I recommend everyone in this thread call OpenAI and talk that support agent. I had some issue and tried to trip it up, spoke naturally and ambiguously, and it actually did a pretty good job.
I feel like this is an example of Sturgeon's Law - almost every thread can be filled with complaints, because most everything is crap.
What's more interesting is the cases where it isn't. Those prove that the idea can be good, but it's obviously a lot more work than "have an LLM answer customer questions".
I've asked my bank's support agent about an issue with an app, it also didn't stumble producing a thorough and convincing answer. Entirely wrong, though. Using an LLM to reverse engineer the app turned out to be a much more productive approach.
What's more interesting is the cases where it isn't. Those prove that the idea can be good, but it's obviously a lot more work than "have an LLM answer customer questions".