normative

Describe the brain in terms of architecture and learning rules

Rather than chasing interpretability of individual learned features (like the 'Golden Gate Bridge' circuit), which will be hopelessly complex, we should describe the brain the way we describe an LLM — in terms of architecture, learning rule, initialization, hyperparameters, and training data — because (per Kording & Lillicrap) a network trained to compute arbitrarily complex things can never be fully interpreted, but the recipe that produced it can be understood.

normativepending

Speaker

Adam Marblestone

Evidence Quote

“we're never going to be able to fully capture that with interpretability, I think. It's just going to just be doing really complicated computations internally. But we can still say that the way it got that way is that it had an architecture and we gave it this training data and it had this loss function. So I want to describe the brain in the same way.”

Source

Adam Marblestone – AI is missing something fundamental about the brain— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:32:22 AM

Your notes

Loading notes...