Gunnar_Zarncke comments on Barriers to Mechanistic Interpretability for AGI Safety

[Gunnar_Zarncke]

This is not primarily about LLMs, which are Simulators (see also Janus’ Simulators), but about more general systems—AGIs.

[Logan Riggs]

I meant to cover this in the “for different environments” parts. Like if we self-play on certain games, we’ll still have access to those games.