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

391–400 of 870 posts

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

#391

Post by _dark_matter_ »

chrisjj wrote: post #278
jjfoooo4 wrote: post #87

Earlier quoted context omitted.

That was true for me, but is no longer. It's been especially helpful in explaining and understanding arcane bits of legacy code behavior my users ask about. I trigger Claude to examine the code and figure out how the feature works, then tell it to update the documentation accordingly.

> I trigger Claude to examine the code and figure out how the feature works, then tell it to update the documentation accordingly. And how do you verify its output isn't total fabrication?

Your docs are a contact. You can verify that contract using integration tests

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

#392

Post by UnlockedSecrets »

bojo wrote: post #310
bojo wrote: post #303

Earlier quoted context omitted.

I've been an EM for the last 10 of my 25 year Software Engineering career. Coding is, frankly, boring to me anymore, even though I enjoyed doing it most of my career. I had this project I wanted to exist in world but couldn't be bothered to get started. Decided to figure out what this "vibe coding" nonsense is, and now there's a certain level of joy to all of this again. Being able to clearly define everything using…

In case anyone is curious, here was my epiphany project from 2 weeks ago: https://github.com/boj/the-project I then realized I could feed it everything it ever needed to know. Just create a docs/* folder and tell it to read that every session. Through discovery I learned about CLAUDE.md, and adding skills. Now I have an /analyst, /engineer, and /devops that I talk to all day with their own logic and limitations, as w…

How much did this type of project cost you to make?

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

#393

Post by YetAnotherNick »

storystarling wrote: post #200
YetAnotherNick wrote: post #141

Earlier quoted context omitted.

With optimizations and new hardware, power is almost a negligible cost. You can get 5.5M tokens/s/MW[1] for kimi k2(=20M/KWH=181M tokens/$) which is 400x cheaper than current pricing. It's just Nvidia/TSMC/other manufacturers eating up the profit now because they can. My bet is that China will match current Nvidia within 5 years. [1]: https://developer-blogs.nvidia.com/wp-content/uploads/2026/0...

Electricity is negligible but the dominant cost is the hardware depreciation itself. Also inference is typically memory bandwidth bound so you are limited by how fast you can move weights rather than raw compute efficiency.

Yes, because the margin is like 80% for Nvidia, and 80% again for the manufacturers like Samsung and TSMC. Once the fixed cost like R and D is amortized the same node technology and hardware capacity could be just few single digit percent of current.

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

#394

Post by yasoob »

porise wrote: post #21

I wish the people who wrote this let us know what king of codebases they are working on. They seem mostly useless in a sufficiently large codebase especially when they are messy and interactions aren't always obvious. I don't know how much better Claude is than ChatGPT, but I can't get ChatGPT to do much useful with an existing large codebase.

Another personal example. I spent around a month last year in January on this application: https://apps.apple.com/us/app/salam-prayer-qibla-quran/id674...

I had never used Swift before that and was able to use AI to whip up a fairly full-featured and complex application with a decent amount of code. I had to make some cross-cutting changes along the way as well that impacted quite a few files and things mostly worked fine with me guiding the AI. Mind you this was a year ago so I can only imagine how much better I would fare now with even better AI models. That whole month was spent not only on coding but on learning Swift enough to fix problems when AI started running into circles and then learning about Xcode profiler to optimize the application for speed and improving perf.

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

#395

Post by rurp »

Havoc wrote: post #309
noosphr wrote: post #288

Earlier quoted context omitted.

There is an old saying back home: an idiot never tires, only sweats. Claude isn't tenacious. It is an idiot that never stops digging because it lacks the meta cognition to ask 'hey, is there a better way to do this?'. Chain of thought's whole raison d'etre was so the model could get out of the local minima it pushed itself in. The issue is that after a year it still falls into slightly deeper local minima. This is fi…

> it lacks the meta cognition to ask 'hey, is there a better way to do this?'. Recently had an AI tell me this code (that it wrote) is a mess and suggested wiping it and starting from scratch with a more structure plan. That seems to hint at some meta cognition outlines

Perhaps. I've had LLMs tell me some code is deeply flawed garbage that should be rewritten about code that exact same LLM wrote minutes before. It could be a sign of deep meta cognition, or it might be due to some cognitive gaps where it has no idea why it did something a minute ago and suddenly has a different idea.

