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

81–90 of 507 posts

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

#81

Post by discordance »

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.

by 100% organic, free range and fair trade programmers

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

#83

Post by emalafeew »

Somebody here said programming is about designing and reusing libraries rather than coding from scratch like LLMs. But that choice has always been a tradeoff between abstraction and bloat vs performance and debuggability. Writing 50 lines of intentional code is often preferable to adapting a 50000 line library. The trick to using LLMs is to not ask for too much. Claude 3.5 could reliably code tasks that would have taken 5-10 min by hand. Claude 3.7 is noticeably better and can handle 10-30 min tasks without error. If you push those limits you will lose instead of save time.

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

#84

Post by mpalmer »

delusional wrote: post #48
rs186 wrote: post #40

A single tweet with lots of analogy, with no screenshot/screen recording/code examples whatsoever. These are just words. Are we just discussing programming based on vibe?

It's influencer culture. It's like when people watch those "software developer" youtubers and pretend it's educational. It's reality television for computer people.

Reality television plus cooking show, exactly.

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

#86

Post by trescenzi »

I’m sorry what is happening with this paragraph:

> As long as the bank authorizations keep coming through, it will push on bug fixes until they're deployed in production, and then start scanning through the user logs to see how well it's doing.

I enjoy using these tools. They help me in my work. But the continual hype makes the discussion around them impossible to be genuine.

So I ask, genuinely, did I miss the configuration section where you can have it scan your logs for new errors and have it argue with you on PRs? Is he trying to say something else? Or is it just anthropomorphizing hype?

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

#87

Post by cglace »

crabl wrote: post #72
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…

What I've noticed from my extensive use over the past couple weeks has been Claude Code really sucks at thinking things through enough to understand the second and third order consequences of the code that it's writing. That said, it's easy enough to work around its deficiencies by using a model with extended thinking (Grok, GPT4.5, Sonnet 3.7 in thinking mode) to write prompts for it and use Claude Code as basically…

In all of these posts I fail to see how this is engineering anymore. It seems like we are one step away from taking ourselves out of the picture completely.

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

#88

Post by tomnipotent »

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…

The author works on Cody at Sourcegraph so I'll give him the benefit of the doubt that he's tried all the major players in the game.

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

#89

Post by frankc »

trescenzi wrote: post #86

I’m sorry what is happening with this paragraph: > As long as the bank authorizations keep coming through, it will push on bug fixes until they're deployed in production, and then start scanning through the user logs to see how well it's doing. I enjoy using these tools. They help me in my work. But the continual hype makes the discussion around them impossible to be genuine. So I ask, genuinely, did I miss the confi…

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 lot of effort and skill manifesting the magic. I'm not doubting other people's experience really, but wondering if they are giving up too fast because they actually don't want it work well for ego reasons.

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

#90

Post by borgdefenser »

ido wrote: post #41
egorfine wrote: post #30

Earlier quoted context omitted.

You have to learn and figure out how to prompt it. My experience with Claude Code is this: one time it produces an incredible result; another time it's an utter failure. There are prompt tips and tricks which have enormous influence on the end result.

Can you give us some of these tips?

You should also try the same prompt multiple times to see how this works.

Sometimes you will get better or worse answers completely by chance.

I think Claude is pretty good if you have it write a function and give it the inputs, output and a data example. You can also put to ask clarifying questions as needed because there is a good chance there are aspects of the prompt that are ambiguous.

My prompts are always better if I write them in a separate text file and then paste them in too. I think I just take my time and think things out more that way instead of trying to get to the answer as fast.

Post reply on HN