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

I've been using Claude Code for a couple of days

twitter.com

Post reply on HN
Print view View original

501–507 of 507 posts

Re: I've been using Claude Code for a couple of days

#501

Post by baruch »

vbezhenar wrote: post #372
InvertedRhodium wrote: post #283

Earlier quoted context omitted.

I'll preface this with the fact I agree that there is a difference between using a framework and being curious enough to dig into the details I think you're veering into No True Scotsman territory here. IMO, the vast majority of programmers wouldn't meet the definition you've put forward here. I don't know many that dig into the operating system, platform, or hardware all that much, though I work in streaming media s…

I'm the one who feels uncomfortable when something is magical. I'm trying to dig whenever possible. I don't always have success. I know very little about Linux kernel internals, for example. That said, it's rarely pays out. Quite the opposite: I often spending lots of time digging unnecessarily. I'm not complaining, I am who I am and I don't want to change. Digging into internals makes me happier and satisfied. And s…

I find that my understanding of different layers is usually not needed but is rarely important toy ability to solve thorny issues or figure out ways to do things or debug issues that others are not even trying.

I'm working in areas of systems programming where such knowledge and willingness to go deeper into the stack is helpful, even if rarely so.

I can't say I understand the kernel, I only scratch the surface of most of it and only dug deeper where I really needed to and only as deep as time allowed me and the need required though.

Re: I've been using Claude Code for a couple of days

#502

Post by intrasight »

chaosprint wrote: post #146
intrasight wrote: post #143

Earlier quoted context omitted.

> extremely painful debugging experiences. I'd claim that if you're debugging the code - or even looking at it for that matter - that you're using AI tools the wrong way.

I'd be very interested to know of a way to make it work with AI that doesn't require debugging if you can illustrate.

Make what work with AI?

Re: I've been using Claude Code for a couple of days

#503

Post by intrasight »

vunderba wrote: post #239
intrasight wrote: post #143

Earlier quoted context omitted.

> extremely painful debugging experiences. I'd claim that if you're debugging the code - or even looking at it for that matter - that you're using AI tools the wrong way.

Congratulations. You allow the AI to make some new subroutine, and you immediately commit and merge the changes to your system. You run it, and it executes without throwing any immediate errors. The business domain is far more nuanced and complex, and your flimsy "does it compile" test for the logic doesn't even begin to cover the necessary gamut of the input domain which you as the expert might have otherwise notice…

>You allow the AI to make some new subroutine

Again, you're using AI the wrong way.

Re: I've been using Claude Code for a couple of days

#504

Post by ZeroTalent »

christophilus wrote: post #274
ZeroTalent wrote: post #266

Earlier quoted context omitted.

The thing is, when you're doing frontend, a human programmer can't write 4,000 lines of React code in 1 hour. A properly configured LLM system can. This is why I wouldn't hire a person who doesn't know how to do this.

What are you doing where 4000 lines of LLM-generated code per hour is a net positive? Sounds like a techdebt machine to me.

UIs in React are very verbose. I'm not saying this is running 24/7.

Re: I've been using Claude Code for a couple of days

#505

Post by Ey7NFZ3P0nzAe »

ddanieltan wrote: post #377
BeetleB wrote: post #169

Earlier quoted context omitted.

Some hints for people stuck like this: Consider using Aider. It's a great tool and cheaper to use than Code. Look at Aiders LLM leaderboard to figure out which LLMs to use. Use its architect mode (although you can get quite fast without it - I personally haven't needed it). Work incrementally. I use at least 3 branches. My main one, a dev one and a debug one. I develop on dev. When I encounter a bug I switch to debug…

do you have a special prompt to instruct aider to log file changes in the repo's README? I've used aider in repos with a README.md but it has not done this update. (granted, i've never /add the readme into aider's context window before either...)

Take a loot at conventions.md in aider.chat documentation

Re: I've been using Claude Code for a couple of days

#506

Post by cybertheory »

If anyone is having trouble with claude code output, my team and I are releasing an MCP server that provides all the latest and greatest technical knowledge in one place for AI to access. We are at 5k waitlists already, go ahead and sign up for updates! https://jetski.ai

Re: I've been using Claude Code for a couple of days

#507

Post by theonething »

rs186 wrote: post #233
frankc wrote: post #225

Earlier quoted context omitted.

I think the interest has more to do with who is doing the tweeting, don't you think?

Reminder: "appeal to authority" is a classical logical fallacy. For me, I don't know this person, which means that all the words are completely meaningless. Which is exactly the point.

> For me, I don't know this person, which means that all the words are completely meaningless.

Because you don't know who Yegge is, the words are meaningless to you? So a body of text is meaningful only if you know who the author is? That's...lame.

Post reply on HN