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

631–640 of 870 posts

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

#631

Post by satvikpendem »

pards wrote: post #575
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…

> I happen to rent and can't keep This is my fear - what happens if the AI companies can't find a path to profitability and shut down?

This is why local models are so important. Even if the non-local ones shut down, and even if you can't run local ones on your own hardware, there will still be inference providers willing to serve your requests.

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

#632

Post by chickensong »

mattmanser wrote: post #455
bedrio wrote: post #410

Earlier quoted context omitted.

I'm worried about that too. If the error is reproducible, the model can eventually figure it out from experience. But a ghost bug that I can't pattern? The model ends up in a "you're absolutely right" loop as it incorrectly guesses different solutions.

Are ghost bugs even real? My first job had the Devs working front-line support years ago. Due to that, I learnt an important lessons in bug fixing. Always be able to re-create the bug first. There are no such thing as ghost bugs, you just need to ask the reporter the right questions. Unless your code is multi-threaded, to which I say, good luck!

They're real at scale. Plenty of bugs don't suface until you're running under heavy load on distributed infrastructure. Often the culprit is low in the stack. Asking the reporter the right questions may not help in this case. You have full traces, but can't reproduce in a test environment.

When the cause is difficult to source or fix, it's sometimes easier to address the effect by coding around the problem, which is why mature code tends to have some unintuitive warts to handle edge cases.

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

#633

Post by runarberg »

Ronsenshi wrote: post #462
tayo42 wrote: post #438

Earlier quoted context omitted.

Anecdotally, i burned out pretty hard and basically didn't open a text editor for half a year (unemployed too). Eventually i got an itch to write code again and it didn't really feel like I was really worse. Maybe it wasn't long enough atrophy but code doesn't seem to quite work like language though ime.

Six months is definitely not long enough of a break for skills to degrade. But it's not just skills, as I wrote in another comment, the biggest thing is knowledge of new tools, new versions of language and its features. I'd say there's at most around 2 years of knowledge runtime (maybe with all this AI stuff this is even shorter). After that period if you don't keep your knowledge up to date it fairly quickly becomes…

I would imagine there is probably some reverse S-curve of skill loss going on. The first year you may retain like 90% (and the 10% are obscure words, rare grammar structures, expressions, etc.), then in the next 2 years you loose more and more every year, and by the 3rd year you’ve lost like 50% of the language, including some common words, useful grammar structures, but retain common greetings, basic structures, etc. and then after like year 5 the regression starts to slow down and by year 10 you may still know 20%, but it is the most basic stuff, and you won‘t be able to use the language in any meaningful way.

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

#634

Post by jv22222 »

nemothekid wrote: post #236
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 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 don't really understand the code "in my bones".

Man, I absolutely hate this feeling.

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

#635

Post by andy_ppp »

throw10920 wrote: post #628
aswegs8 wrote: post #619

Earlier quoted context omitted.

"For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing, produced by external characters which are no part of themselves, will discourage the use of their own memory within them. You have invented an elixir not of memory, but of reminding; and you offer your pupils the appearance of wisdom, not true wisdom, for they…

Writing/reading and AI are so categorically different that the only way you could compare them is if you fundamentally misunderstand how both of them work. And "other people in the past predicted doom about something like this and it didn't happen" is a fallacious non-argument even when the things are comparable.

I read grandparent comment as saying people have been claiming that the sky is falling forever… AI will be both good for learning and development and bad. It’s always up to the individual if it benefits them or atrophies their minds.

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

#636

Post by MillionOClock »

pards wrote: post #575
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…

> I happen to rent and can't keep This is my fear - what happens if the AI companies can't find a path to profitability and shut down?

Recently I was thinking about how some (expensive) customer electronics like the Mac Studio can run pretty powerful open source models with a pretty efficient power consumption, that could pretty easily run on private renewable energy, and that are on most (all?) fronts much more powerful than the original ChatGPT especially if connected to a good knowledge base. Meaning that aside from very extreme scenarios I think it is safe to say that there will always be a way not to go back to how we used to code, as long as we can offer the correct hardware and energy. Of course personally I think we will never need to go to such extreme ends... despite knowing of people who seem to seriously think developed countries heavily run out of electricity one day, which, while I reckon there might be tensions, seems like a laughable idea IMHO.

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

#637

Post by lucianbr »

netcraft wrote: post #618

> Tenacity. 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. This is true to an extent for sure and they will go much longer than most engineers without getting "tired", but I've def seen both sonnet and opus give up multiple times. They've upd…

The glorified autocomplete. Why would the LLM "work on something else then get back on this", is it's subconscious going to solve the problem during that time?

But because people say it, it says it too. Making sense is optional.

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

#638

Post by whistle650 »

throw10920 wrote: post #628
aswegs8 wrote: post #619

Earlier quoted context omitted.

"For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing, produced by external characters which are no part of themselves, will discourage the use of their own memory within them. You have invented an elixir not of memory, but of reminding; and you offer your pupils the appearance of wisdom, not true wisdom, for they…

Writing/reading and AI are so categorically different that the only way you could compare them is if you fundamentally misunderstand how both of them work. And "other people in the past predicted doom about something like this and it didn't happen" is a fallacious non-argument even when the things are comparable.

To understand the impact on computer programming per se, I find it useful to imagine that the first computer programs I had encountered were, somehow, expressed in a rudimentary natural language. That (somewhat) divorces the consideration of AI from its specific impact on programming. Surely it would have pulled me in certain directions. Surely I would have had less direct exposure to the mechanics of things. But, it seems to me that’s a distinction of degree, not of kind.

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

#640

Post by wjSgoWPm5bWAhXB »

throw10920 wrote: post #628
aswegs8 wrote: post #619

Earlier quoted context omitted.

"For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing, produced by external characters which are no part of themselves, will discourage the use of their own memory within them. You have invented an elixir not of memory, but of reminding; and you offer your pupils the appearance of wisdom, not true wisdom, for they…

Writing/reading and AI are so categorically different that the only way you could compare them is if you fundamentally misunderstand how both of them work. And "other people in the past predicted doom about something like this and it didn't happen" is a fallacious non-argument even when the things are comparable.

yes, but people just really like to predict dooms and they also like to be convinced that they live in some special era in human history
Post reply on HN