But won't that future LLM be able to spew out even more? I mean, I regularly produce stuff I can't comprehend at a later date, why won't the same happen to an LLM?
Because you comprehension grows in time only slightly or not at all and at some point will start to decline. That won't be true for LLMs for some time hopefully. And even then at some point they learn to make stuff in a more "divide and conquer" style so they don't need to understand whole big ball of spaghetti all at once.
I mean, even if we don't understand in our brains, what's stopping people from buliding ever more complex systems with LLMs, until the LLMs themselves can't keep up?
