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

I've been using Claude Code for a couple of days

twitter.com

Post reply on HN
Print view View original

181–190 of 507 posts

Re: I've been using Claude Code for a couple of days

#181

Post by ezekiel68 »

techpineapple wrote: post #93
frankc wrote: post #89

Earlier quoted context omitted.

I haven't got to trying claude code yet, but absolutely with cursor and windsurf you can have the agent be reading the output of what it writes and runs and it can fix things it sees. You can also have it review code. It also help some times to have it review in a fresh chat with less context. I really think a lot of people on HN are not really pushing on everything that is available. Its magic for me but I spend a l…

I’m going to keep at it, because I was trained as an SRE, not a developer and have lots of ideas for side projects that have thus far taken a long time to get going, but I’ve been struggling, it sort of quickly gets into these infinite loop situations where it can’t seem it can’t seem to fix a feature and goes back and forth between multiple non working states. CSS layouts but even basic stuff like having the right w…

I can't explain why, but I do get pretty good results with closing a prompt session completely and then initiating a fresh session later on. I have actually seen quite different code from the very same prompt across two sessions.

However, the extra time between sessions does give me the chance to consider where the AI might have gone wrong in the first session and how I could have phrased the initial prompts more effectively.

As others have stated throughout the threads here, I definitely recommend giving it smaller nibbles of problems. When I take this route and get working modules, I will start a fresh prompt session to upload the working code module files and ask it to integrate them into a simple solution with static inputs in a 'main' function. (Because providing coherent inputs from the router function inputs of a web service are simple enough, once these basics are covered)

Basically - I do everything possible in order for the AI to not get distracted or go down a rabbit hole, chasing concerns that humans are very capable of taking care of (without paying tokens for). I will write most of the tests myself and then perhaps afterwards ask it to evaluate the test coverage and provide more of them. This way the new tests are in the format and platform of my choosing.

Re: I've been using Claude Code for a couple of days

#183

Post by BeetleB »

tptacek wrote: post #173
BeetleB wrote: post #169

Earlier quoted context omitted.

Some hints for people stuck like this: Consider using Aider. It's a great tool and cheaper to use than Code. Look at Aiders LLM leaderboard to figure out which LLMs to use. Use its architect mode (although you can get quite fast without it - I personally haven't needed it). Work incrementally. I use at least 3 branches. My main one, a dev one and a debug one. I develop on dev. When I encounter a bug I switch to debug…

The three-branch thing is so smart.

It took a while for me to realize it, and frankly, it's kind of embarrassing that I didn't think of it immediately.

It is, after all, what many of us would do in our manual SW development. But when using an LLM that seems pretty good, we just assume we don't need to follow all the usual good practices.

Re: I've been using Claude Code for a couple of days

#184

Post by babyent »

develoopest wrote: post #4

I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…

I’ve dug into this a few times.

Every single time they were doing something simple.

Just because someone has decades of experience or is a SME in some niche doesn’t mean they’re actually good… engineers.

Re: I've been using Claude Code for a couple of days

#185

Post by Ancalagon »

develoopest wrote: post #4

I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…

Are you actually using claude? There's an enormous difference between claude code and copilot, with the latter being a bigger burden these days than a help.

Re: I've been using Claude Code for a couple of days

#186

Post by babyent »

raylad wrote: post #115

I tried it on a small Django app and was not impressed in the end. It looks like it’s doing a lot, and at first I was very impressed, but after a while I realized that when it ran into a problem it kept on trying nonworking strategies even though it had tried them before and I had added to claude.md instructions to keep track of strategies and not reuse failing ones. It was able to make a little progress, but not get…

Now take your $12 and multiply it by 100k people or more trying it.

Even if you won’t use it again, that’s booked revenue for the next fundraise!

Re: I've been using Claude Code for a couple of days

#187

Post by doug_durham »

clusterhacks wrote: post #153
develoopest wrote: post #4

I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…

I am a slow adopter of new tech but plan to spend a significant amount of time in 2025 using AI tools when coding. I am net negative on AI simply replacing programmers, but I think the practice of development is undergoing a seismic shift at this point. My recent usage is oriented towards using pseudocode descriptions that closely map to Python to produce Python functions. I am very impressed with Claude 3.7's syntac…

At this point very little code is "novel". Everyone is simply rewriting code that has already been written in a similar form. The LLM isn't slurping up and restating code verbatim. It is taking code that it has seen thousands of times and generating a customized version for your needs. It's hubris to think that anyone here is generating "novel" code.

Re: I've been using Claude Code for a couple of days

#188

Post by WD-42 »

BeetleB wrote: post #161
WD-42 wrote: post #121

Earlier quoted context omitted.

So you’re telling me you spent 20 dollars and an entire day for 200 lines of JavaScript and 75 lines of python and this to you constitutes a working re-creation of Claude Code? This is why expectations are all out of whack.

That amount of output is comparable to what many professional engineers produce in a given day, and they are a lot more expensive. Keep in mind this is the commenters first attempt. And I'm surprised he paid so much. Using Aider and Sonnet I've on multiple occasions produced 100+ lines of code in 1-2 hours, for under $2. Most of that time is hunting down one bug it couldn't fix by itself (reflective of real world pro…

The lines of code isn’t the point. Op claimed they asked Claude to recreate Claude code and it was successful. This is obviously an extreme exaggeration. I think this is the crux of a lot of these posts. This code generator output a very basic utility. To some this is a revelation, but it leaves others wondering what all the fuss is about.

It seems to me people’s perspective on code gen has largely to do with their experience level of actually writing code.

Re: I've been using Claude Code for a couple of days

#189

Post by MarkMarine »

vander_elst wrote: post #162
MarkMarine wrote: post #149

Earlier quoted context omitted.

Claude code doesn’t need magic prompts. It’s not perfect but holy moly is it good, when it’s working it just one shots things for you. It’s just EXPENSIVE. I’ve spent 30$ in tokens on it this week. Cursor’s “chat with your codebase” is a funny joke compared to Claude Code. Ask it questions, have it figure things out. I had it analyze the openAPI schema and the backend that is serving the schema for the API I’m writin…

Thanks, but to me this feels too high level I'd really need to see a video of such things to better understand what's going on, how much time it took end to end, what was the quality. Yes I could spend 3 days and 300 bucks playing around with the tool, but I'd prefer to learn things offline first.

That is all right by me, we need the part of the adoption curve that isn’t at the leading edge.

Re: I've been using Claude Code for a couple of days

#190

Post by jmull »

fallinditch wrote: post #170
jmull wrote: post #49

Earlier quoted context omitted.

All I really care about is the end result and, so far, LLMs are nice for code completion, but basically useless for anything else. They write as much code as you want, and it often sorta works, but it’s a bug filled mess. It’s painstaking work to fix everything, on part with writing it yourself. Now, you can just leave it as-is, but what’s the use of releasing software that crappy? I suppose it’s a revolution for tha…

Have you tried using Cursor rules? [1] Creating a standard library stdlib with many (potentially thousands) of rules, and then iteratively adding to and amending the rules as you go, is one of the best practices for successful AI coding. [1] https://docs.cursor.com/context/rules-for-ai

> …many (potentially thousands) of rules, and then iteratively adding to and amending the rules as you go…

Is this an especially better (easier, more efficient) route to a working, quality app/system than conventional programming?

I’m skeptical if the answer to the way to achieve 10x results is 10x more effort.

Post reply on HN