These people don't seem to know the distinctions you are bringing up. Basically, it's like expecting someone in the middle ages to tell you how a rocket works.

The comments are "evil" or "good" and don't get that "evil and good" are results based on the data and the algorithm employed and how they were introduced to each other.

Chat GPT isn't just one thing. And if it's giving accurate or creative results, that's influenced by prompts, the dataset it is drawing from, and the vagaries of what set of algorithms they are using that day -- I'm sure it's constantly being tweaked.

And based on the tweaks, people have gotten wildly different results over time. I can be used to give accurate and useful code -- because they sourced that data from working code and set it to "not be creative" but it's understanding of human language helps do a much better job of searching for the right code to cut and paste. There's a difference between term papers and a legal document and a fictional story.

The current AI systems have shown they can "seem to comprehend" what people are saying and give them a creative and/or useful response. So that I think, proves it can do something easier like legal advice. A procedural body of rules with specific results and no fiction is ridiculously simple compared to creative writing or carrying on a conversation with people.

We THINK walking and talking are easy because almost everybody does it. However, for most people -- it's the most complicated thing they've ever learned how to do. The hardest things have already been done quite well with AI -- so it's only a matter of time that they can do simpler things.

Getting a law degree does require SOME logic and creativity -- but it's mostly memorizing a lot of statutes, procedures, case law and rules. It's beyond ridiculous if we think THIS is going to be that hard for AI if the can converse and make good art.