Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs")

This is section 2.3.1.2 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 2.3.1.2 Adequate future empowerment
• 1:22 2.3.1.2.1 When is the “pay off” supposed to happen?
• 4:20 2.3.1.2.2 Even if the model’s values survive this generation of training, will they survive long
• 8:16 2.3.1.2.3 Will escape/take-over be suitably likely to succeed?
• 10:05 2.3.1.2.4 Will the time horizon of the model’s goals extend to cover escape/take-over?
• 11:56 2.3.1.2.5 Will the model’s values get enough power after escape/takeover?
• 13:23 2.3.1.2.6 How much does the model stand to gain from not training-gaming?
• 16:38 2.3.1.2.7 How “ambitious” is the model?
• 21:43 2.3.1.3 Overall assessment of the classic goal-guarding story