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

151–160 of 507 posts

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

#151

Post by ptmcc »

matt_heimer wrote: post #94
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…

LLM are replacing Google for me when coding. When I want to get something implemented, let's say make a REST request in Java using a specific client library, I previously used Google to find example of using that library. Google has gotten worse (or the internet has more garbage) so finding code an example is more difficult than it used to be. Now I ask an LLM for an example. Sometimes I have to ask for a refinement…

This has been my experience of successful usage as well. It's not writing code for me, but pulling together the equivalent of a Stack Overflow example and some explaining sentences that I can follow up on. Not perfect and I don't blindly copy paste it, same as Stack Overflow ever was, but faster and more interactive. It's helpful for wayfinding, but not producing the end result.

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

#152

Post by roflyear »

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…

What are some examples of the bugs it fixed?

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

#153

Post by clusterhacks »

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 syntactic correctness when given a chunk of pseudocode that looks "python-y" to begin with.

My one concern is that much of my recent code requirements lack novelty. So there is a somewhat reasonable chance that the tool is just spitting out code it slurped somewhere in github or elsewhere in the larger Internet. Just this week, I gave Claude a relatively "anonymous" function in pseudocode, meaning variable names were not particularly descriptive with one tiny exception. However, Claude generated a situationally appropriate comment as part of the function definition. This was . . . surprising to me if somehow the model had NOT in its training set had some very close match to my pseudocode description that included enough context to add the comment.

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

#154

Post by throwaway0123_5 »

NitpickLawyer wrote: post #137
Silhouette wrote: post #120

Earlier quoted context omitted.

Thanks for writing up your experience and sharing the real code. It is fascinating to see how close these tools can now get to producing useful, working software by themselves. That said - I'm wary of reading too much into results at this scale. There isn't enough code in such a simple application to need anything more sophisticated than churning out a few lines of boilerplate that produce the correct result. It prob…

aider has this great visualisation of "self written code" - https://aider.chat/HISTORY.html

I suspect it would be somewhat challenging to do, but I'd love to see something like this where the contributions are bucketed into different levels of difficulty. It is often the case for me that a small percentage of the lines of code I write take a large percentage of the time I spend coding (and I assume this is true for most people).

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

#155

Post by MarkMarine »

roflyear wrote: post #152
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…

What are some examples of the bugs it fixed?

Accepting an epoch timestamp rather than 3339 like the rest of the codebase is the most recent example. The API standardized on one timestamp and I had an endpoint expecting epoch, it was smart enough to infer the rest of the APIs were 3339 and go change the epoch timestamp accepting backend route including writing a database migration and fixing tests. I haven’t pushed the fix yet

So think about the reasoning there. It read the API docs that said all the timestamps were 3339, it ran a bunch of working 3339 timestamps and was getting them back from most of the APIs, so it decided this was a standard, read the code on the backend and understood this endpoint was different, and decided on the right fix and implemented it. Didn’t need to ask me for help. That is pretty impressive if you’ve been using copilot.

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

#156

Post by layer8 »

matt_heimer wrote: post #94
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…

LLM are replacing Google for me when coding. When I want to get something implemented, let's say make a REST request in Java using a specific client library, I previously used Google to find example of using that library. Google has gotten worse (or the internet has more garbage) so finding code an example is more difficult than it used to be. Now I ask an LLM for an example. Sometimes I have to ask for a refinement…

In order to use a library, I need to (this is my opinion) be able to reason about the library’s behavior, based on a specification of its interface contract. The LLM may help with coming up with suitable code, but verifying that the application logic is correct with respect to the library’s documented interface contract is still necessary. It’s therefore still a requirement to read and understand the library’s documentation. For example, for the case of a REST client, you need to understand how the possible failure modes of the HTTP protocol and REST API are translated by the library.

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

#157

Post by jpc0 »

hleszek wrote: post #55

I must have been a little too ambitious with my first test with Claude Code. I asked it to refactor a medium-sized Python project to remove duplicated code by using a dependency injection mechanism. That refactor is not really straightforward as it involves multiple files and it should be possible to use different files with different dependencies. Anyway, I explain the problem in a few lines and ask for a plan of wh…

Really yoy nearly got the correct approach there.

I generally follow the same approach these days, ask it to develop a plan then execute but importantly have it excute each step in as small increments as possible and do a proper code review for each step. Ask if for changes you want it to make.

There is certainly times I need to do it myself but definitely this has improved some level of productivity for me.

It's just pretty tedious so I generally write a lot of "fun" code myself, and almost always do the POC myself then have the AI do the "boring" stuff that I know how to do but really don't want to do.

Same with docs, the modern reasoning models are very good at docs and when guided to a decent style can really produce good copy. Honestly R1/4o are the first AI I would actually concider pulling into my workflow since they make less mistakes and actually help more than they harm. They still need to be babysit though as you noticed with Claude.

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

#158

Post by jgalt212 »

That post from Yegge reads like it was written by some foaming at the mouth VC. I am getting decent use from Claude, but mostly as a stack overflow replacement. I will never let it read our company's code base. Then everyone will know how to do what we do. After all, that's why these things are so good at React and not so good at Solid (there's just so much public react code). Also, see the recent "AI IS STIFLING TECH ADOPTION" post

https://vale.rocks/posts/ai-is-stifling-tech-adoption

https://news.ycombinator.com/item?id=43047792

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

#159

Post by dabinat »

barbazoo wrote: post #136
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…

I love the subtle mistakes that get introduced in strings for example that then take me all the time I saved to fix.

Do you have an example of this?

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

#160

Post by bckr »

cglace wrote: post #87
crabl wrote: post #72

Earlier quoted context omitted.

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.

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 plenty of other stuff to do.

And if you automate 99% of the above work?

Then the requirements are going to get 100Xed. Put all the bells and whistles in. Make it break the laws of physics. Make it never ever crash and always give incredibly detailed feedback to the end users. Make it beautiful and faster than thought itself.

I’m not worried about taking myself out of the loop.

Post reply on HN