[sfink]

Came to say this.

Chess move training data is much more likely to consist of examples of people trying to win than it is to consist of random legal or even illegal moves. You could argue that the intention belongs to the people providing the input and not the LLM, but that seems like a distinction without a difference.

[labrador]

True, because the LLM has no intention (sorry Blake Lemoine.) I'm puzzled about what people say about AI, when to me it is simply a talking library. I started going to public libraries at a young age (I'm 66) so to me I'm talking to the authors of the books, not some mysterious conscious machine.