloud bills right now, today! It's not a niche thing either, probably the majority of AWS consumers have to think about this, regularly.

Re: How Anthropic teams use Claude Code

#19

Post by lovich »

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 rewrites, overall lower quality.

I’m legitimately surprised at your feeling on this. I might not want the granular cost put in my face constantly but I do like the ability to see how much my queries cost when I am experimenting with prompt setup for agents. Occasionally I find wording things one way or the other has a significantly cheaper cost.

Why do you think it will lead to a chilling effect instead of the normal effect of engineers ruthlessly innovating costs down now that there is a measurable target?

Re: How Anthropic teams use Claude Code

#20

Post by jonstewart »

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…

And just like a slot machine, it seems pretty clear that some people get addicted to it even if it doesn’t make them better off.
Post reply on HN