Comment by jillesvangurp | Hacker News Reader

Comment by jillesvangurp | Hacker News Reader

Parent Full thread

The relevant question is who is going to pay you to write code manually. It's something that's increasingly hard to justify. The answer is of course that people are not paying for code to be written or generated but for some problem to be solved. Whoever does that with the least amount of drama and cost gets the business. And using AI tools just allows for compressing the timelines a bit in a way that is hard to ignore.

Most code out there isn't all that great. I've been in this industry since the nineties. There are a lot of not so great software engineers doing mediocre work. People are romanticizing how great and magnificent their code is (or used to be). The reality of manually crafted code is of course a lot less flattering. Many code bases become hard to maintain over time and are riddled with bugs. And it's not like sloppy code is a new thing. Poorly executed software projects have been very common for a long time. That's not going to go away.

I personally am advocating for writing small amounts of code because I think it makes you more productive

Spending a day manually reworking the architecture in my experience can save you $1000s in tokens and weeks of headaches.

We’re trying to build a software factory with hands tied behind our back

>There are a lot of not so great software engineers doing mediocre work.

Yeah, and they are all producing 10x as much mediocre work now.

> The relevant question is who is going to pay you to write code manually.

Hopefully companies in the industries where software quality matters and is regulated, e.g.: medicine, aviation, nuclear, etc.

Although this market is relatively small.

You seem to assume that people still have an inherent advantage here. Mostly those sectors compensate for well documented human failures with very rigid and expensive processes and testing. And of course despite that, stuff still goes wrong occasionally.

I actually think AI based automation is going to be a key enabler in those kinds of strict environments as well. Recent work on identifying e.g. security bugs seems to be resulting in a lot of improvement that has somehow escaped decades of human scrutiny. With good quality harnesses (manual or automated), I don't see any big objection against using generated code here.

There are ways humans have an advantage. Not in the line by line code, but in the experience of having the whole mental model in your head.

Writing some code with the whole context in your head is the human advantage.

I’m not precious about that code. Maybe it needs to be rewritten by an agent. Or we could build good abstractions so it’s trivial to see the system. We could also use systems that by their design force us + agents away from security, performance, etc

Sadly, AI can process semantic vectors in latent space much more effectively than any human.

Reply on news.ycombinator.com