factual

Models have an 'I don't know' circuit gated by name recognition

Models retrieve facts via circuits that include an awareness of when they don't know: by default an 'I don't know' circuit fires, but recognizing a known entity inhibits it; crucially this inhibition triggers only on the name, so recognizing a famous name like Andrej Karpathy turns off 'I don't know' even when the model lacks the specific fact (his papers), forcing it to confabulate—a mechanism that enables downstream predictions about hallucination.

factualpending

Speaker

Trenton Bricken

Evidence Quote

“if you ask it, "Who is Michael Batkin?" —which is just a made-up fictional person— it will by default just say, "I don't know." It's only with Michael Jordan or someone else that it will then inhibit the "I don't know" circuit.”

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...