Go offline with the Player FM app!
"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs")
Manage episode 386533588 series 3402048
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
1. "Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs") (00:00:00)
2. 2.2.3 “Clean” vs. “messy” goal-directedness (00:00:28)
3. 2.2.3.1 Does scheming require a higher standard of goal-directedness? (00:09:27)
64 episodes
Manage episode 386533588 series 3402048
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
1. "Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs") (00:00:00)
2. 2.2.3 “Clean” vs. “messy” goal-directedness (00:00:28)
3. 2.2.3.1 Does scheming require a higher standard of goal-directedness? (00:09:27)
64 episodes
All episodes
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.