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

6 weeks of Claude Code

blog.puzzmo.com

Post reply on HN
Print view View original

531–540 of 603 posts

Re: 6 weeks of Claude Code

#531

Post by ModernMech »

handfuloflight wrote: post #529
ModernMech wrote: post #520

Earlier quoted context omitted.

> to me Key words there. To you, it's a electric saw because you already know how to program, and that's the other person's point; it doesn't necessarily empower people to build software. You? Yes. Generally though when you hand the public an electric saw and say "have at it, build stuff" you end up with a lot of lost appendages. Sadly, in this case the "lost appendages" are going to be man-decades of time spent undo…

> Sadly, in this case the "lost appendages" are going to be man-decades of time spent undoing all the landmines vibecoders are going to plant around the digital commons. Aren't you being overly optimistic that these would even get traction?

Pessimistic, but yeah. It's just my whole life has been a string of the absolute worst ideas being implemented at scale, so I don't see why this would buck the trend.

Re: 6 weeks of Claude Code

#532

Post by actinium226 »

brentm wrote: post #469
actinium226 wrote: post #460

I see a lot of comments here gushing about CC but I've used and I really don't get it. I find that it takes me just as long to explain to it what I need done as it takes to just do the work myself.

You need to give it something to do that you don't think it will be able to do. That is where I think it starts to click.

I often give it things I think it can do and then it screws those up. I don't see how giving it something I think it can't do will help.

Re: 6 weeks of Claude Code

#533

Post by ifwinterco »

michaelrpeskin wrote: post #478
giancarlostoro wrote: post #169

Earlier quoted context omitted.

If you are a Senior Developer, who is comfortable giving a Junior tips, and then guiding them to fixing them (or just stepping in for a brief moment and writing where they missed something) this is for you. I'm hearing from Senior devs all over thought, that Junior developers are just garbage at it. They product slow, insecure, or just outright awful code with it, and then they PR the code they don't even understand.…

Yes, this! A couple of week ago, I had a little down time and thought about a new algorithm I wanted to implement. In my head it seemed simple enough that 1) I thought the solution was already known, and 2) it would be fairly easy to write. So I asked Claude to "write me a python function that does Foo". I spent a whole morning going back and forth getting crap and nothing at all like what I wanted. I don't know what…

The LLM will never admit it doesn't have a clue what's going on, but over time you develop a sense of when it's onto something and when it's trapped in a loop of plausible sounding nonsense

Edit: Also, it's funny how often you can get it to improve its output by just saying "this looks kind of bad for x reason, there must be a way to make it better"

Re: 6 weeks of Claude Code

#534

Post by ifwinterco »

DrewADesign wrote: post #468
nosianu wrote: post #411

Earlier quoted context omitted.

Brains are not computers and we don't learn by being given abstract rules. We also don't learn nearly as well from class room teaching as we do from doing things IRL for a real purpose - the brain always knows the difference and that the (real, non-artificially created) stakes are low in a teaching environment. That's also the huge difference between AI and brains: AI does not work on the real world but on our commun…

Yeah. The only, and I mean only non-social/networking advantages to universities stem from forced learning/reasoning about complex theoretical concepts that form the requisite base knowledge to learn the practical requirements of your field while on the job. Trade schools and certificate programs are designed to churn out people with journeyman-level skills in some field. They repeatedly drill you on the practical da…

It's not a particularly moral way to think, but if you're currently mid level or senior, the junior dev pipeline being cut off will be beneficial to you personally in a few years' time.

Potentially very beneficial, if it turns out software engineers are still needed but nobody has been training them for half a decade

Re: 6 weeks of Claude Code

#535

Post by sitkack »

FirmwareBurner wrote: post #482
sitkack wrote: post #326

Earlier quoted context omitted.

The unemployment in India is going to be catastrophic. Geopolitical.

Unlikely. Microsoft had layoffs everywhere except India. There they keep hiring more. As song as the can keep upskilling themselves while still being much cheaper than US workers they won't fear unemployment. Just yesterday I saw on X a video of a Miami hotel where the check-in procedure was via a video call to a receptionist in India.

Six months from now, that singular worker if they are still employed, will manage a high number of receptionist avatars. And then they themselves will be replaced. It will still lead to a massive collapse in the labor market and with all of that excess labor, existing jobs while being overworked will still see flat to decreasing wages.

