AI Safety Fundamentals: Alignment Embedded Agents
6 snips
May 13, 2023 Computer scientist Scott Garrabrant discusses the challenge of building learning agents for real-world goals. The podcast explores the concept of embedded agents, the four complications of embedded agency, and open problems in world models and subsystem alignment. It also delves into the conflicts that arise when spinning up sub-agents with different goals.
Chapters
Transcript
Episode notes
1 2 3 4 5
Introduction
00:00 • 2min
Embedded Agents: Challenges and Complications
01:50 • 9min
The Four Complications of Embedded Agency: Decision Theory and Embedded World Models
10:57 • 3min
Open problems in embedded world models, robust delegation, and subsystem alignment
13:28 • 2min
Spinning up Sub-Agents and the Challenge of Alignment
15:41 • 2min