← Back to context

Comment by vidarh

9 hours ago

They're arguing that we have no evidence that humans have access to our underlying thoughts any more than the models do.

What does that mean though, to “have access to our underlying thoughts”? Humans can obviously mentally do things that are impossible for a language model to do, because it’s trivial to show that humans do not need language to do mental tasks, and this includes things related to thought, so I don’t really get what is being argued in the first place.