Live data from Hacker News

The creator of Claude Code's Claude setup

twitter.com

161–170 of 423 posts

Re: The creator of Claude Code's Claude setup

#161

Earlier quoted context omitted.

Where is Claude's checkout? Do you have them all share the same local files or does each use its own copy?

People are doing this lots of different ways. Some run it in its own containers or in instances on the web. Some are using git worktrees. I use a worktree for anything large, but smaller stuff is just done in the local files. Sloppy? Perhaps, but Claude has never made such a big mess that it has needed its work wiped.

> Sloppy? Perhaps, but Claude has never made such a big mess that it has needed its work wiped.

I think a key thing to point out to people here is that Claude's built in editing tools won't generally allow it to write to a file that has changed since last time it read it, so if it tries to write and gets an error it will tend to re-read the file, adjust its changes accordingly before trying again. I don't know how foolproof those tests are, because Claude can get creative with sed and cat to edit files, and of course if a change crosses file boundaries this might not avoid broken changes entirely. But generally - as you said - it seems good at avoiding big messes.

Re: The creator of Claude Code's Claude setup

#162
post #53

Earlier quoted context omitted.

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.

Yeah same. Also it completely freezes on my iPhone with sufficient code highlighting. It becomes completely unusable until I restart the App, and then breaks once a new message is sent.

Re: The creator of Claude Code's Claude setup

#163
post #145

Earlier quoted context omitted.

dark mode is easier on battery for OLEDs but not on LCDs where black needs the pixel to be fully active (white is off, black is on). black on white is easier to read than white on black full stop, no astigmatism necessary. https://esa.org/communication-engagement/2018/08/03/resource... ambient lightning is highly recommended to not strain your vision.

The link you shared literally says neither is better and it depends on the person.

like "Also, in every color combination surveyed, the darker text on a lighter background was rated more readable than its inverse (e.g. blue text on white background ranked higher then white text on blue background)"?

yes it's all preference, vision is subjective, but being surprised that dark mode isn't best is in this context... weird.

Re: The creator of Claude Code's Claude setup

#164
Ao this guy is personally responsible for the RAM shortage, it seems. Jokes aside, i have a similar setup, but with a mix of claude and a local model. Claude can access the local model for simple and repetitive tasks, and it actually does a good job on testing UI. Great way to save tokens.

Re: The creator of Claude Code's Claude setup

#165
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…

I hope self-promotion isn't frowned upon, but I've been spending the past months figuring out a workflow [1] that helps tackle the "more complicated problems" and ensure long-term maintainability of projects when done purely through Claude Code. Effectively, I try to: - Do not allow the LLM to make any implicit decisions, but instead confirm with the user. - Ensure code is written in such a way that it's easy to unde…

> Ensure code is written in such a way that it's easy to understand for LLMs

Over the summer last year, I had the AI (Gemini Pro 2.5) write base libraries from scratch that area easy for itself to write code against. Now GPro3 can one-shot (with, at most, a single debug loop at the REPL) 100% of the normal code I need developed (back office/business-type code).

Huge productivity booster, there are a few things that are very easy for humans to do that AI struggles with. By removing them, the AI has been just fantastic to work with.

Re: The creator of Claude Code's Claude setup

#166
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…

> I need 1 agent that successfully solves the most important problem. If you only have that one problem, that is a reasonable criticism, but you may have 10 different problems and want to focus on the important one while the smaller stuff is AIed away. > I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I am generally happy with the assumpti…

Exactly. And if that problem is complex, your first step should be to plan how to sub-divide it anyway. So just ask Claude to map out interdependencies for tasks to look for opportunities to paralellise.

Re: The creator of Claude Code's Claude setup

#168
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…

I hope self-promotion isn't frowned upon, but I've been spending the past months figuring out a workflow [1] that helps tackle the "more complicated problems" and ensure long-term maintainability of projects when done purely through Claude Code. Effectively, I try to: - Do not allow the LLM to make any implicit decisions, but instead confirm with the user. - Ensure code is written in such a way that it's easy to unde…

> Ensure code is written in such a way that it's easy to understand for LLMs;

> Capture all "invisible knowledge" around decisions and architecture that's difficult to infer from code alone.

I work on projects where people love to create all sorts of complex abstractions but also hate writing ADRs (so they don’t) or often any sorts of comments and when they do they’re not very well written. Like the expectation is that you should call and ask the person who wrote something or have a multi-hour meeting where you make decisions and write nothing down.

That sort of environment is only conductive to manual work, dear reader, avoid those. Heed the advice above about documenting stuff.

Re: The creator of Claude Code's Claude setup

#169
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…

My initial response to reading this post was "wow, I think I'd rather just write the code".

I also remain a bit skeptical because, if all of this really worked (and I mean over a long time and scaling to meet a range of business requirements), even if it's not how I personally want to write code, shouldn't we be seeing a ton of 1 person startups?

I see Bay area startups pushing 996 and requiring living in the Bay area because of the importance of working in an office to reduce communication hurdles. But if I can really 10x my current productivity, I can get the power of a seed series startup with even less communication overhead (I could also get by with much less capital). Imagine being able to hire 10 reliable junior-mid engineers who unquestionably followed your instruction and didn't need to sleep. This is what I keep being told we have for $200/month. Forget not needing engineers, why do we need angel investors or even early stage VC? A single smart engineer should be able, if all the claims I'm hearing are true, to easily accomplish in months what used to take years.

But I keep seeing products shipped at the same speed but with a $200 per month per user overhead. Honestly I would love to be wrong on this because that would be incredibly cool. But unfortunately I'm not seeing it yet.

Re: The creator of Claude Code's Claude setup

#170
post #134

Earlier quoted context omitted.

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?

No, I'm suggesting that given the context, it's a tiny concession to make...
Post reply on HN