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

Joe Carlsmith Audio

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

1. Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs") (00:00:00)

2. 2.3.1.2 Adequate future empowerment (00:00:33)

3. 2.3.1.2.1 When is the “pay off” supposed to happen? (00:01:22)

4. 2.3.1.2.2 Even if the model’s values survive this generation of training, will they survive long (00:04:20)

5. 2.3.1.2.3 Will escape/take-over be suitably likely to succeed? (00:08:16)

6. 2.3.1.2.4 Will the time horizon of the model’s goals extend to cover escape/take-over? (00:10:05)

7. 2.3.1.2.5 Will the model’s values get enough power after escape/takeover? (00:11:56)

8. 2.3.1.2.6 How much does the model stand to gain from not training-gaming? (00:13:23)

9. 2.3.1.2.7 How “ambitious” is the model? (00:16:38)

10. 2.3.1.3 Overall assessment of the classic goal-guarding story (00:21:43)