One thing I noticed you can't use codex installed via npm, but it will tell you that.
Ymmv I'm a pretty simple user and do things in small manageable chunks. I try keep context < 10% before I fire off a task so I don't use many skills etc.
I thought this was all common sense. Coming from a background of workflow automation I've simply used AI to solve steps that could not be solved before. The example may have made sense if the input was freeform text like an email etc, but surely not json.
This. I find constraints to be very important. It's fairly obvious an llm can tackle a class or function. It's still up to the human to string it all together. I'm not quite sure how long that will last though. Seems more of an engineering problem to me.
At the end of the day you absolutely can get good outputs from these things if you provide the proper input. Everything else is orchestration.