Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My experience with Claude Code after two weeks of adventures

sankalp.bearblog.dev

Post reply on HN
Print view View original

61–70 of 388 posts

Re: My experience with Claude Code after two weeks of adventures

#61

Post by kypro »

HN has flipped so quickly on saying how AI produces unreliable slop, to most people using it to replace junior devs at their org – something I was heavily criticised for saying orgs should be doing a few months back.

Progress doesn't end here either, imo CC is more a mid-level engineer with a top-tier senior engineer's knowledge. I think we're getting to the point where we can begin to replace the majority of engineers (even seniors) for just a handful of seniors engineers to prompt and review AI produced code and PRs.

Not quite there yet, of course, but definitely feeling that shift starting now... There's going to be huge productivity boosts for tech companies towards the end this year if we can get there.

Exciting times.

Re: My experience with Claude Code after two weeks of adventures

#62

Post by wyldfire »

arealaccount wrote: post #12
iambateman wrote: post #7

Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

I have seen both success and failure. It's definitely cool and I like to think of it as another perspective for when I get stuck or confused.

When it creates a bunch of useless junk I feel free to discard it and either try again with clearer guidelines (or switch to Opus).

Re: My experience with Claude Code after two weeks of adventures

#63

Post by 2sk21 »

deeshee wrote: post #15

It's great to see even the most hardcore developers who are not fond of change being happy with the latest releases related to AI-assisted development. My workflow now boils down to 2 tools really - leap.new to go from 0 to 1 because it also generates the backend code w/ infra + deployment and then I pick it up in Zed/Claude Code and continue working on it.

I'm curious: Do you scrutinize every line of code that's generated?

Re: My experience with Claude Code after two weeks of adventures

#64

Post by dejavucoder »

libraryofbabel wrote: post #58
arealaccount wrote: post #12

Earlier quoted context omitted.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…

Fair point.

For context, I was using Claude Code on a Ruby + Typescript large open source codebase. 50M+ tokens. They had specs and e2e tests so yeah I did have feedback when I was done with a feature - I could run specs and Claude Code could form a loop. I would usually advise it to fix specs one by one. --fail-fast to find errors fast.

Prior to Claude Code, I have been using Cursor for an year or so.

Sonnet is particularly good at NextJS and Typescript stuff. I also ran this on a medium sized Python codebase and some ML related work too (ranging from langchain to Pytorch lol)

I don't do a lot of prompting, just enough to describe my problem clearly. I try my best to identify the relevant context or direct the model to find it fast.

I made new claude.md files.

Re: My experience with Claude Code after two weeks of adventures

#66

Post by state_less »

libraryofbabel wrote: post #58
arealaccount wrote: post #12

Earlier quoted context omitted.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…

Here's a few general observations.

Your LLM (CC) doesn't have your whole codebase in context, so it can run off and make changes without considering that some remote area of the codebase are (subtly?) depending on the part that claude just changed. This can be mitigated to some degree depending on the language and tests in place.

The LLM (CC) might identify a bug in the codebase, fix it, and then figure, "Well, my work here is done." and just leave it as is without considering ramifications or that the same sort of bug might be found elsewhere.

I could go on, but my point is to simply validate the issues people will be having, while also acknowledging those seeing the value of an LLM like CC. It does provides useful work (e.g. large tedious refactors, prototyping, tracking down a variety of bugs, and so on...).

Re: My experience with Claude Code after two weeks of adventures

#67

Post by iambateman »

ivanech wrote: post #57
iambateman wrote: post #7

Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.

Just got it at work today and it’s a dramatic step change beyond Cursor despite using the same foundation models. Very surprising! There was a task a month ago where AI assistance was a big net negative. Did the same thing today w/ Claude Code in 20ish minutes. And for Much less context babysitting too. Claude code is really good at finding the things it needs and adding them to its context. I find Cursor’s agent mod…

Cool! If you're on pro, you can use a _lot_ of claude code without paying for API usage, btw.

Re: My experience with Claude Code after two weeks of adventures

#68

Post by Herring »

_se wrote: post #44
pragmatic wrote: post #13

Earlier quoted context omitted.

Could you elaborate a bit on the tasks,languages,domain etc you’re using it with? People have such widely varying experiences and I’m wondering why.

It's always POC apps in js or python, or very small libraries in other popular languages with good structure from the start. There are ways to make them somewhat better in other cases (automated testing/validation/linting being a big one), but for the type of thing that 95% of developers are doing day to day (working on a big, sprawling code base where none of those attributes apply), it's not close to being there. T…

I like them for refactoring and “explain this massive codebase please”. Basically polishing or investigating things that already work.

But I think we should expect the scope of LLM work to improve rapidly in the next few years.

https://metr.org/blog/2025-03-19-measuring-ai-ability-to-com...

Re: My experience with Claude Code after two weeks of adventures

#70

Post by simonw »

state_less wrote: post #66
libraryofbabel wrote: post #58

Earlier quoted context omitted.

Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…

Here's a few general observations. Your LLM (CC) doesn't have your whole codebase in context, so it can run off and make changes without considering that some remote area of the codebase are (subtly?) depending on the part that claude just changed. This can be mitigated to some degree depending on the language and tests in place. The LLM (CC) might identify a bug in the codebase, fix it, and then figure, "Well, my wo…

Right, which is why having a comprehensive test suite is such an enormous unlock for this class of technology.

If your tests are good, Claude Code can run them and use them to check it hasn't broken any distant existing behavior.

Post reply on HN