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

221–230 of 870 posts

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

#221

Post by krupan »

fooker wrote: post #94
einrealist wrote: post #55

> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. Somewhere, there are GPUs/NPUs running hot. You send all the neces…

> It might become cheaper or it might not If it does not, this is going to be first technology in the history of mankind that has not become cheaper. (But anyway, it already costs half compared to last year)

There are plenty of technologies that have not become cheaper, or at least not cheap enough, to go big and change the world. You probably haven't heard of them because obviously they didn't succeed.

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

#222

Post by root_axis »

fooker wrote: post #94
einrealist wrote: post #55

> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. Somewhere, there are GPUs/NPUs running hot. You send all the neces…

> It might become cheaper or it might not If it does not, this is going to be first technology in the history of mankind that has not become cheaper. (But anyway, it already costs half compared to last year)

Not true. Bitcoin has continued to rise in cost since its introduction (as in the aggregate cost incurred to run the network).

LLMs will face their own challenges with respect to reducing costs, since self-attention grows quadratically. These are still early days, so there remains a lot of low hanging fruit in terms of optimizations, but all of that becomes negligible in the face of quadratic attention.

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

#223

Post by freediver »

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…

My experience is the opposite - I haven't used my brain more in a while.. Typing characters was never what developers were valued for anyway. The joy of building is back too.

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

#224

Post by vindex10 »

languid-photic wrote: post #63
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.

They build Claude Code fully with Claude Code.

Ah, now I understand why @autocomplete suddenly got broken between versions and still not fixed )

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

#225

Post by redox99 »

einrealist wrote: post #55

> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. Somewhere, there are GPUs/NPUs running hot. You send all the neces…

> And you most likely do not pay the actual costs.

This is one of the weakest anti AI postures. "It's a bubble and when free VC money stops you'll be left with nothing". Like it's some kind of mystery how expensive these models are to run.

You have open weight models right now like Kimi K2.5 and GLM 4.7. These are very strong models, only months behind the top labs. And they are not very expensive to run at scale. You can do the math. In fact there are third parties serving these models for profit.

The money pit is training these models (and not that much if you are efficient like chinese models). Once they are trained, they are served with large profit margins compared to the inference cost.

OpenAI and Anthropic are without a doubt selling their API for a lot more than the cost of running the model.

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

#226

Post by xienze »

sailfast wrote: post #204
gtowey wrote: post #105

Earlier quoted context omitted.

The value extortion plan writes itself. How long before someone pitches the idea that the models explicitly almost keep solving your problem to get you to keep spending? Would you even know?

That’s far-fetched. It’s in the interest of the model builders to solve your problem as efficiently as possible token-wise. High value to user + lower compute costs = better pricing power and better margins overall.

> It’s in the interest of the model builders to solve your problem as efficiently as possible token-wise.

Unless you’re paying by the token.

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

#227

Post by zetazzed »

Macha wrote: post #80

> - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? Starcraft and Factorio are exactly what it is not. Starcraft has a loooot of micro involved at any level beyond mid level play, despite all the "pro macros and beats gold league with mass queens" meme videos. I guess it could be like Factorio if you're playing it by plugging together blueprint books from o…

It's like the Victoria 3 combat system. You just send an army and a general to a given front and let them get to work with no micro. Easy! But of course some percentage of the time they do something crazy like deciding to redeploy from your existential Franco-Prussian war front to a minor colonial uprising...

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

#228

Post by simonw »

bflesch wrote: post #182
simonw wrote: post #132

Earlier quoted context omitted.

Have you tried showing it a copy of your coding standards? I also find pointing it to an existing folder full of code that conforms to certain standards can work really well.

Yeah let's share all your IP for the vague promise that it will somehow work ;)

You just gave me a revelation as to why some people report being unable to get decent results out of coding agents!

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

#229

Post by gsk22 »

simianwords wrote: post #122
Macha wrote: post #85

Earlier quoted context omitted.

Which is equal parts praise and damnation. Claude Code does do a lot of nice things that people just kind of don't bother for time cost / reward when writing TUIs that they've probably only done because they're using AI heavily, but equally it has a lot of underbaked edges (like accidentally shadowing the user's shell configuration when it tries to install terminal bindings for shift-enter even though the terminal it…

i haven't used Claude Code but come on.. it is a production level quality application used seriously by millions.

If you haven't used it, how can you judge its quality level?

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

#230

Post by krupan »

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 been thinking along these lines. LLMs seem to have arrived right when we were all getting addicted to reels/tic tocks/whatever. For some reason we love to swipe, swipe, swipe, until we get something funny/interesting/shocking, that gives us a short-lasting dopamine hit (or whatever chemicals it is) that feels good for about 1 second, and we want MORE, so we keep swiping.

Using an LLM is almost exactly the same. You get the occasional, "wow! I've never seen it do that before!" moments (whether that thing it just did was even useful or not), get a short hit of feel goods, and then we keep using it trying to get another hit. It keeps providing them at just the right intervals for people to keep them going just like they do with tick tock

Post reply on HN