johnswentworth comments on How To Go From Interpretability To Alignment: Just Retarget The Search

johnswentworth 12 Aug 2022 15:52 UTC
LW: 10 AF: 8
0
AF
I indeed think those are the relevant cruxes.
What links here?
- Highlights: Wentworth, Shah, and Murphy on “Retargeting the Search” by RobertM (14 Sep 2023 2:18 UTC; 85 points)