Right. One of the most remarkable side effects of the recent advances in AI has been a swath of the tech industry bleating desperately in unison that whatever an ML model might do, it isn't "real" intelligence because humans are magic and, since tensors don't have that magic, AI can't "really" think.

In fact, it is quite hilarious that in the last 5 years the go-to criticism of state-of-the art AI has switched from "It can only do one specfic thing very well!" to "It can't do any specific thing very well!".

We have really struck a goldmine with unsupervised LLMs. While before the range of forms of intelligence we could cover only contained high performance "specific" intelligence, we now finally have an outpost in low performance "general" intelligence.

All we have to do is perform a pincer movement! Any data is tokens, any models can be interfaced.

I predict models will be trained on DNS-Server data streams.

> Pick any human. I claim there exists some subject that ChatGPT has a better understanding of than this human, based on a surface-level evaluation.

Isn't that a low bar, though? For any human, you can find some subject that that human knows next to nothing about. It's kind of like saying "Google is smarter than humanity because for any human, I can find some fact that a Google search will reveal that that human doesn't know".

Maybe it is a low-bar, that's subjective. But I do mean understanding, not just knowing some facts. You could say that google was the point where we could say "Pick any human. I claim there exists some subjects that Google has more factual knowledge of than this human, based on a pure reproduction based evaluation."

With ChatGPT I claim that it beats humans in real "understanding" of at least some subject

Your claim is trivially disprovable.

Ask ChatGPT over for a family dinner.

How so? ChatGPT understands Chemistry better than me and I attend the family dinner.