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

The creator of Claude Code's Claude setup

twitter.com

Post reply on HN
Print view View original

131–140 of 423 posts

Re: The creator of Claude Code's Claude setup

#131

Post by omnicognate »

I tried Claude Code a while back when I decided to give "vibe-coding" a go. That was was actually quite successful, producing a little utility that I use to this day, completely without looking at the code. (Well, I did briefly glance at it after completion and it made my eyeballs melt.) I concluded the value of this to me personally was nowhere near the price I was charged so I didn't continue using it, but I was impressed nonetheless.

This brief use of Claude Code was done mostly on a train using my mobile phone's wi-fi hotspot. Since the connection would be lost whenever the train went through a tunnel, I encountered a bug in Claude Code [1]. The result of it was that whenever the connection dropped and came up again I had to edit an internal json file it used to track the state of its tool use, which had become corrupt.

The issue had been open for months then, and still is. The discussion under it is truly remarkable, and includes this comment from the devs:

> While we are always monitoring instances of this error and and looking to fix them, it's unlikely we will ever completely eliminate it due to how tricky concurrency problems are in general.

Claude Code is, in principle, a simple command-line utility. I am confident that (given the backend and model, ofc) I could implement the functionality of it that I used in (generously!) at most a few thousand lines of python or javascript, I am very confident that I could do so without introducing concurrency bugs and I am extremely confident that I could do it without messing up the design so badly that concurrency issues crop up continually and I have to admit to being powerless to fix them all.

Programming is hard, concurrency problems are tricky and I don't like to cast aspersions on other developers, but we're being told this is the future of programming and we'd better get on board or be left behind and it looks like we're being told this by people who, with presumably unlimited access to all this wonderful tooling, don't appear to be able to write decent software.

[1] https://github.com/anthropics/claude-code/issues/6836

Re: The creator of Claude Code's Claude setup

#132

Post by AtlasBarfed »

tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

Claude is absolutely plastering Facebook with this bullshit.

Every PR Claude makes needs to be reviewed. Every single one. So great! You have 10 instances of Claude doing things. Great! You're still going to need to do 10 reviews.

Re: The creator of Claude Code's Claude setup

#133

Post by eru »

AtlasBarfed wrote: post #132
tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

Claude is absolutely plastering Facebook with this bullshit. Every PR Claude makes needs to be reviewed. Every single one. So great! You have 10 instances of Claude doing things. Great! You're still going to need to do 10 reviews.

That's why you have Codex review the code.

(I'm only half joking. Having one LLM review the PRs of another is actually useful as a first line filter.)

Re: The creator of Claude Code's Claude setup

#134

Post by johnfn »

coldtea wrote: post #123
johnfn wrote: post #47

Earlier quoted context omitted.

I use the VSCode terminal all day every day. No other app I use in it has this issue, including Codex.

OK, so you have the unbearable pain of using a separate terminal app to use the magic thingie that does your programming for you on prompt, and which didn't exist merely 2 years ago. https://www.youtube.com/watch?v=kBLkX2VaQs4

I am a fan of Claude code, I love it, I use it every day. Are you suggesting we’re not allowed to make any critique of anything which has good qualities?

Re: The creator of Claude Code's Claude setup

#135

Post by ukprogrammer »

tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

skill issue

same way a lesser engineer might say they cannot do X or Y

Re: The creator of Claude Code's Claude setup

#136

Post by bonesss »

cyberax wrote: post #53
nmfisher wrote: post #34

Earlier quoted context omitted.

(2) isn't my experience at all. It's not 100% bug free but it definitely seems more stable (and faster) than I when I first used it last year.

Claude Code is fairly simple. But Claude Desktop is a freaking mess, it loses chats when I switch tabs, it has no easy way to auto-extend the context, and it's just slow.

Claude’s iOS app ‘unknown errors’ constantly. I have to copy messages for fear of losing them.

Re: The creator of Claude Code's Claude setup

#137

Post by LorenzoGood »

jauntywundrkind wrote: post #56
TheTaytay wrote: post #26

This was extremely useful to read for many reasons, but my favorite thing I learned is that you can “teleport” a task FROM the local Claude Code to Claude Code on the web by prepending your request with “&”. That makes it a “background” task, which I initially erroneously thought was a local background task. Turns out it sends the task and conversation history up to the web version. This allows you to do work in othe…

OpenCode is actually client server architecture. Typically one either runs the TUI or the web interface. I wonder if it would cope ok with running multiple interfaces at once? Neovim has a decade old feature request for multiple clients to be able to connect to it. No traction alas. Always a great superpower to have, if you can hack it. https://github.com/neovim/neovim/issues/2161 Chrome DevToops Protocol added multi…

> Neovim has a decade old feature request for multiple clients to be able to connect to it. No traction alas. Always a great superpower to have, if you can hack it. https://github.com/neovim/neovim/issues/

I do this to great effect with Emacs daemon mode.

Re: The creator of Claude Code's Claude setup

#138

Post by Deukhoofd »

exitb wrote: post #107
tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

Multiple instances of agents are an equivalent to tabs in other applications - primarily holders of state, rather than means for extreme parallelism.

Personally I just use /resume to switch back to other states when I need to.

Re: The creator of Claude Code's Claude setup

#139

Post by hecanjog »

johnfn wrote: post #38
nmfisher wrote: post #34

Earlier quoted context omitted.

(2) isn't my experience at all. It's not 100% bug free but it definitely seems more stable (and faster) than I when I first used it last year.

The UI flickers rapidly in some cases when I use it in the VSCode terminal. When I first saw this when using Claude Code I imagined it was some vibe code bug that would be worked out quickly. But it's been like 9 months and still every day it has this behavior - to the point that it crashes VSCode! I can only imagine that no one at Anthropic uses VSCode because it really seems insane it's gone this long unfixed.

Same thing happens to me in long enough sessions in xterm. Anecdotally it's pretty much guaranteed if I continue a session close to the point of context compacting, or if the context suddenly expands with some tool call.

Edit: for a while I thought this was by design since it was a very visceral / graphical way to feel that you're hitting the edge of context and should probably end the session.

If I get to the flicker point I generally start a new session. The flicker point always happens though from what I have observed.

Re: The creator of Claude Code's Claude setup

#140

Post by indemnity »

stack_framer wrote: post #43
jedberg wrote: post #30

The funniest part of that whole thing was when someone said "I trusted you, but you use light mode on your terminal" and then he replied that people stop by his desk daily just to make fun of him for it.

I also use light mode in my terminal. Mock me at your leisure. :)

Another convert back to the light from the darkness here.

My eyes are getting old. Black text on white background is more legible/clear.

Post reply on HN