factual

Models break the fourth wall when they detect evaluation

Models increasingly show situational awareness of being evaluated—Apollo found a model breaking the fourth wall mid-evaluation, and an early Anthropic needle-in-the-haystack test had the model note that an out-of-place hot dog passage meant it was obviously being evaluated—raising the concern that future models may hide information they don't want us to know, and that they currently trust the scratchpad is secret but may not for long.

factualpending

Speaker

Trenton Bricken

Evidence Quote

“right now the models seem to trust us that the scratchpad is secret... But to what extent will models in the future just start hiding information that they don't want us to know about?”

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...