What made you think of this idea?

The one where you aren’t frustrated by the usage of it.

Yeah, you need to be really brave to setup your system incorrectly.

You’re doing something wrong, maybe ask someone knowledgeable for help with your system. It doesn’t happen to other people.

Can’t confirm, I’m old and a nerd and I love C++

Oh yeah, you absolutely can test it.
And then it gives you (and this is a real example, with real function names removed)

find_something > dirpath
…
rm - rf $dirpath/*
do_something_in_the_dir(dirpath)

And it will work, but on a failure of a first question, instead of failing gracefully it wipes your hard drive clean.
You can find shit like that on the regular Internet, but the difference is, it will be downvoted and some nerd will leave a snarky comment explaining why it’s stupid. When llm gives you that, you don’t have ways to distinguish a working code from a slow boiling trap

As with a lot of things in your life, you think you know something, but actually you don’t.

You. I couldn’t avoid you. That’s what I’m mildly afraid of.

What’s scary is that chatbots will make more people like you.

I see you aren’t grasping the concept, and now are saying some random words to hide this fact. But then again, it is to be expected, we kind of started with the idea that you lack higher cognitive functions

More like how some people are afraid of needles but aren’t afraid of deadly diseases. Their primitive understanding of reality allows them to draw connection between prick and pain, but not between an invisible to the naked eye organism and a gruesome death.

See, this is the problem I’m talking about. You think you can gauge if the code works or not, but even for small pieces (and in some cases, especially for small pieces) there is a world of very bad, very dangerous shit that lies between “works” and “not works”.
And it is as dangerous when you trust it to explain something for you. It’s by definition something you don’t know therefore can’t check.

It’s not that LLM can’t know truth, that’s obvious but besides the point. Its that the user can’t really determine when the lies are, not to the degree that you can be when getting info from a human.
So you really need to check everything, every claim, every word, every sound. You can’t assume good intentions, there are no intentions in real sence of the word, you can’t extrapolate or intrapolate. Every word of the data you’re getting might be a lie with the same certainty as any other word.
It requires so much effort to check properly, you either skip some or spend more time that you would without the layer of lies.

But like why not go to the real sorces directly in the first place? Why add unnecessary layer that doesn’t really add anything?

It is a big deal. There is thr whole set of ways humans can gauge validity of the info, that are perpendicular to the way we interact with fancy autocomplete.
Every single word might be false, with no pattern to it. So if you can and do check it, you just wasting your time and humanity’s resources instead of finding the info yourself in the first place. If you don’t, or if you think you do, it’s even worse, you are being fed lies and believe them extra hard.

Yeah, same. I have to learn now to learn in spite of all the old disillusioned creatures that hated their lives almost as much as they hated students.
And yet, I’m afraid learning from chatbots might be even worse.

Yeah, you know, just like my cat is scared of distant fireworks but doesn’t give a flying fuck about climate change or rise of fascism in our own country.

so much of our lives is made up of people lying

And that’s why we, as humans, know how to look for signs of this in other humans. This is the skill we have to learn precisely because of that. Not only it’s not applicable when you read the generated bullshit, it actually does the opposite.
Some people are mistaken, some people are actively misleading, almost no one has the combination of being wrong just enough, and confident just enough, to sneak their bullshit under the bullshit detector.

It’s not normal for a teacher to get angry. Those people should be replaced by good teachers, not by a nicely-lying-to-you-bot. It’s not a jab at you, of course, but at the system.

The level of psychopathy required from a human to be as blatant at lying as an llm is almost unachievable