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

251–260 of 507 posts

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

#251

Post by majormajor »

BeetleB wrote: post #169
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…

> 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.

how big/complex does the codebase have to be for this to be for you to actually save time compared to just using a debugger and fixing it yourself directly? (I'm assuming here that bugs in smaller codebases are that much easier for a human to identify quickly)

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

#252

Post by majormajor »

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…

> 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).

Was this using technologies you aren't familiar with? If not, the output rate seems pretty low (very human-paced, just with an extra couple bucks spent.)

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

#253

Post by majormajor »

smallerfish wrote: post #192
alextingle wrote: post #166

Earlier quoted context omitted.

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 co…

No, I'm not doing leetcode or algorithm questions - it's basically "build a [tiny] product to specs", in a series of steps. I'm evaluating candidates on their process, their effectiveness, their communication (I ask for narration), and their attention to detail. I do review code afterwards. And, bear in mind that this is only round 1 - once I talk with the ones who do well, I'll go deep on a number of topics to under…

> it's basically "build a [tiny] product to specs", in a series of steps

That seems like exactly what the person you're replying to is saying - that sounds like basic standard product-engineering stuff, but simpler, like any of a million examples out there that an LLM has seen a million times. "Here's a problem LLMs are good at, wow, the people using the LLMs do best at it." Tautolgy.

So it's great for finding people who can use an LLM to do tiny product things.

In the same way takehomes had all the same limitations. More power to you if those are the people you are looking for, though.

But it also sounds like a process that most people with better options are gonna pass on most of the time. (Also like with takehomes.)

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

#254

Post by tymscar »

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 agree with you that the tweet is basically useless but what they have done there is not an appeal to authority fallacy. They have only explained why it’s popular. Arguably your response is a genetic fallacy.

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

#255

Post by CGamesPlay »

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 seconds and $0.73 to search the code base and make a +51 line diff. After it finished, I was quite impressed by its results; it did exactly the correct set of changes I would have done.

Now, this is a higher level of task than I would normally give to Aider (because I didn't provide any file names, and it requires changing multiple files), so I was not surprised that Aider completely missed the files it needed to modify to start (asking me to add 1 correct file and 2 incorrect files). I did a second attempt after manually adding the correct files. After doing this, it produced an equivalent diff to Claude Code. Aider did this in 1 LLM prompt, or about 15 seconds, with a total cost of $0.07, about 10% of the Claude Code cost.

Overall, it seems clear that the higher level of autonomy carries a higher cost with it. My project here was 7k SLOC; I would worry about ballooning costs on much larger projects.

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

#257

Post by nyarlathotep_ »

UltraSane wrote: post #175
fallinditch wrote: post #170

Earlier quoted context omitted.

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

at that point aren't you just replacing regular programming with creating the thousands of rules? I suppose the rules are reusable so it might be a form of meta-programming or advanced codegen

People endlessly creating "rules" for their proompts is the new version of constantly tweaking Vim or Emacs configurations

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

#258

Post by majormajor »

draebek wrote: post #231
bckr wrote: post #160

Earlier quoted context omitted.

I don’t write binaries, assembly, or C. If I don’t have to write an application, I’m okay with that. I still have to write the requirements, design, and acceptance criteria. I still have to gather the requirements from stakeholders, figure out why those will or will not work, provision infra, figure out how to glue said infra together, test and observe and debug the whole thing, get feedback from stakeholders… I have…

I have to say that I am worried that, by taking myself out of the loop for the 99%, I'm going to get worse at the 1% of things that occasionally fall into my lap because the LLM can't seem to do them. I think software engineering is a skill that is "use it or lose it", like many others. There's also the question of whether I will enjoy my craft if it is reduced to, say, mostly being a business analyst and requirement…

It's very specialized already, though.

How many devs could debug both a K8s network configuration issue and a bug in an Android app caused by a weird vendor's OS tweak? Not most of us.

Some people will be better at pushing the LLM things to generate the write crap for the MVP. Some people will be better at using these tools for testing and debugging. Some people will be better at incidence response. They'll probably all be using tools with some level of AI "magic" in them, but the specialization will be somewhat recognizable to what it's been for the past decade.

If you're on the business side you still want a team of people running that stuff until there's a step-change in the ability to trust these things and they get so good you'd be able to give over control of all your cloud/datacenter/network/whatever infrastructure and spending.

And at THAT point... the unemployed software engineers can team up with the unemployed lawyers and doctors and blue-collar workers who were replaced by embodied-LLM-powered robots and ... go riot and ransack some billionare's houses until they decide that these new magical productivity machines should let everyone have more free time and luxury, not less.

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

#260

Post by geoka9 »

draebek wrote: post #231
bckr wrote: post #160

Earlier quoted context omitted.

I don’t write binaries, assembly, or C. If I don’t have to write an application, I’m okay with that. I still have to write the requirements, design, and acceptance criteria. I still have to gather the requirements from stakeholders, figure out why those will or will not work, provision infra, figure out how to glue said infra together, test and observe and debug the whole thing, get feedback from stakeholders… I have…

I have to say that I am worried that, by taking myself out of the loop for the 99%, I'm going to get worse at the 1% of things that occasionally fall into my lap because the LLM can't seem to do them. I think software engineering is a skill that is "use it or lose it", like many others. There's also the question of whether I will enjoy my craft if it is reduced to, say, mostly being a business analyst and requirement…

Reading some of the comments in the "Layoffs don't work" right before reading comments here must have been one of the more surreal experiences for me :)

The takes are as different as (paraphrasing): "if a person can't create something with en empty text editor, I fail them", and "if a person can't speed run through an unrealistically large set of goals because they don't use AI-assisted development, I fail them".

I guess one should keep their skills at both honed at all times, even if neither are particularly useful at most real jobs, because you never know when you're going to be laid off and interviewing.

Post reply on HN