To be clear, I wasn't talking about an actual picture generating model. It was raw GPT trained on just text, asked to write instructions for a paint program to output a unicorn. That's more convincing because it's multiple steps away from the basic task it was trained on. Here, I found the paper, it starts with unicorns and then starts exploring other images, and eventually they delve into way more detail than I actually read. There's a video talk that goes with it.

The trick with trying to "make" an AI do semantics, is that we don't know what semantics is, exactly. I mean, that's kind of what we started out with (remember the old pattern-matching chatbots?) but simpler approaches often worked better. Even the Transformer block itself is barely more complicated than a plain feed-forward network. I don't think that's so much because neural nets are more efficient (they really aren't) but because we were looking for an answer to a question we didn't have.

I think the challenge going forwards is freeing all that know-how from the black box we've put it in, somehow. Assuming we do want to mess with something so dangerous if handled carelessly.