[CuriouslyC]

You shouldn't be. For code bases where context is mostly local they destroy human throughput by comparison. They only fall down hard when used in spaghetti dumpster fire codebases where you have to paste the contents of 6+ files into context or the code crosses a multiple service boundaries to do anything.

A competent engineer architects their systems to make their tools as effective as possible, so maybe your idea of competent is "first order" and you need higher order conception of a good software engineer.

[grogenaut]

could you provide some examples, code or repos and questions where it does a good job for you (question can also just be completion). Obviously you're having really good experiences with the tools that other aren't having. I'd definitely appreciate that over a lot of assurances taht I'm doing it wrong with my spaghetti code.

[CuriouslyC]

Try these:

Take a SQL schema, and ask AI to generate crud endpoints for the schema, then sit down and code it by yourself. Then try generating client side actions and state management for those endpoints. Time yourself, and compare how long it takes you. Even if you're fast and you cut and paste from template work and quickly hand edit, the AI will be done and on a smoke break before you're even a quarter of the way through.

Ask the AI to generate correctly typed seed data for your database, using realistic values. Again, the AI will be done long before you.

Try porting a library of helper functions from one language to another. This is another task where AI will win handily

Also, ask AI to write unit tests with mocks for your existing code. It's not amazing at integration tests but with mocks in play it slays.

[NoGravitas]

Most of the things you list can be done deterministically, without the risk of AI errors. The first one in particular is just scaffolding that Visual Studio has had for Entity Framework and ASP.NET MVC for a decade now. And if you were using, e.g., LISP, you'd just write a DEFCRUD macro for it once, and re-use it for every similar project.

[grogenaut]

Thank you. That was a lot more informative than the argument you were having. And it's now obvious to me the value you're getting and a few areas that would work for me that I'll try. I'm not slapping out crud apps day to day, but can see how I could accelerate myself.

I appreciate it.

[linuxftw]

Your experience mirrors mine. I use ChatGPT or meta for boiler plate code like this. I write golang at my day job, and there's a lot of boiler plat for that language, saves a lot of time, but most importantly, does the tedious boring things I hate doing.

[skydhash]

Why does no one uses snippets or create scaffold for projects? My main requirement for a tool is to be deterministic. So that I don't spend time monitoring it as failure is very distinct from success.

[Jensson]

Those things are a tiny part of the work though and are all about generating boilerplate code. Tons of boilerplate code isn't the hallmark of a great codebase, I don't think many programmers spends more than 10% of their time writing boilerplate code, unless they work at a very dysfunctional org.

It is true it is faster than humans at some tasks, but the remaining tasks were most of the time, you can't gain more than 11% speedup by speeding up 10% of the work.

[grogenaut]

What's your point? The other person is speeding themself up, and it works for them. What's the appropriate bar for speedups. What would be enough to satisfy you? What problems do you have that AI isn't speeding up that you still feel aren't worth spending your brain on?maybe list them and see if the other people has thoughts on how to go about it?

Things don't move forward by saying it can't be done or belittle others accomplishments.

[pdimitar]

> They only fall down hard when used in spaghetti dumpster fire codebases where you have to paste the contents of 6+ files into context or the code crosses a multiple service boundaries to do anything.

So humans do better than them in at least 80% of all code everywhere, if not 95% even? Cool, good to know.

Care to provide some examples to back your otherwise extraordinary claim btw?

[CuriouslyC]

You sure seem invested in hating AI, what's your problem brother?

[pdimitar]

I don't "hate" AI because (1) AI does not exist so how can I hate something that doesn't exist? And (2) I don't "hate" a machine, I cringe at people who make grand claims with zero proof. Yes. Zero. Not small, not infinitesimal -- zero.

I just can't make peace with the fact that I inhabit the same planet as people who can't make elementary distinctions.

[CuriouslyC]

I can't make peace that I'm on the same planet as people who can't use google worth a shit: https://mitsloan.mit.edu/ideas-made-to-matter/how-generative...

And yet somehow want to act high and mighty and be insulting as fuck.

[pdimitar]

You failed to mention the word "can", which is a theoretical.

We can all Google stuff because internet is big and supports anyone's views, which means it's more important than ever to be informed and be able to infer well. Something that you seem to want to defer to sources that support your beliefs. Not nice finding that on a hacker forum but statistical outliers exist.

Live long and prosper. And be insulted, I suppose.

[krfrewH]

You are stealing and laundering my open source code and take the credit, that is the problem.

Fortunately, as pdimitar pointed out, so far it is an ineffective scam that mostly produces LoC.