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

21–30 of 248 posts

Re: How Anthropic teams use Claude Code

#21

Post by threatofrain »

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…

This is an easy calculation for everyone. Think about whether Claude is giving you the a sufficient boost in performance, and if not... then it's too expensive. No doubt some people are in some combination of domain, legacy, complexity of codebase, etc., where Claude just doesn't cut it.

Re: How Anthropic teams use Claude Code

#22

Post by jonstewart »

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.

Re: How Anthropic teams use Claude Code

#25

Post by preommr »

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 training data (e.g. setting up a web server with little to no deps in golang), that it can do with almost 100% certainty, where it's really easy to blaze through in a few minutes, and then I can setup the architecture for some very flat code flows. This can genuinely improve my output by 30%-50%

Re: How Anthropic teams use Claude Code

#26

Post by nextworddev »

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.

You will start seriously worrying about coding AI bills within 6 months

Re: How Anthropic teams use Claude Code

#28

Post by ants_everywhere »

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.

Oh yeah totally. It feels a bit deceptive sometimes.

Like just now it says "great the tests are consistently passing!" So I ran the same test command and 4 of the 7 tests are so broken they don't even build.

Re: How Anthropic teams use Claude Code

#30

Post by mhrmsn »

It'd be more interesting if they shared actual examples of complete prompts, CLAUDE.md files, settings and MCP servers to achieve certain things.

The documentation is good, but is kept relatively general and I have a feeling that the quality of Claude Code's output really depends on the specific setup and prompts you use.

Post reply on HN