Comment by glenstein
2 hours ago
Tangent on the tangent: I think that's true in a minority of cases and in a majority of AI cases. Though in principle I think it should be possible for an LLM to have access to and faithfully represent its own reasoning.
On the contrary, I would argue that it's true in a totality of AI cases.
To your point, I agree that nominally there should be a way to give conceptual names to paths of weights, and when answering a question, notice which weights were and were not applied and retrospect on that.
That's not what reasoning traces as they currently exist are, though.