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

YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

fastcompany.com

Post reply on HN
Print view View original

91–100 of 108 posts

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#91

Post by ethbr1 »

pjc50 wrote: post #34
apimade wrote: post #11

This is what happens when you give people tools that let them achieve an outcome, without necessarily giving them the judgement or expertise to know whether the outcome is any good. If you asked me to build a house, I could probably assemble something that would stand for a few months. Hopefully. It might even keep the rain out. But it might also fall on my head, because I do not know enough about building houses to…

I think this is where aggregate effects have to be considered. One person building an idiosyncratic house out of found materials: neat little project. One million people doing so: shanty town that can be seen from orbit and is a disaster waiting to happen. The Web already had a problem with externalizing costs onto users. Both the simple cost of poorly executing websites (power, mobile data, time), and more subtle on…

Imho, this is the biggest concern for civilization-scale cost of AI being deployed all fields.

On the one hand: Amazing power! Look at how much more output everyone is generating!

On the other hand: Society maintaining guardrails that were engineered around human failure modes are completely inappropriate for bounding something that makes 10% random errors everywhere.

To re-use an example upthread... what if you had an LLM that could build an entire house? Foundation? Plumbing? Electrical? Roofing? Septic?

And then we let everyone guide that LLM to build their own house.

We'd drastically increase the housing supply, but every house would have 10% of its systems built incorrectly.

We could fix that by requiring grounding in building codes, automated reviews, etc. But none of that hard work updating guardrails is something AI accelerationists are interested in working on.

So you end up with a society where every septic system has a 10% chance of being misdesigned...

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#92

Post by danaris »

titanomachy wrote: post #33

> The larger point is that while AI coding tools make it easy to pump out lots of code, it’s really (still) the quality of the code that matters. Quantity, in other words, doesn’t necessarily equal quality. They didn't provide any evidence for this point. They showed that the code is bad quality, but not that it matters that it's bad.

It never matters.

Until it does.

And if you've been relying on quality not mattering, then when it starts mattering—when you get hit by a security bug, or unexpected data loss, or your software is inexplicably displaying goatse—then you have no way to proceed without learning how to do quality.

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#94

Post by tavavex »

Are there ANY institutions remaining that haven't completely succumbed to the Church of Quantity? It was already bad before AI, on the web especially, and now that it's widely used it feels like no one cares about anything anymore. Ask any developer and they would gladly offer you 100x the code shipped 10x faster, but recoil at the idea of making it even 1.5x better or more performant. Everyone has accepted that quality doesn't matter because... you can remake the same flawed thing ten times in an hour? Code is discarded just as quickly as it was spawned into existence, never having been worth anything to anyone. But at least some very influential people get to take the speed they firehosed this code at and brag about it. Not what they made, not its quality, but about a metric that only builds street cred among a million people doing the same thing and not really going anywhere.

I knew that the elite of the tech world never really cared, they were just forced to. They don't care about what they make as long as some numbers and statements look good so they get more money at any cost. What's shocking is that everyone else agrees with them - that in all contexts, quality is dead and less than worthless. Just stop caring bro.

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#95

Post by tasuki »

zerof1l wrote: post #35

Measuring success in LoC is so wrong… It's like bragging that you took 10,000 steps to reach the store by walking in circles when you could have taken 500 steps if you just walked straight. The end result is the same. AI has a tendency to generate more code than necessary. It keeps re-inventing things, and every time you ask it to add a new feature or fix something, it just keeps on piling the code. I now periodicall…

> It's like bragging that you took 10,000 steps to reach the store by walking in circles when you could have taken 500 steps if you just walked straight. The end result is the same.

The case is different with LoC though: the more the worse. I'd much maintain the thing written in 500 lines than the one written in 10,000 lines.

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#96

Post by PunchyHamster »

apimade wrote: post #11

This is what happens when you give people tools that let them achieve an outcome, without necessarily giving them the judgement or expertise to know whether the outcome is any good. If you asked me to build a house, I could probably assemble something that would stand for a few months. Hopefully. It might even keep the rain out. But it might also fall on my head, because I do not know enough about building houses to…

> If you asked me to build a house, I could probably assemble something that would stand for a few months. Hopefully. It might even keep the rain out. But it might also fall on my head, because I do not know enough about building houses to be confident that it won’t.

Oh no. You'd go and research that, look at existing stuff, read about it, look at tutorials and while still making a ton of mistakes at least try to follow best practices.

People don't do that when they use AI to do task unfamiliar with them. They look at it working and just okay it the moment it "looks okay". They don't even ask the AI followup questions, just accept whatever

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#98

Post by 27183 »

ethbr1 wrote: post #91
pjc50 wrote: post #34

Earlier quoted context omitted.

I think this is where aggregate effects have to be considered. One person building an idiosyncratic house out of found materials: neat little project. One million people doing so: shanty town that can be seen from orbit and is a disaster waiting to happen. The Web already had a problem with externalizing costs onto users. Both the simple cost of poorly executing websites (power, mobile data, time), and more subtle on…

Imho, this is the biggest concern for civilization-scale cost of AI being deployed all fields. On the one hand: Amazing power! Look at how much more output everyone is generating! On the other hand: Society maintaining guardrails that were engineered around human failure modes are completely inappropriate for bounding something that makes 10% random errors everywhere. To re-use an example upthread... what if you had…

> We could fix that by requiring grounding in building codes, automated reviews, etc.

It's an open question whether, with all those guardrails, AI would provide any speedup.

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#99

Post by chrisandchris »

> Once Garry’s agent observed the usage data of his site, it would have corrected all these mistakes without Gregorein writing the thread.

That struck me most and that's why we (software developers) are never going to be engineer.

Consider a doctor just trying ang going along if the patient survives. A brige constructor doing something and after each car that passes fixing problems. A car manufacturer trying new brakes in production without testing. A builder starting to build a house and fix it while people already live there. The list could go on.

It's sad to see a profession on such a decline. I use AI myself, but please please keep doing something _professionally_ or stop doing it as your profession.

Re: YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

#100

Post by Voultapher »

wayland_jeremy wrote: post #80
operation_moose wrote: post #24

Earlier quoted context omitted.

AI feels to me like having access to someone who got a D in literally every single course offered at a university. If you don't know anything about the subject they are smarter than you. If you do know the subject its unsettling how bad they are. Basically the Gell-Mann effect: > The phenomenon of a person trusting newspapers for topics which that person is not knowledgeable about, despite recognizing the newspaper a…

We're trying to up the GPA on the code quality exam by giving them access to structural metrics calculated on graph representations of the programs they write. Hoping this is the study guide template they need to start getting an A in minimizing slop, even if they're actually a D student. They're good at optimizing against scores... https://github.com/Krv-Labs/topos

Good on you for trying, and I'm not saying it can't improve things. Optimizing for structural metrics is still only as good as the metrics. I can say with confidence that no metric exists for good design, because good design is art. Art requires creativity and the evaluation lies in the eye of the beholder. It also doesn't help with the bigger picture, AIs often do the wrong thing because they have been tasked to do the wrong thing.
Post reply on HN