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

AI coding

geohot.github.io

Post reply on HN
Print view View original

11–20 of 299 posts

Re: AI coding

#11

Post by Earw0rm »

How do we resolve the observable tension here with the fact that self-driving cars are operating right now, relatively successfully, in ten or so major American cities?

Not a billion dollar business yet, maybe, but 300 cars generating five or six figures revenue per year each isn't far off.

(And I say this as someone who is skeptical that totally autonomous cars worldwide will ever be a thing, but you can get to £10Bn far, far before that point. Become the dominant mode of transport in just ONE major American city and you're most of the way there).

Re: AI coding

#13

Post by ChrisMarshallNY »

luckylion wrote: post #7
ChrisMarshallNY wrote: post #2

> AI makes you feel 20% more productive but in reality makes you 19% slower. How many more billions are we going to waste on this? Adderall is similar. It makes people feel a lot more productive, but research on its effectiveness[0] seems to show that, at best, we get only a mild improvement in productivity, and marked deterioration of cognitive abilities. [0] https://pmc.ncbi.nlm.nih.gov/articles/PMC6165228/

Research on _13_ people, that's a very important caveat when evaluating something like adderal.

I’m quite sure that there’s a ton more research on it. The drug’s been around for decades. Lots of time for plenty of studies.

If legitimate research had found it to be drastically better, that study would definitely have been published in a big way.

Unscientifically, I personally know quite a number of folks that sincerely believed that they couldn’t function without it, but have since learned that they do far better on their own. I haven’t met a single one that actually had their productivity decline (after an adjustment period, of course), after giving up Adderall. In fact, I know several, that have had their careers really take off, after giving it up.

Re: AI coding

#14

Post by ur-whale »

I agree that most natural languages are a very poor tool to write code specification in.

Specifically, natural language is:

   - ambiguous (LLMs solve this to a certain extent)

   - extremely verbose

   - doesn't lend itself well to refactoring

   - the same thing can be expressed in way too many different ways, which leads to instability in specs -> code -> specs -> code -> specs loops (and these are essential to do incremental work)
Having something at our disposal that you can write code specs in, that is as easy as natural language yet, more concise, easy to learn and most of all not so anal/rigid as typical code languages are would be fantastic.

Maybe LLMs can be sued to design such a thing ?

Re: AI coding

#15

Post by pydry »

martini333 wrote: post #8

I agree. I use LLM to do things like brainstorm, explaining programming concepts and debug. I will not use it to write code. The output is not good enough, and I feel dumber. I only see the worst of my programming collegues coding with AI. And the results are actual trash. They have no actual understanding of the code "they" are writing, and they have no idea how to actually debug what "they" made, if LLM is not help…

Me too.

I used to be a bit more open minded on this topic but im increasingly viewing any programmers who use AI for anything other than brainstorming and looking stuff up/explaining it as simply bad at what they do.

Re: AI coding

#16

Post by Eikon »

luckylion wrote: post #7
ChrisMarshallNY wrote: post #2

> AI makes you feel 20% more productive but in reality makes you 19% slower. How many more billions are we going to waste on this? Adderall is similar. It makes people feel a lot more productive, but research on its effectiveness[0] seems to show that, at best, we get only a mild improvement in productivity, and marked deterioration of cognitive abilities. [0] https://pmc.ncbi.nlm.nih.gov/articles/PMC6165228/

Research on _13_ people, that's a very important caveat when evaluating something like adderal.

It’s interesting how science can become closer to pseudoscience than proper research through paper-milling.

It seems like that with such small groups and effects you could run the same “study” again and again until you get the result that you initially desired.

Re: AI coding

#17

Post by saejox »

> AI makes you feel 20% more productive but in reality makes you 19% slower. How many more billions are we going to waste on this?

True in the long run. Like a car with a high acceleration but low top speed.

AI makes you start fast, but regret later because you don't have the top speed.

Re: AI coding

#18

Post by demirbey05 »

I started fully coding with Claude Code. It's not just vibe coding, but rather AI-assisted coding. I've noticed there's a considerable decrease in my understanding of the whole codebase, even though I'm the only one who has been coding this codebase for 2 years. I'm struggling to answer my colleagues' questions.

I am not defending we should drop AI, but we should really measure its effects and take actions accordingly. It's more than just getting more productivity.

Re: AI coding

#19

Post by numbers_guy »

demirbey05 wrote: post #18

I started fully coding with Claude Code. It's not just vibe coding, but rather AI-assisted coding. I've noticed there's a considerable decrease in my understanding of the whole codebase, even though I'm the only one who has been coding this codebase for 2 years. I'm struggling to answer my colleagues' questions. I am not defending we should drop AI, but we should really measure its effects and take actions accordingl…

This is the chief reason I don't use integrations. I just use chat, because I want to physically understand and insert code myself. Else you end up with the code overtaking your understanding of it.

Re: AI coding

#20

Post by ur-whale »

I do agree with many points in the article, but not about the last part, namely that coding with AI assist makes you slower.

Personal experience (data points count = 1), as a somewhat seasoned dev (>30yrs of coding), it makes me WAY faster. I confess to not read the code produced at each iteration other than skimming through it for obvious architectural code smell, but I do read the final version line by line and make a few changes until I'm happy.

Long story short: things that would take me a week to put together now take a couple of hours. The vast bulk of the time saved is not having to identify the libraries I need, and not to have to rummage through API documentation.

Post reply on HN