I've been using Claude Code for a couple of days • Hacker News Board

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

#281

Post by InvertedRhodium » Mon, Mar 10, 2025, 2:15 AM UTC

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…

My workflow for that kind of thing goes something like this (I use Sonnet 3.7 Thinking in Cursor):

1. 1st prompt is me describing what I want to build, what I know I want and any requirements or restrictions I'm aware of. Based on these requirements, ask a series of questions to produce a complete specification document.

2. Workshop the specification back and forward until I feel it's complete enough.

3. Ask the agent to implement the specification we came up with.

4. Tell the agent to implement Cursor Rules based on the specifications to ensure consistent implementation details in future LLM sessions.

I'd say it's pretty good 80% of the time. You definitely still need to understand the problem domain and be able to validate the work that's been produced but assuming you had some architectural guidelines you should be able to follow the code easily.

The Cursor Rules step makes all the difference in my experience. I picked most of this workflow up from here: https://ghuntley.com/stdlib/

Edit: A very helpful rule is to tell Cursor to always checkout a new branch based on the latest HEAD of master/main for all of it's work.

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

#282

Post by CGamesPlay » Mon, Mar 10, 2025, 2:15 AM UTC

personjerry wrote: post #269

CGamesPlay wrote: post #255

I decided to check this out after seeing the discussion here. I had previously misunderstood that it required a Claude.ai plan, but it actually just uses your API keys. I did a comparison between Claude Code and Aider (my normal go-to): I asked it to do clone a minor feature in my existing app with some minor modifications (specifically, a new global keyboard shortcut in a Swift app). Claude Code spent about 60 secon…

That seems like a steal? Engineers are paid much more to do much less

No, I'm paid much more to do much more than what I did in this simple task. Claude didn't even test the changes (in this case, it does not have the hardware required to do that), or decide that the feature needed to be implemented in the first place. But my comparison wasn't "how do I compare to Claude Code", it was "how does Aider compare to Claude Code". My boss does not use Aider or Claude Code, and would not be happy with the results of replacing me with it (yet).

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

#283

Post by InvertedRhodium » Mon, Mar 10, 2025, 2:17 AM UTC

bikamonki wrote: post #280

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…

Right on point. The same principle applies when deciding whether to use a framework or not. Coders often marvel at the speed with which they can build something using a framework they don’t fully understand. However, a true programmer seeks to know and comprehend what’s happening under the hood.

I'll preface this with the fact I agree that there is a difference between using a framework and being curious enough to dig into the details I think you're veering into No True Scotsman territory here.

IMO, the vast majority of programmers wouldn't meet the definition you've put forward here. I don't know many that dig into the operating system, platform, or hardware all that much, though I work in streaming media so that might just be an industry bias.

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

#284

Post by roarcher » Mon, Mar 10, 2025, 2:22 AM UTC

nsonha wrote: post #106

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?

if it's real that person interviewed at least one candidate per day last year. Idk what kind of engineering role in what kind of org where you even do that.

I suspect he doesn't do much engineering, which would explain why he's impressed by candidates who can quickly churn out small rote sample projects with AI. Anyone who actually writes software for a living knows that working on a large production code base has little in common with this.

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

#285

Post by madmountaingoat » Mon, Mar 10, 2025, 2:25 AM UTC

gitgud wrote: post #243

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…

Interesting, but it seems ridiculous to disambiguate “Programmer” vs “Coder”. They’re synonymous words and mean the same thing right? Person who writes logic for machines

The different mindsets exist, but I agree these are bad words to differentiate them. Back when I started in software in the 80s a common expression was: there are two types of programmers, nerds and hippies. The distinction falling along similar lines - nerds needed to taste the metal, while hippies were more interested in getting stuff done.

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

#286

Post by caseyf7 » Mon, Mar 10, 2025, 2:26 AM UTC

CGamesPlay wrote: post #255

I decided to check this out after seeing the discussion here. I had previously misunderstood that it required a Claude.ai plan, but it actually just uses your API keys. I did a comparison between Claude Code and Aider (my normal go-to): I asked it to do clone a minor feature in my existing app with some minor modifications (specifically, a new global keyboard shortcut in a Swift app). Claude Code spent about 60 secon…

Which model did you use with aider?

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

#287

Post by y1n0 » Mon, Mar 10, 2025, 2:28 AM UTC

CGamesPlay wrote: post #282

personjerry wrote: post #269

Earlier quoted context omitted.

That seems like a steal? Engineers are paid much more to do much less

No, I'm paid much more to do much more than what I did in this simple task. Claude didn't even test the changes (in this case, it does not have the hardware required to do that), or decide that the feature needed to be implemented in the first place. But my comparison wasn't "how do I compare to Claude Code", it was "how does Aider compare to Claude Code". My boss does not use Aider or Claude Code, and would not be h…

I think you missed the point. The claim is that it would have cost you more to hire a person to do what either claude code or aider did.

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

#288

Post by CGamesPlay » Mon, Mar 10, 2025, 2:31 AM UTC

caseyf7 wrote: post #286

CGamesPlay wrote: post #255

I decided to check this out after seeing the discussion here. I had previously misunderstood that it required a Claude.ai plan, but it actually just uses your API keys. I did a comparison between Claude Code and Aider (my normal go-to): I asked it to do clone a minor feature in my existing app with some minor modifications (specifically, a new global keyboard shortcut in a Swift app). Claude Code spent about 60 secon…

Which model did you use with aider?

My post above was with sonnet-3.5. When I used sonnet-3.7, it didn't speculate at the files at all; it simply requested that I add the appropriate ones.

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

#289

Post by dpritchett » Mon, Mar 10, 2025, 2:32 AM UTC

gitgud wrote: post #243

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…

Interesting, but it seems ridiculous to disambiguate “Programmer” vs “Coder”. They’re synonymous words and mean the same thing right? Person who writes logic for machines

There may never be a perfect taxonomy of programmer archetypes.

I imagine most of us here can agree that some elevate the craft and ritual to great effect while others avoid such high-minded conceits in favor of shipping whatever hits the expected target this week.

I’ve been both at different points in my career. Usually it’s a response to my environment.

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

#290

Post by frankc » Mon, Mar 10, 2025, 2:36 AM UTC

rs186 wrote: post #233

frankc wrote: post #225

Earlier quoted context omitted.

I think the interest has more to do with who is doing the tweeting, don't you think?

Reminder: "appeal to authority" is a classical logical fallacy. For me, I don't know this person, which means that all the words are completely meaningless. Which is exactly the point.

I don't think it's really an appeal to authority. No one is saying it must be true because this guy says its true. However, when a very respected figure in software engineer culture like Steve Yegge gives an opinion, that is more noteworthy than when random joe schmo gives his opinion. The fact that you don't know who he is means it's not interesting to you. Clearly, it's noteworthy to others.