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

16/11/2023 22 min
Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs")

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

Episode Synopsis

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