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

Claude Code's DX is too good. And that's a problem

bharath.sh

Post reply on HN
Print view View original

31–40 of 97 posts

Re: Claude Code's DX is too good. And that's a problem

#31

Post by koolba »

> What happened next: Claude installed every CLI, prompted me to login once, then went into autopilot. Configured each service. Ran commands. Checked logs. Auto-corrected errors. Got the app running in minutes.

> In another instance, a GitHub workflow was failing. Claude asked if it could SSH into my Hetzner instance to investigate. I said yes. It connected, looked up the config, restarted the Docker instances causing issues, and renewed some certificates as a hygiene step - which I never asked it to do.

This type of thing scares the crap out of me and I’m flabbergasted that anyone wold give an LLM unrestricted shell access to a server.

Re: Claude Code's DX is too good. And that's a problem

#32

Post by jabedude »

koolba wrote: post #31

> What happened next: Claude installed every CLI, prompted me to login once, then went into autopilot. Configured each service. Ran commands. Checked logs. Auto-corrected errors. Got the app running in minutes. > In another instance, a GitHub workflow was failing. Claude asked if it could SSH into my Hetzner instance to investigate. I said yes. It connected, looked up the config, restarted the Docker instances causin…

I've also noticed Claude "running away" and doing a bunch of work I never asked it to do.

Re: Claude Code's DX is too good. And that's a problem

#33

Post by raincole »

tmoravec wrote: post #21

> In a monorepo, just loading the project consumes ~20k tokens I don't work on a monorepo, and as an example, what I would consider a mid-size service in my mid-size company is 7M tokens. I can't but ask: do all people who are so enthusiastic about AI for coding only work on trivial projects?

I'm quite sure "loading the project" isn't putting every single line of code into the context. Probably just a huge CLAUDE.md or something.

Either that or this author is completely out of touch with reality.

Re: Claude Code's DX is too good. And that's a problem

#34

Post by pico303 »

The example in the article of letting Claude deploy the app worries me. It has me thinking of that line, “AI is really good until you know what you’re talking about.” If the author was clueless of how to deploy the app, how do they know the app was deployed safely or securely?

Just this past week I asked Claude for some help with C++ and a library I was somewhat unfamiliar with. What it produced looked great—-if you didn’t know C++ very well. It turned out Claude knew even less about this library than I did, generating tons of code that was completely incorrect. I eventually solve my problem through research and trial and error, and it was nothing like what Claude recommended. It certainly didn’t leave me feeling confident enough to let the LLM have the level of control over my computer or project that the author is allowing it in the article.

I’m not looking forward to a future spending all my time cleaning up the messes LLM’s create.

Re: Claude Code's DX is too good. And that's a problem

#35

Post by salomonk_mur »

ltbarcly3 wrote: post #15

"With Opus 4.5, Claude Code feels like having a god-level engineer beside you." Well, not to me or the people I respect. It's getting very good, but it's like having a recent college grad who obsessively reads documentation. Someone with low skill but very high knowledge, often knowledge they are mixing up or not quite getting right. I think if Claude is already 'better' at coding than you, maybe think about going ba…

I had it One-shot the full architecture for a fairly advanced distributed system for a client. It then one shot the actual code design (following absolutely all our our internal requirements on auth, stack to use, security, code styling, documentation, etc). It then one shot (and we code reviewed everything thoroughly) each of the 5 micro services needed.

It one shot the infrastructure to use and created the terraform file to put it up anywhere. It deployed it.

It caught some of the errors it had made by itself after load-testing, and corrected them. It created the load test itself (following patterns from previews projects we had).

It did all of this in a week. With human supervision on each step, but in a fucking week. We gave it all the context it needed and one-shotted everything.

It is more than god-level. If you are not getting these increases in productivity, you are using it wrong.

Re: Claude Code's DX is too good. And that's a problem

#36

Post by ltbarcly3 »

GiorgioG wrote: post #11

If only LLMs didn’t just make shit up regularly.

They both make stuff up and make very obvious mis-interpretations of evidence. If you take the output of an LLM, and ask another LLM to check it, this dramatically reduces this. Even if you do it with the same LLM but without the existing context. I was able to write a detailed analysis of a rule system by doing this with 3 steps, claude -> chatgpt -> gemini3. It caught all the mistakes, including overstatements and vague statements. It wasn't perfect, but even after one review the # of mistakes or stupid statements was almost 0.

Re: Claude Code's DX is too good. And that's a problem

#37

Post by esafak »

fluidcruft wrote: post #3

I sort of agree with this about cognitive load. I'm somewhat new (started dipping my toes around July) but use Claude code heavily now. I did spend a lot of time playing with configuring it at first and creating agents etc. But I have a weird setup where I have three computers that I work on and at one point I realized vanilla Claude Code had adopted the things I was doing as defaults (and improved on them). So I hav…

If you haven't grokked MCP yet don't bother now; it's on the way out. Instead do learn to write an AGENT.md file (create a CLAUDE.md file to point to it) then list all the tools you have at its disposal. It will probably know how to use them; it just needs to be told what's available.

Re: Claude Code's DX is too good. And that's a problem

#38

Post by Lx1oG-AWb6h_ZG0 »

lnbharath wrote: post #24
fluidcruft wrote: post #3

I sort of agree with this about cognitive load. I'm somewhat new (started dipping my toes around July) but use Claude code heavily now. I did spend a lot of time playing with configuring it at first and creating agents etc. But I have a weird setup where I have three computers that I work on and at one point I realized vanilla Claude Code had adopted the things I was doing as defaults (and improved on them). So I hav…

I definitely relate with your sentiment and I like your term "configuration bankruptcy" on MCP, the mental model that clicked for me is "giving claude access to tools it can call" so that instead of copy pasting from your database or API, claude can just... query it playwright MCP for me is godsend

I thought skills were supposed to help with “giving claude access to tools it can call”. When would one use MCP over skills?

Re: Claude Code's DX is too good. And that's a problem

#39

Post by ltbarcly3 »

dawnerd wrote: post #20
ltbarcly3 wrote: post #15

"With Opus 4.5, Claude Code feels like having a god-level engineer beside you." Well, not to me or the people I respect. It's getting very good, but it's like having a recent college grad who obsessively reads documentation. Someone with low skill but very high knowledge, often knowledge they are mixing up or not quite getting right. I think if Claude is already 'better' at coding than you, maybe think about going ba…

Yet when I try it, it feels like a developer fresh out of a coding bootcamp with no real experience. There’s no real reasoning, problem solving is still brute forced. It still rewrites rather than modifies. The context is way too limiting and it gets lost in its own “thinking”

The problem solving is very very not brute force. I have seen it make detailed analysis. Often if a problem stumps me it also stumps Claude, no surprise there. But if I give it a ticket I haven't looked at yet, it is often able to find the exact problem via careful 'reasoning' and fix it in 1/100th the time it would take me.

Re: Claude Code's DX is too good. And that's a problem

#40

Post by konart »

skydhash wrote: post #18

> With Opus 4.5, Claude Code feels like having a god-level engineer beside you. Opinionated but friendly. Zero ego. > Claude was halfway through refactoring a complex auth flow[...] Then I realized: I'd forgotten to mention that one of those files was also used by a cron job. That is the kind of research you do before you go to refactoring. > Claude Code freed them from "the anxiety of the first step in programming c…

>Is there a first step in programming? If there is, that would be thinking

I'd argue that a first step (regardless of field) is either a necessity or curiosity.

Thinking comes later. (And to be honest I can't really think of it as a "step", simply because this is a process).

Post reply on HN