It's surprising to me that these things are so hard to use well. If you asked me before ChatGPT to guess how the user experience with this kind of technology would be, I would have said I expect it to be as intuitive as talking, almost no friction. I think this is a natural expectation that, when violated, turn a lot of people off.
> intuitive as talking
Except talking is not intuitive. It's an unbelievably hard skill. How many years have you spent on talking until you can communicate like an adult? To convey complicated political, philosophical, or technical ideas? To express your feelings honestly without offending others?
For most people it takes from 20 years to a lifetime. Personally I can't even describe a simple (but not commonly known) algorithm to another programmer without a whitboard.
I was speaking two languages at two years old, and debating political systems by ten. I'm not really sure that talking is actually that hard, depending on your cultural background. The more diverse, the easier you may find it to convey incredibly complex concepts. I'm not an outlier - I'm a boring statistical point.
I've heard plenty of overly complicated explanations of what a monad is. It's also not a complicated concept. Return a partial binding until all argument slots are filled, then return the result of the function. Jargon gets in the way of simple explanations. Ask a kid to explain something, and it will probably be a hell of a lot clearer.
The more experience you have, the harder it often is to draw out something untainted by that experience to give to someone else. We are the sum of our experience, and so its so darn easy to get lost in that, rather than to speak from where the other person is standing.
> I would have said I expect it to be as intuitive as talking, almost no friction
There is so much friction when you try to do anything technical by talking to someone that don't know you, you have to know each other extremely well for there to be no friction.
This is why people prefer communicating in pseudo code rather than natural language when discussing programming, its really hard to describe what you want in words.
For me this is exactely one of the biggest developments as LLMs became available: They 'get it' much more than the previous tech (search engines) and fill in the blanks much more than previously thought possible.
Sure if you leave out too much context you get generic responses but that isn't too surprising.