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

161–170 of 388 posts

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

#161

Post by djaychela »

postalcoder wrote: post #159
djaychela wrote: post #155

Can someone offer me some help? I've just been messing about "vibe coding" little python apps with local llm, continue and vscode. And I got so far with it. Then I found the free tier of claude so I fed in the "works so far" version with the changes that the local llm made, and it fixed and updated all the issues (with clear explanation) in one go. Success! So my next level attempt was to get all the spec and prompts…

It's likely you're running into "too deep into mediocre code with unclear interfaces and a lot of hidden assumptions hell" that LLMs are generally poor at handling. If you're running into an inextricable wall then it's better to do a controlled demolition. ie, take everything written by chatgpt and have the highest-quality model you have summarize what the game does, and break down all the features in depth. Then, ta…

Thanks.

I think I should have made it more clear in my post, the code is claude's and was done from scratch (the first app was a mandelbrot viewer which it added features to, this is a platfrom game).

It's a single file at the moment (I did give a suggested project structure with files for each area of responsibility) and it kind-of-works.

I think I could create the missing method in the class but wanted to see if it was possible by getting the tools to do it - it's as much of an experiment in the process and the end result.

Thanks for replying, I shall investigate what you've suggested and see what happens.

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

#162

Post by zer00eyz »

dejavucoder wrote: post #64
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…

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 part…

I spend a fair amount of time tinkering in Home Assistant. My experience with that platform and LLM's can be summed up as "this is amazing".

I also do a fair amount of data shuffling with Golang. My LLM experience there is "mixed".

Then I deal with quite a few "fringe" code bases and problem spaces. There LLM's fall flat past the stuff that is boiler plate.

"I work in construction and use a hammer" could mean framer, roofer or smashing out concrete with a sledge. I suspect that "I am a developer, I write code" plays out in much the same way, and those details dictate experience.

Just based on the volume of ruby and typescript, and the overlap of the output of these platforms your experience is going to be pretty good. I would be curious if you went and did something less mainstream, and in a less common language (say Zig) if you would have the same feelings and feedback that you do now. Based on my own experience I suspect you would not.

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

#163

Post by iammrpayments »

ants_everywhere wrote: post #89
_se wrote: post #44

Earlier quoted context omitted.

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…

> They're amazing. But the moment you try to do the more "serious" work with them, it falls apart rapidly. Sorry, but this is just not true. I'm using agents with a totally idiosyncratic code base of Haskell + Bazel + Flutter. It's a stack that is so quirky and niche that even Google hasn't been able to make it work well despite all their developer talent and years of SWEs pushing for things like Haskell support inte…

I’m going to ask what I’ve asked the last person here who said they are “10-20x” more productive:

If you’re really that more productive, why don’t you quit your job and vibecode 10 ios apps (in your case that would be 50 to 100 proportionally)

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

#164

Post by aniforprez »

quesera wrote: post #97
dontlaugh wrote: post #49

Earlier quoted context omitted.

I still don’t get why I should want that. I’ve mentored and managed juniors. They’re usually a net negative in productivity until they are no longer juniors.

My current working theory is this: People who enjoy mentoring juniors are generally satisfied with the ROI of iterating through LLM code generation. People who find juniors sort-of-frustrating-but-part-of-the-job-sometimes have a higher denominator on that ROI calc, and ask themselves why they would keep banging their head against the LLM wall. The first group is probably wiser and more efficient at multiplying their…

It's the complete opposite for me. I enjoy the process of mentoring juniors and am usually sought out for a lot of little issues like fixing git workflows or questions on how a process works. Working with an LLM is absolutely not what I want to do because I'd much rather mentees actually learn and ask me less and less questions. My experience with AI so far is that it never learns at all and it has never felt to me like a human. It pretends to be contrite and apologises for mistakes but it makes those mistakes anyway. It's the worst kind of junior who repeats the same mistake multiple times and doesn't bother committing those to memory.

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

#165

Post by beoberha »

graphememes wrote: post #87

It's great for me. I have a claude.md at the root of every folder generally, outlined in piped text for minimal context addition about the rulesets for that folder, it always creates tests for what it's doing and is set to do so in a very specific folder in a very specific way otherwise it tries to create debug files instead. I also have set rules for re-use so that way it doesn't proliferate with "enhanced" class va…

What do you consider an “agent stream”? I can’t even imagine the cognitive overhead of managing 60-70 agents let alone the physical ability to churn through them as they complete their work and re-launch them.

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

#166

Post by hamandcheese »

yoyohello13 wrote: post #122
erentz wrote: post #50

There must at this point be lots and lots of actual walkthroughs of people coding using Claude Code, or whatever, and producing real world apps or libraries with them right? Would be neat to have a list because this is what I want to read (or watch), rather than people just continuously telling me all this is amazing but not showing me it’s amazing.

Something really feels off about the whole thing. I use Claude code. I like it, it definitely saves me time reading docs or looking on stack overflow. It’s a phenomenal tool. If we are to believe the hype though, shouldn’t these tools be launching software into the stratosphere? Like the CEO of stripe said AI tools provide a x100 increase in productivity. That was 3-4months ago. Shouldn’t stripe be launching rockets…

I imagine most CEOs are hyped about serving the same shit sandwich for less money, rather than serving up a tastier sandwich.

Or, as another commenter said, it's for investors, not developers, and certainly not the scum users.

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

#167

Post by datpuz »

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 wait til the honeymoon period ends and you actually have to stand behind that slop you didn't realize you were dumping into your codebase.

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

#169

Post by mrheosuper »

erentz wrote: post #50

There must at this point be lots and lots of actual walkthroughs of people coding using Claude Code, or whatever, and producing real world apps or libraries with them right? Would be neat to have a list because this is what I want to read (or watch), rather than people just continuously telling me all this is amazing but not showing me it’s amazing.

IIRC most of the code in Claude is written by it(or some other LLM)

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

#170

Post by crinkly »

hamandcheese wrote: post #168

For me the best part about AI is that when I'm feeling lazy, I can tell the AI to do it. Whether it gives me gold or gives me shit, it doesn't matter, because I have now started my work.

I go for a walk and have a coffee. It feels less intellectually dishonest. Best to solve human problems with human solutions.
Post reply on HN