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

161–170 of 507 posts

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

#161

Post by BeetleB »

WD-42 wrote: post #121
slooonz wrote: post #69

Earlier quoted context omitted.

I decided to try seriously the Sonnet 3.7. I started with a simple prompt on claude.ai ("Do you know claude code ? Can you do a simple implementation for me ?"). After minimal tweaking from me, it gave me this : https://gist.github.com/sloonz/3eb7d7582c33e95f2b000a0920016... After interacting with this tool, I decided it would be nice if the tool could edit itself, so I asked (him ? it ?) to create its next version.…

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 programming experience).

There were many other bugs, but I would just point out the failures I was seeing and it would fix it itself. For particularly difficult bugs it would at times even produce a full new script just to aid with debugging. I would run it and it would spit out diagnostics which I fed back into the chat.

The code was decent quality - better than what some of my colleagues write.

I could probably have it be even more productive if I didn't insist on reading the code it produced.

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

#162

Post by vander_elst »

MarkMarine wrote: post #149
vander_elst wrote: post #140

Are there any videos showing these very advanced use cases? I'd be interested in learning how to achieve this level of proficiency. At the moment I still feel I'm better off without ai

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.

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

#163

Post by collingreen »

nsonha wrote: post #105
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…

this space is moving really fast, I suggest before forming an definitive opinion try the best tool, such as the latest Claude model and use "agentic" mode or the equivalence on your client. For example, on Copilot this mode is brand new and only available in vscode insider. Cursor and other tools have had it for a little longer.

People have been saying it writes amazing code that works for far longer than that setup has been available though. Your comment makes me think the product is still trying to catch up to these expectations people are setting.

That being said I appreciate your suggestion and will consider giving that a shot.

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

#164

Post by collingreen »

intrasight wrote: post #143
chaosprint wrote: post #56

It seems the original poster hasn't extensively tried various AI coding assistants like Cursor or Windsurf. Just a quick heads-up based on my recent experience with agent-based AI: while it's comfortable and efficient 90% of the time, the remaining 10% can lead to extremely painful debugging experiences. In my view, the optimal scenarios for using LLM coding assistants are: - Architectural discussions, effectively re…

> extremely painful debugging experiences. I'd claim that if you're debugging the code - or even looking at it for that matter - that you're using AI tools the wrong way.

This is exactly my impression of the summary of these kinds of posts and, I'm speculating here, maybe where there is such a stark difference.

I'm guessing that the folks who read the output and want to understand it deeply and want to "approve" it like a standard pull request are having a very different perspective and workflow than those who are just embracing the vibe.

I do not know if one leads to better outcomes than the other.

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

#165

Post by riwsky »

Shebanator wrote: post #133
ramblerman wrote: post #47

Earlier quoted context omitted.

lol - I thought the same, but the charitable take after looking at the user's profile is that he is a journalist, and not tech savvy. So I understand his request as more along the lines of, can you explain this in a way that I understand it. For which summarization is the wrong phrasing. ie.. It seems trivial on hacker news, but that post would be pure giberish for most of our parents.

That's steve yegge ( https://en.wikipedia.org/wiki/Steve_Yegge ) you are talking about. Kids these days, sheesh, they think lisp is a speech impediment.... /s

They’re not—they’re talking about this guy who replied to yegge: https://x.com/Beirutspring/status/1898689770563260535

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

#166

Post by alextingle »

smallerfish wrote: post #125
triyambakam wrote: post #92

Earlier quoted context omitted.

Hundreds of candidates? That's significant if not an exaggeration. What are the stark differences you have seen? Did you inquire about the candidate's use of language models?

Yes. I do async video interviews in round 1 of my interview process in order to narrow the candidate funnel. Candidates get a question at the start of the interview, with a series of things to work through in their own IDE while sharing their screen. I review all recordings (though I will skip around, and if candidates don't get very far I won't spend a lot of time watching at 1x speed.) The question as laid out enco…

Is the question actually difficult, though? If you ask for some standard task, then of course those who are leaning heavily on LLMs will do well, as that's exactly where they work best. That doesn't tell you anything about the performance of those candidates in situations where the LLM won't help them.

I suppose, if you are specifically looking for coders to perform routine tasks, then you'll get what you need.

Of course, you could argue that ~90% of a programmer's work day is performing standard tasks, and even brilliant programmers who don't use LLMs will lose so much productivity that they are not worth hiring... Counterpoint: IMO, the amount of code you bash out in a given time bears no relation to your usefulness as a programmer. In fact, producing lots of code is often a problem.

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

#167

Post by LeftHandPlane »

beezlewax wrote: post #34
abxyz wrote: post #26

Earlier quoted context omitted.

I think it's probably the difference between "code" and "programming". An LLM can produce code and if you're willing to surrender to the LLMs version of whatever it is you ask for, then you can have a great and productive time. If you're opinionated about programming, LLMs fall short. Most people (software engineers, developers, whatever) are not "programmers" they're "coders" which is why they have a positive impres…

I'm waiting for artisan programming to become a thing.

Artisanal firmware is the future (or the past? or both?): https://www.youtube.com/watch?v=vBXsRC64hw4

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

#168

Post by noufalibrahim »

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'm in the same boat. I've found it useful in micro contexts but in larger programs, it's like a "yes man" that just agrees with what I suggest and creates an implementation without considering the larger ramifications. I don't know if it's just me.

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

#169

Post by BeetleB »

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…

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 reason is it can produce a lot of code to fix a bug. It will write some code to fix it. That won't work. It will try again and write even more code. Repeat until fixed. But in the end I only needed a small subset of the new code. So you then revert all the changes and have it fix it again telling it the correct fix.

Don't debug on your dev branch.

Aider's auto committing is scary but really handy.

Limit your context to 25k.

Only add files that you think are necessary.

Combining the two: Don't have large files.

Add a Readme.md file. It will then update the file as it makes code changes. This can give you a glimpse of what it's trying to do and if it writes something problematic you know it's not properly understanding your goal.

Accept that it is not you and will write code differently from you. Think of it as a moderately experienced coder who is modifying the codebase. It's not going to follow all your conventions.

https://aider.chat/

https://aider.chat/docs/leaderboards/

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

#170

Post by fallinditch »

jmull wrote: post #49
abxyz wrote: post #26

Earlier quoted context omitted.

I think it's probably the difference between "code" and "programming". An LLM can produce code and if you're willing to surrender to the LLMs version of whatever it is you ask for, then you can have a great and productive time. If you're opinionated about programming, LLMs fall short. Most people (software engineers, developers, whatever) are not "programmers" they're "coders" which is why they have a positive impres…

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

Post reply on HN