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

341–350 of 603 posts

Re: 6 weeks of Claude Code

#341

Post by akra »

yumraj wrote: post #262
Aurornis wrote: post #77

Earlier quoted context omitted.

> as a vibe coding skeptic, I was amazed. The interesting thing about all of this vibe coding skepticism, cynicism, and backlash is that many people have their expectations set extremely low. They’re convinced everything the tools produce will be junk or that the worst case examples people provide are representative of the average. Then they finally go out and use the tools and realize that they exceed their (extreme…

> Yeah we all know Claude Code isn’t going to generate a $10 billion SaaS with a team of 10 people… Not trying to argue, since I don’t have counter evidence, but how can you be so sure?

The question is not whether you can or can't, but whether it is still worth it long term:

- There is a moat of doing so (i.e. will people actually pay for your SaaS knowing that they could do it too via AI) and..

- How many large scale ideas do you need post AI? Many SaaS products are subscription based and loaded with features you don't need. Most people would prefer a simple product that just does what they need without the ongoing costs.

There will be more software. The question is who accrues the economic value of this additional software - the SWE/tech industry (incumbent), the AI industry (disruptor?) and/or the consumer. For the SWE's/tech workers it probably isn't what they envisioned when they started/studied for this industry.

Re: 6 weeks of Claude Code

#342

Post by leptons »

awesome_dude wrote: post #244
shortrounddev2 wrote: post #241

Earlier quoted context omitted.

They're substantively different. Using a compiler requires you to have an internalized model of a state machine and, importantly, a formal language. C, assembler, java, etc. are all essentially different from using the softness of the English language to coerce results out of a black box

No, not at all. In both all you need is the ability to communicate to the machine in a way that the machine can convert your ideas into actions. The restricted language of a compiler is a handicap, not evidence of a skill - we've been saying forever that "Natural Language" compilers would be a game changer, and that's all that an AI really is Edit: It appears that this discussion is going to end up with a definition…

Writing code that gets compiled is deterministic, but asking an LLM to produce code is a non-deterministic guessing game.

Notice how nobody is skeptical of compilers?

Re: 6 weeks of Claude Code

#343

Post by AndyNemmity »

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…

I have the main agent use Opus, and have it always call sub-agents running Sonnet. That's the best setup I've found.

I turn off compacting to be manual, makes it easy to find a stopping point and write all context out to an md file before compacting.

First prompt isn't very important to me.

I haven't found i need special phrases. What matters is how context heavy I can make my subagents.

Re: 6 weeks of Claude Code

#344

Post by AndyNemmity »

felipeerias wrote: post #285
zmmmmm wrote: post #276

I'm most interested in how well these tools can tackle complex legacy systems. We have tonnes of code that's been built over a decade with all kinds of idioms and stylistic conventions that are enforced primarily through manual review. This relates in part to working in a regulated environment where we know certain types of things need radical transparency and auditability, so writing code the "normal" way a develope…

You need to provide agentic tools with enough context about the project so they can find their way around. In Claude Code this is typically done via a CLAUDE.md document at the root of the codebase. I work on Chromium and my experience improved immensely by using a detailed context document (~3,000 words) with all sorts of relevant information, from the software architecture and folder organisation to the C++ coding…

In my experience, doing it via Claude.md is significantly worse than doing it in the sub-agents context.

Re: 6 weeks of Claude Code

#346

Post by AndyNemmity »

zmmmmm wrote: post #276

I'm most interested in how well these tools can tackle complex legacy systems. We have tonnes of code that's been built over a decade with all kinds of idioms and stylistic conventions that are enforced primarily through manual review. This relates in part to working in a regulated environment where we know certain types of things need radical transparency and auditability, so writing code the "normal" way a develope…

It's still easier to handle greenfield projects, but everything is improving, and the gap is decreasing.

Re: 6 weeks of Claude Code

#347

Post by AndyNemmity »

mrmincent wrote: post #186
blackqueeriroh wrote: post #184

I have nearly 20 years of experience in technology, and have been writing toy scripts or baby automations for most of my career. I started out in a managed services help desk and took that route many folks take across and around the different IT disciplines. I mostly spend my days administering SaaS tools, and one of my largest frustrations has always been that I didn’t know enough to really build a good plugin or ad…

ADHD here, and Claude code has been a game changer for me as well. I don’t get sidetracked going lost in documentation loops, suffer decision paralysis, or forget what I’m currently doing or what I need to do next. It’s almost like I’m body doubling with Claude code.

well said. I'm actually getting better at coding oddly enough because i'm reading so much more code.

Re: 6 weeks of Claude Code

#348

Post by AndyNemmity »

strange_quark wrote: post #235
nrclark wrote: post #223

Does Claude Code use a different model then Claude.ai? Because Sonnet 4 and Opus 4 routinely get things wrong for me. Both of them have sent me on wild goose chases, where they confidently claimed "X is happening" about my code but were 100% wrong. They also hallucinated APIs, and just got a lot of details wrong in general. The problem-space I was exploring was libusb and Python, and I used ChatGPT and also Claude.ai…

Pretty sure it’s the same model. The reason that claude code is “good” is because it can run tests, compile the code, run a linter, etc. If you actually pay attention to what it’s doing, at least in my experience, it constantly fucks up, but can sort of correct itself by taking feedback from outside tools. Eventually it proclaims “Perfect!” (which annoys me to no end), and spits out code that at least looks like it s…

You're right, but you can actually improve it pretty dramatically with sub agents. Once you get into a groove with sub agents, it really makes a big difference.

Re: 6 weeks of Claude Code

#349

Post by ako »

yubblegum wrote: post #292
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.…

> 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. If this is the case then we better have full AI generated code within the next 10 years since those "juniors" will remain atrophied juniors forever and the old timers will be checking in with the big cloc…

IT education and computer science (at least part of it) will need a stronger focus on software engineering and software architecture skills to teach developers how to be in control of an AI dev tool.

Re: 6 weeks of Claude Code

#350

Post by AtlasBarfed »

Aurornis wrote: post #88
MarkMarine wrote: post #60

Earlier quoted context omitted.

Claude code is great until it isn’t. You’re going to get to a point where you need to modify something or add something… a small feature that would have been easy if you wrote everything, and now it’s impossible because the architecture is just a mishmash of vibe coded stuff you don’t understand.

The people successfully using Claude Code for big projects aren’t letting it get to the point where they don’t understand what it wrote. The best results come from working iteratively with it. I reject about 1/3 of edits to request some changes or a change of direction. If you just try to have it jam on code until the end result appears to work then you will be disappointed. But that’s operator error.

Remind me in two years...

I understand completely what you're saying. But with the delusions that management is under right now, you're just going to seem like someone that's resisting the flow of code and becoming a bottleneck.

Post reply on HN