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

#396

Post by dugidugout »

nfredericks wrote: post #320
jasonfarnon wrote: post #298

Earlier quoted context omitted.

Aren't you still better off than the rest of us who found what they love + invested decades in it before it lost its value. Isn't it better to lose your love when you still have time to find a new one?

This is genuinely such a good take

Especially on the topic of value! We are all intuitively aware that value is highly contextual, but get in a knot trying to rationalize value long past genuine engagement!

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

#397

Post by amluto »

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…

I’ve actually found the tool that inspires the most worry about brain atrophy to be Copilot. Vscode is full of flashing suggestions all over. A couple days ago, I wanted to write a very quick program, and it was basically impossible to write any of it without Copilot suggesting a whole series of ways to do what it thought I was doing. And it seems that MS wants this: the obvious control to turn it off is actually just “snooze.”

I found the setting and turned it off for real. Good riddance. I’ll use the hotkey on occasion.

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

#398

Post by supriyo-biswas »

retsibsi wrote: post #352
d0mine wrote: post #234

Earlier quoted context omitted.

> far-fetched Remember Google? Once it was far-fetched that they would make the search worse just to show you more ads. Now, it is a reality. With tokens, it is even more direct. The more tokens users spend, the more money for providers.

> Now, it is a reality. What are the details of this? I'm not playing dumb, and of course I've noticed the decline, but I thought it was a combination of losing the battle with SEO shite and leaning further and further into a 'give the user what you think they want, rather than what they actually asked for' philosophy.

https://www.wheresyoured.at/the-men-who-killed-google/

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

#399

Post by ithkuil »

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.

Don't worry. This will create the demand for even more powerful models that are able to untangle the mess created by previous models.

Once we realize the kind of mess _those_ models created, well, we'll need even more capable models.

It's a variation on the theme of Kernighan insight about the more "clever" you are while coding the harder it will be to debug.

EDIT: Simplicity is a way out but it's hard under normal circumstances, now with this kind of pressure to ship fast because the colleague with the AI chimp can outperform you, aiming at simplicity will require some widespread understanding

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

#400

Post by nemothekid »

mh2266 wrote: post #354
nemothekid wrote: post #236

Earlier quoted context omitted.

I think I should write more about but I have been feeling very similar. I've been recently exploring using claude code/codex recently as the "default", so I've decided to implement a side project. My gripe with AI tools in the past is that the kind of work I do is large and complex and with previous models it just wasn't efficient to either provide enough context or deal with context rot when working on a large appli…

> I've been trying to implement a multiplayer game with server authoritative networking in Rust with Bevy. I specifically chose Bevy as the latest version was after Claude's cut off, it had a number of breaking changes, and there aren't a lot of deep examples online. I am interested in doing something similar (Bevy. not multiplayer). I had the thought that you ought be able to provide a cargo doc or rust-analyzer equ…

>I had the thought that you ought be able to provide a cargo doc or rust-analyzer equivalent over MCP? This... must exist?

I've found that there are two issues that arise that I'm not sure how to solve. You can give it docs and point to it and it can generally figure out syntax, but the next issue I see is that without examples, it kind of just brute forces problems like a 14 year old.

For example, the input system originally just let you move left and right, and it popped it into an observer function. As I added more and more controls, it began to litter with more and more code, until it was ~600 line function responsible for a large chunk of game logic.

While trying to parse it I then had it refactor the code - but I don't know if the current code is idiomatic. What would be the cargo doc or rust-analyzer equivalent for good architecture?

Im running into this same problem when trying to claude code for internal projects. Some parts of the codebase just have really intuitive internal frameworks and claude code can rip through them and provide great idiomatic code. Others are bogged down by years of tech debt and performance hacks and claude code can't be trusted with anything other than multi-paragraph prompts.

>I'm also curious how you test if the game is, um... fun?

Lucky enough for me this is a learning exercise, so I'm not optimizing for fun. I guess you could ask claude code to inject more fun.

Post reply on HN