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

251–260 of 322 posts

Re: What makes Claude Code so damn good

#251

Post by FergusArgyll »

dang wrote: post #152
dingnuts wrote: post #8

Earlier quoted context omitted.

I appreciate the vague negative takes on tools like this where it feels like there is so much hype it's impossible to have a different opinion. "It's bad" is perfectly substantiative in my opinion; this person tried it, didn't like it, and doesn't have much more to say because of that, but it's still a useful perspective. Is this why HN is so dang pro-AI? the negative comments, even small ones, are moderated away? ex…

HN is by no means "pro-AI". It's sharply divided, and (as always with these things) each side assumes the other side is dominant.

"After viewing identical samples of major network television coverage of the Beirut massacre, both pro-Israeli and pro-Arab partisans rated these programs, and those responsible for them, as being biased against their side."

https://users.ssc.wisc.edu/~jpiliavi/965/hwang.pdf

Re: What makes Claude Code so damn good

#252

Post by dtagames »

brokegrammer wrote: post #205

I don't get it. The title says "What makes Claude Code so damn good", which implies that they will show how Claude Code is better than other tools, or just better in general. But they go about repeating the Claude Code documentation using different wording. Am I missing something here? Or is this just Anthropic shilling?

The difference between Claude Code and Cursor is that one is a command line tool and the other an IDE. You can use Claude models in both and all these techniques can be applied with Cursor and its rules, too.

It's Coke vs. Pepsi.

Re: What makes Claude Code so damn good

#253

Post by phyzome »

Uehreka wrote: post #94
lambda wrote: post #70

Earlier quoted context omitted.

It can be more than one reason. First of all, keep in mind that research has shown that people generally overestimate the productivity gains of LLM coding assistance. Even when using a coding assistant makes them less productive, they feel like they are more productive. Second, yeah, experience matters, both with programming and LLM coding assistants. The better you are, the less helpful the coding assistant will be,…

> research has shown that people generally overestimate the productivity gains of LLM coding assistance. I don’t think this research is fully baked. I don’t see a story in these results that aligns with my experience and makes me think “yeah, that actually is what I’m doing”. I get that at this point I’m supposed to go “the effect is so subtle that even I don’t notice it!” But experience tells me that’s not normally…

I mean, you're one person (so it doesn't have to match) and you're not carefully measuring everything (so you don't have a basis for comparison).

Re: What makes Claude Code so damn good

#254

Post by poniko »

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

Pretty much every time Claude code is stuck or more or less just coding in circles i use Gemini PRO to analyze the code/data and feed the response into Claude to solve it. I also have much more success with Gemini when creating big sql transforming scripts or similar. Both are quite bad on bigger tasks, they get you 60% and then i spend days and days to trying to get to 100% .. its such a time sink when i select the wrong task for the llm.

Re: What makes Claude Code so damn good

#255

Post by phyzome »

apwell23 wrote: post #83
on_the_train wrote: post #72

The lengths people will go through to avoid to code is astonishing

writing code is not the fun part of coding. I only realized that after using claude code.

Well, I suppose we might have found one of the discriminators in why some people love LLMs and some hate them...

Re: What makes Claude Code so damn good

#256

Post by rob_c »

Context window length with further fine tuning and a good system prompt... Nothing too much different other than anthro correctly banked on larger context windows (and stability with training/eval) is the key to massive improvements.

Re: What makes Claude Code so damn good

#257

Post by afarah1 »

paool wrote: post #188
OtherShrezzing wrote: post #25

I think it’s just that the base model is good at real world coding tasks - as opposed to the types of coding tasks in the common benchmarks. If you use GitHub Copilot - which has its own system level prompts - you can hotswap between models, and Claude outperforms OpenAI’s and Google’s models by such a large margin that the others are functionally useless in comparison.

It's not just the base model Try using opus with cline in vs code. Then use Claude code. I don't know the best way to quantify the differences, but I know I get more done in CC.

But is it a game changer vs CoPilot in Agent mode with Claude 4 Sonnet?

Because it's twice the price and doesn't even have a trial.

I feel like if it were a game changer, like Cursor once was vs Ask mode with GPT, it would be worth it, but CoPilot has come a long way and the only up-to-date comparisons I've read point to it being marginally better or the same, but twice the price.

Re: What makes Claude Code so damn good

#258

Post by mnvrth »

badestrand wrote: post #185
OtherShrezzing wrote: post #25

I think it’s just that the base model is good at real world coding tasks - as opposed to the types of coding tasks in the common benchmarks. If you use GitHub Copilot - which has its own system level prompts - you can hotswap between models, and Claude outperforms OpenAI’s and Google’s models by such a large margin that the others are functionally useless in comparison.

I read all the praise about Claude Code, tried it for a month and was very disappointed. For me it doesn't work any better than Cursor's sidebar and has worse UX on top. I wonder if I am doing something wrong because it just makes lots of stupid mistakes when coding for me, in two different code bases.

I'll suggest giving it another shot. It really is a game changer (I can't tell what you're doing wrong, but in a few people I've seen it has been about doing a psychological switch. I wrote about it a bit here - https://mnvr.in/beginners-mind, sharing in case it helps you see how you might approach it differently)

Re: What makes Claude Code so damn good

#259

Post by SpaceNoodled »

dotancohen wrote: post #250
slimebot80 wrote: post #249

Earlier quoted context omitted.

Nowhere in the title does it compare to other tools? Just that's it's damn good.

The phrase "so damn good" implies a benchmark, which itself is implied to be the average of comparable tools. Without these premises, one could state that the 1996 Yugo was so damn good. I mean, it was better than a horse.

I dunno, horses are pretty great.

Re: What makes Claude Code so damn good

#260

Post by SpaceNoodled »

sdsd wrote: post #33

Oof, this comes at a hard moment in my Claude Code usage. I'm trying to have it help me debug some Elastic issues on Security Onion but after a few minutes it spits out a zillion lines of obfuscated JS and says: Error: kill EPERM at process.kill (node:internal/process/per_thread:226:13) at Ba2 (file:///usr/local/lib/node_modules/@anthropic-ai/claude-code/cli.js:506:19791) at file:///usr/local/lib/node_modules/@anthro…

Looks like you're better off.
Post reply on HN