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

747s and coding agents

carlkolon.com

Post reply on HN
Print view View original

81–90 of 97 posts

Re: 747s and coding agents

#81

Post by demorro »

bornfreddy wrote: post #79
demorro wrote: post #36

Earlier quoted context omitted.

> Does this mean you'd be incapable of learning anything? Yes. This strikes me as obvious. People don't have the sort of impulse control you're implying by default, it has to be learnt just like anything else. This sort of environment would make you an idiot if it's all you've ever known. You might as well be saying that you can just explain to children why they should eat their vegetables and rely on them to be rati…

I agree with your premise, but this example I strongly disagree with: > You might as well be saying that you can just explain to children why they should eat their vegetables and rely on them to be rational actors. YES! Explain to them, and trust them. They might not do exactly as you wish for them, but I'll bet you don't do exactly as you wish for yourself either. The children need your trust and they must learn how…

You're right, it was a bad example. I also don't eat my vegetables. I was more trying to make the point that most of us are not rational actors either, was just using children as a convenient proxy, unfairly.

Re: 747s and coding agents

#82

Post by bornfreddy »

cortesoft wrote: post #70
braebo wrote: post #65

Earlier quoted context omitted.

Or we can just do art or live short, simple lives now that we won capitalism and our basic needs can be automated in a global socialist utopia.

I don’t really like making art though. I like programming.

That is art, when done properly.

Re: 747s and coding agents

#83

Post by 0x00cl »

cafebabbe wrote: post #77
0x00cl wrote: post #61

Earlier quoted context omitted.

> We should be very concerned for the next generation. When you have the constant temptation of digging yourself out of a problem just by asking an LLM how will you ever learn anything? This is just the same concern whenever a new technology appears. * Socrates argued that writing would weaken memory, that it would create only superficially knowledge but incapable of really understanding. But it didn't destroy it. It…

Socrates was proven dead wrong by neurobiology. LLMs making you dumber is far from being "disproven" by science. Quite the opposite https://arxiv.org/abs/2506.08872

I'm not sure what you mean by Socrates was proven dead wrong.

The study you linked doesn't show that people are becoming dumber because of LLMs, its just showing that when you offload tasks to these tools your brain engages less in that specific task, just like you'd do with a calculator, instead of doing complex calculations on paper, the calculator will do them for you, or when writing and using a spell-checker or using a search engine, instead of opening a book and searching. The question is whether in the long-term cognitive capacity is reduced, and like I said before this argument predates LLMs (All the way back to Socrates)

Also, take the study with a grain of salt as this is a small sample with only 54 participants for a single task on a short term study.

Personally, I believe LLMs just allows us to have a higher level of abstraction.

Re: 747s and coding agents

#85

Post by MeanEYE »

aryehof wrote: post #66
cedws wrote: post #24

We should be very concerned for the next generation. When you have the constant temptation of digging yourself out of a problem just by asking an LLM how will you ever learn anything? My biggest lessons were from hours of pain and toil, scouring the internet. When I finally found the solution, the dopamine hit ensured that lesson was burned into my neurons. There is no such dopamine hit with LLMs. You vaguely try to…

My concern is also, how will programming and software design ever improve?

In my eyes, it will be same as introduction of garbage collectors. It will help to a degree, make people more lazy along the way and cause some additional and brand new issues. But over all very little will change as for serious implementations human intellect is still going to be the primary actor and AI will be disallowed.

Re: 747s and coding agents

#86

Post by MeanEYE »

eastbound wrote: post #26
cedws wrote: post #24

We should be very concerned for the next generation. When you have the constant temptation of digging yourself out of a problem just by asking an LLM how will you ever learn anything? My biggest lessons were from hours of pain and toil, scouring the internet. When I finally found the solution, the dopamine hit ensured that lesson was burned into my neurons. There is no such dopamine hit with LLMs. You vaguely try to…

At the beginning of the internet, I used to save all webpages where I’d find info, just in case I would be stuck without a connection or if the website removed it. I had parts of the MDN. The internet never fell. I bet it’ll be the same with AI. You will never not have AI. The big difference is the internet was a liberation movement: Everything became open. And free. AI is the opposite: By design, everything is close…

Not only that. AI will have increasingly diminishing returns as it relies on good quality human written code. As that starts being less and less true, quality of generated code will also suffer since at some point AI will train from AI generated content.

Re: 747s and coding agents

#87

Post by MeanEYE »

skepticATX wrote: post #3

Reviewing code is absolutely different from writing it, and in my opinion much harder if the goal is more than surface level understanding. This is what I am still grappling with. Agents make more productive, but also probably worse at my job.

The biggest problem in my head with AI generated code is that its mistakes are subtle but can still be critical. There will be a point where people don't understand generated code and just leave it unmodified allowing other code to pile up and depend on it. At that point you no longer have a bug, but a new feature. Also, AI doesn't grasp things on a big scale, just shits out output with highest score. This doesn't mean output is a great fit for your project or for upcoming plans.

Re: 747s and coding agents

#88

Post by northfield27 »

I have also felt something similar.

A few days back, I tried to implement a PDF reader by pure vibe coding. I used all my free Antigravity, Cursor, and Co-pilot tokens to create a half-baked, but working Next.js PDF-reader that (to be honest) I wouldn't have glued together without 2 weeks of work. As an MLE, I have done negligible web development using JavaScript and have mostly worked with Python and C.

But the struggle actually started after the free tokens were exhausted. I was feeling anxious to even look into those Next.js files. I am not able to describe, but it was probably some kind of fear - fear of either not being able to debug/implement a new feature, or not willing to put in precious hours (precious because of FOMO that I could do something cool with AI-paired vibe coding) to understand and build the feature myself.

I abandoned that project since that day. Haven't opened it yet - partly because I am waiting for the renewal of free tokens.

Re: 747s and coding agents

#89

Post by scuff3d »

jeffrwells wrote: post #68
scuff3d wrote: post #52

What the fuck are people working on where it's possible for the LLM to just add entire features. Refactors and class/method level code can be impressive, anything highly structured with good guard rails. As soon as things start to reach beyond that it falls to absolute garbage.

I built this entire app on ios + website without opening an IDE. https://www.gophergolfer.com/iphone NextJS, Rails, GraphQL, React Native Certainly wasn't one-shot for all of it but case in point it has dozens and dozens of "features" all LLM implemented

Is the source code available?

Re: 747s and coding agents

#90

Post by scuff3d »

bitwize wrote: post #63
scuff3d wrote: post #52

What the fuck are people working on where it's possible for the LLM to just add entire features. Refactors and class/method level code can be impressive, anything highly structured with good guard rails. As soon as things start to reach beyond that it falls to absolute garbage.

There are companies building entire applications, indeed replicating the functionality of existing SaaS applications to test their original applications,with no humans in the development loop. We're looking at the twilight of programming as a human skill. The LLMs are just that good.

I mean... It takes 10 minutes of testing to know this is bullshit. At least in the near term. I've sat with an agent and played the part of a vibe coder. Not looking at the code, frankly providing more guidance and feedback then a vibe coder could, and even in a thousand line app it falls to absolute shit fast. It does get something that "technically" works, but it will collapse in on itself in no time.

The act of designing software might be changing, less writing the actual code, but someone who knows what the fuck they're doing still has to guide the ship.

Post reply on HN