Hacker News Reader

Comment by ldjkfkdsjnv | Hacker News Reader

The theory is that this solves the data shortage problem, they can generate a ton of chain of reasoning data from what we already have. True iterative improvement, like out of a science fiction novel

These models are going to get embedded deeply into IDE's, like cursor has, and essentially end software development as we know it. A properly written requirements spec, and an engineer, can do the work of 5. Software engineering as done by hand is going to disappear. Saas startups whose moat is a harvard ceo and 5 million in capital will watch their margins disappear. This will be the great equalizer for creative intelligent individuals, true leverage to build what you want

View on HN

> A properly written requirements spec, and an engineer, can do the work of 5.

I do not think this will scale. GPT o1 is presumably good for bootstrapping a project using tools that the engineer is not familiar with. The model will struggle to update a sizable codebase, however, with dependencies between the files.

Secondly, no matter the size of the codebase and no matter the model used, the engineer still has to review every single line before incorporating it into the project. Only a competent engineer can review code effectively.

I respectfully, but completely disagree. Right now with sonnet 3.5 + cursor ide, I'm not writing that much of my own code at my FAANG job. I am generating a ton, passing in documentation from internal libraries, iterating on the result. Most of the time, I just accept its changes.

This is going to rapidly happen. All we need are a few more model releases, not even a step function improvement

Don't you still have to explain your requirement really well to it, in a lot of detail? In a terse language like Python, I might as well just write the code. In a verbose language like Java, perhaps there is more of a value in detailing the requirement.

Not really, most of the changes are straightforward. Also, alot of the time it writes better syntax than i would. Sometimes I write a bunch of psuedo code and hsave it fill in the detials, then write the tests

> Not really

How on earth are you conveying your intent to the model? Or is your intent so CRUDdy that it doesn't need to be conveyed?

It depends on what you're doing.

If you're writing something specific to your particular problem, or thinking through how to structure your data, or even working on something tough to describe in words like UI design, it probably is easier to just code it yourself in most high-level languages. On the other hand, if you're just trying to get a framework or library to do something and you don't want to spend a bunch of time reading the docs to remember the special incantations needed to just make it do the thing you already know it can do, the AI speeds things up considerably.

An abstraction machete. Heh.

This is a wonderful term for it!

I use the same workflow. It’s taking a while for me to learn to sense when it’s getting off track and I need to start a new chat session in general it’s pretty amazing if given very clear guidance at the right moments.

Find harder problems to solve.

I can easily make Claude freak out and run into limits. Claude is amazing but it only works at the abstraction level you ask of it, so if you ask it to write code to solve a problem it'll only solve that immediate problem, it doesn't have awareness of any larger refactorings or design improvements that could be made to improve what solution is even possible.

> I'm not writing that much of my own code at my FAANG job.

> Most of the time, I just accept its changes.

This speaks more about the problems at FAANG, other companies, etc than AI vs a human developer. And AI isn't the real fix.

Are we just repeating things 100x a day or is it still so chaotic and immature? Or are we implying that AI is at a point where it's writing Google Spanner from scratch and you're able to review and confirm it passes transactional tests?

We went from "it's useless because..." - "it outputs gibberish" to "it just copypastes" to "it only works for simple things" to "it can't make Google Spanner from scratch".

> We went from

None of the above.

This isn't about how "smart" AI is.

1. Let's assume it was smart and can update a field spanning 1000s of microservices to deliver this new feature. Is this really something you should celebrate? I'd say no. At this point there should have been better tooling and infrastructure in place.

2. Is there really infinite CRUD to add after >10 years? In the same organization where you need >100s of developers all the time? 1s where you'd ignore code reviews and "just accept its changes"? Whether I write code or my colleagues etc I'd have a meaningful discussion about the proposed changes, the impacts and most likely suggest changes because nothing is perfect.

So again, it's about the environment, the organization or at least this individual case where coding isn't just about adding some lines to a file. And that's with AI or not.

> This speaks more about the problems at FAANG

Right - "most of my work can be done by Sonnet 3.5" doesn't exactly conjure up an image of a high level or challenging job. It seems the challenge with FAANG companies is getting hired, not the actual work most people do there.

Not everyone has the same experience with the replaceability of their job role as you do. I've tried pretty hard and it just doesn't work for me. Admittedly I'm in compilers which makes it a bit harder, but just in general there are a lot of engineers who are in the same relative position.

How would you characterize the type of applications/code you are working on? Can you give an example? How much of your work is architecture/design (software engineering), and how much more like grunt work or systems integration just coding stuff up ?

I think SaaS startups with a Harvard founder and 5 million are going to crush it in the world you describe. The marginal cost of building decreases, but brands, trust, and reach do not follow the same scaling laws.

Access to capital and pedigree are still going to be a big plus.

I dunno man. I just spent a couple hours trying to get it to write functioning code to read from my RTSP stream, detect if my kid is playing piano, and send the result to HomeAssistant. It did not succeed.

How many hours without it?

Not the OP, but in my experience LLMs fail in ways that indicate they will never solve the problem.

Stuck in loops, correct their mistakes with worse mistakes, hallucinating things that don’t exist and being unable to correct.

Working on my own, I have the confidence that I know I can make incremental forward progress on a problem. That’s much preferable.

But when working with an LLM you can still contribute.

That remains to yet be seen, as I kept insisting that an LLM should be able to write this in its entirety with success with "just one more prompt change".

What data shortage problem? I'm not convinced that a shortage of data is the problem with current generation LLMs. This isn't like robotics where every robot is unique and you had to historically start from scratch every time you changed to a different robot. It's more likely that we are running into some sort of generalization bottleneck, because the training process is operating without feedback on the information/semantic level. There is no loss function for "does the code compile?". Instead, the loss function checks "does the output conform to the dataset?".

Which will mean...there is going to be a lot more software?

Probably yeah

a lot more broken software. Companies release broken software intentionally just to be quick to market. Now can you imagine the same, but the "engineers" literally cannot make the product better even if they wanted to. They never learned to code properly. So they can't tell whether the code is good.

a properly written requirements spec is something that doesn't exist in the vast majority of cases.

Such statements are made by management folks who dont code, and somehow think coding can be hand-waved away.

Sure, this tool will improve the productivity of sw engineers, but so did the compiler which came 50 years back.

Reply on news.ycombinator.com