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

341–350 of 388 posts

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

#341

Post by beyang »

Wowfunhappy wrote: post #254
nico wrote: post #243

Earlier quoted context omitted.

I used to feel similarly. But recently started using Claude Code and it does feel a lot better than Cursor for me I'm not sure why. However, Claude does seem to know better where things are and knows not to make unnecessary changes. I still need to guide it and tell it to do things differently some times, but it feels like it's a lot more effective Personally, I also like that usually it just presents to me only one…

> Personally, I also like that usually it just presents to me only one change/file at a time, so it's easier for me to review This is interesting. I haven't used Cursor, but one of my frustrations with Claude Code is that some of the individual changes it asks me to approve are too small for me to make a decision. There are cases where I almost denied a change initially, then realized Claude's approach made sense onc…

If you like Claude Code but either (1) prefer an agent that doesn't ask for review on each file edit or (2) miss the IDE for things like reviewing diffs, I'd humbly submit you try out Amp: https://ampcode.com. It has both a CLI and VS Code extension, and we built it from the ground up for agentic coding, so no asking for permission on each edit, a first-class editor extension (personally I spend more and more time reviewing diffs and VS Code's diff view is great), and it employs subagents for codebase search and extended thinking (using a combo of Sonnet and o3) to maximize use of the context window.

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

#342

Post by NewUser76312 »

I'm still not sold on these "AIs in your codebase" tools. Same for 'vibe coding'.

I use AI like a scalpel - I go in and figure out exactly what I want, use my prompting experience to get a few functions, or up to 1 script at a time, read it, put it in, and stress-test it immediately.

As a result, I am extremely happy with my AI-generated code about 95% of the time. However, this requires that I still understand my codebase, requirements, failure modes, etc.

My philosophy is that software dev creation speed is certainly important, but durability is even more critical. Currently, it seems like going too deep with these AI tools is sacrificing the former for the latter. If all you're doing is POCs all day I could see it (even then, don't let them get too big...) but it's just not for me, at least not yet.

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

#343

Post by ookblah »

jimbokun wrote: post #339
ookblah wrote: post #129

Earlier quoted context omitted.

i mean i get it, but at some point you have to either assume everyone is lying or we are all bots or something. it's probably the same feeling i get when i read someone having trouble and my first thought is like "they aren't using it right". i'm sure the reverse is something like "they aren't a real programmer" LOL.

It's much simpler than that. Without concrete details about the exact steps you're taking, these conversations are heat without light.

and without concrete details about the exact steps you're taking to fail these conversations are heat without light. see how that works?

nobody can be bothered to show how these coding llms fall flat on their face apparently with their own real detailed examples and people can't be bothered to setup some detailed youtube video with all source code because in the end i'm not trying that hard to convince people to use tools they don't want to use.

i think with all the comments maybe the more people who stumble through this the better. the cloudflare example is a decent starting point and i've already given you the general approach. i'm fine with that being a copout lol.

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

#344

Post by _sharp »

NewUser76312 wrote: post #342

I'm still not sold on these "AIs in your codebase" tools. Same for 'vibe coding'. I use AI like a scalpel - I go in and figure out exactly what I want, use my prompting experience to get a few functions, or up to 1 script at a time, read it, put it in, and stress-test it immediately. As a result, I am extremely happy with my AI-generated code about 95% of the time. However, this requires that I still understand my co…

You should consider documenting your durability requirements, failure modes, important context related to the feature/component your working on, as you would a junior engineer. Then, you can re-use the context documents. If the AI doesn't know what your expectations are, it will just assume you need a PoC, and give you PoC code quality.

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

#345

Post by applied_heat »

crinkly wrote: post #193
jasoncartwright wrote: post #191

Earlier quoted context omitted.

I enjoy the idea that when programming before AI I wasn't 'merely a machine operator'

I did most of my programming and thinking on paper before I committed to the machine. I still do today.

What is the niche?

I do control systems that have to work first try and after running the plant through its paces I’m out the door never to return

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

#346

Post by nico »

beyang wrote: post #341
Wowfunhappy wrote: post #254

Earlier quoted context omitted.

> Personally, I also like that usually it just presents to me only one change/file at a time, so it's easier for me to review This is interesting. I haven't used Cursor, but one of my frustrations with Claude Code is that some of the individual changes it asks me to approve are too small for me to make a decision. There are cases where I almost denied a change initially, then realized Claude's approach made sense onc…

If you like Claude Code but either (1) prefer an agent that doesn't ask for review on each file edit or (2) miss the IDE for things like reviewing diffs, I'd humbly submit you try out Amp: https://ampcode.com . It has both a CLI and VS Code extension, and we built it from the ground up for agentic coding, so no asking for permission on each edit, a first-class editor extension (personally I spend more and more time r…

Thank you for the suggestion. Do you guys also have subscription plans? Or do I need to pay separately for the models/apis I use?

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

#347

Post by ModernMech »

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 thought this as well, but I just got burned in a way that caused me to lose so much time: I was feeling lazy and allowed AI to write some code for me. It looked good and compiled so I committed and pushed it. Weeks later I experienced a crash that I couldn't pinpoint. After hours of debugging, I eventually realized the culprit was that bit of code created by AI from weeks ago; it used a function that was defined in my code in a way that wasn't intended, causing a panic sometimes and weird off-by-one errors other times. The offending function was only a few lines of code. Had I not been lazy and just took 10 minutes to write it, I would have saved myself a whole afternoon of frustrating debugging.

Lesson learned: being lazy with AI has a hidden cost.

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

#348

Post by williamsss »

As a daily active user of Cursor and CC user myself, it’s gratifying to discover nuanced tricks that push productivity further. I stumble upon one every now and again.

Solid write up. And chock full of useful tricks!

I was manually copy pasting PR change requests today to CC where some of this would have saved my wrists some pain.

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

#349

Post by jimbokun »

ookblah wrote: post #343
jimbokun wrote: post #339

Earlier quoted context omitted.

It's much simpler than that. Without concrete details about the exact steps you're taking, these conversations are heat without light.

and without concrete details about the exact steps you're taking to fail these conversations are heat without light. see how that works? nobody can be bothered to show how these coding llms fall flat on their face apparently with their own real detailed examples and people can't be bothered to setup some detailed youtube video with all source code because in the end i'm not trying that hard to convince people to use…

> and without concrete details about the exact steps you're taking to fail these conversations are heat without light.

Of course.

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

#350

Post by oblio »

swader999 wrote: post #265
ianberdin wrote: post #244

Earlier quoted context omitted.

And so you don’t think I just dropped in to try it out: no, I’ve been using Cursor every day for many months. I set up the rules very precisely, make maps, write instructions and constraints so the LLM understands how to work with the current codebase—where to find things, what to do, what not to do, what things should look like. I try to write as concisely as possible so everything fits in the context window. I have…

I remember a few projects before all the AI where I would setup templates, little code generators, patterns to follow. Just make it really easy to do the right things. Was so easy to get things done. Was a small team, like minded, easy to row in the same direction. Your post reminded me of that. I too notice this about Claude, I've written commands, massaged Claude.md, even hooks. Given it very precise feature guides…

> My highest velocity was about 1.6 fib complexity points a day over thirty years, now it's 4.3 with Claude the last three weeks which is nuts.

Where do you work that you managed to track what I assume are Agile story points over 30 years, also, so accurately?

I don't even remember my median number for a sprint, let alone my daily average over long periods of time.

Post reply on HN