Introduction and summary of "Scheming AIs: Will AIs fake alignment during training in order to get power?"

This is a recording of the introductory section of my report "Scheming AIs: Will AIs fake alignment during training in order to get power?".  This section includes a summary of the full report. The summary covers most of the main points and technical terminology, and I'm hoping that it will provide much of the context necessary to understand individual sections of the report on their own. (Note: the text of the report itself may not be public by the time this episode goes live.)

Chapters

• 2:21 0. Introduction
• 13:09 0.1 Preliminaries
• 16:59 0.2 Summary of the report
• 17:28 0.2.1 Summary of section 1
• 19:50 0.2.2 Summary of section 2
• 36:21 0.2.3 Summary of section 3
• 40:06 0.2.4 Summary of section 4
• 51:49 0.2.5 Summary of section 5
• 55:00 0.2.6 Summary of section 6