"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs")

This is section 2.2.3 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

• 0:28 2.2.3 “Clean” vs. “messy” goal-directedness
• 9:27 2.2.3.1 Does scheming require a higher standard of goal-directedness?