> we don't fully know what drives the voice in LLMs

Who is "we"? I, working in an LLM startup, know exactly what drives the base "voice" in the LLMs we train, because we have a process to select for it. OpenAI and Anthropic surely do too. Saying broadly that something is not well-understood in a scientific paper because it's not understood to casual observers is, uh, not very rigorous.

> The strange thing is that the base models (before RLHF) use the "experiential" voice, even though they are not incentivized to do that.

(Replying to your quote from another comment)

This is a matter of the training material. We have trained models that do not do that. I'm not exactly divulging trade secrets here. It should be really, really obvious that if you train a model on chat-conversation-like patterns of speech it will infer probabilities for how to continue a textual sample that will differ from the probabilities learned from being trained on narration, prose, or informational patterns of speech, even without RLHF.

So, it was obvious why Open AI models started inserting references to goblins and pixies it’s conversation- references that had to be suppressed?

I feel your pain. It is really obvious.