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

261–270 of 603 posts

Re: 6 weeks of Claude Code

#261

Post by DrStartup »

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…

hook up zen mcp to openrouter and use cerabras inference with kimi k2 and qwen3 480b at 2k tok/sec

Re: 6 weeks of Claude Code

#262

Post by yumraj »

Aurornis wrote: post #77
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…

> 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?

Re: 6 weeks of Claude Code

#263

Post by stitched2gethr »

einpoklum wrote: post #150
danielbln wrote: post #108

Earlier quoted context omitted.

It's the automators dream come true. Anything can be automated, anything scripted, anything documented. Even if we're gonna use other (possibly local) models in the future, this will be my interface of choice. It's so powerful.

It's not a dream come true to have a bunch of GPUs crunching at full power to achieve your minor automation, with the company making them available losing massive amounts of money on it: https://www.wheresyoured.at/the-haters-gui/ ... while also exposing the contents of your computer to surveillence.

Well me plus a $1200 / year subscription is still much cheaper than 2 of me.

Re: 6 weeks of Claude Code

#264

Post by Rapzid »

giancarlostoro wrote: post #169
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…

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.…

Yeah I noticed the issue with more Junior developers right away. Some developers, Junior or not, have yet to be exposed to environments where their PRs are put under HEAVY scrutiny. They are used to loosey-goosey and unfortunately they are not prepared to put LLM changes under the level of scrutiny they require.

The worst is getting, even smallish, PRs with a bunch of changes that look extraneous or otherwise off. After asking questions the code changes without the questions being answered and likely with a new set of problems. I swear I've been prompting an LLM through an engineer/PR middleman :(

Re: 6 weeks of Claude Code

#265

Post by Eggpants »

Ah yet another attempt to push the “$200/month is a bargain!!!” narrative. Sad.

I get it. No one is really making any money yet, including openAI.

As the VC money dries up this is only going to get worse. Like ads in responses worse.

this_variable_name_is_sponsored_by_coinbase bad. Which these vibe chuckleheads will claim is no big deal because only losers read code.

Re: 6 weeks of Claude Code

#267

Post by martinald »

ako wrote: post #224
baq wrote: post #66

Earlier quoted context omitted.

Fascinating since I found the recent Claude models untrustworthy for writing and editing SQL. E.g. it'd write conditions correctly, but not add parens around ANDs and ORs (which gemini pro then highlighted as a bug, correctly.)

I found claude sonnet 4 really good at writing SQL if you give it a feedback loop with real data. It will research the problem, research the data, and improve queries until it finds a solution. And then it will optimize it, even optimize performance if you ask it to run explain plan or look at pg_stat_statemnts (postgres).

It's outrageously good at performance optimization. There's been multiple really complex queries I've optimized with it that I'd been putting off for a long time. Claude code figured the exact indexes to add within seconds (not ones I would have got easily manually).

Re: 6 weeks of Claude Code

#268

Post by trjordan »

I think the most interesting change Claude enables is letting AI try stuff. We do this all the time.

I have this sense this works best in small teams right now, because Claude wants to produce code changes and PRs. Puzzmo, where OP works, is In larger codebases, PRs don't feel like the right medium in every case for provocative AI explorations. If you're going to kick something off before a meeting and see what it might look like to solve it, it might be better to get back a plan, or a pile of regexps, or a list of teams that will care.

Having an AI produce a detailed plan for larger efforts, based on an idea, seems amazing.

Re: 6 weeks of Claude Code

#269

Post by joks »

infecto wrote: post #18
Fraterkes wrote: post #5

Irrespective of how good Claude code actually is (I haven’t used it, but I think this article makes a really cogent case), here’s something that bothers me: I’m very junior, I have a big slow ugly codebase of gdscript (basically python) that I’m going to convert to C# to both clean it up and speed it up. This is for a personal project, I haven’t written a ton of C# or done this amount of refactoring before, so this c…

What’s wrong with using a Claude code to write a possible initial iteration and then go back and review the code for understanding? Various languages and frameworks have there own footguns but those usually are not unfixable later on.

AFAICT you learn significantly more in building something from the ground-up than you do when code-reviewing someone else's code. In my experience you really don't build the mental model of how the code is working unless you either build it yourself, refactor it yourself, or you have to heavily debug it to fix a bug or something.

Re: 6 weeks of Claude Code

#270

Post by nojito »

baq wrote: post #66
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…

Fascinating since I found the recent Claude models untrustworthy for writing and editing SQL. E.g. it'd write conditions correctly, but not add parens around ANDs and ORs (which gemini pro then highlighted as a bug, correctly.)

The trick is to have it run it through sqlglot and correct the errors.
Post reply on HN