Fooling yourself into thinking the LLMs are "understanding" what you are saying or asking is a trap. The output you get may be useful, but it is not due to any sort of understanding.

The elements of human work you mentioned are why it can be both rewarding and painful to interact with humans, but at the end of the day it is important to keep trying to do that work/keep trying to interact with each other. I don't know if we want to go back to cubicles where we just talk to robots all day. Of course some work environments are just awful, and there is not much remedy for that.

It’s going to sound delusional, but my own understanding of my understanding is that there’s probably no such thing, only a feeling of familiarity and some heuristics.

All I do is invoke “pictures” of semantic blobs in my mind, and my unconscious parts pull up more “pictures” in connection to that. Which I verbalize in turn, apply logic checks, and thus get this feeling that I’m meaningfully thinking about something, a sensation of comprehension. I could be even blatantly wrong about something, misunderstanding doesn’t feel any different in the moment.

And reasoning models (try to) capture that. The underlying processes are certainly different, it’s a Chinese Room alright - but if my own understanding is an illusion, the fact that machine model of it isn’t how I do it myself (but only a statistical approximation) doesn’t seem to matter - at least not for inputs and outputs between two black boxes (me or model).

I just don’t believe in p-zombies any more than I believe in Santa, I guess.

>> Fooling yourself into thinking the LLMs are "understanding" what you are saying or asking is a trap. The output you get may be useful, but it is not due to any sort of understanding.

I hear this a lot but I think it's a matter of semantics and ultimately not very useful. I don't care whether the LLM understands me the way a human would. I use the LLM to get useful output. I want it to do something and it does that thing.