[enriquepablo]

LLMs tell you one thing and not its negation, this choice is semantic. "just language in absence of any context or reference" is a set that includes every valid text. The usefulness of LLMs is their ability to mostly respect whatever semantics you establish in the prompt in their choice of output.

[suddenlybananas]

LLMs will definitely tell you a thing and its negation if you prompt them differently.

[ursAxZA]

Isn’t it just symbols in, symbols out? We have hardware that can process long symbol sequences very fast — that’s basically it.