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

What makes Claude Code so damn good

minusx.ai

Post reply on HN
Print view View original

131–140 of 322 posts

Re: What makes Claude Code so damn good

#131

Post by yumraj »

imiric wrote: post #100
yumraj wrote: post #74

I made insane progress with CC over last several weeks, but lately have noticed progress stalling. I’m in the middle of some refactoring/bug fixing/optimization but it’s constantly running into issues, making half baked changes, not able to fix regressions etc. Still trying to figure out how to make do a better job. Might have to break it into smaller chunks or something. Been pretty frustrating couple of weeks. If a…

> If anyone has pointers, I’m all ears!! Give programming a try, you might like it.

Yeah, have been doing that for 30 years.

Next…

Re: What makes Claude Code so damn good

#132

Post by BeetleB »

foobarbecue wrote: post #123
BeetleB wrote: post #122

Earlier quoted context omitted.

Hmm... It may be the size of the changes you're asking for. I tend to micromanage it. I don't know your algorithm, but if it's complex enough, I may have done 4 separate prompts - one for each step.

Isn't it easier to just write the code???

Depends on the algorithm. When you've been coding for a few decades, you really, really don't want to write yet another trivial algorithm you've written multiple tens of times in your life. There's no joy in it.

Let the LLM do the boring stuff, and focus on writing the fun stuff.

Also, setting up logging in Python is never fun.

Re: What makes Claude Code so damn good

#133

Post by Herring »

_ea1k wrote: post #23
alex1138 wrote: post #5

What do people think of Google's Gemini (Pro?) compared to Claude for code? I really like a lot of what Google produces, but they can't seem to keep a product that they don't shut down and they can be pretty ham-fisted, both with corporate control (Chrome and corrupt practices) and censorship

For the web ui (chat)? I actually really like gemini 2.5 pro. For the command line tool (claude code vs gemini code)? It isn't even close. Gemini code was useless. Claude code was mostly just slow.

Yeah I was also getting much better results on the Gemini web ui compared to the Gemini terminal. Haven't gotten to Claude yet.

Re: What makes Claude Code so damn good

#134

Post by pawelduda »

ta12653421 wrote: post #89
ta12653421 wrote: post #19

Earlier quoted context omitted.

Productivity boost is unbelieveable! If you handle it right, its a boon - its like having 3 junior devs at hand. And I'm talking about using the web interface. I guess most people are not paying and cant therefore apply the project-space (which is one of the best features), which unleashes its full magic. Even if I'm currently without a job, I'm still paying because it helps me.

LOL why do I get downvoted for explaining my experience? :-D

Because you posted a success story about LLM usage on HN

Re: What makes Claude Code so damn good

#135

Post by conception »

rolls-reus wrote: post #111
conception wrote: post #85

Ive seen context forge has a way to use hooks to keep CC going after context condensing. Are there any other patterns or tools people are using with CC to keep it on task, with current context until it has a validated completion of its task? I feel like we have all these tools separately but nothing brings it all together and also isn’t crazy buggy.

What’s context forge?

https://github.com/webdevtodayjason/context-forge

Re: What makes Claude Code so damn good

#136

Post by conception »

kroaton wrote: post #107
conception wrote: post #85

Ive seen context forge has a way to use hooks to keep CC going after context condensing. Are there any other patterns or tools people are using with CC to keep it on task, with current context until it has a validated completion of its task? I feel like we have all these tools separately but nothing brings it all together and also isn’t crazy buggy.

Load up the context with your information + task list (broken down into phases). Have Sonnet implement phase one tasks and mark phase 1 as done. Go into planning mode, have Opus review the work (you should ideally also review it at this point). Double press escape and go back to the point in the conversation where you loaded up the context with your information + task list. Tell it to do phase 2. Repeat until you run…

Yes, i can manage CC through a task list but there’s nothing technically stopping all your steps from happening automatically. That tool just doesn’t exist yet as far as I can tell but it’s not a very advanced tool to build. I’m surprised no one has put those steps together.

Also if the task runs out of context it will get progressively worse rather than refresh its own context from time to time.

Re: What makes Claude Code so damn good

#137

Post by koakuma-chan »

throwaway314155 wrote: post #129
koakuma-chan wrote: post #110

Earlier quoted context omitted.

https://github.com/dnakov/claude-code :trollface:

That's been DMCA'd since you posted it. Happen to know where I can find a fork?

> That's been DMCA'd since you posted it.

I know, thus the :trollface:

> Happen to know where I can find a fork?

I don't know where you can find a fork, but even if there is a fork somewhere that's still alive, which is unlikely, it would be for a really old version of Claude Code. You would probably be better off reverse engineering the minified JavaScript or whatever that ships with the latest Claude Code.

Re: What makes Claude Code so damn good

#138

Post by nuwandavek »

ahmedhawas123 wrote: post #104

Thanks for sharing this. At a time where this is a rush towards multi-agent systems, this is helpful to see how an LLM-first organization is going after it. Lots of the design aspects here are things I experiment with day to day so it's good to see others use it as well A few takeaways for me from this (1) Long prompts are good - and don't forget basic things like explaining in the prompt what the tool is, how to hel…

(author of the blogpost here) Yeah, you can extract a LOT of performance from the basics and don't have to do any complicated setup for ~99% of use cases. Keep the loop simple, have clear tools (it is ok if tools overlap in function). Clarity and simplicity >>> everything else.

Re: What makes Claude Code so damn good

#139

Post by upcoming-sesame »

_ea1k wrote: post #23
alex1138 wrote: post #5

What do people think of Google's Gemini (Pro?) compared to Claude for code? I really like a lot of what Google produces, but they can't seem to keep a product that they don't shut down and they can be pretty ham-fisted, both with corporate control (Chrome and corrupt practices) and censorship

For the web ui (chat)? I actually really like gemini 2.5 pro. For the command line tool (claude code vs gemini code)? It isn't even close. Gemini code was useless. Claude code was mostly just slow.

You mean Gemini CLI. Yeah it's confusing

Re: What makes Claude Code so damn good

#140

Post by nuwandavek »

dingnuts wrote: post #4

[flagged]

(blogpost author here) You're right! I did make the distinction in an earlier draft, but decided to use "RAG" interchangeably with vector search, as it is popularly known today in code-gen systems. I'd probably go back to the previous version too.

But I do think there is a qualitative different between getting candidates and adding them to context before generating (retrieval augmented generation) vs the LLM searching for context till it is satisfied.

Post reply on HN