LessWrong (Curated & Popular) "Thomas Kwa's MIRI research experience" by Thomas Kwa and others
Oct 6, 2023
Thomas Kwa shares his research experience working with MIRI. They discuss concrete problems, information hazard prevention, agent reflection, deconfusion, empirical feedback, and understanding cognition.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Introduction
00:00 • 4min
Frustration with Lack of Concrete Problems
04:28 • 10min
Implementation of Information Hazard Prevention
14:20 • 2min
Agent Reflection and Research Feedback
15:59 • 6min
Deconfusion, Alignment, and Research Experience
21:43 • 14min
Importance of Empirical Feedback in Interpretability and Intelligence
36:08 • 3min
Shift in Focus: Understanding Cognition
38:50 • 13min