What Makes Claude Code So Damn Good

The idea here is: if you have a substantive point, make it thoughtfully. If not, please don't comment until you do.

https://news.ycombinator.com/newsguidelines.html

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.

My tactic is to work with Gemini to build a dense summary of the project and create a high level plan of action, then take that to gpt5 and have it try to improve the plan, and convert it to a hyper detailed workflow xml document laying out all the steps to implement the plan, which I then hand to claude.

This avoids pretty much all of Claude's unplanned bumbling.

That's been my experience, anyway. Maybe it hates me? I sure hate it.

I think Claude is much more predictable and follows instructions better- the todo list it manages seems very helpful in this respect.

(I don’t use any clients that answer coding questions by using the context of my repos).

It’s not consistent, though. I haven’t figured out what they are but it feels like there are circumstances where it’s more prone to doing ugly hacky things.

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.

(Not disagreeing, but most of these comments -- on both sides -- are pretty vague.)

If people are getting faster responses than this regularly, it could account for a large amount of the difference in experiences.

Despite the persistent memes here and elsewhere, it doesn't depend very much on the particular tool you use (with the exception of model choice), how you hold it, or your experience prompting (beyond a bare minimum of competence). People who jump into any conversation with "use tool X" or "you just don't understand how to prompt" are the noise floor of any conversation about AI-assisted coding. Folks might as well be talking about Santeria.

Even for projects that I initiate with LLM support, I find that the usefulness of the tool declines quickly as the codebase increases in size. The iron law of the context window rules everything.

Edit: one thing I'll add, which I only recently realized exists (perhaps stupidly) is that there is a population of people who are willing to prompt expensive LLMs dozens of times to get a single working output. This approach seems to me to be roughly equivalent to pulling the lever on a slot machine, or blindly copy-pasting from Stack Overflow, and is not what I am talking about. I am talking about the tradeoffs involved in using LLMs as an assistant for human-guided programming.

https://jj-vcs.github.io/jj/

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, it can take less work to just write what you want than convince an LLM to do it.

Third, some people are more sensitive to the kind of errors or style that LLMs tend to use. I frequently can't stand the output of LLMs, even if it technically works; it doesn't live to to my personal standards.

The thing is, a lot of the code that people write is cookie-cutter stuff. Possibly the entirety of frontend development. It's not copy-paste per se, but it is porting and adapting common patterns on differently-shaped data. It's pseudo-copy-paste, and of course AI's going to be good at it, this is its whole schtick. But it's not, like, interesting coding.

I get lost a bit at things like this, from the link. The lessons in the article match my experience with LLMs and tools around them (see also: RAG is a pain in the ass and vector embedding similarity is very far from a magic bullet), but the takeaway - write really good prompts instead of writing code - doesn't ring true.

If I need to write out all the decision points and steps of the change I'm going to make, why am I not just doing it myself?

Especially when I have an editor that can do a lot of automated changes faster/safer than grep-based text-first tooling? If I know the language the syntax isn't an issue; if I don't know the language it's harder to trust the output of the model. (And if I 90% know the language but have some questions, I use an LLM to plow through the lines I used to have to go to Google for - which is a speedup, but a single-digit-percentage one.)

My experience is that the tools fall down pretty quickly because I keep trying to make them to let me skip the details of every single task. That's how I work with real human coworkers. And then something goes sideways. When I try to pseudocode the full flow vs actually writing the code I lose the speed advantage, and often end up with a nasty 80%-there-but-I-don't-really-know-how-to-fix-the-other-20%-without-breaking-the-80% situation because I noticed a case I didn't explicitly talk about that it guessed wrong on. So then it's either slow and tedious or `git reset` and try again.

(99% of these issues go away when doing greenfield tooling or scripts for operations or prototyping, which is what the vast majority of compelling "wow" examples I've seen have been, but only applies to my day job sometimes.)

But the situation is very different if you’re coding slop in the first place (front end stuff, small repo simple code). The LLMs can churn that slop out at a rapid clip.

A lot of programmers work on maintaining huge monolith codebases, built on top of 10-years old tech using obscure proprietary dependencies. Usually they dont have most of the code to begin with and APIs are often not well documented.

If I only ever wrote small Python scripts, did small to medium JavaScript front end or full stack websites, or a number of other generic tasks where LLMs are well trained I’d probably have a different opinion.

Drop into one of my non-generic Rust codebases that does something complex and I could spent hours trying to keep the LLM moving in the right direction and away from all of the dead ends and thought loops.

It really depends on what you’re using them for.

That said, there are a lot of commenters who haven’t spent more than a few hours playing with LLMs and see every LLM misstep as confirmation of their preconceived ideas that they’re entirely useless.

Everytime I tried LLMs, I had the feeling of talking with a ignorant trying to sound VERY CLEVER: terrible mistakes at every line, surrounded with punchlines, rocket emojis and tons of bullshit. (I'm partly kidding).

Maybe there are situations where LLMs are useful e.g. if you can properly delimit and isolate your problem; but when you have to write code that is meant to mess up with the internal of some piece of software then it doesn't do well.

It would be nice to know from each part of the "happy users" and "mecontent usere" of LLMs in what context they experimented with it to be more informed on this question.

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.

With a subscription plan, Anthropic is highly incentivized to be efficient in their loops beyond just making it a better experience for users.

It makes me think that the language/platform/architecture that is "most known" by LLMs will soon be the preferred -- sort of a homogenization of technologies by LLM usage. Because if you can be 10x as successfully vibey in, say, nodejs versus elixir or go -- well, why would you opt for those in a greenfield project at all? Particularly if you aren't a tech shop and that choice allows you to use junior coders as if they were midlevel or senior.

Config files should be mature programming languages, not Yaml/Json files.

This is essential to productivity for humans and LLMs alike. The more reliable your edit/test loop, the better your results will be. It doesn't matter if it's compiling code, validating yaml, or anything else.

To your broader question. People have been trying to crack the low-code nut for ages. I don't think it's solvable. Either you make something overly restrictive, or you are inventing a very bad programming language which is doomed to fail because professional coders will never use it.

Overall, it has been working pretty well. I did make a tweak I haven't pushed yet to make it always writes the outline to a file first (instead of just terminal). And I've also started adding slash commands to the instructions so I can type things like "/create some flow" and then just "/refresh" (instead of "pardon me, would you mind refreshing that flow now?").

https://github.com/pglevy/breadboarding-kit

Then add a grader step to your agentic loop that is triggered after the files are modified. Give feedback to the model if there any errors and it will fix them.

Raw code. Use case was configuring a mapping of health data JSON from heterogeneous sources to a standard (also JSON) format. Initial prototype was a YAML DSL, based on the same theory as yours. LLMs had difficulty using the DSL’s semantics correctly, or even getting its syntax (not YAML-level syntax, but the schema: nesting levels for different constructs, and so on). It’s possible that better error loops or something would have cracked it, but a second prototype generating jq worked so much better out of the box that we basically never looked back.

You can see the system prompts too.

It's all how the base model has been trained to break tasks into discrete steps and work through them patiently, with some robustness to failure cases.

I've now gone back to just using vanilla CC with a really really rich claude.md file.

I run into bugs which are not documented in documentation or anywhere except github issues.

Is it legal to search github issues using LLM? if yes how?