Varieties of fake alignment (Section 1.1 of "Scheming AIs")

This is section 1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” 

Text of the report here: https://arxiv.org/abs/2311.08379
 
Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
 
Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power

Chapters

• 0:33 1. Scheming and its significance
• 1:29 1.1 Varieties of fake alignment
• 2:30 1.1.1 Alignment fakers
• 4:29 1.1.2 Training-gamers
• 10:14 1.1.3 Power-motivated instrumental training-gamers, or “schemers”
• 11:48 1.1.4 Goal-guarding schemers