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

41–50 of 248 posts

Re: How Anthropic teams use Claude Code

#41

Post by whatever1 »

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.

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

Re: How Anthropic teams use Claude Code

#42

Post by jasonthorsness »

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 think it’s easy to spend _time_ when the reward is intangible or unlikely, like an evening writing toy applications to learn something new or prototyping some off-the-wall change in a service that might have an interesting performance impact. If development becomes metered in both time and to-the-penny dollars, I at least will have to fight the attitude that the rewards also need to be more concrete and probable.

Re: How Anthropic teams use Claude Code

#43

Post by spike021 »

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…

a couple weekends ago i handed it the basic MLB api and asked it to create some widgets for MacOS to show me stuff like league/division/wildcard standings along with basic settings to pick which should be shown. it cranked out a working widget in like a half hour with minimal input.

i know some swift so i checked on what it was doing. for a quick hack project it did all the work and easily updated things i saw issues with.

for a one-off like that, not bad at all. not too dissimilar from your example.

Re: How Anthropic teams use Claude Code

#44

Post by chrisweekly »

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.

FYI the idiom comes from card games, not restaurants. It's "table stakes", as in "the minimum amount required to commit to the game to be allowed to play".

Re: How Anthropic teams use Claude Code

#46

Post by animex »

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 just had the same thing happen. Some comprehensive tests were failing, and it decide to write a simple test instead rather than investigate why these more complicated tests were failing. I wonder if the team is trying to save compute by urging it to complete tasks more quickly! Claude seems to be under a compute crunch as often I get API timeouts/errors.

Re: How Anthropic teams use Claude Code

#48

Post by neom »

chrisweekly wrote: post #44
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.

FYI the idiom comes from card games, not restaurants. It's "table stakes", as in "the minimum amount required to commit to the game to be allowed to play".

I'm bad at speeling. :(

Re: How Anthropic teams use Claude Code

#49

Post by joe_the_user »

bgwalter wrote: post #40

So this style of articles is the future? Pages of unconnected bullet points that mention the word "Claude" at least 100 times. No real information and nothing to remember.

Yeah, I don't think all the information in the article is useful but it seems like disorganized dump - or a melding together of several article - boiler plate "we use Claude for all good things" and specific useful tips all run together.

It definitely has a "we use AI enough that we've lost the ability to communicate coherently" vibe to it.

Re: How Anthropic teams use Claude Code

#50

Post by gmueckl »

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.

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