Re: 6 weeks of Claude Code

#536

Post by ifwinterco »

pmg101 wrote: post #513
ChuckMcM wrote: post #500

Earlier quoted context omitted.

Yes, there are companies that opt for broken organizations for a variety of reasons. The observation though is this; Does this lead to a world where the 'minimum' programmer is what we consider today to be a 'Senior Dev' ? It echoes the transition of machinists to operators of CAD/CAM workstations to operate machining centers, rather than hands on the dials of a mill or lathe. It certainly seems like it might make en…

It'll be interesting to see if in a decade when a whole cohort of juniors didn't get trained whether LLMs will be able to do the whole job. I'm guessing a lot of companies are willing to bet on yes.

The issue is there's a kind of prisoner's dilemma going on - probably some people can see that there's a serious risk of still needing software engineers in 10 years' time and there not being enough because nobody is training juniors in 2025.

However, noticing this doesn't help because if you invest in training juniors in 2025 but nobody else does, someone else can just recruit them in 2030 and benefit from your investment

Re: 6 weeks of Claude Code

#537

Post by js2 »

exographicskip wrote: post #495
js2 wrote: post #313

Earlier quoted context omitted.

I've also found it good at catching mistakes and helping write commit messages. "Review the top-most commit. Did I make any mistakes? Did I leave anything out of the commit message?" Sometimes I let it write the message for me: "Write a new commit message for the current commit." I've had to tell it how to write commit messages though. It likes to offer subjective opinions, use superlatives and guess at why something…

This is a good call! Do you have claude use atomic commits or do you manually copy/paste the output? Saving your summary instructions as a CLAUDE.md

I'll tell it to commit or amend depending upon the situation. Then I'll open the message in my editor and revise what it wrote.

Re: 6 weeks of Claude Code

#538

Post by jerpint »

unshavedyak wrote: post #25
jeswin wrote: post #19

Claude Code is ahead of anything else, in a very noticeable way. (I've been writing my own cli tooling for AI codegen from 2023 - and in that journey I've tried most of the options out there. It has been a big part of my work - so that's how I know.) I agree with many things that the author is doing: 1. Monorepos can save time 2. Start with a good spec. Spend enough time on the spec. You can get AI to write most of t…

> 2. Start with a good spec. Spend enough time on the spec. You can get AI to write most of the spec for you, if you provide a good outline. Curious how you outline the spec, concretely. A sister markdown document? How detailed is it? etc. > 3. Make sure you have tests from the beginning. This is the most important part. Tests (along with good specs) are how an AI agent can recurse into a good solution. TDD is back.…

I wrote a tool for this, which allows you to co-create and maintain a context repository with your LLMs

https://github.com/jerpint/context-llemur

CLI for the humans, MCP for the LLMS. Whatever is in the context repository should be used by the LLM for its next steps and you are both responsible for maintaining it as tasks start getting done and the project evolves

I’ve been having good success with it so far

Re: 6 weeks of Claude Code

#539

Post by nkzd »

buffer1337 wrote: post #84

I've been using Claude code 12-16 hours a day since I first got it running two weeks ago. Here's the tips I've discovered: 1. Immediately change to sonnet (the cli defaults to opus for max users). I tested coding with opus extensively and it never matches the quality of sonnet. 2. Compacting often ends progress - it's difficult to get back to the same quality of code after compacting. 3. First prompt is very importan…

How are you using Claude Code 16 hours a day?

Re: 6 weeks of Claude Code

#540

Post by jerpint »

rane wrote: post #90
jeswin wrote: post #29

Earlier quoted context omitted.

> Curious how you outline the spec, concretely. A sister markdown document? How detailed is it? etc. Yes. I write the outline in markdown. And then get AI to flesh it out. The I generate a project structure, with stubbed API signatures. Then I keep refining until I've achieved a good level of detail - including full API signatures and database schemas. > Ironically i've been struggling with this. For best results i'v…

I don't even write the outline myself. I tell CC to come up with a plan, and then we iterate on that together with CC and I might also give it to Gemini for review and tell CC to apply Gemini's suggestions.

I built a tool for this exact workflow in mind but with MCP and versioning included so you can easily track and edit the files on any platform including cursor, Claude desktop etc

https://github.com/jerpint/context-llemur

Post reply on HN