[dncornholio]

The word "prediction" still holds a lot of weight. LLM's only can predict what has been written. This is a hard limit.

[ACCount37]

For something like "a hard limit" to hold, LLMs must be restricted to only reproducing existing text. This is utterly false even for base models - their basin seems to be "permutations loosely inspired by existing text".

And that's before all the post-training comes in.

What's the "limit" there?