Share
The simplest questions often have the most complex answers. The Philosopher's Zone is your guide through the strange thickets of logic, metaphysics and ethics.
…
continue reading
Manage episode 388134113 series 3402048
Content provided by Joe Carlsmith. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Joe Carlsmith or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://staging.podcastplayer.com/legal.
This is section 4.3 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. Simplicity arguments for scheming (Section 4.3 of "Scheming AIs") (00:00:00)
2. 4.3 Simplicity arguments (00:00:28)
3. 4.3.1 What is “simplicity”? (00:00:40)
4. 4.3.2 Does SGD select for simplicity? (00:04:24)
5. 4.3.3 The simplicity advantages of schemer-like goals (00:05:53)
6. 4.3.4 How big are these simplicity advantages? (00:07:57)
7. 4.3.5 Does this sort of simplicity-focused argument make plausible predictions about the sort (00:16:25)
8. 4.3.6 Overall assessment of simplicity arguments (00:18:53)
67 episodes
))
