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

A few random notes from Claude coding quite a bit last few weeks

twitter.com

Post reply on HN
Print view View original

501–510 of 870 posts

Re: A few random notes from Claude coding quite a bit last few weeks

#501

Post by twa927 »

DominikPeters wrote: post #293
twa927 wrote: post #121

I don't see the AI capacity jump in the recent months at all. For me it's more the opposite, CC works worse than a few months ago. Keeps forgetting the rules from CLAUDE.md, hallucinates function calls, generates tons of over-verbose plans, generates overengineered code. Where I find it a clear net-positive is pure frontend code (HTML + Tailwind), it's spaghetti but since it's just visualization, it's OK.

Are you using Opus 4.5? Sounds more like Sonnet.

Yes I'm using Sonnet 4.5. Thanks for the tip, will try Opus 4.5, although costs might become an issue.

Re: A few random notes from Claude coding quite a bit last few weeks

#502

Post by taytus »

viccis wrote: post #213
ryandrake wrote: post #23

Earlier quoted context omitted.

I noticed the same thing, but wasn't able to put it into words before reading that. Been experimenting with LLM-based coding just so I can understand it and talk intelligently about it (instead of just being that grouchy curmudgeon), and the thought in the back of my mind while using Claude Code is always: "I got into programming because I like programming, not whatever this is..." Yes, I'm building stupid things fas…

Same. This kind of coding feels like it got rid of the building aspect of programming that always felt nice, and it replaced it entirely with business logic concerns, product requirements, code reviews, etc. All the stuff I can generally take or leave. It's like I'm always in a meeting. >If I was intellectually excited about telling something to do this for me, I'd have gotten into management. Exactly this. This is t…

Because you are not coding, you are building. I've been coding since I was 7 years old, now I'm building.

Re: A few random notes from Claude coding quite a bit last few weeks

#503

Post by simonw »

chrisjj wrote: post #487
polishdude20 wrote: post #104

Earlier quoted context omitted.

What I have enjoyed about programming is being able to get the computer to do exactly what I want. The possibilities are bounded by only what I can conceive in my mind. I feel like with AI that can happen faster.

Have you an example of getting a coding chatbot to do exactly what you want?

https://gisthost.github.io/?a41ce6304367e2ced59cd237c576b817... - which built https://github.com/datasette/datasette-transactions exactly the way I wanted it to be built

Re: A few random notes from Claude coding quite a bit last few weeks

#504

Post by e12e »

overfeed wrote: post #365
daxfohl wrote: post #65

I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…

> Eventually it was easier just to quit fighting it and let it do things the way it wanted. I wouldn't have believed it a few tears ago if you told me the industry would one day, in lockstep, decide that shipping more tech-debt is awesome. If the unstated bet doesn't pay off, that is, AI development will outpace the rate it generates cruft, then there will be hell to pay.

> ... few tears ago

Brilliant. Even if it was a typo.

Re: A few random notes from Claude coding quite a bit last few weeks

#505

Post by koiueo »

locknitpicker wrote: post #448
striking wrote: post #118

Earlier quoted context omitted.

It's not just brain atrophy, I think. I think part of it is that we're actively making a tradeoff to focus on learning how to use the model rather than learning how to use our own brains and work with each other. This would be fine if not for one thing: the meta-skill of learning to use the LLM depreciates too. Today's LLM is gonna go away someday, the way you have to use it will change. You will be on a forever trea…

> It's not just brain atrophy, I think. I think part of it is that we're actively making a tradeoff to focus on learning how to use the model rather than learning how to use our own brains and work with each other. I agree with the sentiment but I would have framed it differently. The LLM is a tool, just like code completion or a code generator. Right now we focus mainly on how to use a tool, the coding agent, to ach…

The little experience I have with LLM confidently shows that LLMs are much better at navigating and modifying a well structured code base. And they struggle, sometimes to a point where they can't progress at all, if tasked to work on bad code. I mean, the kind of bad you always get after multiple rounds of unsupervised vibe coding.

Re: A few random notes from Claude coding quite a bit last few weeks

#506

Post by ryanjshaw »

bandrami wrote: post #460
locknitpicker wrote: post #448

Earlier quoted context omitted.

> It's not just brain atrophy, I think. I think part of it is that we're actively making a tradeoff to focus on learning how to use the model rather than learning how to use our own brains and work with each other. I agree with the sentiment but I would have framed it differently. The LLM is a tool, just like code completion or a code generator. Right now we focus mainly on how to use a tool, the coding agent, to ach…

Previous tools have been deterministic and understandable. I write code with emacs and can at any point look at the source and tell you why it did what it did. But I could produce the same program with vi or vscode or whatever, at the cost of some frustration. But they all ultimately transform keystrokes to a text file in largely the same way, and the compiler I'm targeting changes that to asm and thence to binary in…

> and can at any point look at the source and tell you why it did what it did

Even years later? Most people can’t unless there’s good comments and design. Which AI can replicate, so if we need to do that anyway, how is AI specially worse than a human looking back at code written poorly years ago?

Re: A few random notes from Claude coding quite a bit last few weeks

#508

Post by originalvichy »

gloosx wrote: post #447

So what is he even coding there all the time? Does anybody have any info on what he is actually working on besides all the vibe-coding tweets? There seems to be zero output from they guy for the past 2 years (except tweets)

Helper scripts for APIs for applications and tools I know well. LLMs have made my work bearable. Many software providers expose great apis, but expert use cases require data output/input that relies on 50-500 line scripts. Thanks to the models post gpt4.5 most requirements are solvable in 15 minutes when they could have taken multiple workdays to write and check by hand. The only major gap is safe ad-hoc environments to run these in. I provide these helper functions for clients that would love to keep the runtime in the same data environment as the tool, but not all popular software support FaaS style environments that provide something like a simple python env.

Re: A few random notes from Claude coding quite a bit last few weeks

#509

Post by gregjor »

arh5451 wrote: post #507

Thank you for the really excellent summation. I echo your thought 1 to 1. I have found it more difficult to learn new languages or coding skills, because I am no longer forced to go through the painful slow grind of learning.

Painful slow grind? I have always found the learning part what I enjoy most about programming. I don't intend to outsource that a chatbot.

Re: A few random notes from Claude coding quite a bit last few weeks

#510

Post by gregjor »

jedberg wrote: post #302

> You realize that stamina is a core bottleneck to work There has been a lot of research that shows that grit is far more correlated to success than intelligence. This is an interesting way to show something similar. AIs have endless grit (or at least as endless as your budget). They may outperform us simply because they don't ever get tired and give up. Full quote for context: Tenacity. It's so interesting to watch…

LLMs do not have grit or tenacity. Tenacity doesn't desribe a machine that doesn't need sleep or experience tiredness, or stress. Grit doesn't describe a chatbot that will tirelessly spew out answers and code because it has no stake or interest in the result, never perceives that it doesn't know something, and never reflects on its shortcomings.
Post reply on HN