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

301–310 of 603 posts

Re: 6 weeks of Claude Code

#301

Post by Lucasoato »

lukaslalinsky wrote: post #57

I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…

> I couldn't imagine paying >100$/month for a dev tool in the past, but I'm seriously considering upgrading to the Max plans.

Sadly, my experience with the Max plan has been extremely poor. It’s not even comparable, I’ve been vastly experimenting with claude code in the last weeks, spending more than 80$ per day, it’s amazing. The problem is that in the Max plan you’re not the one managing the context length, and this ruins the model ability to keep things memory. Of course this is expected, the longer the context the more expensive to run, but it’s so frustrating to fail in a coding task because it’s so obvious the model lost a crucial part of the context.

Re: 6 weeks of Claude Code

#302

Post by whitefang »

kachapopopow wrote: post #116
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 had success with creating a VERY detailed plan.md file - down to how all systems connect together, letting claude-loop[1] run while I sleep and coming back in the morning manually patching it up. [1]: https://github.com/DeprecatedLuke/claude-loop

You are the 5% they were talking about lol.

Re: 6 weeks of Claude Code

#303

Post by boringg »

andrekandre wrote: post #300
0x696C6961 wrote: post #278

Earlier quoted context omitted.

Our offshore devs keep doing this and it drives me nuts. No answers to my question, completely different code gets pushed.

> No answers to my question, completely different code gets pushed. at what point does that cost become higher than benefit?

It does but most execs dont care about long term they want that perf bonus before they leave in 3-4 years

Re: 6 weeks of Claude Code

#304

Post by radley »

dimal wrote: post #297
lukaslalinsky wrote: post #57

I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…

Technically you’re not vibe coding. You’re using AI to do software engineering. Vibe coding is specifically the process of having AI produce code and plowing ahead without understanding it. I know I’m being pedantic, but people mean very different things when they talk about this stuff, and I don’t think any credence should be given to vibe coding.

Both are vibe coding. The term was coined by Andrej Karpathy, a computer scientist who served as the director of artificial intelligence at Tesla.

Maybe you're thinking of slop coding?

Re: 6 weeks of Claude Code

#305

Post by skydhash »

SparkyMcUnicorn wrote: post #289
dv_dt wrote: post #228

Earlier quoted context omitted.

Script? I havent used anything more complex than "tar xzf file" in a decade

Remembering one thing is easy, remembering all the things is not. With an agentic CLI I don't need to remember anything, other than if it looks safe or not.

No one remember all the things. It's usually ctrl+r (history search) or write it down in some script or alias.

Re: 6 weeks of Claude Code

#306

Post by radley »

Freedom2 wrote: post #83
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…

It doesn't help that a lot of skeptics are also dishonest. A few days ago someone here tried to claim that inserting verbose debug logging, something Claude Code would be very good at, is "actually programming" and it's important work for humans to do. No, Claude can create logs all across my codebase with much better formatting far faster than I can, so I can focus on actual problem solving. It's frustrating, but pa…

No, some skeptics are actually dishonest. It's part of trolling, and trolling is in fashion right now. Granted, some skeptics are fair, but many do it strictly for the views, without any due diligence.

Re: 6 weeks of Claude Code

#307

Post by radley »

tecleandor wrote: post #195
Freedom2 wrote: post #179

Earlier quoted context omitted.

Thank you for calling out my inaccuracy. One thing I'm always appreciative for in HN is the level of pedantry day after day.

That's not pedantry, pedantry would be if it were a very minor or technical detail, but being dishonest doesn't have anything to do with having a different opinion. But this comment might step a bit into pedantry.

> But this comment might step a bit into pedantry.

Especially if I point out that they said "are also", not "are".

Re: 6 weeks of Claude Code

#308

Post by sibeliuss »

jadbox wrote: post #286

Good article, but fwiw, I think GraphQL is a bane for web dev for 90% of projects. It overcomplicates, bloats, and doesn't add anything over regular OpenAPI specs for what is usually just CRUD resource operations.

You either get it, or you don't! But if you do...

Re: 6 weeks of Claude Code

#309

Post by maxjustus »

lukaslalinsky wrote: post #57

I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…

One thing I’ve started doing is using Gemini cli as a sidecar for Claude Code to load in a huge amount of context around a set of changes to get a second opinion - it’s been pretty handy for that particular use case due to its context size advantage

Re: 6 weeks of Claude Code

#310

Post by jmtame »

polishdude20 wrote: post #192

Does anyone have advice on how to hire developers who can utilize AI coding tools effectively?

I've thought about this lately. In order to do that, you need to know where people typically stumble, and then create a rubric around that. Here are some things I'd look for:

- Ability to clearly define requirements up front (the equivalent mistake in coding interviews is to start by coding, rather than asking questions and understanding the problem + solution 100% before writing a single line of code). This might be the majority of the interview.

- Ability to anticipate where the LLM will make mistakes. See if they use perplexity/context7 for example. Relying solely on the LLM's training data is a mistake.

- A familiarity with how to parallelize work and when that's useful vs not. Do they understand how to use something like worktrees, multiple repos, or docker to split up the work?

- Uses tests (including end-to-end and visual testing)

- Can they actually deliver a working feature/product within a reasonable amount of time?

- Is the final result looking like AI slop, or is it actually performant, maintainable (by both humans and new context windows), well-designed, and follows best practices?

- Are they able to work effectively within a large codebase? (this depends on what stage you're in; if you're a larger company, this is important, but if you're a startup, you probably want the 0->1 type of interview)

- What sort of tools are they using? I'd give more weight if someone was using Claude Code, because that's just the best tool for the job. And if they're just doing the trendy thing like using Claude Agents, I'd subtract points.

- How efficient did they use the AI? Did they just churn through tokens? Did they use the right model given the task complexity?

Post reply on HN