On: Can large language models reason about medical questions?

[dekhn]

Spitting out the results of a bunch of experts is the opposite of reasoning. Or more correctly, it's one limited form of reasoning: an ensemble prediction made from a mixture of experts. That's not an interesting form of reasoning because literally all the decisions are encoded in the weights you apply to the experts.

[rafaelero → dekhn]

You seem very confused and I invite you to think again about what you said.