normative

Interpretability should cast a wide net with eyes wide open

Even though high-level probes might seem more appropriate (like using high-level history rather than particle physics to explain who won WWII), interpretability should pursue ground-up understanding as a North Star because models are alien brains lacking human social norms whose learned beliefs and goals are unknown; you want to enter deployment without assuming what deception will look like, casting the widest possible net within a broader safety portfolio of probes, behavioral interrogation, and circuit-level inspection.

normativepending

Speaker

Trenton Bricken

Evidence Quote

“do you really trust—you're about to deploy this system and you really hope it's aligned with humanity—that you've successfully iterated through all the possible ways that it's going to scheme or sandbag”

Source

Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:51 AM

Your notes

Loading notes...