[ruthmarx]

LLMs are not at a point where we should be treating them as a solution to any software engineering issue, period.

[nprateem]

I've used it to write horrendously complex queries across multiple tables. It can do things I don't know how to and that would have taken significant time to learn. All I know is it works and it's performant when you tell it to be.

It's been particularly helpful for aggregations, subqueries etc. You may not think LLMs are there yet but my project is proof. Try it yourself.

[ruthmarx]

> It can do things I don't know how to and that would have taken significant time to learn. All I know is it works

Until it fucks up and you have no clue how to fix it, and either does the LLM.

[nprateem]

Or just read the code like I would if a colleague had written it, or do you think it's chucking out assembler?

[ruthmarx]

What good will reading the code do you when by your own admission you can't understand it?

[nprateem]

I said I couldn't write it, not that I suddenly became unable to reason or understand programming.

[ruthmarx]

You said you had no interest in learning it.

If you didn't learn it, you don't know it.

It doesn't matter if you can reason or 'understand programming' if you haven't learned what is necessary to understand this particular piece of programming.

Or is it that you think you can 'reason or understand' any piece of programming? And you possibly assume that is easier, to read what an LLM generates rather learning what is necessary to write it yourself?

[LtWorf]

Spending time to learn? Nah better never learn and put together barely working stuff that nobody dares to change!

This isn't something new.

[9dev]

Yet people do, will continue doing so, and it works. Trying to stuff the toothpaste back into the tube isn’t going to work, insisting on people just using plain text mail, or stop calling the pound symbol hashtag. It’s just old men yelling at clouds.