For example, I now use GPT3 for every single code debugging problem that I have.
I input the bug/problamatic code into the service, ask it for an answer, and then I take the code and see if it fixes my problem I was having.
It doesn't work half the time, but thats fine. Then I just figure out the bug the normal way.
But the other half the time, it immediately solves my problem, and then I run my code and it works/ does what I want.
How do you know when to dig through those obscure manuals?
It seems to me that it'd be more useful when:
a) I don't care whether the text says things which are not true
Write me a poem about ...
b) I care, and will have to verify it's results, but that cost is worth it
Generate some test data ...
I think we're at a very dangerous intersection between an apparent decline in American's ability to detect nonsense and an automated way to create convincing nonsense.
> It is basically like having an incredibly smart engineer/scientists/philosopher/etc that can explain things quite well, but for pretty much every field.
I like to think about it like asking questions to a well read but dishonest student during an oral exam. They know some things, and try really hard to answer every question, even resort to making things up in hope of getting a passing grade.