I use AI/LLMs hard for my programming. They allow me to do work I could never have done before. But there’s no chance at all of an LLM one shotting anything that I aim to build. Every single step in the process is an intensely human grind trying to understand the LLM and coax it to make the thing I have in mind. The people who are panicking aren’t using this stuff in depth. If they were, then they would have no anxie…
This has been my experience. I tend to use chats, in a synchronous, single-threaded manner, as opposed to agents, in an asynchronous way. That’s because I think of the LLM as a “know-it-all smartass personal assistant”; not an “employee replacement.” I just enjoy writing my own software. If I have a tool that will help me to lubricate the tight bits, I’ll use it.
Occasionally of course it's way off, in which case I have to tell it to stfu ("snooze").
Also it's great at presenting someone else's knowledge, as it doesn't actually know facts - just what token should come after a sequence of others. The other day I just pasted an error message from a system that I wasn't familiar with and it explained in detail what the problem was and how to solve it - brilliant, just what I wanted.