Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code: Best practices for agentic coding

anthropic.com

Post reply on HN
Print view View original

191–200 of 268 posts

Re: Claude Code: Best practices for agentic coding

#191

Post by neodypsis »

flashgordon wrote: post #145

So I feel like a grandpa reading this. I gave Claude code a solid shot. Had some wins but costs started blowing up. I switched to Gemini AI where I only upload files I want it to work on and make sure to refactor often so modularity remains fairly high. It's an amazing experience. If this is any measure - I've been averaging about 5-6 "small features" per 10k tokens. And I totally suck at fe coding!! The other intere…

A combination that works nicely to solve bugs is: 1) have Gemini analyze the code and the problem, 2) ask it to create a prompt for Claude to fix the problem, 3) give Claude the markdown prompt and the code, 4) give Gemini the output from Claude to review, 5) repeat if necessary

Re: Claude Code: Best practices for agentic coding

#192

Post by Quarrel »

westoncb wrote: post #173
simonw wrote: post #149

The "ultrathink" thing is pretty funny: > We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" I had a poke around and it's not a feature of the Claude model, it's specific to Claude Code. There's a "megathi…

That's awesome, and almost certainly an Unreal Tournament reference (when you chain enough kills in short time it moves through a progression that includes "megakill" and "ultrakill").

Ultrakill is from Quake :)

Re: Claude Code: Best practices for agentic coding

#193

Post by beefnugs »

Isn't this bad that every model company is making their own version of the IDE level tool?

Wasn't it clearly bad when facebook would get real close to buying another company... then decide naw, we got developers out the ass lets just steal the idea and put them out of business

Re: Claude Code: Best practices for agentic coding

#194

Post by ngruhn »

jjmarr wrote: post #153
owebmaster wrote: post #112

Earlier quoted context omitted.

Important to remind people this is only true if you have a profitable product, otherwise you’re spending money you haven’t earned.

If what I'm doing doesn't have a positive expected value, the correct move isn't to use inferior dev tooling to save money, it's to stop working on it entirely.

Come on, every hobby has negative expected value. You're not doing it for the money but it still makes sense to save money.

Re: Claude Code: Best practices for agentic coding

#195

Post by dannersy »

zomglings wrote: post #49
ghuntley wrote: post #12

Earlier quoted context omitted.

$200/month isn't that much. Folks, I'm hanging around with are spending $100 USD to $500 USD daily as the new norm as a cost of doing business and remaining competitive. That might seem expensive, but it's cheap... https://ghuntley.com/redlining

$100/day seems reasonable as an upper-percentile spend per programmer. $500/day sounds insane. A 2.5 hour session with Claude Code costs me somewhere between $15 and $20. Taking $20/2.5 hours as the estimate, $100 would buy me 12.5 hours of programming.

I'm waiting for the day this AI bubble bursts since as far as we can tell almost all these AI "providers" are operating at a loss. I wonder if this billing model actually makes profit or if it's still just burning cash in hopes of AGI being around the corner. We have yet to see a product that is useful and affordable enough to justify the cost.

Re: Claude Code: Best practices for agentic coding

#196

Post by vessenes »

Wowfunhappy wrote: post #120
zoogeny wrote: post #29

So I have been using Cursor a lot more in a vibe code way lately and I have been coming across what a lot of people report: sometimes the model will rewrite perfectly working code that I didn't ask it to touch and break it. In most cases, it is because I am asking the model to do too much at once. Which is fine, I am learning the right level of abstraction/instruction where the model is effective consistently. But wh…

> So I have been using Cursor a lot more in a vibe code way lately and I have been coming across what a lot of people report: sometimes the model will rewrite perfectly working code that I didn't ask it to touch and break it. I don't find this particularly problematic because I can quickly see the unnecessary changes in git and revert them. Like, I guess it would be nice if I didn't have to do that, but compared to t…

i think this is particularly claude 3.7 behavior - at least in my experience, it's ... eager. overeager. smarter than 3."6" but still, it has little chill. gemini is better; o3 better yet. I'm mostly off claude as a daily driver coding assistant, but it had a really long run - longest so far.

Re: Claude Code: Best practices for agentic coding

#197

Post by vessenes »

neodypsis wrote: post #191
flashgordon wrote: post #145

So I feel like a grandpa reading this. I gave Claude code a solid shot. Had some wins but costs started blowing up. I switched to Gemini AI where I only upload files I want it to work on and make sure to refactor often so modularity remains fairly high. It's an amazing experience. If this is any measure - I've been averaging about 5-6 "small features" per 10k tokens. And I totally suck at fe coding!! The other intere…

A combination that works nicely to solve bugs is: 1) have Gemini analyze the code and the problem, 2) ask it to create a prompt for Claude to fix the problem, 3) give Claude the markdown prompt and the code, 4) give Gemini the output from Claude to review, 5) repeat if necessary

If you like this plan, you can do this from the command line:

`aider --model gemini --architect --editor-model claude-3.7` and aider will take care of all the fiddly bits including git commits for you.

right now `aider --model o3 --architect` has the highest rating on the Aider leaderboards, but it costs wayyy more than just --model gemini.

Re: Claude Code: Best practices for agentic coding

#198

Post by oezi »

jjmarr wrote: post #153
owebmaster wrote: post #112

Earlier quoted context omitted.

Important to remind people this is only true if you have a profitable product, otherwise you’re spending money you haven’t earned.

If what I'm doing doesn't have a positive expected value, the correct move isn't to use inferior dev tooling to save money, it's to stop working on it entirely.

There might be value but you might not receive any of it. Most salaried employees won't see returns.

Re: Claude Code: Best practices for agentic coding

#199

Post by oezi »

winrid wrote: post #143
hu3 wrote: post #130

Earlier quoted context omitted.

I guess the question the is: can't VScode Copilot do the same for a fixed $20/month? It even has access to all SOTA models like Claude 3.7, Gemini 2.5 Pro and GPT o3

I haven't tried copilot. Mostly because I don't use VSCode, I use jetbrains ides. How do they provide Claude 3.7 for $20/mo with unlimited usage?

By providing bad UI that you don't use it so much.

Re: Claude Code: Best practices for agentic coding

#200

Post by oezi »

troupo wrote: post #132
oxidant wrote: post #104

Earlier quoted context omitted.

Think about what you would do in an unfamiliar project with no context and the ticket "please fix the authorization bug in /api/users/:id". You'd start by grepping the code base and trying to understand it. Compare that to, "fix the permission in src/controllers/users.ts in the function `getById`. We need to check the user in the JWT is the same user that is being requested"

So, AIs are overeager junior developers at best, and not the magical programmer replacements they are advertised as.

As of April 2025. The pace is so fast that it will overtake seniors within years maybe months.
Post reply on HN